diff options
1474 files changed, 25819 insertions, 10149 deletions
@@ -142,13 +142,17 @@ Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com> Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com> Brendan Higgins <brendan.higgins@linux.dev> <brendanhiggins@google.com> Brian Avery <b.avery@hp.com> +Brian Cain <bcain@kernel.org> <brian.cain@oss.qualcomm.com> +Brian Cain <bcain@kernel.org> <bcain@quicinc.com> Brian King <brking@us.ibm.com> Brian Silverman <bsilver16384@gmail.com> <brian.silverman@bluerivertech.com> Bryan Tan <bryan-bt.tan@broadcom.com> <bryantan@vmware.com> Cai Huoqing <cai.huoqing@linux.dev> <caihuoqing@baidu.com> Can Guo <quic_cang@quicinc.com> <cang@codeaurora.org> Carl Huang <quic_cjhuang@quicinc.com> <cjhuang@codeaurora.org> -Carlos Bilbao <carlos.bilbao.osdev@gmail.com> <carlos.bilbao@amd.com> +Carlos Bilbao <carlos.bilbao@kernel.org> <carlos.bilbao@amd.com> +Carlos Bilbao <carlos.bilbao@kernel.org> <carlos.bilbao.osdev@gmail.com> +Carlos Bilbao <carlos.bilbao@kernel.org> <bilbao@vt.edu> Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> Chao Yu <chao@kernel.org> <chao2.yu@samsung.com> @@ -165,6 +169,7 @@ Christian Brauner <brauner@kernel.org> <christian.brauner@canonical.com> Christian Brauner <brauner@kernel.org> <christian.brauner@ubuntu.com> Christian Marangi <ansuelsmth@gmail.com> Christophe Ricard <christophe.ricard@gmail.com> +Christopher Obbard <christopher.obbard@linaro.org> <chris.obbard@collabora.com> Christoph Hellwig <hch@lst.de> Chuck Lever <chuck.lever@oracle.com> <cel@kernel.org> Chuck Lever <chuck.lever@oracle.com> <cel@netapp.com> @@ -221,6 +226,7 @@ Fangrui Song <i@maskray.me> <maskray@google.com> Felipe W Damasio <felipewd@terra.com.br> Felix Kuhling <fxkuehl@gmx.de> Felix Moeller <felix@derklecks.de> +Feng Tang <feng.79.tang@gmail.com> <feng.tang@intel.com> Fenglin Wu <quic_fenglinw@quicinc.com> <fenglinw@codeaurora.org> Filipe Lautert <filipe@icewall.org> Finn Thain <fthain@linux-m68k.org> <fthain@telegraphics.com.au> @@ -261,6 +267,7 @@ Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com> Guru Das Srinagesh <quic_gurus@quicinc.com> <gurus@codeaurora.org> Gustavo Padovan <gustavo@las.ic.unicamp.br> Gustavo Padovan <padovan@profusion.mobi> +Hamza Mahfooz <hamzamahfooz@linux.microsoft.com> <hamza.mahfooz@amd.com> Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org> Hans Verkuil <hverkuil@xs4all.nl> <hansverk@cisco.com> Hans Verkuil <hverkuil@xs4all.nl> <hverkuil-cisco@xs4all.nl> @@ -311,6 +318,8 @@ Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com> Jean Tourrilhes <jt@hpl.hp.com> Jeevan Shriram <quic_jshriram@quicinc.com> <jshriram@codeaurora.org> Jeff Garzik <jgarzik@pretzel.yyz.us> +Jeff Johnson <jeff.johnson@oss.qualcomm.com> <jjohnson@codeaurora.org> +Jeff Johnson <jeff.johnson@oss.qualcomm.com> <quic_jjohnson@quicinc.com> Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net> Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com> Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> @@ -370,6 +379,7 @@ Juha Yrjola <juha.yrjola@solidboot.com> Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> Iskren Chernev <me@iskren.info> <iskren.chernev@gmail.com> Kalle Valo <kvalo@kernel.org> <kvalo@codeaurora.org> +Kalle Valo <kvalo@kernel.org> <quic_kvalo@quicinc.com> Kalyan Thota <quic_kalyant@quicinc.com> <kalyan_t@codeaurora.org> Karthikeyan Periyasamy <quic_periyasa@quicinc.com> <periyasa@codeaurora.org> Kathiravan T <quic_kathirav@quicinc.com> <kathirav@codeaurora.org> @@ -524,6 +534,7 @@ Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk> Nicholas Piggin <npiggin@gmail.com> <npiggin@suse.de> Nicholas Piggin <npiggin@gmail.com> <nickpiggin@yahoo.com.au> Nicholas Piggin <npiggin@gmail.com> <piggin@cyberone.com.au> +Nick Desaulniers <nick.desaulniers+lkml@gmail.com> <ndesaulniers@google.com> Nicolas Ferre <nicolas.ferre@microchip.com> <nicolas.ferre@atmel.com> Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org> Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org> @@ -761,6 +772,7 @@ Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn> Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com> +Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com> Yusuke Goda <goda.yusuke@renesas.com> Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com> Zhu Yanjun <zyjzyj2000@gmail.com> <yanjunz@nvidia.com> @@ -2515,11 +2515,9 @@ D: SLS distribution D: Initial implementation of VC's, pty's and select() N: Pavel Machek -E: pavel@ucw.cz +E: pavel@kernel.org P: 4096R/92DFCE96 4FA7 9EEF FCD4 C44F C585 B8C7 C060 2241 92DF CE96 -D: Softcursor for vga, hypertech cdrom support, vcsa bugfix, nbd, -D: sun4/330 port, capabilities for elf, speedup for rm on ext2, USB, -D: work on suspend-to-ram/disk, killing duplicates from ioctl32, +D: NBD, Sun4/330 port, USB, work on suspend-to-ram/disk, D: Altera SoCFPGA and Nokia N900 support. S: Czech Republic diff --git a/Documentation/ABI/stable/sysfs-class-bluetooth b/Documentation/ABI/stable/sysfs-class-bluetooth new file mode 100644 index 000000000000..36be02471174 --- /dev/null +++ b/Documentation/ABI/stable/sysfs-class-bluetooth @@ -0,0 +1,9 @@ +What: /sys/class/bluetooth/hci<index>/reset +Date: 14-Jan-2025 +KernelVersion: 6.13 +Contact: linux-bluetooth@vger.kernel.org +Description: This write-only attribute allows users to trigger the vendor reset + method on the Bluetooth device when arbitrary data is written. + The reset may or may not be done through the device transport + (e.g., UART/USB), and can also be done through an out-of-band + approach such as GPIO. diff --git a/Documentation/arch/arm64/gcs.rst b/Documentation/arch/arm64/gcs.rst index 1f65a3193e77..226c0b008456 100644 --- a/Documentation/arch/arm64/gcs.rst +++ b/Documentation/arch/arm64/gcs.rst @@ -37,7 +37,7 @@ intended to be exhaustive. shadow stacks rather than GCS. * Support for GCS is reported to userspace via HWCAP_GCS in the aux vector - AT_HWCAP2 entry. + AT_HWCAP entry. * GCS is enabled per thread. While there is support for disabling GCS at runtime this should be done with great care. diff --git a/Documentation/arch/riscv/hwprobe.rst b/Documentation/arch/riscv/hwprobe.rst index 955fbcd19ce9..f273ea15a8e8 100644 --- a/Documentation/arch/riscv/hwprobe.rst +++ b/Documentation/arch/riscv/hwprobe.rst @@ -293,3 +293,13 @@ The following keys are defined: * :c:macro:`RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED`: Misaligned vector accesses are not supported at all and will generate a misaligned address fault. + +* :c:macro:`RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0`: A bitmask containing the + thead vendor extensions that are compatible with the + :c:macro:`RISCV_HWPROBE_BASE_BEHAVIOR_IMA`: base system behavior. + + * T-HEAD + + * :c:macro:`RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR`: The xtheadvector vendor + extension is supported in the T-Head ISA extensions spec starting from + commit a18c801634 ("Add T-Head VECTOR vendor extension. "). diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst index 51665a3e6a50..1e0e7358e14a 100644 --- a/Documentation/block/ublk.rst +++ b/Documentation/block/ublk.rst @@ -333,6 +333,4 @@ References .. [#userspace_readme] https://github.com/ming1/ubdsrv/blob/master/README -.. [#stefan] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/ - .. [#xiaoguang] https://lore.kernel.org/linux-block/YoOr6jBfgVm8GvWg@stefanha-x1.localdomain/ diff --git a/Documentation/devicetree/bindings/arm/fsl.yaml b/Documentation/devicetree/bindings/arm/fsl.yaml index 371317554863..0db2cbd7891f 100644 --- a/Documentation/devicetree/bindings/arm/fsl.yaml +++ b/Documentation/devicetree/bindings/arm/fsl.yaml @@ -1091,6 +1091,7 @@ properties: - dmo,imx8mp-data-modul-edm-sbc # i.MX8MP eDM SBC - emcraft,imx8mp-navqp # i.MX8MP Emcraft Systems NavQ+ Kit - fsl,imx8mp-evk # i.MX8MP EVK Board + - fsl,imx8mp-evk-revb4 # i.MX8MP EVK Rev B4 Board - gateworks,imx8mp-gw71xx-2x # i.MX8MP Gateworks Board - gateworks,imx8mp-gw72xx-2x # i.MX8MP Gateworks Board - gateworks,imx8mp-gw73xx-2x # i.MX8MP Gateworks Board @@ -1271,6 +1272,7 @@ properties: items: - enum: - fsl,imx8qm-mek # i.MX8QM MEK Board + - fsl,imx8qm-mek-revd # i.MX8QM MEK Rev D Board - toradex,apalis-imx8 # Apalis iMX8 Modules - toradex,apalis-imx8-v1.1 # Apalis iMX8 V1.1 Modules - const: fsl,imx8qm @@ -1299,6 +1301,7 @@ properties: - enum: - einfochips,imx8qxp-ai_ml # i.MX8QXP AI_ML Board - fsl,imx8qxp-mek # i.MX8QXP MEK Board + - fsl,imx8qxp-mek-wcpu # i.MX8QXP MEK WCPU Board - const: fsl,imx8qxp - description: i.MX8DXL based Boards diff --git a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml index 0858fd635282..4cdff6161bf0 100644 --- a/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,gpucc.yaml @@ -8,6 +8,7 @@ title: Qualcomm Graphics Clock & Reset Controller maintainers: - Taniya Das <quic_tdas@quicinc.com> + - Imran Shaik <quic_imrashai@quicinc.com> description: | Qualcomm graphics clock control module provides the clocks, resets and power @@ -23,10 +24,12 @@ description: | include/dt-bindings/clock/qcom,gpucc-sm8150.h include/dt-bindings/clock/qcom,gpucc-sm8250.h include/dt-bindings/clock/qcom,gpucc-sm8350.h + include/dt-bindings/clock/qcom,qcs8300-gpucc.h properties: compatible: enum: + - qcom,qcs8300-gpucc - qcom,sdm845-gpucc - qcom,sa8775p-gpucc - qcom,sc7180-gpucc diff --git a/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml b/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml index 36a60d8f5ae3..81623f59d11d 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sa8775p-camcc.yaml @@ -8,16 +8,20 @@ title: Qualcomm Camera Clock & Reset Controller on SA8775P maintainers: - Taniya Das <quic_tdas@quicinc.com> + - Imran Shaik <quic_imrashai@quicinc.com> description: | Qualcomm camera clock control module provides the clocks, resets and power domains on SA8775p. - See also: include/dt-bindings/clock/qcom,sa8775p-camcc.h + See also: + include/dt-bindings/clock/qcom,qcs8300-camcc.h + include/dt-bindings/clock/qcom,sa8775p-camcc.h properties: compatible: enum: + - qcom,qcs8300-camcc - qcom,sa8775p-camcc clocks: diff --git a/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml b/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml index 928131bff4c1..07e5d811d816 100644 --- a/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml +++ b/Documentation/devicetree/bindings/clock/qcom,sa8775p-videocc.yaml @@ -18,6 +18,7 @@ description: | properties: compatible: enum: + - qcom,qcs8300-videocc - qcom,sa8775p-videocc clocks: diff --git a/Documentation/devicetree/bindings/display/panel/powertip,hx8238a.yaml b/Documentation/devicetree/bindings/display/panel/powertip,hx8238a.yaml new file mode 100644 index 000000000000..b7d74faeb5d5 --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/powertip,hx8238a.yaml @@ -0,0 +1,29 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/powertip,hx8238a.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Powertip Electronic Technology Co. 320 x 240 LCD panel + +maintainers: + - Lukasz Majewski <lukma@denx.de> + +allOf: + - $ref: panel-dpi.yaml# + +properties: + compatible: + items: + - const: powertip,hx8238a + - {} # panel-dpi, but not listed here to avoid false select + + height-mm: true + panel-timing: true + port: true + power-supply: true + width-mm: true + +additionalProperties: false + +... diff --git a/Documentation/devicetree/bindings/display/panel/powertip,st7272.yaml b/Documentation/devicetree/bindings/display/panel/powertip,st7272.yaml new file mode 100644 index 000000000000..f3622800f13f --- /dev/null +++ b/Documentation/devicetree/bindings/display/panel/powertip,st7272.yaml @@ -0,0 +1,29 @@ +# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/display/panel/powertip,st7272.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Powertip Electronic Technology Co. 320 x 240 LCD panel + +maintainers: + - Lukasz Majewski <lukma@denx.de> + +allOf: + - $ref: panel-dpi.yaml# + +properties: + compatible: + items: + - const: powertip,st7272 + - {} # panel-dpi, but not listed here to avoid false select + + height-mm: true + panel-timing: true + port: true + power-supply: true + width-mm: true + +additionalProperties: false + +... diff --git a/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml b/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml index 55e3e490d0e6..31c4ffcb599c 100644 --- a/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml +++ b/Documentation/devicetree/bindings/display/ti/ti,am65x-dss.yaml @@ -23,7 +23,7 @@ properties: compatible: enum: - ti,am625-dss - - ti,am62a7,dss + - ti,am62a7-dss - ti,am65x-dss reg: diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt b/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt deleted file mode 100644 index cd17684aaab5..000000000000 --- a/Documentation/devicetree/bindings/dma/adi,axi-dmac.txt +++ /dev/null @@ -1,61 +0,0 @@ -Analog Devices AXI-DMAC DMA controller - -Required properties: - - compatible: Must be "adi,axi-dmac-1.00.a". - - reg: Specification for the controllers memory mapped register map. - - interrupts: Specification for the controllers interrupt. - - clocks: Phandle and specifier to the controllers AXI interface clock - - #dma-cells: Must be 1. - -Required sub-nodes: - - adi,channels: This sub-node must contain a sub-node for each DMA channel. For - the channel sub-nodes the following bindings apply. They must match the - configuration options of the peripheral as it was instantiated. - -Required properties for adi,channels sub-node: - - #size-cells: Must be 0 - - #address-cells: Must be 1 - -Required channel sub-node properties: - - reg: Which channel this node refers to. - - adi,source-bus-width, - adi,destination-bus-width: Width of the source or destination bus in bits. - - adi,source-bus-type, - adi,destination-bus-type: Type of the source or destination bus. Must be one - of the following: - 0 (AXI_DMAC_TYPE_AXI_MM): Memory mapped AXI interface - 1 (AXI_DMAC_TYPE_AXI_STREAM): Streaming AXI interface - 2 (AXI_DMAC_TYPE_AXI_FIFO): FIFO interface - -Deprecated optional channel properties: - - adi,length-width: Width of the DMA transfer length register. - - adi,cyclic: Must be set if the channel supports hardware cyclic DMA - transfers. - - adi,2d: Must be set if the channel supports hardware 2D DMA transfers. - -DMA clients connected to the AXI-DMAC DMA controller must use the format -described in the dma.txt file using a one-cell specifier. The value of the -specifier refers to the DMA channel index. - -Example: - -dma: dma@7c420000 { - compatible = "adi,axi-dmac-1.00.a"; - reg = <0x7c420000 0x10000>; - interrupts = <0 57 0>; - clocks = <&clkc 16>; - #dma-cells = <1>; - - adi,channels { - #size-cells = <0>; - #address-cells = <1>; - - dma-channel@0 { - reg = <0>; - adi,source-bus-width = <32>; - adi,source-bus-type = <ADI_AXI_DMAC_TYPE_MM_AXI>; - adi,destination-bus-width = <64>; - adi,destination-bus-type = <ADI_AXI_DMAC_TYPE_FIFO>; - }; - }; -}; diff --git a/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml b/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml new file mode 100644 index 000000000000..63b6fb0423c2 --- /dev/null +++ b/Documentation/devicetree/bindings/dma/adi,axi-dmac.yaml @@ -0,0 +1,129 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/dma/adi,axi-dmac.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Analog Devices AXI-DMAC DMA controller + +description: | + FPGA-based DMA controller designed for use with high-speed converter hardware. + + http://analogdevicesinc.github.io/hdl/library/axi_dmac/index.html + +maintainers: + - Nuno Sa <nuno.sa@analog.com> + +additionalProperties: false + +properties: + compatible: + const: adi,axi-dmac-1.00.a + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + "#dma-cells": + const: 1 + + adi,channels: + deprecated: true + type: object + description: + This sub-node must contain a sub-node for each DMA channel. This node is + only required for IP versions older than 4.3.a and should otherwise be + omitted. + additionalProperties: false + + properties: + "#size-cells": + const: 0 + "#address-cells": + const: 1 + + patternProperties: + "^dma-channel@[0-9a-f]+$": + type: object + description: + DMA channel properties based on HDL compile-time configuration. + additionalProperties: false + + properties: + reg: + maxItems: 1 + + adi,source-bus-width: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Width of the source bus in bits. + enum: [8, 16, 32, 64, 128] + + adi,destination-bus-width: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Width of the destination bus in bits. + enum: [8, 16, 32, 64, 128] + + adi,source-bus-type: + $ref: /schemas/types.yaml#/definitions/uint32 + description: | + Type of the source bus. + + 0: Memory mapped AXI interface + 1: Streaming AXI interface + 2: FIFO interface + enum: [0, 1, 2] + + adi,destination-bus-type: + $ref: /schemas/types.yaml#/definitions/uint32 + description: Type of the destination bus (see adi,source-bus-type). + enum: [0, 1, 2] + + adi,length-width: + deprecated: true + $ref: /schemas/types.yaml#/definitions/uint32 + description: Width of the DMA transfer length register. + + adi,cyclic: + deprecated: true + type: boolean + description: + Must be set if the channel supports hardware cyclic DMA transfers. + + adi,2d: + deprecated: true + type: boolean + description: + Must be set if the channel supports hardware 2D DMA transfers. + + required: + - reg + - adi,source-bus-width + - adi,destination-bus-width + - adi,source-bus-type + - adi,destination-bus-type + + required: + - "#size-cells" + - "#address-cells" + +required: + - compatible + - reg + - interrupts + - clocks + - "#dma-cells" + +examples: + - | + dma-controller@7c420000 { + compatible = "adi,axi-dmac-1.00.a"; + reg = <0x7c420000 0x10000>; + interrupts = <0 57 0>; + clocks = <&clkc 16>; + #dma-cells = <1>; + }; diff --git a/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml b/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml index 02d5bd035409..9b5180c0a7c4 100644 --- a/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml +++ b/Documentation/devicetree/bindings/dma/allwinner,sun4i-a10-dma.yaml @@ -22,7 +22,9 @@ properties: number. compatible: - const: allwinner,sun4i-a10-dma + enum: + - allwinner,sun4i-a10-dma + - allwinner,suniv-f1c100s-dma reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml b/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml new file mode 100644 index 000000000000..9ca1c5d1f00f --- /dev/null +++ b/Documentation/devicetree/bindings/dma/atmel,sama5d4-dma.yaml @@ -0,0 +1,79 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/dma/atmel,sama5d4-dma.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microchip AT91 Extensible Direct Memory Access Controller + +maintainers: + - Nicolas Ferre <nicolas.ferre@microchip.com> + - Charan Pedumuru <charan.pedumuru@microchip.com> + +description: + The DMA Controller (XDMAC) is a AHB-protocol central direct memory access + controller. It performs peripheral data transfer and memory move operations + over one or two bus ports through the unidirectional communication + channel. Each channel is fully programmable and provides both peripheral + or memory-to-memory transfers. The channel features are configurable at + implementation. + +allOf: + - $ref: dma-controller.yaml# + +properties: + compatible: + oneOf: + - enum: + - atmel,sama5d4-dma + - microchip,sama7g5-dma + - items: + - enum: + - microchip,sam9x60-dma + - microchip,sam9x7-dma + - const: atmel,sama5d4-dma + + "#dma-cells": + description: | + Represents the number of integer cells in the `dmas` property of client + devices. The single cell specifies the channel configuration register: + - bit 13: SIF (Source Interface Identifier) for memory interface. + - bit 14: DIF (Destination Interface Identifier) for peripheral interface. + - bit 30-24: PERID (Peripheral Identifier). + const: 1 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + const: dma_clk + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - "#dma-cells" + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/clock/at91.h> + #include <dt-bindings/dma/at91.h> + #include <dt-bindings/interrupt-controller/irq.h> + dma-controller@f0008000 { + compatible = "atmel,sama5d4-dma"; + reg = <0xf0008000 0x1000>; + interrupts = <20 IRQ_TYPE_LEVEL_HIGH 0>; + #dma-cells = <1>; + clocks = <&pmc PMC_TYPE_PERIPHERAL 20>; + clock-names = "dma_clk"; + }; diff --git a/Documentation/devicetree/bindings/dma/atmel-xdma.txt b/Documentation/devicetree/bindings/dma/atmel-xdma.txt deleted file mode 100644 index 76d649b3a25d..000000000000 --- a/Documentation/devicetree/bindings/dma/atmel-xdma.txt +++ /dev/null @@ -1,54 +0,0 @@ -* Atmel Extensible Direct Memory Access Controller (XDMAC) - -* XDMA Controller -Required properties: -- compatible: Should be "atmel,sama5d4-dma", "microchip,sam9x60-dma" or - "microchip,sama7g5-dma" or - "microchip,sam9x7-dma", "atmel,sama5d4-dma". -- reg: Should contain DMA registers location and length. -- interrupts: Should contain DMA interrupt. -- #dma-cells: Must be <1>, used to represent the number of integer cells in -the dmas property of client devices. - - The 1st cell specifies the channel configuration register: - - bit 13: SIF, source interface identifier, used to get the memory - interface identifier, - - bit 14: DIF, destination interface identifier, used to get the peripheral - interface identifier, - - bit 30-24: PERID, peripheral identifier. - -Example: - -dma1: dma-controller@f0004000 { - compatible = "atmel,sama5d4-dma"; - reg = <0xf0004000 0x200>; - interrupts = <50 4 0>; - #dma-cells = <1>; -}; - - -* DMA clients -DMA clients connected to the Atmel XDMA controller must use the format -described in the dma.txt file, using a one-cell specifier for each channel. -The two cells in order are: -1. A phandle pointing to the DMA controller. -2. Channel configuration register. Configurable fields are: - - bit 13: SIF, source interface identifier, used to get the memory - interface identifier, - - bit 14: DIF, destination interface identifier, used to get the peripheral - interface identifier, - - bit 30-24: PERID, peripheral identifier. - -Example: - -i2c2: i2c@f8024000 { - compatible = "atmel,at91sam9x5-i2c"; - reg = <0xf8024000 0x4000>; - interrupts = <34 4 6>; - dmas = <&dma1 - (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) - | AT91_XDMAC_DT_PERID(6))>, - <&dma1 - (AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) - | AT91_XDMAC_DT_PERID(7))>; - dma-names = "tx", "rx"; -}; diff --git a/Documentation/devicetree/bindings/dma/fsl,edma.yaml b/Documentation/devicetree/bindings/dma/fsl,edma.yaml index d54140f18d34..4f925469533e 100644 --- a/Documentation/devicetree/bindings/dma/fsl,edma.yaml +++ b/Documentation/devicetree/bindings/dma/fsl,edma.yaml @@ -26,9 +26,13 @@ properties: - fsl,imx93-edma3 - fsl,imx93-edma4 - fsl,imx95-edma5 + - nxp,s32g2-edma - items: - const: fsl,ls1028a-edma - const: fsl,vf610-edma + - items: + - const: nxp,s32g3-edma + - const: nxp,s32g2-edma reg: minItems: 1 @@ -221,6 +225,36 @@ allOf: properties: power-domains: false + - if: + properties: + compatible: + contains: + const: nxp,s32g2-edma + then: + properties: + clocks: + minItems: 2 + maxItems: 2 + clock-names: + items: + - const: dmamux0 + - const: dmamux1 + interrupts: + minItems: 3 + maxItems: 3 + interrupt-names: + items: + - const: tx-0-15 + - const: tx-16-31 + - const: err + reg: + minItems: 3 + maxItems: 3 + "#dma-cells": + const: 2 + dma-channels: + const: 32 + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml index 877147e95ecc..d3f8c269916c 100644 --- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml +++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.yaml @@ -13,9 +13,6 @@ description: | maintainers: - Jon Hunter <jonathanh@nvidia.com> -allOf: - - $ref: dma-controller.yaml# - properties: compatible: oneOf: @@ -29,7 +26,19 @@ properties: - const: nvidia,tegra186-adma reg: - maxItems: 1 + description: + The 'page' region describes the address space of the page + used for accessing the DMA channel registers. The 'global' + region describes the address space of the global DMA registers. + In the absence of the 'reg-names' property, there must be a + single entry that covers the address space of the global DMA + registers and the DMA channel registers. + minItems: 1 + maxItems: 2 + + reg-names: + minItems: 1 + maxItems: 2 interrupts: description: | @@ -63,6 +72,49 @@ required: - clocks - clock-names +allOf: + - $ref: dma-controller.yaml# + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra210-adma + then: + properties: + reg: + items: + - description: Full address space range of DMA registers. + + - if: + properties: + compatible: + contains: + enum: + - nvidia,tegra186-adma + then: + anyOf: + - properties: + reg: + items: + - description: Full address space range of DMA registers. + - properties: + reg: + items: + - description: Channel Page address space range of DMA registers. + reg-names: + items: + - const: page + - properties: + reg: + items: + - description: Channel Page address space range of DMA registers. + - description: Global Page address space range of DMA registers. + reg-names: + items: + - const: page + - const: global + additionalProperties: false examples: diff --git a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml index 4ad56a409b9c..7052468b15c8 100644 --- a/Documentation/devicetree/bindings/dma/qcom,gpi.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,gpi.yaml @@ -25,7 +25,9 @@ properties: - items: - enum: - qcom,qcm2290-gpi-dma + - qcom,qcs8300-gpi-dma - qcom,qdu1000-gpi-dma + - qcom,sa8775p-gpi-dma - qcom,sar2130p-gpi-dma - qcom,sc7280-gpi-dma - qcom,sdx75-gpi-dma @@ -35,10 +37,12 @@ properties: - qcom,sm8450-gpi-dma - qcom,sm8550-gpi-dma - qcom,sm8650-gpi-dma + - qcom,sm8750-gpi-dma - qcom,x1e80100-gpi-dma - const: qcom,sm6350-gpi-dma - items: - enum: + - qcom,qcs615-gpi-dma - qcom,sdm670-gpi-dma - qcom,sm6125-gpi-dma - qcom,sm8150-gpi-dma diff --git a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml index f26c914a3a9a..b7bca1a83769 100644 --- a/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml +++ b/Documentation/devicetree/bindings/dma/stm32/st,stm32-dmamux.yaml @@ -15,6 +15,16 @@ allOf: properties: "#dma-cells": const: 3 + description: | + Each cell represents the following: + 1. The mux input number/line for the request + 2. Bitfield representing DMA channel configuration that is passed + to the real DMA controller + 3. Bitfield representing device dependent DMA features passed to + the real DMA controller + + For bitfield definitions of cells 2 and 3, see the associated + bindings doc for the actual DMA controller in st,stm32-dma.yaml. compatible: const: st,stm32h7-dmamux diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml index 27b8e1636560..b5bc842c5a0e 100644 --- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml +++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml @@ -34,6 +34,7 @@ properties: - ti,am62a-dmss-bcdma-csirx - ti,am64-dmss-bcdma - ti,j721s2-dmss-bcdma-csi + - ti,j722s-dmss-bcdma-csi reg: minItems: 3 @@ -196,7 +197,9 @@ allOf: properties: compatible: contains: - const: ti,j721s2-dmss-bcdma-csi + enum: + - ti,j721s2-dmss-bcdma-csi + - ti,j722s-dmss-bcdma-csi then: properties: ti,sci-rm-range-bchan: false diff --git a/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml b/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml index b2adc7174177..dca16e202da9 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/microchip,lan966x-oic.yaml @@ -14,9 +14,8 @@ allOf: description: | The Microchip LAN966x outband interrupt controller (OIC) maps the internal - interrupt sources of the LAN966x device to an external interrupt. - When the LAN966x device is used as a PCI device, the external interrupt is - routed to the PCI interrupt. + interrupt sources of the LAN966x device to a PCI interrupt when the LAN966x + device is used as a PCI device. properties: compatible: diff --git a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml index f117471fb06f..e7ee0d9efed8 100644 --- a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml @@ -22,12 +22,12 @@ properties: oneOf: - items: - enum: - - qcom,qcs8300-ethqos - - const: qcom,sa8775p-ethqos + - qcom,qcs615-ethqos + - const: qcom,qcs404-ethqos - items: - enum: - - qcom,qcs615-ethqos - - const: qcom,sm8150-ethqos + - qcom,qcs8300-ethqos + - const: qcom,sa8775p-ethqos - enum: - qcom,qcs404-ethqos - qcom,sa8775p-ethqos diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml index 070c4c9b8643..aace072e2d52 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml @@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies ath10k wireless devices maintainers: - - Kalle Valo <kvalo@kernel.org> - Jeff Johnson <jjohnson@kernel.org> description: diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml index a71fdf05bc1e..a4425cf196ab 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml @@ -8,7 +8,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies ath11k wireless devices (PCIe) maintainers: - - Kalle Valo <kvalo@kernel.org> - Jeff Johnson <jjohnson@kernel.org> description: | diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml index ff5763dc66a8..a69ffb7b3cb8 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml @@ -8,7 +8,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Qualcomm Technologies ath11k wireless devices maintainers: - - Kalle Valo <kvalo@kernel.org> - Jeff Johnson <jjohnson@kernel.org> description: | diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml index cbfb559f6b69..318f305405e3 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml @@ -9,7 +9,6 @@ title: Qualcomm Technologies ath12k wireless devices (PCIe) with WSI interface maintainers: - Jeff Johnson <jjohnson@kernel.org> - - Kalle Valo <kvalo@kernel.org> description: | Qualcomm Technologies IEEE 802.11be PCIe devices with WSI interface. diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml index 1b5884015b15..9e557cb838c7 100644 --- a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml +++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k.yaml @@ -9,7 +9,6 @@ title: Qualcomm Technologies ath12k wireless devices (PCIe) maintainers: - Jeff Johnson <quic_jjohnson@quicinc.com> - - Kalle Valo <kvalo@kernel.org> description: Qualcomm Technologies IEEE 802.11be PCIe devices. diff --git a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml index d37f544ab8aa..39c209249c9c 100644 --- a/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml +++ b/Documentation/devicetree/bindings/nvmem/qcom,qfprom.yaml @@ -36,6 +36,7 @@ properties: - qcom,qcs404-qfprom - qcom,qcs615-qfprom - qcom,qcs8300-qfprom + - qcom,sar2130p-qfprom - qcom,sc7180-qfprom - qcom,sc7280-qfprom - qcom,sc8280xp-qfprom diff --git a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml index d3cd7997879f..1b3de6678c08 100644 --- a/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml +++ b/Documentation/devicetree/bindings/phy/phy-rockchip-naneng-combphy.yaml @@ -13,6 +13,7 @@ properties: compatible: enum: - rockchip,rk3568-naneng-combphy + - rockchip,rk3576-naneng-combphy - rockchip,rk3588-naneng-combphy reg: diff --git a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml index 58ce2d91d28c..f60804687412 100644 --- a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml @@ -15,12 +15,21 @@ description: properties: compatible: - enum: - - qcom,ipq6018-qmp-pcie-phy - - qcom,ipq8074-qmp-gen3-pcie-phy - - qcom,ipq8074-qmp-pcie-phy - - qcom,ipq9574-qmp-gen3x1-pcie-phy - - qcom,ipq9574-qmp-gen3x2-pcie-phy + oneOf: + - enum: + - qcom,ipq6018-qmp-pcie-phy + - qcom,ipq8074-qmp-gen3-pcie-phy + - qcom,ipq8074-qmp-pcie-phy + - qcom,ipq9574-qmp-gen3x1-pcie-phy + - qcom,ipq9574-qmp-gen3x2-pcie-phy + - items: + - enum: + - qcom,ipq5424-qmp-gen3x1-pcie-phy + - const: qcom,ipq9574-qmp-gen3x1-pcie-phy + - items: + - enum: + - qcom,ipq5424-qmp-gen3x2-pcie-phy + - const: qcom,ipq9574-qmp-gen3x2-pcie-phy reg: items: diff --git a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml index 4aed4b5d65ec..39851ba9de43 100644 --- a/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,qusb2-phy.yaml @@ -18,6 +18,7 @@ properties: oneOf: - items: - enum: + - qcom,ipq5424-qusb2-phy - qcom,ipq6018-qusb2-phy - qcom,ipq8074-qusb2-phy - qcom,ipq9574-qusb2-phy 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 13fdf5f1beba..89391649e0b5 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -16,8 +16,10 @@ description: properties: compatible: enum: + - qcom,qcs615-qmp-gen3x1-pcie-phy - qcom,sa8775p-qmp-gen4x2-pcie-phy - qcom,sa8775p-qmp-gen4x4-pcie-phy + - qcom,sar2130p-qmp-gen3x2-pcie-phy - qcom,sc8180x-qmp-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy @@ -32,6 +34,7 @@ properties: - qcom,sm8250-qmp-gen3x2-pcie-phy - qcom,sm8250-qmp-modem-pcie-phy - qcom,sm8350-qmp-gen3x1-pcie-phy + - qcom,sm8350-qmp-gen3x2-pcie-phy - qcom,sm8450-qmp-gen3x1-pcie-phy - qcom,sm8450-qmp-gen4x2-pcie-phy - qcom,sm8550-qmp-gen3x2-pcie-phy @@ -139,6 +142,7 @@ allOf: compatible: contains: enum: + - qcom,sar2130p-qmp-gen3x2-pcie-phy - qcom,sc8180x-qmp-pcie-phy - qcom,sdm845-qhp-pcie-phy - qcom,sdm845-qmp-pcie-phy @@ -149,6 +153,7 @@ allOf: - qcom,sm8250-qmp-gen3x2-pcie-phy - qcom,sm8250-qmp-modem-pcie-phy - qcom,sm8350-qmp-gen3x1-pcie-phy + - qcom,sm8350-qmp-gen3x2-pcie-phy - qcom,sm8450-qmp-gen3x1-pcie-phy - qcom,sm8450-qmp-gen3x2-pcie-phy - qcom,sm8550-qmp-gen3x2-pcie-phy @@ -167,6 +172,7 @@ allOf: compatible: contains: enum: + - qcom,qcs615-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy - qcom,sc8280xp-qmp-gen3x4-pcie-phy diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml index baf5134ea3d8..a1b55168e050 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml @@ -16,6 +16,7 @@ description: properties: compatible: enum: + - qcom,ipq5424-qmp-usb3-phy - qcom,ipq6018-qmp-usb3-phy - qcom,ipq8074-qmp-usb3-phy - qcom,ipq9574-qmp-usb3-phy @@ -89,6 +90,7 @@ allOf: compatible: contains: enum: + - qcom,ipq5424-qmp-usb3-phy - qcom,ipq6018-qmp-usb3-phy - qcom,ipq8074-qmp-usb3-phy - qcom,ipq9574-qmp-usb3-phy diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml index 2d0d7e9e6431..358a6736a951 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb43dp-phy.yaml @@ -16,6 +16,7 @@ description: properties: compatible: enum: + - qcom,sar2130p-qmp-usb3-dp-phy - qcom,sc7180-qmp-usb3-dp-phy - qcom,sc7280-qmp-usb3-dp-phy - qcom,sc8180x-qmp-usb3-dp-phy @@ -127,6 +128,7 @@ allOf: properties: compatible: enum: + - qcom,sar2130p-qmp-usb3-dp-phy - qcom,sc8280xp-qmp-usb43dp-phy - qcom,sm6350-qmp-usb3-dp-phy - qcom,sm8550-qmp-usb3-dp-phy diff --git a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml index f2fd2df68a9e..b7241ce975b9 100644 --- a/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/qcom,smd-rpm-regulator.yaml @@ -22,7 +22,7 @@ description: Each sub-node is identified using the node's name, with valid values listed for each of the pmics below. - For mp5496, s1, s2 + For mp5496, s1, s2, l2, l5 For pm2250, s1, s2, s3, s4, l1, l2, l3, l4, l5, l6, l7, l8, l9, l10, l11, l12, l13, l14, l15, l16, l17, l18, l19, l20, l21, l22 diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index acb5b9ba6f04..2c72f148a74b 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -26,6 +26,18 @@ description: | allOf: - $ref: /schemas/cpu.yaml# - $ref: extensions.yaml + - if: + not: + properties: + compatible: + contains: + enum: + - thead,c906 + - thead,c910 + - thead,c920 + then: + properties: + thead,vlenb: false properties: compatible: @@ -96,6 +108,13 @@ properties: description: The blocksize in bytes for the Zicboz cache operations. + thead,vlenb: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + VLEN/8, the vector register length in bytes. This property is required on + thead systems where the vector register length is not identical on all harts, or + the vlenb CSR is not available. + # RISC-V has multiple properties for cache op block sizes as the sizes # differ between individual CBO extensions cache-op-block-size: false diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml index 9c7dd7e75e0c..a63b994e0763 100644 --- a/Documentation/devicetree/bindings/riscv/extensions.yaml +++ b/Documentation/devicetree/bindings/riscv/extensions.yaml @@ -621,6 +621,10 @@ properties: latency, as ratified in commit 56ed795 ("Update riscv-crypto-spec-vector.adoc") of riscv-crypto. + # vendor extensions, each extension sorted alphanumerically under the + # vendor they belong to. Vendors are sorted alphanumerically as well. + + # Andes - const: xandespmu description: The Andes Technology performance monitor extension for counter overflow @@ -628,6 +632,12 @@ properties: Registers in the AX45MP datasheet. https://www.andestech.com/wp-content/uploads/AX45MP-1C-Rev.-5.0.0-Datasheet.pdf + # T-HEAD + - const: xtheadvector + description: + The T-HEAD specific 0.7.1 vector implementation as written in + https://github.com/T-head-Semi/thead-extension-spec/blob/95358cb2cca9489361c61d335e03d3134b14133f/xtheadvector.adoc. + allOf: # Zcb depends on Zca - if: diff --git a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml index a14b52178c4b..2599b847f406 100644 --- a/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml +++ b/Documentation/devicetree/bindings/rtc/rtc-mxc.yaml @@ -14,9 +14,13 @@ maintainers: properties: compatible: - enum: - - fsl,imx1-rtc - - fsl,imx21-rtc + oneOf: + - const: fsl,imx1-rtc + - const: fsl,imx21-rtc + - items: + - enum: + - fsl,imx31-rtc + - const: fsl,imx21-rtc reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml b/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml index 5aa00617291c..1f0e6787a746 100644 --- a/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml +++ b/Documentation/devicetree/bindings/sound/ti,pcm1681.yaml @@ -4,7 +4,7 @@ $id: http://devicetree.org/schemas/sound/ti,pcm1681.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Texas Instruments PCM1681 8-channel PWM Processor +title: Texas Instruments PCM1681 8-channel Digital-to-Analog Converter maintainers: - Shenghao Ding <shenghao-ding@ti.com> diff --git a/Documentation/driver-api/infrastructure.rst b/Documentation/driver-api/infrastructure.rst index 3d52dfdfa9fd..35e36fee4238 100644 --- a/Documentation/driver-api/infrastructure.rst +++ b/Documentation/driver-api/infrastructure.rst @@ -41,6 +41,12 @@ Device Drivers Base .. kernel-doc:: drivers/base/class.c :export: +.. kernel-doc:: include/linux/device/faux.h + :internal: + +.. kernel-doc:: drivers/base/faux.c + :export: + .. kernel-doc:: drivers/base/node.c :internal: diff --git a/Documentation/filesystems/bcachefs/SubmittingPatches.rst b/Documentation/filesystems/bcachefs/SubmittingPatches.rst new file mode 100644 index 000000000000..026b12ae0d6a --- /dev/null +++ b/Documentation/filesystems/bcachefs/SubmittingPatches.rst @@ -0,0 +1,98 @@ +Submitting patches to bcachefs: +=============================== + +Patches must be tested before being submitted, either with the xfstests suite +[0], or the full bcachefs test suite in ktest [1], depending on what's being +touched. Note that ktest wraps xfstests and will be an easier method to running +it for most users; it includes single-command wrappers for all the mainstream +in-kernel local filesystems. + +Patches will undergo more testing after being merged (including +lockdep/kasan/preempt/etc. variants), these are not generally required to be +run by the submitter - but do put some thought into what you're changing and +which tests might be relevant, e.g. are you dealing with tricky memory layout +work? kasan, are you doing locking work? then lockdep; and ktest includes +single-command variants for the debug build types you'll most likely need. + +The exception to this rule is incomplete WIP/RFC patches: if you're working on +something nontrivial, it's encouraged to send out a WIP patch to let people +know what you're doing and make sure you're on the right track. Just make sure +it includes a brief note as to what's done and what's incomplete, to avoid +confusion. + +Rigorous checkpatch.pl adherence is not required (many of its warnings are +considered out of date), but try not to deviate too much without reason. + +Focus on writing code that reads well and is organized well; code should be +aesthetically pleasing. + +CI: +=== + +Instead of running your tests locally, when running the full test suite it's +prefereable to let a server farm do it in parallel, and then have the results +in a nice test dashboard (which can tell you which failures are new, and +presents results in a git log view, avoiding the need for most bisecting). + +That exists [2], and community members may request an account. If you work for +a big tech company, you'll need to help out with server costs to get access - +but the CI is not restricted to running bcachefs tests: it runs any ktest test +(which generally makes it easy to wrap other tests that can run in qemu). + +Other things to think about: +============================ + +- How will we debug this code? Is there sufficient introspection to diagnose + when something starts acting wonky on a user machine? + + We don't necessarily need every single field of every data structure visible + with introspection, but having the important fields of all the core data + types wired up makes debugging drastically easier - a bit of thoughtful + foresight greatly reduces the need to have people build custom kernels with + debug patches. + + More broadly, think about all the debug tooling that might be needed. + +- Does it make the codebase more or less of a mess? Can we also try to do some + organizing, too? + +- Do new tests need to be written? New assertions? How do we know and verify + that the code is correct, and what happens if something goes wrong? + + We don't yet have automated code coverage analysis or easy fault injection - + but for now, pretend we did and ask what they might tell us. + + Assertions are hugely important, given that we don't yet have a systems + language that can do ergonomic embedded correctness proofs. Hitting an assert + in testing is much better than wandering off into undefined behaviour la-la + land - use them. Use them judiciously, and not as a replacement for proper + error handling, but use them. + +- Does it need to be performance tested? Should we add new peformance counters? + + bcachefs has a set of persistent runtime counters which can be viewed with + the 'bcachefs fs top' command; this should give users a basic idea of what + their filesystem is currently doing. If you're doing a new feature or looking + at old code, think if anything should be added. + +- If it's a new on disk format feature - have upgrades and downgrades been + tested? (Automated tests exists but aren't in the CI, due to the hassle of + disk image management; coordinate to have them run.) + +Mailing list, IRC: +================== + +Patches should hit the list [3], but much discussion and code review happens on +IRC as well [4]; many people appreciate the more conversational approach and +quicker feedback. + +Additionally, we have a lively user community doing excellent QA work, which +exists primarily on IRC. Please make use of that resource; user feedback is +important for any nontrivial feature, and documenting it in commit messages +would be a good idea. + +[0]: git://git.kernel.org/pub/scm/fs/xfs/xfstests-dev.git +[1]: https://evilpiepirate.org/git/ktest.git/ +[2]: https://evilpiepirate.org/~testdashboard/ci/ +[3]: linux-bcachefs@vger.kernel.org +[4]: irc.oftc.net#bcache, #bcachefs-dev diff --git a/Documentation/filesystems/bcachefs/index.rst b/Documentation/filesystems/bcachefs/index.rst index 95fc4b90739e..7db4d7ceab58 100644 --- a/Documentation/filesystems/bcachefs/index.rst +++ b/Documentation/filesystems/bcachefs/index.rst @@ -9,4 +9,5 @@ bcachefs Documentation :numbered: CodingStyle + SubmittingPatches errorcodes diff --git a/Documentation/filesystems/fuse-io-uring.rst b/Documentation/filesystems/fuse-io-uring.rst new file mode 100644 index 000000000000..d73dd0dbd238 --- /dev/null +++ b/Documentation/filesystems/fuse-io-uring.rst @@ -0,0 +1,99 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +FUSE-over-io-uring design documentation +======================================= + +This documentation covers basic details how the fuse +kernel/userspace communication through io-uring is configured +and works. For generic details about FUSE see fuse.rst. + +This document also covers the current interface, which is +still in development and might change. + +Limitations +=========== +As of now not all requests types are supported through io-uring, userspace +is required to also handle requests through /dev/fuse after io-uring setup +is complete. Specifically notifications (initiated from the daemon side) +and interrupts. + +Fuse io-uring configuration +=========================== + +Fuse kernel requests are queued through the classical /dev/fuse +read/write interface - until io-uring setup is complete. + +In order to set up fuse-over-io-uring fuse-server (user-space) +needs to submit SQEs (opcode = IORING_OP_URING_CMD) to the /dev/fuse +connection file descriptor. Initial submit is with the sub command +FUSE_URING_REQ_REGISTER, which will just register entries to be +available in the kernel. + +Once at least one entry per queue is submitted, kernel starts +to enqueue to ring queues. +Note, every CPU core has its own fuse-io-uring queue. +Userspace handles the CQE/fuse-request and submits the result as +subcommand FUSE_URING_REQ_COMMIT_AND_FETCH - kernel completes +the requests and also marks the entry available again. If there are +pending requests waiting the request will be immediately submitted +to the daemon again. + +Initial SQE +-----------:: + + | | FUSE filesystem daemon + | | + | | >io_uring_submit() + | | IORING_OP_URING_CMD / + | | FUSE_URING_CMD_REGISTER + | | [wait cqe] + | | >io_uring_wait_cqe() or + | | >io_uring_submit_and_wait() + | | + | >fuse_uring_cmd() | + | >fuse_uring_register() | + + +Sending requests with CQEs +--------------------------:: + + | | FUSE filesystem daemon + | | [waiting for CQEs] + | "rm /mnt/fuse/file" | + | | + | >sys_unlink() | + | >fuse_unlink() | + | [allocate request] | + | >fuse_send_one() | + | ... | + | >fuse_uring_queue_fuse_req | + | [queue request on fg queue] | + | >fuse_uring_add_req_to_ring_ent() | + | ... | + | >fuse_uring_copy_to_ring() | + | >io_uring_cmd_done() | + | >request_wait_answer() | + | [sleep on req->waitq] | + | | [receives and handles CQE] + | | [submit result and fetch next] + | | >io_uring_submit() + | | IORING_OP_URING_CMD/ + | | FUSE_URING_CMD_COMMIT_AND_FETCH + | >fuse_uring_cmd() | + | >fuse_uring_commit_fetch() | + | >fuse_uring_commit() | + | >fuse_uring_copy_from_ring() | + | [ copy the result to the fuse req] | + | >fuse_uring_req_end() | + | >fuse_request_end() | + | [wake up req->waitq] | + | >fuse_uring_next_fuse_req | + | [wait or handle next req] | + | | + | [req->waitq woken up] | + | <fuse_unlink() | + | <sys_unlink() | + + + diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst index 44e9e77ffe0d..2636f2a41bd3 100644 --- a/Documentation/filesystems/index.rst +++ b/Documentation/filesystems/index.rst @@ -98,6 +98,7 @@ Documentation for filesystem implementations. hpfs fuse fuse-io + fuse-io-uring inotify isofs nilfs2 diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index f5e3676db954..d20a32b77b60 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -17,7 +17,8 @@ dentry_operations prototypes:: - int (*d_revalidate)(struct dentry *, unsigned int); + int (*d_revalidate)(struct inode *, const struct qstr *, + struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, @@ -30,6 +31,8 @@ prototypes:: struct vfsmount *(*d_automount)(struct path *path); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); + bool (*d_unalias_trylock)(const struct dentry *); + void (*d_unalias_unlock)(const struct dentry *); locking rules: @@ -49,6 +52,8 @@ d_dname: no no no no d_automount: no no yes no d_manage: no no yes (ref-walk) maybe d_real no no yes no +d_unalias_trylock yes no no no +d_unalias_unlock yes no no no ================== =========== ======== ============== ======== inode_operations diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst index c1c121055204..1639e78e3146 100644 --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -1141,3 +1141,19 @@ pointer are gone. set_blocksize() takes opened struct file instead of struct block_device now and it *must* be opened exclusive. + +--- + +** mandatory** + +->d_revalidate() gets two extra arguments - inode of parent directory and +name our dentry is expected to have. Both are stable (dir is pinned in +non-RCU case and will stay around during the call in RCU case, and name +is guaranteed to stay unchanging). Your instance doesn't have to use +either, but it often helps to avoid a lot of painful boilerplate. +Note that while name->name is stable and NUL-terminated, it may (and +often will) have name->name[name->len] equal to '/' rather than '\0' - +in normal case it points into the pathname being looked up. +NOTE: if you need something like full path from the root of filesystem, +you are still on your own - this assists with simple cases, but it's not +magic. diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 0b18af3f954e..31eea688609a 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -1251,7 +1251,8 @@ defined: .. code-block:: c struct dentry_operations { - int (*d_revalidate)(struct dentry *, unsigned int); + int (*d_revalidate)(struct inode *, const struct qstr *, + struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, @@ -1264,6 +1265,8 @@ defined: struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); + bool (*d_unalias_trylock)(const struct dentry *); + void (*d_unalias_unlock)(const struct dentry *); }; ``d_revalidate`` @@ -1427,6 +1430,25 @@ defined: For non-regular files, the 'dentry' argument is returned. +``d_unalias_trylock`` + if present, will be called by d_splice_alias() before moving a + preexisting attached alias. Returning false prevents __d_move(), + making d_splice_alias() fail with -ESTALE. + + Rationale: setting FS_RENAME_DOES_D_MOVE will prevent d_move() + and d_exchange() calls from the outside of filesystem methods; + however, it does not guarantee that attached dentries won't + be renamed or moved by d_splice_alias() finding a preexisting + alias for a directory inode. Normally we would not care; + however, something that wants to stabilize the entire path to + root over a blocking operation might need that. See 9p for one + (and hopefully only) example. + +``d_unalias_unlock`` + should be paired with ``d_unalias_trylock``; that one is called after + __d_move() call in __d_unalias(). + + Each dentry has a pointer to its parent dentry, as well as a hash list of child dentries. Child dentries are basically like files in a directory. diff --git a/Documentation/kbuild/gendwarfksyms.rst b/Documentation/kbuild/gendwarfksyms.rst new file mode 100644 index 000000000000..e4beaae7e456 --- /dev/null +++ b/Documentation/kbuild/gendwarfksyms.rst @@ -0,0 +1,308 @@ +======================= +DWARF module versioning +======================= + +1. Introduction +=============== + +When CONFIG_MODVERSIONS is enabled, symbol versions for modules +are typically calculated from preprocessed source code using the +**genksyms** tool. However, this is incompatible with languages such +as Rust, where the source code has insufficient information about +the resulting ABI. With CONFIG_GENDWARFKSYMS (and CONFIG_DEBUG_INFO) +selected, **gendwarfksyms** is used instead to calculate symbol versions +from the DWARF debugging information, which contains the necessary +details about the final module ABI. + +1.1. Usage +========== + +gendwarfksyms accepts a list of object files on the command line, and a +list of symbol names (one per line) in standard input:: + + Usage: gendwarfksyms [options] elf-object-file ... < symbol-list + + Options: + -d, --debug Print debugging information + --dump-dies Dump DWARF DIE contents + --dump-die-map Print debugging information about die_map changes + --dump-types Dump type strings + --dump-versions Dump expanded type strings used for symbol versions + -s, --stable Support kABI stability features + -T, --symtypes file Write a symtypes file + -h, --help Print this message + + +2. Type information availability +================================ + +While symbols are typically exported in the same translation unit (TU) +where they're defined, it's also perfectly fine for a TU to export +external symbols. For example, this is done when calculating symbol +versions for exports in stand-alone assembly code. + +To ensure the compiler emits the necessary DWARF type information in the +TU where symbols are actually exported, gendwarfksyms adds a pointer +to exported symbols in the `EXPORT_SYMBOL()` macro using the following +macro:: + + #define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; + + +When a symbol pointer is found in DWARF, gendwarfksyms can use its +type for calculating symbol versions even if the symbol is defined +elsewhere. The name of the symbol pointer is expected to start with +`__gendwarfksyms_ptr_`, followed by the name of the exported symbol. + +3. Symtypes output format +========================= + +Similarly to genksyms, gendwarfksyms supports writing a symtypes +file for each processed object that contain types for exported +symbols and each referenced type that was used in calculating symbol +versions. These files can be useful when trying to determine what +exactly caused symbol versions to change between builds. To generate +symtypes files during a kernel build, set `KBUILD_SYMTYPES=1`. + +Matching the existing format, the first column of each line contains +either a type reference or a symbol name. Type references have a +one-letter prefix followed by "#" and the name of the type. Four +reference types are supported:: + + e#<type> = enum + s#<type> = struct + t#<type> = typedef + u#<type> = union + +Type names with spaces in them are wrapped in single quotes, e.g.:: + + s#'core::result::Result<u8, core::num::error::ParseIntError>' + +The rest of the line contains a type string. Unlike with genksyms that +produces C-style type strings, gendwarfksyms uses the same simple parsed +DWARF format produced by **--dump-dies**, but with type references +instead of fully expanded strings. + +4. Maintaining a stable kABI +============================ + +Distribution maintainers often need the ability to make ABI compatible +changes to kernel data structures due to LTS updates or backports. Using +the traditional `#ifndef __GENKSYMS__` to hide these changes from symbol +versioning won't work when processing object files. To support this +use case, gendwarfksyms provides kABI stability features designed to +hide changes that won't affect the ABI when calculating versions. These +features are all gated behind the **--stable** command line flag and are +not used in the mainline kernel. To use stable features during a kernel +build, set `KBUILD_GENDWARFKSYMS_STABLE=1`. + +Examples for using these features are provided in the +**scripts/gendwarfksyms/examples** directory, including helper macros +for source code annotation. Note that as these features are only used to +transform the inputs for symbol versioning, the user is responsible for +ensuring that their changes actually won't break the ABI. + +4.1. kABI rules +=============== + +kABI rules allow distributions to fine-tune certain parts +of gendwarfksyms output and thus control how symbol +versions are calculated. These rules are defined in the +`.discard.gendwarfksyms.kabi_rules` section of the object file and +consist of simple null-terminated strings with the following structure:: + + version\0type\0target\0value\0 + +This string sequence is repeated as many times as needed to express all +the rules. The fields are as follows: + +- `version`: Ensures backward compatibility for future changes to the + structure. Currently expected to be "1". +- `type`: Indicates the type of rule being applied. +- `target`: Specifies the target of the rule, typically the fully + qualified name of the DWARF Debugging Information Entry (DIE). +- `value`: Provides rule-specific data. + +The following helper macro, for example, can be used to specify rules +in the source code:: + + #define __KABI_RULE(hint, target, value) \ + static const char __PASTE(__gendwarfksyms_rule_, \ + __COUNTER__)[] __used __aligned(1) \ + __section(".discard.gendwarfksyms.kabi_rules") = \ + "1\0" #hint "\0" #target "\0" #value + + +Currently, only the rules discussed in this section are supported, but +the format is extensible enough to allow further rules to be added as +need arises. + +4.1.1. Managing definition visibility +===================================== + +A declaration can change into a full definition when additional includes +are pulled into the translation unit. This changes the versions of any +symbol that references the type even if the ABI remains unchanged. As +it may not be possible to drop includes without breaking the build, the +`declonly` rule can be used to specify a type as declaration-only, even +if the debugging information contains the full definition. + +The rule fields are expected to be as follows: + +- `type`: "declonly" +- `target`: The fully qualified name of the target data structure + (as shown in **--dump-dies** output). +- `value`: This field is ignored. + +Using the `__KABI_RULE` macro, this rule can be defined as:: + + #define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, ) + +Example usage:: + + struct s { + /* definition */ + }; + + KABI_DECLONLY(s); + +4.1.2. Adding enumerators +========================= + +For enums, all enumerators and their values are included in calculating +symbol versions, which becomes a problem if we later need to add more +enumerators without changing symbol versions. The `enumerator_ignore` +rule allows us to hide named enumerators from the input. + +The rule fields are expected to be as follows: + +- `type`: "enumerator_ignore" +- `target`: The fully qualified name of the target enum + (as shown in **--dump-dies** output) and the name of the + enumerator field separated by a space. +- `value`: This field is ignored. + +Using the `__KABI_RULE` macro, this rule can be defined as:: + + #define KABI_ENUMERATOR_IGNORE(fqn, field) \ + __KABI_RULE(enumerator_ignore, fqn field, ) + +Example usage:: + + enum e { + A, B, C, D, + }; + + KABI_ENUMERATOR_IGNORE(e, B); + KABI_ENUMERATOR_IGNORE(e, C); + +If the enum additionally includes an end marker and new values must +be added in the middle, we may need to use the old value for the last +enumerator when calculating versions. The `enumerator_value` rule allows +us to override the value of an enumerator for version calculation: + +- `type`: "enumerator_value" +- `target`: The fully qualified name of the target enum + (as shown in **--dump-dies** output) and the name of the + enumerator field separated by a space. +- `value`: Integer value used for the field. + +Using the `__KABI_RULE` macro, this rule can be defined as:: + + #define KABI_ENUMERATOR_VALUE(fqn, field, value) \ + __KABI_RULE(enumerator_value, fqn field, value) + +Example usage:: + + enum e { + A, B, C, LAST, + }; + + KABI_ENUMERATOR_IGNORE(e, C); + KABI_ENUMERATOR_VALUE(e, LAST, 2); + +4.3. Adding structure members +============================= + +Perhaps the most common ABI compatible change is adding a member to a +kernel data structure. When changes to a structure are anticipated, +distribution maintainers can pre-emptively reserve space in the +structure and take it into use later without breaking the ABI. If +changes are needed to data structures without reserved space, existing +alignment holes can potentially be used instead. While kABI rules could +be added for these type of changes, using unions is typically a more +natural method. This section describes gendwarfksyms support for using +reserved space in data structures and hiding members that don't change +the ABI when calculating symbol versions. + +4.3.1. Reserving space and replacing members +============================================ + +Space is typically reserved for later use by appending integer types, or +arrays, to the end of the data structure, but any type can be used. Each +reserved member needs a unique name, but as the actual purpose is usually +not known at the time the space is reserved, for convenience, names that +start with `__kabi_` are left out when calculating symbol versions:: + + struct s { + long a; + long __kabi_reserved_0; /* reserved for future use */ + }; + +The reserved space can be taken into use by wrapping the member in a +union, which includes the original type and the replacement member:: + + struct s { + long a; + union { + long __kabi_reserved_0; /* original type */ + struct b b; /* replaced field */ + }; + }; + +If the `__kabi_` naming scheme was used when reserving space, the name +of the first member of the union must start with `__kabi_reserved`. This +ensures the original type is used when calculating versions, but the name +is again left out. The rest of the union is ignored. + +If we're replacing a member that doesn't follow this naming convention, +we also need to preserve the original name to avoid changing versions, +which we can do by changing the first union member's name to start with +`__kabi_renamed` followed by the original name. + +The examples include `KABI_(RESERVE|USE|REPLACE)*` macros that help +simplify the process and also ensure the replacement member is correctly +aligned and its size won't exceed the reserved space. + +4.3.2. Hiding members +===================== + +Predicting which structures will require changes during the support +timeframe isn't always possible, in which case one might have to resort +to placing new members into existing alignment holes:: + + struct s { + int a; + /* a 4-byte alignment hole */ + unsigned long b; + }; + + +While this won't change the size of the data structure, one needs to +be able to hide the added members from symbol versioning. Similarly +to reserved fields, this can be accomplished by wrapping the added +member to a union where one of the fields has a name starting with +`__kabi_ignored`:: + + struct s { + int a; + union { + char __kabi_ignored_0; + int n; + }; + unsigned long b; + }; + +With **--stable**, both versions produce the same symbol version. diff --git a/Documentation/kbuild/index.rst b/Documentation/kbuild/index.rst index cee2f99f734b..e82af05cd652 100644 --- a/Documentation/kbuild/index.rst +++ b/Documentation/kbuild/index.rst @@ -21,6 +21,7 @@ Kernel Build System reproducible-builds gcc-plugins llvm + gendwarfksyms .. only:: subproject and html diff --git a/Documentation/kbuild/modules.rst b/Documentation/kbuild/modules.rst index 101de236cd0c..a42f00d8cb90 100644 --- a/Documentation/kbuild/modules.rst +++ b/Documentation/kbuild/modules.rst @@ -423,6 +423,26 @@ Symbols From the Kernel (vmlinux + modules) 1) It lists all exported symbols from vmlinux and all modules. 2) It lists the CRC if CONFIG_MODVERSIONS is enabled. +Version Information Formats +--------------------------- + + Exported symbols have information stored in __ksymtab or __ksymtab_gpl + sections. Symbol names and namespaces are stored in __ksymtab_strings, + using a format similar to the string table used for ELF. If + CONFIG_MODVERSIONS is enabled, the CRCs corresponding to exported + symbols will be added to the __kcrctab or __kcrctab_gpl. + + If CONFIG_BASIC_MODVERSIONS is enabled (default with + CONFIG_MODVERSIONS), imported symbols will have their symbol name and + CRC stored in the __versions section of the importing module. This + mode only supports symbols of length up to 64 bytes. + + If CONFIG_EXTENDED_MODVERSIONS is enabled (required to enable both + CONFIG_MODVERSIONS and CONFIG_RUST at the same time), imported symbols + will have their symbol name recorded in the __version_ext_names + section as a series of concatenated, null-terminated strings. CRCs for + these symbols will be recorded in the __version_ext_crcs section. + Symbols and External Modules ---------------------------- diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 259cb211a338..655d8d10fe24 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1524,7 +1524,8 @@ attribute-sets: nested-attributes: bitset - name: hwtstamp-flags - type: u32 + type: nest + nested-attributes: bitset operations: enum-model: directional diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst index 62519d38c58b..b018ce346392 100644 --- a/Documentation/networking/can.rst +++ b/Documentation/networking/can.rst @@ -699,10 +699,10 @@ RAW socket option CAN_RAW_JOIN_FILTERS The CAN_RAW socket can set multiple CAN identifier specific filters that lead to multiple filters in the af_can.c filter processing. These filters -are indenpendent from each other which leads to logical OR'ed filters when +are independent from each other which leads to logical OR'ed filters when applied (see :ref:`socketcan-rawfilter`). -This socket option joines the given CAN filters in the way that only CAN +This socket option joins the given CAN filters in the way that only CAN frames are passed to user space that matched *all* given CAN filters. The semantic for the applied filters is therefore changed to a logical AND. diff --git a/Documentation/networking/iso15765-2.rst b/Documentation/networking/iso15765-2.rst index 0e9d96074178..37ebb2c417cb 100644 --- a/Documentation/networking/iso15765-2.rst +++ b/Documentation/networking/iso15765-2.rst @@ -369,8 +369,8 @@ to their default. addr.can_family = AF_CAN; addr.can_ifindex = if_nametoindex("can0"); - addr.tp.tx_id = 0x18DA42F1 | CAN_EFF_FLAG; - addr.tp.rx_id = 0x18DAF142 | CAN_EFF_FLAG; + addr.can_addr.tp.tx_id = 0x18DA42F1 | CAN_EFF_FLAG; + addr.can_addr.tp.rx_id = 0x18DAF142 | CAN_EFF_FLAG; ret = bind(s, (struct sockaddr *)&addr, sizeof(addr)); if (ret < 0) diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index dc45c0211353..03e1d3610333 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -41,7 +41,7 @@ blackhole_timeout - INTEGER (seconds) MPTCP is re-enabled and will reset to the initial value when the blackhole issue goes away. - 0 to disable the blackhole detection. + 0 to disable the blackhole detection. This is a per-namespace sysctl. Default: 3600 diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst index 6083210ab2a4..f970a2be271a 100644 --- a/Documentation/networking/napi.rst +++ b/Documentation/networking/napi.rst @@ -362,7 +362,7 @@ It is expected that ``irq-suspend-timeout`` will be set to a value much larger than ``gro_flush_timeout`` as ``irq-suspend-timeout`` should suspend IRQs for the duration of one userland processing cycle. -While it is not stricly necessary to use ``napi_defer_hard_irqs`` and +While it is not strictly necessary to use ``napi_defer_hard_irqs`` and ``gro_flush_timeout`` to use IRQ suspension, their use is strongly recommended. diff --git a/Documentation/power/video.rst b/Documentation/power/video.rst index 337a2ba9f32f..8ab2458d1304 100644 --- a/Documentation/power/video.rst +++ b/Documentation/power/video.rst @@ -190,7 +190,7 @@ Toshiba Portege 3020CT s3_mode (3) Toshiba Satellite 4030CDT s3_mode (3) (S1 also works OK) Toshiba Satellite 4080XCDT s3_mode (3) (S1 also works OK) Toshiba Satellite 4090XCDT ??? [#f1]_ -Toshiba Satellite P10-554 s3_bios,s3_mode (4)[#f3]_ +Toshiba Satellite P10-554 s3_bios,s3_mode (4) [#f3]_ Toshiba M30 (2) xor X with nvidia driver using internal AGP Uniwill 244IIO ??? [#f1]_ =============================== =============================================== diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 82b5e378eebf..a0beca805362 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -59,7 +59,6 @@ iptables 1.4.2 iptables -V openssl & libcrypto 1.0.0 openssl version bc 1.06.95 bc --version Sphinx\ [#f1]_ 2.4.4 sphinx-build --version -cpio any cpio --version GNU tar 1.28 tar --version gtags (optional) 6.6.5 gtags --version mkimage (optional) 2017.01 mkimage --version @@ -536,11 +535,6 @@ mcelog - <https://www.mcelog.org/> -cpio ----- - -- <https://www.gnu.org/software/cpio/> - Networking ********** diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index daebce49cfdf..0e19d2f0d6bb 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -308,7 +308,7 @@ an involved disclosed party. The current ambassadors list: Google Kees Cook <keescook@chromium.org> - LLVM Nick Desaulniers <ndesaulniers@google.com> + LLVM Nick Desaulniers <nick.desaulniers+lkml@gmail.com> ============= ======================================================== If you want your organization to be added to the ambassadors list, please diff --git a/Documentation/translations/sp_SP/index.rst b/Documentation/translations/sp_SP/index.rst index aae7018b0d1a..2b50283e1608 100644 --- a/Documentation/translations/sp_SP/index.rst +++ b/Documentation/translations/sp_SP/index.rst @@ -7,7 +7,7 @@ Traducción al español \kerneldocCJKoff -:maintainer: Carlos Bilbao <carlos.bilbao.osdev@gmail.com> +:maintainer: Carlos Bilbao <carlos.bilbao@kernel.org> .. _sp_disclaimer: diff --git a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst index 7d4d694967c7..9d444b9c46d3 100644 --- a/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst +++ b/Documentation/translations/sp_SP/process/embargoed-hardware-issues.rst @@ -287,7 +287,7 @@ revelada involucrada. La lista de embajadores actuales: Google Kees Cook <keescook@chromium.org> - LLVM Nick Desaulniers <ndesaulniers@google.com> + LLVM Nick Desaulniers <nick.desaulniers+lkml@gmail.com> ============= ======================================================== Si quiere que su organización se añada a la lista de embajadores, por diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 0d1c3a820ce6..2b52eb77e29c 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1419,7 +1419,7 @@ fetch) is injected in the guest. S390: ^^^^^ -Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set. +Returns -EINVAL or -EEXIST if the VM has the KVM_VM_S390_UCONTROL flag set. Returns -EINVAL if called on a protected VM. 4.36 KVM_SET_TSS_ADDR diff --git a/MAINTAINERS b/MAINTAINERS index 936e80f2c9ce..3864d473f52f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -987,6 +987,12 @@ L: linux-edac@vger.kernel.org S: Supported F: drivers/ras/amd/atl/* +AMD AE4DMA DRIVER +M: Basavaraj Natikar <Basavaraj.Natikar@amd.com> +L: dmaengine@vger.kernel.org +S: Supported +F: drivers/dma/amd/ae4dma/ + AMD AXI W1 DRIVER M: Kris Chaplin <kris.chaplin@amd.com> R: Thomas Delev <thomas.delev@amd.com> @@ -1084,7 +1090,7 @@ F: drivers/video/fbdev/geode/ AMD HSMP DRIVER M: Naveen Krishna Chatradhi <naveenkrishna.chatradhi@amd.com> -R: Carlos Bilbao <carlos.bilbao.osdev@gmail.com> +R: Carlos Bilbao <carlos.bilbao@kernel.org> L: platform-driver-x86@vger.kernel.org S: Maintained F: Documentation/arch/x86/amd_hsmp.rst @@ -1179,8 +1185,8 @@ F: tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py AMD PTDMA DRIVER M: Basavaraj Natikar <Basavaraj.Natikar@amd.com> L: dmaengine@vger.kernel.org -S: Maintained -F: drivers/dma/ptdma/ +S: Supported +F: drivers/dma/amd/ptdma/ AMD QDMA DRIVER M: Nishad Saraf <nishads@amd.com> @@ -2203,7 +2209,6 @@ F: sound/soc/codecs/cs42l84.* F: sound/soc/codecs/ssm3515.c ARM/APPLE MACHINE SUPPORT -M: Hector Martin <marcan@marcan.st> M: Sven Peter <sven@svenpeter.dev> R: Alyssa Rosenzweig <alyssa@rosenzweig.io> L: asahi@lists.linux.dev @@ -3649,7 +3654,6 @@ F: Documentation/devicetree/bindings/phy/phy-ath79-usb.txt F: drivers/phy/qualcomm/phy-ath79-usb.c ATHEROS ATH GENERIC UTILITIES -M: Kalle Valo <kvalo@kernel.org> M: Jeff Johnson <jjohnson@kernel.org> L: linux-wireless@vger.kernel.org S: Supported @@ -3854,13 +3858,6 @@ W: https://ez.analog.com/linux-software-drivers F: Documentation/devicetree/bindings/pwm/adi,axi-pwmgen.yaml F: drivers/pwm/pwm-axi-pwmgen.c -AXXIA I2C CONTROLLER -M: Krzysztof Adamski <krzysztof.adamski@nokia.com> -L: linux-i2c@vger.kernel.org -S: Maintained -F: Documentation/devicetree/bindings/i2c/i2c-axxia.txt -F: drivers/i2c/busses/i2c-axxia.c - AZ6007 DVB DRIVER M: Mauro Carvalho Chehab <mchehab@kernel.org> L: linux-media@vger.kernel.org @@ -3949,6 +3946,7 @@ M: Kent Overstreet <kent.overstreet@linux.dev> L: linux-bcachefs@vger.kernel.org S: Supported C: irc://irc.oftc.net/bcache +P: Documentation/filesystems/bcachefs/SubmittingPatches.rst T: git https://evilpiepirate.org/git/bcachefs.git F: fs/bcachefs/ F: Documentation/filesystems/bcachefs/ @@ -4096,6 +4094,7 @@ S: Supported W: http://www.bluez.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/bluetooth/bluetooth-next.git +F: Documentation/ABI/stable/sysfs-class-bluetooth F: include/net/bluetooth/ F: net/bluetooth/ @@ -5656,7 +5655,7 @@ F: .clang-format CLANG/LLVM BUILD SUPPORT M: Nathan Chancellor <nathan@kernel.org> -R: Nick Desaulniers <ndesaulniers@google.com> +R: Nick Desaulniers <nick.desaulniers+lkml@gmail.com> R: Bill Wendling <morbo@google.com> R: Justin Stitt <justinstitt@google.com> L: llvm@lists.linux.dev @@ -5850,7 +5849,7 @@ F: drivers/usb/atm/cxacru.c CONFIDENTIAL COMPUTING THREAT MODEL FOR X86 VIRTUALIZATION (SNP/TDX) M: Elena Reshetova <elena.reshetova@intel.com> -M: Carlos Bilbao <carlos.bilbao.osdev@gmail.com> +M: Carlos Bilbao <carlos.bilbao@kernel.org> S: Maintained F: Documentation/security/snp-tdx-threat-model.rst @@ -7109,8 +7108,10 @@ F: rust/kernel/device.rs F: rust/kernel/device_id.rs F: rust/kernel/devres.rs F: rust/kernel/driver.rs +F: rust/kernel/faux.rs F: rust/kernel/platform.rs F: samples/rust/rust_driver_platform.rs +F: samples/rust/rust_driver_faux.rs DRIVERS FOR OMAP ADAPTIVE VOLTAGE SCALING (AVS) M: Nishanth Menon <nm@ti.com> @@ -9411,7 +9412,7 @@ F: fs/freevxfs/ FREEZER M: "Rafael J. Wysocki" <rafael@kernel.org> -M: Pavel Machek <pavel@ucw.cz> +M: Pavel Machek <pavel@kernel.org> L: linux-pm@vger.kernel.org S: Supported F: Documentation/power/freezing-of-tasks.rst @@ -9634,6 +9635,13 @@ W: https://linuxtv.org T: git git://linuxtv.org/media.git F: drivers/media/radio/radio-gemtek* +GENDWARFKSYMS +M: Sami Tolvanen <samitolvanen@google.com> +L: linux-modules@vger.kernel.org +L: linux-kbuild@vger.kernel.org +S: Maintained +F: scripts/gendwarfksyms/ + GENERIC ARCHITECTURE TOPOLOGY M: Sudeep Holla <sudeep.holla@arm.com> L: linux-kernel@vger.kernel.org @@ -9821,8 +9829,7 @@ F: drivers/input/touchscreen/goodix* GOOGLE ETHERNET DRIVERS M: Jeroen de Borst <jeroendb@google.com> -M: Praveen Kaligineedi <pkaligineedi@google.com> -R: Shailend Chand <shailend@google.com> +M: Harshitha Ramamurthy <hramamurthy@google.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/google/gve.rst @@ -9864,7 +9871,7 @@ S: Maintained F: drivers/staging/gpib/ GPIO ACPI SUPPORT -M: Mika Westerberg <mika.westerberg@linux.intel.com> +M: Mika Westerberg <westeri@kernel.org> M: Andy Shevchenko <andriy.shevchenko@linux.intel.com> L: linux-gpio@vger.kernel.org L: linux-acpi@vger.kernel.org @@ -10239,7 +10246,7 @@ F: drivers/video/fbdev/hgafb.c HIBERNATION (aka Software Suspend, aka swsusp) M: "Rafael J. Wysocki" <rafael@kernel.org> -M: Pavel Machek <pavel@ucw.cz> +M: Pavel Machek <pavel@kernel.org> L: linux-pm@vger.kernel.org S: Supported B: https://bugzilla.kernel.org @@ -10808,7 +10815,7 @@ S: Odd Fixes F: drivers/tty/hvc/ I2C ACPI SUPPORT -M: Mika Westerberg <mika.westerberg@linux.intel.com> +M: Mika Westerberg <westeri@kernel.org> L: linux-i2c@vger.kernel.org L: linux-acpi@vger.kernel.org S: Maintained @@ -11317,7 +11324,7 @@ S: Orphan F: drivers/video/fbdev/imsttfb.c INDEX OF FURTHER KERNEL DOCUMENTATION -M: Carlos Bilbao <carlos.bilbao.osdev@gmail.com> +M: Carlos Bilbao <carlos.bilbao@kernel.org> S: Maintained F: Documentation/process/kernel-docs.rst @@ -13110,8 +13117,8 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har F: scripts/leaking_addresses.pl LED SUBSYSTEM -M: Pavel Machek <pavel@ucw.cz> M: Lee Jones <lee@kernel.org> +M: Pavel Machek <pavel@kernel.org> L: linux-leds@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/lee/leds.git @@ -16271,6 +16278,7 @@ F: drivers/scsi/sun3_scsi_vme.c NCSI LIBRARY M: Samuel Mendoza-Jonas <sam@mendozajonas.com> +R: Paul Fertser <fercerpav@gmail.com> S: Maintained F: net/ncsi/ @@ -16423,7 +16431,7 @@ X: drivers/net/can/ X: drivers/net/wireless/ NETWORKING DRIVERS (WIRELESS) -M: Kalle Valo <kvalo@kernel.org> +M: Johannes Berg <johannes@sipsolutions.net> L: linux-wireless@vger.kernel.org S: Maintained W: https://wireless.wiki.kernel.org/ @@ -16447,6 +16455,28 @@ F: include/net/dsa.h F: net/dsa/ F: tools/testing/selftests/drivers/net/dsa/ +NETWORKING [ETHTOOL] +M: Andrew Lunn <andrew@lunn.ch> +M: Jakub Kicinski <kuba@kernel.org> +F: Documentation/netlink/specs/ethtool.yaml +F: Documentation/networking/ethtool-netlink.rst +F: include/linux/ethtool* +F: include/uapi/linux/ethtool* +F: net/ethtool/ +F: tools/testing/selftests/drivers/net/*/ethtool* + +NETWORKING [ETHTOOL CABLE TEST] +M: Andrew Lunn <andrew@lunn.ch> +F: net/ethtool/cabletest.c +F: tools/testing/selftests/drivers/net/*/ethtool* +K: cable_test + +NETWORKING [ETHTOOL MAC MERGE] +M: Vladimir Oltean <vladimir.oltean@nxp.com> +F: net/ethtool/mm.c +F: tools/testing/selftests/drivers/net/hw/ethtool_mm.sh +K: ethtool_mm + NETWORKING [GENERAL] M: "David S. Miller" <davem@davemloft.net> M: Eric Dumazet <edumazet@google.com> @@ -16478,6 +16508,7 @@ F: include/linux/netdev* F: include/linux/netlink.h F: include/linux/netpoll.h F: include/linux/rtnetlink.h +F: include/linux/sctp.h F: include/linux/seq_file_net.h F: include/linux/skbuff* F: include/net/ @@ -16494,6 +16525,7 @@ F: include/uapi/linux/netdev* F: include/uapi/linux/netlink.h F: include/uapi/linux/netlink_diag.h F: include/uapi/linux/rtnetlink.h +F: include/uapi/linux/sctp.h F: lib/net_utils.c F: lib/random32.c F: net/ @@ -16605,6 +16637,8 @@ F: tools/testing/selftests/net/mptcp/ NETWORKING [TCP] M: Eric Dumazet <edumazet@google.com> +M: Neal Cardwell <ncardwell@google.com> +R: Kuniyuki Iwashima <kuniyu@amazon.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/net_cachelines/tcp_sock.rst @@ -16632,6 +16666,31 @@ F: include/net/tls.h F: include/uapi/linux/tls.h F: net/tls/* +NETWORKING [SOCKETS] +M: Eric Dumazet <edumazet@google.com> +M: Kuniyuki Iwashima <kuniyu@amazon.com> +M: Paolo Abeni <pabeni@redhat.com> +M: Willem de Bruijn <willemb@google.com> +S: Maintained +F: include/linux/sock_diag.h +F: include/linux/socket.h +F: include/linux/sockptr.h +F: include/net/sock.h +F: include/net/sock_reuseport.h +F: include/uapi/linux/socket.h +F: net/core/*sock* +F: net/core/scm.c +F: net/socket.c + +NETWORKING [UNIX SOCKETS] +M: Kuniyuki Iwashima <kuniyu@amazon.com> +S: Maintained +F: include/net/af_unix.h +F: include/net/netns/unix.h +F: include/uapi/linux/unix_diag.h +F: net/unix/ +F: tools/testing/selftests/net/af_unix/ + NETXEN (1/10) GbE SUPPORT M: Manish Chopra <manishc@marvell.com> M: Rahul Verma <rahulv@marvell.com> @@ -16765,7 +16824,7 @@ F: include/linux/tick.h F: kernel/time/tick*.* NOKIA N900 CAMERA SUPPORT (ET8EK8 SENSOR, AD5820 FOCUS) -M: Pavel Machek <pavel@ucw.cz> +M: Pavel Machek <pavel@kernel.org> M: Sakari Ailus <sakari.ailus@iki.fi> L: linux-media@vger.kernel.org S: Maintained @@ -17697,6 +17756,7 @@ L: netdev@vger.kernel.org L: dev@openvswitch.org S: Maintained W: http://openvswitch.org +F: Documentation/networking/openvswitch.rst F: include/uapi/linux/openvswitch.h F: net/openvswitch/ F: tools/testing/selftests/net/openvswitch/ @@ -19296,7 +19356,6 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/ F: drivers/media/tuners/qt1010* QUALCOMM ATH12K WIRELESS DRIVER -M: Kalle Valo <kvalo@kernel.org> M: Jeff Johnson <jjohnson@kernel.org> L: ath12k@lists.infradead.org S: Supported @@ -19306,7 +19365,6 @@ F: drivers/net/wireless/ath/ath12k/ N: ath12k QUALCOMM ATHEROS ATH10K WIRELESS DRIVER -M: Kalle Valo <kvalo@kernel.org> M: Jeff Johnson <jjohnson@kernel.org> L: ath10k@lists.infradead.org S: Supported @@ -19316,7 +19374,6 @@ F: drivers/net/wireless/ath/ath10k/ N: ath10k QUALCOMM ATHEROS ATH11K WIRELESS DRIVER -M: Kalle Valo <kvalo@kernel.org> M: Jeff Johnson <jjohnson@kernel.org> L: ath11k@lists.infradead.org S: Supported @@ -19437,7 +19494,7 @@ F: drivers/misc/fastrpc.c F: include/uapi/misc/fastrpc.h QUALCOMM HEXAGON ARCHITECTURE -M: Brian Cain <bcain@quicinc.com> +M: Brian Cain <brian.cain@oss.qualcomm.com> L: linux-hexagon@vger.kernel.org S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/bcain/linux.git @@ -19451,6 +19508,15 @@ L: dmaengine@vger.kernel.org S: Supported F: drivers/dma/qcom/hidma* +QUALCOMM I2C QCOM GENI DRIVER +M: Mukesh Kumar Savaliya <quic_msavaliy@quicinc.com> +M: Viken Dadhaniya <quic_vdadhani@quicinc.com> +L: linux-i2c@vger.kernel.org +L: linux-arm-msm@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/i2c/qcom,i2c-geni-qcom.yaml +F: drivers/i2c/busses/i2c-qcom-geni.c + QUALCOMM I2C CCI DRIVER M: Loic Poulain <loic.poulain@linaro.org> M: Robert Foss <rfoss@kernel.org> @@ -22199,7 +22265,7 @@ Q: http://patchwork.linuxtv.org/project/linux-media/list/ F: drivers/media/dvb-frontends/sp2* SPANISH DOCUMENTATION -M: Carlos Bilbao <carlos.bilbao.osdev@gmail.com> +M: Carlos Bilbao <carlos.bilbao@kernel.org> R: Avadhut Naik <avadhut.naik@amd.com> S: Maintained F: Documentation/translations/sp_SP/ @@ -22501,7 +22567,6 @@ F: drivers/phy/starfive/phy-jh7110-dphy-rx.c STARFIVE JH7110 DPHY TX DRIVER M: Keith Zhao <keith.zhao@starfivetech.com> -M: Shengyang Chen <shengyang.chen@starfivetech.com> S: Supported F: Documentation/devicetree/bindings/phy/starfive,jh7110-dphy-tx.yaml F: drivers/phy/starfive/phy-jh7110-dphy-tx.c @@ -22791,7 +22856,7 @@ F: drivers/sh/ SUSPEND TO RAM M: "Rafael J. Wysocki" <rafael@kernel.org> M: Len Brown <len.brown@intel.com> -M: Pavel Machek <pavel@ucw.cz> +M: Pavel Machek <pavel@kernel.org> L: linux-pm@vger.kernel.org S: Supported B: https://bugzilla.kernel.org @@ -25724,11 +25789,13 @@ F: arch/x86/entry/vdso/ XARRAY M: Matthew Wilcox <willy@infradead.org> L: linux-fsdevel@vger.kernel.org +L: linux-mm@kvack.org S: Supported F: Documentation/core-api/xarray.rst F: include/linux/idr.h F: include/linux/xarray.h F: lib/idr.c +F: lib/test_xarray.c F: lib/xarray.c F: tools/testing/radix-tree @@ -26208,7 +26275,7 @@ K: zstd ZSWAP COMPRESSED SWAP CACHING M: Johannes Weiner <hannes@cmpxchg.org> -M: Yosry Ahmed <yosryahmed@google.com> +M: Yosry Ahmed <yosry.ahmed@linux.dev> M: Nhat Pham <nphamcs@gmail.com> R: Chengming Zhou <chengming.zhou@linux.dev> L: linux-mm@kvack.org @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 13 +PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc3 NAME = Baby Opossum Posse # *DOCUMENTATION* @@ -1120,8 +1120,8 @@ LDFLAGS_vmlinux += --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL) endif # Align the bit size of userspace programs with the kernel -KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) -KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS)) +KBUILD_USERCFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)) +KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)) # make the checker run with the right architecture CHECKFLAGS += --arch=$(ARCH) @@ -1421,18 +1421,13 @@ ifneq ($(wildcard $(resolve_btfids_O)),) $(Q)$(MAKE) -sC $(srctree)/tools/bpf/resolve_btfids O=$(resolve_btfids_O) clean endif -# Clear a bunch of variables before executing the submake -ifeq ($(quiet),silent_) -tools_silent=s -endif - tools/: FORCE $(Q)mkdir -p $(objtree)/tools - $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ + $(Q)$(MAKE) LDFLAGS= O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ tools/%: FORCE $(Q)mkdir -p $(objtree)/tools - $(Q)$(MAKE) LDFLAGS= MAKEFLAGS="$(tools_silent) $(filter --j% -j,$(MAKEFLAGS))" O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ $* + $(Q)$(MAKE) LDFLAGS= O=$(abspath $(objtree)) subdir=tools -C $(srctree)/tools/ $* # --------------------------------------------------------------------------- # Kernel selftest diff --git a/arch/alpha/include/asm/elf.h b/arch/alpha/include/asm/elf.h index 4d7c46f50382..50c82187e60e 100644 --- a/arch/alpha/include/asm/elf.h +++ b/arch/alpha/include/asm/elf.h @@ -74,7 +74,7 @@ typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG]; /* * This is used to ensure we don't load something for the wrong architecture. */ -#define elf_check_arch(x) ((x)->e_machine == EM_ALPHA) +#define elf_check_arch(x) (((x)->e_machine == EM_ALPHA) && !((x)->e_flags & EF_ALPHA_32BIT)) /* * These are used to set parameters in the core dumps. @@ -137,10 +137,6 @@ extern int dump_elf_task(elf_greg_t *dest, struct task_struct *task); : amask (AMASK_CIX) ? "ev6" : "ev67"); \ }) -#define SET_PERSONALITY(EX) \ - set_personality(((EX).e_flags & EF_ALPHA_32BIT) \ - ? PER_LINUX_32BIT : PER_LINUX) - extern int alpha_l1i_cacheshape; extern int alpha_l1d_cacheshape; extern int alpha_l2_cacheshape; diff --git a/arch/alpha/include/asm/hwrpb.h b/arch/alpha/include/asm/hwrpb.h index fc76f36265ad..db831cf8de10 100644 --- a/arch/alpha/include/asm/hwrpb.h +++ b/arch/alpha/include/asm/hwrpb.h @@ -135,7 +135,7 @@ struct crb_struct { /* virtual->physical map */ unsigned long map_entries; unsigned long map_pages; - struct vf_map_struct map[1]; + struct vf_map_struct map[]; }; struct memclust_struct { diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 635f0a5f5bbd..02e8817a8921 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -360,7 +360,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte) extern void paging_init(void); -/* We have our own get_unmapped_area to cope with ADDR_LIMIT_32BIT. */ +/* We have our own get_unmapped_area */ #define HAVE_ARCH_UNMAPPED_AREA #endif /* _ALPHA_PGTABLE_H */ diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index 55bb1c09fd39..5dce5518a211 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -8,23 +8,19 @@ #ifndef __ASM_ALPHA_PROCESSOR_H #define __ASM_ALPHA_PROCESSOR_H -#include <linux/personality.h> /* for ADDR_LIMIT_32BIT */ - /* * We have a 42-bit user address space: 4TB user VM... */ #define TASK_SIZE (0x40000000000UL) -#define STACK_TOP \ - (current->personality & ADDR_LIMIT_32BIT ? 0x80000000 : 0x00120000000UL) +#define STACK_TOP (0x00120000000UL) #define STACK_TOP_MAX 0x00120000000UL /* This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE \ - ((current->personality & ADDR_LIMIT_32BIT) ? 0x40000000 : TASK_SIZE / 2) +#define TASK_UNMAPPED_BASE (TASK_SIZE / 2) /* This is dead. Everything has been moved to thread_info. */ struct thread_struct { }; diff --git a/arch/alpha/include/uapi/asm/ptrace.h b/arch/alpha/include/uapi/asm/ptrace.h index 5ca45934fcbb..72ed913a910f 100644 --- a/arch/alpha/include/uapi/asm/ptrace.h +++ b/arch/alpha/include/uapi/asm/ptrace.h @@ -42,6 +42,8 @@ struct pt_regs { unsigned long trap_a0; unsigned long trap_a1; unsigned long trap_a2; +/* This makes the stack 16-byte aligned as GCC expects */ + unsigned long __pad0; /* These are saved by PAL-code: */ unsigned long ps; unsigned long pc; diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c index 4cfeae42c79a..e9dad60b147f 100644 --- a/arch/alpha/kernel/asm-offsets.c +++ b/arch/alpha/kernel/asm-offsets.c @@ -19,9 +19,13 @@ static void __used foo(void) DEFINE(TI_STATUS, offsetof(struct thread_info, status)); BLANK(); + DEFINE(SP_OFF, offsetof(struct pt_regs, ps)); DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs)); BLANK(); + DEFINE(SWITCH_STACK_SIZE, sizeof(struct switch_stack)); + BLANK(); + DEFINE(HAE_CACHE, offsetof(struct alpha_machine_vector, hae_cache)); DEFINE(HAE_REG, offsetof(struct alpha_machine_vector, hae_register)); } diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index dd26062d75b3..f4d41b4538c2 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -15,10 +15,6 @@ .set noat .cfi_sections .debug_frame -/* Stack offsets. */ -#define SP_OFF 184 -#define SWITCH_STACK_SIZE 64 - .macro CFI_START_OSF_FRAME func .align 4 .globl \func @@ -198,8 +194,8 @@ CFI_END_OSF_FRAME entArith CFI_START_OSF_FRAME entMM SAVE_ALL /* save $9 - $15 so the inline exception code can manipulate them. */ - subq $sp, 56, $sp - .cfi_adjust_cfa_offset 56 + subq $sp, 64, $sp + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -214,7 +210,7 @@ CFI_START_OSF_FRAME entMM .cfi_rel_offset $13, 32 .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 - addq $sp, 56, $19 + addq $sp, 64, $19 /* handle the fault */ lda $8, 0x3fff bic $sp, $8, $8 @@ -227,7 +223,7 @@ CFI_START_OSF_FRAME entMM ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - addq $sp, 56, $sp + addq $sp, 64, $sp .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -235,7 +231,7 @@ CFI_START_OSF_FRAME entMM .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 /* finish up the syscall as normal. */ br ret_from_sys_call CFI_END_OSF_FRAME entMM @@ -382,8 +378,8 @@ entUnaUser: .cfi_restore $0 .cfi_adjust_cfa_offset -256 SAVE_ALL /* setup normal kernel stack */ - lda $sp, -56($sp) - .cfi_adjust_cfa_offset 56 + lda $sp, -64($sp) + .cfi_adjust_cfa_offset 64 stq $9, 0($sp) stq $10, 8($sp) stq $11, 16($sp) @@ -399,7 +395,7 @@ entUnaUser: .cfi_rel_offset $14, 40 .cfi_rel_offset $15, 48 lda $8, 0x3fff - addq $sp, 56, $19 + addq $sp, 64, $19 bic $sp, $8, $8 jsr $26, do_entUnaUser ldq $9, 0($sp) @@ -409,7 +405,7 @@ entUnaUser: ldq $13, 32($sp) ldq $14, 40($sp) ldq $15, 48($sp) - lda $sp, 56($sp) + lda $sp, 64($sp) .cfi_restore $9 .cfi_restore $10 .cfi_restore $11 @@ -417,7 +413,7 @@ entUnaUser: .cfi_restore $13 .cfi_restore $14 .cfi_restore $15 - .cfi_adjust_cfa_offset -56 + .cfi_adjust_cfa_offset -64 br ret_from_sys_call CFI_END_OSF_FRAME entUna diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 86185021f75a..a08e8edef1a4 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -1210,8 +1210,7 @@ SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p) return ret; } -/* Get an address range which is currently unmapped. Similar to the - generic version except that we know how to honor ADDR_LIMIT_32BIT. */ +/* Get an address range which is currently unmapped. */ static unsigned long arch_get_unmapped_area_1(unsigned long addr, unsigned long len, @@ -1230,13 +1229,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { - unsigned long limit; - - /* "32 bit" actually means 31 bit, since pointers sign extend. */ - if (current->personality & ADDR_LIMIT_32BIT) - limit = 0x80000000; - else - limit = TASK_SIZE; + unsigned long limit = TASK_SIZE; if (len > limit) return -ENOMEM; diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 681f56089d9c..dc91de50f906 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -13,6 +13,7 @@ #include <linux/log2.h> #include <linux/dma-map-ops.h> #include <linux/iommu-helper.h> +#include <linux/string_choices.h> #include <asm/io.h> #include <asm/hwrpb.h> @@ -212,7 +213,7 @@ static int pci_dac_dma_supported(struct pci_dev *dev, u64 mask) /* If both conditions above are met, we are fine. */ DBGA("pci_dac_dma_supported %s from %ps\n", - ok ? "yes" : "no", __builtin_return_address(0)); + str_yes_no(ok), __builtin_return_address(0)); return ok; } diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index a9a38c80c4a7..7004397937cf 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -649,7 +649,7 @@ s_reg_to_mem (unsigned long s_reg) static int unauser_reg_offsets[32] = { R(r0), R(r1), R(r2), R(r3), R(r4), R(r5), R(r6), R(r7), R(r8), /* r9 ... r15 are stored in front of regs. */ - -56, -48, -40, -32, -24, -16, -8, + -64, -56, -48, -40, -32, -24, -16, /* padding at -8 */ R(r16), R(r17), R(r18), R(r19), R(r20), R(r21), R(r22), R(r23), R(r24), R(r25), R(r26), R(r27), R(r28), R(gp), diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index 8c9850437e67..a9816bbc9f34 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,8 +78,8 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ - (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+10 : (r)-10]) + (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-17 : \ + (r) <= 18 ? (r)+11 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 62da5827f471..f27e6b90428e 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -18,6 +18,7 @@ config ARC select ARCH_SUPPORTS_ATOMIC_RMW if ARC_HAS_LLSC select ARCH_32BIT_OFF_T select BUILDTIME_TABLE_SORT + select GENERIC_BUILTIN_DTB select CLONE_BACKWARDS select COMMON_CLK select DMA_DIRECT_REMAP @@ -550,11 +551,11 @@ config ARC_DBG_JUMP_LABEL part of static keys (jump labels) related code. endif -config ARC_BUILTIN_DTB_NAME +config BUILTIN_DTB_NAME string "Built in DTB" + default "nsim_700" help - Set the name of the DTB to embed in the vmlinux binary - Leaving it blank selects the "nsim_700" dtb. + Set the name of the DTB to embed in the vmlinux binary. endmenu # "ARC Architecture Configuration" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index fb98478ed1ab..0c5e6e6314f2 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -82,9 +82,6 @@ KBUILD_CFLAGS += $(cflags-y) KBUILD_AFLAGS += $(KBUILD_CFLAGS) KBUILD_LDFLAGS += $(ldflags-y) -# w/o this dtb won't embed into kernel binary -core-y += arch/arc/boot/dts/ - core-y += arch/arc/plat-sim/ core-$(CONFIG_ARC_PLAT_TB10X) += arch/arc/plat-tb10x/ core-$(CONFIG_ARC_PLAT_AXS10X) += arch/arc/plat-axs10x/ diff --git a/arch/arc/boot/dts/Makefile b/arch/arc/boot/dts/Makefile index 48704dfdf75c..ee5664f0640d 100644 --- a/arch/arc/boot/dts/Makefile +++ b/arch/arc/boot/dts/Makefile @@ -1,13 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -# Built-in dtb -builtindtb-y := nsim_700 -ifneq ($(CONFIG_ARC_BUILTIN_DTB_NAME),) - builtindtb-y := $(CONFIG_ARC_BUILTIN_DTB_NAME) -endif - -obj-y += $(builtindtb-y).dtb.o -dtb-y := $(builtindtb-y).dtb +dtb-y := $(addsuffix .dtb, $(CONFIG_BUILTIN_DTB_NAME)) # for CONFIG_OF_ALL_DTBS test dtb- := $(patsubst $(src)/%.dts,%.dtb, $(wildcard $(src)/*.dts)) diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index 319bbe270322..a7cd526dd7ca 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -23,7 +23,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS101=y CONFIG_ARC_CACHE_LINE_SHIFT=5 -CONFIG_ARC_BUILTIN_DTB_NAME="axs101" +CONFIG_BUILTIN_DTB_NAME="axs101" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 8c1f1a111a17..afa6a348f444 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -22,7 +22,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="axs103" +CONFIG_BUILTIN_DTB_NAME="axs103" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 75cab9f25b5b..2bfa6371953c 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -22,7 +22,7 @@ CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y -CONFIG_ARC_BUILTIN_DTB_NAME="axs103_idu" +CONFIG_BUILTIN_DTB_NAME="axs103_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 8c3ed5d6e6c3..3a1577112078 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -14,7 +14,7 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_PERF_EVENTS=y # CONFIG_COMPAT_BRK is not set -CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs" +CONFIG_BUILTIN_DTB_NAME="haps_hs" CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_COMPACTION is not set diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 6fc98c1b9b36..a3cf940b1f5b 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -16,7 +16,7 @@ CONFIG_PERF_EVENTS=y # CONFIG_VM_EVENT_COUNTERS is not set # CONFIG_COMPAT_BRK is not set CONFIG_SMP=y -CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs_idu" +CONFIG_BUILTIN_DTB_NAME="haps_hs_idu" CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 9e79154b5535..1558e8e87767 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -20,7 +20,7 @@ CONFIG_ISA_ARCV2=y CONFIG_SMP=y CONFIG_LINUX_LINK_BASE=0x90000000 CONFIG_LINUX_RAM_BASE=0x80000000 -CONFIG_ARC_BUILTIN_DTB_NAME="hsdk" +CONFIG_BUILTIN_DTB_NAME="hsdk" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 51092c39e360..f8b3235d9a65 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -17,7 +17,7 @@ CONFIG_PERF_EVENTS=y # CONFIG_SLUB_DEBUG is not set # CONFIG_COMPAT_BRK is not set CONFIG_ISA_ARCOMPACT=y -CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" +CONFIG_BUILTIN_DTB_NAME="nsim_700" CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 70c17bca4939..ee45dc0877fb 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -19,7 +19,7 @@ CONFIG_ISA_ARCOMPACT=y CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set -CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci" +CONFIG_BUILTIN_DTB_NAME="nsimosci" # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index 59a3b6642fe7..e0a309970c20 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -19,7 +19,7 @@ CONFIG_KPROBES=y CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs" +CONFIG_BUILTIN_DTB_NAME="nsimosci_hs" # CONFIG_COMPACTION is not set CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 1419fc946a08..88325b8b49cf 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -16,7 +16,7 @@ CONFIG_MODULES=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set -CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu" +CONFIG_BUILTIN_DTB_NAME="nsimosci_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 5aba3d850fa2..865fbc19ef03 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -26,7 +26,7 @@ CONFIG_MODULE_UNLOAD=y CONFIG_ARC_PLAT_TB10X=y CONFIG_ARC_CACHE_LINE_SHIFT=5 CONFIG_HZ=250 -CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk" +CONFIG_BUILTIN_DTB_NAME="abilis_tb100_dvk" CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index 50c343913825..03d9ac20baa9 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -13,7 +13,7 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y CONFIG_ISA_ARCV2=y -CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38" +CONFIG_BUILTIN_DTB_NAME="vdk_hs38" CONFIG_PREEMPT=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 6d9e1d9f71d2..c09488992f13 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -15,7 +15,7 @@ CONFIG_AXS103=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set -CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp" +CONFIG_BUILTIN_DTB_NAME="vdk_hs38_smp" CONFIG_PREEMPT=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c index 905b1b191546..db8be609fab2 100644 --- a/arch/arm/kernel/isa.c +++ b/arch/arm/kernel/isa.c @@ -16,7 +16,7 @@ static unsigned int isa_membase, isa_portbase, isa_portshift; -static struct ctl_table ctl_isa_vars[] = { +static const struct ctl_table ctl_isa_vars[] = { { .procname = "membase", .data = &isa_membase, diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index fcdd0ed3eca8..940343beb3d4 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -225,7 +225,6 @@ config ARM64 select HAVE_FUNCTION_ERROR_INJECTION select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_RETVAL select HAVE_GCC_PLUGINS select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && \ HW_PERF_EVENTS && HAVE_PERF_EVENTS_NMI diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 358c68565bfd..2b25d671365f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -48,7 +48,11 @@ KBUILD_CFLAGS += $(CC_FLAGS_NO_FPU) \ KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) +ifeq ($(call test-ge, $(CONFIG_RUSTC_VERSION), 108500),y) +KBUILD_RUSTFLAGS += --target=aarch64-unknown-none-softfloat +else KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon" +endif KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 47f2cf408eed..78ec1ef2cfe8 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -605,48 +605,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) __cpacr_to_cptr_set(clr, set));\ } while (0) -static __always_inline void kvm_write_cptr_el2(u64 val) -{ - if (has_vhe() || has_hvhe()) - write_sysreg(val, cpacr_el1); - else - write_sysreg(val, cptr_el2); -} - -/* Resets the value of cptr_el2 when returning to the host. */ -static __always_inline void __kvm_reset_cptr_el2(struct kvm *kvm) -{ - u64 val; - - if (has_vhe()) { - val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN); - if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_EL1_SMEN_EL1EN; - } else if (has_hvhe()) { - val = CPACR_EL1_FPEN; - - if (!kvm_has_sve(kvm) || !guest_owns_fp_regs()) - val |= CPACR_EL1_ZEN; - if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_EL1_SMEN; - } else { - val = CPTR_NVHE_EL2_RES1; - - if (kvm_has_sve(kvm) && guest_owns_fp_regs()) - val |= CPTR_EL2_TZ; - if (!cpus_have_final_cap(ARM64_SME)) - val |= CPTR_EL2_TSM; - } - - kvm_write_cptr_el2(val); -} - -#ifdef __KVM_NVHE_HYPERVISOR__ -#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2(kern_hyp_va((v)->kvm)) -#else -#define kvm_reset_cptr_el2(v) __kvm_reset_cptr_el2((v)->kvm) -#endif - /* * Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE * format if E2H isn't set. diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 7cfa024de4e3..3a7ec98ef123 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -100,7 +100,7 @@ static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc, void *(*to_va)(phys_addr_t phys)) { - phys_addr_t *p = to_va(mc->head); + phys_addr_t *p = to_va(mc->head & PAGE_MASK); if (!mc->nr_pages) return NULL; @@ -615,8 +615,6 @@ struct cpu_sve_state { struct kvm_host_data { #define KVM_HOST_DATA_FLAG_HAS_SPE 0 #define KVM_HOST_DATA_FLAG_HAS_TRBE 1 -#define KVM_HOST_DATA_FLAG_HOST_SVE_ENABLED 2 -#define KVM_HOST_DATA_FLAG_HOST_SME_ENABLED 3 #define KVM_HOST_DATA_FLAG_TRBE_ENABLED 4 #define KVM_HOST_DATA_FLAG_EL1_TRACING_CONFIGURED 5 unsigned long flags; @@ -624,23 +622,13 @@ struct kvm_host_data { struct kvm_cpu_context host_ctxt; /* - * All pointers in this union are hyp VA. + * Hyp VA. * sve_state is only used in pKVM and if system_supports_sve(). */ - union { - struct user_fpsimd_state *fpsimd_state; - struct cpu_sve_state *sve_state; - }; - - union { - /* HYP VA pointer to the host storage for FPMR */ - u64 *fpmr_ptr; - /* - * Used by pKVM only, as it needs to provide storage - * for the host - */ - u64 fpmr; - }; + struct cpu_sve_state *sve_state; + + /* Used by pKVM only. */ + u64 fpmr; /* Ownership of the FP regs */ enum { diff --git a/arch/arm64/kernel/cacheinfo.c b/arch/arm64/kernel/cacheinfo.c index d9c9218fa1fd..309942b06c5b 100644 --- a/arch/arm64/kernel/cacheinfo.c +++ b/arch/arm64/kernel/cacheinfo.c @@ -101,16 +101,18 @@ int populate_cache_leaves(unsigned int cpu) unsigned int level, idx; enum cache_type type; struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); - struct cacheinfo *this_leaf = this_cpu_ci->info_list; + struct cacheinfo *infos = this_cpu_ci->info_list; for (idx = 0, level = 1; level <= this_cpu_ci->num_levels && - idx < this_cpu_ci->num_leaves; idx++, level++) { + idx < this_cpu_ci->num_leaves; level++) { type = get_cache_type(level); if (type == CACHE_TYPE_SEPARATE) { - ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); - ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); + if (idx + 1 >= this_cpu_ci->num_leaves) + break; + ci_leaf_init(&infos[idx++], CACHE_TYPE_DATA, level); + ci_leaf_init(&infos[idx++], CACHE_TYPE_INST, level); } else { - ci_leaf_init(this_leaf++, type, level); + ci_leaf_init(&infos[idx++], type, level); } } return 0; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 4eb7c6698ae4..d561cf3b8ac7 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -3091,6 +3091,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG), + HWCAP_CAP(ID_AA64ISAR3_EL1, FPRCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_FPRCVT), HWCAP_CAP(ID_AA64PFR0_EL1, FP, IMP, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(ID_AA64PFR0_EL1, FP, FP16, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD), @@ -3180,8 +3181,6 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8), - HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4), HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), @@ -3192,6 +3191,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4), HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM8), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM4), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), #ifdef CONFIG_ARM64_POE diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8c4c1a2186cc..8370d55f0353 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -562,7 +562,7 @@ static int vec_proc_do_default_vl(const struct ctl_table *table, int write, return 0; } -static struct ctl_table sve_default_vl_table[] = { +static const struct ctl_table sve_default_vl_table[] = { { .procname = "sve_default_vector_length", .mode = 0644, @@ -585,7 +585,7 @@ static int __init sve_sysctl_init(void) { return 0; } #endif /* ! (CONFIG_ARM64_SVE && CONFIG_SYSCTL) */ #if defined(CONFIG_ARM64_SME) && defined(CONFIG_SYSCTL) -static struct ctl_table sme_default_vl_table[] = { +static const struct ctl_table sme_default_vl_table[] = { { .procname = "sme_default_vector_length", .mode = 0644, @@ -1695,31 +1695,6 @@ void fpsimd_signal_preserve_current_state(void) } /* - * Called by KVM when entering the guest. - */ -void fpsimd_kvm_prepare(void) -{ - if (!system_supports_sve()) - return; - - /* - * KVM does not save host SVE state since we can only enter - * the guest from a syscall so the ABI means that only the - * non-saved SVE state needs to be saved. If we have left - * SVE enabled for performance reasons then update the task - * state to be FPSIMD only. - */ - get_cpu_fpsimd_context(); - - if (test_and_clear_thread_flag(TIF_SVE)) { - sve_to_fpsimd(current); - current->thread.fp_type = FP_STATE_FPSIMD; - } - - put_cpu_fpsimd_context(); -} - -/* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling * this function. diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 2968a33bb3bc..42faebb7b712 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -859,7 +859,7 @@ long get_tagged_addr_ctrl(struct task_struct *task) * disable it for tasks that already opted in to the relaxed ABI. */ -static struct ctl_table tagged_addr_sysctl_table[] = { +static const struct ctl_table tagged_addr_sysctl_table[] = { { .procname = "tagged_addr_disabled", .mode = 0644, diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 1a2c72f3e7f8..cb180684d10d 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -194,12 +194,19 @@ static void amu_fie_setup(const struct cpumask *cpus) int cpu; /* We are already set since the last insmod of cpufreq driver */ - if (unlikely(cpumask_subset(cpus, amu_fie_cpus))) + if (cpumask_available(amu_fie_cpus) && + unlikely(cpumask_subset(cpus, amu_fie_cpus))) return; - for_each_cpu(cpu, cpus) { + for_each_cpu(cpu, cpus) if (!freq_counters_valid(cpu)) return; + + if (!cpumask_available(amu_fie_cpus) && + !zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) { + WARN_ONCE(1, "Failed to allocate FIE cpumask for CPUs[%*pbl]\n", + cpumask_pr_args(cpus)); + return; } cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus); @@ -237,17 +244,8 @@ static struct notifier_block init_amu_fie_notifier = { static int __init init_amu_fie(void) { - int ret; - - if (!zalloc_cpumask_var(&amu_fie_cpus, GFP_KERNEL)) - return -ENOMEM; - - ret = cpufreq_register_notifier(&init_amu_fie_notifier, + return cpufreq_register_notifier(&init_amu_fie_notifier, CPUFREQ_POLICY_NOTIFIER); - if (ret) - free_cpumask_var(amu_fie_cpus); - - return ret; } core_initcall(init_amu_fie); diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 4ec32e86a8da..47ad6944f9f0 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -41,6 +41,7 @@ SECTIONS */ /DISCARD/ : { *(.note.GNU-stack .note.gnu.property) + *(.ARM.attributes) } .note : { *(.note.*) } :text :note diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index f84c71f04d9e..e73326bd3ff7 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -162,6 +162,7 @@ SECTIONS /DISCARD/ : { *(.interp .dynamic) *(.dynsym .dynstr .hash .gnu.hash) + *(.ARM.attributes) } . = KIMAGE_VADDR; diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index d3d243366536..70802e4c91cf 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -447,21 +447,19 @@ static void kvm_timer_update_status(struct arch_timer_context *ctx, bool level) static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level, struct arch_timer_context *timer_ctx) { - int ret; - kvm_timer_update_status(timer_ctx, new_level); timer_ctx->irq.level = new_level; trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_irq(timer_ctx), timer_ctx->irq.level); - if (!userspace_irqchip(vcpu->kvm)) { - ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu, - timer_irq(timer_ctx), - timer_ctx->irq.level, - timer_ctx); - WARN_ON(ret); - } + if (userspace_irqchip(vcpu->kvm)) + return; + + kvm_vgic_inject_irq(vcpu->kvm, vcpu, + timer_irq(timer_ctx), + timer_ctx->irq.level, + timer_ctx); } /* Only called for a fully emulated timer */ @@ -471,10 +469,8 @@ static void timer_emulate(struct arch_timer_context *ctx) trace_kvm_timer_emulate(ctx, should_fire); - if (should_fire != ctx->irq.level) { + if (should_fire != ctx->irq.level) kvm_timer_update_irq(ctx->vcpu, should_fire, ctx); - return; - } kvm_timer_update_status(ctx, should_fire); @@ -761,21 +757,6 @@ static void kvm_timer_vcpu_load_nested_switch(struct kvm_vcpu *vcpu, timer_irq(map->direct_ptimer), &arch_timer_irq_ops); WARN_ON_ONCE(ret); - - /* - * The virtual offset behaviour is "interesting", as it - * always applies when HCR_EL2.E2H==0, but only when - * accessed from EL1 when HCR_EL2.E2H==1. So make sure we - * track E2H when putting the HV timer in "direct" mode. - */ - if (map->direct_vtimer == vcpu_hvtimer(vcpu)) { - struct arch_timer_offset *offs = &map->direct_vtimer->offset; - - if (vcpu_el2_e2h_is_set(vcpu)) - offs->vcpu_offset = NULL; - else - offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2); - } } } @@ -976,31 +957,21 @@ void kvm_timer_sync_nested(struct kvm_vcpu *vcpu) * which allows trapping of the timer registers even with NV2. * Still, this is still worse than FEAT_NV on its own. Meh. */ - if (!vcpu_el2_e2h_is_set(vcpu)) { - if (cpus_have_final_cap(ARM64_HAS_ECV)) - return; - - /* - * A non-VHE guest hypervisor doesn't have any direct access - * to its timers: the EL2 registers trap (and the HW is - * fully emulated), while the EL0 registers access memory - * despite the access being notionally direct. Boo. - * - * We update the hardware timer registers with the - * latest value written by the guest to the VNCR page - * and let the hardware take care of the rest. - */ - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CTL_EL0), SYS_CNTV_CTL); - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTV_CVAL_EL0), SYS_CNTV_CVAL); - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CTL_EL0), SYS_CNTP_CTL); - write_sysreg_el0(__vcpu_sys_reg(vcpu, CNTP_CVAL_EL0), SYS_CNTP_CVAL); - } else { + if (!cpus_have_final_cap(ARM64_HAS_ECV)) { /* * For a VHE guest hypervisor, the EL2 state is directly - * stored in the host EL1 timers, while the emulated EL0 + * stored in the host EL1 timers, while the emulated EL1 * state is stored in the VNCR page. The latter could have * been updated behind our back, and we must reset the * emulation of the timers. + * + * A non-VHE guest hypervisor doesn't have any direct access + * to its timers: the EL2 registers trap despite being + * notionally direct (we use the EL1 HW, as for VHE), while + * the EL1 registers access memory. + * + * In both cases, process the emulated timers on each guest + * exit. Boo. */ struct timer_map map; get_timer_map(vcpu, &map); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 646e806c6ca6..b8e55a441282 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2290,6 +2290,19 @@ static int __init init_subsystems(void) break; case -ENODEV: case -ENXIO: + /* + * No VGIC? No pKVM for you. + * + * Protected mode assumes that VGICv3 is present, so no point + * in trying to hobble along if vgic initialization fails. + */ + if (is_protected_kvm_enabled()) + goto out; + + /* + * Otherwise, userspace could choose to implement a GIC for its + * guest on non-cooperative hardware. + */ vgic_present = false; err = 0; break; @@ -2400,6 +2413,13 @@ static void kvm_hyp_init_symbols(void) kvm_nvhe_sym(id_aa64smfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64SMFR0_EL1); kvm_nvhe_sym(__icache_flags) = __icache_flags; kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; + + /* + * Flush entire BSS since part of its data containing init symbols is read + * while the MMU is off. + */ + kvm_flush_dcache_to_poc(kvm_ksym_ref(__hyp_bss_start), + kvm_ksym_ref(__hyp_bss_end) - kvm_ksym_ref(__hyp_bss_start)); } static int __init kvm_hyp_init_protection(u32 hyp_va_bits) @@ -2461,14 +2481,6 @@ static void finalize_init_hyp_mode(void) per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state); } - } else { - for_each_possible_cpu(cpu) { - struct user_fpsimd_state *fpsimd_state; - - fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs; - per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state = - kern_hyp_va(fpsimd_state); - } } } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 4d3d1a2eb157..7f6e43d25691 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -54,50 +54,18 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (!system_supports_fpsimd()) return; - fpsimd_kvm_prepare(); - /* - * We will check TIF_FOREIGN_FPSTATE just before entering the - * guest in kvm_arch_vcpu_ctxflush_fp() and override this to - * FP_STATE_FREE if the flag set. + * Ensure that any host FPSIMD/SVE/SME state is saved and unbound such + * that the host kernel is responsible for restoring this state upon + * return to userspace, and the hyp code doesn't need to save anything. + * + * When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures + * that PSTATE.{SM,ZA} == {0,0}. */ - *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; - *host_data_ptr(fpsimd_state) = kern_hyp_va(¤t->thread.uw.fpsimd_state); - *host_data_ptr(fpmr_ptr) = kern_hyp_va(¤t->thread.uw.fpmr); - - host_data_clear_flag(HOST_SVE_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) - host_data_set_flag(HOST_SVE_ENABLED); - - if (system_supports_sme()) { - host_data_clear_flag(HOST_SME_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) - host_data_set_flag(HOST_SME_ENABLED); - - /* - * If PSTATE.SM is enabled then save any pending FP - * state and disable PSTATE.SM. If we leave PSTATE.SM - * enabled and the guest does not enable SME via - * CPACR_EL1.SMEN then operations that should be valid - * may generate SME traps from EL1 to EL1 which we - * can't intercept and which would confuse the guest. - * - * Do the same for PSTATE.ZA in the case where there - * is state in the registers which has not already - * been saved, this is very unlikely to happen. - */ - if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { - *host_data_ptr(fp_owner) = FP_STATE_FREE; - fpsimd_save_and_flush_cpu_state(); - } - } + fpsimd_save_and_flush_cpu_state(); + *host_data_ptr(fp_owner) = FP_STATE_FREE; - /* - * If normal guests gain SME support, maintain this behavior for pKVM - * guests, which don't support SME. - */ - WARN_ON(is_protected_kvm_enabled() && system_supports_sme() && - read_sysreg_s(SYS_SVCR)); + WARN_ON_ONCE(system_supports_sme() && read_sysreg_s(SYS_SVCR)); } /* @@ -162,52 +130,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); - /* - * If we have VHE then the Hyp code will reset CPACR_EL1 to - * the default value and we need to reenable SME. - */ - if (has_vhe() && system_supports_sme()) { - /* Also restore EL0 state seen on entry */ - if (host_data_test_flag(HOST_SME_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN); - else - sysreg_clear_set(CPACR_EL1, - CPACR_EL1_SMEN_EL0EN, - CPACR_EL1_SMEN_EL1EN); - isb(); - } - if (guest_owns_fp_regs()) { - if (vcpu_has_sve(vcpu)) { - u64 zcr = read_sysreg_el1(SYS_ZCR); - - /* - * If the vCPU is in the hyp context then ZCR_EL1 is - * loaded with its vEL2 counterpart. - */ - __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr; - - /* - * Restore the VL that was saved when bound to the CPU, - * which is the maximum VL for the guest. Because the - * layout of the data when saving the sve state depends - * on the VL, we need to use a consistent (i.e., the - * maximum) VL. - * Note that this means that at guest exit ZCR_EL1 is - * not necessarily the same as on guest entry. - * - * ZCR_EL2 holds the guest hypervisor's VL when running - * a nested guest, which could be smaller than the - * max for the vCPU. Similar to above, we first need to - * switch to a VL consistent with the layout of the - * vCPU's SVE state. KVM support for NV implies VHE, so - * using the ZCR_EL1 alias is safe. - */ - if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) - sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, - SYS_ZCR_EL1); - } - /* * Flush (save and invalidate) the fpsimd/sve state so that if * the host tries to use fpsimd/sve, it's not using stale data @@ -219,18 +142,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) * when needed. */ fpsimd_save_and_flush_cpu_state(); - } else if (has_vhe() && system_supports_sve()) { - /* - * The FPSIMD/SVE state in the CPU has not been touched, and we - * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been - * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE - * for EL0. To avoid spurious traps, restore the trap state - * seen by kvm_arch_vcpu_load_fp(): - */ - if (host_data_test_flag(HOST_SVE_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); - else - sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } local_irq_restore(flags); diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 4433a234aa9b..9f4e8d68ab50 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN alternative_else_nop_endif mrs x1, isr_el1 cbz x1, 1f + + // Ensure that __guest_enter() always provides a context + // synchronization event so that callers don't need ISBs for anything + // that would usually be synchonized by the ERET. + isb mov x0, #ARM_EXCEPTION_IRQ ret diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index f838a45665f2..23bbe28eaaf9 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -326,7 +326,7 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); } -static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2); @@ -375,7 +375,87 @@ static inline void __hyp_sve_save_host(void) true); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu); +static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + if (vcpu_has_sve(vcpu)) { + /* A guest hypervisor may restrict the effective max VL. */ + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) + zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2); + else + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)); + write_sysreg_el1(zcr_el1, SYS_ZCR); + } +} + +static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + /* + * When the guest owns the FP regs, we know that guest+hyp traps for + * any FPSIMD/SVE/SME features exposed to the guest have been disabled + * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd() + * prior to __guest_entry(). As __guest_entry() guarantees a context + * synchronization event, we don't need an ISB here to avoid taking + * traps for anything that was exposed to the guest. + */ + if (vcpu_has_sve(vcpu)) { + zcr_el1 = read_sysreg_el1(SYS_ZCR); + __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1; + + /* + * The guest's state is always saved using the guest's max VL. + * Ensure that the host has the guest's max VL active such that + * the host can save the guest's state lazily, but don't + * artificially restrict the host to the guest's max VL. + */ + if (has_vhe()) { + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + } else { + zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el1(zcr_el1, SYS_ZCR); + } + } +} + +static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) +{ + /* + * Non-protected kvm relies on the host restoring its sve state. + * Protected kvm restores the host's sve state as not to reveal that + * fpsimd was used by a guest nor leak upper sve bits. + */ + if (system_supports_sve()) { + __hyp_sve_save_host(); + + /* Re-enable SVE traps if not supported for the guest vcpu. */ + if (!vcpu_has_sve(vcpu)) + cpacr_clear_set(CPACR_EL1_ZEN, 0); + + } else { + __fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs)); + } + + if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) + *host_data_ptr(fpmr) = read_sysreg_s(SYS_FPMR); +} + /* * We trap the first access to the FP/SIMD to save the host context and @@ -383,7 +463,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu); * If FP/SIMD is not implemented, handle the trap and inject an undefined * instruction exception to the guest. Similarly for trapped SVE accesses. */ -static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { bool sve_guest; u8 esr_ec; @@ -425,7 +505,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) isb(); /* Write out the host state if it's in the registers */ - if (host_owns_fp_regs()) + if (is_protected_kvm_enabled() && host_owns_fp_regs()) kvm_hyp_save_fpsimd_host(vcpu); /* Restore the guest state */ @@ -501,9 +581,22 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) return true; } +/* Open-coded version of timer_get_offset() to allow for kern_hyp_va() */ +static inline u64 hyp_timer_get_offset(struct arch_timer_context *ctxt) +{ + u64 offset = 0; + + if (ctxt->offset.vm_offset) + offset += *kern_hyp_va(ctxt->offset.vm_offset); + if (ctxt->offset.vcpu_offset) + offset += *kern_hyp_va(ctxt->offset.vcpu_offset); + + return offset; +} + static inline u64 compute_counter_value(struct arch_timer_context *ctxt) { - return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt); + return arch_timer_read_cntpct_el0() - hyp_timer_get_offset(ctxt); } static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu) @@ -587,7 +680,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) return true; } -static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) { if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && handle_tx2_tvm(vcpu)) @@ -607,7 +700,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) { if (static_branch_unlikely(&vgic_v3_cpuif_trap) && __vgic_v3_perform_cpuif_access(vcpu) == 1) @@ -616,19 +709,18 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, + u64 *exit_code) { if (!__populate_fault_info(vcpu)) return true; return false; } -static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); -static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); +#define kvm_hyp_handle_iabt_low kvm_hyp_handle_memory_fault +#define kvm_hyp_handle_watchpt_low kvm_hyp_handle_memory_fault -static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) { if (kvm_hyp_handle_memory_fault(vcpu, exit_code)) return true; @@ -658,23 +750,16 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); - -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); - /* * Allow the hypervisor to handle the exit with an exit handler if it has one. * * Returns true if the hypervisor handled the exit, and control should go back * to the guest, or false if it hasn't. */ -static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); - exit_handler_fn fn; - - fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; - + exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; if (fn) return fn(vcpu, exit_code); @@ -704,20 +789,9 @@ static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code * the guest, false when we should restore the host state and return to the * main run loop. */ -static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - /* - * Save PSTATE early so that we can evaluate the vcpu mode - * early on. - */ - synchronize_vcpu_pstate(vcpu, exit_code); - - /* - * Check whether we want to repaint the state one way or - * another. - */ - early_exit_filter(vcpu, exit_code); - if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); @@ -747,7 +821,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) goto exit; /* Check if there's an exit handler and allow it to handle the exit. */ - if (kvm_hyp_handle_exit(vcpu, exit_code)) + if (kvm_hyp_handle_exit(vcpu, exit_code, handlers)) goto guest; exit: /* Return to the host kernel and handle the exit */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 5c134520e180..2c37680d954c 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -5,6 +5,7 @@ */ #include <hyp/adjust_pc.h> +#include <hyp/switch.h> #include <asm/pgtable-types.h> #include <asm/kvm_asm.h> @@ -83,7 +84,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (system_supports_sve()) __hyp_sve_restore_host(); else - __fpsimd_restore_state(*host_data_ptr(fpsimd_state)); + __fpsimd_restore_state(host_data_ptr(host_ctxt.fp_regs)); if (has_fpmr) write_sysreg_s(*host_data_ptr(fpmr), SYS_FPMR); @@ -91,11 +92,34 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; } +static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + hyp_vcpu->vcpu.arch.debug_owner = host_vcpu->arch.debug_owner; + + if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu)) + hyp_vcpu->vcpu.arch.vcpu_debug_state = host_vcpu->arch.vcpu_debug_state; + else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu)) + hyp_vcpu->vcpu.arch.external_debug_state = host_vcpu->arch.external_debug_state; +} + +static void sync_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu)) + host_vcpu->arch.vcpu_debug_state = hyp_vcpu->vcpu.arch.vcpu_debug_state; + else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu)) + host_vcpu->arch.external_debug_state = hyp_vcpu->vcpu.arch.external_debug_state; +} + static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) { struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; fpsimd_sve_flush(); + flush_debug_state(hyp_vcpu); hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt; @@ -123,6 +147,7 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) unsigned int i; fpsimd_sve_sync(&hyp_vcpu->vcpu); + sync_debug_state(hyp_vcpu); host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt; @@ -200,8 +225,12 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) sync_hyp_vcpu(hyp_vcpu); } else { + struct kvm_vcpu *vcpu = kern_hyp_va(host_vcpu); + /* The host is fully trusted, run its vCPU directly. */ - ret = __kvm_vcpu_run(kern_hyp_va(host_vcpu)); + fpsimd_lazy_switch_to_guest(vcpu); + ret = __kvm_vcpu_run(vcpu); + fpsimd_lazy_switch_to_host(vcpu); } out: cpu_reg(host_ctxt, 1) = ret; @@ -651,12 +680,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) case ESR_ELx_EC_SMC64: handle_host_smc(host_ctxt); break; - case ESR_ELx_EC_SVE: - cpacr_clear_set(0, CPACR_EL1_ZEN); - isb(); - sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, - SYS_ZCR_EL2); - break; case ESR_ELx_EC_IABT_LOW: case ESR_ELx_EC_DABT_LOW: handle_host_mem_abort(host_ctxt); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 7ad7b133b81a..19c3c631708c 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -943,10 +943,10 @@ static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ip ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level); if (ret) return ret; - if (level != KVM_PGTABLE_LAST_LEVEL) - return -E2BIG; if (!kvm_pte_valid(pte)) return -ENOENT; + if (level != KVM_PGTABLE_LAST_LEVEL) + return -E2BIG; state = guest_get_page_state(pte, ipa); if (state != PKVM_PAGE_SHARED_BORROWED) @@ -998,63 +998,73 @@ unlock: return ret; } -int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) +static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa) { - struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); - u64 ipa = hyp_pfn_to_phys(gfn); u64 phys; int ret; - if (prot & ~KVM_PGTABLE_PROT_RWX) - return -EINVAL; + if (!IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) + return; host_lock_component(); guest_lock_component(vm); ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); guest_unlock_component(vm); host_unlock_component(); - return ret; + WARN_ON(ret && ret != -ENOENT); } -int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) { + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; int ret; - host_lock_component(); - guest_lock_component(vm); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); guest_unlock_component(vm); - host_unlock_component(); return ret; } -int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +int __pkvm_host_wrprotect_guest(u64 gfn, struct pkvm_hyp_vm *vm) { u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; int ret; - host_lock_component(); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + + assert_host_shared_guest(vm, ipa); guest_lock_component(vm); + ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, PAGE_SIZE); + guest_unlock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); + return ret; +} + +int __pkvm_host_test_clear_young_guest(u64 gfn, bool mkold, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + int ret; + + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, PAGE_SIZE, mkold); guest_unlock_component(vm); - host_unlock_component(); return ret; } @@ -1063,18 +1073,14 @@ int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu) { struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); u64 ipa = hyp_pfn_to_phys(gfn); - u64 phys; - int ret; - - host_lock_component(); - guest_lock_component(vm); - ret = __check_host_shared_guest(vm, &phys, ipa); - if (!ret) - kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + assert_host_shared_guest(vm, ipa); + guest_lock_component(vm); + kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); guest_unlock_component(vm); - host_unlock_component(); - return ret; + return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6c846d033d24..7d2ba6ef0261 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -39,6 +39,9 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) { u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */ + if (!guest_owns_fp_regs()) + __activate_traps_fpsimd32(vcpu); + if (has_hvhe()) { val |= CPACR_EL1_TTA; @@ -47,6 +50,8 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (vcpu_has_sve(vcpu)) val |= CPACR_EL1_ZEN; } + + write_sysreg(val, cpacr_el1); } else { val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1; @@ -61,12 +66,32 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (!guest_owns_fp_regs()) val |= CPTR_EL2_TFP; + + write_sysreg(val, cptr_el2); } +} - if (!guest_owns_fp_regs()) - __activate_traps_fpsimd32(vcpu); +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + if (has_hvhe()) { + u64 val = CPACR_EL1_FPEN; + + if (cpus_have_final_cap(ARM64_SVE)) + val |= CPACR_EL1_ZEN; + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN; - kvm_write_cptr_el2(val); + write_sysreg(val, cpacr_el1); + } else { + u64 val = CPTR_NVHE_EL2_RES1; + + if (!cpus_have_final_cap(ARM64_SVE)) + val |= CPTR_EL2_TZ; + if (!cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; + + write_sysreg(val, cptr_el2); + } } static void __activate_traps(struct kvm_vcpu *vcpu) @@ -119,7 +144,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); - kvm_reset_cptr_el2(vcpu); + __deactivate_cptr_traps(vcpu); write_sysreg(__kvm_hyp_host_vector, vbar_el2); } @@ -192,34 +217,6 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_handle_pvm_sysreg(vcpu, exit_code)); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - /* - * Non-protected kvm relies on the host restoring its sve state. - * Protected kvm restores the host's sve state as not to reveal that - * fpsimd was used by a guest nor leak upper sve bits. - */ - if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) { - __hyp_sve_save_host(); - - /* Re-enable SVE traps if not supported for the guest vcpu. */ - if (!vcpu_has_sve(vcpu)) - cpacr_clear_set(CPACR_EL1_ZEN, 0); - - } else { - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - } - - if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) { - u64 val = read_sysreg_s(SYS_FPMR); - - if (unlikely(is_protected_kvm_enabled())) - *host_data_ptr(fpmr) = val; - else - **host_data_ptr(fpmr_ptr) = val; - } -} - static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, @@ -251,19 +248,21 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) return hyp_exit_handlers; } -/* - * Some guests (e.g., protected VMs) are not be allowed to run in AArch32. - * The ARMv8 architecture does not give the hypervisor a mechanism to prevent a - * guest from dropping to AArch32 EL0 if implemented by the CPU. If the - * hypervisor spots a guest in such a state ensure it is handled, and don't - * trust the host to spot or fix it. The check below is based on the one in - * kvm_arch_vcpu_ioctl_run(). - * - * Returns false if the guest ran in AArch32 when it shouldn't have, and - * thus should exit to the host, or true if a the guest run loop can continue. - */ -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { + const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); + + synchronize_vcpu_pstate(vcpu, exit_code); + + /* + * Some guests (e.g., protected VMs) are not be allowed to run in + * AArch32. The ARMv8 architecture does not give the hypervisor a + * mechanism to prevent a guest from dropping to AArch32 EL0 if + * implemented by the CPU. If the hypervisor spots a guest in such a + * state ensure it is handled, and don't trust the host to spot or fix + * it. The check below is based on the one in + * kvm_arch_vcpu_ioctl_run(). + */ if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) { /* * As we have caught the guest red-handed, decide that it isn't @@ -276,6 +275,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); *exit_code |= ARM_EXCEPTION_IL; } + + return __fixup_guest_exit(vcpu, exit_code, handlers); } /* Switch to the guest for legacy non-VHE systems */ diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index b5b9dbaf1fdd..647737d6e8d0 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -136,6 +136,16 @@ write: write_sysreg(val, cpacr_el1); } +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN; + + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN_EL1EN; + + write_sysreg(val, cpacr_el1); +} + static void __activate_traps(struct kvm_vcpu *vcpu) { u64 val; @@ -207,7 +217,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); - kvm_reset_cptr_el2(vcpu); + __deactivate_cptr_traps(vcpu); if (!arm64_kernel_unmapped_at_el0()) host_vectors = __this_cpu_read(this_cpu_vector); @@ -413,14 +423,6 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - - if (kvm_has_fpmr(vcpu->kvm)) - **host_data_ptr(fpmr_ptr) = read_sysreg_s(SYS_FPMR); -} - static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code) { int ret = -EINVAL; @@ -538,13 +540,10 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { - return hyp_exit_handlers; -} + synchronize_vcpu_pstate(vcpu, exit_code); -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) -{ /* * If we were in HYP context on entry, adjust the PSTATE view * so that the usual helpers work correctly. @@ -564,6 +563,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); *vcpu_cpsr(vcpu) |= mode; } + + return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers); } /* Switch to the guest for VHE systems running in EL2 */ @@ -578,6 +579,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_save_host_state_vhe(host_ctxt); + fpsimd_lazy_switch_to_guest(vcpu); + /* * Note that ARM erratum 1165522 requires us to configure both stage 1 * and stage 2 translation for the guest context before we clear @@ -602,6 +605,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __deactivate_traps(vcpu); + fpsimd_lazy_switch_to_host(vcpu); + sysreg_restore_host_state_vhe(host_ctxt); if (guest_owns_fp_regs()) diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 33d2ace68665..0c9387d2f507 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -67,26 +67,27 @@ int kvm_vcpu_init_nested(struct kvm_vcpu *vcpu) if (!tmp) return -ENOMEM; + swap(kvm->arch.nested_mmus, tmp); + /* * If we went through a realocation, adjust the MMU back-pointers in * the previously initialised kvm_pgtable structures. */ if (kvm->arch.nested_mmus != tmp) for (int i = 0; i < kvm->arch.nested_mmus_size; i++) - tmp[i].pgt->mmu = &tmp[i]; + kvm->arch.nested_mmus[i].pgt->mmu = &kvm->arch.nested_mmus[i]; for (int i = kvm->arch.nested_mmus_size; !ret && i < num_mmus; i++) - ret = init_nested_s2_mmu(kvm, &tmp[i]); + ret = init_nested_s2_mmu(kvm, &kvm->arch.nested_mmus[i]); if (ret) { for (int i = kvm->arch.nested_mmus_size; i < num_mmus; i++) - kvm_free_stage2_pgd(&tmp[i]); + kvm_free_stage2_pgd(&kvm->arch.nested_mmus[i]); return ret; } kvm->arch.nested_mmus_size = num_mmus; - kvm->arch.nested_mmus = tmp; return 0; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index f6cd1ea7fb55..82430c1e1dd0 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1452,6 +1452,16 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, return true; } +static bool access_hv_timer(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (!vcpu_el2_e2h_is_set(vcpu)) + return undef_access(vcpu, p, r); + + return access_arch_timer(vcpu, p, r); +} + static s64 kvm_arm64_ftr_safe_value(u32 id, const struct arm64_ftr_bits *ftrp, s64 new, s64 cur) { @@ -3103,9 +3113,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(CNTHP_CTL_EL2, access_arch_timer, reset_val, 0), EL2_REG(CNTHP_CVAL_EL2, access_arch_timer, reset_val, 0), - { SYS_DESC(SYS_CNTHV_TVAL_EL2), access_arch_timer }, - EL2_REG(CNTHV_CTL_EL2, access_arch_timer, reset_val, 0), - EL2_REG(CNTHV_CVAL_EL2, access_arch_timer, reset_val, 0), + { SYS_DESC(SYS_CNTHV_TVAL_EL2), access_hv_timer }, + EL2_REG(CNTHV_CTL_EL2, access_hv_timer, reset_val, 0), + EL2_REG(CNTHV_CVAL_EL2, access_hv_timer, reset_val, 0), { SYS_DESC(SYS_CNTKCTL_EL12), access_cntkctl_el12 }, diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index bc7e22ab5d81..775461cf2d2d 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -34,9 +34,9 @@ * * CPU Interface: * - * - kvm_vgic_vcpu_init(): initialization of static data that - * doesn't depend on any sizing information or emulation type. No - * allocation is allowed there. + * - kvm_vgic_vcpu_init(): initialization of static data that doesn't depend + * on any sizing information. Private interrupts are allocated if not + * already allocated at vgic-creation time. */ /* EARLY INIT */ @@ -58,6 +58,8 @@ void kvm_vgic_early_init(struct kvm *kvm) /* CREATION */ +static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type); + /** * kvm_vgic_create: triggered by the instantiation of the VGIC device by * user space, either through the legacy KVM_CREATE_IRQCHIP ioctl (v2 only) @@ -112,6 +114,22 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) goto out_unlock; } + kvm_for_each_vcpu(i, vcpu, kvm) { + ret = vgic_allocate_private_irqs_locked(vcpu, type); + if (ret) + break; + } + + if (ret) { + kvm_for_each_vcpu(i, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + kfree(vgic_cpu->private_irqs); + vgic_cpu->private_irqs = NULL; + } + + goto out_unlock; + } + kvm->arch.vgic.in_kernel = true; kvm->arch.vgic.vgic_model = type; @@ -180,7 +198,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) return 0; } -static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu) +static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu, u32 type) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; int i; @@ -218,17 +236,28 @@ static int vgic_allocate_private_irqs_locked(struct kvm_vcpu *vcpu) /* PPIs */ irq->config = VGIC_CONFIG_LEVEL; } + + switch (type) { + case KVM_DEV_TYPE_ARM_VGIC_V3: + irq->group = 1; + irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + break; + case KVM_DEV_TYPE_ARM_VGIC_V2: + irq->group = 0; + irq->targets = BIT(vcpu->vcpu_id); + break; + } } return 0; } -static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu) +static int vgic_allocate_private_irqs(struct kvm_vcpu *vcpu, u32 type) { int ret; mutex_lock(&vcpu->kvm->arch.config_lock); - ret = vgic_allocate_private_irqs_locked(vcpu); + ret = vgic_allocate_private_irqs_locked(vcpu, type); mutex_unlock(&vcpu->kvm->arch.config_lock); return ret; @@ -258,7 +287,7 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) if (!irqchip_in_kernel(vcpu->kvm)) return 0; - ret = vgic_allocate_private_irqs(vcpu); + ret = vgic_allocate_private_irqs(vcpu, dist->vgic_model); if (ret) return ret; @@ -295,7 +324,7 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i; + int ret = 0; unsigned long idx; lockdep_assert_held(&kvm->arch.config_lock); @@ -315,35 +344,6 @@ int vgic_init(struct kvm *kvm) if (ret) goto out; - /* Initialize groups on CPUs created before the VGIC type was known */ - kvm_for_each_vcpu(idx, vcpu, kvm) { - ret = vgic_allocate_private_irqs_locked(vcpu); - if (ret) - goto out; - - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, i); - - switch (dist->vgic_model) { - case KVM_DEV_TYPE_ARM_VGIC_V3: - irq->group = 1; - irq->mpidr = kvm_vcpu_get_mpidr_aff(vcpu); - break; - case KVM_DEV_TYPE_ARM_VGIC_V2: - irq->group = 0; - irq->targets = 1U << idx; - break; - default: - ret = -EINVAL; - } - - vgic_put_irq(kvm, irq); - - if (ret) - goto out; - } - } - /* * If we have GICv4.1 enabled, unconditionally request enable the * v4 support so that we get HW-accelerated vSGIs. Otherwise, only diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 19c67ed1a21f..18543b603c77 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -162,6 +162,13 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp, unsigned long next; unsigned long addr = start; + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_p4dp = trans_alloc(info); + if (!dst_p4dp) + return -ENOMEM; + pgd_populate(NULL, dst_pgdp, dst_p4dp); + } + dst_p4dp = p4d_offset(dst_pgdp, start); src_p4dp = p4d_offset(src_pgdp, start); do { diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h index bf6cf5579cf4..9c58fb81f7fd 100644 --- a/arch/hexagon/include/asm/cmpxchg.h +++ b/arch/hexagon/include/asm/cmpxchg.h @@ -56,7 +56,7 @@ __arch_xchg(unsigned long x, volatile void *ptr, int size) __typeof__(ptr) __ptr = (ptr); \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ - __typeof__(*(ptr)) __oldval = 0; \ + __typeof__(*(ptr)) __oldval = (__typeof__(*(ptr))) 0; \ \ asm volatile( \ "1: %0 = memw_locked(%1);\n" \ diff --git a/arch/hexagon/include/asm/setup.h b/arch/hexagon/include/asm/setup.h new file mode 100644 index 000000000000..9f2749cd4052 --- /dev/null +++ b/arch/hexagon/include/asm/setup.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 and + * only version 2 as published by the Free Software Foundation. + */ + +#ifndef _ASM_HEXAGON_SETUP_H +#define _ASM_HEXAGON_SETUP_H + +#include <linux/init.h> +#include <uapi/asm/setup.h> + +extern char external_cmdline_buffer; + +void __init setup_arch_memory(void); + +#endif diff --git a/arch/hexagon/include/uapi/asm/setup.h b/arch/hexagon/include/uapi/asm/setup.h index 8ce9428b1583..598f74f671f6 100644 --- a/arch/hexagon/include/uapi/asm/setup.h +++ b/arch/hexagon/include/uapi/asm/setup.h @@ -17,19 +17,9 @@ * 02110-1301, USA. */ -#ifndef _ASM_SETUP_H -#define _ASM_SETUP_H - -#ifdef __KERNEL__ -#include <linux/init.h> -#else -#define __init -#endif +#ifndef _UAPI_ASM_HEXAGON_SETUP_H +#define _UAPI_ASM_HEXAGON_SETUP_H #include <asm-generic/setup.h> -extern char external_cmdline_buffer; - -void __init setup_arch_memory(void); - #endif diff --git a/arch/hexagon/kernel/time.c b/arch/hexagon/kernel/time.c index f0f207e2a694..6f851e1cd4ee 100644 --- a/arch/hexagon/kernel/time.c +++ b/arch/hexagon/kernel/time.c @@ -170,8 +170,7 @@ static void __init time_init_deferred(void) ce_dev->cpumask = cpu_all_mask; - if (!resource) - resource = rtos_timer_device.resource; + resource = rtos_timer_device.resource; /* ioremap here means this has to run later, after paging init */ rtos_timer = ioremap(resource->start, resource_size(resource)); diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index 75e062722d28..e732aa01c2ff 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -135,7 +135,7 @@ static void do_show_stack(struct task_struct *task, unsigned long *fp, } /* Attempt to continue past exception. */ - if (0 == newfp) { + if (!newfp) { struct pt_regs *regs = (struct pt_regs *) (((void *)fp) + 8); @@ -195,8 +195,10 @@ int die(const char *str, struct pt_regs *regs, long err) printk(KERN_EMERG "Oops: %s[#%d]:\n", str, ++die.counter); if (notify_die(DIE_OOPS, str, regs, err, pt_cause(regs), SIGSEGV) == - NOTIFY_STOP) + NOTIFY_STOP) { + spin_unlock_irq(&die.lock); return 1; + } print_modules(); show_regs(regs); diff --git a/arch/loongarch/include/asm/cpu-info.h b/arch/loongarch/include/asm/cpu-info.h index 35e0a230a484..7f5bc0ad9d50 100644 --- a/arch/loongarch/include/asm/cpu-info.h +++ b/arch/loongarch/include/asm/cpu-info.h @@ -76,27 +76,6 @@ extern const char *__cpu_full_name[]; #define cpu_family_string() __cpu_family[raw_smp_processor_id()] #define cpu_full_name_string() __cpu_full_name[raw_smp_processor_id()] -struct seq_file; -struct notifier_block; - -extern int register_proc_cpuinfo_notifier(struct notifier_block *nb); -extern int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v); - -#define proc_cpuinfo_notifier(fn, pri) \ -({ \ - static struct notifier_block fn##_nb = { \ - .notifier_call = fn, \ - .priority = pri \ - }; \ - \ - register_proc_cpuinfo_notifier(&fn##_nb); \ -}) - -struct proc_cpuinfo_notifier_args { - struct seq_file *m; - unsigned long n; -}; - static inline bool cpus_are_siblings(int cpua, int cpub) { struct cpuinfo_loongarch *infoa = &cpu_data[cpua]; diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h index 3383c9d24e94..b87d1d5e5890 100644 --- a/arch/loongarch/include/asm/smp.h +++ b/arch/loongarch/include/asm/smp.h @@ -77,6 +77,8 @@ extern int __cpu_logical_map[NR_CPUS]; #define SMP_IRQ_WORK BIT(ACTION_IRQ_WORK) #define SMP_CLEAR_VECTOR BIT(ACTION_CLEAR_VECTOR) +struct seq_file; + struct secondary_data { unsigned long stack; unsigned long thread_info; diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 86d5d90ebefe..4f0912141781 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -18,16 +18,19 @@ .align 5 SYM_FUNC_START(__arch_cpu_idle) - /* start of rollback region */ - LONG_L t0, tp, TI_FLAGS - nop - andi t0, t0, _TIF_NEED_RESCHED - bnez t0, 1f - nop - nop - nop + /* start of idle interrupt region */ + ori t0, zero, CSR_CRMD_IE + /* idle instruction needs irq enabled */ + csrxchg t0, t0, LOONGARCH_CSR_CRMD + /* + * If an interrupt lands here; between enabling interrupts above and + * going idle on the next instruction, we must *NOT* go idle since the + * interrupt could have set TIF_NEED_RESCHED or caused an timer to need + * reprogramming. Fall through -- see handle_vint() below -- and have + * the idle loop take care of things. + */ idle 0 - /* end of rollback region */ + /* end of idle interrupt region */ 1: jr ra SYM_FUNC_END(__arch_cpu_idle) @@ -35,11 +38,10 @@ SYM_CODE_START(handle_vint) UNWIND_HINT_UNDEFINED BACKUP_T0T1 SAVE_ALL - la_abs t1, __arch_cpu_idle + la_abs t1, 1b LONG_L t0, sp, PT_ERA - /* 32 byte rollback region */ - ori t0, t0, 0x1f - xori t0, t0, 0x1f + /* 3 instructions idle interrupt region */ + ori t0, t0, 0b1100 bne t0, t1, 1f LONG_S t0, sp, PT_ERA 1: move a0, sp diff --git a/arch/loongarch/kernel/idle.c b/arch/loongarch/kernel/idle.c index 0b5dd2faeb90..54b247d8cdb6 100644 --- a/arch/loongarch/kernel/idle.c +++ b/arch/loongarch/kernel/idle.c @@ -11,7 +11,6 @@ void __cpuidle arch_cpu_idle(void) { - raw_local_irq_enable(); - __arch_cpu_idle(); /* idle instruction needs irq enabled */ + __arch_cpu_idle(); raw_local_irq_disable(); } diff --git a/arch/loongarch/kernel/proc.c b/arch/loongarch/kernel/proc.c index 6ce46d92f1f1..cea30768ae92 100644 --- a/arch/loongarch/kernel/proc.c +++ b/arch/loongarch/kernel/proc.c @@ -13,28 +13,12 @@ #include <asm/processor.h> #include <asm/time.h> -/* - * No lock; only written during early bootup by CPU 0. - */ -static RAW_NOTIFIER_HEAD(proc_cpuinfo_chain); - -int __ref register_proc_cpuinfo_notifier(struct notifier_block *nb) -{ - return raw_notifier_chain_register(&proc_cpuinfo_chain, nb); -} - -int proc_cpuinfo_notifier_call_chain(unsigned long val, void *v) -{ - return raw_notifier_call_chain(&proc_cpuinfo_chain, val, v); -} - static int show_cpuinfo(struct seq_file *m, void *v) { unsigned long n = (unsigned long) v - 1; unsigned int isa = cpu_data[n].isa_level; unsigned int version = cpu_data[n].processor_id & 0xff; unsigned int fp_version = cpu_data[n].fpu_vers; - struct proc_cpuinfo_notifier_args proc_cpuinfo_notifier_args; #ifdef CONFIG_SMP if (!cpu_online(n)) @@ -91,20 +75,13 @@ static int show_cpuinfo(struct seq_file *m, void *v) if (cpu_has_lbt_mips) seq_printf(m, " lbt_mips"); seq_printf(m, "\n"); - seq_printf(m, "Hardware Watchpoint\t: %s", - cpu_has_watch ? "yes, " : "no\n"); + seq_printf(m, "Hardware Watchpoint\t: %s", str_yes_no(cpu_has_watch)); if (cpu_has_watch) { - seq_printf(m, "iwatch count: %d, dwatch count: %d\n", + seq_printf(m, ", iwatch count: %d, dwatch count: %d", cpu_data[n].watch_ireg_count, cpu_data[n].watch_dreg_count); } - proc_cpuinfo_notifier_args.m = m; - proc_cpuinfo_notifier_args.n = n; - - raw_notifier_call_chain(&proc_cpuinfo_chain, 0, - &proc_cpuinfo_notifier_args); - - seq_printf(m, "\n"); + seq_printf(m, "\n\n"); return 0; } diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c index 1ef8c6383535..de8fa5a8a825 100644 --- a/arch/loongarch/kernel/reset.c +++ b/arch/loongarch/kernel/reset.c @@ -33,7 +33,7 @@ void machine_halt(void) console_flush_on_panic(CONSOLE_FLUSH_PENDING); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -53,7 +53,7 @@ void machine_power_off(void) #endif while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } @@ -74,6 +74,6 @@ void machine_restart(char *command) acpi_reboot(); while (true) { - __arch_cpu_idle(); + __asm__ __volatile__("idle 0" : : : "memory"); } } diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c index bf9268bf26d5..f6d3242b9234 100644 --- a/arch/loongarch/kvm/main.c +++ b/arch/loongarch/kvm/main.c @@ -303,9 +303,9 @@ int kvm_arch_enable_virtualization_cpu(void) * TOE=0: Trap on Exception. * TIT=0: Trap on Timer. */ - if (env & CSR_GCFG_GCIP_ALL) + if (env & CSR_GCFG_GCIP_SECURE) gcfg |= CSR_GCFG_GCI_SECURE; - if (env & CSR_GCFG_MATC_ROOT) + if (env & CSR_GCFG_MATP_ROOT) gcfg |= CSR_GCFG_MATC_ROOT; write_csr_gcfg(gcfg); diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S index 0c292f818492..1be185e94807 100644 --- a/arch/loongarch/kvm/switch.S +++ b/arch/loongarch/kvm/switch.S @@ -85,7 +85,7 @@ * Guest CRMD comes from separate GCSR_CRMD register */ ori t0, zero, CSR_PRMD_PIE - csrxchg t0, t0, LOONGARCH_CSR_PRMD + csrwr t0, LOONGARCH_CSR_PRMD /* Set PVM bit to setup ertn to guest context */ ori t0, zero, CSR_GSTAT_PVM diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c index fb72095c8077..20f941af3e9e 100644 --- a/arch/loongarch/kvm/vcpu.c +++ b/arch/loongarch/kvm/vcpu.c @@ -1548,9 +1548,6 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Restore timer state regardless */ kvm_restore_timer(vcpu); - - /* Control guest page CCA attribute */ - change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT); kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); /* Restore hardware PMU CSRs */ diff --git a/arch/loongarch/lib/csum.c b/arch/loongarch/lib/csum.c index a5e84b403c3b..df309ae4045d 100644 --- a/arch/loongarch/lib/csum.c +++ b/arch/loongarch/lib/csum.c @@ -25,7 +25,7 @@ unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len) const u64 *ptr; u64 data, sum64 = 0; - if (unlikely(len == 0)) + if (unlikely(len <= 0)) return 0; offset = (unsigned long)buff & 7; diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c index bf8678248444..99165903908a 100644 --- a/arch/loongarch/mm/pageattr.c +++ b/arch/loongarch/mm/pageattr.c @@ -3,6 +3,7 @@ * Copyright (C) 2024 Loongson Technology Corporation Limited */ +#include <linux/memblock.h> #include <linux/pagewalk.h> #include <linux/pgtable.h> #include <asm/set_memory.h> @@ -167,7 +168,7 @@ bool kernel_page_present(struct page *page) unsigned long addr = (unsigned long)page_address(page); if (addr < vm_map_base) - return true; + return memblock_is_memory(__pa(addr)); pgd = pgd_offset_k(addr); if (pgd_none(pgdp_get(pgd))) diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 8acfa66e1095..dbf2ea561c85 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -626,6 +626,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 35e9a0872304..b0fd199cc0a4 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -583,6 +583,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index 32891ddd3cc5..bb5b2d3b6c10 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -603,6 +603,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index ca276f0db3dd..8315a13bab73 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -575,6 +575,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index e83f14fe1a4f..350370657e5f 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -585,6 +585,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 6b58be24da79..f942b4755702 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -602,6 +602,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 0e8d24f82565..b1eaad02efab 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -689,6 +689,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 24a7608c13ac..6309a4442bb3 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -575,6 +575,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index c415f75821f3..3feb0731f814 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -576,6 +576,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 2c715a8ff551..ea04b1b0da7d 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -592,6 +592,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 15ff37fcccbf..f52d9af92153 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -572,6 +572,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 40a44bf9f48d..f348447824da 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -573,6 +573,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 4a2b40ce39e0..85fa9962266a 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -27,8 +27,8 @@ */ struct pt_regs { #ifdef CONFIG_32BIT - /* Pad bytes for argument save space on the stack. */ - unsigned long pad0[8]; + /* Saved syscall stack arguments; entries 0-3 unused. */ + unsigned long args[8]; #endif /* Saved main processor registers. */ diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index ebdf4d910af2..056aa1b713e2 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -57,37 +57,21 @@ static inline void mips_syscall_update_nr(struct task_struct *task, static inline void mips_get_syscall_arg(unsigned long *arg, struct task_struct *task, struct pt_regs *regs, unsigned int n) { - unsigned long usp __maybe_unused = regs->regs[29]; - +#ifdef CONFIG_32BIT switch (n) { case 0: case 1: case 2: case 3: *arg = regs->regs[4 + n]; - - return; - -#ifdef CONFIG_32BIT - case 4: case 5: case 6: case 7: - get_user(*arg, (int *)usp + n); return; -#endif - -#ifdef CONFIG_64BIT case 4: case 5: case 6: case 7: -#ifdef CONFIG_MIPS32_O32 - if (test_tsk_thread_flag(task, TIF_32BIT_REGS)) - get_user(*arg, (int *)usp + n); - else -#endif - *arg = regs->regs[4 + n]; - + *arg = regs->args[n]; return; -#endif - - default: - BUG(); } - - unreachable(); +#else + *arg = regs->regs[4 + n]; + if ((IS_ENABLED(CONFIG_MIPS32_O32) && + test_tsk_thread_flag(task, TIF_32BIT_REGS))) + *arg = (unsigned int)*arg; +#endif } static inline long syscall_get_error(struct task_struct *task, diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c index cb1045ebab06..b910ec54a3a1 100644 --- a/arch/mips/kernel/asm-offsets.c +++ b/arch/mips/kernel/asm-offsets.c @@ -27,6 +27,12 @@ void output_ptreg_defines(void); void output_ptreg_defines(void) { COMMENT("MIPS pt_regs offsets."); +#ifdef CONFIG_32BIT + OFFSET(PT_ARG4, pt_regs, args[4]); + OFFSET(PT_ARG5, pt_regs, args[5]); + OFFSET(PT_ARG6, pt_regs, args[6]); + OFFSET(PT_ARG7, pt_regs, args[7]); +#endif OFFSET(PT_R0, pt_regs, regs[0]); OFFSET(PT_R1, pt_regs, regs[1]); OFFSET(PT_R2, pt_regs, regs[2]); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 2c604717e630..4947a4f39e37 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -64,10 +64,10 @@ load_a6: user_lw(t7, 24(t0)) # argument #7 from usp load_a7: user_lw(t8, 28(t0)) # argument #8 from usp loads_done: - sw t5, 16(sp) # argument #5 to ksp - sw t6, 20(sp) # argument #6 to ksp - sw t7, 24(sp) # argument #7 to ksp - sw t8, 28(sp) # argument #8 to ksp + sw t5, PT_ARG4(sp) # argument #5 to ksp + sw t6, PT_ARG5(sp) # argument #6 to ksp + sw t7, PT_ARG6(sp) # argument #7 to ksp + sw t8, PT_ARG7(sp) # argument #8 to ksp .set pop .section __ex_table,"a" diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index e8a57c206758..349b8aad1159 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -382,15 +382,15 @@ 368 o32 io_pgetevents sys_io_pgetevents_time32 compat_sys_io_pgetevents # room for arch specific calls 393 o32 semget sys_semget -394 o32 semctl sys_old_semctl compat_sys_old_semctl +394 o32 semctl sys_semctl compat_sys_semctl 395 o32 shmget sys_shmget -396 o32 shmctl sys_old_shmctl compat_sys_old_shmctl +396 o32 shmctl sys_shmctl compat_sys_shmctl 397 o32 shmat sys_shmat compat_sys_shmat 398 o32 shmdt sys_shmdt 399 o32 msgget sys_msgget 400 o32 msgsnd sys_msgsnd compat_sys_msgsnd 401 o32 msgrcv sys_msgrcv compat_sys_msgrcv -402 o32 msgctl sys_old_msgctl compat_sys_old_msgctl +402 o32 msgctl sys_msgctl compat_sys_msgctl 403 o32 clock_gettime64 sys_clock_gettime sys_clock_gettime 404 o32 clock_settime64 sys_clock_settime sys_clock_settime 405 o32 clock_adjtime64 sys_clock_adjtime sys_clock_adjtime diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index e9c46b59ebbc..465eb96c755e 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -448,6 +448,7 @@ CONFIG_TEST_PRINTF=m CONFIG_TEST_SCANF=m CONFIG_TEST_BITMAP=m CONFIG_TEST_UUID=m +CONFIG_TEST_XARRAY=m CONFIG_TEST_MAPLE_TREE=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_IDA=m diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index c3efacab4b94..aa90a048f319 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -77,9 +77,17 @@ /* * With 4K page size the real_pte machinery is all nops. */ -#define __real_pte(e, p, o) ((real_pte_t){(e)}) +static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset) +{ + return (real_pte_t){pte}; +} + #define __rpte_to_pte(r) ((r).pte) -#define __rpte_to_hidx(r,index) (pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT) + +static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) +{ + return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT; +} #define pte_iterate_hashed_subpages(rpte, psize, va, index, shift) \ do { \ diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 30b56c67fa61..e527cd3ef128 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -97,7 +97,7 @@ void power4_idle(void) /* * Register the sysctl to set/clear powersave_nap. */ -static struct ctl_table powersave_nap_ctl_table[] = { +static const struct ctl_table powersave_nap_ctl_table[] = { { .procname = "powersave-nap", .data = &powersave_nap, diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index 45dac7b46aa3..34a5aec4908f 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -369,6 +369,24 @@ static void dedotify_versions(struct modversion_info *vers, } } +/* Same as normal versions, remove a leading dot if present. */ +static void dedotify_ext_version_names(char *str_seq, unsigned long size) +{ + unsigned long out = 0; + unsigned long in; + char last = '\0'; + + for (in = 0; in < size; in++) { + /* Skip one leading dot */ + if (last == '\0' && str_seq[in] == '.') + in++; + last = str_seq[in]; + str_seq[out++] = last; + } + /* Zero the trailing portion of the names table for robustness */ + memset(&str_seq[out], 0, size - out); +} + /* * Undefined symbols which refer to .funcname, hack to funcname. Make .TOC. * seem to be defined (value set later). @@ -438,10 +456,12 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr, me->arch.toc_section = i; if (sechdrs[i].sh_addralign < 8) sechdrs[i].sh_addralign = 8; - } - else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0) + } else if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0) dedotify_versions((void *)hdr + sechdrs[i].sh_offset, sechdrs[i].sh_size); + else if (strcmp(secstrings + sechdrs[i].sh_name, "__version_ext_names") == 0) + dedotify_ext_version_names((void *)hdr + sechdrs[i].sh_offset, + sechdrs[i].sh_size); if (sechdrs[i].sh_type == SHT_SYMTAB) dedotify((void *)hdr + sechdrs[i].sh_offset, diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c index af97fbb3c257..f84e0337cc02 100644 --- a/arch/powerpc/lib/code-patching.c +++ b/arch/powerpc/lib/code-patching.c @@ -108,7 +108,7 @@ static int text_area_cpu_up(unsigned int cpu) unsigned long addr; int err; - area = get_vm_area(PAGE_SIZE, VM_ALLOC); + area = get_vm_area(PAGE_SIZE, 0); if (!area) { WARN_ONCE(1, "Failed to create text area for cpu %d\n", cpu); @@ -493,7 +493,9 @@ static int __do_patch_instructions_mm(u32 *addr, u32 *code, size_t len, bool rep orig_mm = start_using_temp_mm(patching_mm); + kasan_disable_current(); err = __patch_instructions(patch_addr, code, len, repeat_instr); + kasan_enable_current(); /* context synchronisation performed by __patch_instructions */ stop_using_temp_mm(patching_mm, orig_mm); diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c index 1893f66371fa..b12ef382fec7 100644 --- a/arch/powerpc/platforms/pseries/eeh_pseries.c +++ b/arch/powerpc/platforms/pseries/eeh_pseries.c @@ -580,8 +580,10 @@ static int pseries_eeh_get_state(struct eeh_pe *pe, int *delay) switch(rets[0]) { case 0: - result = EEH_STATE_MMIO_ACTIVE | - EEH_STATE_DMA_ACTIVE; + result = EEH_STATE_MMIO_ACTIVE | + EEH_STATE_DMA_ACTIVE | + EEH_STATE_MMIO_ENABLED | + EEH_STATE_DMA_ENABLED; break; case 1: result = EEH_STATE_RESET_ACTIVE | diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 29f1a0cc59cd..ae6f7a235d8b 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -2208,6 +2208,9 @@ static long spapr_tce_unset_window(struct iommu_table_group *table_group, int nu const char *win_name; int ret = -ENODEV; + if (!tbl) /* The table was never created OR window was never opened */ + return 0; + mutex_lock(&dma_win_init_mutex); if ((num == 0) && is_default_window_table(table_group, tbl)) diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index 1798f0f14d58..62bd8e2d5d4c 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -53,7 +53,7 @@ struct update_props_workarea { static unsigned int nmi_wd_lpm_factor = 200; #ifdef CONFIG_SYSCTL -static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { +static const struct ctl_table nmi_wd_lpm_factor_ctl_table[] = { { .procname = "nmi_wd_lpm_factor", .data = &nmi_wd_lpm_factor, diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c index 1aa0cb097c9c..7b9a5ea9cad9 100644 --- a/arch/powerpc/sysdev/fsl_msi.c +++ b/arch/powerpc/sysdev/fsl_msi.c @@ -75,7 +75,7 @@ static void fsl_msi_print_chip(struct irq_data *irqd, struct seq_file *p) srs = (hwirq >> msi_data->srs_shift) & MSI_SRS_MASK; cascade_virq = msi_data->cascade_array[srs]->virq; - seq_printf(p, " fsl-msi-%d", cascade_virq); + seq_printf(p, "fsl-msi-%d", cascade_virq); } diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata index 2acc7d876e1f..e318119d570d 100644 --- a/arch/riscv/Kconfig.errata +++ b/arch/riscv/Kconfig.errata @@ -119,4 +119,15 @@ config ERRATA_THEAD_PMU If you don't know what to do here, say "Y". +config ERRATA_THEAD_GHOSTWRITE + bool "Apply T-Head Ghostwrite errata" + depends on ERRATA_THEAD && RISCV_ISA_XTHEADVECTOR + default y + help + The T-Head C9xx cores have a vulnerability in the xtheadvector + instruction set. When this errata is enabled, the CPUs will be probed + to determine if they are vulnerable and disable xtheadvector. + + If you don't know what to do here, say "Y". + endmenu # "CPU errata selection" diff --git a/arch/riscv/Kconfig.vendor b/arch/riscv/Kconfig.vendor index 6f1cdd32ed29..b096548fe0ff 100644 --- a/arch/riscv/Kconfig.vendor +++ b/arch/riscv/Kconfig.vendor @@ -16,4 +16,30 @@ config RISCV_ISA_VENDOR_EXT_ANDES If you don't know what to do here, say Y. endmenu +menu "T-Head" +config RISCV_ISA_VENDOR_EXT_THEAD + bool "T-Head vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here to disable detection of and support for all T-Head vendor + extensions. Without this option enabled, T-Head vendor extensions will + not be detected at boot and their presence not reported to userspace. + + If you don't know what to do here, say Y. + +config RISCV_ISA_XTHEADVECTOR + bool "xtheadvector extension support" + depends on RISCV_ISA_VENDOR_EXT_THEAD + depends on RISCV_ISA_V + depends on FPU + default y + help + Say N here if you want to disable all xtheadvector related procedures + in the kernel. This will disable vector for any T-Head board that + contains xtheadvector rather than the standard vector. + + If you don't know what to do here, say Y. +endmenu + endmenu diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink index 829b9abc91f6..6b0580949b6a 100644 --- a/arch/riscv/Makefile.postlink +++ b/arch/riscv/Makefile.postlink @@ -10,6 +10,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib quiet_cmd_relocs_check = CHKREL $@ cmd_relocs_check = \ @@ -19,11 +20,6 @@ ifdef CONFIG_RELOCATABLE quiet_cmd_cp_vmlinux_relocs = CPREL vmlinux.relocs cmd_cp_vmlinux_relocs = cp vmlinux vmlinux.relocs -quiet_cmd_relocs_strip = STRIPREL $@ -cmd_relocs_strip = $(OBJCOPY) --remove-section='.rel.*' \ - --remove-section='.rel__*' \ - --remove-section='.rela.*' \ - --remove-section='.rela__*' $@ endif # `@true` prevents complaint when there is nothing to be done @@ -33,7 +29,7 @@ vmlinux: FORCE ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) $(call if_changed,cp_vmlinux_relocs) - $(call if_changed,relocs_strip) + $(call if_changed,strip_relocs) endif clean: diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi index 64c3c2e6cbe0..6367112e614a 100644 --- a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi @@ -27,7 +27,8 @@ riscv,isa = "rv64imafdc"; riscv,isa-base = "rv64i"; riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", - "zifencei", "zihpm"; + "zifencei", "zihpm", "xtheadvector"; + thead,vlenb = <128>; #cooling-cells = <2>; cpu0_intc: interrupt-controller { diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index a924ef116d5e..0f7dcbe3c45b 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -10,7 +10,6 @@ CONFIG_MEMCG=y CONFIG_BLK_CGROUP=y CONFIG_CGROUP_SCHED=y CONFIG_CFS_BANDWIDTH=y -CONFIG_RT_GROUP_SCHED=y CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_FREEZER=y CONFIG_CGROUP_HUGETLB=y diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c index e24770a77932..0b942183f708 100644 --- a/arch/riscv/errata/thead/errata.c +++ b/arch/riscv/errata/thead/errata.c @@ -10,6 +10,7 @@ #include <linux/string.h> #include <linux/uaccess.h> #include <asm/alternative.h> +#include <asm/bugs.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/dma-noncoherent.h> @@ -142,6 +143,31 @@ static bool errata_probe_pmu(unsigned int stage, return true; } +static bool errata_probe_ghostwrite(unsigned int stage, + unsigned long arch_id, unsigned long impid) +{ + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_GHOSTWRITE)) + return false; + + /* + * target-c9xx cores report arch_id and impid as 0 + * + * While ghostwrite may not affect all c9xx cores that implement + * xtheadvector, there is no futher granularity than c9xx. Assume + * vulnerable for this entire class of processors when xtheadvector is + * enabled. + */ + if (arch_id != 0 || impid != 0) + return false; + + if (stage != RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + ghostwrite_set_vulnerable(); + + return true; +} + static u32 thead_errata_probe(unsigned int stage, unsigned long archid, unsigned long impid) { @@ -155,6 +181,8 @@ static u32 thead_errata_probe(unsigned int stage, if (errata_probe_pmu(stage, archid, impid)) cpu_req_errata |= BIT(ERRATA_THEAD_PMU); + errata_probe_ghostwrite(stage, archid, impid); + return cpu_req_errata; } diff --git a/arch/riscv/include/asm/bugs.h b/arch/riscv/include/asm/bugs.h new file mode 100644 index 000000000000..17ca0a947730 --- /dev/null +++ b/arch/riscv/include/asm/bugs.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Interface for managing mitigations for riscv vulnerabilities. + * + * Copyright (C) 2024 Rivos Inc. + */ + +#ifndef __ASM_BUGS_H +#define __ASM_BUGS_H + +/* Watch out, ordering is important here. */ +enum mitigation_state { + UNAFFECTED, + MITIGATED, + VULNERABLE, +}; + +void ghostwrite_set_vulnerable(void); +bool ghostwrite_enable_mitigation(void); +enum mitigation_state ghostwrite_get_state(void); + +#endif /* __ASM_BUGS_H */ diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index 4bd054c54c21..569140d6e639 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -34,6 +34,8 @@ DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); /* Per-cpu ISA extensions. */ extern struct riscv_isainfo hart_isa[NR_CPUS]; +extern u32 thead_vlenb_of; + void __init riscv_user_isa_enable(void); #define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) { \ diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 37bdea65bbd8..6fed42e37705 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -30,6 +30,12 @@ #define SR_VS_CLEAN _AC(0x00000400, UL) #define SR_VS_DIRTY _AC(0x00000600, UL) +#define SR_VS_THEAD _AC(0x01800000, UL) /* xtheadvector Status */ +#define SR_VS_OFF_THEAD _AC(0x00000000, UL) +#define SR_VS_INITIAL_THEAD _AC(0x00800000, UL) +#define SR_VS_CLEAN_THEAD _AC(0x01000000, UL) +#define SR_VS_DIRTY_THEAD _AC(0x01800000, UL) + #define SR_XS _AC(0x00018000, UL) /* Extension Status */ #define SR_XS_OFF _AC(0x00000000, UL) #define SR_XS_INITIAL _AC(0x00008000, UL) @@ -315,6 +321,15 @@ #define CSR_STIMECMP 0x14D #define CSR_STIMECMPH 0x15D +/* xtheadvector symbolic CSR names */ +#define CSR_VXSAT 0x9 +#define CSR_VXRM 0xa + +/* xtheadvector CSR masks */ +#define CSR_VXRM_MASK 3 +#define CSR_VXRM_SHIFT 1 +#define CSR_VXSAT_MASK 1 + /* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */ #define CSR_SISELECT 0x150 #define CSR_SIREG 0x151 diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index 7c8a71a526a3..6e426ed7919a 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -25,7 +25,8 @@ #ifdef CONFIG_ERRATA_THEAD #define ERRATA_THEAD_MAE 0 #define ERRATA_THEAD_PMU 1 -#define ERRATA_THEAD_NUMBER 2 +#define ERRATA_THEAD_GHOSTWRITE 2 +#define ERRATA_THEAD_NUMBER 3 #endif #ifdef __ASSEMBLY__ diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h index fc8130f995c1..72be100afa23 100644 --- a/arch/riscv/include/asm/futex.h +++ b/arch/riscv/include/asm/futex.h @@ -85,7 +85,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, __enable_user_access(); __asm__ __volatile__ ( - "1: lr.w.aqrl %[v],%[u] \n" + "1: lr.w %[v],%[u] \n" " bne %[v],%z[ov],3f \n" "2: sc.w.aqrl %[t],%z[nv],%[u] \n" " bnez %[t],1b \n" diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 1ce1df6d0ff3..dd624523981c 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2023 Rivos, Inc + * Copyright 2023-2024 Rivos, Inc */ #ifndef _ASM_HWPROBE_H @@ -8,7 +8,7 @@ #include <uapi/asm/hwprobe.h> -#define RISCV_HWPROBE_MAX_KEY 10 +#define RISCV_HWPROBE_MAX_KEY 11 static inline bool riscv_hwprobe_key_is_valid(__s64 key) { @@ -21,6 +21,7 @@ static inline bool hwprobe_key_is_bitmask(__s64 key) case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: case RISCV_HWPROBE_KEY_IMA_EXT_0: case RISCV_HWPROBE_KEY_CPUPERF_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: return true; } diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h index 94e33216b2d9..0e71eb82f920 100644 --- a/arch/riscv/include/asm/switch_to.h +++ b/arch/riscv/include/asm/switch_to.h @@ -117,7 +117,7 @@ do { \ __set_prev_cpu(__prev->thread); \ if (has_fpu()) \ __switch_to_fpu(__prev, __next); \ - if (has_vector()) \ + if (has_vector() || has_xtheadvector()) \ __switch_to_vector(__prev, __next); \ if (switch_to_should_flush_icache(__next)) \ local_flush_icache_all(); \ diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h index c7c023afbacd..e8a83f55be2b 100644 --- a/arch/riscv/include/asm/vector.h +++ b/arch/riscv/include/asm/vector.h @@ -18,6 +18,27 @@ #include <asm/cpufeature.h> #include <asm/csr.h> #include <asm/asm.h> +#include <asm/vendorid_list.h> +#include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/thead.h> + +#define __riscv_v_vstate_or(_val, TYPE) ({ \ + typeof(_val) _res = _val; \ + if (has_xtheadvector()) \ + _res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD; \ + else \ + _res = (_res & ~SR_VS) | SR_VS_##TYPE; \ + _res; \ +}) + +#define __riscv_v_vstate_check(_val, TYPE) ({ \ + bool _res; \ + if (has_xtheadvector()) \ + _res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD; \ + else \ + _res = ((_val) & SR_VS) == SR_VS_##TYPE; \ + _res; \ +}) extern unsigned long riscv_v_vsize; int riscv_v_setup_vsize(void); @@ -41,39 +62,62 @@ static __always_inline bool has_vector(void) return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X); } +static __always_inline bool has_xtheadvector_no_alternatives(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR); + else + return false; +} + +static __always_inline bool has_xtheadvector(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID, + RISCV_ISA_VENDOR_EXT_XTHEADVECTOR); + else + return false; +} + static inline void __riscv_v_vstate_clean(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_CLEAN; + regs->status = __riscv_v_vstate_or(regs->status, CLEAN); } static inline void __riscv_v_vstate_dirty(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_DIRTY; + regs->status = __riscv_v_vstate_or(regs->status, DIRTY); } static inline void riscv_v_vstate_off(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_OFF; + regs->status = __riscv_v_vstate_or(regs->status, OFF); } static inline void riscv_v_vstate_on(struct pt_regs *regs) { - regs->status = (regs->status & ~SR_VS) | SR_VS_INITIAL; + regs->status = __riscv_v_vstate_or(regs->status, INITIAL); } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { - return (regs->status & SR_VS) != 0; + return !__riscv_v_vstate_check(regs->status, OFF); } static __always_inline void riscv_v_enable(void) { - csr_set(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_set(CSR_SSTATUS, SR_VS_THEAD); + else + csr_set(CSR_SSTATUS, SR_VS); } static __always_inline void riscv_v_disable(void) { - csr_clear(CSR_SSTATUS, SR_VS); + if (has_xtheadvector()) + csr_clear(CSR_SSTATUS, SR_VS_THEAD); + else + csr_clear(CSR_SSTATUS, SR_VS); } static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) @@ -82,10 +126,36 @@ static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) "csrr %0, " __stringify(CSR_VSTART) "\n\t" "csrr %1, " __stringify(CSR_VTYPE) "\n\t" "csrr %2, " __stringify(CSR_VL) "\n\t" - "csrr %3, " __stringify(CSR_VCSR) "\n\t" - "csrr %4, " __stringify(CSR_VLENB) "\n\t" : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), - "=r" (dest->vcsr), "=r" (dest->vlenb) : :); + "=r" (dest->vcsr) : :); + + if (has_xtheadvector()) { + unsigned long status; + + /* + * CSR_VCSR is defined as + * [2:1] - vxrm[1:0] + * [0] - vxsat + * The earlier vector spec implemented by T-Head uses separate + * registers for the same bit-elements, so just combine those + * into the existing output field. + * + * Additionally T-Head cores need FS to be enabled when accessing + * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions. + * Though the cores do not implement the VXRM and VXSAT fields in the + * FCSR CSR that vector-0.7.1 specifies. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT; + + dest->vlenb = riscv_v_vsize / 32; + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + dest->vcsr = csr_read(CSR_VCSR); + dest->vlenb = csr_read(CSR_VLENB); + } } static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) @@ -96,9 +166,25 @@ static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src "vsetvl x0, %2, %1\n\t" ".option pop\n\t" "csrw " __stringify(CSR_VSTART) ", %0\n\t" - "csrw " __stringify(CSR_VCSR) ", %3\n\t" - : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl), - "r" (src->vcsr) :); + : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl)); + + if (has_xtheadvector()) { + unsigned long status = csr_read(CSR_SSTATUS); + + /* + * Similar to __vstate_csr_save above, restore values for the + * separate VXRM and VXSAT CSRs from the vcsr variable. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + + csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK); + csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK); + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + csr_write(CSR_VCSR, src->vcsr); + } } static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, @@ -108,19 +194,33 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, riscv_v_enable(); __vstate_csr_save(save_to); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V0T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vse8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } riscv_v_disable(); } @@ -130,19 +230,33 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_ unsigned long vl; riscv_v_enable(); - asm volatile ( - ".option push\n\t" - ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vle8.v v0, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vle8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl) : "r" (datap) : "memory"); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V0T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vle8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } __vstate_csr_restore(restore_from); riscv_v_disable(); } @@ -152,33 +266,41 @@ static inline void __riscv_v_vstate_discard(void) unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1); riscv_v_enable(); + if (has_xtheadvector()) + asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4"); + else + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + ".option pop\n\t": "=&r" (vl)); + asm volatile ( ".option push\n\t" ".option arch, +zve32x\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" "vmv.v.i v0, -1\n\t" "vmv.v.i v8, -1\n\t" "vmv.v.i v16, -1\n\t" "vmv.v.i v24, -1\n\t" "vsetvl %0, x0, %1\n\t" ".option pop\n\t" - : "=&r" (vl) : "r" (vtype_inval) : "memory"); + : "=&r" (vl) : "r" (vtype_inval)); + riscv_v_disable(); } static inline void riscv_v_vstate_discard(struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_OFF) - return; - - __riscv_v_vstate_discard(); - __riscv_v_vstate_dirty(regs); + if (riscv_v_vstate_query(regs)) { + __riscv_v_vstate_discard(); + __riscv_v_vstate_dirty(regs); + } } static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) == SR_VS_DIRTY) { + if (__riscv_v_vstate_check(regs->status, DIRTY)) { __riscv_v_vstate_save(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -187,7 +309,7 @@ static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { __riscv_v_vstate_restore(vstate, vstate->datap); __riscv_v_vstate_clean(regs); } @@ -196,7 +318,7 @@ static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, static inline void riscv_v_vstate_set_restore(struct task_struct *task, struct pt_regs *regs) { - if ((regs->status & SR_VS) != SR_VS_OFF) { + if (riscv_v_vstate_query(regs)) { set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE); riscv_v_vstate_on(regs); } @@ -270,6 +392,8 @@ struct pt_regs; static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; } static __always_inline bool has_vector(void) { return false; } static __always_inline bool insn_is_vector(u32 insn_buf) { return false; } +static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; } +static __always_inline bool has_xtheadvector(void) { return false; } static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; } static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; } diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h new file mode 100644 index 000000000000..e85c75b3b340 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H + +#include <asm/vendor_extensions.h> + +#include <linux/types.h> + +/* + * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX. + */ +#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR 0 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead; + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void disable_xtheadvector(void); +#else +static inline void disable_xtheadvector(void) { } +#endif + +/* Extension specific helpers */ + +/* + * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older + * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for + * vsetvli t4, x0, e8, m8, d1 + */ +#define THEAD_VSETVLI_T4X0E8M8D1 ".long 0x00307ed7\n\t" + +/* + * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same + * encoding as the standard vse8.v and vle8.v, compilers seem to optimize + * the call resulting in a different encoding and then using a value for + * the "mop" field that is not part of vector-0.7.1 + * So encode specific variants for vstate_save and _restore. + */ +#define THEAD_VSB_V_V0T0 ".long 0x02028027\n\t" +#define THEAD_VSB_V_V8T0 ".long 0x02028427\n\t" +#define THEAD_VSB_V_V16T0 ".long 0x02028827\n\t" +#define THEAD_VSB_V_V24T0 ".long 0x02028c27\n\t" +#define THEAD_VLB_V_V0T0 ".long 0x012028007\n\t" +#define THEAD_VLB_V_V8T0 ".long 0x012028407\n\t" +#define THEAD_VLB_V_V16T0 ".long 0x012028807\n\t" +#define THEAD_VLB_V_V24T0 ".long 0x012028c07\n\t" + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h new file mode 100644 index 000000000000..65a9c5612466 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H + +#include <linux/cpumask.h> + +#include <uapi/asm/hwprobe.h> + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h new file mode 100644 index 000000000000..6b9293e984a9 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2024 Rivos, Inc + */ + +#ifndef _ASM_RISCV_SYS_HWPROBE_H +#define _ASM_RISCV_SYS_HWPROBE_H + +#include <asm/cpufeature.h> + +#define VENDOR_EXT_KEY(ext) \ + do { \ + if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \ + pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + } while (false) + +/* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + * + * _extension_checks is an arbitrary C block to set the values of pair->value + * and missing. It should be filled with VENDOR_EXT_KEY expressions. + */ +#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks) \ + do { \ + int cpu; \ + u64 missing = 0; \ + for_each_cpu(cpu, (cpus)) { \ + struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu]; \ + _extension_checks \ + } \ + (pair)->value &= ~missing; \ + } while (false) \ + +#endif /* _ASM_RISCV_SYS_HWPROBE_H */ diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index 3af142b99f77..c3c1cc951cb9 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2023 Rivos, Inc + * Copyright 2023-2024 Rivos, Inc */ #ifndef _UAPI_ASM_HWPROBE_H @@ -94,6 +94,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW 2 #define RISCV_HWPROBE_MISALIGNED_VECTOR_FAST 3 #define RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED 4 +#define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0 11 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ /* Flags */ diff --git a/arch/riscv/include/uapi/asm/vendor/thead.h b/arch/riscv/include/uapi/asm/vendor/thead.h new file mode 100644 index 000000000000..43790ebe5faf --- /dev/null +++ b/arch/riscv/include/uapi/asm/vendor/thead.h @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#define RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR (1 << 0) diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 063d1faf5a53..8d186bfced45 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -123,3 +123,5 @@ obj-$(CONFIG_COMPAT) += compat_vdso/ obj-$(CONFIG_64BIT) += pi/ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o + +obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o diff --git a/arch/riscv/kernel/bugs.c b/arch/riscv/kernel/bugs.c new file mode 100644 index 000000000000..3655fe7d678c --- /dev/null +++ b/arch/riscv/kernel/bugs.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Rivos Inc. + */ + +#include <linux/cpu.h> +#include <linux/device.h> +#include <linux/sprintf.h> + +#include <asm/bugs.h> +#include <asm/vendor_extensions/thead.h> + +static enum mitigation_state ghostwrite_state; + +void ghostwrite_set_vulnerable(void) +{ + ghostwrite_state = VULNERABLE; +} + +/* + * Vendor extension alternatives will use the value set at the time of boot + * alternative patching, thus this must be called before boot alternatives are + * patched (and after extension probing) to be effective. + * + * Returns true if mitgated, false otherwise. + */ +bool ghostwrite_enable_mitigation(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR) && + ghostwrite_state == VULNERABLE && !cpu_mitigations_off()) { + disable_xtheadvector(); + ghostwrite_state = MITIGATED; + return true; + } + + return false; +} + +enum mitigation_state ghostwrite_get_state(void) +{ + return ghostwrite_state; +} + +ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) { + switch (ghostwrite_state) { + case UNAFFECTED: + return sprintf(buf, "Not affected\n"); + case MITIGATED: + return sprintf(buf, "Mitigation: xtheadvector disabled\n"); + case VULNERABLE: + fallthrough; + default: + return sprintf(buf, "Vulnerable\n"); + } + } else { + return sprintf(buf, "Not affected\n"); + } +} diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index c0916ed318c2..c6ba750536c3 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -17,6 +17,7 @@ #include <linux/of.h> #include <asm/acpi.h> #include <asm/alternative.h> +#include <asm/bugs.h> #include <asm/cacheflush.h> #include <asm/cpufeature.h> #include <asm/hwcap.h> @@ -26,6 +27,7 @@ #include <asm/sbi.h> #include <asm/vector.h> #include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/thead.h> #define NUM_ALPHA_EXTS ('z' - 'a' + 1) @@ -39,6 +41,8 @@ static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; /* Per-cpu ISA extensions. */ struct riscv_isainfo hart_isa[NR_CPUS]; +u32 thead_vlenb_of; + /** * riscv_isa_extension_base() - Get base extension word * @@ -791,9 +795,50 @@ static void __init riscv_fill_vendor_ext_list(int cpu) } } +static int has_thead_homogeneous_vlenb(void) +{ + int cpu; + u32 prev_vlenb = 0; + u32 vlenb; + + /* Ignore thead,vlenb property if xtheavector is not enabled in the kernel */ + if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return 0; + + for_each_possible_cpu(cpu) { + struct device_node *cpu_node; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + return -ENOENT; + } + + if (of_property_read_u32(cpu_node, "thead,vlenb", &vlenb)) { + of_node_put(cpu_node); + + if (prev_vlenb) + return -ENOENT; + continue; + } + + if (prev_vlenb && vlenb != prev_vlenb) { + of_node_put(cpu_node); + return -ENOENT; + } + + prev_vlenb = vlenb; + of_node_put(cpu_node); + } + + thead_vlenb_of = vlenb; + return 0; +} + static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) { unsigned int cpu; + bool mitigated; for_each_possible_cpu(cpu) { unsigned long this_hwcap = 0; @@ -844,6 +889,17 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) riscv_fill_vendor_ext_list(cpu); } + /* + * Execute ghostwrite mitigation immediately after detecting extensions + * to disable xtheadvector if necessary. + */ + mitigated = ghostwrite_enable_mitigation(); + + if (!mitigated && has_xtheadvector_no_alternatives() && has_thead_homogeneous_vlenb() < 0) { + pr_warn("Unsupported heterogeneous vlenb detected, vector extension disabled.\n"); + disable_xtheadvector(); + } + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) return -ENOENT; @@ -896,7 +952,8 @@ void __init riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X)) { + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X) || + has_xtheadvector_no_alternatives()) { /* * This cannot fail when called on the boot hart */ diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c index 6afe80c7f03a..99972a48e86b 100644 --- a/arch/riscv/kernel/kernel_mode_vector.c +++ b/arch/riscv/kernel/kernel_mode_vector.c @@ -143,7 +143,7 @@ static int riscv_v_start_kernel_context(bool *is_nested) /* Transfer the ownership of V from user to kernel, then save */ riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY); - if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) { + if (__riscv_v_vstate_check(task_pt_regs(current)->status, DIRTY)) { uvstate = ¤t->thread.vstate; __riscv_v_vstate_save(uvstate, uvstate->datap); } @@ -160,7 +160,7 @@ asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs) return; depth = riscv_v_ctx_get_depth(); - if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY) + if (depth == 0 && __riscv_v_vstate_check(regs->status, DIRTY)) riscv_preempt_v_set_dirty(); riscv_v_ctx_depth_inc(); @@ -208,7 +208,7 @@ void kernel_vector_begin(void) { bool nested = false; - if (WARN_ON(!has_vector())) + if (WARN_ON(!(has_vector() || has_xtheadvector()))) return; BUG_ON(!may_use_simd()); @@ -236,7 +236,7 @@ EXPORT_SYMBOL_GPL(kernel_vector_begin); */ void kernel_vector_end(void) { - if (WARN_ON(!has_vector())) + if (WARN_ON(!(has_vector() || has_xtheadvector()))) return; riscv_v_disable(); diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index 58b6482c2bf6..7c244de77180 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -190,7 +190,7 @@ void flush_thread(void) void arch_release_task_struct(struct task_struct *tsk) { /* Free the vector context of datap. */ - if (has_vector()) + if (has_vector() || has_xtheadvector()) riscv_v_thread_free(tsk); } @@ -240,7 +240,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) p->thread.s[0] = 0; } p->thread.riscv_v_flags = 0; - if (has_vector()) + if (has_vector() || has_xtheadvector()) riscv_v_thread_alloc(p); p->thread.ra = (unsigned long)ret_from_fork; p->thread.sp = (unsigned long)childregs; /* kernel sp */ @@ -364,7 +364,7 @@ static bool try_to_set_pmm(unsigned long value) * disable it for tasks that already opted in to the relaxed ABI. */ -static struct ctl_table tagged_addr_sysctl_table[] = { +static const struct ctl_table tagged_addr_sysctl_table[] = { { .procname = "tagged_addr_disabled", .mode = 0644, diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index dcd282419456..94e905eea1de 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -189,7 +189,7 @@ static long restore_sigcontext(struct pt_regs *regs, return 0; case RISCV_V_MAGIC: - if (!has_vector() || !riscv_v_vstate_query(regs) || + if (!(has_vector() || has_xtheadvector()) || !riscv_v_vstate_query(regs) || size != riscv_v_sc_size) return -EINVAL; @@ -211,7 +211,7 @@ static size_t get_rt_frame_size(bool cal_all) frame_size = sizeof(*frame); - if (has_vector()) { + if (has_vector() || has_xtheadvector()) { if (cal_all || riscv_v_vstate_query(task_pt_regs(current))) total_context_size += riscv_v_sc_size; } @@ -284,7 +284,7 @@ static long setup_sigcontext(struct rt_sigframe __user *frame, if (has_fpu()) err |= save_fp_state(regs, &sc->sc_fpregs); /* Save the vector state. */ - if (has_vector() && riscv_v_vstate_query(regs)) + if ((has_vector() || has_xtheadvector()) && riscv_v_vstate_query(regs)) err |= save_v_state(regs, (void __user **)&sc_ext_ptr); /* Write zero to fp-reserved space and check it on restore_sigcontext */ err |= __put_user(0, &sc->sc_extdesc.reserved); diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c index cb93adfffc48..bcd3b816306c 100644 --- a/arch/riscv/kernel/sys_hwprobe.c +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -15,6 +15,7 @@ #include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/vector.h> +#include <asm/vendor_extensions/thead_hwprobe.h> #include <vdso/vsyscall.h> @@ -286,6 +287,10 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, pair->value = riscv_timebase; break; + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: + hwprobe_isa_vendor_ext_thead_0(pair, cpus); + break; + /* * For forward compatibility, unknown keys don't fail the whole * call, but get their element key set to -1 and value set to 0 diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c index 821818886fab..184f780c932d 100644 --- a/arch/riscv/kernel/vector.c +++ b/arch/riscv/kernel/vector.c @@ -33,7 +33,17 @@ int riscv_v_setup_vsize(void) { unsigned long this_vsize; - /* There are 32 vector registers with vlenb length. */ + /* + * There are 32 vector registers with vlenb length. + * + * If the thead,vlenb property was provided by the firmware, use that + * instead of probing the CSRs. + */ + if (thead_vlenb_of) { + riscv_v_vsize = thead_vlenb_of * 32; + return 0; + } + riscv_v_enable(); this_vsize = csr_read(CSR_VLENB) * 32; riscv_v_disable(); @@ -53,7 +63,7 @@ int riscv_v_setup_vsize(void) void __init riscv_v_setup_ctx_cache(void) { - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return; riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx", @@ -173,7 +183,7 @@ bool riscv_v_first_use_handler(struct pt_regs *regs) u32 __user *epc = (u32 __user *)regs->epc; u32 insn = (u32)regs->badaddr; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return false; /* Do not handle if V is not supported, or disabled */ @@ -216,7 +226,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk) bool inherit; int cur, next; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return; next = riscv_v_ctrl_get_next(tsk); @@ -238,7 +248,7 @@ void riscv_v_vstate_ctrl_init(struct task_struct *tsk) long riscv_v_vstate_ctrl_get_current(void) { - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return -EINVAL; return current->thread.vstate_ctrl & PR_RISCV_V_VSTATE_CTRL_MASK; @@ -249,7 +259,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg) bool inherit; int cur, next; - if (!has_vector()) + if (!(has_vector() || has_xtheadvector())) return -EINVAL; if (arg & ~PR_RISCV_V_VSTATE_CTRL_MASK) @@ -287,7 +297,7 @@ long riscv_v_vstate_ctrl_set_current(unsigned long arg) #ifdef CONFIG_SYSCTL -static struct ctl_table riscv_v_default_vstate_table[] = { +static const struct ctl_table riscv_v_default_vstate_table[] = { { .procname = "riscv_v_default_allow", .data = &riscv_v_implicit_uacc, @@ -299,7 +309,7 @@ static struct ctl_table riscv_v_default_vstate_table[] = { static int __init riscv_v_sysctl_init(void) { - if (has_vector()) + if (has_vector() || has_xtheadvector()) if (!register_sysctl("abi", riscv_v_default_vstate_table)) return -EINVAL; return 0; @@ -309,7 +319,7 @@ static int __init riscv_v_sysctl_init(void) static int __init riscv_v_sysctl_init(void) { return 0; } #endif /* ! CONFIG_SYSCTL */ -static int riscv_v_init(void) +static int __init riscv_v_init(void) { return riscv_v_sysctl_init(); } diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c index a8126d118341..a31ff84740eb 100644 --- a/arch/riscv/kernel/vendor_extensions.c +++ b/arch/riscv/kernel/vendor_extensions.c @@ -6,6 +6,7 @@ #include <asm/vendorid_list.h> #include <asm/vendor_extensions.h> #include <asm/vendor_extensions/andes.h> +#include <asm/vendor_extensions/thead.h> #include <linux/array_size.h> #include <linux/types.h> @@ -14,6 +15,9 @@ struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[] = { #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES &riscv_isa_vendor_ext_list_andes, #endif +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + &riscv_isa_vendor_ext_list_thead, +#endif }; const size_t riscv_isa_vendor_ext_list_size = ARRAY_SIZE(riscv_isa_vendor_ext_list); @@ -41,6 +45,12 @@ bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsig cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap; break; #endif + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + case THEAD_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap; + break; + #endif default: return false; } diff --git a/arch/riscv/kernel/vendor_extensions/Makefile b/arch/riscv/kernel/vendor_extensions/Makefile index 6a61aed944f1..866414c81a9f 100644 --- a/arch/riscv/kernel/vendor_extensions/Makefile +++ b/arch/riscv/kernel/vendor_extensions/Makefile @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_ANDES) += andes.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead_hwprobe.o diff --git a/arch/riscv/kernel/vendor_extensions/thead.c b/arch/riscv/kernel/vendor_extensions/thead.c new file mode 100644 index 000000000000..519dbf70710a --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/cpufeature.h> +#include <asm/vendor_extensions.h> +#include <asm/vendor_extensions/thead.h> + +#include <linux/array_size.h> +#include <linux/cpumask.h> +#include <linux/types.h> + +/* All T-Head vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_thead[] = { + __RISCV_ISA_EXT_DATA(xtheadvector, RISCV_ISA_VENDOR_EXT_XTHEADVECTOR), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_thead), + .ext_data = riscv_isa_vendor_ext_thead, +}; + +void disable_xtheadvector(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap[cpu].isa); + + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap.isa); +} diff --git a/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c new file mode 100644 index 000000000000..2eba34011786 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <asm/vendor_extensions/thead.h> +#include <asm/vendor_extensions/thead_hwprobe.h> +#include <asm/vendor_extensions/vendor_hwprobe.h> + +#include <linux/cpumask.h> +#include <linux/types.h> + +#include <uapi/asm/hwprobe.h> +#include <uapi/asm/vendor/thead.h> + +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus) +{ + VENDOR_EXTENSION_SUPPORTED(pair, cpus, + riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap, { + VENDOR_EXT_KEY(XTHEADVECTOR); + }); +} diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index a9f2b4af8f3f..0194324a0c50 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -22,6 +22,57 @@ #include "../kernel/head.h" +static void show_pte(unsigned long addr) +{ + pgd_t *pgdp, pgd; + p4d_t *p4dp, p4d; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + struct mm_struct *mm = current->mm; + + if (!mm) + mm = &init_mm; + + pr_alert("Current %s pgtable: %luK pagesize, %d-bit VAs, pgdp=0x%016llx\n", + current->comm, PAGE_SIZE / SZ_1K, VA_BITS, + mm == &init_mm ? (u64)__pa_symbol(mm->pgd) : virt_to_phys(mm->pgd)); + + pgdp = pgd_offset(mm, addr); + pgd = pgdp_get(pgdp); + pr_alert("[%016lx] pgd=%016lx", addr, pgd_val(pgd)); + if (pgd_none(pgd) || pgd_bad(pgd) || pgd_leaf(pgd)) + goto out; + + p4dp = p4d_offset(pgdp, addr); + p4d = p4dp_get(p4dp); + pr_cont(", p4d=%016lx", p4d_val(p4d)); + if (p4d_none(p4d) || p4d_bad(p4d) || p4d_leaf(p4d)) + goto out; + + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + pr_cont(", pud=%016lx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud) || pud_leaf(pud)) + goto out; + + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get(pmdp); + pr_cont(", pmd=%016lx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd) || pmd_leaf(pmd)) + goto out; + + ptep = pte_offset_map(pmdp, addr); + if (!ptep) + goto out; + + pte = ptep_get(ptep); + pr_cont(", pte=%016lx", pte_val(pte)); + pte_unmap(ptep); +out: + pr_cont("\n"); +} + static void die_kernel_fault(const char *msg, unsigned long addr, struct pt_regs *regs) { @@ -31,6 +82,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, addr); bust_spinlocks(0); + show_pte(addr); die(regs, "Oops"); make_task_dead(SIGKILL); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 722178ae3488..15b2eda4c364 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -268,8 +268,12 @@ static void __init setup_bootmem(void) */ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) { max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE; - memblock_cap_memory_range(phys_ram_base, - max_mapped_addr - phys_ram_base); + if (memblock_end_of_DRAM() > max_mapped_addr) { + memblock_cap_memory_range(phys_ram_base, + max_mapped_addr - phys_ram_base); + pr_warn("Physical memory overflows the linear mapping size: region above %pa removed", + &max_mapped_addr); + } } /* diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 6e9545d8b0c7..9c9ec08d78c7 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -52,13 +52,19 @@ config KASAN_SHADOW_OFFSET depends on KASAN default 0x1C000000000000 -config GCC_ASM_FLAG_OUTPUT_BROKEN +config CC_ASM_FLAG_OUTPUT_BROKEN def_bool CC_IS_GCC && GCC_VERSION < 140200 help GCC versions before 14.2.0 may die with an internal compiler error in some configurations if flag output operands are used within inline assemblies. +config CC_HAS_ASM_AOR_FORMAT_FLAGS + def_bool !(CC_IS_CLANG && CLANG_VERSION < 190100) + help + Clang versions before 19.1.0 do not support A, + O, and R inline assembly format flags. + config S390 def_bool y # @@ -72,6 +78,7 @@ config S390 select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM select ARCH_ENABLE_MEMORY_HOTREMOVE select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CRC32 select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 3f25498dac65..5fae311203c2 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -22,7 +22,7 @@ KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__ ifndef CONFIG_AS_IS_LLVM KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf)) endif -KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack +KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2 -mpacked-stack -std=gnu11 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY KBUILD_CFLAGS_DECOMPRESSOR += -D__DECOMPRESSOR KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float -mbackchain diff --git a/arch/s390/Makefile.postlink b/arch/s390/Makefile.postlink index df82f5410769..1ae5478cd6ac 100644 --- a/arch/s390/Makefile.postlink +++ b/arch/s390/Makefile.postlink @@ -11,6 +11,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib CMD_RELOCS=arch/s390/tools/relocs OUT_RELOCS = arch/s390/boot @@ -19,11 +20,6 @@ quiet_cmd_relocs = RELOCS $(OUT_RELOCS)/relocs.S mkdir -p $(OUT_RELOCS); \ $(CMD_RELOCS) $@ > $(OUT_RELOCS)/relocs.S -quiet_cmd_strip_relocs = RSTRIP $@ - cmd_strip_relocs = \ - $(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \ - --remove-section='.rela.*' --remove-section='.rela__*' $@ - vmlinux: FORCE $(call cmd,relocs) $(call cmd,strip_relocs) diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c index 91a30e017d65..dd7ba7587dd5 100644 --- a/arch/s390/appldata/appldata_base.c +++ b/arch/s390/appldata/appldata_base.c @@ -52,7 +52,7 @@ static int appldata_interval_handler(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static struct ctl_table_header *appldata_sysctl_header; -static struct ctl_table appldata_table[] = { +static const struct ctl_table appldata_table[] = { { .procname = "timer", .mode = S_IRUGO | S_IWUSR, diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c index 11e0c3d5dbc8..79afb5fa7f1f 100644 --- a/arch/s390/boot/als.c +++ b/arch/s390/boot/als.c @@ -46,7 +46,7 @@ void print_missing_facilities(void) * z/VM adds a four character prefix. */ if (strlen(als_str) > 70) { - boot_printk("%s\n", als_str); + boot_emerg("%s\n", als_str); *als_str = '\0'; } u16_to_decimal(val_str, i * BITS_PER_LONG + j); @@ -54,7 +54,7 @@ void print_missing_facilities(void) first = 0; } } - boot_printk("%s\n", als_str); + boot_emerg("%s\n", als_str); } static void facility_mismatch(void) @@ -62,10 +62,10 @@ static void facility_mismatch(void) struct cpuid id; get_cpu_id(&id); - boot_printk("The Linux kernel requires more recent processor hardware\n"); - boot_printk("Detected machine-type number: %4x\n", id.machine); + boot_emerg("The Linux kernel requires more recent processor hardware\n"); + boot_emerg("Detected machine-type number: %4x\n", id.machine); print_missing_facilities(); - boot_printk("See Principles of Operations for facility bits\n"); + boot_emerg("See Principles of Operations for facility bits\n"); disabled_wait(); } diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 56244fe78182..69f261566a64 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -8,6 +8,7 @@ #ifndef __ASSEMBLY__ +#include <linux/printk.h> #include <asm/physmem_info.h> struct machine_info { @@ -47,13 +48,16 @@ void physmem_set_usable_limit(unsigned long limit); void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size); void physmem_free(enum reserved_range_type type); /* for continuous/multiple allocations per type */ -unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size, - unsigned long align); +unsigned long physmem_alloc_or_die(enum reserved_range_type type, unsigned long size, + unsigned long align); +unsigned long physmem_alloc(enum reserved_range_type type, unsigned long size, + unsigned long align, bool die_on_oom); /* for single allocations, 1 per type */ unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long size, unsigned long align, unsigned long min, unsigned long max, bool die_on_oom); unsigned long get_physmem_alloc_pos(void); +void dump_physmem_reserved(void); bool ipl_report_certs_intersects(unsigned long addr, unsigned long size, unsigned long *intersection_start); bool is_ipl_block_dump(void); @@ -69,12 +73,28 @@ void print_pgm_check_info(void); unsigned long randomize_within_range(unsigned long size, unsigned long align, unsigned long min, unsigned long max); void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned long asce_limit); -void __printf(1, 2) boot_printk(const char *fmt, ...); +int __printf(1, 2) boot_printk(const char *fmt, ...); void print_stacktrace(unsigned long sp); void error(char *m); int get_random(unsigned long limit, unsigned long *value); +void boot_rb_dump(void); + +#ifndef boot_fmt +#define boot_fmt(fmt) fmt +#endif + +#define boot_emerg(fmt, ...) boot_printk(KERN_EMERG boot_fmt(fmt), ##__VA_ARGS__) +#define boot_alert(fmt, ...) boot_printk(KERN_ALERT boot_fmt(fmt), ##__VA_ARGS__) +#define boot_crit(fmt, ...) boot_printk(KERN_CRIT boot_fmt(fmt), ##__VA_ARGS__) +#define boot_err(fmt, ...) boot_printk(KERN_ERR boot_fmt(fmt), ##__VA_ARGS__) +#define boot_warn(fmt, ...) boot_printk(KERN_WARNING boot_fmt(fmt), ##__VA_ARGS__) +#define boot_notice(fmt, ...) boot_printk(KERN_NOTICE boot_fmt(fmt), ##__VA_ARGS__) +#define boot_info(fmt, ...) boot_printk(KERN_INFO boot_fmt(fmt), ##__VA_ARGS__) +#define boot_debug(fmt, ...) boot_printk(KERN_DEBUG boot_fmt(fmt), ##__VA_ARGS__) extern struct machine_info machine; +extern int boot_console_loglevel; +extern bool boot_ignore_loglevel; /* Symbols defined by linker scripts */ extern const char kernel_version[]; diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index f478e8e9cbda..03500b9d9fb9 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/string.h> +#include <asm/boot_data.h> #include <asm/page.h> #include "decompressor.h" #include "boot.h" @@ -63,6 +64,15 @@ static unsigned long free_mem_end_ptr = (unsigned long) _end + BOOT_HEAP_SIZE; #include "../../../../lib/decompress_unzstd.c" #endif +static void decompress_error(char *m) +{ + if (bootdebug) + boot_rb_dump(); + boot_emerg("Decompression error: %s\n", m); + boot_emerg(" -- System halted\n"); + disabled_wait(); +} + unsigned long mem_safe_offset(void) { return ALIGN(free_mem_end_ptr, PAGE_SIZE); @@ -71,5 +81,5 @@ unsigned long mem_safe_offset(void) void deploy_kernel(void *output) { __decompress(_compressed_start, _compressed_end - _compressed_start, - NULL, NULL, output, vmlinux.image_size, NULL, error); + NULL, NULL, output, vmlinux.image_size, NULL, decompress_error); } diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c index 557462e62cd7..d3731f2983b7 100644 --- a/arch/s390/boot/ipl_parm.c +++ b/arch/s390/boot/ipl_parm.c @@ -215,7 +215,7 @@ static void check_cleared_facilities(void) for (i = 0; i < ARRAY_SIZE(als); i++) { if ((stfle_fac_list[i] & als[i]) != als[i]) { - boot_printk("Warning: The Linux kernel requires facilities cleared via command line option\n"); + boot_emerg("The Linux kernel requires facilities cleared via command line option\n"); print_missing_facilities(); break; } @@ -313,5 +313,23 @@ void parse_boot_command_line(void) #endif if (!strcmp(param, "relocate_lowcore") && test_facility(193)) relocate_lowcore = 1; + if (!strcmp(param, "earlyprintk")) + boot_earlyprintk = true; + if (!strcmp(param, "debug")) + boot_console_loglevel = CONSOLE_LOGLEVEL_DEBUG; + if (!strcmp(param, "bootdebug")) { + bootdebug = true; + if (val) + strncpy(bootdebug_filter, val, sizeof(bootdebug_filter) - 1); + } + if (!strcmp(param, "quiet")) + boot_console_loglevel = CONSOLE_LOGLEVEL_QUIET; + if (!strcmp(param, "ignore_loglevel")) + boot_ignore_loglevel = true; + if (!strcmp(param, "loglevel")) { + boot_console_loglevel = simple_strtoull(val, NULL, 10); + if (boot_console_loglevel < CONSOLE_LOGLEVEL_MIN) + boot_console_loglevel = CONSOLE_LOGLEVEL_MIN; + } } } diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c index d00898852a88..f73cd757a5f7 100644 --- a/arch/s390/boot/ipl_report.c +++ b/arch/s390/boot/ipl_report.c @@ -30,7 +30,6 @@ static unsigned long get_cert_comp_list_size(void) { struct ipl_rb_certificate_entry *cert; struct ipl_rb_component_entry *comp; - size_t size; /* * Find the length for the IPL report boot data @@ -155,7 +154,7 @@ void save_ipl_cert_comp_list(void) return; size = get_cert_comp_list_size(); - early_ipl_comp_list_addr = physmem_alloc_top_down(RR_CERT_COMP_LIST, size, sizeof(int)); + early_ipl_comp_list_addr = physmem_alloc_or_die(RR_CERT_COMP_LIST, size, sizeof(int)); ipl_cert_list_addr = early_ipl_comp_list_addr + early_ipl_comp_list_size; copy_components_bootdata(); diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c index f864d2bff775..941f4c9e27cc 100644 --- a/arch/s390/boot/kaslr.c +++ b/arch/s390/boot/kaslr.c @@ -32,7 +32,7 @@ struct prng_parm { static int check_prng(void) { if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) { - boot_printk("KASLR disabled: CPU has no PRNG\n"); + boot_warn("KASLR disabled: CPU has no PRNG\n"); return 0; } if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG)) @@ -168,7 +168,7 @@ static unsigned long iterate_valid_positions(unsigned long size, unsigned long a * cannot have chains. * * On the other hand, "dynamic" or "repetitive" allocations are done via - * physmem_alloc_top_down(). These allocations are tightly packed together + * physmem_alloc_or_die(). These allocations are tightly packed together * top down from the end of online memory. physmem_alloc_pos represents * current position where those allocations start. * diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c index 5abe59fb3bc0..633f11600aab 100644 --- a/arch/s390/boot/pgm_check_info.c +++ b/arch/s390/boot/pgm_check_info.c @@ -17,13 +17,14 @@ void print_stacktrace(unsigned long sp) (unsigned long)_stack_end }; bool first = true; - boot_printk("Call Trace:\n"); + boot_emerg("Call Trace:\n"); while (!(sp & 0x7) && on_stack(&boot_stack, sp, sizeof(struct stack_frame))) { struct stack_frame *sf = (struct stack_frame *)sp; - boot_printk(first ? "(sp:%016lx [<%016lx>] %pS)\n" : - " sp:%016lx [<%016lx>] %pS\n", - sp, sf->gprs[8], (void *)sf->gprs[8]); + if (first) + boot_emerg("(sp:%016lx [<%016lx>] %pS)\n", sp, sf->gprs[8], (void *)sf->gprs[8]); + else + boot_emerg(" sp:%016lx [<%016lx>] %pS\n", sp, sf->gprs[8], (void *)sf->gprs[8]); if (sf->back_chain <= sp) break; sp = sf->back_chain; @@ -36,30 +37,30 @@ void print_pgm_check_info(void) unsigned long *gpregs = (unsigned long *)get_lowcore()->gpregs_save_area; struct psw_bits *psw = &psw_bits(get_lowcore()->psw_save_area); - boot_printk("Linux version %s\n", kernel_version); + if (bootdebug) + boot_rb_dump(); + boot_emerg("Linux version %s\n", kernel_version); if (!is_prot_virt_guest() && early_command_line[0]) - boot_printk("Kernel command line: %s\n", early_command_line); - boot_printk("Kernel fault: interruption code %04x ilc:%x\n", - get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1); + boot_emerg("Kernel command line: %s\n", early_command_line); + boot_emerg("Kernel fault: interruption code %04x ilc:%d\n", + get_lowcore()->pgm_code, get_lowcore()->pgm_ilc >> 1); if (kaslr_enabled()) { - boot_printk("Kernel random base: %lx\n", __kaslr_offset); - boot_printk("Kernel random base phys: %lx\n", __kaslr_offset_phys); + boot_emerg("Kernel random base: %lx\n", __kaslr_offset); + boot_emerg("Kernel random base phys: %lx\n", __kaslr_offset_phys); } - boot_printk("PSW : %016lx %016lx (%pS)\n", - get_lowcore()->psw_save_area.mask, - get_lowcore()->psw_save_area.addr, - (void *)get_lowcore()->psw_save_area.addr); - boot_printk( - " R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n", - psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck, - psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri, - psw->eaba); - boot_printk("GPRS: %016lx %016lx %016lx %016lx\n", gpregs[0], gpregs[1], gpregs[2], gpregs[3]); - boot_printk(" %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]); - boot_printk(" %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]); - boot_printk(" %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]); + boot_emerg("PSW : %016lx %016lx (%pS)\n", + get_lowcore()->psw_save_area.mask, + get_lowcore()->psw_save_area.addr, + (void *)get_lowcore()->psw_save_area.addr); + boot_emerg(" R:%x T:%x IO:%x EX:%x Key:%x M:%x W:%x P:%x AS:%x CC:%x PM:%x RI:%x EA:%x\n", + psw->per, psw->dat, psw->io, psw->ext, psw->key, psw->mcheck, + psw->wait, psw->pstate, psw->as, psw->cc, psw->pm, psw->ri, psw->eaba); + boot_emerg("GPRS: %016lx %016lx %016lx %016lx\n", gpregs[0], gpregs[1], gpregs[2], gpregs[3]); + boot_emerg(" %016lx %016lx %016lx %016lx\n", gpregs[4], gpregs[5], gpregs[6], gpregs[7]); + boot_emerg(" %016lx %016lx %016lx %016lx\n", gpregs[8], gpregs[9], gpregs[10], gpregs[11]); + boot_emerg(" %016lx %016lx %016lx %016lx\n", gpregs[12], gpregs[13], gpregs[14], gpregs[15]); print_stacktrace(get_lowcore()->gpregs_save_area[15]); - boot_printk("Last Breaking-Event-Address:\n"); - boot_printk(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break, - (void *)get_lowcore()->pgm_last_break); + boot_emerg("Last Breaking-Event-Address:\n"); + boot_emerg(" [<%016lx>] %pS\n", (unsigned long)get_lowcore()->pgm_last_break, + (void *)get_lowcore()->pgm_last_break); } diff --git a/arch/s390/boot/physmem_info.c b/arch/s390/boot/physmem_info.c index 7617aa2d2f7e..aa096ef68e8c 100644 --- a/arch/s390/boot/physmem_info.c +++ b/arch/s390/boot/physmem_info.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define boot_fmt(fmt) "physmem: " fmt #include <linux/processor.h> #include <linux/errno.h> #include <linux/init.h> @@ -28,7 +29,7 @@ static struct physmem_range *__get_physmem_range_ptr(u32 n) return &physmem_info.online[n]; if (unlikely(!physmem_info.online_extended)) { physmem_info.online_extended = (struct physmem_range *)physmem_alloc_range( - RR_MEM_DETECT_EXTENDED, ENTRIES_EXTENDED_MAX, sizeof(long), 0, + RR_MEM_DETECT_EXT, ENTRIES_EXTENDED_MAX, sizeof(long), 0, physmem_alloc_pos, true); } return &physmem_info.online_extended[n - MEM_INLINED_ENTRIES]; @@ -207,11 +208,16 @@ unsigned long detect_max_physmem_end(void) max_physmem_end = search_mem_end(); physmem_info.info_source = MEM_DETECT_BIN_SEARCH; } + boot_debug("Max physical memory: 0x%016lx (info source: %s)\n", max_physmem_end, + get_physmem_info_source()); return max_physmem_end; } void detect_physmem_online_ranges(unsigned long max_physmem_end) { + unsigned long start, end; + int i; + if (!sclp_early_read_storage_info()) { physmem_info.info_source = MEM_DETECT_SCLP_STOR_INFO; } else if (physmem_info.info_source == MEM_DETECT_DIAG500_STOR_LIMIT) { @@ -226,12 +232,16 @@ void detect_physmem_online_ranges(unsigned long max_physmem_end) } else if (max_physmem_end) { add_physmem_online_range(0, max_physmem_end); } + boot_debug("Online memory ranges (info source: %s):\n", get_physmem_info_source()); + for_each_physmem_online_range(i, &start, &end) + boot_debug(" online [%d]: 0x%016lx-0x%016lx\n", i, start, end); } void physmem_set_usable_limit(unsigned long limit) { physmem_info.usable = limit; physmem_alloc_pos = limit; + boot_debug("Usable memory limit: 0x%016lx\n", limit); } static void die_oom(unsigned long size, unsigned long align, unsigned long min, unsigned long max) @@ -241,38 +251,47 @@ static void die_oom(unsigned long size, unsigned long align, unsigned long min, enum reserved_range_type t; int i; - boot_printk("Linux version %s\n", kernel_version); + boot_emerg("Linux version %s\n", kernel_version); if (!is_prot_virt_guest() && early_command_line[0]) - boot_printk("Kernel command line: %s\n", early_command_line); - boot_printk("Out of memory allocating %lx bytes %lx aligned in range %lx:%lx\n", - size, align, min, max); - boot_printk("Reserved memory ranges:\n"); + boot_emerg("Kernel command line: %s\n", early_command_line); + boot_emerg("Out of memory allocating %lu bytes 0x%lx aligned in range %lx:%lx\n", + size, align, min, max); + boot_emerg("Reserved memory ranges:\n"); for_each_physmem_reserved_range(t, range, &start, &end) { - boot_printk("%016lx %016lx %s\n", start, end, get_rr_type_name(t)); + boot_emerg("%016lx %016lx %s\n", start, end, get_rr_type_name(t)); total_reserved_mem += end - start; } - boot_printk("Usable online memory ranges (info source: %s [%x]):\n", - get_physmem_info_source(), physmem_info.info_source); + boot_emerg("Usable online memory ranges (info source: %s [%d]):\n", + get_physmem_info_source(), physmem_info.info_source); for_each_physmem_usable_range(i, &start, &end) { - boot_printk("%016lx %016lx\n", start, end); + boot_emerg("%016lx %016lx\n", start, end); total_mem += end - start; } - boot_printk("Usable online memory total: %lx Reserved: %lx Free: %lx\n", - total_mem, total_reserved_mem, - total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0); + boot_emerg("Usable online memory total: %lu Reserved: %lu Free: %lu\n", + total_mem, total_reserved_mem, + total_mem > total_reserved_mem ? total_mem - total_reserved_mem : 0); print_stacktrace(current_frame_address()); - boot_printk("\n\n -- System halted\n"); + boot_emerg(" -- System halted\n"); disabled_wait(); } -void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) +static void _physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) { physmem_info.reserved[type].start = addr; physmem_info.reserved[type].end = addr + size; } +void physmem_reserve(enum reserved_range_type type, unsigned long addr, unsigned long size) +{ + _physmem_reserve(type, addr, size); + boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Reserve:", addr, addr + size, + get_rr_type_name(type)); +} + void physmem_free(enum reserved_range_type type) { + boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Free:", physmem_info.reserved[type].start, + physmem_info.reserved[type].end, get_rr_type_name(type)); physmem_info.reserved[type].start = 0; physmem_info.reserved[type].end = 0; } @@ -339,41 +358,73 @@ unsigned long physmem_alloc_range(enum reserved_range_type type, unsigned long s max = min(max, physmem_alloc_pos); addr = __physmem_alloc_range(size, align, min, max, 0, NULL, die_on_oom); if (addr) - physmem_reserve(type, addr, size); + _physmem_reserve(type, addr, size); + boot_debug("%-14s 0x%016lx-0x%016lx %s\n", "Alloc range:", addr, addr + size, + get_rr_type_name(type)); return addr; } -unsigned long physmem_alloc_top_down(enum reserved_range_type type, unsigned long size, - unsigned long align) +unsigned long physmem_alloc(enum reserved_range_type type, unsigned long size, + unsigned long align, bool die_on_oom) { struct reserved_range *range = &physmem_info.reserved[type]; - struct reserved_range *new_range; + struct reserved_range *new_range = NULL; unsigned int ranges_left; unsigned long addr; addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, physmem_alloc_ranges, - &ranges_left, true); + &ranges_left, die_on_oom); + if (!addr) + return 0; /* if not a consecutive allocation of the same type or first allocation */ if (range->start != addr + size) { if (range->end) { - physmem_alloc_pos = __physmem_alloc_range( - sizeof(struct reserved_range), 0, 0, physmem_alloc_pos, - physmem_alloc_ranges, &ranges_left, true); - new_range = (struct reserved_range *)physmem_alloc_pos; + addr = __physmem_alloc_range(sizeof(struct reserved_range), 0, 0, + physmem_alloc_pos, physmem_alloc_ranges, + &ranges_left, true); + new_range = (struct reserved_range *)addr; + addr = __physmem_alloc_range(size, align, 0, addr, ranges_left, + &ranges_left, die_on_oom); + if (!addr) + return 0; *new_range = *range; range->chain = new_range; - addr = __physmem_alloc_range(size, align, 0, physmem_alloc_pos, - ranges_left, &ranges_left, true); } range->end = addr + size; } + if (type != RR_VMEM) { + boot_debug("%-14s 0x%016lx-0x%016lx %-20s align 0x%lx split %d\n", "Alloc topdown:", + addr, addr + size, get_rr_type_name(type), align, !!new_range); + } range->start = addr; physmem_alloc_pos = addr; physmem_alloc_ranges = ranges_left; return addr; } +unsigned long physmem_alloc_or_die(enum reserved_range_type type, unsigned long size, + unsigned long align) +{ + return physmem_alloc(type, size, align, true); +} + unsigned long get_physmem_alloc_pos(void) { return physmem_alloc_pos; } + +void dump_physmem_reserved(void) +{ + struct reserved_range *range; + enum reserved_range_type t; + unsigned long start, end; + + boot_debug("Reserved memory ranges:\n"); + for_each_physmem_reserved_range(t, range, &start, &end) { + if (end) { + boot_debug("%-14s 0x%016lx-0x%016lx @%012lx chain %012lx\n", + get_rr_type_name(t), start, end, (unsigned long)range, + (unsigned long)range->chain); + } + } +} diff --git a/arch/s390/boot/printk.c b/arch/s390/boot/printk.c index 35f18f2b936e..b4c66fa667d5 100644 --- a/arch/s390/boot/printk.c +++ b/arch/s390/boot/printk.c @@ -5,21 +5,111 @@ #include <linux/ctype.h> #include <asm/stacktrace.h> #include <asm/boot_data.h> +#include <asm/sections.h> #include <asm/lowcore.h> #include <asm/setup.h> #include <asm/sclp.h> #include <asm/uv.h> #include "boot.h" +int boot_console_loglevel = CONFIG_CONSOLE_LOGLEVEL_DEFAULT; +bool boot_ignore_loglevel; +char __bootdata(boot_rb)[PAGE_SIZE * 2]; +bool __bootdata(boot_earlyprintk); +size_t __bootdata(boot_rb_off); +char __bootdata(bootdebug_filter)[128]; +bool __bootdata(bootdebug); + +static void boot_rb_add(const char *str, size_t len) +{ + /* leave double '\0' in the end */ + size_t avail = sizeof(boot_rb) - boot_rb_off - 1; + + /* store strings separated by '\0' */ + if (len + 1 > avail) + boot_rb_off = 0; + strcpy(boot_rb + boot_rb_off, str); + boot_rb_off += len + 1; +} + +static void print_rb_entry(const char *str) +{ + sclp_early_printk(printk_skip_level(str)); +} + +static bool debug_messages_printed(void) +{ + return boot_earlyprintk && (boot_ignore_loglevel || boot_console_loglevel > LOGLEVEL_DEBUG); +} + +void boot_rb_dump(void) +{ + if (debug_messages_printed()) + return; + sclp_early_printk("Boot messages ring buffer:\n"); + boot_rb_foreach(print_rb_entry); +} + const char hex_asc[] = "0123456789abcdef"; static char *as_hex(char *dst, unsigned long val, int pad) { - char *p, *end = p = dst + max(pad, (int)__fls(val | 1) / 4 + 1); + char *p = dst + max(pad, (int)__fls(val | 1) / 4 + 1); - for (*p-- = 0; p >= dst; val >>= 4) + for (*p-- = '\0'; p >= dst; val >>= 4) *p-- = hex_asc[val & 0x0f]; - return end; + return dst; +} + +#define MAX_NUMLEN 21 +static char *as_dec(char *buf, unsigned long val, bool is_signed) +{ + bool negative = false; + char *p = buf + MAX_NUMLEN; + + if (is_signed && (long)val < 0) { + val = (val == LONG_MIN ? LONG_MIN : -(long)val); + negative = true; + } + + *--p = '\0'; + do { + *--p = '0' + (val % 10); + val /= 10; + } while (val); + + if (negative) + *--p = '-'; + return p; +} + +static ssize_t strpad(char *dst, size_t dst_size, const char *src, + int _pad, bool zero_pad, bool decimal) +{ + ssize_t len = strlen(src), pad = _pad; + char *p = dst; + + if (max(len, abs(pad)) >= dst_size) + return -E2BIG; + + if (pad > len) { + if (decimal && zero_pad && *src == '-') { + *p++ = '-'; + src++; + len--; + pad--; + } + memset(p, zero_pad ? '0' : ' ', pad - len); + p += pad - len; + } + memcpy(p, src, len); + p += len; + if (pad < 0 && -pad > len) { + memset(p, ' ', -pad - len); + p += -pad - len; + } + *p = '\0'; + return p - dst; } static char *symstart(char *p) @@ -58,35 +148,94 @@ static noinline char *findsym(unsigned long ip, unsigned short *off, unsigned sh return NULL; } -static noinline char *strsym(void *ip) +#define MAX_SYMLEN 64 +static noinline char *strsym(char *buf, void *ip) { - static char buf[64]; unsigned short off; unsigned short len; char *p; p = findsym((unsigned long)ip, &off, &len); if (p) { - strncpy(buf, p, sizeof(buf)); + strncpy(buf, p, MAX_SYMLEN); /* reserve 15 bytes for offset/len in symbol+0x1234/0x1234 */ - p = buf + strnlen(buf, sizeof(buf) - 15); + p = buf + strnlen(buf, MAX_SYMLEN - 15); strcpy(p, "+0x"); - p = as_hex(p + 3, off, 0); - strcpy(p, "/0x"); - as_hex(p + 3, len, 0); + as_hex(p + 3, off, 0); + strcat(p, "/0x"); + as_hex(p + strlen(p), len, 0); } else { as_hex(buf, (unsigned long)ip, 16); } return buf; } -void boot_printk(const char *fmt, ...) +static inline int printk_loglevel(const char *buf) +{ + if (buf[0] == KERN_SOH_ASCII && buf[1]) { + switch (buf[1]) { + case '0' ... '7': + return buf[1] - '0'; + } + } + return MESSAGE_LOGLEVEL_DEFAULT; +} + +static void boot_console_earlyprintk(const char *buf) +{ + int level = printk_loglevel(buf); + + /* always print emergency messages */ + if (level > LOGLEVEL_EMERG && !boot_earlyprintk) + return; + buf = printk_skip_level(buf); + /* print debug messages only when bootdebug is enabled */ + if (level == LOGLEVEL_DEBUG && (!bootdebug || !bootdebug_filter_match(skip_timestamp(buf)))) + return; + if (boot_ignore_loglevel || level < boot_console_loglevel) + sclp_early_printk(buf); +} + +static char *add_timestamp(char *buf) +{ +#ifdef CONFIG_PRINTK_TIME + union tod_clock *boot_clock = (union tod_clock *)&get_lowcore()->boot_clock; + unsigned long ns = tod_to_ns(get_tod_clock() - boot_clock->tod); + char ts[MAX_NUMLEN]; + + *buf++ = '['; + buf += strpad(buf, MAX_NUMLEN, as_dec(ts, ns / NSEC_PER_SEC, 0), 5, 0, 0); + *buf++ = '.'; + buf += strpad(buf, MAX_NUMLEN, as_dec(ts, (ns % NSEC_PER_SEC) / NSEC_PER_USEC, 0), 6, 1, 0); + *buf++ = ']'; + *buf++ = ' '; +#endif + return buf; +} + +#define va_arg_len_type(args, lenmod, typemod) \ + ((lenmod == 'l') ? va_arg(args, typemod long) : \ + (lenmod == 'h') ? (typemod short)va_arg(args, typemod int) : \ + (lenmod == 'H') ? (typemod char)va_arg(args, typemod int) : \ + (lenmod == 'z') ? va_arg(args, typemod long) : \ + va_arg(args, typemod int)) + +int boot_printk(const char *fmt, ...) { char buf[1024] = { 0 }; char *end = buf + sizeof(buf) - 1; /* make sure buf is 0 terminated */ - unsigned long pad; - char *p = buf; + bool zero_pad, decimal; + char *strval, *p = buf; + char valbuf[MAX(MAX_SYMLEN, MAX_NUMLEN)]; va_list args; + char lenmod; + ssize_t len; + int pad; + + *p++ = KERN_SOH_ASCII; + *p++ = printk_get_level(fmt) ?: '0' + MESSAGE_LOGLEVEL_DEFAULT; + p = add_timestamp(p); + fmt = printk_skip_level(fmt); va_start(args, fmt); for (; p < end && *fmt; fmt++) { @@ -94,31 +243,56 @@ void boot_printk(const char *fmt, ...) *p++ = *fmt; continue; } - pad = isdigit(*++fmt) ? simple_strtol(fmt, (char **)&fmt, 10) : 0; + if (*++fmt == '%') { + *p++ = '%'; + continue; + } + zero_pad = (*fmt == '0'); + pad = simple_strtol(fmt, (char **)&fmt, 10); + lenmod = (*fmt == 'h' || *fmt == 'l' || *fmt == 'z') ? *fmt++ : 0; + if (lenmod == 'h' && *fmt == 'h') { + lenmod = 'H'; + fmt++; + } + decimal = false; switch (*fmt) { case 's': - p = buf + strlcat(buf, va_arg(args, char *), sizeof(buf)); + if (lenmod) + goto out; + strval = va_arg(args, char *); + zero_pad = false; break; case 'p': - if (*++fmt != 'S') + if (*++fmt != 'S' || lenmod) goto out; - p = buf + strlcat(buf, strsym(va_arg(args, void *)), sizeof(buf)); + strval = strsym(valbuf, va_arg(args, void *)); + zero_pad = false; break; - case 'l': - if (*++fmt != 'x' || end - p <= max(sizeof(long) * 2, pad)) - goto out; - p = as_hex(p, va_arg(args, unsigned long), pad); + case 'd': + case 'i': + strval = as_dec(valbuf, va_arg_len_type(args, lenmod, signed), 1); + decimal = true; + break; + case 'u': + strval = as_dec(valbuf, va_arg_len_type(args, lenmod, unsigned), 0); break; case 'x': - if (end - p <= max(sizeof(int) * 2, pad)) - goto out; - p = as_hex(p, va_arg(args, unsigned int), pad); + strval = as_hex(valbuf, va_arg_len_type(args, lenmod, unsigned), 0); break; default: goto out; } + len = strpad(p, end - p, strval, pad, zero_pad, decimal); + if (len == -E2BIG) + break; + p += len; } out: va_end(args); - sclp_early_printk(buf); + len = strlen(buf); + if (len) { + boot_rb_add(buf, len); + boot_console_earlyprintk(buf); + } + return len; } diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index e6b06692ddc8..885bd1dd2c82 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define boot_fmt(fmt) "startup: " fmt #include <linux/string.h> #include <linux/elf.h> #include <asm/page-states.h> @@ -42,7 +43,8 @@ struct machine_info machine; void error(char *x) { - boot_printk("\n\n%s\n\n -- System halted", x); + boot_emerg("%s\n", x); + boot_emerg(" -- System halted\n"); disabled_wait(); } @@ -143,7 +145,7 @@ static void rescue_initrd(unsigned long min, unsigned long max) return; old_addr = addr; physmem_free(RR_INITRD); - addr = physmem_alloc_top_down(RR_INITRD, size, 0); + addr = physmem_alloc_or_die(RR_INITRD, size, 0); memmove((void *)addr, (void *)old_addr, size); } @@ -222,12 +224,16 @@ static void setup_ident_map_size(unsigned long max_physmem_end) if (oldmem_data.start) { __kaslr_enabled = 0; ident_map_size = min(ident_map_size, oldmem_data.size); + boot_debug("kdump memory limit: 0x%016lx\n", oldmem_data.size); } else if (ipl_block_valid && is_ipl_block_dump()) { __kaslr_enabled = 0; - if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size) + if (!sclp_early_get_hsa_size(&hsa_size) && hsa_size) { ident_map_size = min(ident_map_size, hsa_size); + boot_debug("Stand-alone dump limit: 0x%016lx\n", hsa_size); + } } #endif + boot_debug("Identity map size: 0x%016lx\n", ident_map_size); } #define FIXMAP_SIZE round_up(MEMCPY_REAL_SIZE + ABS_LOWCORE_MAP_SIZE, sizeof(struct lowcore)) @@ -267,6 +273,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE)); BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE); vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE); + boot_debug("vmem size estimated: 0x%016lx\n", vsize); if (IS_ENABLED(CONFIG_KASAN) || __NO_KASLR_END_KERNEL > _REGION2_SIZE || (vsize > _REGION2_SIZE && kaslr_enabled())) { asce_limit = _REGION1_SIZE; @@ -290,8 +297,10 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) * otherwise asce_limit and rte_size would have been adjusted. */ vmax = adjust_to_uv_max(asce_limit); + boot_debug("%d level paging 0x%016lx vmax\n", vmax == _REGION1_SIZE ? 4 : 3, vmax); #ifdef CONFIG_KASAN BUILD_BUG_ON(__NO_KASLR_END_KERNEL > KASAN_SHADOW_START); + boot_debug("KASAN shadow area: 0x%016lx-0x%016lx\n", KASAN_SHADOW_START, KASAN_SHADOW_END); /* force vmalloc and modules below kasan shadow */ vmax = min(vmax, KASAN_SHADOW_START); #endif @@ -305,19 +314,27 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) pos = 0; kernel_end = vmax - pos * THREAD_SIZE; kernel_start = round_down(kernel_end - kernel_size, THREAD_SIZE); + boot_debug("Randomization range: 0x%016lx-0x%016lx\n", vmax - kaslr_len, vmax); + boot_debug("kernel image: 0x%016lx-0x%016lx (kaslr)\n", kernel_start, + kernel_size + kernel_size); } else if (vmax < __NO_KASLR_END_KERNEL || vsize > __NO_KASLR_END_KERNEL) { kernel_start = round_down(vmax - kernel_size, THREAD_SIZE); - boot_printk("The kernel base address is forced to %lx\n", kernel_start); + boot_debug("kernel image: 0x%016lx-0x%016lx (constrained)\n", kernel_start, + kernel_start + kernel_size); } else { kernel_start = __NO_KASLR_START_KERNEL; + boot_debug("kernel image: 0x%016lx-0x%016lx (nokaslr)\n", kernel_start, + kernel_start + kernel_size); } __kaslr_offset = kernel_start; + boot_debug("__kaslr_offset: 0x%016lx\n", __kaslr_offset); MODULES_END = round_down(kernel_start, _SEGMENT_SIZE); MODULES_VADDR = MODULES_END - MODULES_LEN; VMALLOC_END = MODULES_VADDR; if (IS_ENABLED(CONFIG_KMSAN)) VMALLOC_END -= MODULES_LEN * 2; + boot_debug("modules area: 0x%016lx-0x%016lx\n", MODULES_VADDR, MODULES_END); /* allow vmalloc area to occupy up to about 1/2 of the rest virtual space left */ vsize = (VMALLOC_END - FIXMAP_SIZE) / 2; @@ -329,10 +346,15 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) VMALLOC_END -= vmalloc_size * 2; } VMALLOC_START = VMALLOC_END - vmalloc_size; + boot_debug("vmalloc area: 0x%016lx-0x%016lx\n", VMALLOC_START, VMALLOC_END); __memcpy_real_area = round_down(VMALLOC_START - MEMCPY_REAL_SIZE, PAGE_SIZE); + boot_debug("memcpy real area: 0x%016lx-0x%016lx\n", __memcpy_real_area, + __memcpy_real_area + MEMCPY_REAL_SIZE); __abs_lowcore = round_down(__memcpy_real_area - ABS_LOWCORE_MAP_SIZE, sizeof(struct lowcore)); + boot_debug("abs lowcore: 0x%016lx-0x%016lx\n", __abs_lowcore, + __abs_lowcore + ABS_LOWCORE_MAP_SIZE); /* split remaining virtual space between 1:1 mapping & vmemmap array */ pages = __abs_lowcore / (PAGE_SIZE + sizeof(struct page)); @@ -352,8 +374,11 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size) BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS)); max_mappable = max(ident_map_size, MAX_DCSS_ADDR); max_mappable = min(max_mappable, vmemmap_start); - if (IS_ENABLED(CONFIG_RANDOMIZE_IDENTITY_BASE)) - __identity_base = round_down(vmemmap_start - max_mappable, rte_size); +#ifdef CONFIG_RANDOMIZE_IDENTITY_BASE + __identity_base = round_down(vmemmap_start - max_mappable, rte_size); +#endif + boot_debug("identity map: 0x%016lx-0x%016lx\n", __identity_base, + __identity_base + ident_map_size); return asce_limit; } @@ -412,6 +437,10 @@ void startup_kernel(void) psw_t psw; setup_lpp(); + store_ipl_parmblock(); + uv_query_info(); + setup_boot_command_line(); + parse_boot_command_line(); /* * Non-randomized kernel physical start address must be _SEGMENT_SIZE @@ -431,12 +460,8 @@ void startup_kernel(void) oldmem_data.start = parmarea.oldmem_base; oldmem_data.size = parmarea.oldmem_size; - store_ipl_parmblock(); read_ipl_report(); - uv_query_info(); sclp_early_read_info(); - setup_boot_command_line(); - parse_boot_command_line(); detect_facilities(); cmma_init(); sanitize_prot_virt_host(); @@ -526,6 +551,7 @@ void startup_kernel(void) __kaslr_offset, __kaslr_offset_phys); kaslr_adjust_got(__kaslr_offset); setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit); + dump_physmem_reserved(); copy_bootdata(); __apply_alternatives((struct alt_instr *)_vmlinux_info.alt_instructions, (struct alt_instr *)_vmlinux_info.alt_instructions_end, @@ -542,5 +568,6 @@ void startup_kernel(void) */ psw.addr = __kaslr_offset + vmlinux.entry; psw.mask = PSW_KERNEL_BITS; + boot_debug("Starting kernel at: 0x%016lx\n", psw.addr); __load_psw(psw); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 881a1ece422f..cfca94a8eac4 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define boot_fmt(fmt) "vmem: " fmt #include <linux/sched/task.h> #include <linux/pgtable.h> #include <linux/kasan.h> @@ -13,6 +14,7 @@ #include "decompressor.h" #include "boot.h" +#define INVALID_PHYS_ADDR (~(phys_addr_t)0) struct ctlreg __bootdata_preserved(s390_invalid_asce); #ifdef CONFIG_PROC_FS @@ -31,12 +33,42 @@ enum populate_mode { POPULATE_IDENTITY, POPULATE_KERNEL, #ifdef CONFIG_KASAN + /* KASAN modes should be last and grouped together, see is_kasan_populate_mode() */ POPULATE_KASAN_MAP_SHADOW, POPULATE_KASAN_ZERO_SHADOW, POPULATE_KASAN_SHALLOW #endif }; +#define POPULATE_MODE_NAME(t) case POPULATE_ ## t: return #t +static inline const char *get_populate_mode_name(enum populate_mode t) +{ + switch (t) { + POPULATE_MODE_NAME(NONE); + POPULATE_MODE_NAME(DIRECT); + POPULATE_MODE_NAME(LOWCORE); + POPULATE_MODE_NAME(ABS_LOWCORE); + POPULATE_MODE_NAME(IDENTITY); + POPULATE_MODE_NAME(KERNEL); +#ifdef CONFIG_KASAN + POPULATE_MODE_NAME(KASAN_MAP_SHADOW); + POPULATE_MODE_NAME(KASAN_ZERO_SHADOW); + POPULATE_MODE_NAME(KASAN_SHALLOW); +#endif + default: + return "UNKNOWN"; + } +} + +static bool is_kasan_populate_mode(enum populate_mode mode) +{ +#ifdef CONFIG_KASAN + return mode >= POPULATE_KASAN_MAP_SHADOW; +#else + return false; +#endif +} + static void pgtable_populate(unsigned long addr, unsigned long end, enum populate_mode mode); #ifdef CONFIG_KASAN @@ -52,9 +84,12 @@ static pte_t pte_z; static inline void kasan_populate(unsigned long start, unsigned long end, enum populate_mode mode) { - start = PAGE_ALIGN_DOWN(__sha(start)); - end = PAGE_ALIGN(__sha(end)); - pgtable_populate(start, end, mode); + unsigned long sha_start = PAGE_ALIGN_DOWN(__sha(start)); + unsigned long sha_end = PAGE_ALIGN(__sha(end)); + + boot_debug("%-17s 0x%016lx-0x%016lx >> 0x%016lx-0x%016lx\n", get_populate_mode_name(mode), + start, end, sha_start, sha_end); + pgtable_populate(sha_start, sha_end, mode); } static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kernel_end) @@ -200,7 +235,7 @@ static void *boot_crst_alloc(unsigned long val) unsigned long size = PAGE_SIZE << CRST_ALLOC_ORDER; unsigned long *table; - table = (unsigned long *)physmem_alloc_top_down(RR_VMEM, size, size); + table = (unsigned long *)physmem_alloc_or_die(RR_VMEM, size, size); crst_table_init(table, val); __arch_set_page_dat(table, 1UL << CRST_ALLOC_ORDER); return table; @@ -216,7 +251,7 @@ static pte_t *boot_pte_alloc(void) * during POPULATE_KASAN_MAP_SHADOW when EDAT is off */ if (!pte_leftover) { - pte_leftover = (void *)physmem_alloc_top_down(RR_VMEM, PAGE_SIZE, PAGE_SIZE); + pte_leftover = (void *)physmem_alloc_or_die(RR_VMEM, PAGE_SIZE, PAGE_SIZE); pte = pte_leftover + _PAGE_TABLE_SIZE; __arch_set_page_dat(pte, 1); } else { @@ -228,11 +263,12 @@ static pte_t *boot_pte_alloc(void) return pte; } -static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_mode mode) +static unsigned long resolve_pa_may_alloc(unsigned long addr, unsigned long size, + enum populate_mode mode) { switch (mode) { case POPULATE_NONE: - return -1; + return INVALID_PHYS_ADDR; case POPULATE_DIRECT: return addr; case POPULATE_LOWCORE: @@ -245,38 +281,64 @@ static unsigned long _pa(unsigned long addr, unsigned long size, enum populate_m return __identity_pa(addr); #ifdef CONFIG_KASAN case POPULATE_KASAN_MAP_SHADOW: - addr = physmem_alloc_top_down(RR_VMEM, size, size); - memset((void *)addr, 0, size); - return addr; + /* Allow to fail large page allocations, this will fall back to 1mb/4k pages */ + addr = physmem_alloc(RR_VMEM, size, size, size == PAGE_SIZE); + if (addr) { + memset((void *)addr, 0, size); + return addr; + } + return INVALID_PHYS_ADDR; #endif default: - return -1; + return INVALID_PHYS_ADDR; } } -static bool large_allowed(enum populate_mode mode) +static bool large_page_mapping_allowed(enum populate_mode mode) { - return (mode == POPULATE_DIRECT) || (mode == POPULATE_IDENTITY) || (mode == POPULATE_KERNEL); + switch (mode) { + case POPULATE_DIRECT: + case POPULATE_IDENTITY: + case POPULATE_KERNEL: +#ifdef CONFIG_KASAN + case POPULATE_KASAN_MAP_SHADOW: +#endif + return true; + default: + return false; + } } -static bool can_large_pud(pud_t *pu_dir, unsigned long addr, unsigned long end, - enum populate_mode mode) +static unsigned long try_get_large_pud_pa(pud_t *pu_dir, unsigned long addr, unsigned long end, + enum populate_mode mode) { - unsigned long size = end - addr; + unsigned long pa, size = end - addr; + + if (!machine.has_edat2 || !large_page_mapping_allowed(mode) || + !IS_ALIGNED(addr, PUD_SIZE) || (size < PUD_SIZE)) + return INVALID_PHYS_ADDR; + + pa = resolve_pa_may_alloc(addr, size, mode); + if (!IS_ALIGNED(pa, PUD_SIZE)) + return INVALID_PHYS_ADDR; - return machine.has_edat2 && large_allowed(mode) && - IS_ALIGNED(addr, PUD_SIZE) && (size >= PUD_SIZE) && - IS_ALIGNED(_pa(addr, size, mode), PUD_SIZE); + return pa; } -static bool can_large_pmd(pmd_t *pm_dir, unsigned long addr, unsigned long end, - enum populate_mode mode) +static unsigned long try_get_large_pmd_pa(pmd_t *pm_dir, unsigned long addr, unsigned long end, + enum populate_mode mode) { - unsigned long size = end - addr; + unsigned long pa, size = end - addr; - return machine.has_edat1 && large_allowed(mode) && - IS_ALIGNED(addr, PMD_SIZE) && (size >= PMD_SIZE) && - IS_ALIGNED(_pa(addr, size, mode), PMD_SIZE); + if (!machine.has_edat1 || !large_page_mapping_allowed(mode) || + !IS_ALIGNED(addr, PMD_SIZE) || (size < PMD_SIZE)) + return INVALID_PHYS_ADDR; + + pa = resolve_pa_may_alloc(addr, size, mode); + if (!IS_ALIGNED(pa, PMD_SIZE)) + return INVALID_PHYS_ADDR; + + return pa; } static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long end, @@ -290,7 +352,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e if (pte_none(*pte)) { if (kasan_pte_populate_zero_shadow(pte, mode)) continue; - entry = __pte(_pa(addr, PAGE_SIZE, mode)); + entry = __pte(resolve_pa_may_alloc(addr, PAGE_SIZE, mode)); entry = set_pte_bit(entry, PAGE_KERNEL); set_pte(pte, entry); pages++; @@ -303,7 +365,7 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long end, enum populate_mode mode) { - unsigned long next, pages = 0; + unsigned long pa, next, pages = 0; pmd_t *pmd, entry; pte_t *pte; @@ -313,8 +375,9 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e if (pmd_none(*pmd)) { if (kasan_pmd_populate_zero_shadow(pmd, addr, next, mode)) continue; - if (can_large_pmd(pmd, addr, next, mode)) { - entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode)); + pa = try_get_large_pmd_pa(pmd, addr, next, mode); + if (pa != INVALID_PHYS_ADDR) { + entry = __pmd(pa); entry = set_pmd_bit(entry, SEGMENT_KERNEL); set_pmd(pmd, entry); pages++; @@ -334,7 +397,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long end, enum populate_mode mode) { - unsigned long next, pages = 0; + unsigned long pa, next, pages = 0; pud_t *pud, entry; pmd_t *pmd; @@ -344,8 +407,9 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e if (pud_none(*pud)) { if (kasan_pud_populate_zero_shadow(pud, addr, next, mode)) continue; - if (can_large_pud(pud, addr, next, mode)) { - entry = __pud(_pa(addr, _REGION3_SIZE, mode)); + pa = try_get_large_pud_pa(pud, addr, next, mode); + if (pa != INVALID_PHYS_ADDR) { + entry = __pud(pa); entry = set_pud_bit(entry, REGION3_KERNEL); set_pud(pud, entry); pages++; @@ -388,6 +452,13 @@ static void pgtable_populate(unsigned long addr, unsigned long end, enum populat pgd_t *pgd; p4d_t *p4d; + if (!is_kasan_populate_mode(mode)) { + boot_debug("%-17s 0x%016lx-0x%016lx -> 0x%016lx-0x%016lx\n", + get_populate_mode_name(mode), addr, end, + resolve_pa_may_alloc(addr, 0, mode), + resolve_pa_may_alloc(end - 1, 0, mode) + 1); + } + pgd = pgd_offset(&init_mm, addr); for (; addr < end; addr = next, pgd++) { next = pgd_addr_end(addr, end); diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index d6beec5292a0..44f01a4bc810 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -740,7 +740,6 @@ CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y -CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_USER=m # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8cfbfb10bba8..8bcd37edd3c9 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -725,7 +725,6 @@ CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y CONFIG_IMA_APPRAISE=y -CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor" CONFIG_BUG_ON_DATA_CORRUPTION=y CONFIG_CRYPTO_FIPS=y CONFIG_CRYPTO_USER=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index bcbaa069de96..853b2326a171 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -62,7 +62,6 @@ CONFIG_ZFCP=y # CONFIG_INOTIFY_USER is not set # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_LSM="yama,loadpin,safesetid,integrity" # CONFIG_ZLIB_DFLTCC is not set CONFIG_XZ_DEC_MICROLZMA=y CONFIG_PRINTK_TIME=y diff --git a/arch/s390/include/asm/asm-extable.h b/arch/s390/include/asm/asm-extable.h index 4a6b0a8b6412..2e829c16fd8a 100644 --- a/arch/s390/include/asm/asm-extable.h +++ b/arch/s390/include/asm/asm-extable.h @@ -9,11 +9,11 @@ #define EX_TYPE_NONE 0 #define EX_TYPE_FIXUP 1 #define EX_TYPE_BPF 2 -#define EX_TYPE_UA_STORE 3 -#define EX_TYPE_UA_LOAD_MEM 4 +#define EX_TYPE_UA_FAULT 3 #define EX_TYPE_UA_LOAD_REG 5 #define EX_TYPE_UA_LOAD_REGPAIR 6 #define EX_TYPE_ZEROPAD 7 +#define EX_TYPE_FPC 8 #define EX_DATA_REG_ERR_SHIFT 0 #define EX_DATA_REG_ERR GENMASK(3, 0) @@ -69,11 +69,8 @@ #define EX_TABLE_AMODE31(_fault, _target) \ __EX_TABLE(.amode31.ex_table, _fault, _target, EX_TYPE_FIXUP, __stringify(%%r0), __stringify(%%r0), 0) -#define EX_TABLE_UA_STORE(_fault, _target, _regerr) \ - __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_STORE, _regerr, _regerr, 0) - -#define EX_TABLE_UA_LOAD_MEM(_fault, _target, _regerr, _regmem, _len) \ - __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_MEM, _regerr, _regmem, _len) +#define EX_TABLE_UA_FAULT(_fault, _target, _regerr) \ + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_FAULT, _regerr, _regerr, 0) #define EX_TABLE_UA_LOAD_REG(_fault, _target, _regerr, _regzero) \ __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_UA_LOAD_REG, _regerr, _regzero, 0) @@ -84,4 +81,7 @@ #define EX_TABLE_ZEROPAD(_fault, _target, _regdata, _regaddr) \ __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_ZEROPAD, _regdata, _regaddr, 0) +#define EX_TABLE_FPC(_fault, _target) \ + __EX_TABLE(__ex_table, _fault, _target, EX_TYPE_FPC, __stringify(%%r0), __stringify(%%r0), 0) + #endif /* __ASM_EXTABLE_H */ diff --git a/arch/s390/include/asm/asm.h b/arch/s390/include/asm/asm.h index ec011b94af2a..e9062b01e2a2 100644 --- a/arch/s390/include/asm/asm.h +++ b/arch/s390/include/asm/asm.h @@ -28,7 +28,7 @@ * [var] also contains the program mask. CC_TRANSFORM() moves the condition * code to the two least significant bits and sets all other bits to zero. */ -#if defined(__GCC_ASM_FLAG_OUTPUTS__) && !(IS_ENABLED(CONFIG_GCC_ASM_FLAG_OUTPUT_BROKEN)) +#if defined(__GCC_ASM_FLAG_OUTPUTS__) && !(IS_ENABLED(CONFIG_CC_ASM_FLAG_OUTPUT_BROKEN)) #define __HAVE_ASM_FLAG_OUTPUTS__ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 15aa64e3020e..a5ca0a947691 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -53,14 +53,18 @@ static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsig unsigned long mask; int cc; - if (__builtin_constant_p(nr)) { + /* + * With CONFIG_PROFILE_ALL_BRANCHES enabled gcc fails to + * handle __builtin_constant_p() in some cases. + */ + if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && __builtin_constant_p(nr)) { addr = (const volatile unsigned char *)ptr; addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE; mask = 1UL << (nr & (BITS_PER_BYTE - 1)); asm volatile( " tm %[addr],%[mask]\n" : "=@cc" (cc) - : [addr] "R" (*addr), [mask] "I" (mask) + : [addr] "Q" (*addr), [mask] "I" (mask) ); return cc == 3; } diff --git a/arch/s390/include/asm/boot_data.h b/arch/s390/include/asm/boot_data.h index f7eed27b3220..f55f8227058e 100644 --- a/arch/s390/include/asm/boot_data.h +++ b/arch/s390/include/asm/boot_data.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_S390_BOOT_DATA_H +#include <linux/string.h> #include <asm/setup.h> #include <asm/ipl.h> @@ -15,4 +16,54 @@ extern unsigned long ipl_cert_list_size; extern unsigned long early_ipl_comp_list_addr; extern unsigned long early_ipl_comp_list_size; +extern char boot_rb[PAGE_SIZE * 2]; +extern bool boot_earlyprintk; +extern size_t boot_rb_off; +extern char bootdebug_filter[128]; +extern bool bootdebug; + +#define boot_rb_foreach(cb) \ + do { \ + size_t off = boot_rb_off + strlen(boot_rb + boot_rb_off) + 1; \ + size_t len; \ + for (; off < sizeof(boot_rb) && (len = strlen(boot_rb + off)); off += len + 1) \ + cb(boot_rb + off); \ + for (off = 0; off < boot_rb_off && (len = strlen(boot_rb + off)); off += len + 1) \ + cb(boot_rb + off); \ + } while (0) + +/* + * bootdebug_filter is a comma separated list of strings, + * where each string can be a prefix of the message. + */ +static inline bool bootdebug_filter_match(const char *buf) +{ + char *p = bootdebug_filter, *s; + char *end; + + if (!*p) + return true; + + end = p + strlen(p); + while (p < end) { + p = skip_spaces(p); + s = memscan(p, ',', end - p); + if (!strncmp(p, buf, s - p)) + return true; + p = s + 1; + } + return false; +} + +static inline const char *skip_timestamp(const char *buf) +{ +#ifdef CONFIG_PRINTK_TIME + const char *p = memchr(buf, ']', strlen(buf)); + + if (p && p[1] == ' ') + return p + 2; +#endif + return buf; +} + #endif /* _ASM_S390_BOOT_DATA_H */ diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h index de510c9f6efa..f668bffd6dd3 100644 --- a/arch/s390/include/asm/fpu-insn.h +++ b/arch/s390/include/asm/fpu-insn.h @@ -100,19 +100,12 @@ static __always_inline void fpu_lfpc(unsigned int *fpc) */ static inline void fpu_lfpc_safe(unsigned int *fpc) { - u32 tmp; - instrument_read(fpc, sizeof(*fpc)); asm_inline volatile( - "0: lfpc %[fpc]\n" - "1: nopr %%r7\n" - ".pushsection .fixup, \"ax\"\n" - "2: lghi %[tmp],0\n" - " sfpc %[tmp]\n" - " jg 1b\n" - ".popsection\n" - EX_TABLE(1b, 2b) - : [tmp] "=d" (tmp) + " lfpc %[fpc]\n" + "0: nopr %%r7\n" + EX_TABLE_FPC(0b, 0b) + : : [fpc] "Q" (*fpc) : "memory"); } @@ -183,7 +176,19 @@ static __always_inline void fpu_vgfmg(u8 v1, u8 v2, u8 v3) : "memory"); } -#ifdef CONFIG_CC_IS_CLANG +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS + +static __always_inline void fpu_vl(u8 v1, const void *vxr) +{ + instrument_read(vxr, sizeof(__vector128)); + asm volatile("VL %[v1],%O[vxr],,%R[vxr]\n" + : + : [vxr] "Q" (*(__vector128 *)vxr), + [v1] "I" (v1) + : "memory"); +} + +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vl(u8 v1, const void *vxr) { @@ -197,19 +202,7 @@ static __always_inline void fpu_vl(u8 v1, const void *vxr) : "memory", "1"); } -#else /* CONFIG_CC_IS_CLANG */ - -static __always_inline void fpu_vl(u8 v1, const void *vxr) -{ - instrument_read(vxr, sizeof(__vector128)); - asm volatile("VL %[v1],%O[vxr],,%R[vxr]\n" - : - : [vxr] "Q" (*(__vector128 *)vxr), - [v1] "I" (v1) - : "memory"); -} - -#endif /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vleib(u8 v, s16 val, u8 index) { @@ -238,7 +231,7 @@ static __always_inline u64 fpu_vlgvf(u8 v, u16 index) return val; } -#ifdef CONFIG_CC_IS_CLANG +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) { @@ -246,17 +239,15 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) size = min(index + 1, sizeof(__vector128)); instrument_read(vxr, size); - asm volatile( - " la 1,%[vxr]\n" - " VLL %[v1],%[index],0,1\n" - : - : [vxr] "R" (*(u8 *)vxr), - [index] "d" (index), - [v1] "I" (v1) - : "memory", "1"); + asm volatile("VLL %[v1],%[index],%O[vxr],%R[vxr]\n" + : + : [vxr] "Q" (*(u8 *)vxr), + [index] "d" (index), + [v1] "I" (v1) + : "memory"); } -#else /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) { @@ -264,17 +255,19 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) size = min(index + 1, sizeof(__vector128)); instrument_read(vxr, size); - asm volatile("VLL %[v1],%[index],%O[vxr],%R[vxr]\n" - : - : [vxr] "Q" (*(u8 *)vxr), - [index] "d" (index), - [v1] "I" (v1) - : "memory"); + asm volatile( + " la 1,%[vxr]\n" + " VLL %[v1],%[index],0,1\n" + : + : [vxr] "R" (*(u8 *)vxr), + [index] "d" (index), + [v1] "I" (v1) + : "memory", "1"); } -#endif /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -#ifdef CONFIG_CC_IS_CLANG +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS #define fpu_vlm(_v1, _v3, _vxrs) \ ({ \ @@ -284,17 +277,15 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) } *_v = (void *)(_vxrs); \ \ instrument_read(_v, size); \ - asm volatile( \ - " la 1,%[vxrs]\n" \ - " VLM %[v1],%[v3],0,1\n" \ - : \ - : [vxrs] "R" (*_v), \ - [v1] "I" (_v1), [v3] "I" (_v3) \ - : "memory", "1"); \ + asm volatile("VLM %[v1],%[v3],%O[vxrs],%R[vxrs]\n" \ + : \ + : [vxrs] "Q" (*_v), \ + [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory"); \ (_v3) - (_v1) + 1; \ }) -#else /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ #define fpu_vlm(_v1, _v3, _vxrs) \ ({ \ @@ -304,15 +295,17 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) } *_v = (void *)(_vxrs); \ \ instrument_read(_v, size); \ - asm volatile("VLM %[v1],%[v3],%O[vxrs],%R[vxrs]\n" \ - : \ - : [vxrs] "Q" (*_v), \ - [v1] "I" (_v1), [v3] "I" (_v3) \ - : "memory"); \ + asm volatile( \ + " la 1,%[vxrs]\n" \ + " VLM %[v1],%[v3],0,1\n" \ + : \ + : [vxrs] "R" (*_v), \ + [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory", "1"); \ (_v3) - (_v1) + 1; \ }) -#endif /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vlr(u8 v1, u8 v2) { @@ -362,7 +355,18 @@ static __always_inline void fpu_vsrlb(u8 v1, u8 v2, u8 v3) : "memory"); } -#ifdef CONFIG_CC_IS_CLANG +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS + +static __always_inline void fpu_vst(u8 v1, const void *vxr) +{ + instrument_write(vxr, sizeof(__vector128)); + asm volatile("VST %[v1],%O[vxr],,%R[vxr]\n" + : [vxr] "=Q" (*(__vector128 *)vxr) + : [v1] "I" (v1) + : "memory"); +} + +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vst(u8 v1, const void *vxr) { @@ -375,20 +379,23 @@ static __always_inline void fpu_vst(u8 v1, const void *vxr) : "memory", "1"); } -#else /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -static __always_inline void fpu_vst(u8 v1, const void *vxr) +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS + +static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) { - instrument_write(vxr, sizeof(__vector128)); - asm volatile("VST %[v1],%O[vxr],,%R[vxr]\n" - : [vxr] "=Q" (*(__vector128 *)vxr) - : [v1] "I" (v1) + unsigned int size; + + size = min(index + 1, sizeof(__vector128)); + instrument_write(vxr, size); + asm volatile("VSTL %[v1],%[index],%O[vxr],%R[vxr]\n" + : [vxr] "=Q" (*(u8 *)vxr) + : [index] "d" (index), [v1] "I" (v1) : "memory"); } -#endif /* CONFIG_CC_IS_CLANG */ - -#ifdef CONFIG_CC_IS_CLANG +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) { @@ -404,23 +411,9 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) : "memory", "1"); } -#else /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) -{ - unsigned int size; - - size = min(index + 1, sizeof(__vector128)); - instrument_write(vxr, size); - asm volatile("VSTL %[v1],%[index],%O[vxr],%R[vxr]\n" - : [vxr] "=Q" (*(u8 *)vxr) - : [index] "d" (index), [v1] "I" (v1) - : "memory"); -} - -#endif /* CONFIG_CC_IS_CLANG */ - -#ifdef CONFIG_CC_IS_CLANG +#ifdef CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS #define fpu_vstm(_v1, _v3, _vxrs) \ ({ \ @@ -430,16 +423,14 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) } *_v = (void *)(_vxrs); \ \ instrument_write(_v, size); \ - asm volatile( \ - " la 1,%[vxrs]\n" \ - " VSTM %[v1],%[v3],0,1\n" \ - : [vxrs] "=R" (*_v) \ - : [v1] "I" (_v1), [v3] "I" (_v3) \ - : "memory", "1"); \ + asm volatile("VSTM %[v1],%[v3],%O[vxrs],%R[vxrs]\n" \ + : [vxrs] "=Q" (*_v) \ + : [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory"); \ (_v3) - (_v1) + 1; \ }) -#else /* CONFIG_CC_IS_CLANG */ +#else /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ #define fpu_vstm(_v1, _v3, _vxrs) \ ({ \ @@ -449,14 +440,16 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) } *_v = (void *)(_vxrs); \ \ instrument_write(_v, size); \ - asm volatile("VSTM %[v1],%[v3],%O[vxrs],%R[vxrs]\n" \ - : [vxrs] "=Q" (*_v) \ - : [v1] "I" (_v1), [v3] "I" (_v3) \ - : "memory"); \ + asm volatile( \ + " la 1,%[vxrs]\n" \ + " VSTM %[v1],%[v3],0,1\n" \ + : [vxrs] "=R" (*_v) \ + : [v1] "I" (_v1), [v3] "I" (_v3) \ + : "memory", "1"); \ (_v3) - (_v1) + 1; \ }) -#endif /* CONFIG_CC_IS_CLANG */ +#endif /* CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ static __always_inline void fpu_vupllf(u8 v1, u8 v2) { diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index a3b73a4f626e..185331e91f83 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -51,6 +51,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) { return addr; } +#define ftrace_get_symaddr(fentry_ip) ((unsigned long)(fentry_ip)) #include <linux/ftrace_regs.h> diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index 752a2310f0d6..f5781794356b 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -2,80 +2,95 @@ #ifndef _ASM_S390_FUTEX_H #define _ASM_S390_FUTEX_H +#include <linux/instrumented.h> #include <linux/uaccess.h> #include <linux/futex.h> #include <asm/asm-extable.h> #include <asm/mmu_context.h> #include <asm/errno.h> -#define __futex_atomic_op(insn, ret, oldval, newval, uaddr, oparg) \ - asm volatile( \ - " sacf 256\n" \ - "0: l %1,0(%6)\n" \ - "1:"insn \ - "2: cs %1,%2,0(%6)\n" \ - "3: jl 1b\n" \ - " lhi %0,0\n" \ - "4: sacf 768\n" \ - EX_TABLE(0b,4b) EX_TABLE(1b,4b) \ - EX_TABLE(2b,4b) EX_TABLE(3b,4b) \ - : "=d" (ret), "=&d" (oldval), "=&d" (newval), \ - "=m" (*uaddr) \ - : "0" (-EFAULT), "d" (oparg), "a" (uaddr), \ - "m" (*uaddr) : "cc"); +#define FUTEX_OP_FUNC(name, insn) \ +static uaccess_kmsan_or_inline int \ +__futex_atomic_##name(int oparg, int *old, u32 __user *uaddr) \ +{ \ + int rc, new; \ + \ + instrument_copy_from_user_before(old, uaddr, sizeof(*old)); \ + asm_inline volatile( \ + " sacf 256\n" \ + "0: l %[old],%[uaddr]\n" \ + "1:"insn \ + "2: cs %[old],%[new],%[uaddr]\n" \ + "3: jl 1b\n" \ + " lhi %[rc],0\n" \ + "4: sacf 768\n" \ + EX_TABLE_UA_FAULT(0b, 4b, %[rc]) \ + EX_TABLE_UA_FAULT(1b, 4b, %[rc]) \ + EX_TABLE_UA_FAULT(2b, 4b, %[rc]) \ + EX_TABLE_UA_FAULT(3b, 4b, %[rc]) \ + : [rc] "=d" (rc), [old] "=&d" (*old), \ + [new] "=&d" (new), [uaddr] "+Q" (*uaddr) \ + : [oparg] "d" (oparg) \ + : "cc"); \ + if (!rc) \ + instrument_copy_from_user_after(old, uaddr, sizeof(*old), 0); \ + return rc; \ +} + +FUTEX_OP_FUNC(set, "lr %[new],%[oparg]\n") +FUTEX_OP_FUNC(add, "lr %[new],%[old]\n ar %[new],%[oparg]\n") +FUTEX_OP_FUNC(or, "lr %[new],%[old]\n or %[new],%[oparg]\n") +FUTEX_OP_FUNC(and, "lr %[new],%[old]\n nr %[new],%[oparg]\n") +FUTEX_OP_FUNC(xor, "lr %[new],%[old]\n xr %[new],%[oparg]\n") -static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, - u32 __user *uaddr) +static inline +int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { - int oldval = 0, newval, ret; + int old, rc; switch (op) { case FUTEX_OP_SET: - __futex_atomic_op("lr %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_set(oparg, &old, uaddr); break; case FUTEX_OP_ADD: - __futex_atomic_op("lr %2,%1\nar %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_add(oparg, &old, uaddr); break; case FUTEX_OP_OR: - __futex_atomic_op("lr %2,%1\nor %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_or(oparg, &old, uaddr); break; case FUTEX_OP_ANDN: - __futex_atomic_op("lr %2,%1\nnr %2,%5\n", - ret, oldval, newval, uaddr, ~oparg); + rc = __futex_atomic_and(~oparg, &old, uaddr); break; case FUTEX_OP_XOR: - __futex_atomic_op("lr %2,%1\nxr %2,%5\n", - ret, oldval, newval, uaddr, oparg); + rc = __futex_atomic_xor(oparg, &old, uaddr); break; default: - ret = -ENOSYS; + rc = -ENOSYS; } - - if (!ret) - *oval = oldval; - - return ret; + if (!rc) + *oval = old; + return rc; } -static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, - u32 oldval, u32 newval) +static uaccess_kmsan_or_inline +int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { - int ret; + int rc; - asm volatile( - " sacf 256\n" - "0: cs %1,%4,0(%5)\n" - "1: la %0,0\n" - "2: sacf 768\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) - : "=d" (ret), "+d" (oldval), "=m" (*uaddr) - : "0" (-EFAULT), "d" (newval), "a" (uaddr), "m" (*uaddr) + instrument_copy_from_user_before(uval, uaddr, sizeof(*uval)); + asm_inline volatile( + " sacf 256\n" + "0: cs %[old],%[new],%[uaddr]\n" + "1: lhi %[rc],0\n" + "2: sacf 768\n" + EX_TABLE_UA_FAULT(0b, 2b, %[rc]) + EX_TABLE_UA_FAULT(1b, 2b, %[rc]) + : [rc] "=d" (rc), [old] "+d" (oldval), [uaddr] "+Q" (*uaddr) + : [new] "d" (newval) : "cc", "memory"); *uval = oldval; - return ret; + instrument_copy_from_user_after(uval, uaddr, sizeof(*uval), 0); + return rc; } #endif /* _ASM_S390_FUTEX_H */ diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h index 13f51a6a5bb1..4e73ef46d4b2 100644 --- a/arch/s390/include/asm/gmap.h +++ b/arch/s390/include/asm/gmap.h @@ -23,7 +23,6 @@ /** * struct gmap_struct - guest address space * @list: list head for the mm->context gmap list - * @crst_list: list of all crst tables used in the guest address space * @mm: pointer to the parent mm_struct * @guest_to_host: radix tree with guest to host address translation * @host_to_guest: radix tree with pointer to segment table entries @@ -35,7 +34,6 @@ * @guest_handle: protected virtual machine handle for the ultravisor * @host_to_rmap: radix tree with gmap_rmap lists * @children: list of shadow gmap structures - * @pt_list: list of all page tables used in the shadow guest address space * @shadow_lock: spinlock to protect the shadow gmap list * @parent: pointer to the parent gmap for shadow guest address spaces * @orig_asce: ASCE for which the shadow page table has been created @@ -45,7 +43,6 @@ */ struct gmap { struct list_head list; - struct list_head crst_list; struct mm_struct *mm; struct radix_tree_root guest_to_host; struct radix_tree_root host_to_guest; @@ -61,7 +58,6 @@ struct gmap { /* Additional data for shadow guest address spaces */ struct radix_tree_root host_to_rmap; struct list_head children; - struct list_head pt_list; spinlock_t shadow_lock; struct gmap *parent; unsigned long orig_asce; @@ -106,23 +102,21 @@ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit); void gmap_remove(struct gmap *gmap); struct gmap *gmap_get(struct gmap *gmap); void gmap_put(struct gmap *gmap); +void gmap_free(struct gmap *gmap); +struct gmap *gmap_alloc(unsigned long limit); int gmap_map_segment(struct gmap *gmap, unsigned long from, unsigned long to, unsigned long len); int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len); unsigned long __gmap_translate(struct gmap *, unsigned long gaddr); -unsigned long gmap_translate(struct gmap *, unsigned long gaddr); int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr); -int gmap_fault(struct gmap *, unsigned long gaddr, unsigned int fault_flags); void gmap_discard(struct gmap *, unsigned long from, unsigned long to); void __gmap_zap(struct gmap *, unsigned long gaddr); void gmap_unlink(struct mm_struct *, unsigned long *table, unsigned long vmaddr); int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val); -struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, - int edat_level); -int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level); +void gmap_unshadow(struct gmap *sg); int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, int fake); int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, @@ -131,24 +125,22 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, int fake); int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, int fake); -int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, - unsigned long *pgt, int *dat_protection, int *fake); int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte); void gmap_register_pte_notifier(struct gmap_notifier *); void gmap_unregister_pte_notifier(struct gmap_notifier *); -int gmap_mprotect_notify(struct gmap *, unsigned long start, - unsigned long len, int prot); +int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits); void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4], unsigned long gaddr, unsigned long vmaddr); int s390_disable_cow_sharing(void); -void s390_unlist_old_asce(struct gmap *gmap); int s390_replace_asce(struct gmap *gmap); void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns); int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool interruptible); +int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split); +unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level); /** * s390_uv_destroy_range - Destroy a range of pages in the given mm. diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 97c7c8127543..9a367866cab0 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -30,6 +30,8 @@ #define KVM_S390_ESCA_CPU_SLOTS 248 #define KVM_MAX_VCPUS 255 +#define KVM_INTERNAL_MEM_SLOTS 1 + /* * These seem to be used for allocating ->chip in the routing table, which we * don't use. 1 is as small as we can get to reduce the needed memory. If we @@ -931,12 +933,14 @@ struct sie_page2 { u8 reserved928[0x1000 - 0x928]; /* 0x0928 */ }; +struct vsie_page; + struct kvm_s390_vsie { struct mutex mutex; struct radix_tree_root addr_to_page; int page_count; int next; - struct page *pages[KVM_MAX_VCPUS]; + struct vsie_page *pages[KVM_MAX_VCPUS]; }; struct kvm_s390_gisa_iam { diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 4f43cdd9835b..1ff145f7b52b 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -184,7 +184,11 @@ extern struct vm_layout vm_layout; #define __kaslr_offset vm_layout.kaslr_offset #define __kaslr_offset_phys vm_layout.kaslr_offset_phys +#ifdef CONFIG_RANDOMIZE_IDENTITY_BASE #define __identity_base vm_layout.identity_base +#else +#define __identity_base 0UL +#endif #define ident_map_size vm_layout.identity_size static inline unsigned long kaslr_offset(void) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index a3b51056a177..3ca5af4cfe43 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -420,9 +420,10 @@ void setup_protection_map(void); #define PGSTE_HC_BIT 0x0020000000000000UL #define PGSTE_GR_BIT 0x0004000000000000UL #define PGSTE_GC_BIT 0x0002000000000000UL -#define PGSTE_UC_BIT 0x0000800000000000UL /* user dirty (migration) */ -#define PGSTE_IN_BIT 0x0000400000000000UL /* IPTE notify bit */ -#define PGSTE_VSIE_BIT 0x0000200000000000UL /* ref'd in a shadow table */ +#define PGSTE_ST2_MASK 0x0000ffff00000000UL +#define PGSTE_UC_BIT 0x0000000000008000UL /* user dirty (migration) */ +#define PGSTE_IN_BIT 0x0000000000004000UL /* IPTE notify bit */ +#define PGSTE_VSIE_BIT 0x0000000000002000UL /* ref'd in a shadow table */ /* Guest Page State used for virtualization */ #define _PGSTE_GPS_ZERO 0x0000000080000000UL @@ -2007,4 +2008,18 @@ extern void s390_reset_cmma(struct mm_struct *mm); #define pmd_pgtable(pmd) \ ((pgtable_t)__va(pmd_val(pmd) & -sizeof(pte_t)*PTRS_PER_PTE)) +static inline unsigned long gmap_pgste_get_pgt_addr(unsigned long *pgt) +{ + unsigned long *pgstes, res; + + pgstes = pgt + _PAGE_ENTRIES; + + res = (pgstes[0] & PGSTE_ST2_MASK) << 16; + res |= pgstes[1] & PGSTE_ST2_MASK; + res |= (pgstes[2] & PGSTE_ST2_MASK) >> 16; + res |= (pgstes[3] & PGSTE_ST2_MASK) >> 32; + + return res; +} + #endif /* _S390_PAGE_H */ diff --git a/arch/s390/include/asm/physmem_info.h b/arch/s390/include/asm/physmem_info.h index 51b68a43e195..7ef3bbec98b0 100644 --- a/arch/s390/include/asm/physmem_info.h +++ b/arch/s390/include/asm/physmem_info.h @@ -26,7 +26,7 @@ enum reserved_range_type { RR_AMODE31, RR_IPLREPORT, RR_CERT_COMP_LIST, - RR_MEM_DETECT_EXTENDED, + RR_MEM_DETECT_EXT, RR_VMEM, RR_MAX }; @@ -128,7 +128,7 @@ static inline const char *get_rr_type_name(enum reserved_range_type t) RR_TYPE_NAME(AMODE31); RR_TYPE_NAME(IPLREPORT); RR_TYPE_NAME(CERT_COMP_LIST); - RR_TYPE_NAME(MEM_DETECT_EXTENDED); + RR_TYPE_NAME(MEM_DETECT_EXT); RR_TYPE_NAME(VMEM); default: return "UNKNOWN"; diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 4da3b2956285..18f37dff03c9 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -172,6 +172,7 @@ void sclp_early_printk(const char *s); void __sclp_early_printk(const char *s, unsigned int len); void sclp_emergency_printk(const char *s); +int sclp_init(void); int sclp_early_get_memsize(unsigned long *mem); int sclp_early_get_hsa_size(unsigned long *hsa_size); int _sclp_get_core_info(struct sclp_core_info *info); diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index a81f897a81ce..f5920163ee97 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -22,16 +22,117 @@ void debug_user_asce(int exit); -unsigned long __must_check -raw_copy_from_user(void *to, const void __user *from, unsigned long n); +union oac { + unsigned int val; + struct { + struct { + unsigned short key : 4; + unsigned short : 4; + unsigned short as : 2; + unsigned short : 4; + unsigned short k : 1; + unsigned short a : 1; + } oac1; + struct { + unsigned short key : 4; + unsigned short : 4; + unsigned short as : 2; + unsigned short : 4; + unsigned short k : 1; + unsigned short a : 1; + } oac2; + }; +}; -unsigned long __must_check -raw_copy_to_user(void __user *to, const void *from, unsigned long n); +static __always_inline __must_check unsigned long +raw_copy_from_user_key(void *to, const void __user *from, unsigned long size, unsigned long key) +{ + unsigned long rem; + union oac spec = { + .oac2.key = key, + .oac2.as = PSW_BITS_AS_SECONDARY, + .oac2.k = 1, + .oac2.a = 1, + }; -#ifndef CONFIG_KASAN -#define INLINE_COPY_FROM_USER -#define INLINE_COPY_TO_USER -#endif + asm_inline volatile( + " lr %%r0,%[spec]\n" + "0: mvcos 0(%[to]),0(%[from]),%[size]\n" + "1: jz 5f\n" + " algr %[size],%[val]\n" + " slgr %[from],%[val]\n" + " slgr %[to],%[val]\n" + " j 0b\n" + "2: la %[rem],4095(%[from])\n" /* rem = from + 4095 */ + " nr %[rem],%[val]\n" /* rem = (from + 4095) & -4096 */ + " slgr %[rem],%[from]\n" + " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ + " jnh 6f\n" + "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" + "4: slgr %[size],%[rem]\n" + " j 6f\n" + "5: lghi %[size],0\n" + "6:\n" + EX_TABLE(0b, 2b) + EX_TABLE(1b, 2b) + EX_TABLE(3b, 6b) + EX_TABLE(4b, 6b) + : [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem) + : [val] "a" (-4096UL), [spec] "d" (spec.val) + : "cc", "memory", "0"); + return size; +} + +static __always_inline __must_check unsigned long +raw_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return raw_copy_from_user_key(to, from, n, 0); +} + +static __always_inline __must_check unsigned long +raw_copy_to_user_key(void __user *to, const void *from, unsigned long size, unsigned long key) +{ + unsigned long rem; + union oac spec = { + .oac1.key = key, + .oac1.as = PSW_BITS_AS_SECONDARY, + .oac1.k = 1, + .oac1.a = 1, + }; + + asm_inline volatile( + " lr %%r0,%[spec]\n" + "0: mvcos 0(%[to]),0(%[from]),%[size]\n" + "1: jz 5f\n" + " algr %[size],%[val]\n" + " slgr %[to],%[val]\n" + " slgr %[from],%[val]\n" + " j 0b\n" + "2: la %[rem],4095(%[to])\n" /* rem = to + 4095 */ + " nr %[rem],%[val]\n" /* rem = (to + 4095) & -4096 */ + " slgr %[rem],%[to]\n" + " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ + " jnh 6f\n" + "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" + "4: slgr %[size],%[rem]\n" + " j 6f\n" + "5: lghi %[size],0\n" + "6:\n" + EX_TABLE(0b, 2b) + EX_TABLE(1b, 2b) + EX_TABLE(3b, 6b) + EX_TABLE(4b, 6b) + : [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem) + : [val] "a" (-4096UL), [spec] "d" (spec.val) + : "cc", "memory", "0"); + return size; +} + +static __always_inline __must_check unsigned long +raw_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + return raw_copy_to_user_key(to, from, n, 0); +} unsigned long __must_check _copy_from_user_key(void *to, const void __user *from, unsigned long n, unsigned long key); @@ -55,63 +156,71 @@ copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned lo return n; } -union oac { - unsigned int val; - struct { - struct { - unsigned short key : 4; - unsigned short : 4; - unsigned short as : 2; - unsigned short : 4; - unsigned short k : 1; - unsigned short a : 1; - } oac1; - struct { - unsigned short key : 4; - unsigned short : 4; - unsigned short as : 2; - unsigned short : 4; - unsigned short k : 1; - unsigned short a : 1; - } oac2; - }; -}; - int __noreturn __put_user_bad(void); #ifdef CONFIG_KMSAN -#define get_put_user_noinstr_attributes \ - noinline __maybe_unused __no_sanitize_memory +#define uaccess_kmsan_or_inline noinline __maybe_unused __no_sanitize_memory #else -#define get_put_user_noinstr_attributes __always_inline +#define uaccess_kmsan_or_inline __always_inline #endif -#define DEFINE_PUT_USER(type) \ -static get_put_user_noinstr_attributes int \ +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#define DEFINE_PUT_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ +__put_user_##type##_noinstr(unsigned type __user *to, \ + unsigned type *from, \ + unsigned long size) \ +{ \ + asm goto( \ + " llilh %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: nopr %%r7\n" \ + EX_TABLE(0b, %l[Efault]) \ + EX_TABLE(1b, %l[Efault]) \ + : [to] "+Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ + : "cc", "0" \ + : Efault \ + ); \ + return 0; \ +Efault: \ + return -EFAULT; \ +} + +#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +#define DEFINE_PUT_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ __put_user_##type##_noinstr(unsigned type __user *to, \ unsigned type *from, \ unsigned long size) \ { \ - union oac __oac_spec = { \ - .oac1.as = PSW_BITS_AS_SECONDARY, \ - .oac1.a = 1, \ - }; \ int rc; \ \ asm volatile( \ - " lr 0,%[spec]\n" \ - "0: mvcos %[_to],%[_from],%[_size]\n" \ - "1: xr %[rc],%[rc]\n" \ + " llilh %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: lhi %[rc],0\n" \ "2:\n" \ - EX_TABLE_UA_STORE(0b, 2b, %[rc]) \ - EX_TABLE_UA_STORE(1b, 2b, %[rc]) \ - : [rc] "=&d" (rc), [_to] "+Q" (*(to)) \ - : [_size] "d" (size), [_from] "Q" (*(from)), \ - [spec] "d" (__oac_spec.val) \ + EX_TABLE_UA_FAULT(0b, 2b, %[rc]) \ + EX_TABLE_UA_FAULT(1b, 2b, %[rc]) \ + : [rc] "=d" (rc), [to] "+Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ : "cc", "0"); \ return rc; \ -} \ - \ +} + +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +DEFINE_PUT_USER_NOINSTR(char); +DEFINE_PUT_USER_NOINSTR(short); +DEFINE_PUT_USER_NOINSTR(int); +DEFINE_PUT_USER_NOINSTR(long); + +#define DEFINE_PUT_USER(type) \ static __always_inline int \ __put_user_##type(unsigned type __user *to, unsigned type *from, \ unsigned long size) \ @@ -128,69 +237,111 @@ DEFINE_PUT_USER(short); DEFINE_PUT_USER(int); DEFINE_PUT_USER(long); -static __always_inline int __put_user_fn(void *x, void __user *ptr, unsigned long size) -{ - int rc; +#define __put_user(x, ptr) \ +({ \ + __typeof__(*(ptr)) __x = (x); \ + int __prc; \ + \ + __chk_user_ptr(ptr); \ + switch (sizeof(*(ptr))) { \ + case 1: \ + __prc = __put_user_char((unsigned char __user *)(ptr), \ + (unsigned char *)&__x, \ + sizeof(*(ptr))); \ + break; \ + case 2: \ + __prc = __put_user_short((unsigned short __user *)(ptr),\ + (unsigned short *)&__x, \ + sizeof(*(ptr))); \ + break; \ + case 4: \ + __prc = __put_user_int((unsigned int __user *)(ptr), \ + (unsigned int *)&__x, \ + sizeof(*(ptr))); \ + break; \ + case 8: \ + __prc = __put_user_long((unsigned long __user *)(ptr), \ + (unsigned long *)&__x, \ + sizeof(*(ptr))); \ + break; \ + default: \ + __prc = __put_user_bad(); \ + break; \ + } \ + __builtin_expect(__prc, 0); \ +}) - switch (size) { - case 1: - rc = __put_user_char((unsigned char __user *)ptr, - (unsigned char *)x, - size); - break; - case 2: - rc = __put_user_short((unsigned short __user *)ptr, - (unsigned short *)x, - size); - break; - case 4: - rc = __put_user_int((unsigned int __user *)ptr, - (unsigned int *)x, - size); - break; - case 8: - rc = __put_user_long((unsigned long __user *)ptr, - (unsigned long *)x, - size); - break; - default: - __put_user_bad(); - break; - } - return rc; -} +#define put_user(x, ptr) \ +({ \ + might_fault(); \ + __put_user(x, ptr); \ +}) int __noreturn __get_user_bad(void); -#define DEFINE_GET_USER(type) \ -static get_put_user_noinstr_attributes int \ +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#define DEFINE_GET_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ __get_user_##type##_noinstr(unsigned type *to, \ - unsigned type __user *from, \ + const unsigned type __user *from, \ + unsigned long size) \ +{ \ + asm goto( \ + " lhi %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: nopr %%r7\n" \ + EX_TABLE(0b, %l[Efault]) \ + EX_TABLE(1b, %l[Efault]) \ + : [to] "=Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ + : "cc", "0" \ + : Efault \ + ); \ + return 0; \ +Efault: \ + *to = 0; \ + return -EFAULT; \ +} + +#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +#define DEFINE_GET_USER_NOINSTR(type) \ +static uaccess_kmsan_or_inline int \ +__get_user_##type##_noinstr(unsigned type *to, \ + const unsigned type __user *from, \ unsigned long size) \ { \ - union oac __oac_spec = { \ - .oac2.as = PSW_BITS_AS_SECONDARY, \ - .oac2.a = 1, \ - }; \ int rc; \ \ asm volatile( \ - " lr 0,%[spec]\n" \ - "0: mvcos 0(%[_to]),%[_from],%[_size]\n" \ - "1: xr %[rc],%[rc]\n" \ + " lhi %%r0,%[spec]\n" \ + "0: mvcos %[to],%[from],%[size]\n" \ + "1: lhi %[rc],0\n" \ "2:\n" \ - EX_TABLE_UA_LOAD_MEM(0b, 2b, %[rc], %[_to], %[_ksize]) \ - EX_TABLE_UA_LOAD_MEM(1b, 2b, %[rc], %[_to], %[_ksize]) \ - : [rc] "=&d" (rc), "=Q" (*(to)) \ - : [_size] "d" (size), [_from] "Q" (*(from)), \ - [spec] "d" (__oac_spec.val), [_to] "a" (to), \ - [_ksize] "K" (size) \ + EX_TABLE_UA_FAULT(0b, 2b, %[rc]) \ + EX_TABLE_UA_FAULT(1b, 2b, %[rc]) \ + : [rc] "=d" (rc), [to] "=Q" (*to) \ + : [size] "d" (size), [from] "Q" (*from), \ + [spec] "I" (0x81) \ : "cc", "0"); \ + if (likely(!rc)) \ + return 0; \ + *to = 0; \ return rc; \ -} \ - \ +} + +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +DEFINE_GET_USER_NOINSTR(char); +DEFINE_GET_USER_NOINSTR(short); +DEFINE_GET_USER_NOINSTR(int); +DEFINE_GET_USER_NOINSTR(long); + +#define DEFINE_GET_USER(type) \ static __always_inline int \ -__get_user_##type(unsigned type *to, unsigned type __user *from, \ +__get_user_##type(unsigned type *to, const unsigned type __user *from, \ unsigned long size) \ { \ int rc; \ @@ -205,107 +356,50 @@ DEFINE_GET_USER(short); DEFINE_GET_USER(int); DEFINE_GET_USER(long); -static __always_inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size) -{ - int rc; - - switch (size) { - case 1: - rc = __get_user_char((unsigned char *)x, - (unsigned char __user *)ptr, - size); - break; - case 2: - rc = __get_user_short((unsigned short *)x, - (unsigned short __user *)ptr, - size); - break; - case 4: - rc = __get_user_int((unsigned int *)x, - (unsigned int __user *)ptr, - size); - break; - case 8: - rc = __get_user_long((unsigned long *)x, - (unsigned long __user *)ptr, - size); - break; - default: - __get_user_bad(); - break; - } - return rc; -} - -/* - * These are the main single-value transfer routines. They automatically - * use the right size if we just have the right pointer type. - */ -#define __put_user(x, ptr) \ -({ \ - __typeof__(*(ptr)) __x = (x); \ - int __pu_err = -EFAULT; \ - \ - __chk_user_ptr(ptr); \ - switch (sizeof(*(ptr))) { \ - case 1: \ - case 2: \ - case 4: \ - case 8: \ - __pu_err = __put_user_fn(&__x, ptr, sizeof(*(ptr))); \ - break; \ - default: \ - __put_user_bad(); \ - break; \ - } \ - __builtin_expect(__pu_err, 0); \ -}) - -#define put_user(x, ptr) \ -({ \ - might_fault(); \ - __put_user(x, ptr); \ -}) - #define __get_user(x, ptr) \ ({ \ - int __gu_err = -EFAULT; \ + const __user void *____guptr = (ptr); \ + int __grc; \ \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: { \ + const unsigned char __user *__guptr = ____guptr; \ unsigned char __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_char(&__x, __guptr, sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ case 2: { \ + const unsigned short __user *__guptr = ____guptr; \ unsigned short __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_short(&__x, __guptr, sizeof(*(ptr)));\ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ case 4: { \ + const unsigned int __user *__guptr = ____guptr; \ unsigned int __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_int(&__x, __guptr, sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ case 8: { \ + const unsigned long __user *__guptr = ____guptr; \ unsigned long __x; \ \ - __gu_err = __get_user_fn(&__x, ptr, sizeof(*(ptr))); \ + __grc = __get_user_long(&__x, __guptr, sizeof(*(ptr))); \ (x) = *(__force __typeof__(*(ptr)) *)&__x; \ break; \ }; \ default: \ - __get_user_bad(); \ + __grc = __get_user_bad(); \ break; \ } \ - __builtin_expect(__gu_err, 0); \ + __builtin_expect(__grc, 0); \ }) #define get_user(x, ptr) \ @@ -341,109 +435,71 @@ static inline void *s390_kernel_write(void *dst, const void *src, size_t size) return __s390_kernel_write(dst, src, size); } -int __noreturn __put_kernel_bad(void); +void __noreturn __mvc_kernel_nofault_bad(void); -#define __put_kernel_asm(val, to, insn) \ -({ \ - int __rc; \ - \ - asm volatile( \ - "0: " insn " %[_val],%[_to]\n" \ - "1: xr %[rc],%[rc]\n" \ - "2:\n" \ - EX_TABLE_UA_STORE(0b, 2b, %[rc]) \ - EX_TABLE_UA_STORE(1b, 2b, %[rc]) \ - : [rc] "=d" (__rc), [_to] "+Q" (*(to)) \ - : [_val] "d" (val) \ - : "cc"); \ - __rc; \ -}) +#if defined(CONFIG_CC_HAS_ASM_GOTO_OUTPUT) && defined(CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS) -#define __put_kernel_nofault(dst, src, type, err_label) \ +#define __mvc_kernel_nofault(dst, src, type, err_label) \ do { \ - unsigned long __x = (unsigned long)(*((type *)(src))); \ - int __pk_err; \ - \ switch (sizeof(type)) { \ case 1: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "stc"); \ - break; \ case 2: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "sth"); \ - break; \ case 4: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "st"); \ - break; \ case 8: \ - __pk_err = __put_kernel_asm(__x, (type *)(dst), "stg"); \ + asm goto( \ + "0: mvc %O[_dst](%[_len],%R[_dst]),%[_src]\n" \ + "1: nopr %%r7\n" \ + EX_TABLE(0b, %l[err_label]) \ + EX_TABLE(1b, %l[err_label]) \ + : [_dst] "=Q" (*(type *)dst) \ + : [_src] "Q" (*(type *)(src)), \ + [_len] "I" (sizeof(type)) \ + : \ + : err_label); \ break; \ default: \ - __pk_err = __put_kernel_bad(); \ + __mvc_kernel_nofault_bad(); \ break; \ } \ - if (unlikely(__pk_err)) \ - goto err_label; \ } while (0) -int __noreturn __get_kernel_bad(void); - -#define __get_kernel_asm(val, from, insn) \ -({ \ - int __rc; \ - \ - asm volatile( \ - "0: " insn " %[_val],%[_from]\n" \ - "1: xr %[rc],%[rc]\n" \ - "2:\n" \ - EX_TABLE_UA_LOAD_REG(0b, 2b, %[rc], %[_val]) \ - EX_TABLE_UA_LOAD_REG(1b, 2b, %[rc], %[_val]) \ - : [rc] "=d" (__rc), [_val] "=d" (val) \ - : [_from] "Q" (*(from)) \ - : "cc"); \ - __rc; \ -}) +#else /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT) && CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ -#define __get_kernel_nofault(dst, src, type, err_label) \ +#define __mvc_kernel_nofault(dst, src, type, err_label) \ do { \ - int __gk_err; \ + type *(__dst) = (type *)(dst); \ + int __rc; \ \ switch (sizeof(type)) { \ - case 1: { \ - unsigned char __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "ic"); \ - *((type *)(dst)) = (type)__x; \ - break; \ - }; \ - case 2: { \ - unsigned short __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "lh"); \ - *((type *)(dst)) = (type)__x; \ - break; \ - }; \ - case 4: { \ - unsigned int __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "l"); \ - *((type *)(dst)) = (type)__x; \ - break; \ - }; \ - case 8: { \ - unsigned long __x; \ - \ - __gk_err = __get_kernel_asm(__x, (type *)(src), "lg"); \ - *((type *)(dst)) = (type)__x; \ + case 1: \ + case 2: \ + case 4: \ + case 8: \ + asm_inline volatile( \ + "0: mvc 0(%[_len],%[_dst]),%[_src]\n" \ + "1: lhi %[_rc],0\n" \ + "2:\n" \ + EX_TABLE_UA_FAULT(0b, 2b, %[_rc]) \ + EX_TABLE_UA_FAULT(1b, 2b, %[_rc]) \ + : [_rc] "=d" (__rc), \ + "=m" (*__dst) \ + : [_src] "Q" (*(type *)(src)), \ + [_dst] "a" (__dst), \ + [_len] "I" (sizeof(type))); \ + if (__rc) \ + goto err_label; \ break; \ - }; \ default: \ - __gk_err = __get_kernel_bad(); \ + __mvc_kernel_nofault_bad(); \ break; \ } \ - if (unlikely(__gk_err)) \ - goto err_label; \ } while (0) +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT && CONFIG_CC_HAS_ASM_AOR_FORMAT_FLAGS */ + +#define __get_kernel_nofault __mvc_kernel_nofault +#define __put_kernel_nofault __mvc_kernel_nofault + void __cmpxchg_user_key_called_with_bad_pointer(void); #define CMPXCHG_USER_KEY_MAX_LOOPS 128 diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index dc332609f2c3..b11f5b6d0bd1 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -628,12 +628,12 @@ static inline int is_prot_virt_host(void) } int uv_pin_shared(unsigned long paddr); -int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); -int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr); int uv_destroy_folio(struct folio *folio); int uv_destroy_pte(pte_t pte); int uv_convert_from_secure_pte(pte_t pte); -int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); +int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb); +int uv_convert_from_secure(unsigned long paddr); +int uv_convert_from_secure_folio(struct folio *folio); void setup_uv(void); diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index ba6b7329a10e..ce038e9205f7 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -1122,7 +1122,7 @@ static int s390dbf_procactive(const struct ctl_table *table, int write, return 0; } -static struct ctl_table s390dbf_table[] = { +static const struct ctl_table s390dbf_table[] = { { .procname = "debug_stoppable", .data = &debug_stoppable, diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 62f8f5a750a3..2fa25164df7d 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -50,6 +50,7 @@ decompressor_handled_param(facilities); decompressor_handled_param(nokaslr); decompressor_handled_param(cmma); decompressor_handled_param(relocate_lowcore); +decompressor_handled_param(bootdebug); #if IS_ENABLED(CONFIG_KVM) decompressor_handled_param(prot_virt); #endif @@ -58,7 +59,7 @@ static void __init kasan_early_init(void) { #ifdef CONFIG_KASAN init_task.kasan_depth = 0; - sclp_early_printk("KernelAddressSanitizer initialized\n"); + pr_info("KernelAddressSanitizer initialized\n"); #endif } diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index c0b2c97efefb..63ba6306632e 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -266,18 +266,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14]; - int bit; if (unlikely(ftrace_graph_is_dead())) return; if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; - bit = ftrace_test_recursion_trylock(ip, *parent); - if (bit < 0) - return; if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs)) *parent = (unsigned long)&return_to_handler; - ftrace_test_recursion_unlock(bit); } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/s390/kernel/hiperdispatch.c b/arch/s390/kernel/hiperdispatch.c index 2a99a216ab62..7857a7e8e56c 100644 --- a/arch/s390/kernel/hiperdispatch.c +++ b/arch/s390/kernel/hiperdispatch.c @@ -292,7 +292,7 @@ static int hiperdispatch_ctl_handler(const struct ctl_table *ctl, int write, return 0; } -static struct ctl_table hiperdispatch_ctl_table[] = { +static const struct ctl_table hiperdispatch_ctl_table[] = { { .procname = "hiperdispatch", .mode = 0644, diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 1298f0860733..d78bcfe707b5 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -157,6 +157,12 @@ u64 __bootdata_preserved(stfle_fac_list[16]); EXPORT_SYMBOL(stfle_fac_list); struct oldmem_data __bootdata_preserved(oldmem_data); +char __bootdata(boot_rb)[PAGE_SIZE * 2]; +bool __bootdata(boot_earlyprintk); +size_t __bootdata(boot_rb_off); +char __bootdata(bootdebug_filter)[128]; +bool __bootdata(bootdebug); + unsigned long __bootdata_preserved(VMALLOC_START); EXPORT_SYMBOL(VMALLOC_START); @@ -686,7 +692,7 @@ static void __init reserve_physmem_info(void) { unsigned long addr, size; - if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size)) + if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size)) memblock_reserve(addr, size); } @@ -694,7 +700,7 @@ static void __init free_physmem_info(void) { unsigned long addr, size; - if (get_physmem_reserved(RR_MEM_DETECT_EXTENDED, &addr, &size)) + if (get_physmem_reserved(RR_MEM_DETECT_EXT, &addr, &size)) memblock_phys_free(addr, size); } @@ -724,7 +730,7 @@ static void __init reserve_lowcore(void) void *lowcore_end = lowcore_start + sizeof(struct lowcore); void *start, *end; - if ((void *)__identity_base < lowcore_end) { + if (absolute_pointer(__identity_base) < lowcore_end) { start = max(lowcore_start, (void *)__identity_base); end = min(lowcore_end, (void *)(__identity_base + ident_map_size)); memblock_reserve(__pa(start), __pa(end)); @@ -866,6 +872,23 @@ static void __init log_component_list(void) } /* + * Print avoiding interpretation of % in buf and taking bootdebug option + * into consideration. + */ +static void __init print_rb_entry(const char *buf) +{ + char fmt[] = KERN_SOH "0boot: %s"; + int level = printk_get_level(buf); + + buf = skip_timestamp(printk_skip_level(buf)); + if (level == KERN_DEBUG[1] && (!bootdebug || !bootdebug_filter_match(buf))) + return; + + fmt[1] = level; + printk(fmt, buf); +} + +/* * Setup function called from init/main.c just after the banner * was printed. */ @@ -884,6 +907,9 @@ void __init setup_arch(char **cmdline_p) pr_info("Linux is running natively in 64-bit mode\n"); else pr_info("Linux is running as a guest in 64-bit mode\n"); + /* Print decompressor messages if not already printed */ + if (!boot_earlyprintk) + boot_rb_foreach(print_rb_entry); if (have_relocated_lowcore()) pr_info("Lowcore relocated to 0x%px\n", get_lowcore()); @@ -987,3 +1013,8 @@ void __init setup_arch(char **cmdline_p) /* Add system specific data to the random pool */ setup_randomness(); } + +void __init arch_cpu_finalize_init(void) +{ + sclp_init(); +} diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 3808f942a433..211cc8382e4a 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -667,7 +667,7 @@ static int polarization_ctl_handler(const struct ctl_table *ctl, int write, return set_polarization(polarization); } -static struct ctl_table topology_ctl_table[] = { +static const struct ctl_table topology_ctl_table[] = { { .procname = "topology", .mode = 0644, diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 6f9654a191ad..9f05df2da2f7 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -19,19 +19,6 @@ #include <asm/sections.h> #include <asm/uv.h> -#if !IS_ENABLED(CONFIG_KVM) -unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr) -{ - return 0; -} - -int gmap_fault(struct gmap *gmap, unsigned long gaddr, - unsigned int fault_flags) -{ - return 0; -} -#endif - /* the bootdata_preserved fields come from ones in arch/s390/boot/uv.c */ int __bootdata_preserved(prot_virt_guest); EXPORT_SYMBOL(prot_virt_guest); @@ -159,6 +146,7 @@ int uv_destroy_folio(struct folio *folio) folio_put(folio); return rc; } +EXPORT_SYMBOL(uv_destroy_folio); /* * The present PTE still indirectly holds a folio reference through the mapping. @@ -175,7 +163,7 @@ int uv_destroy_pte(pte_t pte) * * @paddr: Absolute host address of page to be exported */ -static int uv_convert_from_secure(unsigned long paddr) +int uv_convert_from_secure(unsigned long paddr) { struct uv_cb_cfs uvcb = { .header.cmd = UVC_CMD_CONV_FROM_SEC_STOR, @@ -187,11 +175,12 @@ static int uv_convert_from_secure(unsigned long paddr) return -EINVAL; return 0; } +EXPORT_SYMBOL_GPL(uv_convert_from_secure); /* * The caller must already hold a reference to the folio. */ -static int uv_convert_from_secure_folio(struct folio *folio) +int uv_convert_from_secure_folio(struct folio *folio) { int rc; @@ -206,6 +195,7 @@ static int uv_convert_from_secure_folio(struct folio *folio) folio_put(folio); return rc; } +EXPORT_SYMBOL_GPL(uv_convert_from_secure_folio); /* * The present PTE still indirectly holds a folio reference through the mapping. @@ -237,13 +227,33 @@ static int expected_folio_refs(struct folio *folio) return res; } -static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) +/** + * make_folio_secure() - make a folio secure + * @folio: the folio to make secure + * @uvcb: the uvcb that describes the UVC to be used + * + * The folio @folio will be made secure if possible, @uvcb will be passed + * as-is to the UVC. + * + * Return: 0 on success; + * -EBUSY if the folio is in writeback or has too many references; + * -E2BIG if the folio is large; + * -EAGAIN if the UVC needs to be attempted again; + * -ENXIO if the address is not mapped; + * -EINVAL if the UVC failed for other reasons. + * + * Context: The caller must hold exactly one extra reference on the folio + * (it's the same logic as split_folio()) + */ +int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) { int expected, cc = 0; + if (folio_test_large(folio)) + return -E2BIG; if (folio_test_writeback(folio)) - return -EAGAIN; - expected = expected_folio_refs(folio); + return -EBUSY; + expected = expected_folio_refs(folio) + 1; if (!folio_ref_freeze(folio, expected)) return -EBUSY; set_bit(PG_arch_1, &folio->flags); @@ -267,251 +277,7 @@ static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) return -EAGAIN; return uvcb->rc == 0x10a ? -ENXIO : -EINVAL; } - -/** - * should_export_before_import - Determine whether an export is needed - * before an import-like operation - * @uvcb: the Ultravisor control block of the UVC to be performed - * @mm: the mm of the process - * - * Returns whether an export is needed before every import-like operation. - * This is needed for shared pages, which don't trigger a secure storage - * exception when accessed from a different guest. - * - * Although considered as one, the Unpin Page UVC is not an actual import, - * so it is not affected. - * - * No export is needed also when there is only one protected VM, because the - * page cannot belong to the wrong VM in that case (there is no "other VM" - * it can belong to). - * - * Return: true if an export is needed before every import, otherwise false. - */ -static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm) -{ - /* - * The misc feature indicates, among other things, that importing a - * shared page from a different protected VM will automatically also - * transfer its ownership. - */ - if (uv_has_feature(BIT_UV_FEAT_MISC)) - return false; - if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED) - return false; - return atomic_read(&mm->context.protected_count) > 1; -} - -/* - * Drain LRU caches: the local one on first invocation and the ones of all - * CPUs on successive invocations. Returns "true" on the first invocation. - */ -static bool drain_lru(bool *drain_lru_called) -{ - /* - * If we have tried a local drain and the folio refcount - * still does not match our expected safe value, try with a - * system wide drain. This is needed if the pagevecs holding - * the page are on a different CPU. - */ - if (*drain_lru_called) { - lru_add_drain_all(); - /* We give up here, don't retry immediately. */ - return false; - } - /* - * We are here if the folio refcount does not match the - * expected safe value. The main culprits are usually - * pagevecs. With lru_add_drain() we drain the pagevecs - * on the local CPU so that hopefully the refcount will - * reach the expected safe value. - */ - lru_add_drain(); - *drain_lru_called = true; - /* The caller should try again immediately */ - return true; -} - -/* - * Requests the Ultravisor to make a page accessible to a guest. - * If it's brought in the first time, it will be cleared. If - * it has been exported before, it will be decrypted and integrity - * checked. - */ -int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) -{ - struct vm_area_struct *vma; - bool drain_lru_called = false; - spinlock_t *ptelock; - unsigned long uaddr; - struct folio *folio; - pte_t *ptep; - int rc; - -again: - rc = -EFAULT; - mmap_read_lock(gmap->mm); - - uaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(uaddr)) - goto out; - vma = vma_lookup(gmap->mm, uaddr); - if (!vma) - goto out; - /* - * Secure pages cannot be huge and userspace should not combine both. - * In case userspace does it anyway this will result in an -EFAULT for - * the unpack. The guest is thus never reaching secure mode. If - * userspace is playing dirty tricky with mapping huge pages later - * on this will result in a segmentation fault. - */ - if (is_vm_hugetlb_page(vma)) - goto out; - - rc = -ENXIO; - ptep = get_locked_pte(gmap->mm, uaddr, &ptelock); - if (!ptep) - goto out; - if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) { - folio = page_folio(pte_page(*ptep)); - rc = -EAGAIN; - if (folio_test_large(folio)) { - rc = -E2BIG; - } else if (folio_trylock(folio)) { - if (should_export_before_import(uvcb, gmap->mm)) - uv_convert_from_secure(PFN_PHYS(folio_pfn(folio))); - rc = make_folio_secure(folio, uvcb); - folio_unlock(folio); - } - - /* - * Once we drop the PTL, the folio may get unmapped and - * freed immediately. We need a temporary reference. - */ - if (rc == -EAGAIN || rc == -E2BIG) - folio_get(folio); - } - pte_unmap_unlock(ptep, ptelock); -out: - mmap_read_unlock(gmap->mm); - - switch (rc) { - case -E2BIG: - folio_lock(folio); - rc = split_folio(folio); - folio_unlock(folio); - folio_put(folio); - - switch (rc) { - case 0: - /* Splitting succeeded, try again immediately. */ - goto again; - case -EAGAIN: - /* Additional folio references. */ - if (drain_lru(&drain_lru_called)) - goto again; - return -EAGAIN; - case -EBUSY: - /* Unexpected race. */ - return -EAGAIN; - } - WARN_ON_ONCE(1); - return -ENXIO; - case -EAGAIN: - /* - * If we are here because the UVC returned busy or partial - * completion, this is just a useless check, but it is safe. - */ - folio_wait_writeback(folio); - folio_put(folio); - return -EAGAIN; - case -EBUSY: - /* Additional folio references. */ - if (drain_lru(&drain_lru_called)) - goto again; - return -EAGAIN; - case -ENXIO: - if (gmap_fault(gmap, gaddr, FAULT_FLAG_WRITE)) - return -EFAULT; - return -EAGAIN; - } - return rc; -} -EXPORT_SYMBOL_GPL(gmap_make_secure); - -int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) -{ - struct uv_cb_cts uvcb = { - .header.cmd = UVC_CMD_CONV_TO_SEC_STOR, - .header.len = sizeof(uvcb), - .guest_handle = gmap->guest_handle, - .gaddr = gaddr, - }; - - return gmap_make_secure(gmap, gaddr, &uvcb); -} -EXPORT_SYMBOL_GPL(gmap_convert_to_secure); - -/** - * gmap_destroy_page - Destroy a guest page. - * @gmap: the gmap of the guest - * @gaddr: the guest address to destroy - * - * An attempt will be made to destroy the given guest page. If the attempt - * fails, an attempt is made to export the page. If both attempts fail, an - * appropriate error is returned. - */ -int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr) -{ - struct vm_area_struct *vma; - struct folio_walk fw; - unsigned long uaddr; - struct folio *folio; - int rc; - - rc = -EFAULT; - mmap_read_lock(gmap->mm); - - uaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(uaddr)) - goto out; - vma = vma_lookup(gmap->mm, uaddr); - if (!vma) - goto out; - /* - * Huge pages should not be able to become secure - */ - if (is_vm_hugetlb_page(vma)) - goto out; - - rc = 0; - folio = folio_walk_start(&fw, vma, uaddr, 0); - if (!folio) - goto out; - /* - * See gmap_make_secure(): large folios cannot be secure. Small - * folio implies FW_LEVEL_PTE. - */ - if (folio_test_large(folio) || !pte_write(fw.pte)) - goto out_walk_end; - rc = uv_destroy_folio(folio); - /* - * Fault handlers can race; it is possible that two CPUs will fault - * on the same secure page. One CPU can destroy the page, reboot, - * re-enter secure mode and import it, while the second CPU was - * stuck at the beginning of the handler. At some point the second - * CPU will be able to progress, and it will not be able to destroy - * the page. In that case we do not want to terminate the process, - * we instead try to export the page. - */ - if (rc) - rc = uv_convert_from_secure_folio(folio); -out_walk_end: - folio_walk_end(&fw, vma); -out: - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_destroy_page); +EXPORT_SYMBOL_GPL(make_folio_secure); /* * To be called with the folio locked or with an extra reference! This will diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 377b9aaf8c92..ff1ddba96352 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -52,7 +52,6 @@ SECTIONS SOFTIRQENTRY_TEXT FTRACE_HOTPATCH_TRAMPOLINES_TEXT *(.text.*_indirect_*) - *(.fixup) *(.gnu.warning) . = ALIGN(PAGE_SIZE); _etext = .; /* End of text section */ diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile index 02217fb4ae10..f0ffe874adc2 100644 --- a/arch/s390/kvm/Makefile +++ b/arch/s390/kvm/Makefile @@ -8,7 +8,7 @@ include $(srctree)/virt/kvm/Makefile.kvm ccflags-y := -Ivirt/kvm -Iarch/s390/kvm kvm-y += kvm-s390.o intercept.o interrupt.o priv.o sigp.o -kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o +kvm-y += diag.o gaccess.o guestdbg.o vsie.o pv.o gmap.o gmap-vsie.o kvm-$(CONFIG_VFIO_PCI_ZDEV_KVM) += pci.o obj-$(CONFIG_KVM) += kvm.o diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 9816b0060fbe..f6fded15633a 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -16,6 +16,7 @@ #include <asm/gmap.h> #include <asm/dat-bits.h> #include "kvm-s390.h" +#include "gmap.h" #include "gaccess.h" /* @@ -1393,6 +1394,44 @@ shadow_pgt: } /** + * shadow_pgt_lookup() - find a shadow page table + * @sg: pointer to the shadow guest address space structure + * @saddr: the address in the shadow aguest address space + * @pgt: parent gmap address of the page table to get shadowed + * @dat_protection: if the pgtable is marked as protected by dat + * @fake: pgt references contiguous guest memory block, not a pgtable + * + * Returns 0 if the shadow page table was found and -EAGAIN if the page + * table was not found. + * + * Called with sg->mm->mmap_lock in read. + */ +static int shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, unsigned long *pgt, + int *dat_protection, int *fake) +{ + unsigned long pt_index; + unsigned long *table; + struct page *page; + int rc; + + spin_lock(&sg->guest_table_lock); + table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */ + if (table && !(*table & _SEGMENT_ENTRY_INVALID)) { + /* Shadow page tables are full pages (pte+pgste) */ + page = pfn_to_page(*table >> PAGE_SHIFT); + pt_index = gmap_pgste_get_pgt_addr(page_to_virt(page)); + *pgt = pt_index & ~GMAP_SHADOW_FAKE_TABLE; + *dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT); + *fake = !!(pt_index & GMAP_SHADOW_FAKE_TABLE); + rc = 0; + } else { + rc = -EAGAIN; + } + spin_unlock(&sg->guest_table_lock); + return rc; +} + +/** * kvm_s390_shadow_fault - handle fault on a shadow page table * @vcpu: virtual cpu * @sg: pointer to the shadow guest address space structure @@ -1415,6 +1454,9 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, int dat_protection, fake; int rc; + if (KVM_BUG_ON(!gmap_is_shadow(sg), vcpu->kvm)) + return -EFAULT; + mmap_read_lock(sg->mm); /* * We don't want any guest-2 tables to change - so the parent @@ -1423,7 +1465,7 @@ int kvm_s390_shadow_fault(struct kvm_vcpu *vcpu, struct gmap *sg, */ ipte_lock(vcpu->kvm); - rc = gmap_shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake); + rc = shadow_pgt_lookup(sg, saddr, &pgt, &dat_protection, &fake); if (rc) rc = kvm_s390_shadow_tables(sg, saddr, &pgt, &dat_protection, &fake); diff --git a/arch/s390/kvm/gmap-vsie.c b/arch/s390/kvm/gmap-vsie.c new file mode 100644 index 000000000000..a6d1dbb04c97 --- /dev/null +++ b/arch/s390/kvm/gmap-vsie.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Guest memory management for KVM/s390 nested VMs. + * + * Copyright IBM Corp. 2008, 2020, 2024 + * + * Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * David Hildenbrand <david@redhat.com> + * Janosch Frank <frankja@linux.vnet.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pgtable.h> +#include <linux/pagemap.h> +#include <linux/mman.h> + +#include <asm/lowcore.h> +#include <asm/gmap.h> +#include <asm/uv.h> + +#include "kvm-s390.h" +#include "gmap.h" + +/** + * gmap_find_shadow - find a specific asce in the list of shadow tables + * @parent: pointer to the parent gmap + * @asce: ASCE for which the shadow table is created + * @edat_level: edat level to be used for the shadow translation + * + * Returns the pointer to a gmap if a shadow table with the given asce is + * already available, ERR_PTR(-EAGAIN) if another one is just being created, + * otherwise NULL + * + * Context: Called with parent->shadow_lock held + */ +static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, int edat_level) +{ + struct gmap *sg; + + lockdep_assert_held(&parent->shadow_lock); + list_for_each_entry(sg, &parent->children, list) { + if (!gmap_shadow_valid(sg, asce, edat_level)) + continue; + if (!sg->initialized) + return ERR_PTR(-EAGAIN); + refcount_inc(&sg->ref_count); + return sg; + } + return NULL; +} + +/** + * gmap_shadow - create/find a shadow guest address space + * @parent: pointer to the parent gmap + * @asce: ASCE for which the shadow table is created + * @edat_level: edat level to be used for the shadow translation + * + * The pages of the top level page table referred by the asce parameter + * will be set to read-only and marked in the PGSTEs of the kvm process. + * The shadow table will be removed automatically on any change to the + * PTE mapping for the source table. + * + * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory, + * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the + * parent gmap table could not be protected. + */ +struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level) +{ + struct gmap *sg, *new; + unsigned long limit; + int rc; + + if (KVM_BUG_ON(parent->mm->context.allow_gmap_hpage_1m, (struct kvm *)parent->private) || + KVM_BUG_ON(gmap_is_shadow(parent), (struct kvm *)parent->private)) + return ERR_PTR(-EFAULT); + spin_lock(&parent->shadow_lock); + sg = gmap_find_shadow(parent, asce, edat_level); + spin_unlock(&parent->shadow_lock); + if (sg) + return sg; + /* Create a new shadow gmap */ + limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11)); + if (asce & _ASCE_REAL_SPACE) + limit = -1UL; + new = gmap_alloc(limit); + if (!new) + return ERR_PTR(-ENOMEM); + new->mm = parent->mm; + new->parent = gmap_get(parent); + new->private = parent->private; + new->orig_asce = asce; + new->edat_level = edat_level; + new->initialized = false; + spin_lock(&parent->shadow_lock); + /* Recheck if another CPU created the same shadow */ + sg = gmap_find_shadow(parent, asce, edat_level); + if (sg) { + spin_unlock(&parent->shadow_lock); + gmap_free(new); + return sg; + } + if (asce & _ASCE_REAL_SPACE) { + /* only allow one real-space gmap shadow */ + list_for_each_entry(sg, &parent->children, list) { + if (sg->orig_asce & _ASCE_REAL_SPACE) { + spin_lock(&sg->guest_table_lock); + gmap_unshadow(sg); + spin_unlock(&sg->guest_table_lock); + list_del(&sg->list); + gmap_put(sg); + break; + } + } + } + refcount_set(&new->ref_count, 2); + list_add(&new->list, &parent->children); + if (asce & _ASCE_REAL_SPACE) { + /* nothing to protect, return right away */ + new->initialized = true; + spin_unlock(&parent->shadow_lock); + return new; + } + spin_unlock(&parent->shadow_lock); + /* protect after insertion, so it will get properly invalidated */ + mmap_read_lock(parent->mm); + rc = __kvm_s390_mprotect_many(parent, asce & _ASCE_ORIGIN, + ((asce & _ASCE_TABLE_LENGTH) + 1), + PROT_READ, GMAP_NOTIFY_SHADOW); + mmap_read_unlock(parent->mm); + spin_lock(&parent->shadow_lock); + new->initialized = true; + if (rc) { + list_del(&new->list); + gmap_free(new); + new = ERR_PTR(rc); + } + spin_unlock(&parent->shadow_lock); + return new; +} diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c new file mode 100644 index 000000000000..02adf151d4de --- /dev/null +++ b/arch/s390/kvm/gmap.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Guest memory management for KVM/s390 + * + * Copyright IBM Corp. 2008, 2020, 2024 + * + * Author(s): Claudio Imbrenda <imbrenda@linux.ibm.com> + * Martin Schwidefsky <schwidefsky@de.ibm.com> + * David Hildenbrand <david@redhat.com> + * Janosch Frank <frankja@linux.vnet.ibm.com> + */ + +#include <linux/compiler.h> +#include <linux/kvm.h> +#include <linux/kvm_host.h> +#include <linux/pgtable.h> +#include <linux/pagemap.h> + +#include <asm/lowcore.h> +#include <asm/gmap.h> +#include <asm/uv.h> + +#include "gmap.h" + +/** + * should_export_before_import - Determine whether an export is needed + * before an import-like operation + * @uvcb: the Ultravisor control block of the UVC to be performed + * @mm: the mm of the process + * + * Returns whether an export is needed before every import-like operation. + * This is needed for shared pages, which don't trigger a secure storage + * exception when accessed from a different guest. + * + * Although considered as one, the Unpin Page UVC is not an actual import, + * so it is not affected. + * + * No export is needed also when there is only one protected VM, because the + * page cannot belong to the wrong VM in that case (there is no "other VM" + * it can belong to). + * + * Return: true if an export is needed before every import, otherwise false. + */ +static bool should_export_before_import(struct uv_cb_header *uvcb, struct mm_struct *mm) +{ + /* + * The misc feature indicates, among other things, that importing a + * shared page from a different protected VM will automatically also + * transfer its ownership. + */ + if (uv_has_feature(BIT_UV_FEAT_MISC)) + return false; + if (uvcb->cmd == UVC_CMD_UNPIN_PAGE_SHARED) + return false; + return atomic_read(&mm->context.protected_count) > 1; +} + +static int __gmap_make_secure(struct gmap *gmap, struct page *page, void *uvcb) +{ + struct folio *folio = page_folio(page); + int rc; + + /* + * Secure pages cannot be huge and userspace should not combine both. + * In case userspace does it anyway this will result in an -EFAULT for + * the unpack. The guest is thus never reaching secure mode. + * If userspace plays dirty tricks and decides to map huge pages at a + * later point in time, it will receive a segmentation fault or + * KVM_RUN will return -EFAULT. + */ + if (folio_test_hugetlb(folio)) + return -EFAULT; + if (folio_test_large(folio)) { + mmap_read_unlock(gmap->mm); + rc = kvm_s390_wiggle_split_folio(gmap->mm, folio, true); + mmap_read_lock(gmap->mm); + if (rc) + return rc; + folio = page_folio(page); + } + + if (!folio_trylock(folio)) + return -EAGAIN; + if (should_export_before_import(uvcb, gmap->mm)) + uv_convert_from_secure(folio_to_phys(folio)); + rc = make_folio_secure(folio, uvcb); + folio_unlock(folio); + + /* + * In theory a race is possible and the folio might have become + * large again before the folio_trylock() above. In that case, no + * action is performed and -EAGAIN is returned; the callers will + * have to try again later. + * In most cases this implies running the VM again, getting the same + * exception again, and make another attempt in this function. + * This is expected to happen extremely rarely. + */ + if (rc == -E2BIG) + return -EAGAIN; + /* The folio has too many references, try to shake some off */ + if (rc == -EBUSY) { + mmap_read_unlock(gmap->mm); + kvm_s390_wiggle_split_folio(gmap->mm, folio, false); + mmap_read_lock(gmap->mm); + return -EAGAIN; + } + + return rc; +} + +/** + * gmap_make_secure() - make one guest page secure + * @gmap: the guest gmap + * @gaddr: the guest address that needs to be made secure + * @uvcb: the UVCB specifying which operation needs to be performed + * + * Context: needs to be called with kvm->srcu held. + * Return: 0 on success, < 0 in case of error (see __gmap_make_secure()). + */ +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) +{ + struct kvm *kvm = gmap->private; + struct page *page; + int rc = 0; + + lockdep_assert_held(&kvm->srcu); + + page = gfn_to_page(kvm, gpa_to_gfn(gaddr)); + mmap_read_lock(gmap->mm); + if (page) + rc = __gmap_make_secure(gmap, page, uvcb); + kvm_release_page_clean(page); + mmap_read_unlock(gmap->mm); + + return rc; +} + +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr) +{ + struct uv_cb_cts uvcb = { + .header.cmd = UVC_CMD_CONV_TO_SEC_STOR, + .header.len = sizeof(uvcb), + .guest_handle = gmap->guest_handle, + .gaddr = gaddr, + }; + + return gmap_make_secure(gmap, gaddr, &uvcb); +} + +/** + * __gmap_destroy_page() - Destroy a guest page. + * @gmap: the gmap of the guest + * @page: the page to destroy + * + * An attempt will be made to destroy the given guest page. If the attempt + * fails, an attempt is made to export the page. If both attempts fail, an + * appropriate error is returned. + * + * Context: must be called holding the mm lock for gmap->mm + */ +static int __gmap_destroy_page(struct gmap *gmap, struct page *page) +{ + struct folio *folio = page_folio(page); + int rc; + + /* + * See gmap_make_secure(): large folios cannot be secure. Small + * folio implies FW_LEVEL_PTE. + */ + if (folio_test_large(folio)) + return -EFAULT; + + rc = uv_destroy_folio(folio); + /* + * Fault handlers can race; it is possible that two CPUs will fault + * on the same secure page. One CPU can destroy the page, reboot, + * re-enter secure mode and import it, while the second CPU was + * stuck at the beginning of the handler. At some point the second + * CPU will be able to progress, and it will not be able to destroy + * the page. In that case we do not want to terminate the process, + * we instead try to export the page. + */ + if (rc) + rc = uv_convert_from_secure_folio(folio); + + return rc; +} + +/** + * gmap_destroy_page() - Destroy a guest page. + * @gmap: the gmap of the guest + * @gaddr: the guest address to destroy + * + * An attempt will be made to destroy the given guest page. If the attempt + * fails, an attempt is made to export the page. If both attempts fail, an + * appropriate error is returned. + * + * Context: may sleep. + */ +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr) +{ + struct page *page; + int rc = 0; + + mmap_read_lock(gmap->mm); + page = gfn_to_page(gmap->private, gpa_to_gfn(gaddr)); + if (page) + rc = __gmap_destroy_page(gmap, page); + kvm_release_page_clean(page); + mmap_read_unlock(gmap->mm); + return rc; +} diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h new file mode 100644 index 000000000000..c8f031c9ea5f --- /dev/null +++ b/arch/s390/kvm/gmap.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * KVM guest address space mapping code + * + * Copyright IBM Corp. 2007, 2016, 2025 + * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> + * Claudio Imbrenda <imbrenda@linux.ibm.com> + */ + +#ifndef ARCH_KVM_S390_GMAP_H +#define ARCH_KVM_S390_GMAP_H + +#define GMAP_SHADOW_FAKE_TABLE 1ULL + +int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb); +int gmap_convert_to_secure(struct gmap *gmap, unsigned long gaddr); +int gmap_destroy_page(struct gmap *gmap, unsigned long gaddr); +struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level); + +/** + * gmap_shadow_valid - check if a shadow guest address space matches the + * given properties and is still valid + * @sg: pointer to the shadow guest address space structure + * @asce: ASCE for which the shadow table is requested + * @edat_level: edat level to be used for the shadow translation + * + * Returns 1 if the gmap shadow is still valid and matches the given + * properties, the caller can continue using it. Returns 0 otherwise, the + * caller has to request a new shadow gmap in this case. + * + */ +static inline int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level) +{ + if (sg->removed) + return 0; + return sg->orig_asce == asce && sg->edat_level == edat_level; +} + +#endif diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index 5bbaadf75dc6..610dd44a948b 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -21,6 +21,7 @@ #include "gaccess.h" #include "trace.h" #include "trace-s390.h" +#include "gmap.h" u8 kvm_s390_get_ilen(struct kvm_vcpu *vcpu) { @@ -367,7 +368,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) reg2, &srcaddr, GACC_FETCH, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - rc = gmap_fault(vcpu->arch.gmap, srcaddr, 0); + rc = kvm_s390_handle_dat_fault(vcpu, srcaddr, 0); if (rc != 0) return rc; @@ -376,7 +377,7 @@ static int handle_mvpg_pei(struct kvm_vcpu *vcpu) reg1, &dstaddr, GACC_STORE, 0); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); - rc = gmap_fault(vcpu->arch.gmap, dstaddr, FAULT_FLAG_WRITE); + rc = kvm_s390_handle_dat_fault(vcpu, dstaddr, FOLL_WRITE); if (rc != 0) return rc; @@ -549,7 +550,7 @@ static int handle_pv_uvc(struct kvm_vcpu *vcpu) * If the unpin did not succeed, the guest will exit again for the UVC * and we will retry the unpin. */ - if (rc == -EINVAL) + if (rc == -EINVAL || rc == -ENXIO) return 0; /* * If we got -EAGAIN here, we simply return it. It will eventually diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index d4f031e086fc..07ff0e10cb7f 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2893,7 +2893,8 @@ int kvm_set_routing_entry(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { - u64 uaddr; + u64 uaddr_s, uaddr_i; + int idx; switch (ue->type) { /* we store the userspace addresses instead of the guest addresses */ @@ -2901,14 +2902,16 @@ int kvm_set_routing_entry(struct kvm *kvm, if (kvm_is_ucontrol(kvm)) return -EINVAL; e->set = set_adapter_int; - uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); - if (uaddr == -EFAULT) - return -EFAULT; - e->adapter.summary_addr = uaddr; - uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.ind_addr); - if (uaddr == -EFAULT) + + idx = srcu_read_lock(&kvm->srcu); + uaddr_s = gpa_to_hva(kvm, ue->u.adapter.summary_addr); + uaddr_i = gpa_to_hva(kvm, ue->u.adapter.ind_addr); + srcu_read_unlock(&kvm->srcu, idx); + + if (kvm_is_error_hva(uaddr_s) || kvm_is_error_hva(uaddr_i)) return -EFAULT; - e->adapter.ind_addr = uaddr; + e->adapter.summary_addr = uaddr_s; + e->adapter.ind_addr = uaddr_i; e->adapter.summary_offset = ue->u.adapter.summary_offset; e->adapter.ind_offset = ue->u.adapter.ind_offset; e->adapter.adapter_id = ue->u.adapter.adapter_id; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index d8080c27d45b..ebecb96bacce 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -50,6 +50,7 @@ #include "kvm-s390.h" #include "gaccess.h" #include "pci.h" +#include "gmap.h" #define CREATE_TRACE_POINTS #include "trace.h" @@ -3428,8 +3429,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) VM_EVENT(kvm, 3, "vm created with type %lu", type); if (type & KVM_VM_S390_UCONTROL) { + struct kvm_userspace_memory_region2 fake_memslot = { + .slot = KVM_S390_UCONTROL_MEMSLOT, + .guest_phys_addr = 0, + .userspace_addr = 0, + .memory_size = ALIGN_DOWN(TASK_SIZE, _SEGMENT_SIZE), + .flags = 0, + }; + kvm->arch.gmap = NULL; kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT; + /* one flat fake memslot covering the whole address-space */ + mutex_lock(&kvm->slots_lock); + KVM_BUG_ON(kvm_set_internal_memslot(kvm, &fake_memslot), kvm); + mutex_unlock(&kvm->slots_lock); } else { if (sclp.hamax == U64_MAX) kvm->arch.mem_limit = TASK_SIZE_MAX; @@ -4498,6 +4511,75 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu) return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS); } +static int __kvm_s390_fixup_fault_sync(struct gmap *gmap, gpa_t gaddr, unsigned int flags) +{ + struct kvm *kvm = gmap->private; + gfn_t gfn = gpa_to_gfn(gaddr); + bool unlocked; + hva_t vmaddr; + gpa_t tmp; + int rc; + + if (kvm_is_ucontrol(kvm)) { + tmp = __gmap_translate(gmap, gaddr); + gfn = gpa_to_gfn(tmp); + } + + vmaddr = gfn_to_hva(kvm, gfn); + rc = fixup_user_fault(gmap->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); + if (!rc) + rc = __gmap_link(gmap, gaddr, vmaddr); + return rc; +} + +/** + * __kvm_s390_mprotect_many() - Apply specified protection to guest pages + * @gmap: the gmap of the guest + * @gpa: the starting guest address + * @npages: how many pages to protect + * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE + * @bits: pgste notification bits to set + * + * Returns: 0 in case of success, < 0 in case of error - see gmap_protect_one() + * + * Context: kvm->srcu and gmap->mm need to be held in read mode + */ +int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot, + unsigned long bits) +{ + unsigned int fault_flag = (prot & PROT_WRITE) ? FAULT_FLAG_WRITE : 0; + gpa_t end = gpa + npages * PAGE_SIZE; + int rc; + + for (; gpa < end; gpa = ALIGN(gpa + 1, rc)) { + rc = gmap_protect_one(gmap, gpa, prot, bits); + if (rc == -EAGAIN) { + __kvm_s390_fixup_fault_sync(gmap, gpa, fault_flag); + rc = gmap_protect_one(gmap, gpa, prot, bits); + } + if (rc < 0) + return rc; + } + + return 0; +} + +static int kvm_s390_mprotect_notify_prefix(struct kvm_vcpu *vcpu) +{ + gpa_t gaddr = kvm_s390_get_prefix(vcpu); + int idx, rc; + + idx = srcu_read_lock(&vcpu->kvm->srcu); + mmap_read_lock(vcpu->arch.gmap->mm); + + rc = __kvm_s390_mprotect_many(vcpu->arch.gmap, gaddr, 2, PROT_WRITE, GMAP_NOTIFY_MPROT); + + mmap_read_unlock(vcpu->arch.gmap->mm); + srcu_read_unlock(&vcpu->kvm->srcu, idx); + + return rc; +} + static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu) { retry: @@ -4513,9 +4595,8 @@ retry: */ if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) { int rc; - rc = gmap_mprotect_notify(vcpu->arch.gmap, - kvm_s390_get_prefix(vcpu), - PAGE_SIZE * 2, PROT_WRITE); + + rc = kvm_s390_mprotect_notify_prefix(vcpu); if (rc) { kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu); return rc; @@ -4766,11 +4847,111 @@ static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_irq(vcpu, &pgm_info); } +static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu) +{ + KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, + "Unexpected program interrupt 0x%x, TEID 0x%016lx", + current->thread.gmap_int_code, current->thread.gmap_teid.val); +} + +/* + * __kvm_s390_handle_dat_fault() - handle a dat fault for the gmap of a vcpu + * @vcpu: the vCPU whose gmap is to be fixed up + * @gfn: the guest frame number used for memslots (including fake memslots) + * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps + * @flags: FOLL_* flags + * + * Return: 0 on success, < 0 in case of error. + * Context: The mm lock must not be held before calling. May sleep. + */ +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags) +{ + struct kvm_memory_slot *slot; + unsigned int fault_flags; + bool writable, unlocked; + unsigned long vmaddr; + struct page *page; + kvm_pfn_t pfn; + int rc; + + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return vcpu_post_run_addressing_exception(vcpu); + + fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0; + if (vcpu->arch.gmap->pfault_enabled) + flags |= FOLL_NOWAIT; + vmaddr = __gfn_to_hva_memslot(slot, gfn); + +try_again: + pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page); + + /* Access outside memory, inject addressing exception */ + if (is_noslot_pfn(pfn)) + return vcpu_post_run_addressing_exception(vcpu); + /* Signal pending: try again */ + if (pfn == KVM_PFN_ERR_SIGPENDING) + return -EAGAIN; + + /* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */ + if (pfn == KVM_PFN_ERR_NEEDS_IO) { + trace_kvm_s390_major_guest_pfault(vcpu); + if (kvm_arch_setup_async_pf(vcpu)) + return 0; + vcpu->stat.pfault_sync++; + /* Could not setup async pfault, try again synchronously */ + flags &= ~FOLL_NOWAIT; + goto try_again; + } + /* Any other error */ + if (is_error_pfn(pfn)) + return -EFAULT; + + /* Success */ + mmap_read_lock(vcpu->arch.gmap->mm); + /* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */ + rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked); + if (!rc) + rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr); + scoped_guard(spinlock, &vcpu->kvm->mmu_lock) { + kvm_release_faultin_page(vcpu->kvm, page, false, writable); + } + mmap_read_unlock(vcpu->arch.gmap->mm); + return rc; +} + +static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags) +{ + unsigned long gaddr_tmp; + gfn_t gfn; + + gfn = gpa_to_gfn(gaddr); + if (kvm_is_ucontrol(vcpu->kvm)) { + /* + * This translates the per-vCPU guest address into a + * fake guest address, which can then be used with the + * fake memslots that are identity mapping userspace. + * This allows ucontrol VMs to use the normal fault + * resolution path, like normal VMs. + */ + mmap_read_lock(vcpu->arch.gmap->mm); + gaddr_tmp = __gmap_translate(vcpu->arch.gmap, gaddr); + mmap_read_unlock(vcpu->arch.gmap->mm); + if (gaddr_tmp == -EFAULT) { + vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; + vcpu->run->s390_ucontrol.trans_exc_code = gaddr; + vcpu->run->s390_ucontrol.pgm_code = PGM_SEGMENT_TRANSLATION; + return -EREMOTE; + } + gfn = gpa_to_gfn(gaddr_tmp); + } + return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags); +} + static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) { unsigned int flags = 0; unsigned long gaddr; - int rc = 0; gaddr = current->thread.gmap_teid.addr * PAGE_SIZE; if (kvm_s390_cur_gmap_fault_is_write()) @@ -4781,9 +4962,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) vcpu->stat.exit_null++; break; case PGM_NON_SECURE_STORAGE_ACCESS: - KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, - "Unexpected program interrupt 0x%x, TEID 0x%016lx", - current->thread.gmap_int_code, current->thread.gmap_teid.val); + kvm_s390_assert_primary_as(vcpu); /* * This is normal operation; a page belonging to a protected * guest has not been imported yet. Try to import the page into @@ -4794,9 +4973,7 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) break; case PGM_SECURE_STORAGE_ACCESS: case PGM_SECURE_STORAGE_VIOLATION: - KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, - "Unexpected program interrupt 0x%x, TEID 0x%016lx", - current->thread.gmap_int_code, current->thread.gmap_teid.val); + kvm_s390_assert_primary_as(vcpu); /* * This can happen after a reboot with asynchronous teardown; * the new guest (normal or protected) will run on top of the @@ -4825,40 +5002,15 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu) case PGM_REGION_FIRST_TRANS: case PGM_REGION_SECOND_TRANS: case PGM_REGION_THIRD_TRANS: - KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm, - "Unexpected program interrupt 0x%x, TEID 0x%016lx", - current->thread.gmap_int_code, current->thread.gmap_teid.val); - if (vcpu->arch.gmap->pfault_enabled) { - rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT); - if (rc == -EFAULT) - return vcpu_post_run_addressing_exception(vcpu); - if (rc == -EAGAIN) { - trace_kvm_s390_major_guest_pfault(vcpu); - if (kvm_arch_setup_async_pf(vcpu)) - return 0; - vcpu->stat.pfault_sync++; - } else { - return rc; - } - } - rc = gmap_fault(vcpu->arch.gmap, gaddr, flags); - if (rc == -EFAULT) { - if (kvm_is_ucontrol(vcpu->kvm)) { - vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; - vcpu->run->s390_ucontrol.trans_exc_code = gaddr; - vcpu->run->s390_ucontrol.pgm_code = 0x10; - return -EREMOTE; - } - return vcpu_post_run_addressing_exception(vcpu); - } - break; + kvm_s390_assert_primary_as(vcpu); + return vcpu_dat_fault_handler(vcpu, gaddr, flags); default: KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx", current->thread.gmap_int_code, current->thread.gmap_teid.val); send_sig(SIGSEGV, current, 0); break; } - return rc; + return 0; } static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) @@ -5737,7 +5889,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, } #endif case KVM_S390_VCPU_FAULT: { - r = gmap_fault(vcpu->arch.gmap, arg, 0); + idx = srcu_read_lock(&vcpu->kvm->srcu); + r = vcpu_dat_fault_handler(vcpu, arg, 0); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_ENABLE_CAP: @@ -5853,7 +6007,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, { gpa_t size; - if (kvm_is_ucontrol(kvm)) + if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS) return -EINVAL; /* When we are protected, we should not change the memory slots */ @@ -5905,6 +6059,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, { int rc = 0; + if (kvm_is_ucontrol(kvm)) + return; + switch (change) { case KVM_MR_DELETE: rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 597d7a71deeb..8d3bbb2dd8d2 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -20,6 +20,8 @@ #include <asm/processor.h> #include <asm/sclp.h> +#define KVM_S390_UCONTROL_MEMSLOT (KVM_USER_MEM_SLOTS + 0) + static inline void kvm_s390_fpu_store(struct kvm_run *run) { fpu_stfpc(&run->s.regs.fpc); @@ -279,6 +281,15 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) return gd; } +static inline hva_t gpa_to_hva(struct kvm *kvm, gpa_t gpa) +{ + hva_t hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); + + if (!kvm_is_error_hva(hva)) + hva |= offset_in_page(gpa); + return hva; +} + /* implemented in pv.c */ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); @@ -408,6 +419,14 @@ void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu); void kvm_s390_set_cpu_timer(struct kvm_vcpu *vcpu, __u64 cputm); __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu); int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc); +int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags); +int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot, + unsigned long bits); + +static inline int kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gpa_t gaddr, unsigned int flags) +{ + return __kvm_s390_handle_dat_fault(vcpu, gpa_to_gfn(gaddr), gaddr, flags); +} /* implemented in diag.c */ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 75e81ba26d04..22c012aa5206 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -17,6 +17,7 @@ #include <linux/sched/mm.h> #include <linux/mmu_notifier.h> #include "kvm-s390.h" +#include "gmap.h" bool kvm_s390_pv_is_protected(struct kvm *kvm) { @@ -638,10 +639,28 @@ static int unpack_one(struct kvm *kvm, unsigned long addr, u64 tweak, .tweak[1] = offset, }; int ret = gmap_make_secure(kvm->arch.gmap, addr, &uvcb); + unsigned long vmaddr; + bool unlocked; *rc = uvcb.header.rc; *rrc = uvcb.header.rrc; + if (ret == -ENXIO) { + mmap_read_lock(kvm->mm); + vmaddr = gfn_to_hva(kvm, gpa_to_gfn(addr)); + if (kvm_is_error_hva(vmaddr)) { + ret = -EFAULT; + } else { + ret = fixup_user_fault(kvm->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); + if (!ret) + ret = __gmap_link(kvm->arch.gmap, addr, vmaddr); + } + mmap_read_unlock(kvm->mm); + if (!ret) + return -EAGAIN; + return ret; + } + if (ret && ret != -EAGAIN) KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: failed addr %llx with rc %x rrc %x", uvcb.gaddr, *rc, *rrc); @@ -660,6 +679,8 @@ int kvm_s390_pv_unpack(struct kvm *kvm, unsigned long addr, unsigned long size, KVM_UV_EVENT(kvm, 3, "PROTVIRT VM UNPACK: start addr %lx size %lx", addr, size); + guard(srcu)(&kvm->srcu); + while (offset < size) { ret = unpack_one(kvm, addr, tweak, offset, rc, rrc); if (ret == -EAGAIN) { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index a687695d8f68..a78df3a4f353 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -13,6 +13,7 @@ #include <linux/bitmap.h> #include <linux/sched/signal.h> #include <linux/io.h> +#include <linux/mman.h> #include <asm/gmap.h> #include <asm/mmu_context.h> @@ -22,6 +23,11 @@ #include <asm/facility.h> #include "kvm-s390.h" #include "gaccess.h" +#include "gmap.h" + +enum vsie_page_flags { + VSIE_PAGE_IN_USE = 0, +}; struct vsie_page { struct kvm_s390_sie_block scb_s; /* 0x0000 */ @@ -46,7 +52,18 @@ struct vsie_page { gpa_t gvrd_gpa; /* 0x0240 */ gpa_t riccbd_gpa; /* 0x0248 */ gpa_t sdnx_gpa; /* 0x0250 */ - __u8 reserved[0x0700 - 0x0258]; /* 0x0258 */ + /* + * guest address of the original SCB. Remains set for free vsie + * pages, so we can properly look them up in our addr_to_page + * radix tree. + */ + gpa_t scb_gpa; /* 0x0258 */ + /* + * Flags: must be set/cleared atomically after the vsie page can be + * looked up by other CPUs. + */ + unsigned long flags; /* 0x0260 */ + __u8 reserved[0x0700 - 0x0268]; /* 0x0268 */ struct kvm_s390_crypto_cb crycb; /* 0x0700 */ __u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE]; /* 0x0800 */ }; @@ -584,7 +601,6 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct vsie_page *cur; unsigned long prefix; - struct page *page; int i; if (!gmap_is_shadow(gmap)) @@ -594,10 +610,9 @@ void kvm_s390_vsie_gmap_notifier(struct gmap *gmap, unsigned long start, * therefore we can safely reference them all the time. */ for (i = 0; i < kvm->arch.vsie.page_count; i++) { - page = READ_ONCE(kvm->arch.vsie.pages[i]); - if (!page) + cur = READ_ONCE(kvm->arch.vsie.pages[i]); + if (!cur) continue; - cur = page_to_virt(page); if (READ_ONCE(cur->gmap) != gmap) continue; prefix = cur->scb_s.prefix << GUEST_PREFIX_SHIFT; @@ -1345,6 +1360,20 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return rc; } +/* Try getting a given vsie page, returning "true" on success. */ +static inline bool try_get_vsie_page(struct vsie_page *vsie_page) +{ + if (test_bit(VSIE_PAGE_IN_USE, &vsie_page->flags)) + return false; + return !test_and_set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); +} + +/* Put a vsie page acquired through get_vsie_page / try_get_vsie_page. */ +static void put_vsie_page(struct vsie_page *vsie_page) +{ + clear_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); +} + /* * Get or create a vsie page for a scb address. * @@ -1355,16 +1384,21 @@ static int vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) { struct vsie_page *vsie_page; - struct page *page; int nr_vcpus; rcu_read_lock(); - page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9); + vsie_page = radix_tree_lookup(&kvm->arch.vsie.addr_to_page, addr >> 9); rcu_read_unlock(); - if (page) { - if (page_ref_inc_return(page) == 2) - return page_to_virt(page); - page_ref_dec(page); + if (vsie_page) { + if (try_get_vsie_page(vsie_page)) { + if (vsie_page->scb_gpa == addr) + return vsie_page; + /* + * We raced with someone reusing + putting this vsie + * page before we grabbed it. + */ + put_vsie_page(vsie_page); + } } /* @@ -1375,36 +1409,40 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) mutex_lock(&kvm->arch.vsie.mutex); if (kvm->arch.vsie.page_count < nr_vcpus) { - page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA); - if (!page) { + vsie_page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO | GFP_DMA); + if (!vsie_page) { mutex_unlock(&kvm->arch.vsie.mutex); return ERR_PTR(-ENOMEM); } - page_ref_inc(page); - kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = page; + __set_bit(VSIE_PAGE_IN_USE, &vsie_page->flags); + kvm->arch.vsie.pages[kvm->arch.vsie.page_count] = vsie_page; kvm->arch.vsie.page_count++; } else { /* reuse an existing entry that belongs to nobody */ while (true) { - page = kvm->arch.vsie.pages[kvm->arch.vsie.next]; - if (page_ref_inc_return(page) == 2) + vsie_page = kvm->arch.vsie.pages[kvm->arch.vsie.next]; + if (try_get_vsie_page(vsie_page)) break; - page_ref_dec(page); kvm->arch.vsie.next++; kvm->arch.vsie.next %= nr_vcpus; } - radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9); + if (vsie_page->scb_gpa != ULONG_MAX) + radix_tree_delete(&kvm->arch.vsie.addr_to_page, + vsie_page->scb_gpa >> 9); } - page->index = addr; - /* double use of the same address */ - if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, page)) { - page_ref_dec(page); + /* Mark it as invalid until it resides in the tree. */ + vsie_page->scb_gpa = ULONG_MAX; + + /* Double use of the same address or allocation failure. */ + if (radix_tree_insert(&kvm->arch.vsie.addr_to_page, addr >> 9, + vsie_page)) { + put_vsie_page(vsie_page); mutex_unlock(&kvm->arch.vsie.mutex); return NULL; } + vsie_page->scb_gpa = addr; mutex_unlock(&kvm->arch.vsie.mutex); - vsie_page = page_to_virt(page); memset(&vsie_page->scb_s, 0, sizeof(struct kvm_s390_sie_block)); release_gmap_shadow(vsie_page); vsie_page->fault_addr = 0; @@ -1412,14 +1450,6 @@ static struct vsie_page *get_vsie_page(struct kvm *kvm, unsigned long addr) return vsie_page; } -/* put a vsie page acquired via get_vsie_page */ -static void put_vsie_page(struct kvm *kvm, struct vsie_page *vsie_page) -{ - struct page *page = pfn_to_page(__pa(vsie_page) >> PAGE_SHIFT); - - page_ref_dec(page); -} - int kvm_s390_handle_vsie(struct kvm_vcpu *vcpu) { struct vsie_page *vsie_page; @@ -1470,7 +1500,7 @@ out_unshadow: out_unpin_scb: unpin_scb(vcpu, vsie_page, scb_addr); out_put: - put_vsie_page(vcpu->kvm, vsie_page); + put_vsie_page(vsie_page); return rc < 0 ? rc : 0; } @@ -1486,18 +1516,18 @@ void kvm_s390_vsie_init(struct kvm *kvm) void kvm_s390_vsie_destroy(struct kvm *kvm) { struct vsie_page *vsie_page; - struct page *page; int i; mutex_lock(&kvm->arch.vsie.mutex); for (i = 0; i < kvm->arch.vsie.page_count; i++) { - page = kvm->arch.vsie.pages[i]; + vsie_page = kvm->arch.vsie.pages[i]; kvm->arch.vsie.pages[i] = NULL; - vsie_page = page_to_virt(page); release_gmap_shadow(vsie_page); /* free the radix tree entry */ - radix_tree_delete(&kvm->arch.vsie.addr_to_page, page->index >> 9); - __free_page(page); + if (vsie_page->scb_gpa != ULONG_MAX) + radix_tree_delete(&kvm->arch.vsie.addr_to_page, + vsie_page->scb_gpa >> 9); + free_page((unsigned long)vsie_page); } kvm->arch.vsie.page_count = 0; mutex_unlock(&kvm->arch.vsie.mutex); diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index c7c269d5c491..f977b7c37efc 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -31,51 +31,6 @@ void debug_user_asce(int exit) } #endif /*CONFIG_DEBUG_ENTRY */ -static unsigned long raw_copy_from_user_key(void *to, const void __user *from, - unsigned long size, unsigned long key) -{ - unsigned long rem; - union oac spec = { - .oac2.key = key, - .oac2.as = PSW_BITS_AS_SECONDARY, - .oac2.k = 1, - .oac2.a = 1, - }; - - asm volatile( - " lr 0,%[spec]\n" - "0: mvcos 0(%[to]),0(%[from]),%[size]\n" - "1: jz 5f\n" - " algr %[size],%[val]\n" - " slgr %[from],%[val]\n" - " slgr %[to],%[val]\n" - " j 0b\n" - "2: la %[rem],4095(%[from])\n" /* rem = from + 4095 */ - " nr %[rem],%[val]\n" /* rem = (from + 4095) & -4096 */ - " slgr %[rem],%[from]\n" - " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ - " jnh 6f\n" - "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" - "4: slgr %[size],%[rem]\n" - " j 6f\n" - "5: slgr %[size],%[size]\n" - "6:\n" - EX_TABLE(0b, 2b) - EX_TABLE(1b, 2b) - EX_TABLE(3b, 6b) - EX_TABLE(4b, 6b) - : [size] "+&a" (size), [from] "+&a" (from), [to] "+&a" (to), [rem] "=&a" (rem) - : [val] "a" (-4096UL), [spec] "d" (spec.val) - : "cc", "memory", "0"); - return size; -} - -unsigned long raw_copy_from_user(void *to, const void __user *from, unsigned long n) -{ - return raw_copy_from_user_key(to, from, n, 0); -} -EXPORT_SYMBOL(raw_copy_from_user); - unsigned long _copy_from_user_key(void *to, const void __user *from, unsigned long n, unsigned long key) { @@ -93,51 +48,6 @@ unsigned long _copy_from_user_key(void *to, const void __user *from, } EXPORT_SYMBOL(_copy_from_user_key); -static unsigned long raw_copy_to_user_key(void __user *to, const void *from, - unsigned long size, unsigned long key) -{ - unsigned long rem; - union oac spec = { - .oac1.key = key, - .oac1.as = PSW_BITS_AS_SECONDARY, - .oac1.k = 1, - .oac1.a = 1, - }; - - asm volatile( - " lr 0,%[spec]\n" - "0: mvcos 0(%[to]),0(%[from]),%[size]\n" - "1: jz 5f\n" - " algr %[size],%[val]\n" - " slgr %[to],%[val]\n" - " slgr %[from],%[val]\n" - " j 0b\n" - "2: la %[rem],4095(%[to])\n" /* rem = to + 4095 */ - " nr %[rem],%[val]\n" /* rem = (to + 4095) & -4096 */ - " slgr %[rem],%[to]\n" - " clgr %[size],%[rem]\n" /* copy crosses next page boundary? */ - " jnh 6f\n" - "3: mvcos 0(%[to]),0(%[from]),%[rem]\n" - "4: slgr %[size],%[rem]\n" - " j 6f\n" - "5: slgr %[size],%[size]\n" - "6:\n" - EX_TABLE(0b, 2b) - EX_TABLE(1b, 2b) - EX_TABLE(3b, 6b) - EX_TABLE(4b, 6b) - : [size] "+&a" (size), [to] "+&a" (to), [from] "+&a" (from), [rem] "=&a" (rem) - : [val] "a" (-4096UL), [spec] "d" (spec.val) - : "cc", "memory", "0"); - return size; -} - -unsigned long raw_copy_to_user(void __user *to, const void *from, unsigned long n) -{ - return raw_copy_to_user_key(to, from, n, 0); -} -EXPORT_SYMBOL(raw_copy_to_user); - unsigned long _copy_to_user_key(void __user *to, const void *from, unsigned long n, unsigned long key) { diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 7bf0f691827b..39f44b6256e0 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -332,7 +332,7 @@ static int cmm_timeout_handler(const struct ctl_table *ctl, int write, return 0; } -static struct ctl_table cmm_table[] = { +static const struct ctl_table cmm_table[] = { { .procname = "cmm_pages", .mode = 0644, diff --git a/arch/s390/mm/extable.c b/arch/s390/mm/extable.c index 0a0738a473af..a046be1715cf 100644 --- a/arch/s390/mm/extable.c +++ b/arch/s390/mm/extable.c @@ -7,6 +7,7 @@ #include <linux/panic.h> #include <asm/asm-extable.h> #include <asm/extable.h> +#include <asm/fpu.h> const struct exception_table_entry *s390_search_extables(unsigned long addr) { @@ -26,7 +27,7 @@ static bool ex_handler_fixup(const struct exception_table_entry *ex, struct pt_r return true; } -static bool ex_handler_ua_store(const struct exception_table_entry *ex, struct pt_regs *regs) +static bool ex_handler_ua_fault(const struct exception_table_entry *ex, struct pt_regs *regs) { unsigned int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data); @@ -35,18 +36,6 @@ static bool ex_handler_ua_store(const struct exception_table_entry *ex, struct p return true; } -static bool ex_handler_ua_load_mem(const struct exception_table_entry *ex, struct pt_regs *regs) -{ - unsigned int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data); - unsigned int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data); - size_t len = FIELD_GET(EX_DATA_LEN, ex->data); - - regs->gprs[reg_err] = -EFAULT; - memset((void *)regs->gprs[reg_addr], 0, len); - regs->psw.addr = extable_fixup(ex); - return true; -} - static bool ex_handler_ua_load_reg(const struct exception_table_entry *ex, bool pair, struct pt_regs *regs) { @@ -77,6 +66,13 @@ static bool ex_handler_zeropad(const struct exception_table_entry *ex, struct pt return true; } +static bool ex_handler_fpc(const struct exception_table_entry *ex, struct pt_regs *regs) +{ + fpu_sfpc(0); + regs->psw.addr = extable_fixup(ex); + return true; +} + bool fixup_exception(struct pt_regs *regs) { const struct exception_table_entry *ex; @@ -89,16 +85,16 @@ bool fixup_exception(struct pt_regs *regs) return ex_handler_fixup(ex, regs); case EX_TYPE_BPF: return ex_handler_bpf(ex, regs); - case EX_TYPE_UA_STORE: - return ex_handler_ua_store(ex, regs); - case EX_TYPE_UA_LOAD_MEM: - return ex_handler_ua_load_mem(ex, regs); + case EX_TYPE_UA_FAULT: + return ex_handler_ua_fault(ex, regs); case EX_TYPE_UA_LOAD_REG: return ex_handler_ua_load_reg(ex, false, regs); case EX_TYPE_UA_LOAD_REGPAIR: return ex_handler_ua_load_reg(ex, true, regs); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(ex, regs); + case EX_TYPE_FPC: + return ex_handler_fpc(ex, regs); } panic("invalid exception table entry"); } diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c index 16b8a36c56de..94d927785800 100644 --- a/arch/s390/mm/gmap.c +++ b/arch/s390/mm/gmap.c @@ -24,6 +24,16 @@ #include <asm/page.h> #include <asm/tlb.h> +/* + * The address is saved in a radix tree directly; NULL would be ambiguous, + * since 0 is a valid address, and NULL is returned when nothing was found. + * The lower bits are ignored by all users of the macro, so it can be used + * to distinguish a valid address 0 from a NULL. + */ +#define VALID_GADDR_FLAG 1 +#define IS_GADDR_VALID(gaddr) ((gaddr) & VALID_GADDR_FLAG) +#define MAKE_VALID_GADDR(gaddr) (((gaddr) & HPAGE_MASK) | VALID_GADDR_FLAG) + #define GMAP_SHADOW_FAKE_TABLE 1ULL static struct page *gmap_alloc_crst(void) @@ -43,7 +53,7 @@ static struct page *gmap_alloc_crst(void) * * Returns a guest address space structure. */ -static struct gmap *gmap_alloc(unsigned long limit) +struct gmap *gmap_alloc(unsigned long limit) { struct gmap *gmap; struct page *page; @@ -70,9 +80,7 @@ static struct gmap *gmap_alloc(unsigned long limit) gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT); if (!gmap) goto out; - INIT_LIST_HEAD(&gmap->crst_list); INIT_LIST_HEAD(&gmap->children); - INIT_LIST_HEAD(&gmap->pt_list); INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT); @@ -82,8 +90,6 @@ static struct gmap *gmap_alloc(unsigned long limit) page = gmap_alloc_crst(); if (!page) goto out_free; - page->index = 0; - list_add(&page->lru, &gmap->crst_list); table = page_to_virt(page); crst_table_init(table, etype); gmap->table = table; @@ -97,6 +103,7 @@ out_free: out: return NULL; } +EXPORT_SYMBOL_GPL(gmap_alloc); /** * gmap_create - create a guest address space @@ -185,32 +192,46 @@ static void gmap_rmap_radix_tree_free(struct radix_tree_root *root) } while (nr > 0); } +static void gmap_free_crst(unsigned long *table, bool free_ptes) +{ + bool is_segment = (table[0] & _SEGMENT_ENTRY_TYPE_MASK) == 0; + int i; + + if (is_segment) { + if (!free_ptes) + goto out; + for (i = 0; i < _CRST_ENTRIES; i++) + if (!(table[i] & _SEGMENT_ENTRY_INVALID)) + page_table_free_pgste(page_ptdesc(phys_to_page(table[i]))); + } else { + for (i = 0; i < _CRST_ENTRIES; i++) + if (!(table[i] & _REGION_ENTRY_INVALID)) + gmap_free_crst(__va(table[i] & PAGE_MASK), free_ptes); + } + +out: + free_pages((unsigned long)table, CRST_ALLOC_ORDER); +} + /** * gmap_free - free a guest address space * @gmap: pointer to the guest address space structure * * No locks required. There are no references to this gmap anymore. */ -static void gmap_free(struct gmap *gmap) +void gmap_free(struct gmap *gmap) { - struct page *page, *next; - /* Flush tlb of all gmaps (if not already done for shadows) */ if (!(gmap_is_shadow(gmap) && gmap->removed)) gmap_flush_tlb(gmap); /* Free all segment & region tables. */ - list_for_each_entry_safe(page, next, &gmap->crst_list, lru) - __free_pages(page, CRST_ALLOC_ORDER); + gmap_free_crst(gmap->table, gmap_is_shadow(gmap)); + gmap_radix_tree_free(&gmap->guest_to_host); gmap_radix_tree_free(&gmap->host_to_guest); /* Free additional data for a shadow gmap */ if (gmap_is_shadow(gmap)) { - struct ptdesc *ptdesc, *n; - - /* Free all page tables. */ - list_for_each_entry_safe(ptdesc, n, &gmap->pt_list, pt_list) - page_table_free_pgste(ptdesc); gmap_rmap_radix_tree_free(&gmap->host_to_rmap); /* Release reference to the parent */ gmap_put(gmap->parent); @@ -218,6 +239,7 @@ static void gmap_free(struct gmap *gmap) kfree(gmap); } +EXPORT_SYMBOL_GPL(gmap_free); /** * gmap_get - increase reference counter for guest address space @@ -298,10 +320,8 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, crst_table_init(new, init); spin_lock(&gmap->guest_table_lock); if (*table & _REGION_ENTRY_INVALID) { - list_add(&page->lru, &gmap->crst_list); *table = __pa(new) | _REGION_ENTRY_LENGTH | (*table & _REGION_ENTRY_TYPE_MASK); - page->index = gaddr; page = NULL; } spin_unlock(&gmap->guest_table_lock); @@ -310,21 +330,23 @@ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, return 0; } -/** - * __gmap_segment_gaddr - find virtual address from segment pointer - * @entry: pointer to a segment table entry in the guest address space - * - * Returns the virtual address in the guest address space for the segment - */ -static unsigned long __gmap_segment_gaddr(unsigned long *entry) +static unsigned long host_to_guest_lookup(struct gmap *gmap, unsigned long vmaddr) { - struct page *page; - unsigned long offset; + return (unsigned long)radix_tree_lookup(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); +} - offset = (unsigned long) entry / sizeof(unsigned long); - offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE; - page = pmd_pgtable_page((pmd_t *) entry); - return page->index + offset; +static unsigned long host_to_guest_delete(struct gmap *gmap, unsigned long vmaddr) +{ + return (unsigned long)radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); +} + +static pmd_t *host_to_guest_pmd_delete(struct gmap *gmap, unsigned long vmaddr, + unsigned long *gaddr) +{ + *gaddr = host_to_guest_delete(gmap, vmaddr); + if (IS_GADDR_VALID(*gaddr)) + return (pmd_t *)gmap_table_walk(gmap, *gaddr, 1); + return NULL; } /** @@ -336,16 +358,19 @@ static unsigned long __gmap_segment_gaddr(unsigned long *entry) */ static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr) { - unsigned long *entry; + unsigned long gaddr; int flush = 0; + pmd_t *pmdp; BUG_ON(gmap_is_shadow(gmap)); spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); - if (entry) { - flush = (*entry != _SEGMENT_ENTRY_EMPTY); - *entry = _SEGMENT_ENTRY_EMPTY; + + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { + flush = (pmd_val(*pmdp) != _SEGMENT_ENTRY_EMPTY); + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } + spin_unlock(&gmap->guest_table_lock); return flush; } @@ -464,26 +489,6 @@ unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr) EXPORT_SYMBOL_GPL(__gmap_translate); /** - * gmap_translate - translate a guest address to a user space address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * - * Returns user space address which corresponds to the guest address or - * -EFAULT if no such mapping exists. - * This function does not establish potentially missing page table entries. - */ -unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr) -{ - unsigned long rc; - - mmap_read_lock(gmap->mm); - rc = __gmap_translate(gmap, gaddr); - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_translate); - -/** * gmap_unlink - disconnect a page table from the gmap shadow tables * @mm: pointer to the parent mm_struct * @table: pointer to the host page table @@ -582,7 +587,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) spin_lock(&gmap->guest_table_lock); if (*table == _SEGMENT_ENTRY_EMPTY) { rc = radix_tree_insert(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT, table); + vmaddr >> PMD_SHIFT, + (void *)MAKE_VALID_GADDR(gaddr)); if (!rc) { if (pmd_leaf(*pmd)) { *table = (pmd_val(*pmd) & @@ -605,130 +611,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) radix_tree_preload_end(); return rc; } - -/** - * fixup_user_fault_nowait - manually resolve a user page fault without waiting - * @mm: mm_struct of target mm - * @address: user address - * @fault_flags:flags to pass down to handle_mm_fault() - * @unlocked: did we unlock the mmap_lock while retrying - * - * This function behaves similarly to fixup_user_fault(), but it guarantees - * that the fault will be resolved without waiting. The function might drop - * and re-acquire the mm lock, in which case @unlocked will be set to true. - * - * The guarantee is that the fault is handled without waiting, but the - * function itself might sleep, due to the lock. - * - * Context: Needs to be called with mm->mmap_lock held in read mode, and will - * return with the lock held in read mode; @unlocked will indicate whether - * the lock has been dropped and re-acquired. This is the same behaviour as - * fixup_user_fault(). - * - * Return: 0 on success, -EAGAIN if the fault cannot be resolved without - * waiting, -EFAULT if the fault cannot be resolved, -ENOMEM if out of - * memory. - */ -static int fixup_user_fault_nowait(struct mm_struct *mm, unsigned long address, - unsigned int fault_flags, bool *unlocked) -{ - struct vm_area_struct *vma; - unsigned int test_flags; - vm_fault_t fault; - int rc; - - fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; - test_flags = fault_flags & FAULT_FLAG_WRITE ? VM_WRITE : VM_READ; - - vma = find_vma(mm, address); - if (unlikely(!vma || address < vma->vm_start)) - return -EFAULT; - if (unlikely(!(vma->vm_flags & test_flags))) - return -EFAULT; - - fault = handle_mm_fault(vma, address, fault_flags, NULL); - /* the mm lock has been dropped, take it again */ - if (fault & VM_FAULT_COMPLETED) { - *unlocked = true; - mmap_read_lock(mm); - return 0; - } - /* the mm lock has not been dropped */ - if (fault & VM_FAULT_ERROR) { - rc = vm_fault_to_errno(fault, 0); - BUG_ON(!rc); - return rc; - } - /* the mm lock has not been dropped because of FAULT_FLAG_RETRY_NOWAIT */ - if (fault & VM_FAULT_RETRY) - return -EAGAIN; - /* nothing needed to be done and the mm lock has not been dropped */ - return 0; -} - -/** - * __gmap_fault - resolve a fault on a guest address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * @fault_flags: flags to pass down to handle_mm_fault() - * - * Context: Needs to be called with mm->mmap_lock held in read mode. Might - * drop and re-acquire the lock. Will always return with the lock held. - */ -static int __gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags) -{ - unsigned long vmaddr; - bool unlocked; - int rc = 0; - -retry: - unlocked = false; - - vmaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(vmaddr)) - return vmaddr; - - if (fault_flags & FAULT_FLAG_RETRY_NOWAIT) - rc = fixup_user_fault_nowait(gmap->mm, vmaddr, fault_flags, &unlocked); - else - rc = fixup_user_fault(gmap->mm, vmaddr, fault_flags, &unlocked); - if (rc) - return rc; - /* - * In the case that fixup_user_fault unlocked the mmap_lock during - * fault-in, redo __gmap_translate() to avoid racing with a - * map/unmap_segment. - * In particular, __gmap_translate(), fixup_user_fault{,_nowait}(), - * and __gmap_link() must all be called atomically in one go; if the - * lock had been dropped in between, a retry is needed. - */ - if (unlocked) - goto retry; - - return __gmap_link(gmap, gaddr, vmaddr); -} - -/** - * gmap_fault - resolve a fault on a guest address - * @gmap: pointer to guest mapping meta data structure - * @gaddr: guest address - * @fault_flags: flags to pass down to handle_mm_fault() - * - * Returns 0 on success, -ENOMEM for out of memory conditions, -EFAULT if the - * vm address is already mapped to a different guest segment, and -EAGAIN if - * FAULT_FLAG_RETRY_NOWAIT was specified and the fault could not be processed - * immediately. - */ -int gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags) -{ - int rc; - - mmap_read_lock(gmap->mm); - rc = __gmap_fault(gmap, gaddr, fault_flags); - mmap_read_unlock(gmap->mm); - return rc; -} -EXPORT_SYMBOL_GPL(gmap_fault); +EXPORT_SYMBOL(__gmap_link); /* * this function is assumed to be called with mmap_lock held @@ -853,8 +736,7 @@ static void gmap_call_notifier(struct gmap *gmap, unsigned long start, * * Note: Can also be called for shadow gmaps. */ -static inline unsigned long *gmap_table_walk(struct gmap *gmap, - unsigned long gaddr, int level) +unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level) { const int asce_type = gmap->asce & _ASCE_TYPE_MASK; unsigned long *table = gmap->table; @@ -905,6 +787,7 @@ static inline unsigned long *gmap_table_walk(struct gmap *gmap, } return table; } +EXPORT_SYMBOL(gmap_table_walk); /** * gmap_pte_op_walk - walk the gmap page table, get the page table lock @@ -1101,86 +984,40 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr, * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE * @bits: pgste notification bits to set * - * Returns 0 if successfully protected, -ENOMEM if out of memory and - * -EFAULT if gaddr is invalid (or mapping for shadows is missing). + * Returns: + * PAGE_SIZE if a small page was successfully protected; + * HPAGE_SIZE if a large page was successfully protected; + * -ENOMEM if out of memory; + * -EFAULT if gaddr is invalid (or mapping for shadows is missing); + * -EAGAIN if the guest mapping is missing and should be fixed by the caller. * - * Called with sg->mm->mmap_lock in read. + * Context: Called with sg->mm->mmap_lock in read. */ -static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr, - unsigned long len, int prot, unsigned long bits) +int gmap_protect_one(struct gmap *gmap, unsigned long gaddr, int prot, unsigned long bits) { - unsigned long vmaddr, dist; pmd_t *pmdp; - int rc; + int rc = 0; BUG_ON(gmap_is_shadow(gmap)); - while (len) { - rc = -EAGAIN; - pmdp = gmap_pmd_op_walk(gmap, gaddr); - if (pmdp) { - if (!pmd_leaf(*pmdp)) { - rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, - bits); - if (!rc) { - len -= PAGE_SIZE; - gaddr += PAGE_SIZE; - } - } else { - rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, - bits); - if (!rc) { - dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK); - len = len < dist ? 0 : len - dist; - gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE; - } - } - gmap_pmd_op_end(gmap, pmdp); - } - if (rc) { - if (rc == -EINVAL) - return rc; - /* -EAGAIN, fixup of userspace mm and gmap */ - vmaddr = __gmap_translate(gmap, gaddr); - if (IS_ERR_VALUE(vmaddr)) - return vmaddr; - rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot); - if (rc) - return rc; - } - } - return 0; -} + pmdp = gmap_pmd_op_walk(gmap, gaddr); + if (!pmdp) + return -EAGAIN; -/** - * gmap_mprotect_notify - change access rights for a range of ptes and - * call the notifier if any pte changes again - * @gmap: pointer to guest mapping meta data structure - * @gaddr: virtual address in the guest address space - * @len: size of area - * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE - * - * Returns 0 if for each page in the given range a gmap mapping exists, - * the new access rights could be set and the notifier could be armed. - * If the gmap mapping is missing for one or more pages -EFAULT is - * returned. If no memory could be allocated -ENOMEM is returned. - * This function establishes missing page table entries. - */ -int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr, - unsigned long len, int prot) -{ - int rc; + if (!pmd_leaf(*pmdp)) { + rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, bits); + if (!rc) + rc = PAGE_SIZE; + } else { + rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, bits); + if (!rc) + rc = HPAGE_SIZE; + } + gmap_pmd_op_end(gmap, pmdp); - if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap)) - return -EINVAL; - if (!MACHINE_HAS_ESOP && prot == PROT_READ) - return -EINVAL; - mmap_read_lock(gmap->mm); - rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT); - mmap_read_unlock(gmap->mm); return rc; } -EXPORT_SYMBOL_GPL(gmap_mprotect_notify); +EXPORT_SYMBOL_GPL(gmap_protect_one); /** * gmap_read_table - get an unsigned long value from a guest page table using @@ -1414,7 +1251,6 @@ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr) __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ ptdesc = page_ptdesc(phys_to_page(pgt)); - list_del(&ptdesc->pt_list); page_table_free_pgste(ptdesc); } @@ -1442,7 +1278,6 @@ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr, __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ ptdesc = page_ptdesc(phys_to_page(pgt)); - list_del(&ptdesc->pt_list); page_table_free_pgste(ptdesc); } } @@ -1472,7 +1307,6 @@ static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr) __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1500,7 +1334,6 @@ static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr, __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1530,7 +1363,6 @@ static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr) __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1558,7 +1390,6 @@ static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr, __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1588,7 +1419,6 @@ static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr) __gmap_unshadow_r2t(sg, raddr, __va(r2t)); /* Free region 2 table */ page = phys_to_page(r2t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } @@ -1620,7 +1450,6 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr, r1t[i] = _REGION1_ENTRY_EMPTY; /* Free region 2 table */ page = phys_to_page(r2t); - list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } @@ -1631,7 +1460,7 @@ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr, * * Called with sg->guest_table_lock */ -static void gmap_unshadow(struct gmap *sg) +void gmap_unshadow(struct gmap *sg) { unsigned long *table; @@ -1657,143 +1486,7 @@ static void gmap_unshadow(struct gmap *sg) break; } } - -/** - * gmap_find_shadow - find a specific asce in the list of shadow tables - * @parent: pointer to the parent gmap - * @asce: ASCE for which the shadow table is created - * @edat_level: edat level to be used for the shadow translation - * - * Returns the pointer to a gmap if a shadow table with the given asce is - * already available, ERR_PTR(-EAGAIN) if another one is just being created, - * otherwise NULL - */ -static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, - int edat_level) -{ - struct gmap *sg; - - list_for_each_entry(sg, &parent->children, list) { - if (sg->orig_asce != asce || sg->edat_level != edat_level || - sg->removed) - continue; - if (!sg->initialized) - return ERR_PTR(-EAGAIN); - refcount_inc(&sg->ref_count); - return sg; - } - return NULL; -} - -/** - * gmap_shadow_valid - check if a shadow guest address space matches the - * given properties and is still valid - * @sg: pointer to the shadow guest address space structure - * @asce: ASCE for which the shadow table is requested - * @edat_level: edat level to be used for the shadow translation - * - * Returns 1 if the gmap shadow is still valid and matches the given - * properties, the caller can continue using it. Returns 0 otherwise, the - * caller has to request a new shadow gmap in this case. - * - */ -int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level) -{ - if (sg->removed) - return 0; - return sg->orig_asce == asce && sg->edat_level == edat_level; -} -EXPORT_SYMBOL_GPL(gmap_shadow_valid); - -/** - * gmap_shadow - create/find a shadow guest address space - * @parent: pointer to the parent gmap - * @asce: ASCE for which the shadow table is created - * @edat_level: edat level to be used for the shadow translation - * - * The pages of the top level page table referred by the asce parameter - * will be set to read-only and marked in the PGSTEs of the kvm process. - * The shadow table will be removed automatically on any change to the - * PTE mapping for the source table. - * - * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory, - * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the - * parent gmap table could not be protected. - */ -struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, - int edat_level) -{ - struct gmap *sg, *new; - unsigned long limit; - int rc; - - BUG_ON(parent->mm->context.allow_gmap_hpage_1m); - BUG_ON(gmap_is_shadow(parent)); - spin_lock(&parent->shadow_lock); - sg = gmap_find_shadow(parent, asce, edat_level); - spin_unlock(&parent->shadow_lock); - if (sg) - return sg; - /* Create a new shadow gmap */ - limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11)); - if (asce & _ASCE_REAL_SPACE) - limit = -1UL; - new = gmap_alloc(limit); - if (!new) - return ERR_PTR(-ENOMEM); - new->mm = parent->mm; - new->parent = gmap_get(parent); - new->private = parent->private; - new->orig_asce = asce; - new->edat_level = edat_level; - new->initialized = false; - spin_lock(&parent->shadow_lock); - /* Recheck if another CPU created the same shadow */ - sg = gmap_find_shadow(parent, asce, edat_level); - if (sg) { - spin_unlock(&parent->shadow_lock); - gmap_free(new); - return sg; - } - if (asce & _ASCE_REAL_SPACE) { - /* only allow one real-space gmap shadow */ - list_for_each_entry(sg, &parent->children, list) { - if (sg->orig_asce & _ASCE_REAL_SPACE) { - spin_lock(&sg->guest_table_lock); - gmap_unshadow(sg); - spin_unlock(&sg->guest_table_lock); - list_del(&sg->list); - gmap_put(sg); - break; - } - } - } - refcount_set(&new->ref_count, 2); - list_add(&new->list, &parent->children); - if (asce & _ASCE_REAL_SPACE) { - /* nothing to protect, return right away */ - new->initialized = true; - spin_unlock(&parent->shadow_lock); - return new; - } - spin_unlock(&parent->shadow_lock); - /* protect after insertion, so it will get properly invalidated */ - mmap_read_lock(parent->mm); - rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN, - ((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE, - PROT_READ, GMAP_NOTIFY_SHADOW); - mmap_read_unlock(parent->mm); - spin_lock(&parent->shadow_lock); - new->initialized = true; - if (rc) { - list_del(&new->list); - gmap_free(new); - new = ERR_PTR(rc); - } - spin_unlock(&parent->shadow_lock); - return new; -} -EXPORT_SYMBOL_GPL(gmap_shadow); +EXPORT_SYMBOL(gmap_unshadow); /** * gmap_shadow_r2t - create an empty shadow region 2 table @@ -1827,9 +1520,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = r2t & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_r2t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -1851,7 +1541,6 @@ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, _REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= (r2t & _REGION_ENTRY_PROTECT); - list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; @@ -1911,9 +1600,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = r3t & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_r3t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -1935,7 +1621,6 @@ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, _REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= (r3t & _REGION_ENTRY_PROTECT); - list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; @@ -1995,9 +1680,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = sgt & _REGION_ENTRY_ORIGIN; - if (fake) - page->index |= GMAP_SHADOW_FAKE_TABLE; s_sgt = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); @@ -2019,7 +1701,6 @@ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, _REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= sgt & _REGION_ENTRY_PROTECT; - list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; @@ -2052,45 +1733,22 @@ out_free: } EXPORT_SYMBOL_GPL(gmap_shadow_sgt); -/** - * gmap_shadow_pgt_lookup - find a shadow page table - * @sg: pointer to the shadow guest address space structure - * @saddr: the address in the shadow aguest address space - * @pgt: parent gmap address of the page table to get shadowed - * @dat_protection: if the pgtable is marked as protected by dat - * @fake: pgt references contiguous guest memory block, not a pgtable - * - * Returns 0 if the shadow page table was found and -EAGAIN if the page - * table was not found. - * - * Called with sg->mm->mmap_lock in read. - */ -int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, - unsigned long *pgt, int *dat_protection, - int *fake) +static void gmap_pgste_set_pgt_addr(struct ptdesc *ptdesc, unsigned long pgt_addr) { - unsigned long *table; - struct page *page; - int rc; + unsigned long *pgstes = page_to_virt(ptdesc_page(ptdesc)); - BUG_ON(!gmap_is_shadow(sg)); - spin_lock(&sg->guest_table_lock); - table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */ - if (table && !(*table & _SEGMENT_ENTRY_INVALID)) { - /* Shadow page tables are full pages (pte+pgste) */ - page = pfn_to_page(*table >> PAGE_SHIFT); - *pgt = page->index & ~GMAP_SHADOW_FAKE_TABLE; - *dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT); - *fake = !!(page->index & GMAP_SHADOW_FAKE_TABLE); - rc = 0; - } else { - rc = -EAGAIN; - } - spin_unlock(&sg->guest_table_lock); - return rc; + pgstes += _PAGE_ENTRIES; + + pgstes[0] &= ~PGSTE_ST2_MASK; + pgstes[1] &= ~PGSTE_ST2_MASK; + pgstes[2] &= ~PGSTE_ST2_MASK; + pgstes[3] &= ~PGSTE_ST2_MASK; + pgstes[0] |= (pgt_addr >> 16) & PGSTE_ST2_MASK; + pgstes[1] |= pgt_addr & PGSTE_ST2_MASK; + pgstes[2] |= (pgt_addr << 16) & PGSTE_ST2_MASK; + pgstes[3] |= (pgt_addr << 32) & PGSTE_ST2_MASK; } -EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup); /** * gmap_shadow_pgt - instantiate a shadow page table @@ -2119,9 +1777,10 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, ptdesc = page_table_alloc_pgste(sg->mm); if (!ptdesc) return -ENOMEM; - ptdesc->pt_index = pgt & _SEGMENT_ENTRY_ORIGIN; + origin = pgt & _SEGMENT_ENTRY_ORIGIN; if (fake) - ptdesc->pt_index |= GMAP_SHADOW_FAKE_TABLE; + origin |= GMAP_SHADOW_FAKE_TABLE; + gmap_pgste_set_pgt_addr(ptdesc, origin); s_pgt = page_to_phys(ptdesc_page(ptdesc)); /* Install shadow page table */ spin_lock(&sg->guest_table_lock); @@ -2140,7 +1799,6 @@ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, /* mark as invalid as long as the parent table is not protected */ *table = (unsigned long) s_pgt | _SEGMENT_ENTRY | (pgt & _SEGMENT_ENTRY_PROTECT) | _SEGMENT_ENTRY_INVALID; - list_add(&ptdesc->pt_list, &sg->pt_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_SEGMENT_ENTRY_INVALID; @@ -2318,7 +1976,6 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte, unsigned long bits) { unsigned long offset, gaddr = 0; - unsigned long *table; struct gmap *gmap, *sg, *next; offset = ((unsigned long) pte) & (255 * sizeof(pte_t)); @@ -2326,12 +1983,9 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - table = radix_tree_lookup(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (table) - gaddr = __gmap_segment_gaddr(table) + offset; + gaddr = host_to_guest_lookup(gmap, vmaddr) + offset; spin_unlock(&gmap->guest_table_lock); - if (!table) + if (!IS_GADDR_VALID(gaddr)) continue; if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) { @@ -2391,10 +2045,8 @@ static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr, rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); if (pmdp) { - gaddr = __gmap_segment_gaddr((unsigned long *)pmdp); pmdp_notify_gmap(gmap, pmdp, gaddr); WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | _SEGMENT_ENTRY_GMAP_UC | @@ -2438,28 +2090,25 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_csp); */ void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr) { - unsigned long *entry, gaddr; + unsigned long gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (entry) { - pmdp = (pmd_t *)entry; - gaddr = __gmap_segment_gaddr(entry); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { pmdp_notify_gmap(gmap, pmdp, gaddr); - WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | - _SEGMENT_ENTRY_GMAP_UC | - _SEGMENT_ENTRY)); + WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC | + _SEGMENT_ENTRY)); if (MACHINE_HAS_TLB_GUEST) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_LOCAL); else if (MACHINE_HAS_IDTE) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL); - *entry = _SEGMENT_ENTRY_EMPTY; + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } spin_unlock(&gmap->guest_table_lock); } @@ -2474,22 +2123,19 @@ EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local); */ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr) { - unsigned long *entry, gaddr; + unsigned long gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); - entry = radix_tree_delete(&gmap->host_to_guest, - vmaddr >> PMD_SHIFT); - if (entry) { - pmdp = (pmd_t *)entry; - gaddr = __gmap_segment_gaddr(entry); + pmdp = host_to_guest_pmd_delete(gmap, vmaddr, &gaddr); + if (pmdp) { pmdp_notify_gmap(gmap, pmdp, gaddr); - WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | - _SEGMENT_ENTRY_GMAP_UC | - _SEGMENT_ENTRY)); + WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | + _SEGMENT_ENTRY_GMAP_UC | + _SEGMENT_ENTRY)); if (MACHINE_HAS_TLB_GUEST) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_GLOBAL); @@ -2497,7 +2143,7 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL); else __pmdp_csp(pmdp); - *entry = _SEGMENT_ENTRY_EMPTY; + *pmdp = __pmd(_SEGMENT_ENTRY_EMPTY); } spin_unlock(&gmap->guest_table_lock); } @@ -2943,49 +2589,6 @@ int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, EXPORT_SYMBOL_GPL(__s390_uv_destroy_range); /** - * s390_unlist_old_asce - Remove the topmost level of page tables from the - * list of page tables of the gmap. - * @gmap: the gmap whose table is to be removed - * - * On s390x, KVM keeps a list of all pages containing the page tables of the - * gmap (the CRST list). This list is used at tear down time to free all - * pages that are now not needed anymore. - * - * This function removes the topmost page of the tree (the one pointed to by - * the ASCE) from the CRST list. - * - * This means that it will not be freed when the VM is torn down, and needs - * to be handled separately by the caller, unless a leak is actually - * intended. Notice that this function will only remove the page from the - * list, the page will still be used as a top level page table (and ASCE). - */ -void s390_unlist_old_asce(struct gmap *gmap) -{ - struct page *old; - - old = virt_to_page(gmap->table); - spin_lock(&gmap->guest_table_lock); - list_del(&old->lru); - /* - * Sometimes the topmost page might need to be "removed" multiple - * times, for example if the VM is rebooted into secure mode several - * times concurrently, or if s390_replace_asce fails after calling - * s390_remove_old_asce and is attempted again later. In that case - * the old asce has been removed from the list, and therefore it - * will not be freed when the VM terminates, but the ASCE is still - * in use and still pointed to. - * A subsequent call to replace_asce will follow the pointer and try - * to remove the same page from the list again. - * Therefore it's necessary that the page of the ASCE has valid - * pointers, so list_del can work (and do nothing) without - * dereferencing stale or invalid pointers. - */ - INIT_LIST_HEAD(&old->lru); - spin_unlock(&gmap->guest_table_lock); -} -EXPORT_SYMBOL_GPL(s390_unlist_old_asce); - -/** * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy * @gmap: the gmap whose ASCE needs to be replaced * @@ -3004,8 +2607,6 @@ int s390_replace_asce(struct gmap *gmap) struct page *page; void *table; - s390_unlist_old_asce(gmap); - /* Replacing segment type ASCEs would cause serious issues */ if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) return -EINVAL; @@ -3013,19 +2614,9 @@ int s390_replace_asce(struct gmap *gmap) page = gmap_alloc_crst(); if (!page) return -ENOMEM; - page->index = 0; table = page_to_virt(page); memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT)); - /* - * The caller has to deal with the old ASCE, but here we make sure - * the new one is properly added to the CRST list, so that - * it will be freed when the VM is torn down. - */ - spin_lock(&gmap->guest_table_lock); - list_add(&page->lru, &gmap->crst_list); - spin_unlock(&gmap->guest_table_lock); - /* Set new table origin while preserving existing ASCE control bits */ asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table); WRITE_ONCE(gmap->asce, asce); @@ -3035,3 +2626,31 @@ int s390_replace_asce(struct gmap *gmap) return 0; } EXPORT_SYMBOL_GPL(s390_replace_asce); + +/** + * kvm_s390_wiggle_split_folio() - try to drain extra references to a folio and optionally split + * @mm: the mm containing the folio to work on + * @folio: the folio + * @split: whether to split a large folio + * + * Context: Must be called while holding an extra reference to the folio; + * the mm lock should not be held. + */ +int kvm_s390_wiggle_split_folio(struct mm_struct *mm, struct folio *folio, bool split) +{ + int rc; + + lockdep_assert_not_held(&mm->mmap_lock); + folio_wait_writeback(folio); + lru_add_drain_all(); + if (split) { + folio_lock(folio); + rc = split_folio(folio); + folio_unlock(folio); + + if (rc != -EBUSY) + return rc; + } + return -EAGAIN; +} +EXPORT_SYMBOL_GPL(kvm_s390_wiggle_split_folio); diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index d33f55b7ee98..30387a6e98ff 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -21,7 +21,7 @@ int page_table_allocate_pgste = 0; EXPORT_SYMBOL(page_table_allocate_pgste); -static struct ctl_table page_table_sysctl[] = { +static const struct ctl_table page_table_sysctl[] = { { .procname = "allocate_pgste", .data = &page_table_allocate_pgste, @@ -176,8 +176,6 @@ unsigned long *page_table_alloc(struct mm_struct *mm) } table = ptdesc_to_virt(ptdesc); __arch_set_page_dat(table, 1); - /* pt_list is used by gmap only */ - INIT_LIST_HEAD(&ptdesc->pt_list); memset64((u64 *)table, _PAGE_INVALID, PTRS_PER_PTE); memset64((u64 *)table + PTRS_PER_PTE, 0, PTRS_PER_PTE); return table; diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 7c684c54e721..8ead999e340b 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -662,7 +662,7 @@ void __init vmem_map_init(void) if (!static_key_enabled(&cpu_has_bear)) set_memory_x(0, 1); if (debug_pagealloc_enabled()) - __set_memory_4k(__va(0), __va(0) + ident_map_size); + __set_memory_4k(__va(0), absolute_pointer(__va(0)) + ident_map_size); pr_info("Write protected kernel read-only data: %luk\n", (unsigned long)(__end_rodata - _stext) >> 10); } diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index d5ace00d10f0..39a481ec4a40 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -171,7 +171,6 @@ void zpci_bus_scan_busses(void) static bool zpci_bus_is_multifunction_root(struct zpci_dev *zdev) { return !s390_pci_no_rid && zdev->rid_available && - zpci_is_device_configured(zdev) && !zdev->vfn; } @@ -332,6 +331,17 @@ error: return rc; } +static bool zpci_bus_is_isolated_vf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + struct pci_dev *pdev; + + pdev = zpci_iov_find_parent_pf(zbus, zdev); + if (!pdev) + return true; + pci_dev_put(pdev); + return false; +} + int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) { bool topo_is_tid = zdev->tid_avail; @@ -346,6 +356,15 @@ int zpci_bus_device_register(struct zpci_dev *zdev, struct pci_ops *ops) topo = topo_is_tid ? zdev->tid : zdev->pchid; zbus = zpci_bus_get(topo, topo_is_tid); + /* + * An isolated VF gets its own domain/bus even if there exists + * a matching domain/bus already + */ + if (zbus && zpci_bus_is_isolated_vf(zbus, zdev)) { + zpci_bus_put(zbus); + zbus = NULL; + } + if (!zbus) { zbus = zpci_bus_alloc(topo, topo_is_tid); if (!zbus) diff --git a/arch/s390/pci/pci_iov.c b/arch/s390/pci/pci_iov.c index ead062bf2b41..191e56a623f6 100644 --- a/arch/s390/pci/pci_iov.c +++ b/arch/s390/pci/pci_iov.c @@ -60,18 +60,35 @@ static int zpci_iov_link_virtfn(struct pci_dev *pdev, struct pci_dev *virtfn, in return 0; } -int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +/** + * zpci_iov_find_parent_pf - Find the parent PF, if any, of the given function + * @zbus: The bus that the PCI function is on, or would be added on + * @zdev: The PCI function + * + * Finds the parent PF, if it exists and is configured, of the given PCI function + * and increments its refcount. Th PF is searched for on the provided bus so the + * caller has to ensure that this is the correct bus to search. This function may + * be used before adding the PCI function to a zbus. + * + * Return: Pointer to the struct pci_dev of the parent PF or NULL if it not + * found. If the function is not a VF or has no RequesterID information, + * NULL is returned as well. + */ +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) { - int i, cand_devfn; - struct zpci_dev *zdev; + int i, vfid, devfn, cand_devfn; struct pci_dev *pdev; - int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ - int rc = 0; if (!zbus->multifunction) - return 0; - - /* If the parent PF for the given VF is also configured in the + return NULL; + /* Non-VFs and VFs without RID available don't have a parent */ + if (!zdev->vfn || !zdev->rid_available) + return NULL; + /* Linux vfid starts at 0 vfn at 1 */ + vfid = zdev->vfn - 1; + devfn = zdev->rid & ZPCI_RID_MASK_DEVFN; + /* + * If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what * devfn the VF would have if it belonged to that PF using the PF's @@ -85,15 +102,26 @@ int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn if (!pdev) continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); - if (cand_devfn == virtfn->devfn) { - rc = zpci_iov_link_virtfn(pdev, virtfn, vfid); - /* balance pci_get_slot() */ - pci_dev_put(pdev); - break; - } + if (cand_devfn == devfn) + return pdev; /* balance pci_get_slot() */ pci_dev_put(pdev); } } + return NULL; +} + +int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) +{ + struct zpci_dev *zdev = to_zpci(virtfn); + struct pci_dev *pdev_pf; + int rc = 0; + + pdev_pf = zpci_iov_find_parent_pf(zbus, zdev); + if (pdev_pf) { + /* Linux' vfids start at 0 while zdev->vfn starts at 1 */ + rc = zpci_iov_link_virtfn(pdev_pf, virtfn, zdev->vfn - 1); + pci_dev_put(pdev_pf); + } return rc; } diff --git a/arch/s390/pci/pci_iov.h b/arch/s390/pci/pci_iov.h index e3fa4e77fc86..d2c2793eb0f3 100644 --- a/arch/s390/pci/pci_iov.h +++ b/arch/s390/pci/pci_iov.h @@ -19,6 +19,8 @@ void zpci_iov_map_resources(struct pci_dev *pdev); int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn); +struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev); + #else /* CONFIG_PCI_IOV */ static inline void zpci_iov_remove_virtfn(struct pci_dev *pdev, int vfn) {} @@ -28,5 +30,10 @@ static inline int zpci_iov_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *v { return 0; } + +static inline struct pci_dev *zpci_iov_find_parent_pf(struct zpci_bus *zbus, struct zpci_dev *zdev) +{ + return NULL; +} #endif /* CONFIG_PCI_IOV */ #endif /* __S390_PCI_IOV_h */ diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index 24eccaa29337..bdcf2a3b6c41 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -13,7 +13,7 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE $(call if_changed_rule,as_o_S) -KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes +KBUILD_CFLAGS := -std=gnu11 -fno-strict-aliasing -Wall -Wstrict-prototypes KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c index a1bc02b29c81..7d76c417f83f 100644 --- a/arch/s390/tools/gen_opcode_table.c +++ b/arch/s390/tools/gen_opcode_table.c @@ -201,6 +201,17 @@ static int cmp_long_insn(const void *a, const void *b) return strcmp(((struct insn *)a)->name, ((struct insn *)b)->name); } +static void print_insn_name(const char *name) +{ + size_t i, len; + + len = strlen(name); + printf("{"); + for (i = 0; i < len; i++) + printf(" \'%c\',", name[i]); + printf(" }"); +} + static void print_long_insn(struct gen_opcode *desc) { struct insn *insn; @@ -223,7 +234,9 @@ static void print_long_insn(struct gen_opcode *desc) insn = &desc->insn[i]; if (insn->name_len < 6) continue; - printf("\t[LONG_INSN_%s] = \"%s\", \\\n", insn->upper, insn->name); + printf("\t[LONG_INSN_%s] = ", insn->upper); + print_insn_name(insn->name); + printf(", \\\n"); } printf("}\n\n"); } @@ -236,11 +249,13 @@ static void print_opcode(struct insn *insn, int nr) if (insn->type->byte != 0) opcode += 2; printf("\t[%4d] = { .opfrag = 0x%s, .format = INSTR_%s, ", nr, opcode, insn->format); - if (insn->name_len < 6) - printf(".name = \"%s\" ", insn->name); - else - printf(".offset = LONG_INSN_%s ", insn->upper); - printf("}, \\\n"); + if (insn->name_len < 6) { + printf(".name = "); + print_insn_name(insn->name); + } else { + printf(".offset = LONG_INSN_%s", insn->upper); + } + printf(" }, \\\n"); } static void add_to_group(struct gen_opcode *desc, struct insn *insn, int offset) diff --git a/arch/sh/Kbuild b/arch/sh/Kbuild index 056efec72c2a..0da6c6d6821a 100644 --- a/arch/sh/Kbuild +++ b/arch/sh/Kbuild @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += kernel/ mm/ boards/ obj-$(CONFIG_SH_FPU_EMU) += math-emu/ -obj-$(CONFIG_USE_BUILTIN_DTB) += boot/dts/ obj-$(CONFIG_HD6446X_SERIES) += cchips/hd6446x/ diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 04ff5fb9242e..89185af7bcc9 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -648,10 +648,11 @@ endmenu menu "Boot options" -config USE_BUILTIN_DTB +config BUILTIN_DTB bool "Use builtin DTB" default n depends on SH_DEVICE_TREE + select GENERIC_BUILTIN_DTB help Link a device tree blob for particular hardware into the kernel, suppressing use of the DTB pointer provided by the bootloader. @@ -659,10 +660,10 @@ config USE_BUILTIN_DTB not capable of providing a DTB to the kernel, or for experimental hardware without stable device tree bindings. -config BUILTIN_DTB_SOURCE +config BUILTIN_DTB_NAME string "Source file for builtin DTB" default "" - depends on USE_BUILTIN_DTB + depends on BUILTIN_DTB help Base name (without suffix, relative to arch/sh/boot/dts) for the a DTS file that will be used to produce the DTB linked into the diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig index 109bec4dad94..1af93be61b1f 100644 --- a/arch/sh/boards/Kconfig +++ b/arch/sh/boards/Kconfig @@ -80,8 +80,8 @@ config SH_7724_SOLUTION_ENGINE select SOLUTION_ENGINE depends on CPU_SUBTYPE_SH7724 select GPIOLIB - select SND_SOC_AK4642 if SND_SIMPLE_CARD select REGULATOR_FIXED_VOLTAGE if REGULATOR + imply SND_SOC_AK4642 if SND_SIMPLE_CARD help Select 7724 SolutionEngine if configuring for a Hitachi SH7724 evaluation board. @@ -259,8 +259,8 @@ config SH_ECOVEC bool "EcoVec" depends on CPU_SUBTYPE_SH7724 select GPIOLIB - select SND_SOC_DA7210 if SND_SIMPLE_CARD select REGULATOR_FIXED_VOLTAGE if REGULATOR + imply SND_SOC_DA7210 if SND_SIMPLE_CARD help Renesas "R0P7724LC0011/21RL (EcoVec)" support. diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile index 4a6dec9714a9..d109978a5eb9 100644 --- a/arch/sh/boot/dts/Makefile +++ b/arch/sh/boot/dts/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_USE_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_SOURCE)) +obj-$(CONFIG_BUILTIN_DTB) += $(addsuffix .dtb.o, $(CONFIG_BUILTIN_DTB_NAME)) diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c index 4e6835de54cf..9022d8af9d68 100644 --- a/arch/sh/kernel/irq.c +++ b/arch/sh/kernel/irq.c @@ -43,9 +43,9 @@ int arch_show_interrupts(struct seq_file *p, int prec) { int j; - seq_printf(p, "%*s: ", prec, "NMI"); + seq_printf(p, "%*s:", prec, "NMI"); for_each_online_cpu(j) - seq_printf(p, "%10u ", per_cpu(irq_stat.__nmi_count, j)); + seq_put_decimal_ull_width(p, " ", per_cpu(irq_stat.__nmi_count, j), 10); seq_printf(p, " Non-maskable interrupts\n"); seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count)); diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index f2b6f16a46b8..039a51291002 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -249,7 +249,7 @@ void __ref sh_fdt_init(phys_addr_t dt_phys) /* Avoid calling an __init function on secondary cpus. */ if (done) return; -#ifdef CONFIG_USE_BUILTIN_DTB +#ifdef CONFIG_BUILTIN_DTB dt_virt = __dtb_start; #else dt_virt = phys_to_virt(dt_phys); @@ -323,7 +323,7 @@ void __init setup_arch(char **cmdline_p) sh_early_platform_driver_probe("earlyprintk", 1, 1); #ifdef CONFIG_OF_EARLY_FLATTREE -#ifdef CONFIG_USE_BUILTIN_DTB +#ifdef CONFIG_BUILTIN_DTB unflatten_and_copy_device_tree(); #else unflatten_device_tree(); diff --git a/arch/um/drivers/rtc_kern.c b/arch/um/drivers/rtc_kern.c index 134a58f93c85..9158c936c128 100644 --- a/arch/um/drivers/rtc_kern.c +++ b/arch/um/drivers/rtc_kern.c @@ -51,6 +51,7 @@ static int uml_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alrm) static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) { + struct timespec64 ts; unsigned long long secs; if (!enable && !uml_rtc_alarm_enabled) @@ -58,7 +59,8 @@ static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) uml_rtc_alarm_enabled = enable; - secs = uml_rtc_alarm_time - ktime_get_real_seconds(); + read_persistent_clock64(&ts); + secs = uml_rtc_alarm_time - ts.tv_sec; if (time_travel_mode == TT_MODE_OFF) { if (!enable) { @@ -73,7 +75,8 @@ static int uml_rtc_alarm_irq_enable(struct device *dev, unsigned int enable) if (enable) time_travel_add_event_rel(¨_rtc_alarm_event, - secs * NSEC_PER_SEC); + secs * NSEC_PER_SEC - + ts.tv_nsec); } return 0; diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index 744e7f31e8ef..dd5580f975cc 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -25,8 +25,10 @@ #define MAX_IRQ_MSG_SIZE (sizeof(struct virtio_pcidev_msg) + sizeof(u32)) #define NUM_IRQ_MSGS 10 -#define HANDLE_NO_FREE(ptr) ((void *)((unsigned long)(ptr) | 1)) -#define HANDLE_IS_NO_FREE(ptr) ((unsigned long)(ptr) & 1) +struct um_pci_message_buffer { + struct virtio_pcidev_msg hdr; + u8 data[8]; +}; struct um_pci_device { struct virtio_device *vdev; @@ -36,6 +38,11 @@ struct um_pci_device { struct virtqueue *cmd_vq, *irq_vq; +#define UM_PCI_WRITE_BUFS 20 + struct um_pci_message_buffer bufs[UM_PCI_WRITE_BUFS + 1]; + void *extra_ptrs[UM_PCI_WRITE_BUFS + 1]; + DECLARE_BITMAP(used_bufs, UM_PCI_WRITE_BUFS); + #define UM_PCI_STAT_WAITING 0 unsigned long status; @@ -61,12 +68,40 @@ static unsigned long um_pci_msi_used[BITS_TO_LONGS(MAX_MSI_VECTORS)]; static unsigned int um_pci_max_delay_us = 40000; module_param_named(max_delay_us, um_pci_max_delay_us, uint, 0644); -struct um_pci_message_buffer { - struct virtio_pcidev_msg hdr; - u8 data[8]; -}; +static int um_pci_get_buf(struct um_pci_device *dev, bool *posted) +{ + int i; + + for (i = 0; i < UM_PCI_WRITE_BUFS; i++) { + if (!test_and_set_bit(i, dev->used_bufs)) + return i; + } -static struct um_pci_message_buffer __percpu *um_pci_msg_bufs; + *posted = false; + return UM_PCI_WRITE_BUFS; +} + +static void um_pci_free_buf(struct um_pci_device *dev, void *buf) +{ + int i; + + if (buf == &dev->bufs[UM_PCI_WRITE_BUFS]) { + kfree(dev->extra_ptrs[UM_PCI_WRITE_BUFS]); + dev->extra_ptrs[UM_PCI_WRITE_BUFS] = NULL; + return; + } + + for (i = 0; i < UM_PCI_WRITE_BUFS; i++) { + if (buf == &dev->bufs[i]) { + kfree(dev->extra_ptrs[i]); + dev->extra_ptrs[i] = NULL; + WARN_ON(!test_and_clear_bit(i, dev->used_bufs)); + return; + } + } + + WARN_ON(1); +} static int um_pci_send_cmd(struct um_pci_device *dev, struct virtio_pcidev_msg *cmd, @@ -82,7 +117,9 @@ static int um_pci_send_cmd(struct um_pci_device *dev, }; struct um_pci_message_buffer *buf; int delay_count = 0; + bool bounce_out; int ret, len; + int buf_idx; bool posted; if (WARN_ON(cmd_size < sizeof(*cmd) || cmd_size > sizeof(*buf))) @@ -101,26 +138,28 @@ static int um_pci_send_cmd(struct um_pci_device *dev, break; } - buf = get_cpu_var(um_pci_msg_bufs); - if (buf) - memcpy(buf, cmd, cmd_size); + bounce_out = !posted && cmd_size <= sizeof(*cmd) && + out && out_size <= sizeof(buf->data); - if (posted) { - u8 *ncmd = kmalloc(cmd_size + extra_size, GFP_ATOMIC); - - if (ncmd) { - memcpy(ncmd, cmd, cmd_size); - if (extra) - memcpy(ncmd + cmd_size, extra, extra_size); - cmd = (void *)ncmd; - cmd_size += extra_size; - extra = NULL; - extra_size = 0; - } else { - /* try without allocating memory */ - posted = false; - cmd = (void *)buf; + buf_idx = um_pci_get_buf(dev, &posted); + buf = &dev->bufs[buf_idx]; + memcpy(buf, cmd, cmd_size); + + if (posted && extra && extra_size > sizeof(buf) - cmd_size) { + dev->extra_ptrs[buf_idx] = kmemdup(extra, extra_size, + GFP_ATOMIC); + + if (!dev->extra_ptrs[buf_idx]) { + um_pci_free_buf(dev, buf); + return -ENOMEM; } + extra = dev->extra_ptrs[buf_idx]; + } else if (extra && extra_size <= sizeof(buf) - cmd_size) { + memcpy((u8 *)buf + cmd_size, extra, extra_size); + cmd_size += extra_size; + extra_size = 0; + extra = NULL; + cmd = (void *)buf; } else { cmd = (void *)buf; } @@ -128,39 +167,40 @@ static int um_pci_send_cmd(struct um_pci_device *dev, sg_init_one(&out_sg, cmd, cmd_size); if (extra) sg_init_one(&extra_sg, extra, extra_size); - if (out) + /* allow stack for small buffers */ + if (bounce_out) + sg_init_one(&in_sg, buf->data, out_size); + else if (out) sg_init_one(&in_sg, out, out_size); /* add to internal virtio queue */ ret = virtqueue_add_sgs(dev->cmd_vq, sgs_list, extra ? 2 : 1, out ? 1 : 0, - posted ? cmd : HANDLE_NO_FREE(cmd), - GFP_ATOMIC); + cmd, GFP_ATOMIC); if (ret) { - if (posted) - kfree(cmd); - goto out; + um_pci_free_buf(dev, buf); + return ret; } if (posted) { virtqueue_kick(dev->cmd_vq); - ret = 0; - goto out; + return 0; } /* kick and poll for getting a response on the queue */ set_bit(UM_PCI_STAT_WAITING, &dev->status); virtqueue_kick(dev->cmd_vq); + ret = 0; while (1) { void *completed = virtqueue_get_buf(dev->cmd_vq, &len); - if (completed == HANDLE_NO_FREE(cmd)) + if (completed == buf) break; - if (completed && !HANDLE_IS_NO_FREE(completed)) - kfree(completed); + if (completed) + um_pci_free_buf(dev, completed); if (WARN_ONCE(virtqueue_is_broken(dev->cmd_vq) || ++delay_count > um_pci_max_delay_us, @@ -172,8 +212,11 @@ static int um_pci_send_cmd(struct um_pci_device *dev, } clear_bit(UM_PCI_STAT_WAITING, &dev->status); -out: - put_cpu_var(um_pci_msg_bufs); + if (bounce_out) + memcpy(out, buf->data, out_size); + + um_pci_free_buf(dev, buf); + return ret; } @@ -187,20 +230,13 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset, .size = size, .addr = offset, }; - /* buf->data is maximum size - we may only use parts of it */ - struct um_pci_message_buffer *buf; - u8 *data; - unsigned long ret = ULONG_MAX; - size_t bytes = sizeof(buf->data); + /* max 8, we might not use it all */ + u8 data[8]; if (!dev) return ULONG_MAX; - buf = get_cpu_var(um_pci_msg_bufs); - data = buf->data; - - if (buf) - memset(data, 0xff, bytes); + memset(data, 0xff, sizeof(data)); switch (size) { case 1: @@ -212,34 +248,26 @@ static unsigned long um_pci_cfgspace_read(void *priv, unsigned int offset, break; default: WARN(1, "invalid config space read size %d\n", size); - goto out; + return ULONG_MAX; } - if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, bytes)) - goto out; + if (um_pci_send_cmd(dev, &hdr, sizeof(hdr), NULL, 0, data, size)) + return ULONG_MAX; switch (size) { case 1: - ret = data[0]; - break; + return data[0]; case 2: - ret = le16_to_cpup((void *)data); - break; + return le16_to_cpup((void *)data); case 4: - ret = le32_to_cpup((void *)data); - break; + return le32_to_cpup((void *)data); #ifdef CONFIG_64BIT case 8: - ret = le64_to_cpup((void *)data); - break; + return le64_to_cpup((void *)data); #endif default: - break; + return ULONG_MAX; } - -out: - put_cpu_var(um_pci_msg_bufs); - return ret; } static void um_pci_cfgspace_write(void *priv, unsigned int offset, int size, @@ -312,13 +340,8 @@ static void um_pci_bar_copy_from(void *priv, void *buffer, static unsigned long um_pci_bar_read(void *priv, unsigned int offset, int size) { - /* buf->data is maximum size - we may only use parts of it */ - struct um_pci_message_buffer *buf; - u8 *data; - unsigned long ret = ULONG_MAX; - - buf = get_cpu_var(um_pci_msg_bufs); - data = buf->data; + /* 8 is maximum size - we may only use parts of it */ + u8 data[8]; switch (size) { case 1: @@ -330,33 +353,25 @@ static unsigned long um_pci_bar_read(void *priv, unsigned int offset, break; default: WARN(1, "invalid config space read size %d\n", size); - goto out; + return ULONG_MAX; } um_pci_bar_copy_from(priv, data, offset, size); switch (size) { case 1: - ret = data[0]; - break; + return data[0]; case 2: - ret = le16_to_cpup((void *)data); - break; + return le16_to_cpup((void *)data); case 4: - ret = le32_to_cpup((void *)data); - break; + return le32_to_cpup((void *)data); #ifdef CONFIG_64BIT case 8: - ret = le64_to_cpup((void *)data); - break; + return le64_to_cpup((void *)data); #endif default: - break; + return ULONG_MAX; } - -out: - put_cpu_var(um_pci_msg_bufs); - return ret; } static void um_pci_bar_copy_to(void *priv, unsigned int offset, @@ -523,11 +538,8 @@ static void um_pci_cmd_vq_cb(struct virtqueue *vq) if (test_bit(UM_PCI_STAT_WAITING, &dev->status)) return; - while ((cmd = virtqueue_get_buf(vq, &len))) { - if (WARN_ON(HANDLE_IS_NO_FREE(cmd))) - continue; - kfree(cmd); - } + while ((cmd = virtqueue_get_buf(vq, &len))) + um_pci_free_buf(dev, cmd); } static void um_pci_irq_vq_cb(struct virtqueue *vq) @@ -1006,10 +1018,6 @@ static int __init um_pci_init(void) "No virtio device ID configured for PCI - no PCI support\n")) return 0; - um_pci_msg_bufs = alloc_percpu(struct um_pci_message_buffer); - if (!um_pci_msg_bufs) - return -ENOMEM; - bridge = pci_alloc_host_bridge(0); if (!bridge) { err = -ENOMEM; @@ -1070,7 +1078,6 @@ free: pci_free_resource_list(&bridge->windows); pci_free_host_bridge(bridge); } - free_percpu(um_pci_msg_bufs); return err; } module_init(um_pci_init); @@ -1082,6 +1089,5 @@ static void __exit um_pci_exit(void) irq_domain_remove(um_pci_inner_domain); pci_free_resource_list(&bridge->windows); pci_free_host_bridge(bridge); - free_percpu(um_pci_msg_bufs); } module_exit(um_pci_exit); diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 65df43fa9be5..ad8d78fb1d9a 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -52,7 +52,7 @@ struct virtio_uml_device { struct platform_device *pdev; struct virtio_uml_platform_data *pdata; - spinlock_t sock_lock; + raw_spinlock_t sock_lock; int sock, req_fd, irq; u64 features; u64 protocol_features; @@ -246,7 +246,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev, if (request_ack) msg->header.flags |= VHOST_USER_FLAG_NEED_REPLY; - spin_lock_irqsave(&vu_dev->sock_lock, flags); + raw_spin_lock_irqsave(&vu_dev->sock_lock, flags); rc = full_sendmsg_fds(vu_dev->sock, msg, size, fds, num_fds); if (rc < 0) goto out; @@ -266,7 +266,7 @@ static int vhost_user_send(struct virtio_uml_device *vu_dev, } out: - spin_unlock_irqrestore(&vu_dev->sock_lock, flags); + raw_spin_unlock_irqrestore(&vu_dev->sock_lock, flags); return rc; } @@ -1239,7 +1239,7 @@ static int virtio_uml_probe(struct platform_device *pdev) goto error_free; vu_dev->sock = rc; - spin_lock_init(&vu_dev->sock_lock); + raw_spin_lock_init(&vu_dev->sock_lock); rc = vhost_user_init(vu_dev); if (rc) diff --git a/arch/um/include/asm/fixmap.h b/arch/um/include/asm/fixmap.h deleted file mode 100644 index 2efac5827188..000000000000 --- a/arch/um/include/asm/fixmap.h +++ /dev/null @@ -1,56 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __UM_FIXMAP_H -#define __UM_FIXMAP_H - -#include <asm/processor.h> -#include <asm/archparam.h> -#include <asm/page.h> -#include <linux/threads.h> - -/* - * Here we define all the compile-time 'special' virtual - * addresses. The point is to have a constant address at - * compile time, but to set the physical address only - * in the boot process. We allocate these special addresses - * from the end of virtual memory (0xfffff000) backwards. - * Also this lets us do fail-safe vmalloc(), we - * can guarantee that these special addresses and - * vmalloc()-ed addresses never overlap. - * - * these 'compile-time allocated' memory buffers are - * fixed-size 4k pages. (or larger if used with an increment - * highger than 1) use fixmap_set(idx,phys) to associate - * physical memory with fixmap indices. - * - * TLB entries of such buffers will not be flushed across - * task switches. - */ - -/* - * on UP currently we will have no trace of the fixmap mechanizm, - * no page table allocations, etc. This might change in the - * future, say framebuffers for the console driver(s) could be - * fix-mapped? - */ -enum fixed_addresses { - __end_of_fixed_addresses -}; - -extern void __set_fixmap (enum fixed_addresses idx, - unsigned long phys, pgprot_t flags); - -/* - * used by vmalloc.c. - * - * Leave one empty page between vmalloc'ed areas and - * the start of the fixmap, and leave one page empty - * at the top of mem.. - */ - -#define FIXADDR_TOP (TASK_SIZE - 2 * PAGE_SIZE) -#define FIXADDR_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) -#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) - -#include <asm-generic/fixmap.h> - -#endif diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 0bd60afcc37d..5601ca98e8a6 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -8,7 +8,8 @@ #ifndef __UM_PGTABLE_H #define __UM_PGTABLE_H -#include <asm/fixmap.h> +#include <asm/page.h> +#include <linux/mm_types.h> #define _PAGE_PRESENT 0x001 #define _PAGE_NEEDSYNC 0x002 @@ -48,11 +49,9 @@ extern unsigned long end_iomem; #define VMALLOC_OFFSET (__va_space) #define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)) -#define PKMAP_BASE ((FIXADDR_START - LAST_PKMAP * PAGE_SIZE) & PMD_MASK) -#define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE) +#define VMALLOC_END (TASK_SIZE-2*PAGE_SIZE) #define MODULES_VADDR VMALLOC_START #define MODULES_END VMALLOC_END -#define MODULES_LEN (MODULES_VADDR - MODULES_END) #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index 338450741aac..a4991746f5ea 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -52,7 +52,7 @@ struct irq_entry { bool sigio_workaround; }; -static DEFINE_SPINLOCK(irq_lock); +static DEFINE_RAW_SPINLOCK(irq_lock); static LIST_HEAD(active_fds); static DECLARE_BITMAP(irqs_allocated, UM_LAST_SIGNAL_IRQ); static bool irqs_suspended; @@ -257,7 +257,7 @@ static struct irq_entry *get_irq_entry_by_fd(int fd) return NULL; } -static void free_irq_entry(struct irq_entry *to_free, bool remove) +static void remove_irq_entry(struct irq_entry *to_free, bool remove) { if (!to_free) return; @@ -265,7 +265,6 @@ static void free_irq_entry(struct irq_entry *to_free, bool remove) if (remove) os_del_epoll_fd(to_free->fd); list_del(&to_free->list); - kfree(to_free); } static bool update_irq_entry(struct irq_entry *entry) @@ -286,17 +285,19 @@ static bool update_irq_entry(struct irq_entry *entry) return false; } -static void update_or_free_irq_entry(struct irq_entry *entry) +static struct irq_entry *update_or_remove_irq_entry(struct irq_entry *entry) { - if (!update_irq_entry(entry)) - free_irq_entry(entry, false); + if (update_irq_entry(entry)) + return NULL; + remove_irq_entry(entry, false); + return entry; } static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, void (*timetravel_handler)(int, int, void *, struct time_travel_event *)) { - struct irq_entry *irq_entry; + struct irq_entry *irq_entry, *to_free = NULL; int err, events = os_event_mask(type); unsigned long flags; @@ -304,9 +305,10 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, if (err < 0) goto out; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); irq_entry = get_irq_entry_by_fd(fd); if (irq_entry) { +already: /* cannot register the same FD twice with the same type */ if (WARN_ON(irq_entry->reg[type].events)) { err = -EALREADY; @@ -316,11 +318,22 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, /* temporarily disable to avoid IRQ-side locking */ os_del_epoll_fd(fd); } else { - irq_entry = kzalloc(sizeof(*irq_entry), GFP_ATOMIC); - if (!irq_entry) { - err = -ENOMEM; - goto out_unlock; + struct irq_entry *new; + + /* don't restore interrupts */ + raw_spin_unlock(&irq_lock); + new = kzalloc(sizeof(*irq_entry), GFP_ATOMIC); + if (!new) { + local_irq_restore(flags); + return -ENOMEM; } + raw_spin_lock(&irq_lock); + irq_entry = get_irq_entry_by_fd(fd); + if (irq_entry) { + to_free = new; + goto already; + } + irq_entry = new; irq_entry->fd = fd; list_add_tail(&irq_entry->list, &active_fds); maybe_sigio_broken(fd); @@ -339,12 +352,11 @@ static int activate_fd(int irq, int fd, enum um_irq_type type, void *dev_id, #endif WARN_ON(!update_irq_entry(irq_entry)); - spin_unlock_irqrestore(&irq_lock, flags); - - return 0; + err = 0; out_unlock: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); out: + kfree(to_free); return err; } @@ -358,19 +370,20 @@ void free_irq_by_fd(int fd) struct irq_entry *to_free; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); to_free = get_irq_entry_by_fd(fd); - free_irq_entry(to_free, true); - spin_unlock_irqrestore(&irq_lock, flags); + remove_irq_entry(to_free, true); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(to_free); } EXPORT_SYMBOL(free_irq_by_fd); static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) { - struct irq_entry *entry; + struct irq_entry *entry, *to_free = NULL; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type i; @@ -386,12 +399,13 @@ static void free_irq_by_irq_and_dev(unsigned int irq, void *dev) os_del_epoll_fd(entry->fd); reg->events = 0; - update_or_free_irq_entry(entry); + to_free = update_or_remove_irq_entry(entry); goto out; } } out: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(to_free); } void deactivate_fd(int fd, int irqnum) @@ -402,7 +416,7 @@ void deactivate_fd(int fd, int irqnum) os_del_epoll_fd(fd); - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); entry = get_irq_entry_by_fd(fd); if (!entry) goto out; @@ -414,9 +428,10 @@ void deactivate_fd(int fd, int irqnum) entry->reg[i].events = 0; } - update_or_free_irq_entry(entry); + entry = update_or_remove_irq_entry(entry); out: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); + kfree(entry); ignore_sigio_fd(fd); } @@ -546,7 +561,7 @@ void um_irqs_suspend(void) irqs_suspended = true; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type t; bool clear = true; @@ -579,7 +594,7 @@ void um_irqs_suspend(void) !__ignore_sigio_fd(entry->fd); } } - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); } void um_irqs_resume(void) @@ -588,7 +603,7 @@ void um_irqs_resume(void) unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { if (entry->suspended) { int err = os_set_fd_async(entry->fd); @@ -602,7 +617,7 @@ void um_irqs_resume(void) } } } - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); irqs_suspended = false; send_sigio_to_self(); @@ -613,7 +628,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on) struct irq_entry *entry; unsigned long flags; - spin_lock_irqsave(&irq_lock, flags); + raw_spin_lock_irqsave(&irq_lock, flags); list_for_each_entry(entry, &active_fds, list) { enum um_irq_type t; @@ -628,7 +643,7 @@ static int normal_irq_set_wake(struct irq_data *d, unsigned int on) } } unlock: - spin_unlock_irqrestore(&irq_lock, flags); + raw_spin_unlock_irqrestore(&irq_lock, flags); return 0; } #else diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index d98812907493..befed230aac2 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -9,7 +9,6 @@ #include <linux/mm.h> #include <linux/swap.h> #include <linux/slab.h> -#include <asm/fixmap.h> #include <asm/page.h> #include <asm/pgalloc.h> #include <as-layout.h> @@ -74,6 +73,7 @@ void __init mem_init(void) kmalloc_ok = 1; } +#if IS_ENABLED(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) /* * Create a page table and place a pointer to it in a middle page * directory entry. @@ -152,7 +152,6 @@ static void __init fixrange_init(unsigned long start, unsigned long end, static void __init fixaddr_user_init( void) { -#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA long size = FIXADDR_USER_END - FIXADDR_USER_START; pte_t *pte; phys_t p; @@ -174,13 +173,12 @@ static void __init fixaddr_user_init( void) pte = virt_to_kpte(vaddr); pte_set_val(*pte, p, PAGE_READONLY); } -#endif } +#endif void __init paging_init(void) { unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 }; - unsigned long vaddr; empty_zero_page = (unsigned long *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); @@ -191,14 +189,9 @@ void __init paging_init(void) max_zone_pfn[ZONE_NORMAL] = end_iomem >> PAGE_SHIFT; free_area_init(max_zone_pfn); - /* - * Fixed mappings, only the page table structure has to be - * created - mappings will be set by set_fixmap(): - */ - vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK; - fixrange_init(vaddr, FIXADDR_TOP, swapper_pg_dir); - +#if IS_ENABLED(CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA) fixaddr_user_init(); +#endif } /* diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 30bdc0a87dc8..0cd6fad3d908 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -191,7 +191,15 @@ void initial_thread_cb(void (*proc)(void *), void *arg) int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { - memcpy(dst, src, arch_task_struct_size); + /* init_task is not dynamically sized (missing FPU state) */ + if (unlikely(src == &init_task)) { + memcpy(dst, src, sizeof(init_task)); + memset((void *)dst + sizeof(init_task), 0, + arch_task_struct_size - sizeof(init_task)); + } else { + memcpy(dst, src, arch_task_struct_size); + } + return 0; } @@ -213,14 +221,6 @@ int __uml_cant_sleep(void) { /* Is in_interrupt() really needed? */ } -int user_context(unsigned long sp) -{ - unsigned long stack; - - stack = sp & (PAGE_MASK << CONFIG_KERNEL_STACK_ORDER); - return stack != (unsigned long) current_thread_info(); -} - extern exitcall_t __uml_exitcall_begin, __uml_exitcall_end; void do_uml_exitcalls(void) diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 8037a967225d..79ea97d4797e 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -264,7 +264,7 @@ EXPORT_SYMBOL(end_iomem); #define MIN_VMALLOC (32 * 1024 * 1024) -static void parse_host_cpu_flags(char *line) +static void __init parse_host_cpu_flags(char *line) { int i; for (i = 0; i < 32*NCAPINTS; i++) { @@ -272,7 +272,8 @@ static void parse_host_cpu_flags(char *line) set_cpu_cap(&boot_cpu_data, i); } } -static void parse_cache_line(char *line) + +static void __init parse_cache_line(char *line) { long res; char *to_parse = strstr(line, ":"); @@ -288,7 +289,7 @@ static void parse_cache_line(char *line) } } -static unsigned long get_top_address(char **envp) +static unsigned long __init get_top_address(char **envp) { unsigned long top_addr = (unsigned long) &top_addr; int i; @@ -376,9 +377,8 @@ int __init linux_main(int argc, char **argv, char **envp) iomem_size = (iomem_size + PAGE_SIZE - 1) & PAGE_MASK; max_physmem = TASK_SIZE - uml_physmem - iomem_size - MIN_VMALLOC; - - if (physmem_size + iomem_size > max_physmem) { - physmem_size = max_physmem - iomem_size; + if (physmem_size > max_physmem) { + physmem_size = max_physmem; os_info("Physical memory size shrunk to %llu bytes\n", physmem_size); } diff --git a/arch/um/os-Linux/main.c b/arch/um/os-Linux/main.c index 0afcdeb8995b..3c63ce19e3bf 100644 --- a/arch/um/os-Linux/main.c +++ b/arch/um/os-Linux/main.c @@ -19,13 +19,11 @@ #include <um_malloc.h> #include "internal.h" -#define PGD_BOUND (4 * 1024 * 1024) #define STACKSIZE (8 * 1024 * 1024) -#define THREAD_NAME_LEN (256) long elf_aux_hwcap; -static void set_stklim(void) +static void __init set_stklim(void) { struct rlimit lim; @@ -48,7 +46,7 @@ static void last_ditch_exit(int sig) exit(1); } -static void install_fatal_handler(int sig) +static void __init install_fatal_handler(int sig) { struct sigaction action; @@ -73,7 +71,7 @@ static void install_fatal_handler(int sig) #define UML_LIB_PATH ":" OS_LIB_PATH "/uml" -static void setup_env_path(void) +static void __init setup_env_path(void) { char *new_path = NULL; char *old_path = NULL; diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index f683cfc9e51a..e2f8f156402f 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -181,6 +181,10 @@ extern char __syscall_stub_start[]; static int stub_exe_fd; +#ifndef CLOSE_RANGE_CLOEXEC +#define CLOSE_RANGE_CLOEXEC (1U << 2) +#endif + static int userspace_tramp(void *stack) { char *const argv[] = { "uml-userspace", NULL }; @@ -202,8 +206,12 @@ static int userspace_tramp(void *stack) init_data.stub_data_fd = phys_mapping(uml_to_phys(stack), &offset); init_data.stub_data_offset = MMAP_OFFSET(offset); - /* Set CLOEXEC on all FDs and then unset on all memory related FDs */ - close_range(0, ~0U, CLOSE_RANGE_CLOEXEC); + /* + * Avoid leaking unneeded FDs to the stub by setting CLOEXEC on all FDs + * and then unsetting it on all memory related FDs. + * This is not strictly necessary from a safety perspective. + */ + syscall(__NR_close_range, 0, ~0U, CLOSE_RANGE_CLOEXEC); fcntl(init_data.stub_data_fd, F_SETFD, 0); for (iomem = iomem_regions; iomem; iomem = iomem->next) @@ -224,7 +232,9 @@ static int userspace_tramp(void *stack) if (ret != sizeof(init_data)) exit(4); - execveat(stub_exe_fd, "", argv, NULL, AT_EMPTY_PATH); + /* Raw execveat for compatibility with older libc versions */ + syscall(__NR_execveat, stub_exe_fd, (unsigned long)"", + (unsigned long)argv, NULL, AT_EMPTY_PATH); exit(5); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 87198d957e2f..be2c311f5118 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2599,7 +2599,8 @@ config MITIGATION_IBPB_ENTRY depends on CPU_SUP_AMD && X86_64 default y help - Compile the kernel with support for the retbleed=ibpb mitigation. + Compile the kernel with support for the retbleed=ibpb and + spec_rstack_overflow={ibpb,ibpb-vmexit} mitigations. config MITIGATION_IBRS_ENTRY bool "Enable IBRS on kernel entry" diff --git a/arch/x86/Makefile.postlink b/arch/x86/Makefile.postlink index fef2e977cc7d..8b8a68162c94 100644 --- a/arch/x86/Makefile.postlink +++ b/arch/x86/Makefile.postlink @@ -11,6 +11,7 @@ __archpost: -include include/config/auto.conf include $(srctree)/scripts/Kbuild.include +include $(srctree)/scripts/Makefile.lib CMD_RELOCS = arch/x86/tools/relocs OUT_RELOCS = arch/x86/boot/compressed @@ -20,11 +21,6 @@ quiet_cmd_relocs = RELOCS $(OUT_RELOCS)/$@.relocs $(CMD_RELOCS) $@ > $(OUT_RELOCS)/$@.relocs; \ $(CMD_RELOCS) --abs-relocs $@ -quiet_cmd_strip_relocs = RSTRIP $@ - cmd_strip_relocs = \ - $(OBJCOPY) --remove-section='.rel.*' --remove-section='.rel__*' \ - --remove-section='.rela.*' --remove-section='.rela__*' $@ - # `@true` prevents complaint when there is nothing to be done vmlinux: FORCE diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index f2051644de94..606c74f27459 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -25,6 +25,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \ # avoid errors with '-march=i386', and future flags may depend on the target to # be valid. KBUILD_CFLAGS := -m$(BITS) -O2 $(CLANG_FLAGS) +KBUILD_CFLAGS += -std=gnu11 KBUILD_CFLAGS += -fno-strict-aliasing -fPIE KBUILD_CFLAGS += -Wundef KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index 76e4e74f35b5..f6d2d8aba643 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -57,7 +57,7 @@ __setup_param("vdso=", vdso_setup, vdso32_setup, 0); /* Register vsyscall32 into the ABI table */ #include <linux/sysctl.h> -static struct ctl_table abi_table2[] = { +static const struct ctl_table abi_table2[] = { { .procname = "vsyscall32", .data = &vdso32_enabled, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7601196d1d18..e86333eee266 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4905,20 +4905,22 @@ static inline bool intel_pmu_broken_perf_cap(void) static void update_pmu_cap(struct x86_hybrid_pmu *pmu) { - unsigned int sub_bitmaps, eax, ebx, ecx, edx; + unsigned int cntr, fixed_cntr, ecx, edx; + union cpuid35_eax eax; + union cpuid35_ebx ebx; - cpuid(ARCH_PERFMON_EXT_LEAF, &sub_bitmaps, &ebx, &ecx, &edx); + cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx); - if (ebx & ARCH_PERFMON_EXT_UMASK2) + if (ebx.split.umask2) pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2; - if (ebx & ARCH_PERFMON_EXT_EQ) + if (ebx.split.eq) pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ; - if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) { + if (eax.split.cntr_subleaf) { cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF, - &eax, &ebx, &ecx, &edx); - pmu->cntr_mask64 = eax; - pmu->fixed_cntr_mask64 = ebx; + &cntr, &fixed_cntr, &ecx, &edx); + pmu->cntr_mask64 = cntr; + pmu->fixed_cntr_mask64 = fixed_cntr; } if (!intel_pmu_broken_perf_cap()) { @@ -4941,11 +4943,6 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu) else pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS); - if (pmu->intel_cap.pebs_output_pt_available) - pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT; - else - pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT; - intel_pmu_check_event_constraints(pmu->event_constraints, pmu->cntr_mask64, pmu->fixed_cntr_mask64, @@ -5023,9 +5020,6 @@ static bool init_hybrid_pmu(int cpu) pr_info("%s PMU driver: ", pmu->name); - if (pmu->intel_cap.pebs_output_pt_available) - pr_cont("PEBS-via-PT "); - pr_cont("\n"); x86_pmu_show_pmu_cap(&pmu->pmu); @@ -5048,8 +5042,11 @@ static void intel_pmu_cpu_starting(int cpu) init_debug_store_on_cpu(cpu); /* - * Deal with CPUs that don't clear their LBRs on power-up. + * Deal with CPUs that don't clear their LBRs on power-up, and that may + * even boot with LBRs enabled. */ + if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && x86_pmu.lbr_nr) + msr_clear_bit(MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_LBR_BIT); intel_pmu_lbr_reset(); cpuc->lbr_sel = NULL; @@ -6370,11 +6367,9 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus) pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities; if (pmu->pmu_type & hybrid_small_tiny) { pmu->intel_cap.perf_metrics = 0; - pmu->intel_cap.pebs_output_pt_available = 1; pmu->mid_ack = true; } else if (pmu->pmu_type & hybrid_big) { pmu->intel_cap.perf_metrics = 1; - pmu->intel_cap.pebs_output_pt_available = 0; pmu->late_ack = true; } } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index ba74e1198328..c2e2eae7309c 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2578,7 +2578,15 @@ void __init intel_ds_init(void) } pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); - if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) { + /* + * The PEBS-via-PT is not supported on hybrid platforms, + * because not all CPUs of a hybrid machine support it. + * The global x86_pmu.intel_cap, which only contains the + * common capabilities, is used to check the availability + * of the feature. The per-PMU pebs_output_pt_available + * in a hybrid machine should be ignored. + */ + if (x86_pmu.intel_cap.pebs_output_pt_available) { pr_cont("PEBS-via-PT, "); x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_AUX_OUTPUT; } diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index d3bb3865c1b1..4952faf03e82 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -370,6 +370,10 @@ static int rapl_pmu_event_init(struct perf_event *event) unsigned int rapl_pmu_idx; struct rapl_pmus *rapl_pmus; + /* only look at RAPL events */ + if (event->attr.type != event->pmu->type) + return -ENOENT; + /* unsupported modes and filters */ if (event->attr.sample_period) /* no sampling */ return -EINVAL; @@ -387,10 +391,6 @@ static int rapl_pmu_event_init(struct perf_event *event) rapl_pmus_scope = rapl_pmus->pmu.scope; if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) { - /* only look at RAPL package events */ - if (event->attr.type != rapl_pmus_pkg->pmu.type) - return -ENOENT; - cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; @@ -398,10 +398,6 @@ static int rapl_pmu_event_init(struct perf_event *event) bit = cfg - 1; event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr; } else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) { - /* only look at RAPL core events */ - if (event->attr.type != rapl_pmus_core->pmu.type) - return -ENOENT; - cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1); if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) return -EINVAL; diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h index ab9f3dd87c80..ab0c78855ecb 100644 --- a/arch/x86/include/asm/hpet.h +++ b/arch/x86/include/asm/hpet.h @@ -84,7 +84,6 @@ extern int hpet_set_rtc_irq_bit(unsigned long bit_mask); extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min, unsigned char sec); extern int hpet_set_periodic_freq(unsigned long freq); -extern int hpet_rtc_dropped_irq(void); extern int hpet_rtc_timer_init(void); extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id); extern int hpet_register_irq_handler(rtc_irq_handler handler); diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index c35550581da0..823c0434bbad 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -48,6 +48,7 @@ KVM_X86_OP(set_idt) KVM_X86_OP(get_gdt) KVM_X86_OP(set_gdt) KVM_X86_OP(sync_dirty_debug_regs) +KVM_X86_OP(set_dr6) KVM_X86_OP(set_dr7) KVM_X86_OP(cache_reg) KVM_X86_OP(get_rflags) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b15cde0a9b5c..0b7af5902ff7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1696,6 +1696,7 @@ struct kvm_x86_ops { void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); + void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index ce4677b8b735..3b496cdcb74b 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -37,6 +37,8 @@ typedef struct { */ atomic64_t tlb_gen; + unsigned long next_trim_cpumask; + #ifdef CONFIG_MODIFY_LDT_SYSCALL struct rw_semaphore ldt_usr_sem; struct ldt_struct *ldt; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 2886cb668d7f..795fdd53bd0a 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -151,6 +151,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); atomic64_set(&mm->context.tlb_gen, 0); + mm->context.next_trim_cpumask = jiffies + HZ; #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9a71880eec07..72765b2fe0d8 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -395,7 +395,8 @@ #define MSR_IA32_PASID_VALID BIT_ULL(31) /* DEBUGCTLMSR bits (others vary by model): */ -#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */ +#define DEBUGCTLMSR_LBR_BIT 0 /* last branch recording */ +#define DEBUGCTLMSR_LBR (1UL << DEBUGCTLMSR_LBR_BIT) #define DEBUGCTLMSR_BTF_SHIFT 1 #define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ #define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 1ac79f361645..0ba8d20f2d1d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -188,11 +188,33 @@ union cpuid10_edx { * detection/enumeration details: */ #define ARCH_PERFMON_EXT_LEAF 0x00000023 -#define ARCH_PERFMON_EXT_UMASK2 0x1 -#define ARCH_PERFMON_EXT_EQ 0x2 -#define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1 #define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 +union cpuid35_eax { + struct { + unsigned int leaf0:1; + /* Counters Sub-Leaf */ + unsigned int cntr_subleaf:1; + /* Auto Counter Reload Sub-Leaf */ + unsigned int acr_subleaf:1; + /* Events Sub-Leaf */ + unsigned int events_subleaf:1; + unsigned int reserved:28; + } split; + unsigned int full; +}; + +union cpuid35_ebx { + struct { + /* UnitMask2 Supported */ + unsigned int umask2:1; + /* EQ-bit Supported */ + unsigned int eq:1; + unsigned int reserved:30; + } split; + unsigned int full; +}; + /* * Intel Architectural LBR CPUID detection/enumeration details: */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 5d9685f92e5c..1581246491b5 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -531,6 +531,7 @@ static inline void __init snp_secure_tsc_init(void) { } #ifdef CONFIG_KVM_AMD_SEV bool snp_probe_rmptable_info(void); +int snp_rmptable_init(void); int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); void snp_dump_hva_rmpentry(unsigned long address); int psmash(u64 pfn); @@ -541,6 +542,7 @@ void kdump_sev_callback(void); void snp_fixup_e820_tables(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_rmptable_init(void) { return -ENOSYS; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } static inline void snp_dump_hva_rmpentry(unsigned long address) {} static inline int psmash(u64 pfn) { return -ENODEV; } diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 69e79fff41b8..02fc2aa06e9e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -222,6 +222,7 @@ struct flush_tlb_info { unsigned int initiating_cpu; u8 stride_shift; u8 freed_tables; + u8 trim_cpumask; }; void flush_tlb_local(void); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7c15d6e83c37..dae6a73be40e 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -227,6 +227,28 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) } static int __init +acpi_check_lapic(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_local_apic *processor = NULL; + + processor = (struct acpi_madt_local_apic *)header; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + /* Ignore invalid ID */ + if (processor->id == 0xff) + return 0; + + /* Ignore processors that can not be onlined */ + if (!acpi_is_processor_usable(processor->lapic_flags)) + return 0; + + has_lapic_cpus = true; + return 0; +} + +static int __init acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) { struct acpi_madt_local_apic *processor = NULL; @@ -257,7 +279,6 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) processor->processor_id, /* ACPI ID */ processor->lapic_flags & ACPI_MADT_ENABLED); - has_lapic_cpus = true; return 0; } @@ -1026,6 +1047,8 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) static int __init acpi_parse_madt_lapic_entries(void) { int count, x2count = 0; + struct acpi_subtable_proc madt_proc[2]; + int ret; if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; @@ -1034,10 +1057,27 @@ static int __init acpi_parse_madt_lapic_entries(void) acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { - count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, - acpi_parse_lapic, MAX_LOCAL_APIC); - x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, - acpi_parse_x2apic, MAX_LOCAL_APIC); + /* Check if there are valid LAPIC entries */ + acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_check_lapic, MAX_LOCAL_APIC); + + /* + * Enumerate the APIC IDs in the order that they appear in the + * MADT, no matter LAPIC entry or x2APIC entry is used. + */ + memset(madt_proc, 0, sizeof(madt_proc)); + madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC; + madt_proc[0].handler = acpi_parse_lapic; + madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC; + madt_proc[1].handler = acpi_parse_x2apic; + ret = acpi_table_parse_entries_array(ACPI_SIG_MADT, + sizeof(struct acpi_table_madt), + madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); + if (ret < 0) { + pr_err("Error parsing LAPIC/X2APIC entries\n"); + return ret; + } + count = madt_proc[0].count; + x2count = madt_proc[1].count; } if (!count && !x2count) { pr_err("No LAPIC entries present\n"); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 243843e44e89..c71b575bf229 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1854,11 +1854,18 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) return temp_state; } +__ro_after_init struct mm_struct *poking_mm; +__ro_after_init unsigned long poking_addr; + static inline void unuse_temporary_mm(temp_mm_state_t prev_state) { lockdep_assert_irqs_disabled(); + switch_mm_irqs_off(NULL, prev_state.mm, current); + /* Clear the cpumask, to indicate no TLB flushing is needed anywhere */ + cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(poking_mm)); + /* * Restore the breakpoints if they were disabled before the temporary mm * was loaded. @@ -1867,9 +1874,6 @@ static inline void unuse_temporary_mm(temp_mm_state_t prev_state) hw_breakpoint_restore(); } -__ro_after_init struct mm_struct *poking_mm; -__ro_after_init unsigned long poking_addr; - static void text_poke_memcpy(void *dst, const void *src, size_t len) { memcpy(dst, src, len); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 5a505aa65489..a5d0998d7604 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1115,6 +1115,8 @@ do_cmd_auto: case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); + mitigate_smt = true; /* * IBPB on entry already obviates the need for @@ -1124,9 +1126,6 @@ do_cmd_auto: setup_clear_cpu_cap(X86_FEATURE_UNRET); setup_clear_cpu_cap(X86_FEATURE_RETHUNK); - setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); - mitigate_smt = true; - /* * There is no need for RSB filling: entry_ibpb() ensures * all predictions, including the RSB, are invalidated, @@ -2646,6 +2645,7 @@ static void __init srso_select_mitigation(void) if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB; /* @@ -2655,6 +2655,13 @@ static void __init srso_select_mitigation(void) */ setup_clear_cpu_cap(X86_FEATURE_UNRET); setup_clear_cpu_cap(X86_FEATURE_RETHUNK); + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); @@ -2663,8 +2670,8 @@ static void __init srso_select_mitigation(void) ibpb_on_vmexit: case SRSO_CMD_IBPB_ON_VMEXIT: - if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { - if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { + if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { + if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; @@ -2676,8 +2683,8 @@ ibpb_on_vmexit: setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { - pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); - } + pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); + } break; default: break; diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c index 704e9241b964..6cba85c79d42 100644 --- a/arch/x86/kernel/cpu/bus_lock.c +++ b/arch/x86/kernel/cpu/bus_lock.c @@ -49,7 +49,7 @@ static unsigned int sysctl_sld_mitigate = 1; static DEFINE_SEMAPHORE(buslock_sem, 1); #ifdef CONFIG_PROC_SYSCTL -static struct ctl_table sld_sysctls[] = { +static const struct ctl_table sld_sysctls[] = { { .procname = "split_lock_mitigate", .data = &sysctl_sld_mitigate, diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 9182303a50b0..7f4b2966e15c 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1382,12 +1382,6 @@ int hpet_set_periodic_freq(unsigned long freq) } EXPORT_SYMBOL_GPL(hpet_set_periodic_freq); -int hpet_rtc_dropped_irq(void) -{ - return is_hpet_enabled(); -} -EXPORT_SYMBOL_GPL(hpet_rtc_dropped_irq); - static void hpet_rtc_timer_reinit(void) { unsigned int delta; diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2cbb3874ad39..8eb3a88707f2 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1180,7 +1180,7 @@ void kvm_set_cpu_caps(void) SYNTHESIZED_F(SBPB), SYNTHESIZED_F(IBPB_BRTYPE), SYNTHESIZED_F(SRSO_NO), - SYNTHESIZED_F(SRSO_USER_KERNEL_NO), + F(SRSO_USER_KERNEL_NO), ); kvm_cpu_cap_init(CPUID_8000_0022_EAX, diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 6a6dd5a84f22..6ebeb6cea6c0 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2226,6 +2226,9 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) u32 vector; bool all_cpus; + if (!lapic_in_kernel(vcpu)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (hc->code == HVCALL_SEND_IPI) { if (!hc->fast) { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi, @@ -2852,7 +2855,8 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED; ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED; - ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + if (!vcpu || lapic_in_kernel(vcpu)) + ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; if (evmcs_ver) ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a45ae60e84ab..d4ac4a1f8b81 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5540,7 +5540,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, union kvm_mmu_page_role root_role; /* NPT requires CR0.PG=1. */ - WARN_ON_ONCE(cpu_role.base.direct); + WARN_ON_ONCE(cpu_role.base.direct || !cpu_role.base.guest_mode); root_role = cpu_role.base; root_role.level = kvm_mmu_get_tdp_level(vcpu); @@ -7120,6 +7120,19 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static void kvm_wake_nx_recovery_thread(struct kvm *kvm) +{ + /* + * The NX recovery thread is spawned on-demand at the first KVM_RUN and + * may not be valid even though the VM is globally visible. Do nothing, + * as such a VM can't have any possible NX huge pages. + */ + struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread); + + if (nx_thread) + vhost_task_wake(nx_thread); +} + static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) { if (nx_hugepage_mitigation_hard_disabled) @@ -7180,7 +7193,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) kvm_mmu_zap_all_fast(kvm); mutex_unlock(&kvm->slots_lock); - vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); } mutex_unlock(&kvm_lock); } @@ -7315,7 +7328,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) - vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); mutex_unlock(&kvm_lock); } @@ -7451,14 +7464,20 @@ static void kvm_mmu_start_lpage_recovery(struct once *once) { struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once); struct kvm *kvm = container_of(ka, struct kvm, arch); + struct vhost_task *nx_thread; kvm->arch.nx_huge_page_last = get_jiffies_64(); - kvm->arch.nx_huge_page_recovery_thread = vhost_task_create( - kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill, - kvm, "kvm-nx-lpage-recovery"); + nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker, + kvm_nx_huge_page_recovery_worker_kill, + kvm, "kvm-nx-lpage-recovery"); - if (kvm->arch.nx_huge_page_recovery_thread) - vhost_task_start(kvm->arch.nx_huge_page_recovery_thread); + if (!nx_thread) + return; + + vhost_task_start(nx_thread); + + /* Make the task visible only once it is fully started. */ + WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread); } int kvm_mmu_post_init_vm(struct kvm *kvm) diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index d77b094d9a4d..04c375bf1ac2 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -646,6 +646,11 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, u32 pause_count12; u32 pause_thresh12; + nested_svm_transition_tlb_flush(vcpu); + + /* Enter Guest-Mode */ + enter_guest_mode(vcpu); + /* * Filled at exit: exit_code, exit_code_hi, exit_info_1, exit_info_2, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. @@ -762,11 +767,6 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, } } - nested_svm_transition_tlb_flush(vcpu); - - /* Enter Guest-Mode */ - enter_guest_mode(vcpu); - /* * Merge guest and host intercepts - must be called with vcpu in * guest-mode to take effect. diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index a2a794c32050..0dbb25442ec1 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2972,6 +2972,16 @@ void __init sev_hardware_setup(void) WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID))) goto out; + /* + * The kernel's initcall infrastructure lacks the ability to express + * dependencies between initcalls, whereas the modules infrastructure + * automatically handles dependencies via symbol loading. Ensure the + * PSP SEV driver is initialized before proceeding if KVM is built-in, + * as the dependency isn't handled by the initcall infrastructure. + */ + if (IS_BUILTIN(CONFIG_KVM_AMD) && sev_module_init()) + goto out; + /* Retrieve SEV CPUID information */ cpuid(0x8000001f, &eax, &ebx, &ecx, &edx); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 7640a84e554a..a713c803a3a3 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1991,11 +1991,11 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) svm->asid = sd->next_asid++; } -static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value) +static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value) { - struct vmcb *vmcb = svm->vmcb; + struct vmcb *vmcb = to_svm(vcpu)->vmcb; - if (svm->vcpu.arch.guest_state_protected) + if (vcpu->arch.guest_state_protected) return; if (unlikely(value != vmcb->save.dr6)) { @@ -4247,10 +4247,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, * Run with all-zero DR6 unless needed, so that we can get the exact cause * of a #DB. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - svm_set_dr6(svm, vcpu->arch.dr6); - else - svm_set_dr6(svm, DR6_ACTIVE_LOW); + if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))) + svm_set_dr6(vcpu, DR6_ACTIVE_LOW); clgi(); kvm_load_guest_xsave_state(vcpu); @@ -5043,6 +5041,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, + .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 2427f918e763..43ee9ed11291 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -61,6 +61,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, + .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f72835e85b6d..6c56d5235f0f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5648,6 +5648,12 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) set_debugreg(DR6_RESERVED, 6); } +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) +{ + lockdep_assert_irqs_disabled(); + set_debugreg(vcpu->arch.dr6, 6); +} + void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val) { vmcs_writel(GUEST_DR7, val); @@ -7417,10 +7423,6 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) vmx->loaded_vmcs->host_state.cr4 = cr4; } - /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ - if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) - set_debugreg(vcpu->arch.dr6, 6); - /* When single-stepping over STI and MOV SS, we must clear the * corresponding interruptibility bits in the guest state. Otherwise * vmentry fails as it then expects bit 14 (BS) in pending debug diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index ce3295a67c04..430773a5ef8e 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -73,6 +73,7 @@ void vmx_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt); +void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val); void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val); void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu); void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6d4a6734b2d6..02159c967d29 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10961,6 +10961,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) set_debugreg(vcpu->arch.eff_db[1], 1); set_debugreg(vcpu->arch.eff_db[2], 2); set_debugreg(vcpu->arch.eff_db[3], 3); + /* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */ + if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6); } else if (unlikely(hw_breakpoint_active())) { set_debugreg(0, 7); } @@ -12741,6 +12744,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); } + once_init(&kvm->arch.nx_once); return 0; out_uninit_mmu: @@ -12750,12 +12754,6 @@ out: return ret; } -int kvm_arch_post_init_vm(struct kvm *kvm) -{ - once_init(&kvm->arch.nx_once); - return 0; -} - static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ac52255fab01..296d294142c8 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -7,7 +7,6 @@ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/sched/task_stack.h> /* task_stack_*(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ -#include <linux/extable.h> /* search_exception_tables */ #include <linux/memblock.h> /* max_low_pfn */ #include <linux/kfence.h> /* kfence_handle_page_fault */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index a2becb85bea7..6cf881a942bb 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -607,18 +607,15 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, cond_mitigation(tsk); /* - * Stop remote flushes for the previous mm. - * Skip kernel threads; we never send init_mm TLB flushing IPIs, - * but the bitmap manipulation can cause cache line contention. + * Leave this CPU in prev's mm_cpumask. Atomic writes to + * mm_cpumask can be expensive under contention. The CPU + * will be removed lazily at TLB flush time. */ - if (prev != &init_mm) { - VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, - mm_cpumask(prev))); - cpumask_clear_cpu(cpu, mm_cpumask(prev)); - } + VM_WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu, + mm_cpumask(prev))); /* Start receiving IPIs and then read tlb_gen (and LAM below) */ - if (next != &init_mm) + if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next))) cpumask_set_cpu(cpu, mm_cpumask(next)); next_tlb_gen = atomic64_read(&next->context.tlb_gen); @@ -760,10 +757,13 @@ static void flush_tlb_func(void *info) if (!local) { inc_irq_stat(irq_tlb_count); count_vm_tlb_event(NR_TLB_REMOTE_FLUSH_RECEIVED); + } - /* Can only happen on remote CPUs */ - if (f->mm && f->mm != loaded_mm) - return; + /* The CPU was left in the mm_cpumask of the target mm. Clear it. */ + if (f->mm && f->mm != loaded_mm) { + cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(f->mm)); + trace_tlb_flush(TLB_REMOTE_WRONG_CPU, 0); + return; } if (unlikely(loaded_mm == &init_mm)) @@ -893,9 +893,36 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu, void *data) +static bool should_flush_tlb(int cpu, void *data) +{ + struct flush_tlb_info *info = data; + + /* Lazy TLB will get flushed at the next context switch. */ + if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu)) + return false; + + /* No mm means kernel memory flush. */ + if (!info->mm) + return true; + + /* The target mm is loaded, and the CPU is not lazy. */ + if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm) + return true; + + /* In cpumask, but not the loaded mm? Periodically remove by flushing. */ + if (info->trim_cpumask) + return true; + + return false; +} + +static bool should_trim_cpumask(struct mm_struct *mm) { - return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); + if (time_after(jiffies, READ_ONCE(mm->context.next_trim_cpumask))) { + WRITE_ONCE(mm->context.next_trim_cpumask, jiffies + HZ); + return true; + } + return false; } DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); @@ -929,7 +956,7 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); else - on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + on_each_cpu_cond_mask(should_flush_tlb, flush_tlb_func, (void *)info, 1, cpumask); } @@ -980,6 +1007,7 @@ static struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, info->freed_tables = freed_tables; info->new_tlb_gen = new_tlb_gen; info->initiating_cpu = smp_processor_id(); + info->trim_cpumask = 0; return info; } @@ -1022,6 +1050,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, * flush_tlb_func_local() directly in this case. */ if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids) { + info->trim_cpumask = should_trim_cpumask(mm); flush_tlb_multi(mm_cpumask(mm), info); } else if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) { lockdep_assert_irqs_enabled(); diff --git a/arch/x86/um/asm/archparam.h b/arch/x86/um/asm/archparam.h deleted file mode 100644 index c17cf68dda0f..000000000000 --- a/arch/x86/um/asm/archparam.h +++ /dev/null @@ -1,20 +0,0 @@ -/* - * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com) - * Copyright 2003 PathScale, Inc. - * Licensed under the GPL - */ - -#ifndef __UM_ARCHPARAM_H -#define __UM_ARCHPARAM_H - -#ifdef CONFIG_X86_32 - -#ifdef CONFIG_X86_PAE -#define LAST_PKMAP 512 -#else -#define LAST_PKMAP 1024 -#endif - -#endif - -#endif diff --git a/arch/x86/um/os-Linux/registers.c b/arch/x86/um/os-Linux/registers.c index 76eaeb93928c..eb1cdadc8a61 100644 --- a/arch/x86/um/os-Linux/registers.c +++ b/arch/x86/um/os-Linux/registers.c @@ -18,6 +18,7 @@ #include <registers.h> #include <sys/mman.h> +static unsigned long ptrace_regset; unsigned long host_fp_size; int get_fp_registers(int pid, unsigned long *regs) @@ -27,7 +28,7 @@ int get_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -39,7 +40,7 @@ int put_fp_registers(int pid, unsigned long *regs) .iov_len = host_fp_size, }; - if (ptrace(PTRACE_SETREGSET, pid, NT_X86_XSTATE, &iov) < 0) + if (ptrace(PTRACE_SETREGSET, pid, ptrace_regset, &iov) < 0) return -errno; return 0; } @@ -58,9 +59,23 @@ int arch_init_registers(int pid) return -ENOMEM; /* GDB has x86_xsave_length, which uses x86_cpuid_count */ - ret = ptrace(PTRACE_GETREGSET, pid, NT_X86_XSTATE, &iov); + ptrace_regset = NT_X86_XSTATE; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); if (ret) ret = -errno; + + if (ret == -ENODEV) { +#ifdef CONFIG_X86_32 + ptrace_regset = NT_PRXFPREG; +#else + ptrace_regset = NT_PRFPREG; +#endif + iov.iov_len = 2 * 1024 * 1024; + ret = ptrace(PTRACE_GETREGSET, pid, ptrace_regset, &iov); + if (ret) + ret = -errno; + } + munmap(iov.iov_base, 2 * 1024 * 1024); host_fp_size = iov.iov_len; diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h index 2dd4ca6713f8..8f7476ff6e95 100644 --- a/arch/x86/um/shared/sysdep/ptrace.h +++ b/arch/x86/um/shared/sysdep/ptrace.h @@ -74,8 +74,6 @@ struct uml_pt_regs { #define UPT_FAULTINFO(r) (&(r)->faultinfo) #define UPT_IS_USER(r) ((r)->is_user) -extern int user_context(unsigned long sp); - extern int arch_init_registers(int pid); #endif /* __SYSDEP_X86_PTRACE_H */ diff --git a/arch/x86/um/signal.c b/arch/x86/um/signal.c index 75087e85b6fd..2934e170b0fe 100644 --- a/arch/x86/um/signal.c +++ b/arch/x86/um/signal.c @@ -187,7 +187,12 @@ static int copy_sc_to_user(struct sigcontext __user *to, * Put magic/size values for userspace. We do not bother to verify them * later on, however, userspace needs them should it try to read the * XSTATE data. And ptrace does not fill in these parts. + * + * Skip this if we do not have an XSTATE frame. */ + if (host_fp_size <= sizeof(to_fp64->fpstate)) + return 0; + BUILD_BUG_ON(sizeof(int) != FP_XSTATE_MAGIC2_SIZE); #ifdef CONFIG_X86_32 __put_user(offsetof(struct _fpstate_32, _fxsr_env) + @@ -367,11 +372,13 @@ int setup_signal_stack_si(unsigned long stack_top, struct ksignal *ksig, int err = 0, sig = ksig->sig; unsigned long fp_to; - frame = (struct rt_sigframe __user *) - round_down(stack_top - sizeof(struct rt_sigframe), 16); + frame = (void __user *)stack_top - sizeof(struct rt_sigframe); /* Add required space for math frame */ - frame = (struct rt_sigframe __user *)((unsigned long)frame - math_size); + frame = (void __user *)((unsigned long)frame - math_size); + + /* ABI requires 16 byte boundary alignment */ + frame = (void __user *)round_down((unsigned long)frame, 16); /* Subtract 128 for a red zone and 8 for proper alignment */ frame = (struct rt_sigframe __user *) ((unsigned long) frame - 128 - 8); diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 1dcc027ec77e..42e74a5a7d78 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -505,19 +505,19 @@ static bool __init setup_rmptable(void) * described in the SNP_INIT_EX firmware command description in the SNP * firmware ABI spec. */ -static int __init snp_rmptable_init(void) +int __init snp_rmptable_init(void) { unsigned int i; u64 val; - if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) - return 0; + if (WARN_ON_ONCE(!cc_platform_has(CC_ATTR_HOST_SEV_SNP))) + return -ENOSYS; - if (!amd_iommu_snp_en) - goto nosnp; + if (WARN_ON_ONCE(!amd_iommu_snp_en)) + return -ENOSYS; if (!setup_rmptable()) - goto nosnp; + return -ENOSYS; /* * Check if SEV-SNP is already enabled, this can happen in case of @@ -530,7 +530,7 @@ static int __init snp_rmptable_init(void) /* Zero out the RMP bookkeeping area */ if (!clear_rmptable_bookkeeping()) { free_rmp_segment_table(); - goto nosnp; + return -ENOSYS; } /* Zero out the RMP entries */ @@ -562,17 +562,8 @@ skip_enable: crash_kexec_post_notifiers = true; return 0; - -nosnp: - cc_platform_clear(CC_ATTR_HOST_SEV_SNP); - return -ENOSYS; } -/* - * This must be called after the IOMMU has been initialized. - */ -device_initcall(snp_rmptable_init); - static void set_rmp_segment_info(unsigned int segment_shift) { rmp_segment_shift = segment_shift; diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 55a4996d0c04..d078de2c952b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -111,6 +111,51 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; */ static DEFINE_SPINLOCK(xen_reservation_lock); +/* Protected by xen_reservation_lock. */ +#define MIN_CONTIG_ORDER 9 /* 2MB */ +static unsigned int discontig_frames_order = MIN_CONTIG_ORDER; +static unsigned long discontig_frames_early[1UL << MIN_CONTIG_ORDER] __initdata; +static unsigned long *discontig_frames __refdata = discontig_frames_early; +static bool discontig_frames_dyn; + +static int alloc_discontig_frames(unsigned int order) +{ + unsigned long *new_array, *old_array; + unsigned int old_order; + unsigned long flags; + + BUG_ON(order < MIN_CONTIG_ORDER); + BUILD_BUG_ON(sizeof(discontig_frames_early) != PAGE_SIZE); + + new_array = (unsigned long *)__get_free_pages(GFP_KERNEL, + order - MIN_CONTIG_ORDER); + if (!new_array) + return -ENOMEM; + + spin_lock_irqsave(&xen_reservation_lock, flags); + + old_order = discontig_frames_order; + + if (order > discontig_frames_order || !discontig_frames_dyn) { + if (!discontig_frames_dyn) + old_array = NULL; + else + old_array = discontig_frames; + + discontig_frames = new_array; + discontig_frames_order = order; + discontig_frames_dyn = true; + } else { + old_array = new_array; + } + + spin_unlock_irqrestore(&xen_reservation_lock, flags); + + free_pages((unsigned long)old_array, old_order - MIN_CONTIG_ORDER); + + return 0; +} + /* * Note about cr3 (pagetable base) values: * @@ -781,6 +826,7 @@ void xen_mm_pin_all(void) { struct page *page; + spin_lock(&init_mm.page_table_lock); spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { @@ -791,6 +837,7 @@ void xen_mm_pin_all(void) } spin_unlock(&pgd_lock); + spin_unlock(&init_mm.page_table_lock); } static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page, @@ -812,6 +859,9 @@ static void __init xen_after_bootmem(void) SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); + + if (alloc_discontig_frames(MIN_CONTIG_ORDER)) + BUG(); } static void xen_unpin_page(struct mm_struct *mm, struct page *page, @@ -887,6 +937,7 @@ void xen_mm_unpin_all(void) { struct page *page; + spin_lock(&init_mm.page_table_lock); spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { @@ -898,6 +949,7 @@ void xen_mm_unpin_all(void) } spin_unlock(&pgd_lock); + spin_unlock(&init_mm.page_table_lock); } static void xen_enter_mmap(struct mm_struct *mm) @@ -2199,10 +2251,6 @@ void __init xen_init_mmu_ops(void) memset(dummy_mapping, 0xff, PAGE_SIZE); } -/* Protected by xen_reservation_lock. */ -#define MAX_CONTIG_ORDER 9 /* 2MB */ -static unsigned long discontig_frames[1<<MAX_CONTIG_ORDER]; - #define VOID_PTE (mfn_pte(0, __pgprot(0))) static void xen_zap_pfn_range(unsigned long vaddr, unsigned int order, unsigned long *in_frames, @@ -2319,18 +2367,25 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle) { - unsigned long *in_frames = discontig_frames, out_frame; + unsigned long *in_frames, out_frame; unsigned long flags; int success; unsigned long vstart = (unsigned long)phys_to_virt(pstart); - if (unlikely(order > MAX_CONTIG_ORDER)) - return -ENOMEM; + if (unlikely(order > discontig_frames_order)) { + if (!discontig_frames_dyn) + return -ENOMEM; + + if (alloc_discontig_frames(order)) + return -ENOMEM; + } memset((void *) vstart, 0, PAGE_SIZE << order); spin_lock_irqsave(&xen_reservation_lock, flags); + in_frames = discontig_frames; + /* 1. Zap current PTEs, remembering MFNs. */ xen_zap_pfn_range(vstart, order, in_frames, NULL); @@ -2354,12 +2409,12 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { - unsigned long *out_frames = discontig_frames, in_frame; + unsigned long *out_frames, in_frame; unsigned long flags; int success; unsigned long vstart; - if (unlikely(order > MAX_CONTIG_ORDER)) + if (unlikely(order > discontig_frames_order)) return; vstart = (unsigned long)phys_to_virt(pstart); @@ -2367,6 +2422,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) spin_lock_irqsave(&xen_reservation_lock, flags); + out_frames = discontig_frames; + /* 1. Find start MFN of contiguous extent. */ in_frame = virt_to_mfn((void *)vstart); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 9252652afe59..894edf8d6d62 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -100,9 +100,6 @@ SYM_FUNC_START(xen_hypercall_hvm) push %r10 push %r9 push %r8 -#ifdef CONFIG_FRAME_POINTER - pushq $0 /* Dummy push for stack alignment. */ -#endif #endif /* Set the vendor specific function. */ call __xen_hypercall_setfunc @@ -117,11 +114,8 @@ SYM_FUNC_START(xen_hypercall_hvm) pop %ebx pop %eax #else - lea xen_hypercall_amd(%rip), %rbx - cmp %rax, %rbx -#ifdef CONFIG_FRAME_POINTER - pop %rax /* Dummy pop. */ -#endif + lea xen_hypercall_amd(%rip), %rcx + cmp %rax, %rcx pop %r8 pop %r9 pop %r10 @@ -132,6 +126,7 @@ SYM_FUNC_START(xen_hypercall_hvm) pop %rcx pop %rax #endif + FRAME_END /* Use correct hypercall function. */ jz xen_hypercall_amd jmp xen_hypercall_intel diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index f1cf7f2909f3..9ed93d91d754 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1546,6 +1546,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) struct request_queue *q = disk->queue; struct blkg_policy_data *pd_prealloc = NULL; struct blkcg_gq *blkg, *pinned_blkg = NULL; + unsigned int memflags; int ret; if (blkcg_policy_enabled(q, pol)) @@ -1560,7 +1561,7 @@ int blkcg_activate_policy(struct gendisk *disk, const struct blkcg_policy *pol) return -EINVAL; if (queue_is_mq(q)) - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); retry: spin_lock_irq(&q->queue_lock); @@ -1624,7 +1625,7 @@ retry: spin_unlock_irq(&q->queue_lock); out: if (queue_is_mq(q)) - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); if (pinned_blkg) blkg_put(pinned_blkg); if (pd_prealloc) @@ -1668,12 +1669,13 @@ void blkcg_deactivate_policy(struct gendisk *disk, { struct request_queue *q = disk->queue; struct blkcg_gq *blkg; + unsigned int memflags; if (!blkcg_policy_enabled(q, pol)) return; if (queue_is_mq(q)) - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); mutex_lock(&q->blkcg_mutex); spin_lock_irq(&q->queue_lock); @@ -1697,7 +1699,7 @@ void blkcg_deactivate_policy(struct gendisk *disk, mutex_unlock(&q->blkcg_mutex); if (queue_is_mq(q)) - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); diff --git a/block/blk-core.c b/block/blk-core.c index 32fb28a6372c..d6c4fa3943b5 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -430,7 +430,6 @@ struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id) refcount_set(&q->refs, 1); mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); - mutex_init(&q->sysfs_dir_lock); mutex_init(&q->limits_lock); mutex_init(&q->rq_qos_mutex); spin_lock_init(&q->queue_lock); diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index c9eb4241e048..d479f5481b66 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -111,7 +111,6 @@ int disk_register_independent_access_ranges(struct gendisk *disk) struct request_queue *q = disk->queue; int i, ret; - lockdep_assert_held(&q->sysfs_dir_lock); lockdep_assert_held(&q->sysfs_lock); if (!iars) @@ -155,7 +154,6 @@ void disk_unregister_independent_access_ranges(struct gendisk *disk) struct blk_independent_access_ranges *iars = disk->ia_ranges; int i; - lockdep_assert_held(&q->sysfs_dir_lock); lockdep_assert_held(&q->sysfs_lock); if (!iars) @@ -289,7 +287,6 @@ void disk_set_independent_access_ranges(struct gendisk *disk, { struct request_queue *q = disk->queue; - mutex_lock(&q->sysfs_dir_lock); mutex_lock(&q->sysfs_lock); if (iars && !disk_check_ia_ranges(disk, iars)) { kfree(iars); @@ -313,6 +310,5 @@ void disk_set_independent_access_ranges(struct gendisk *disk, disk_register_independent_access_ranges(disk); unlock: mutex_unlock(&q->sysfs_lock); - mutex_unlock(&q->sysfs_dir_lock); } EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges); diff --git a/block/blk-iocost.c b/block/blk-iocost.c index a5894ec9696e..65a1d4427ccf 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -3224,6 +3224,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, u32 qos[NR_QOS_PARAMS]; bool enable, user; char *body, *p; + unsigned int memflags; int ret; blkg_conf_init(&ctx, input); @@ -3247,7 +3248,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, ioc = q_to_ioc(disk->queue); } - blk_mq_freeze_queue(disk->queue); + memflags = blk_mq_freeze_queue(disk->queue); blk_mq_quiesce_queue(disk->queue); spin_lock_irq(&ioc->lock); @@ -3347,7 +3348,7 @@ static ssize_t ioc_qos_write(struct kernfs_open_file *of, char *input, wbt_enable_default(disk); blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue); + blk_mq_unfreeze_queue(disk->queue, memflags); blkg_conf_exit(&ctx); return nbytes; @@ -3355,7 +3356,7 @@ einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue); + blk_mq_unfreeze_queue(disk->queue, memflags); ret = -EINVAL; err: @@ -3414,6 +3415,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, { struct blkg_conf_ctx ctx; struct request_queue *q; + unsigned int memflags; struct ioc *ioc; u64 u[NR_I_LCOEFS]; bool user; @@ -3441,7 +3443,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, ioc = q_to_ioc(q); } - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); spin_lock_irq(&ioc->lock); @@ -3493,7 +3495,7 @@ static ssize_t ioc_cost_model_write(struct kernfs_open_file *of, char *input, spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); blkg_conf_exit(&ctx); return nbytes; @@ -3502,7 +3504,7 @@ einval: spin_unlock_irq(&ioc->lock); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); ret = -EINVAL; err: diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index ebb522788d97..42c1e0b9a68f 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -749,9 +749,11 @@ static void blkiolatency_enable_work_fn(struct work_struct *work) */ enabled = atomic_read(&blkiolat->enable_cnt); if (enabled != blkiolat->enabled) { - blk_mq_freeze_queue(blkiolat->rqos.disk->queue); + unsigned int memflags; + + memflags = blk_mq_freeze_queue(blkiolat->rqos.disk->queue); blkiolat->enabled = enabled; - blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue); + blk_mq_unfreeze_queue(blkiolat->rqos.disk->queue, memflags); } } diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c index ad8d6a363f24..444798c5374f 100644 --- a/block/blk-mq-cpumap.c +++ b/block/blk-mq-cpumap.c @@ -87,7 +87,6 @@ void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap, return; fallback: - WARN_ON_ONCE(qmap->nr_queues > 1); - blk_mq_clear_mq_map(qmap); + blk_mq_map_queues(qmap); } EXPORT_SYMBOL_GPL(blk_mq_map_hw_queues); diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 156e9bb07abf..3feeeccf8a99 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -223,30 +223,27 @@ int blk_mq_sysfs_register(struct gendisk *disk) unsigned long i, j; int ret; - lockdep_assert_held(&q->sysfs_dir_lock); - ret = kobject_add(q->mq_kobj, &disk_to_dev(disk)->kobj, "mq"); if (ret < 0) - goto out; + return ret; kobject_uevent(q->mq_kobj, KOBJ_ADD); + mutex_lock(&q->tag_set->tag_list_lock); queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); if (ret) - goto unreg; + goto out_unreg; } + mutex_unlock(&q->tag_set->tag_list_lock); + return 0; - q->mq_sysfs_init_done = true; - -out: - return ret; - -unreg: +out_unreg: queue_for_each_hw_ctx(q, hctx, j) { if (j < i) blk_mq_unregister_hctx(hctx); } + mutex_unlock(&q->tag_set->tag_list_lock); kobject_uevent(q->mq_kobj, KOBJ_REMOVE); kobject_del(q->mq_kobj); @@ -259,15 +256,13 @@ void blk_mq_sysfs_unregister(struct gendisk *disk) struct blk_mq_hw_ctx *hctx; unsigned long i; - lockdep_assert_held(&q->sysfs_dir_lock); - + mutex_lock(&q->tag_set->tag_list_lock); queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); + mutex_unlock(&q->tag_set->tag_list_lock); kobject_uevent(q->mq_kobj, KOBJ_REMOVE); kobject_del(q->mq_kobj); - - q->mq_sysfs_init_done = false; } void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) @@ -275,15 +270,11 @@ void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) struct blk_mq_hw_ctx *hctx; unsigned long i; - mutex_lock(&q->sysfs_dir_lock); - if (!q->mq_sysfs_init_done) - goto unlock; + if (!blk_queue_registered(q)) + return; queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); - -unlock: - mutex_unlock(&q->sysfs_dir_lock); } int blk_mq_sysfs_register_hctxs(struct request_queue *q) @@ -292,9 +283,8 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) unsigned long i; int ret = 0; - mutex_lock(&q->sysfs_dir_lock); - if (!q->mq_sysfs_init_done) - goto unlock; + if (!blk_queue_registered(q)) + goto out; queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); @@ -302,8 +292,6 @@ int blk_mq_sysfs_register_hctxs(struct request_queue *q) break; } -unlock: - mutex_unlock(&q->sysfs_dir_lock); - +out: return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index da39a1cac702..40490ac88045 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -210,12 +210,12 @@ int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout); -void blk_mq_freeze_queue(struct request_queue *q) +void blk_mq_freeze_queue_nomemsave(struct request_queue *q) { blk_freeze_queue_start(q); blk_mq_freeze_queue_wait(q); } -EXPORT_SYMBOL_GPL(blk_mq_freeze_queue); +EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_nomemsave); bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) { @@ -236,12 +236,12 @@ bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic) return unfreeze; } -void blk_mq_unfreeze_queue(struct request_queue *q) +void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q) { if (__blk_mq_unfreeze_queue(q, false)) blk_unfreeze_release_lock(q); } -EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); +EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue_nomemrestore); /* * non_owner variant of blk_freeze_queue_start @@ -4223,13 +4223,14 @@ static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set, bool shared) { struct request_queue *q; + unsigned int memflags; lockdep_assert_held(&set->tag_list_lock); list_for_each_entry(q, &set->tag_list, tag_set_list) { - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); queue_set_hctx_shared(q, shared); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } } @@ -4992,6 +4993,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, struct request_queue *q; LIST_HEAD(head); int prev_nr_hw_queues = set->nr_hw_queues; + unsigned int memflags; int i; lockdep_assert_held(&set->tag_list_lock); @@ -5003,8 +5005,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, if (set->nr_maps == 1 && nr_hw_queues == set->nr_hw_queues) return; + memflags = memalloc_noio_save(); list_for_each_entry(q, &set->tag_list, tag_set_list) - blk_mq_freeze_queue(q); + blk_mq_freeze_queue_nomemsave(q); + /* * Switch IO scheduler to 'none', cleaning up the data associated * with the previous scheduler. We will switch back once we are done @@ -5052,7 +5056,8 @@ switch_back: blk_mq_elv_switch_back(&head, q); list_for_each_entry(q, &set->tag_list, tag_set_list) - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue_nomemrestore(q); + memalloc_noio_restore(memflags); /* Free the excess tags when nr_hw_queues shrink. */ for (i = set->nr_hw_queues; i < prev_nr_hw_queues; i++) diff --git a/block/blk-pm.c b/block/blk-pm.c index 42e842074715..8d3e052f91da 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -89,7 +89,7 @@ int blk_pre_runtime_suspend(struct request_queue *q) if (percpu_ref_is_zero(&q->q_usage_counter)) ret = 0; /* Switch q_usage_counter back to per-cpu mode. */ - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue_nomemrestore(q); if (ret < 0) { spin_lock_irq(&q->queue_lock); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index eb9618cd68ad..d4d4f4dc0e23 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -299,6 +299,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, const struct rq_qos_ops *ops) { struct request_queue *q = disk->queue; + unsigned int memflags; lockdep_assert_held(&q->rq_qos_mutex); @@ -310,14 +311,14 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, * No IO can be in-flight when adding rqos, so freeze queue, which * is fine since we only support rq_qos for blk-mq queue. */ - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); if (rq_qos_id(q, rqos->id)) goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); if (rqos->ops->debugfs_attrs) { mutex_lock(&q->debugfs_mutex); @@ -327,7 +328,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id, return 0; ebusy: - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); return -EBUSY; } @@ -335,17 +336,18 @@ void rq_qos_del(struct rq_qos *rqos) { struct request_queue *q = rqos->disk->queue; struct rq_qos **cur; + unsigned int memflags; lockdep_assert_held(&q->rq_qos_mutex); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); for (cur = &q->rq_qos; *cur; cur = &(*cur)->next) { if (*cur == rqos) { *cur = rqos->next; break; } } - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); mutex_lock(&q->debugfs_mutex); blk_mq_debugfs_unregister_rqos(rqos); diff --git a/block/blk-settings.c b/block/blk-settings.c index db12396ff5c7..c44dadc35e1e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -461,11 +461,12 @@ EXPORT_SYMBOL_GPL(queue_limits_commit_update); int queue_limits_commit_update_frozen(struct request_queue *q, struct queue_limits *lim) { + unsigned int memflags; int ret; - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); ret = queue_limits_commit_update(q, lim); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); return ret; } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e09b455874bf..6f548a4376aa 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -681,7 +681,7 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; - unsigned int noio_flag; + unsigned int memflags; ssize_t res; if (!entry->store_limit && !entry->store) @@ -711,11 +711,9 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr, } mutex_lock(&q->sysfs_lock); - blk_mq_freeze_queue(q); - noio_flag = memalloc_noio_save(); + memflags = blk_mq_freeze_queue(q); res = entry->store(disk, page, length); - memalloc_noio_restore(noio_flag); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); mutex_unlock(&q->sysfs_lock); return res; } @@ -764,7 +762,6 @@ int blk_register_queue(struct gendisk *disk) struct request_queue *q = disk->queue; int ret; - mutex_lock(&q->sysfs_dir_lock); kobject_init(&disk->queue_kobj, &blk_queue_ktype); ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue"); if (ret < 0) @@ -805,7 +802,6 @@ int blk_register_queue(struct gendisk *disk) if (q->elevator) kobject_uevent(&q->elevator->kobj, KOBJ_ADD); mutex_unlock(&q->sysfs_lock); - mutex_unlock(&q->sysfs_dir_lock); /* * SCSI probing may synchronously create and destroy a lot of @@ -830,7 +826,6 @@ out_debugfs_remove: mutex_unlock(&q->sysfs_lock); out_put_queue_kobj: kobject_put(&disk->queue_kobj); - mutex_unlock(&q->sysfs_dir_lock); return ret; } @@ -861,7 +856,6 @@ void blk_unregister_queue(struct gendisk *disk) blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q); mutex_unlock(&q->sysfs_lock); - mutex_lock(&q->sysfs_dir_lock); /* * Remove the sysfs attributes before unregistering the queue data * structures that can be modified through sysfs. @@ -878,7 +872,6 @@ void blk_unregister_queue(struct gendisk *disk) /* Now that we've deleted all child objects, we can delete the queue. */ kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE); kobject_del(&disk->queue_kobj); - mutex_unlock(&q->sysfs_dir_lock); blk_debugfs_remove(disk); } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 82dbaefcfa3b..8d149aff9fd0 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1202,6 +1202,7 @@ static int blk_throtl_init(struct gendisk *disk) { struct request_queue *q = disk->queue; struct throtl_data *td; + unsigned int memflags; int ret; td = kzalloc_node(sizeof(*td), GFP_KERNEL, q->node); @@ -1215,7 +1216,7 @@ static int blk_throtl_init(struct gendisk *disk) * Freeze queue before activating policy, to synchronize with IO path, * which is protected by 'q_usage_counter'. */ - blk_mq_freeze_queue(disk->queue); + memflags = blk_mq_freeze_queue(disk->queue); blk_mq_quiesce_queue(disk->queue); q->td = td; @@ -1239,7 +1240,7 @@ static int blk_throtl_init(struct gendisk *disk) out: blk_mq_unquiesce_queue(disk->queue); - blk_mq_unfreeze_queue(disk->queue); + blk_mq_unfreeze_queue(disk->queue, memflags); return ret; } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 9d08a54c201e..761ea662ddc3 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -1717,9 +1717,10 @@ int blk_revalidate_disk_zones(struct gendisk *disk) else pr_warn("%s: failed to revalidate zones\n", disk->disk_name); if (ret) { - blk_mq_freeze_queue(q); + unsigned int memflags = blk_mq_freeze_queue(q); + disk_free_zone_resources(disk); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } return ret; diff --git a/block/elevator.c b/block/elevator.c index b81216c48b6b..cd2ce4921601 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -570,6 +570,7 @@ static struct elevator_type *elevator_get_default(struct request_queue *q) void elevator_init_mq(struct request_queue *q) { struct elevator_type *e; + unsigned int memflags; int err; WARN_ON_ONCE(blk_queue_registered(q)); @@ -590,13 +591,13 @@ void elevator_init_mq(struct request_queue *q) * * Disk isn't added yet, so verifying queue lock only manually. */ - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_cancel_work_sync(q); err = blk_mq_init_sched(q, e); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); if (err) { pr_warn("\"%s\" elevator initialization failed, " @@ -614,11 +615,12 @@ void elevator_init_mq(struct request_queue *q) */ int elevator_switch(struct request_queue *q, struct elevator_type *new_e) { + unsigned int memflags; int ret; lockdep_assert_held(&q->sysfs_lock); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); if (q->elevator) { @@ -639,7 +641,7 @@ int elevator_switch(struct request_queue *q, struct elevator_type *new_e) out_unfreeze: blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); if (ret) { pr_warn("elv: switch to \"%s\" failed, falling back to \"none\"\n", @@ -651,9 +653,11 @@ out_unfreeze: void elevator_disable(struct request_queue *q) { + unsigned int memflags; + lockdep_assert_held(&q->sysfs_lock); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); elv_unregister_queue(q); @@ -664,7 +668,7 @@ void elevator_disable(struct request_queue *q) blk_add_trace_msg(q, "elv switch: none"); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } /* diff --git a/block/fops.c b/block/fops.c index 6d5c4fc5a216..be9f1dbea9ce 100644 --- a/block/fops.c +++ b/block/fops.c @@ -783,11 +783,12 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to) file_accessed(iocb->ki_filp); ret = blkdev_direct_IO(iocb, to); - if (ret >= 0) { + if (ret > 0) { iocb->ki_pos += ret; count -= ret; } - iov_iter_revert(to, count - iov_iter_count(to)); + if (ret != -EIOCBQUEUED) + iov_iter_revert(to, count - iov_iter_count(to)); if (ret < 0 || !count) goto reexpand; } diff --git a/block/partitions/mac.c b/block/partitions/mac.c index c80183156d68..b02530d98629 100644 --- a/block/partitions/mac.c +++ b/block/partitions/mac.c @@ -53,13 +53,25 @@ int mac_partition(struct parsed_partitions *state) } secsize = be16_to_cpu(md->block_size); put_dev_sector(sect); + + /* + * If the "block size" is not a power of 2, things get weird - we might + * end up with a partition straddling a sector boundary, so we wouldn't + * be able to read a partition entry with read_part_sector(). + * Real block sizes are probably (?) powers of two, so just require + * that. + */ + if (!is_power_of_2(secsize)) + return -1; datasize = round_down(secsize, 512); data = read_part_sector(state, datasize / 512, §); if (!data) return -1; partoffset = secsize % 512; - if (partoffset + sizeof(*part) > datasize) + if (partoffset + sizeof(*part) > datasize) { + put_dev_sector(sect); return -1; + } part = (struct mac_partition *) (data + partoffset); if (be16_to_cpu(part->signature) != MAC_PARTITION_MAGIC) { put_dev_sector(sect); @@ -112,8 +124,8 @@ int mac_partition(struct parsed_partitions *state) int i, l; goodness++; - l = strlen(part->name); - if (strcmp(part->name, "/") == 0) + l = strnlen(part->name, sizeof(part->name)); + if (strncmp(part->name, "/", sizeof(part->name)) == 0) goodness++; for (i = 0; i <= l - 4; ++i) { if (strncasecmp(part->name + i, "root", diff --git a/crypto/fips.c b/crypto/fips.c index a58e7750f532..2fa3a9ee61a1 100644 --- a/crypto/fips.c +++ b/crypto/fips.c @@ -41,7 +41,7 @@ __setup("fips=", fips_enable); static char fips_name[] = FIPS_MODULE_NAME; static char fips_version[] = FIPS_MODULE_VERSION; -static struct ctl_table crypto_sysctl_table[] = { +static const struct ctl_table crypto_sysctl_table[] = { { .procname = "fips_enabled", .data = &fips_enabled, diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index 97d4a032171f..f5b8497cf5ad 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -21,6 +21,11 @@ #define AMDXDNA_AUTOSUSPEND_DELAY 5000 /* milliseconds */ +MODULE_FIRMWARE("amdnpu/1502_00/npu.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_10/npu.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_11/npu.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_20/npu.sbin"); + /* * Bind the driver base on (vendor_id, device_id) pair and later use the * (device_id, rev_id) pair as a key to select the devices. The devices with diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 1e8ffbe25eee..38cf1c342c72 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -397,15 +397,19 @@ int ivpu_boot(struct ivpu_device *vdev) if (ivpu_fw_is_cold_boot(vdev)) { ret = ivpu_pm_dct_init(vdev); if (ret) - goto err_diagnose_failure; + goto err_disable_ipc; ret = ivpu_hw_sched_init(vdev); if (ret) - goto err_diagnose_failure; + goto err_disable_ipc; } return 0; +err_disable_ipc: + ivpu_ipc_disable(vdev); + ivpu_hw_irq_disable(vdev); + disable_irq(vdev->irq); err_diagnose_failure: ivpu_hw_diagnose_failure(vdev); ivpu_mmu_evtq_dump(vdev); diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 87d7411ae059..5060c5dd40d1 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -115,41 +115,57 @@ err_power_down: return ret; } -static void ivpu_pm_recovery_work(struct work_struct *work) +static void ivpu_pm_reset_begin(struct ivpu_device *vdev) { - struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work); - struct ivpu_device *vdev = pm->vdev; - char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL}; - int ret; - - ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter)); - - ret = pm_runtime_resume_and_get(vdev->drm.dev); - if (ret) - ivpu_err(vdev, "Failed to resume NPU: %d\n", ret); - - ivpu_jsm_state_dump(vdev); - ivpu_dev_coredump(vdev); + pm_runtime_disable(vdev->drm.dev); atomic_inc(&vdev->pm->reset_counter); atomic_set(&vdev->pm->reset_pending, 1); down_write(&vdev->pm->reset_lock); +} + +static void ivpu_pm_reset_complete(struct ivpu_device *vdev) +{ + int ret; - ivpu_suspend(vdev); ivpu_pm_prepare_cold_boot(vdev); ivpu_jobs_abort_all(vdev); ivpu_ms_cleanup_all(vdev); ret = ivpu_resume(vdev); - if (ret) + if (ret) { ivpu_err(vdev, "Failed to resume NPU: %d\n", ret); + pm_runtime_set_suspended(vdev->drm.dev); + } else { + pm_runtime_set_active(vdev->drm.dev); + } up_write(&vdev->pm->reset_lock); atomic_set(&vdev->pm->reset_pending, 0); - kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt); pm_runtime_mark_last_busy(vdev->drm.dev); - pm_runtime_put_autosuspend(vdev->drm.dev); + pm_runtime_enable(vdev->drm.dev); +} + +static void ivpu_pm_recovery_work(struct work_struct *work) +{ + struct ivpu_pm_info *pm = container_of(work, struct ivpu_pm_info, recovery_work); + struct ivpu_device *vdev = pm->vdev; + char *evt[2] = {"IVPU_PM_EVENT=IVPU_RECOVER", NULL}; + + ivpu_err(vdev, "Recovering the NPU (reset #%d)\n", atomic_read(&vdev->pm->reset_counter)); + + ivpu_pm_reset_begin(vdev); + + if (!pm_runtime_status_suspended(vdev->drm.dev)) { + ivpu_jsm_state_dump(vdev); + ivpu_dev_coredump(vdev); + ivpu_suspend(vdev); + } + + ivpu_pm_reset_complete(vdev); + + kobject_uevent_env(&vdev->drm.dev->kobj, KOBJ_CHANGE, evt); } void ivpu_pm_trigger_recovery(struct ivpu_device *vdev, const char *reason) @@ -309,7 +325,10 @@ int ivpu_rpm_get(struct ivpu_device *vdev) int ret; ret = pm_runtime_resume_and_get(vdev->drm.dev); - drm_WARN_ON(&vdev->drm, ret < 0); + if (ret < 0) { + ivpu_err(vdev, "Failed to resume NPU: %d\n", ret); + pm_runtime_set_suspended(vdev->drm.dev); + } return ret; } @@ -325,16 +344,13 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev) struct ivpu_device *vdev = pci_get_drvdata(pdev); ivpu_dbg(vdev, PM, "Pre-reset..\n"); - atomic_inc(&vdev->pm->reset_counter); - atomic_set(&vdev->pm->reset_pending, 1); - pm_runtime_get_sync(vdev->drm.dev); - down_write(&vdev->pm->reset_lock); - ivpu_prepare_for_reset(vdev); - ivpu_hw_reset(vdev); - ivpu_pm_prepare_cold_boot(vdev); - ivpu_jobs_abort_all(vdev); - ivpu_ms_cleanup_all(vdev); + ivpu_pm_reset_begin(vdev); + + if (!pm_runtime_status_suspended(vdev->drm.dev)) { + ivpu_prepare_for_reset(vdev); + ivpu_hw_reset(vdev); + } ivpu_dbg(vdev, PM, "Pre-reset done.\n"); } @@ -342,18 +358,12 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev) void ivpu_pm_reset_done_cb(struct pci_dev *pdev) { struct ivpu_device *vdev = pci_get_drvdata(pdev); - int ret; ivpu_dbg(vdev, PM, "Post-reset..\n"); - ret = ivpu_resume(vdev); - if (ret) - ivpu_err(vdev, "Failed to set RESUME state: %d\n", ret); - up_write(&vdev->pm->reset_lock); - atomic_set(&vdev->pm->reset_pending, 0); - ivpu_dbg(vdev, PM, "Post-reset done.\n"); - pm_runtime_mark_last_busy(vdev->drm.dev); - pm_runtime_put_autosuspend(vdev->drm.dev); + ivpu_pm_reset_complete(vdev); + + ivpu_dbg(vdev, PM, "Post-reset done.\n"); } void ivpu_pm_init(struct ivpu_device *vdev) diff --git a/drivers/acpi/arm64/gtdt.c b/drivers/acpi/arm64/gtdt.c index 3561553eff8b..70f8290b659d 100644 --- a/drivers/acpi/arm64/gtdt.c +++ b/drivers/acpi/arm64/gtdt.c @@ -163,7 +163,7 @@ int __init acpi_gtdt_init(struct acpi_table_header *table, { void *platform_timer; struct acpi_table_gtdt *gtdt; - int cnt = 0; + u32 cnt = 0; gtdt = container_of(table, struct acpi_table_gtdt, header); acpi_gtdt_desc.gtdt = gtdt; @@ -188,13 +188,17 @@ int __init acpi_gtdt_init(struct acpi_table_header *table, cnt++; if (cnt != gtdt->platform_timer_count) { + cnt = min(cnt, gtdt->platform_timer_count); + pr_err(FW_BUG "limiting Platform Timer count to %d\n", cnt); + } + + if (!cnt) { acpi_gtdt_desc.platform_timer = NULL; - pr_err(FW_BUG "invalid timer data.\n"); - return -EINVAL; + return 0; } if (platform_timer_count) - *platform_timer_count = gtdt->platform_timer_count; + *platform_timer_count = cnt; return 0; } diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 80a3481c0470..bfbb08b1e6af 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -442,9 +442,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header, return -EINVAL; } - pr_info("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n", - hmat_loc->flags, hmat_data_type(type), ipds, tpds, - hmat_loc->entry_base_unit); + pr_debug("Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n", + hmat_loc->flags, hmat_data_type(type), ipds, tpds, + hmat_loc->entry_base_unit); inits = (u32 *)(hmat_loc + 1); targs = inits + ipds; @@ -455,9 +455,9 @@ static __init int hmat_parse_locality(union acpi_subtable_headers *header, value = hmat_normalize(entries[init * tpds + targ], hmat_loc->entry_base_unit, type); - pr_info(" Initiator-Target[%u-%u]:%u%s\n", - inits[init], targs[targ], value, - hmat_data_type_suffix(type)); + pr_debug(" Initiator-Target[%u-%u]:%u%s\n", + inits[init], targs[targ], value, + hmat_data_type_suffix(type)); hmat_update_target(targs[targ], inits[init], mem_hier, type, value); @@ -485,9 +485,9 @@ static __init int hmat_parse_cache(union acpi_subtable_headers *header, } attrs = cache->cache_attributes; - pr_info("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n", - cache->memory_PD, cache->cache_size, attrs, - cache->number_of_SMBIOShandles); + pr_debug("Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n", + cache->memory_PD, cache->cache_size, attrs, + cache->number_of_SMBIOShandles); target = find_mem_target(cache->memory_PD); if (!target) @@ -546,9 +546,9 @@ static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *heade } if (hmat_revision == 1) - pr_info("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n", - p->reserved3, p->reserved4, p->flags, p->processor_PD, - p->memory_PD); + pr_debug("Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n", + p->reserved3, p->reserved4, p->flags, p->processor_PD, + p->memory_PD); else pr_info("Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n", p->flags, p->processor_PD, p->memory_PD); diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 59fffe34c9d0..00ac0d7bb8c9 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -95,9 +95,13 @@ int __init fix_pxm_node_maps(int max_nid) int i, j, index = -1, count = 0; nodemask_t nodes_to_enable; - if (numa_off || srat_disabled()) + if (numa_off) return -1; + /* no or incomplete node/PXM mapping set, nothing to do */ + if (srat_disabled()) + return 0; + /* find fake nodes PXM mapping */ for (i = 0; i < MAX_NUMNODES; i++) { if (node_to_pxm_map[i] != PXM_INVAL) { @@ -117,6 +121,11 @@ int __init fix_pxm_node_maps(int max_nid) } } } + if (index == -1) { + pr_debug("No node/PXM mapping has been set\n"); + /* nothing more to be done */ + return 0; + } if (WARN(index != max_nid, "%d max nid when expected %d\n", index, max_nid)) return -1; diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c index 747f83f7114d..e549914a636c 100644 --- a/drivers/acpi/prmt.c +++ b/drivers/acpi/prmt.c @@ -287,9 +287,7 @@ static acpi_status acpi_platformrt_space_handler(u32 function, if (!handler || !module) goto invalid_guid; - if (!handler->handler_addr || - !handler->static_data_buffer_addr || - !handler->acpi_param_buffer_addr) { + if (!handler->handler_addr) { buffer->prm_status = PRM_HANDLER_ERROR; return AE_OK; } diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 98d93ed58315..436019d96027 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1187,8 +1187,6 @@ static int acpi_data_prop_read(const struct acpi_device_data *data, } break; } - if (nval == 0) - return -EINVAL; if (obj->type == ACPI_TYPE_BUFFER) { if (proptype != DEV_PROP_U8) @@ -1212,9 +1210,11 @@ static int acpi_data_prop_read(const struct acpi_device_data *data, ret = acpi_copy_property_array_uint(items, (u64 *)val, nval); break; case DEV_PROP_STRING: - ret = acpi_copy_property_array_string( - items, (char **)val, - min_t(u32, nval, obj->package.count)); + nval = min_t(u32, nval, obj->package.count); + if (nval == 0) + return -ENODATA; + + ret = acpi_copy_property_array_string(items, (char **)val, nval); break; default: ret = -EINVAL; diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 90aaec923889..b4cd14e7fa76 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -564,6 +564,12 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = { }, }, { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Eluktronics Inc."), + DMI_MATCH(DMI_BOARD_NAME, "MECH-17"), + }, + }, + { /* TongFang GM6XGxX/TUXEDO Stellaris 16 Gen5 AMD */ .matches = { DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"), diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index cb45ef5240da..068c1612660b 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -408,6 +408,19 @@ static const struct dmi_system_id acpi_quirk_skip_dmi_ids[] = { ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), }, { + /* Vexia Edu Atla 10 tablet 5V version */ + .matches = { + /* Having all 3 of these not set is somewhat unique */ + DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), + DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."), + DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."), + /* Above strings are too generic, also match on BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"), + }, + .driver_data = (void *)(ACPI_QUIRK_SKIP_I2C_CLIENTS | + ACPI_QUIRK_SKIP_ACPI_AC_AND_BATTERY), + }, + { /* Vexia Edu Atla 10 tablet 9V version */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index c085dd81ebe7..63ec2f218431 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4143,6 +4143,10 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = { { "Samsung SSD 860*", NULL, ATA_QUIRK_NO_NCQ_TRIM | ATA_QUIRK_ZERO_AFTER_TRIM | ATA_QUIRK_NO_NCQ_ON_ATI }, + { "Samsung SSD 870 QVO*", NULL, ATA_QUIRK_NO_NCQ_TRIM | + ATA_QUIRK_ZERO_AFTER_TRIM | + ATA_QUIRK_NO_NCQ_ON_ATI | + ATA_QUIRK_NOLPM }, { "Samsung SSD 870*", NULL, ATA_QUIRK_NO_NCQ_TRIM | ATA_QUIRK_ZERO_AFTER_TRIM | ATA_QUIRK_NO_NCQ_ON_ATI }, diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 67f277e1c3bf..5a46c066abc3 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -601,7 +601,7 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct page *page; - unsigned int offset; + unsigned int offset, count; if (!qc->cursg) { qc->curbytes = qc->nbytes; @@ -617,25 +617,27 @@ static void ata_pio_sector(struct ata_queued_cmd *qc) page = nth_page(page, (offset >> PAGE_SHIFT)); offset %= PAGE_SIZE; - trace_ata_sff_pio_transfer_data(qc, offset, qc->sect_size); + /* don't overrun current sg */ + count = min(qc->cursg->length - qc->cursg_ofs, qc->sect_size); + + trace_ata_sff_pio_transfer_data(qc, offset, count); /* * Split the transfer when it splits a page boundary. Note that the * split still has to be dword aligned like all ATA data transfers. */ WARN_ON_ONCE(offset % 4); - if (offset + qc->sect_size > PAGE_SIZE) { + if (offset + count > PAGE_SIZE) { unsigned int split_len = PAGE_SIZE - offset; ata_pio_xfer(qc, page, offset, split_len); - ata_pio_xfer(qc, nth_page(page, 1), 0, - qc->sect_size - split_len); + ata_pio_xfer(qc, nth_page(page, 1), 0, count - split_len); } else { - ata_pio_xfer(qc, page, offset, qc->sect_size); + ata_pio_xfer(qc, page, offset, count); } - qc->curbytes += qc->sect_size; - qc->cursg_ofs += qc->sect_size; + qc->curbytes += count; + qc->cursg_ofs += count; if (qc->cursg_ofs == qc->cursg->length) { qc->cursg = sg_next(qc->cursg); diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 7fb21768ca36..8074a10183dc 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -6,7 +6,7 @@ obj-y := component.o core.o bus.o dd.o syscore.o \ cpu.o firmware.o init.o map.o devres.o \ attribute_container.o transport_class.o \ topology.o container.o property.o cacheinfo.o \ - swnode.o + swnode.o faux.o obj-$(CONFIG_AUXILIARY_BUS) += auxiliary.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o obj-y += power/ diff --git a/drivers/base/base.h b/drivers/base/base.h index 8cf04a557bdb..0042e4774b0c 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -137,6 +137,7 @@ int hypervisor_init(void); static inline int hypervisor_init(void) { return 0; } #endif int platform_bus_init(void); +int faux_bus_init(void); void cpu_dev_init(void); void container_dev_init(void); #ifdef CONFIG_AUXILIARY_BUS diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index fdaa24bb641a..a7e511849875 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -599,6 +599,7 @@ CPU_SHOW_VULN_FALLBACK(retbleed); CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); +CPU_SHOW_VULN_FALLBACK(ghostwrite); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -614,6 +615,7 @@ static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL); static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL); static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); +static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -630,6 +632,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_spec_rstack_overflow.attr, &dev_attr_gather_data_sampling.attr, &dev_attr_reg_file_data_sampling.attr, + &dev_attr_ghostwrite.attr, NULL }; diff --git a/drivers/base/faux.c b/drivers/base/faux.c new file mode 100644 index 000000000000..531e9d789ee0 --- /dev/null +++ b/drivers/base/faux.c @@ -0,0 +1,232 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2025 Greg Kroah-Hartman <gregkh@linuxfoundation.org> + * Copyright (c) 2025 The Linux Foundation + * + * A "simple" faux bus that allows devices to be created and added + * automatically to it. This is to be used whenever you need to create a + * device that is not associated with any "real" system resources, and do + * not want to have to deal with a bus/driver binding logic. It is + * intended to be very simple, with only a create and a destroy function + * available. + */ +#include <linux/err.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/container_of.h> +#include <linux/device/faux.h> +#include "base.h" + +/* + * Internal wrapper structure so we can hold a pointer to the + * faux_device_ops for this device. + */ +struct faux_object { + struct faux_device faux_dev; + const struct faux_device_ops *faux_ops; +}; +#define to_faux_object(dev) container_of_const(dev, struct faux_object, faux_dev.dev) + +static struct device faux_bus_root = { + .init_name = "faux", +}; + +static int faux_match(struct device *dev, const struct device_driver *drv) +{ + /* Match always succeeds, we only have one driver */ + return 1; +} + +static int faux_probe(struct device *dev) +{ + struct faux_object *faux_obj = to_faux_object(dev); + struct faux_device *faux_dev = &faux_obj->faux_dev; + const struct faux_device_ops *faux_ops = faux_obj->faux_ops; + int ret = 0; + + if (faux_ops && faux_ops->probe) + ret = faux_ops->probe(faux_dev); + + return ret; +} + +static void faux_remove(struct device *dev) +{ + struct faux_object *faux_obj = to_faux_object(dev); + struct faux_device *faux_dev = &faux_obj->faux_dev; + const struct faux_device_ops *faux_ops = faux_obj->faux_ops; + + if (faux_ops && faux_ops->remove) + faux_ops->remove(faux_dev); +} + +static const struct bus_type faux_bus_type = { + .name = "faux", + .match = faux_match, + .probe = faux_probe, + .remove = faux_remove, +}; + +static struct device_driver faux_driver = { + .name = "faux_driver", + .bus = &faux_bus_type, + .probe_type = PROBE_FORCE_SYNCHRONOUS, +}; + +static void faux_device_release(struct device *dev) +{ + struct faux_object *faux_obj = to_faux_object(dev); + + kfree(faux_obj); +} + +/** + * faux_device_create_with_groups - Create and register with the driver + * core a faux device and populate the device with an initial + * set of sysfs attributes. + * @name: The name of the device we are adding, must be unique for + * all faux devices. + * @parent: Pointer to a potential parent struct device. If set to + * NULL, the device will be created in the "root" of the faux + * device tree in sysfs. + * @faux_ops: struct faux_device_ops that the new device will call back + * into, can be NULL. + * @groups: The set of sysfs attributes that will be created for this + * device when it is registered with the driver core. + * + * Create a new faux device and register it in the driver core properly. + * If present, callbacks in @faux_ops will be called with the device that + * for the caller to do something with at the proper time given the + * device's lifecycle. + * + * Note, when this function is called, the functions specified in struct + * faux_ops can be called before the function returns, so be prepared for + * everything to be properly initialized before that point in time. + * + * Return: + * * NULL if an error happened with creating the device + * * pointer to a valid struct faux_device that is registered with sysfs + */ +struct faux_device *faux_device_create_with_groups(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops, + const struct attribute_group **groups) +{ + struct faux_object *faux_obj; + struct faux_device *faux_dev; + struct device *dev; + int ret; + + faux_obj = kzalloc(sizeof(*faux_obj), GFP_KERNEL); + if (!faux_obj) + return NULL; + + /* Save off the callbacks so we can use them in the future */ + faux_obj->faux_ops = faux_ops; + + /* Initialize the device portion and register it with the driver core */ + faux_dev = &faux_obj->faux_dev; + dev = &faux_dev->dev; + + device_initialize(dev); + dev->release = faux_device_release; + if (parent) + dev->parent = parent; + else + dev->parent = &faux_bus_root; + dev->bus = &faux_bus_type; + dev->groups = groups; + dev_set_name(dev, "%s", name); + + ret = device_add(dev); + if (ret) { + pr_err("%s: device_add for faux device '%s' failed with %d\n", + __func__, name, ret); + put_device(dev); + return NULL; + } + + return faux_dev; +} +EXPORT_SYMBOL_GPL(faux_device_create_with_groups); + +/** + * faux_device_create - create and register with the driver core a faux device + * @name: The name of the device we are adding, must be unique for all + * faux devices. + * @parent: Pointer to a potential parent struct device. If set to + * NULL, the device will be created in the "root" of the faux + * device tree in sysfs. + * @faux_ops: struct faux_device_ops that the new device will call back + * into, can be NULL. + * + * Create a new faux device and register it in the driver core properly. + * If present, callbacks in @faux_ops will be called with the device that + * for the caller to do something with at the proper time given the + * device's lifecycle. + * + * Note, when this function is called, the functions specified in struct + * faux_ops can be called before the function returns, so be prepared for + * everything to be properly initialized before that point in time. + * + * Return: + * * NULL if an error happened with creating the device + * * pointer to a valid struct faux_device that is registered with sysfs + */ +struct faux_device *faux_device_create(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops) +{ + return faux_device_create_with_groups(name, parent, faux_ops, NULL); +} +EXPORT_SYMBOL_GPL(faux_device_create); + +/** + * faux_device_destroy - destroy a faux device + * @faux_dev: faux device to destroy + * + * Unregisters and cleans up a device that was created with a call to + * faux_device_create() + */ +void faux_device_destroy(struct faux_device *faux_dev) +{ + struct device *dev = &faux_dev->dev; + + if (!faux_dev) + return; + + device_del(dev); + + /* The final put_device() will clean up the memory we allocated for this device. */ + put_device(dev); +} +EXPORT_SYMBOL_GPL(faux_device_destroy); + +int __init faux_bus_init(void) +{ + int ret; + + ret = device_register(&faux_bus_root); + if (ret) { + put_device(&faux_bus_root); + return ret; + } + + ret = bus_register(&faux_bus_type); + if (ret) + goto error_bus; + + ret = driver_register(&faux_driver); + if (ret) + goto error_driver; + + return ret; + +error_driver: + bus_unregister(&faux_bus_type); + +error_bus: + device_unregister(&faux_bus_root); + return ret; +} diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c index ddb70e29eb42..c8afc501a8a4 100644 --- a/drivers/base/firmware_loader/fallback_table.c +++ b/drivers/base/firmware_loader/fallback_table.c @@ -25,7 +25,7 @@ struct firmware_fallback_config fw_fallback_config = { EXPORT_SYMBOL_NS_GPL(fw_fallback_config, "FIRMWARE_LOADER_PRIVATE"); #ifdef CONFIG_SYSCTL -static struct ctl_table firmware_config_table[] = { +static const struct ctl_table firmware_config_table[] = { { .procname = "force_sysfs_fallback", .data = &fw_fallback_config.force_sysfs_fallback, diff --git a/drivers/base/init.c b/drivers/base/init.c index c4954835128c..9d2b06d65dfc 100644 --- a/drivers/base/init.c +++ b/drivers/base/init.c @@ -32,6 +32,7 @@ void __init driver_init(void) /* These are also core pieces, but must come after the * core core pieces. */ + faux_bus_init(); of_core_init(); platform_bus_init(); auxiliary_bus_init(); diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index cbc9a7a75def..40e1d8d8a589 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -656,13 +656,15 @@ static void device_resume_noirq(struct device *dev, pm_message_t state, bool asy * so change its status accordingly. * * Otherwise, the device is going to be resumed, so set its PM-runtime - * status to "active", but do that only if DPM_FLAG_SMART_SUSPEND is set - * to avoid confusing drivers that don't use it. + * status to "active" unless its power.set_active flag is clear, in + * which case it is not necessary to update its PM-runtime status. */ - if (skip_resume) + if (skip_resume) { pm_runtime_set_suspended(dev); - else if (dev_pm_skip_suspend(dev)) + } else if (dev->power.set_active) { pm_runtime_set_active(dev); + dev->power.set_active = false; + } if (dev->pm_domain) { info = "noirq power domain "; @@ -1278,8 +1280,14 @@ Skip: dev->power.may_skip_resume)) dev->power.must_resume = true; - if (dev->power.must_resume) + if (dev->power.must_resume) { + if (dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) { + dev->power.set_active = true; + if (dev->parent && !dev->parent->power.ignore_children) + dev->parent->power.set_active = true; + } dpm_superior_set_must_resume(dev); + } Complete: complete_all(&dev->power.completion); diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index 0bcd81389a29..978613407ea3 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -906,6 +906,7 @@ err_alloc: kfree(d->wake_buf); kfree(d->mask_buf_def); kfree(d->mask_buf); + kfree(d->main_status_buf); kfree(d->status_buf); kfree(d->status_reg_buf); if (d->config_buf) { @@ -981,6 +982,7 @@ void regmap_del_irq_chip(int irq, struct regmap_irq_chip_data *d) kfree(d->wake_buf); kfree(d->mask_buf_def); kfree(d->mask_buf); + kfree(d->main_status_buf); kfree(d->status_reg_buf); kfree(d->status_buf); if (d->config_buf) { diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c index 3523dd82d7a0..4db7f6ce8ade 100644 --- a/drivers/block/aoe/aoedev.c +++ b/drivers/block/aoe/aoedev.c @@ -226,10 +226,11 @@ aoedev_downdev(struct aoedev *d) /* fast fail all pending I/O */ if (d->blkq) { /* UP is cleared, freeze+quiesce to insure all are errored */ - blk_mq_freeze_queue(d->blkq); + unsigned int memflags = blk_mq_freeze_queue(d->blkq); + blk_mq_quiesce_queue(d->blkq); blk_mq_unquiesce_queue(d->blkq); - blk_mq_unfreeze_queue(d->blkq); + blk_mq_unfreeze_queue(d->blkq, memflags); } if (d->gd) diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 110f9aca2667..a81ade622a01 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -746,6 +746,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) unsigned char *p; int sect, nsect; unsigned long flags; + unsigned int memflags; int ret; if (type) { @@ -758,7 +759,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) } q = unit[drive].disk[type]->queue; - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); local_irq_save(flags); @@ -817,7 +818,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) ret = FormatError ? -EIO : 0; out: blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); return ret; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1ec7417c7f00..c05fe27a96b6 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -586,6 +586,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, { struct file *file = fget(arg); struct file *old_file; + unsigned int memflags; int error; bool partscan; bool is_loop; @@ -623,14 +624,14 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, /* and ... switch */ disk_force_media_change(lo->lo_disk); - blk_mq_freeze_queue(lo->lo_queue); + memflags = blk_mq_freeze_queue(lo->lo_queue); mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping); mapping_set_gfp_mask(file->f_mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); loop_update_dio(lo); - blk_mq_unfreeze_queue(lo->lo_queue); + blk_mq_unfreeze_queue(lo->lo_queue, memflags); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; loop_global_unlock(lo, is_loop); @@ -1255,6 +1256,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; bool partscan = false; bool size_changed = false; + unsigned int memflags; err = mutex_lock_killable(&lo->lo_mutex); if (err) @@ -1272,7 +1274,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) } /* I/O needs to be drained before changing lo_offset or lo_sizelimit */ - blk_mq_freeze_queue(lo->lo_queue); + memflags = blk_mq_freeze_queue(lo->lo_queue); err = loop_set_status_from_info(lo, info); if (err) @@ -1281,8 +1283,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) partscan = !(lo->lo_flags & LO_FLAGS_PARTSCAN) && (info->lo_flags & LO_FLAGS_PARTSCAN); - lo->lo_flags &= ~(LOOP_SET_STATUS_SETTABLE_FLAGS | - LOOP_SET_STATUS_CLEARABLE_FLAGS); + lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS; lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS); if (size_changed) { @@ -1295,7 +1296,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) loop_update_dio(lo); out_unfreeze: - blk_mq_unfreeze_queue(lo->lo_queue); + blk_mq_unfreeze_queue(lo->lo_queue, memflags); if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); out_unlock: @@ -1447,6 +1448,7 @@ static int loop_set_capacity(struct loop_device *lo) static int loop_set_dio(struct loop_device *lo, unsigned long arg) { bool use_dio = !!arg; + unsigned int memflags; if (lo->lo_state != Lo_bound) return -ENXIO; @@ -1460,18 +1462,19 @@ static int loop_set_dio(struct loop_device *lo, unsigned long arg) vfs_fsync(lo->lo_backing_file, 0); } - blk_mq_freeze_queue(lo->lo_queue); + memflags = blk_mq_freeze_queue(lo->lo_queue); if (use_dio) lo->lo_flags |= LO_FLAGS_DIRECT_IO; else lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; - blk_mq_unfreeze_queue(lo->lo_queue); + blk_mq_unfreeze_queue(lo->lo_queue, memflags); return 0; } static int loop_set_block_size(struct loop_device *lo, unsigned long arg) { struct queue_limits lim; + unsigned int memflags; int err = 0; if (lo->lo_state != Lo_bound) @@ -1486,10 +1489,10 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg) lim = queue_limits_start_update(lo->lo_queue); loop_update_limits(lo, &lim, arg); - blk_mq_freeze_queue(lo->lo_queue); + memflags = blk_mq_freeze_queue(lo->lo_queue); err = queue_limits_commit_update(lo->lo_queue, &lim); loop_update_dio(lo); - blk_mq_unfreeze_queue(lo->lo_queue); + blk_mq_unfreeze_queue(lo->lo_queue, memflags); return err; } diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index b63a0f29a54a..7bdc7eb808ea 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1234,6 +1234,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, struct socket *sock; struct nbd_sock **socks; struct nbd_sock *nsock; + unsigned int memflags; int err; /* Arg will be cast to int, check it to avoid overflow */ @@ -1247,7 +1248,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, * We need to make sure we don't get any errant requests while we're * reallocating the ->socks array. */ - blk_mq_freeze_queue(nbd->disk->queue); + memflags = blk_mq_freeze_queue(nbd->disk->queue); if (!netlink && !nbd->task_setup && !test_bit(NBD_RT_BOUND, &config->runtime_flags)) @@ -1288,12 +1289,12 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg, INIT_WORK(&nsock->work, nbd_pending_cmd_work); socks[config->num_connections++] = nsock; atomic_inc(&config->live_connections); - blk_mq_unfreeze_queue(nbd->disk->queue); + blk_mq_unfreeze_queue(nbd->disk->queue, memflags); return 0; put_socket: - blk_mq_unfreeze_queue(nbd->disk->queue); + blk_mq_unfreeze_queue(nbd->disk->queue, memflags); sockfd_put(sock); return err; } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 5b393e4a1ddf..faafd7ff43d6 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -7281,9 +7281,10 @@ static ssize_t do_rbd_remove(const char *buf, size_t count) * Prevent new IO from being queued and wait for existing * IO to complete/fail. */ - blk_mq_freeze_queue(rbd_dev->disk->queue); + unsigned int memflags = blk_mq_freeze_queue(rbd_dev->disk->queue); + blk_mark_disk_dead(rbd_dev->disk); - blk_mq_unfreeze_queue(rbd_dev->disk->queue); + blk_mq_unfreeze_queue(rbd_dev->disk->queue, memflags); } del_gendisk(rbd_dev->disk); diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index e4d1e7284dae..282f81616a78 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -1113,6 +1113,7 @@ static void vdc_requeue_inflight(struct vdc_port *port) static void vdc_queue_drain(struct vdc_port *port) { struct request_queue *q = port->disk->queue; + unsigned int memflags; /* * Mark the queue as draining, then freeze/quiesce to ensure @@ -1121,13 +1122,13 @@ static void vdc_queue_drain(struct vdc_port *port) port->drain = 1; spin_unlock_irq(&port->vio.lock); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); spin_lock_irq(&port->vio.lock); port->drain = 0; blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } static void vdc_ldc_reset_timer_work(struct work_struct *work) diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 9914153b365b..3aedcb5add61 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -840,6 +840,7 @@ static int grab_drive(struct floppy_state *fs, enum swim_state state, static void release_drive(struct floppy_state *fs) { struct request_queue *q = disks[fs->index]->queue; + unsigned int memflags; unsigned long flags; swim3_dbg("%s", "-> release drive\n"); @@ -848,10 +849,10 @@ static void release_drive(struct floppy_state *fs) fs->state = idle; spin_unlock_irqrestore(&swim3_lock, flags); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue(q); blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); } static int fd_eject(struct floppy_state *fs) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index bfbe391c20fe..6a61ec35f426 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -1583,11 +1583,12 @@ static int virtblk_freeze_priv(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; struct request_queue *q = vblk->disk->queue; + unsigned int memflags; /* Ensure no requests in virtqueues before deleting vqs. */ - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); blk_mq_quiesce_queue_nowait(q); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); /* Ensure we don't receive any more interrupts */ virtio_reset_device(vdev); diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index 2b79952f3628..091ffe3e1495 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -1320,6 +1320,10 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev, if (opcode == 0xfc01) btintel_pcie_inject_cmd_complete(hdev, opcode); } + /* Firmware raises alive interrupt on HCI_OP_RESET */ + if (opcode == HCI_OP_RESET) + data->gp0_received = false; + hdev->stat.cmd_tx++; break; case HCI_ACLDATA_PKT: @@ -1357,7 +1361,6 @@ static int btintel_pcie_send_frame(struct hci_dev *hdev, opcode, btintel_pcie_alivectxt_state2str(old_ctxt), btintel_pcie_alivectxt_state2str(data->alive_intr_ctxt)); if (opcode == HCI_OP_RESET) { - data->gp0_received = false; ret = wait_event_timeout(data->gp0_wait_q, data->gp0_received, msecs_to_jiffies(BTINTEL_DEFAULT_INTR_TIMEOUT_MS)); diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c index 1230045d78a5..aa5ec1d444a9 100644 --- a/drivers/bluetooth/btnxpuart.c +++ b/drivers/bluetooth/btnxpuart.c @@ -1381,13 +1381,12 @@ static void btnxpuart_tx_work(struct work_struct *work) while ((skb = nxp_dequeue(nxpdev))) { len = serdev_device_write_buf(serdev, skb->data, skb->len); - serdev_device_wait_until_sent(serdev, 0); hdev->stat.byte_tx += len; skb_pull(skb, len); if (skb->len > 0) { skb_queue_head(&nxpdev->txq, skb); - break; + continue; } switch (hci_skb_pkt_type(skb)) { diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 9aa018d4f6f5..90966dfbd278 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -899,11 +899,6 @@ static void btusb_reset(struct hci_dev *hdev) struct btusb_data *data; int err; - if (hdev->reset) { - hdev->reset(hdev); - return; - } - data = hci_get_drvdata(hdev); /* This is not an unbalanced PM reference since the device will reset */ err = usb_autopm_get_interface(data->intf); @@ -2639,8 +2634,15 @@ static void btusb_mtk_claim_iso_intf(struct btusb_data *data) struct btmtk_data *btmtk_data = hci_get_priv(data->hdev); int err; + /* + * The function usb_driver_claim_interface() is documented to need + * locks held if it's not called from a probe routine. The code here + * is called from the hci_power_on workqueue, so grab the lock. + */ + device_lock(&btmtk_data->isopkt_intf->dev); err = usb_driver_claim_interface(&btusb_driver, btmtk_data->isopkt_intf, data); + device_unlock(&btmtk_data->isopkt_intf->dev); if (err < 0) { btmtk_data->isopkt_intf = NULL; bt_dev_err(data->hdev, "Failed to claim iso interface"); diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index 6276551d7968..1e57ebfb7622 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -657,7 +657,7 @@ static void moxtet_irq_print_chip(struct irq_data *d, struct seq_file *p) id = moxtet->modules[pos->idx]; - seq_printf(p, " moxtet-%s.%i#%i", mox_module_name(id), pos->idx, + seq_printf(p, "moxtet-%s.%i#%i", mox_module_name(id), pos->idx, pos->bit); } diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 51745ed1bbab..b163e043c687 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -3612,7 +3612,7 @@ static int cdrom_sysctl_handler(const struct ctl_table *ctl, int write, } /* Place files in /proc/sys/dev/cdrom */ -static struct ctl_table cdrom_table[] = { +static const struct ctl_table cdrom_table[] = { { .procname = "info", .data = &cdrom_sysctl_settings.info, diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 48fe96ab4649..e110857824fc 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -724,7 +724,7 @@ static int hpet_is_known(struct hpet_data *hdp) return 0; } -static struct ctl_table hpet_table[] = { +static const struct ctl_table hpet_table[] = { { .procname = "max-user-freq", .data = &hpet_max_freq, diff --git a/drivers/char/ipmi/ipmi_poweroff.c b/drivers/char/ipmi/ipmi_poweroff.c index 05f17e3e6207..e63c316d8aaa 100644 --- a/drivers/char/ipmi/ipmi_poweroff.c +++ b/drivers/char/ipmi/ipmi_poweroff.c @@ -650,7 +650,7 @@ static struct ipmi_smi_watcher smi_watcher = { #ifdef CONFIG_PROC_FS #include <linux/sysctl.h> -static struct ctl_table ipmi_table[] = { +static const struct ctl_table ipmi_table[] = { { .procname = "poweroff_powercycle", .data = &poweroff_powercycle, .maxlen = sizeof(poweroff_powercycle), diff --git a/drivers/char/random.c b/drivers/char/random.c index 23ee76bbb4aa..2581186fa61b 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1665,7 +1665,7 @@ static int proc_do_rointvec(const struct ctl_table *table, int write, void *buf, return write ? 0 : proc_dointvec(table, 0, buf, lenp, ppos); } -static struct ctl_table random_table[] = { +static const struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 704e84d00639..9e46960f6a86 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -18,6 +18,7 @@ config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM config ARM_AIROHA_SOC_CPUFREQ tristate "Airoha EN7581 SoC CPUFreq support" depends on ARCH_AIROHA || COMPILE_TEST + depends on OF select PM_OPP default ARCH_AIROHA help diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 302df42d6887..463b69a2dff5 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -909,11 +909,6 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy) if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency) pr_warn(FW_WARN "P-state 0 is not max freq\n"); - if (acpi_cpufreq_driver.set_boost) { - set_boost(policy, acpi_cpufreq_driver.boost_enabled); - policy->boost_enabled = acpi_cpufreq_driver.boost_enabled; - } - return result; err_unreg: diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index dd9b8d6993d6..313550fa62d4 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -699,7 +699,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, if (min_perf < lowest_nonlinear_perf) min_perf = lowest_nonlinear_perf; - max_perf = cap_perf; + max_perf = cpudata->max_limit_perf; if (max_perf < min_perf) max_perf = min_perf; @@ -747,7 +747,6 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state) guard(mutex)(&amd_pstate_driver_lock); ret = amd_pstate_cpu_boost_update(policy, state); - policy->boost_enabled = !ret ? state : false; refresh_frequency_limits(policy); return ret; @@ -822,25 +821,28 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata) static void amd_pstate_update_limits(unsigned int cpu) { - struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); + struct cpufreq_policy *policy = NULL; struct amd_cpudata *cpudata; u32 prev_high = 0, cur_high = 0; int ret; bool highest_perf_changed = false; + if (!amd_pstate_prefcore) + return; + + policy = cpufreq_cpu_get(cpu); if (!policy) return; cpudata = policy->driver_data; - if (!amd_pstate_prefcore) - return; - guard(mutex)(&amd_pstate_driver_lock); ret = amd_get_highest_perf(cpu, &cur_high); - if (ret) - goto free_cpufreq_put; + if (ret) { + cpufreq_cpu_put(policy); + return; + } prev_high = READ_ONCE(cpudata->prefcore_ranking); highest_perf_changed = (prev_high != cur_high); @@ -850,8 +852,6 @@ static void amd_pstate_update_limits(unsigned int cpu) if (cur_high < CPPC_MAX_PERF) sched_set_itmt_core_prio((int)cur_high, cpu); } - -free_cpufreq_put: cpufreq_cpu_put(policy); if (!highest_perf_changed) diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 2486a6c5256a..8f512448382f 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -611,7 +611,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * Section 8.4.7.1.1.5 of ACPI 6.1 spec) */ policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); - policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); + policy->max = cppc_perf_to_khz(caps, policy->boost_enabled ? + caps->highest_perf : caps->nominal_perf); /* * Set cpuinfo.min_freq to Lowest to make the full range of performance @@ -619,7 +620,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * nonlinear perf */ policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf); - policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf); + policy->cpuinfo.max_freq = policy->max; policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); policy->shared_type = cpu_data->shared_type; diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 1076e37a18ad..30ffbddc7ece 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1410,10 +1410,6 @@ static int cpufreq_online(unsigned int cpu) goto out_free_policy; } - /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ - if (cpufreq_boost_enabled() && policy_has_boost_freq(policy)) - policy->boost_enabled = true; - /* * The initialization has succeeded and the policy is online. * If there is a problem with its frequency table, take it @@ -1476,6 +1472,10 @@ static int cpufreq_online(unsigned int cpu) blocking_notifier_call_chain(&cpufreq_policy_notifier_list, CPUFREQ_CREATE_POLICY, policy); + } else { + ret = freq_qos_update_request(policy->max_freq_req, policy->max); + if (ret < 0) + goto out_destroy_policy; } if (cpufreq_driver->get && has_target()) { @@ -1570,6 +1570,19 @@ static int cpufreq_online(unsigned int cpu) if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); + /* Let the per-policy boost flag mirror the cpufreq_driver boost during init */ + if (cpufreq_driver->set_boost && + policy->boost_enabled != cpufreq_boost_enabled()) { + policy->boost_enabled = cpufreq_boost_enabled(); + ret = cpufreq_driver->set_boost(policy, policy->boost_enabled); + if (ret) { + /* If the set_boost fails, the online operation is not affected */ + pr_info("%s: CPU%d: Cannot %s BOOST\n", __func__, policy->cpu, + policy->boost_enabled ? "enable" : "disable"); + policy->boost_enabled = !policy->boost_enabled; + } + } + pr_debug("initialization complete\n"); return 0; diff --git a/drivers/cpufreq/s3c64xx-cpufreq.c b/drivers/cpufreq/s3c64xx-cpufreq.c index c6bdfc308e99..9cef71528076 100644 --- a/drivers/cpufreq/s3c64xx-cpufreq.c +++ b/drivers/cpufreq/s3c64xx-cpufreq.c @@ -24,6 +24,7 @@ struct s3c64xx_dvfs { unsigned int vddarm_max; }; +#ifdef CONFIG_REGULATOR static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = { [0] = { 1000000, 1150000 }, [1] = { 1050000, 1150000 }, @@ -31,6 +32,7 @@ static struct s3c64xx_dvfs s3c64xx_dvfs_table[] = { [3] = { 1200000, 1350000 }, [4] = { 1300000, 1350000 }, }; +#endif static struct cpufreq_frequency_table s3c64xx_freq_table[] = { { 0, 0, 66000 }, @@ -51,15 +53,16 @@ static struct cpufreq_frequency_table s3c64xx_freq_table[] = { static int s3c64xx_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index) { - struct s3c64xx_dvfs *dvfs; - unsigned int old_freq, new_freq; + unsigned int new_freq = s3c64xx_freq_table[index].frequency; int ret; +#ifdef CONFIG_REGULATOR + struct s3c64xx_dvfs *dvfs; + unsigned int old_freq; + old_freq = clk_get_rate(policy->clk) / 1000; - new_freq = s3c64xx_freq_table[index].frequency; dvfs = &s3c64xx_dvfs_table[s3c64xx_freq_table[index].driver_data]; -#ifdef CONFIG_REGULATOR if (vddarm && new_freq > old_freq) { ret = regulator_set_voltage(vddarm, dvfs->vddarm_min, diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index 173ddcac540a..8fe5e1b47ef9 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/drivers/cpuidle/governors/teo.c @@ -41,11 +41,7 @@ * idle state 2, the third bin spans from the target residency of idle state 2 * up to, but not including, the target residency of idle state 3 and so on. * The last bin spans from the target residency of the deepest idle state - * supplied by the driver to the scheduler tick period length or to infinity if - * the tick period length is less than the target residency of that state. In - * the latter case, the governor also counts events with the measured idle - * duration between the tick period length and the target residency of the - * deepest idle state. + * supplied by the driver to infinity. * * Two metrics called "hits" and "intercepts" are associated with each bin. * They are updated every time before selecting an idle state for the given CPU @@ -60,6 +56,10 @@ * into by the sleep length (these events are also referred to as "intercepts" * below). * + * The governor also counts "intercepts" with the measured idle duration below + * the tick period length and uses this information when deciding whether or not + * to stop the scheduler tick. + * * In order to select an idle state for a CPU, the governor takes the following * steps (modulo the possible latency constraint that must be taken into account * too): @@ -106,6 +106,12 @@ #include "gov.h" /* + * Idle state exit latency threshold used for deciding whether or not to check + * the time till the closest expected timer event. + */ +#define LATENCY_THRESHOLD_NS (RESIDENCY_THRESHOLD_NS / 2) + +/* * The PULSE value is added to metrics when they grow and the DECAY_SHIFT value * is used for decreasing metrics on a regular basis. */ @@ -124,18 +130,20 @@ struct teo_bin { /** * struct teo_cpu - CPU data used by the TEO cpuidle governor. - * @time_span_ns: Time between idle state selection and post-wakeup update. * @sleep_length_ns: Time till the closest timer event (at the selection time). * @state_bins: Idle state data bins for this CPU. * @total: Grand total of the "intercepts" and "hits" metrics for all bins. - * @tick_hits: Number of "hits" after TICK_NSEC. + * @tick_intercepts: "Intercepts" before TICK_NSEC. + * @short_idles: Wakeups after short idle periods. + * @artificial_wakeup: Set if the wakeup has been triggered by a safety net. */ struct teo_cpu { - s64 time_span_ns; s64 sleep_length_ns; struct teo_bin state_bins[CPUIDLE_STATE_MAX]; unsigned int total; - unsigned int tick_hits; + unsigned int tick_intercepts; + unsigned int short_idles; + bool artificial_wakeup; }; static DEFINE_PER_CPU(struct teo_cpu, teo_cpus); @@ -152,23 +160,17 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) s64 target_residency_ns; u64 measured_ns; - if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) { + cpu_data->short_idles -= cpu_data->short_idles >> DECAY_SHIFT; + + if (cpu_data->artificial_wakeup) { /* - * One of the safety nets has triggered or the wakeup was close - * enough to the closest timer event expected at the idle state - * selection time to be discarded. + * If one of the safety nets has triggered, assume that this + * might have been a long sleep. */ measured_ns = U64_MAX; } else { u64 lat_ns = drv->states[dev->last_state_idx].exit_latency_ns; - /* - * The computations below are to determine whether or not the - * (saved) time till the next timer event and the measured idle - * duration fall into the same "bin", so use last_residency_ns - * for that instead of time_span_ns which includes the cpuidle - * overhead. - */ measured_ns = dev->last_residency_ns; /* * The delay between the wakeup and the first instruction @@ -176,14 +178,16 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) * time, so take 1/2 of the exit latency as a very rough * approximation of the average of it. */ - if (measured_ns >= lat_ns) + if (measured_ns >= lat_ns) { measured_ns -= lat_ns / 2; - else + if (measured_ns < RESIDENCY_THRESHOLD_NS) + cpu_data->short_idles += PULSE; + } else { measured_ns /= 2; + cpu_data->short_idles += PULSE; + } } - cpu_data->total = 0; - /* * Decay the "hits" and "intercepts" metrics for all of the bins and * find the bins that the sleep length and the measured idle duration @@ -195,8 +199,6 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) bin->hits -= bin->hits >> DECAY_SHIFT; bin->intercepts -= bin->intercepts >> DECAY_SHIFT; - cpu_data->total += bin->hits + bin->intercepts; - target_residency_ns = drv->states[i].target_residency_ns; if (target_residency_ns <= cpu_data->sleep_length_ns) { @@ -206,38 +208,22 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) } } - /* - * If the deepest state's target residency is below the tick length, - * make a record of it to help teo_select() decide whether or not - * to stop the tick. This effectively adds an extra hits-only bin - * beyond the last state-related one. - */ - if (target_residency_ns < TICK_NSEC) { - cpu_data->tick_hits -= cpu_data->tick_hits >> DECAY_SHIFT; - - cpu_data->total += cpu_data->tick_hits; - - if (TICK_NSEC <= cpu_data->sleep_length_ns) { - idx_timer = drv->state_count; - if (TICK_NSEC <= measured_ns) { - cpu_data->tick_hits += PULSE; - goto end; - } - } - } - + cpu_data->tick_intercepts -= cpu_data->tick_intercepts >> DECAY_SHIFT; /* * If the measured idle duration falls into the same bin as the sleep * length, this is a "hit", so update the "hits" metric for that bin. * Otherwise, update the "intercepts" metric for the bin fallen into by * the measured idle duration. */ - if (idx_timer == idx_duration) + if (idx_timer == idx_duration) { cpu_data->state_bins[idx_timer].hits += PULSE; - else + } else { cpu_data->state_bins[idx_duration].intercepts += PULSE; + if (TICK_NSEC <= measured_ns) + cpu_data->tick_intercepts += PULSE; + } -end: + cpu_data->total -= cpu_data->total >> DECAY_SHIFT; cpu_data->total += PULSE; } @@ -285,14 +271,12 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); s64 latency_req = cpuidle_governor_latency_req(dev->cpu); ktime_t delta_tick = TICK_NSEC / 2; - unsigned int tick_intercept_sum = 0; unsigned int idx_intercept_sum = 0; unsigned int intercept_sum = 0; unsigned int idx_hit_sum = 0; unsigned int hit_sum = 0; int constraint_idx = 0; int idx0 = 0, idx = -1; - int prev_intercept_idx; s64 duration_ns; int i; @@ -301,10 +285,14 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, dev->last_state_idx = -1; } - cpu_data->time_span_ns = local_clock(); /* - * Set the expected sleep length to infinity in case of an early - * return. + * Set the sleep length to infinity in case the invocation of + * tick_nohz_get_sleep_length() below is skipped, in which case it won't + * be known whether or not the subsequent wakeup is caused by a timer. + * It is generally fine to count the wakeup as an intercept then, except + * for the cases when the CPU is mostly woken up by timers and there may + * be opportunities to ask for a deeper idle state when no imminent + * timers are scheduled which may be missed. */ cpu_data->sleep_length_ns = KTIME_MAX; @@ -360,17 +348,13 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, goto end; } - tick_intercept_sum = intercept_sum + - cpu_data->state_bins[drv->state_count-1].intercepts; - /* * If the sum of the intercepts metric for all of the idle states * shallower than the current candidate one (idx) is greater than the * sum of the intercepts and hits metrics for the candidate state and - * all of the deeper states a shallower idle state is likely to be a + * all of the deeper states, a shallower idle state is likely to be a * better choice. */ - prev_intercept_idx = idx; if (2 * idx_intercept_sum > cpu_data->total - idx_hit_sum) { int first_suitable_idx = idx; @@ -396,41 +380,38 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * first enabled state that is deep enough. */ if (teo_state_ok(i, drv) && - !dev->states_usage[i].disable) + !dev->states_usage[i].disable) { idx = i; - else - idx = first_suitable_idx; - + break; + } + idx = first_suitable_idx; break; } if (dev->states_usage[i].disable) continue; - if (!teo_state_ok(i, drv)) { + if (teo_state_ok(i, drv)) { /* - * The current state is too shallow, but if an - * alternative candidate state has been found, - * it may still turn out to be a better choice. + * The current state is deep enough, but still + * there may be a better one. */ - if (first_suitable_idx != idx) - continue; - - break; + first_suitable_idx = i; + continue; } - first_suitable_idx = i; + /* + * The current state is too shallow, so if no suitable + * states other than the initial candidate have been + * found, give up (the remaining states to check are + * shallower still), but otherwise the first suitable + * state other than the initial candidate may turn out + * to be preferable. + */ + if (first_suitable_idx == idx) + break; } } - if (!idx && prev_intercept_idx) { - /* - * We have to query the sleep length here otherwise we don't - * know after wakeup if our guess was correct. - */ - duration_ns = tick_nohz_get_sleep_length(&delta_tick); - cpu_data->sleep_length_ns = duration_ns; - goto out_tick; - } /* * If there is a latency constraint, it may be necessary to select an @@ -440,24 +421,39 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, idx = constraint_idx; /* - * Skip the timers check if state 0 is the current candidate one, - * because an immediate non-timer wakeup is expected in that case. + * If either the candidate state is state 0 or its target residency is + * low enough, there is basically nothing more to do, but if the sleep + * length is not updated, the subsequent wakeup will be counted as an + * "intercept" which may be problematic in the cases when timer wakeups + * are dominant. Namely, it may effectively prevent deeper idle states + * from being selected at one point even if no imminent timers are + * scheduled. + * + * However, frequent timers in the RESIDENCY_THRESHOLD_NS range on one + * CPU are unlikely (user space has a default 50 us slack value for + * hrtimers and there are relatively few timers with a lower deadline + * value in the kernel), and even if they did happen, the potential + * benefit from using a deep idle state in that case would be + * questionable anyway for latency reasons. Thus if the measured idle + * duration falls into that range in the majority of cases, assume + * non-timer wakeups to be dominant and skip updating the sleep length + * to reduce latency. + * + * Also, if the latency constraint is sufficiently low, it will force + * shallow idle states regardless of the wakeup type, so the sleep + * length need not be known in that case. */ - if (!idx) - goto out_tick; - - /* - * If state 0 is a polling one, check if the target residency of - * the current candidate state is low enough and skip the timers - * check in that case too. - */ - if ((drv->states[0].flags & CPUIDLE_FLAG_POLLING) && - drv->states[idx].target_residency_ns < RESIDENCY_THRESHOLD_NS) + if ((!idx || drv->states[idx].target_residency_ns < RESIDENCY_THRESHOLD_NS) && + (2 * cpu_data->short_idles >= cpu_data->total || + latency_req < LATENCY_THRESHOLD_NS)) goto out_tick; duration_ns = tick_nohz_get_sleep_length(&delta_tick); cpu_data->sleep_length_ns = duration_ns; + if (!idx) + goto out_tick; + /* * If the closest expected timer is before the target residency of the * candidate state, a shallower one needs to be found. @@ -474,7 +470,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, * total wakeup events, do not stop the tick. */ if (drv->states[idx].target_residency_ns < TICK_NSEC && - tick_intercept_sum > cpu_data->total / 2 + cpu_data->total / 8) + cpu_data->tick_intercepts > cpu_data->total / 2 + cpu_data->total / 8) duration_ns = TICK_NSEC / 2; end: @@ -511,17 +507,16 @@ static void teo_reflect(struct cpuidle_device *dev, int state) struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu); dev->last_state_idx = state; - /* - * If the wakeup was not "natural", but triggered by one of the safety - * nets, assume that the CPU might have been idle for the entire sleep - * length time. - */ if (dev->poll_time_limit || (tick_nohz_idle_got_tick() && cpu_data->sleep_length_ns > TICK_NSEC)) { + /* + * The wakeup was not "genuine", but triggered by one of the + * safety nets. + */ dev->poll_time_limit = false; - cpu_data->time_span_ns = cpu_data->sleep_length_ns; + cpu_data->artificial_wakeup = true; } else { - cpu_data->time_span_ns = local_clock() - cpu_data->time_span_ns; + cpu_data->artificial_wakeup = false; } } diff --git a/drivers/crypto/ccp/sp-dev.c b/drivers/crypto/ccp/sp-dev.c index 7eb3e4668286..3467f6db4f50 100644 --- a/drivers/crypto/ccp/sp-dev.c +++ b/drivers/crypto/ccp/sp-dev.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/ccp.h> +#include "sev-dev.h" #include "ccp-dev.h" #include "sp-dev.h" @@ -253,8 +254,12 @@ unlock: static int __init sp_mod_init(void) { #ifdef CONFIG_X86 + static bool initialized; int ret; + if (initialized) + return 0; + ret = sp_pci_init(); if (ret) return ret; @@ -263,6 +268,8 @@ static int __init sp_mod_init(void) psp_pci_init(); #endif + initialized = true; + return 0; #endif @@ -279,6 +286,13 @@ static int __init sp_mod_init(void) return -ENODEV; } +#if IS_BUILTIN(CONFIG_KVM_AMD) && IS_ENABLED(CONFIG_KVM_AMD_SEV) +int __init sev_module_init(void) +{ + return sp_mod_init(); +} +#endif + static void __exit sp_mod_exit(void) { #ifdef CONFIG_X86 diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index a3c57f96138a..013b869b66cb 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -291,11 +291,11 @@ static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm) return devm_add_action_or_reset(host, disable_hdm, cxlhdm); } -int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info) { - struct pci_dev *pdev = to_pci_dev(dev); - struct cxl_dev_state *cxlds = pci_get_drvdata(pdev); + struct pci_dev *pdev = to_pci_dev(cxlds->dev); + struct device *dev = cxlds->dev; int hdm_count, rc, i, ranges = 0; int d = cxlds->cxl_dvsec; u16 cap, ctrl; diff --git a/drivers/cxl/core/regs.c b/drivers/cxl/core/regs.c index 59cb35b40c7e..117c2e94c761 100644 --- a/drivers/cxl/core/regs.c +++ b/drivers/cxl/core/regs.c @@ -289,21 +289,17 @@ static bool cxl_decode_regblock(struct pci_dev *pdev, u32 reg_lo, u32 reg_hi, return true; } -/** - * cxl_find_regblock_instance() - Locate a register block by type / index - * @pdev: The CXL PCI device to enumerate. - * @type: Register Block Indicator id - * @map: Enumeration output, clobbered on error - * @index: Index into which particular instance of a regblock wanted in the - * order found in register locator DVSEC. - * - * Return: 0 if register block enumerated, negative error code otherwise +/* + * __cxl_find_regblock_instance() - Locate a register block or count instances by type / index + * Use CXL_INSTANCES_COUNT for @index if counting instances. * - * A CXL DVSEC may point to one or more register blocks, search for them - * by @type and @index. + * __cxl_find_regblock_instance() may return: + * 0 - if register block enumerated. + * >= 0 - if counting instances. + * < 0 - error code otherwise. */ -int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, - struct cxl_register_map *map, int index) +static int __cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, + struct cxl_register_map *map, int index) { u32 regloc_size, regblocks; int instance = 0; @@ -342,8 +338,30 @@ int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, } map->resource = CXL_RESOURCE_NONE; + if (index == CXL_INSTANCES_COUNT) + return instance; + return -ENODEV; } + +/** + * cxl_find_regblock_instance() - Locate a register block by type / index + * @pdev: The CXL PCI device to enumerate. + * @type: Register Block Indicator id + * @map: Enumeration output, clobbered on error + * @index: Index into which particular instance of a regblock wanted in the + * order found in register locator DVSEC. + * + * Return: 0 if register block enumerated, negative error code otherwise + * + * A CXL DVSEC may point to one or more register blocks, search for them + * by @type and @index. + */ +int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, + struct cxl_register_map *map, unsigned int index) +{ + return __cxl_find_regblock_instance(pdev, type, map, index); +} EXPORT_SYMBOL_NS_GPL(cxl_find_regblock_instance, "CXL"); /** @@ -360,7 +378,7 @@ EXPORT_SYMBOL_NS_GPL(cxl_find_regblock_instance, "CXL"); int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type, struct cxl_register_map *map) { - return cxl_find_regblock_instance(pdev, type, map, 0); + return __cxl_find_regblock_instance(pdev, type, map, 0); } EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, "CXL"); @@ -371,19 +389,13 @@ EXPORT_SYMBOL_NS_GPL(cxl_find_regblock, "CXL"); * * Some regblocks may be repeated. Count how many instances. * - * Return: count of matching regblocks. + * Return: non-negative count of matching regblocks, negative error code otherwise. */ int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type) { struct cxl_register_map map; - int rc, count = 0; - while (1) { - rc = cxl_find_regblock_instance(pdev, type, &map, count); - if (rc) - return count; - count++; - } + return __cxl_find_regblock_instance(pdev, type, &map, CXL_INSTANCES_COUNT); } EXPORT_SYMBOL_NS_GPL(cxl_count_regblock, "CXL"); diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h index 8389a94adb1a..cea706b683b5 100644 --- a/drivers/cxl/core/trace.h +++ b/drivers/cxl/core/trace.h @@ -166,11 +166,13 @@ TRACE_EVENT(cxl_overflow, #define CXL_EVENT_RECORD_FLAG_MAINT_NEEDED BIT(3) #define CXL_EVENT_RECORD_FLAG_PERF_DEGRADED BIT(4) #define CXL_EVENT_RECORD_FLAG_HW_REPLACE BIT(5) +#define CXL_EVENT_RECORD_FLAG_MAINT_OP_SUB_CLASS_VALID BIT(6) #define show_hdr_flags(flags) __print_flags(flags, " | ", \ { CXL_EVENT_RECORD_FLAG_PERMANENT, "PERMANENT_CONDITION" }, \ { CXL_EVENT_RECORD_FLAG_MAINT_NEEDED, "MAINTENANCE_NEEDED" }, \ { CXL_EVENT_RECORD_FLAG_PERF_DEGRADED, "PERFORMANCE_DEGRADED" }, \ - { CXL_EVENT_RECORD_FLAG_HW_REPLACE, "HARDWARE_REPLACEMENT_NEEDED" } \ + { CXL_EVENT_RECORD_FLAG_HW_REPLACE, "HARDWARE_REPLACEMENT_NEEDED" }, \ + { CXL_EVENT_RECORD_FLAG_MAINT_OP_SUB_CLASS_VALID, "MAINT_OP_SUB_CLASS_VALID" } \ ) /* @@ -197,7 +199,8 @@ TRACE_EVENT(cxl_overflow, __field(u16, hdr_related_handle) \ __field(u64, hdr_timestamp) \ __field(u8, hdr_length) \ - __field(u8, hdr_maint_op_class) + __field(u8, hdr_maint_op_class) \ + __field(u8, hdr_maint_op_sub_class) #define CXL_EVT_TP_fast_assign(cxlmd, l, hdr) \ __assign_str(memdev); \ @@ -209,17 +212,19 @@ TRACE_EVENT(cxl_overflow, __entry->hdr_handle = le16_to_cpu((hdr).handle); \ __entry->hdr_related_handle = le16_to_cpu((hdr).related_handle); \ __entry->hdr_timestamp = le64_to_cpu((hdr).timestamp); \ - __entry->hdr_maint_op_class = (hdr).maint_op_class + __entry->hdr_maint_op_class = (hdr).maint_op_class; \ + __entry->hdr_maint_op_sub_class = (hdr).maint_op_sub_class #define CXL_EVT_TP_printk(fmt, ...) \ TP_printk("memdev=%s host=%s serial=%lld log=%s : time=%llu uuid=%pUb " \ "len=%d flags='%s' handle=%x related_handle=%x " \ - "maint_op_class=%u : " fmt, \ + "maint_op_class=%u maint_op_sub_class=%u : " fmt, \ __get_str(memdev), __get_str(host), __entry->serial, \ cxl_event_log_type_str(__entry->log), \ __entry->hdr_timestamp, &__entry->hdr_uuid, __entry->hdr_length,\ show_hdr_flags(__entry->hdr_flags), __entry->hdr_handle, \ __entry->hdr_related_handle, __entry->hdr_maint_op_class, \ + __entry->hdr_maint_op_sub_class, \ ##__VA_ARGS__) TRACE_EVENT(cxl_generic_event, @@ -264,8 +269,30 @@ TRACE_EVENT(cxl_generic_event, ) /* + * Component ID Format + * CXL 3.1 section 8.2.9.2.1; Table 8-44 + */ +#define CXL_PLDM_COMPONENT_ID_ENTITY_VALID BIT(0) +#define CXL_PLDM_COMPONENT_ID_RES_VALID BIT(1) + +#define show_comp_id_pldm_flags(flags) __print_flags(flags, " | ", \ + { CXL_PLDM_COMPONENT_ID_ENTITY_VALID, "PLDM Entity ID" }, \ + { CXL_PLDM_COMPONENT_ID_RES_VALID, "Resource ID" } \ +) + +#define show_pldm_entity_id(flags, valid_comp_id, valid_id_format, comp_id) \ + (flags & valid_comp_id && flags & valid_id_format) ? \ + (comp_id[0] & CXL_PLDM_COMPONENT_ID_ENTITY_VALID) ? \ + __print_hex(&comp_id[1], 6) : "0x00" : "0x00" + +#define show_pldm_resource_id(flags, valid_comp_id, valid_id_format, comp_id) \ + (flags & valid_comp_id && flags & valid_id_format) ? \ + (comp_id[0] & CXL_PLDM_COMPONENT_ID_RES_VALID) ? \ + __print_hex(&comp_id[7], 4) : "0x00" : "0x00" + +/* * General Media Event Record - GMER - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45 */ #define CXL_GMER_EVT_DESC_UNCORECTABLE_EVENT BIT(0) #define CXL_GMER_EVT_DESC_THRESHOLD_EVENT BIT(1) @@ -279,10 +306,18 @@ TRACE_EVENT(cxl_generic_event, #define CXL_GMER_MEM_EVT_TYPE_ECC_ERROR 0x00 #define CXL_GMER_MEM_EVT_TYPE_INV_ADDR 0x01 #define CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x02 -#define show_gmer_mem_event_type(type) __print_symbolic(type, \ - { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ - { CXL_GMER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ - { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \ +#define CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION 0x03 +#define CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR 0x04 +#define CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE 0x05 +#define CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION 0x06 +#define show_gmer_mem_event_type(type) __print_symbolic(type, \ + { CXL_GMER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ + { CXL_GMER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ + { CXL_GMER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" }, \ + { CXL_GMER_MEM_EVT_TYPE_TE_STATE_VIOLATION, "TE State Violation" }, \ + { CXL_GMER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \ + { CXL_GMER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE, "Adv Prog CME Counter Expiration" }, \ + { CXL_GMER_MEM_EVT_TYPE_CKID_VIOLATION, "CKID Violation" } \ ) #define CXL_GMER_TRANS_UNKNOWN 0x00 @@ -292,6 +327,8 @@ TRACE_EVENT(cxl_generic_event, #define CXL_GMER_TRANS_HOST_INJECT_POISON 0x04 #define CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB 0x05 #define CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT 0x06 +#define CXL_GMER_TRANS_INTERNAL_MEDIA_ECS 0x07 +#define CXL_GMER_TRANS_MEDIA_INITIALIZATION 0x08 #define show_trans_type(type) __print_symbolic(type, \ { CXL_GMER_TRANS_UNKNOWN, "Unknown" }, \ { CXL_GMER_TRANS_HOST_READ, "Host Read" }, \ @@ -299,18 +336,57 @@ TRACE_EVENT(cxl_generic_event, { CXL_GMER_TRANS_HOST_SCAN_MEDIA, "Host Scan Media" }, \ { CXL_GMER_TRANS_HOST_INJECT_POISON, "Host Inject Poison" }, \ { CXL_GMER_TRANS_INTERNAL_MEDIA_SCRUB, "Internal Media Scrub" }, \ - { CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT, "Internal Media Management" } \ + { CXL_GMER_TRANS_INTERNAL_MEDIA_MANAGEMENT, "Internal Media Management" }, \ + { CXL_GMER_TRANS_INTERNAL_MEDIA_ECS, "Internal Media Error Check Scrub" }, \ + { CXL_GMER_TRANS_MEDIA_INITIALIZATION, "Media Initialization" } \ ) #define CXL_GMER_VALID_CHANNEL BIT(0) #define CXL_GMER_VALID_RANK BIT(1) #define CXL_GMER_VALID_DEVICE BIT(2) #define CXL_GMER_VALID_COMPONENT BIT(3) +#define CXL_GMER_VALID_COMPONENT_ID_FORMAT BIT(4) #define show_valid_flags(flags) __print_flags(flags, "|", \ { CXL_GMER_VALID_CHANNEL, "CHANNEL" }, \ { CXL_GMER_VALID_RANK, "RANK" }, \ { CXL_GMER_VALID_DEVICE, "DEVICE" }, \ - { CXL_GMER_VALID_COMPONENT, "COMPONENT" } \ + { CXL_GMER_VALID_COMPONENT, "COMPONENT" }, \ + { CXL_GMER_VALID_COMPONENT_ID_FORMAT, "COMPONENT PLDM FORMAT" } \ +) + +#define CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA BIT(0) +#define CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED BIT(1) +#define show_cme_threshold_ev_flags(flags) __print_flags(flags, "|", \ + { \ + CXL_GMER_CME_EV_FLAG_CME_MULTIPLE_MEDIA, \ + "Corrected Memory Errors in Multiple Media Components" \ + }, { \ + CXL_GMER_CME_EV_FLAG_THRESHOLD_EXCEEDED, \ + "Exceeded Programmable Threshold" \ + } \ +) + +#define CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED 0x00 +#define CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR 0x01 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR 0x02 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR 0x03 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR 0x04 +#define CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR 0x05 +#define show_mem_event_sub_type(sub_type) __print_symbolic(sub_type, \ + { CXL_GMER_MEM_EVT_SUB_TYPE_NOT_REPORTED, "Not Reported" }, \ + { CXL_GMER_MEM_EVT_SUB_TYPE_INTERNAL_DATAPATH_ERROR, "Internal Datapath Error" }, \ + { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_COMMAND_TRAINING_ERROR, \ + "Media Link Command Training Error" \ + }, { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CONTROL_TRAINING_ERROR, \ + "Media Link Control Training Error" \ + }, { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_DATA_TRAINING_ERROR, \ + "Media Link Data Training Error" \ + }, { \ + CXL_GMER_MEM_EVT_SUB_TYPE_MEDIA_LINK_CRC_ERROR, "Media Link CRC Error" \ + } \ ) TRACE_EVENT(cxl_general_media, @@ -336,6 +412,9 @@ TRACE_EVENT(cxl_general_media, __field(u16, validity_flags) __field(u8, rank) __field(u8, dpa_flags) + __field(u32, cme_count) + __field(u8, sub_type) + __field(u8, cme_threshold_ev_flags) __string(region_name, cxlr ? dev_name(&cxlr->dev) : "") ), @@ -350,6 +429,7 @@ TRACE_EVENT(cxl_general_media, __entry->dpa &= CXL_DPA_MASK; __entry->descriptor = rec->media_hdr.descriptor; __entry->type = rec->media_hdr.type; + __entry->sub_type = rec->sub_type; __entry->transaction_type = rec->media_hdr.transaction_type; __entry->channel = rec->media_hdr.channel; __entry->rank = rec->media_hdr.rank; @@ -365,27 +445,40 @@ TRACE_EVENT(cxl_general_media, __assign_str(region_name); uuid_copy(&__entry->region_uuid, &uuid_null); } + __entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags; + __entry->cme_count = get_unaligned_le24(rec->cme_count); ), CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' " \ - "descriptor='%s' type='%s' transaction_type='%s' channel=%u rank=%u " \ - "device=%x comp_id=%s validity_flags='%s' " \ - "hpa=%llx region=%s region_uuid=%pUb", + "descriptor='%s' type='%s' sub_type='%s' " \ + "transaction_type='%s' channel=%u rank=%u " \ + "device=%x validity_flags='%s' " \ + "comp_id=%s comp_id_pldm_valid_flags='%s' " \ + "pldm_entity_id=%s pldm_resource_id=%s " \ + "hpa=%llx region=%s region_uuid=%pUb " \ + "cme_threshold_ev_flags='%s' cme_count=%u", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), show_gmer_mem_event_type(__entry->type), + show_mem_event_sub_type(__entry->sub_type), show_trans_type(__entry->transaction_type), __entry->channel, __entry->rank, __entry->device, - __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), show_valid_flags(__entry->validity_flags), - __entry->hpa, __get_str(region_name), &__entry->region_uuid + __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), + show_comp_id_pldm_flags(__entry->comp_id[0]), + show_pldm_entity_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT, + CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + show_pldm_resource_id(__entry->validity_flags, CXL_GMER_VALID_COMPONENT, + CXL_GMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + __entry->hpa, __get_str(region_name), &__entry->region_uuid, + show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags), __entry->cme_count ) ); /* * DRAM Event Record - DER * - * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44 + * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46 */ /* * DRAM Event Record defines many fields the same as the General Media Event @@ -395,11 +488,17 @@ TRACE_EVENT(cxl_general_media, #define CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR 0x01 #define CXL_DER_MEM_EVT_TYPE_INV_ADDR 0x02 #define CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR 0x03 -#define show_dram_mem_event_type(type) __print_symbolic(type, \ - { CXL_DER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ - { CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \ - { CXL_DER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ - { CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" } \ +#define CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION 0x04 +#define CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE 0x05 +#define CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION 0x06 +#define show_dram_mem_event_type(type) __print_symbolic(type, \ + { CXL_DER_MEM_EVT_TYPE_ECC_ERROR, "ECC Error" }, \ + { CXL_DER_MEM_EVT_TYPE_SCRUB_MEDIA_ECC_ERROR, "Scrub Media ECC Error" }, \ + { CXL_DER_MEM_EVT_TYPE_INV_ADDR, "Invalid Address" }, \ + { CXL_DER_MEM_EVT_TYPE_DATA_PATH_ERROR, "Data Path Error" }, \ + { CXL_DER_MEM_EVT_TYPE_TE_STATE_VIOLATION, "TE State Violation" }, \ + { CXL_DER_MEM_EVT_TYPE_AP_CME_COUNTER_EXPIRE, "Adv Prog CME Counter Expiration" }, \ + { CXL_DER_MEM_EVT_TYPE_CKID_VIOLATION, "CKID Violation" } \ ) #define CXL_DER_VALID_CHANNEL BIT(0) @@ -410,15 +509,21 @@ TRACE_EVENT(cxl_general_media, #define CXL_DER_VALID_ROW BIT(5) #define CXL_DER_VALID_COLUMN BIT(6) #define CXL_DER_VALID_CORRECTION_MASK BIT(7) -#define show_dram_valid_flags(flags) __print_flags(flags, "|", \ - { CXL_DER_VALID_CHANNEL, "CHANNEL" }, \ - { CXL_DER_VALID_RANK, "RANK" }, \ - { CXL_DER_VALID_NIBBLE, "NIBBLE" }, \ - { CXL_DER_VALID_BANK_GROUP, "BANK GROUP" }, \ - { CXL_DER_VALID_BANK, "BANK" }, \ - { CXL_DER_VALID_ROW, "ROW" }, \ - { CXL_DER_VALID_COLUMN, "COLUMN" }, \ - { CXL_DER_VALID_CORRECTION_MASK, "CORRECTION MASK" } \ +#define CXL_DER_VALID_COMPONENT BIT(8) +#define CXL_DER_VALID_COMPONENT_ID_FORMAT BIT(9) +#define CXL_DER_VALID_SUB_CHANNEL BIT(10) +#define show_dram_valid_flags(flags) __print_flags(flags, "|", \ + { CXL_DER_VALID_CHANNEL, "CHANNEL" }, \ + { CXL_DER_VALID_RANK, "RANK" }, \ + { CXL_DER_VALID_NIBBLE, "NIBBLE" }, \ + { CXL_DER_VALID_BANK_GROUP, "BANK GROUP" }, \ + { CXL_DER_VALID_BANK, "BANK" }, \ + { CXL_DER_VALID_ROW, "ROW" }, \ + { CXL_DER_VALID_COLUMN, "COLUMN" }, \ + { CXL_DER_VALID_CORRECTION_MASK, "CORRECTION MASK" }, \ + { CXL_DER_VALID_COMPONENT, "COMPONENT" }, \ + { CXL_DER_VALID_COMPONENT_ID_FORMAT, "COMPONENT PLDM FORMAT" }, \ + { CXL_DER_VALID_SUB_CHANNEL, "SUB CHANNEL" } \ ) TRACE_EVENT(cxl_dram, @@ -447,6 +552,12 @@ TRACE_EVENT(cxl_dram, __field(u8, bank_group) /* Out of order to pack trace record */ __field(u8, bank) /* Out of order to pack trace record */ __field(u8, dpa_flags) /* Out of order to pack trace record */ + /* Following are out of order to pack trace record */ + __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE) + __field(u32, cvme_count) + __field(u8, sub_type) + __field(u8, sub_channel) + __field(u8, cme_threshold_ev_flags) __string(region_name, cxlr ? dev_name(&cxlr->dev) : "") ), @@ -460,6 +571,7 @@ TRACE_EVENT(cxl_dram, __entry->dpa &= CXL_DPA_MASK; __entry->descriptor = rec->media_hdr.descriptor; __entry->type = rec->media_hdr.type; + __entry->sub_type = rec->sub_type; __entry->transaction_type = rec->media_hdr.transaction_type; __entry->validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags); __entry->channel = rec->media_hdr.channel; @@ -479,30 +591,47 @@ TRACE_EVENT(cxl_dram, __assign_str(region_name); uuid_copy(&__entry->region_uuid, &uuid_null); } + memcpy(__entry->comp_id, &rec->component_id, + CXL_EVENT_GEN_MED_COMP_ID_SIZE); + __entry->sub_channel = rec->sub_channel; + __entry->cme_threshold_ev_flags = rec->cme_threshold_ev_flags; + __entry->cvme_count = get_unaligned_le24(rec->cvme_count); ), - CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' " \ + CXL_EVT_TP_printk("dpa=%llx dpa_flags='%s' descriptor='%s' type='%s' sub_type='%s' " \ "transaction_type='%s' channel=%u rank=%u nibble_mask=%x " \ "bank_group=%u bank=%u row=%u column=%u cor_mask=%s " \ "validity_flags='%s' " \ - "hpa=%llx region=%s region_uuid=%pUb", + "comp_id=%s comp_id_pldm_valid_flags='%s' " \ + "pldm_entity_id=%s pldm_resource_id=%s " \ + "hpa=%llx region=%s region_uuid=%pUb " \ + "sub_channel=%u cme_threshold_ev_flags='%s' cvme_count=%u", __entry->dpa, show_dpa_flags(__entry->dpa_flags), show_event_desc_flags(__entry->descriptor), show_dram_mem_event_type(__entry->type), + show_mem_event_sub_type(__entry->sub_type), show_trans_type(__entry->transaction_type), __entry->channel, __entry->rank, __entry->nibble_mask, __entry->bank_group, __entry->bank, __entry->row, __entry->column, __print_hex(__entry->cor_mask, CXL_EVENT_DER_CORRECTION_MASK_SIZE), show_dram_valid_flags(__entry->validity_flags), - __entry->hpa, __get_str(region_name), &__entry->region_uuid + __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), + show_comp_id_pldm_flags(__entry->comp_id[0]), + show_pldm_entity_id(__entry->validity_flags, CXL_DER_VALID_COMPONENT, + CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + show_pldm_resource_id(__entry->validity_flags, CXL_DER_VALID_COMPONENT, + CXL_DER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + __entry->hpa, __get_str(region_name), &__entry->region_uuid, + __entry->sub_channel, show_cme_threshold_ev_flags(__entry->cme_threshold_ev_flags), + __entry->cvme_count ) ); /* * Memory Module Event Record - MMER * - * CXL res 3.0 section 8.2.9.2.1.3; Table 8-45 + * CXL res 3.1 section 8.2.9.2.1.3; Table 8-47 */ #define CXL_MMER_HEALTH_STATUS_CHANGE 0x00 #define CXL_MMER_MEDIA_STATUS_CHANGE 0x01 @@ -510,27 +639,35 @@ TRACE_EVENT(cxl_dram, #define CXL_MMER_TEMP_CHANGE 0x03 #define CXL_MMER_DATA_PATH_ERROR 0x04 #define CXL_MMER_LSA_ERROR 0x05 +#define CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR 0x06 +#define CXL_MMER_MEMORY_MEDIA_FRU_ERROR 0x07 +#define CXL_MMER_POWER_MANAGEMENT_FAULT 0x08 #define show_dev_evt_type(type) __print_symbolic(type, \ { CXL_MMER_HEALTH_STATUS_CHANGE, "Health Status Change" }, \ { CXL_MMER_MEDIA_STATUS_CHANGE, "Media Status Change" }, \ { CXL_MMER_LIFE_USED_CHANGE, "Life Used Change" }, \ { CXL_MMER_TEMP_CHANGE, "Temperature Change" }, \ { CXL_MMER_DATA_PATH_ERROR, "Data Path Error" }, \ - { CXL_MMER_LSA_ERROR, "LSA Error" } \ + { CXL_MMER_LSA_ERROR, "LSA Error" }, \ + { CXL_MMER_UNRECOV_SIDEBAND_BUS_ERROR, "Unrecoverable Internal Sideband Bus Error" }, \ + { CXL_MMER_MEMORY_MEDIA_FRU_ERROR, "Memory Media FRU Error" }, \ + { CXL_MMER_POWER_MANAGEMENT_FAULT, "Power Management Fault" } \ ) /* * Device Health Information - DHI * - * CXL res 3.0 section 8.2.9.8.3.1; Table 8-100 + * CXL res 3.1 section 8.2.9.9.3.1; Table 8-133 */ #define CXL_DHI_HS_MAINTENANCE_NEEDED BIT(0) #define CXL_DHI_HS_PERFORMANCE_DEGRADED BIT(1) #define CXL_DHI_HS_HW_REPLACEMENT_NEEDED BIT(2) +#define CXL_DHI_HS_MEM_CAPACITY_DEGRADED BIT(3) #define show_health_status_flags(flags) __print_flags(flags, "|", \ { CXL_DHI_HS_MAINTENANCE_NEEDED, "MAINTENANCE_NEEDED" }, \ { CXL_DHI_HS_PERFORMANCE_DEGRADED, "PERFORMANCE_DEGRADED" }, \ - { CXL_DHI_HS_HW_REPLACEMENT_NEEDED, "REPLACEMENT_NEEDED" } \ + { CXL_DHI_HS_HW_REPLACEMENT_NEEDED, "REPLACEMENT_NEEDED" }, \ + { CXL_DHI_HS_MEM_CAPACITY_DEGRADED, "MEM_CAPACITY_DEGRADED" } \ ) #define CXL_DHI_MS_NORMAL 0x00 @@ -584,6 +721,26 @@ TRACE_EVENT(cxl_dram, #define CXL_DHI_AS_COR_VOL_ERR_CNT(as) ((as & 0x10) >> 4) #define CXL_DHI_AS_COR_PER_ERR_CNT(as) ((as & 0x20) >> 5) +#define CXL_MMER_VALID_COMPONENT BIT(0) +#define CXL_MMER_VALID_COMPONENT_ID_FORMAT BIT(1) +#define show_mem_module_valid_flags(flags) __print_flags(flags, "|", \ + { CXL_MMER_VALID_COMPONENT, "COMPONENT" }, \ + { CXL_MMER_VALID_COMPONENT_ID_FORMAT, "COMPONENT PLDM FORMAT" } \ +) +#define CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED 0x00 +#define CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA 0x01 +#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA 0x02 +#define CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU 0x03 +#define show_dev_event_sub_type(sub_type) __print_symbolic(sub_type, \ + { CXL_MMER_DEV_EVT_SUB_TYPE_NOT_REPORTED, "Not Reported" }, \ + { CXL_MMER_DEV_EVT_SUB_TYPE_INVALID_CONFIG_DATA, "Invalid Config Data" }, \ + { CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_CONFIG_DATA, "Unsupported Config Data" }, \ + { \ + CXL_MMER_DEV_EVT_SUB_TYPE_UNSUPP_MEM_MEDIA_FRU, \ + "Unsupported Memory Media FRU" \ + } \ +) + TRACE_EVENT(cxl_memory_module, TP_PROTO(const struct cxl_memdev *cxlmd, enum cxl_event_log_type log, @@ -606,6 +763,9 @@ TRACE_EVENT(cxl_memory_module, __field(u32, cor_per_err_cnt) __field(s16, device_temp) __field(u8, add_status) + __field(u8, event_sub_type) + __array(u8, comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE) + __field(u16, validity_flags) ), TP_fast_assign( @@ -614,6 +774,7 @@ TRACE_EVENT(cxl_memory_module, /* Memory Module Event */ __entry->event_type = rec->event_type; + __entry->event_sub_type = rec->event_sub_type; /* Device Health Info */ __entry->health_status = rec->info.health_status; @@ -624,13 +785,20 @@ TRACE_EVENT(cxl_memory_module, __entry->cor_per_err_cnt = get_unaligned_le32(rec->info.cor_per_err_cnt); __entry->device_temp = get_unaligned_le16(rec->info.device_temp); __entry->add_status = rec->info.add_status; + __entry->validity_flags = get_unaligned_le16(rec->validity_flags); + memcpy(__entry->comp_id, &rec->component_id, + CXL_EVENT_GEN_MED_COMP_ID_SIZE); ), - CXL_EVT_TP_printk("event_type='%s' health_status='%s' media_status='%s' " \ - "as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \ + CXL_EVT_TP_printk("event_type='%s' event_sub_type='%s' health_status='%s' " \ + "media_status='%s' as_life_used=%s as_dev_temp=%s as_cor_vol_err_cnt=%s " \ "as_cor_per_err_cnt=%s life_used=%u device_temp=%d " \ - "dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u", + "dirty_shutdown_cnt=%u cor_vol_err_cnt=%u cor_per_err_cnt=%u " \ + "validity_flags='%s' " \ + "comp_id=%s comp_id_pldm_valid_flags='%s' " \ + "pldm_entity_id=%s pldm_resource_id=%s", show_dev_evt_type(__entry->event_type), + show_dev_event_sub_type(__entry->event_sub_type), show_health_status_flags(__entry->health_status), show_media_status(__entry->media_status), show_two_bit_status(CXL_DHI_AS_LIFE_USED(__entry->add_status)), @@ -639,7 +807,14 @@ TRACE_EVENT(cxl_memory_module, show_one_bit_status(CXL_DHI_AS_COR_PER_ERR_CNT(__entry->add_status)), __entry->life_used, __entry->device_temp, __entry->dirty_shutdown_cnt, __entry->cor_vol_err_cnt, - __entry->cor_per_err_cnt + __entry->cor_per_err_cnt, + show_mem_module_valid_flags(__entry->validity_flags), + __print_hex(__entry->comp_id, CXL_EVENT_GEN_MED_COMP_ID_SIZE), + show_comp_id_pldm_flags(__entry->comp_id[0]), + show_pldm_entity_id(__entry->validity_flags, CXL_MMER_VALID_COMPONENT, + CXL_MMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id), + show_pldm_resource_id(__entry->validity_flags, CXL_MMER_VALID_COMPONENT, + CXL_MMER_VALID_COMPONENT_ID_FORMAT, __entry->comp_id) ) ); diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 064a15cf559f..bbbaa0d0a670 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -302,10 +302,11 @@ int cxl_map_device_regs(const struct cxl_register_map *map, struct cxl_device_regs *regs); int cxl_map_pmu_regs(struct cxl_register_map *map, struct cxl_pmu_regs *regs); +#define CXL_INSTANCES_COUNT -1 enum cxl_regloc_type; int cxl_count_regblock(struct pci_dev *pdev, enum cxl_regloc_type type); int cxl_find_regblock_instance(struct pci_dev *pdev, enum cxl_regloc_type type, - struct cxl_register_map *map, int index); + struct cxl_register_map *map, unsigned int index); int cxl_find_regblock(struct pci_dev *pdev, enum cxl_regloc_type type, struct cxl_register_map *map); int cxl_setup_regs(struct cxl_register_map *map); @@ -821,7 +822,8 @@ struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port, int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm, struct cxl_endpoint_dvsec_info *info); int devm_cxl_add_passthrough_decoder(struct cxl_port *port); -int cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +struct cxl_dev_state; +int cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info); bool is_cxl_region(struct device *dev); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 6d94ff4a4f1a..a96e54c6259e 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -907,7 +907,8 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) struct cxl_dev_state *cxlds; struct cxl_register_map map; struct cxl_memdev *cxlmd; - int i, rc, pmu_count; + int rc, pmu_count; + unsigned int i; bool irq_avail; /* @@ -1009,6 +1010,9 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return rc; pmu_count = cxl_count_regblock(pdev, CXL_REGLOC_RBI_PMU); + if (pmu_count < 0) + return pmu_count; + for (i = 0; i < pmu_count; i++) { struct cxl_pmu_regs pmu_regs; diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c index 4c83f6a22e58..d2bfd1ff5492 100644 --- a/drivers/cxl/port.c +++ b/drivers/cxl/port.c @@ -98,7 +98,7 @@ static int cxl_endpoint_port_probe(struct cxl_port *port) struct cxl_port *root; int rc; - rc = cxl_dvsec_rr_decode(cxlds->dev, port, &info); + rc = cxl_dvsec_rr_decode(cxlds, &info); if (rc < 0) return rc; diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index e994d6e0779e..8afea2e23360 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -162,8 +162,8 @@ config DMA_SA11X0 config DMA_SUN4I tristate "Allwinner A10 DMA SoCs support" - depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I - default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I) + depends on MACH_SUN4I || MACH_SUN5I || MACH_SUN7I || MACH_SUNIV + default (MACH_SUN4I || MACH_SUN5I || MACH_SUN7I || MACH_SUNIV) select DMA_ENGINE select DMA_VIRTUAL_CHANNELS help @@ -740,8 +740,6 @@ source "drivers/dma/bestcomm/Kconfig" source "drivers/dma/mediatek/Kconfig" -source "drivers/dma/ptdma/Kconfig" - source "drivers/dma/qcom/Kconfig" source "drivers/dma/dw/Kconfig" diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile index 5b2a52f4f2ee..19ba465011a6 100644 --- a/drivers/dma/Makefile +++ b/drivers/dma/Makefile @@ -16,7 +16,6 @@ obj-$(CONFIG_DMATEST) += dmatest.o obj-$(CONFIG_ALTERA_MSGDMA) += altera-msgdma.o obj-$(CONFIG_AMBA_PL08X) += amba-pl08x.o obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/ -obj-$(CONFIG_AMD_PTDMA) += ptdma/ obj-$(CONFIG_APPLE_ADMAC) += apple-admac.o obj-$(CONFIG_AT_HDMAC) += at_hdmac.o obj-$(CONFIG_AT_XDMAC) += at_xdmac.o diff --git a/drivers/dma/amd/Kconfig b/drivers/dma/amd/Kconfig index 7d1f51d69675..00d874872a8f 100644 --- a/drivers/dma/amd/Kconfig +++ b/drivers/dma/amd/Kconfig @@ -1,4 +1,32 @@ # SPDX-License-Identifier: GPL-2.0-only +# + +config AMD_AE4DMA + tristate "AMD AE4DMA Engine" + depends on (X86_64 || COMPILE_TEST) && PCI + depends on AMD_PTDMA + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Enable support for the AMD AE4DMA controller. This controller + provides DMA capabilities to perform high bandwidth memory to + memory and IO copy operations. It performs DMA transfer through + queue-based descriptor management. This DMA controller is intended + to be used with AMD Non-Transparent Bridge devices and not for + general purpose peripheral DMA. + +config AMD_PTDMA + tristate "AMD PassThru DMA Engine" + depends on X86_64 && PCI + select DMA_ENGINE + select DMA_VIRTUAL_CHANNELS + help + Enable support for the AMD PTDMA controller. This controller + provides DMA capabilities to perform high bandwidth memory to + memory and IO copy operations. It performs DMA transfer through + queue-based descriptor management. This DMA controller is intended + to be used with AMD Non-Transparent Bridge devices and not for + general purpose peripheral DMA. config AMD_QDMA tristate "AMD Queue-based DMA" diff --git a/drivers/dma/amd/Makefile b/drivers/dma/amd/Makefile index 37212be9364f..11278c06374d 100644 --- a/drivers/dma/amd/Makefile +++ b/drivers/dma/amd/Makefile @@ -1,3 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_AMD_AE4DMA) += ae4dma/ +obj-$(CONFIG_AMD_PTDMA) += ptdma/ obj-$(CONFIG_AMD_QDMA) += qdma/ diff --git a/drivers/dma/amd/ae4dma/Makefile b/drivers/dma/amd/ae4dma/Makefile new file mode 100644 index 000000000000..e918f85a80ec --- /dev/null +++ b/drivers/dma/amd/ae4dma/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# AMD AE4DMA driver +# + +obj-$(CONFIG_AMD_AE4DMA) += ae4dma.o + +ae4dma-objs := ae4dma-dev.o + +ae4dma-$(CONFIG_PCI) += ae4dma-pci.o diff --git a/drivers/dma/amd/ae4dma/ae4dma-dev.c b/drivers/dma/amd/ae4dma/ae4dma-dev.c new file mode 100644 index 000000000000..8de3bef41b58 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma-dev.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar <Basavaraj.Natikar@amd.com> + */ + +#include "ae4dma.h" + +static unsigned int max_hw_q = 1; +module_param(max_hw_q, uint, 0444); +MODULE_PARM_DESC(max_hw_q, "max hw queues supported by engine (any non-zero value, default: 1)"); + +static void ae4_pending_work(struct work_struct *work) +{ + struct ae4_cmd_queue *ae4cmd_q = container_of(work, struct ae4_cmd_queue, p_work.work); + struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q; + struct pt_cmd *cmd; + u32 cridx; + + for (;;) { + wait_event_interruptible(ae4cmd_q->q_w, + ((atomic64_read(&ae4cmd_q->done_cnt)) < + atomic64_read(&ae4cmd_q->intr_cnt))); + + atomic64_inc(&ae4cmd_q->done_cnt); + + mutex_lock(&ae4cmd_q->cmd_lock); + cridx = readl(cmd_q->reg_control + AE4_RD_IDX_OFF); + while ((ae4cmd_q->dridx != cridx) && !list_empty(&ae4cmd_q->cmd)) { + cmd = list_first_entry(&ae4cmd_q->cmd, struct pt_cmd, entry); + list_del(&cmd->entry); + + ae4_check_status_error(ae4cmd_q, ae4cmd_q->dridx); + cmd->pt_cmd_callback(cmd->data, cmd->ret); + + ae4cmd_q->q_cmd_count--; + ae4cmd_q->dridx = (ae4cmd_q->dridx + 1) % CMD_Q_LEN; + + complete_all(&ae4cmd_q->cmp); + } + mutex_unlock(&ae4cmd_q->cmd_lock); + } +} + +static irqreturn_t ae4_core_irq_handler(int irq, void *data) +{ + struct ae4_cmd_queue *ae4cmd_q = data; + struct pt_cmd_queue *cmd_q; + struct pt_device *pt; + u32 status; + + cmd_q = &ae4cmd_q->cmd_q; + pt = cmd_q->pt; + + pt->total_interrupts++; + atomic64_inc(&ae4cmd_q->intr_cnt); + + status = readl(cmd_q->reg_control + AE4_INTR_STS_OFF); + if (status & BIT(0)) { + status &= GENMASK(31, 1); + writel(status, cmd_q->reg_control + AE4_INTR_STS_OFF); + } + + wake_up(&ae4cmd_q->q_w); + + return IRQ_HANDLED; +} + +void ae4_destroy_work(struct ae4_device *ae4) +{ + struct ae4_cmd_queue *ae4cmd_q; + int i; + + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + + if (!ae4cmd_q->pws) + break; + + cancel_delayed_work_sync(&ae4cmd_q->p_work); + destroy_workqueue(ae4cmd_q->pws); + } +} + +int ae4_core_init(struct ae4_device *ae4) +{ + struct pt_device *pt = &ae4->pt; + struct ae4_cmd_queue *ae4cmd_q; + struct device *dev = pt->dev; + struct pt_cmd_queue *cmd_q; + int i, ret = 0; + + writel(max_hw_q, pt->io_regs); + + for (i = 0; i < max_hw_q; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + ae4cmd_q->id = ae4->cmd_q_count; + ae4->cmd_q_count++; + + cmd_q = &ae4cmd_q->cmd_q; + cmd_q->pt = pt; + + cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ); + + ret = devm_request_irq(dev, ae4->ae4_irq[i], ae4_core_irq_handler, 0, + dev_name(pt->dev), ae4cmd_q); + if (ret) + return ret; + + cmd_q->qsize = Q_SIZE(sizeof(struct ae4dma_desc)); + + cmd_q->qbase = dmam_alloc_coherent(dev, cmd_q->qsize, &cmd_q->qbase_dma, + GFP_KERNEL); + if (!cmd_q->qbase) + return -ENOMEM; + } + + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + + cmd_q = &ae4cmd_q->cmd_q; + + cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ); + + /* Update the device registers with queue information. */ + writel(CMD_Q_LEN, cmd_q->reg_control + AE4_MAX_IDX_OFF); + + cmd_q->qdma_tail = cmd_q->qbase_dma; + writel(lower_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_L_OFF); + writel(upper_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_H_OFF); + + INIT_LIST_HEAD(&ae4cmd_q->cmd); + init_waitqueue_head(&ae4cmd_q->q_w); + + ae4cmd_q->pws = alloc_ordered_workqueue("ae4dma_%d", WQ_MEM_RECLAIM, ae4cmd_q->id); + if (!ae4cmd_q->pws) { + ae4_destroy_work(ae4); + return -ENOMEM; + } + INIT_DELAYED_WORK(&ae4cmd_q->p_work, ae4_pending_work); + queue_delayed_work(ae4cmd_q->pws, &ae4cmd_q->p_work, usecs_to_jiffies(100)); + + init_completion(&ae4cmd_q->cmp); + } + + ret = pt_dmaengine_register(pt); + if (ret) + ae4_destroy_work(ae4); + else + ptdma_debugfs_setup(pt); + + return ret; +} diff --git a/drivers/dma/amd/ae4dma/ae4dma-pci.c b/drivers/dma/amd/ae4dma/ae4dma-pci.c new file mode 100644 index 000000000000..aad0dc4294a3 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma-pci.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar <Basavaraj.Natikar@amd.com> + */ + +#include "ae4dma.h" + +static int ae4_get_irqs(struct ae4_device *ae4) +{ + struct ae4_msix *ae4_msix = ae4->ae4_msix; + struct pt_device *pt = &ae4->pt; + struct device *dev = pt->dev; + struct pci_dev *pdev; + int i, v, ret; + + pdev = to_pci_dev(dev); + + for (v = 0; v < ARRAY_SIZE(ae4_msix->msix_entry); v++) + ae4_msix->msix_entry[v].entry = v; + + ret = pci_alloc_irq_vectors(pdev, v, v, PCI_IRQ_MSIX); + if (ret != v) { + if (ret > 0) + pci_free_irq_vectors(pdev); + + dev_err(dev, "could not enable MSI-X (%d), trying MSI\n", ret); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret < 0) { + dev_err(dev, "could not enable MSI (%d)\n", ret); + return ret; + } + + ret = pci_irq_vector(pdev, 0); + if (ret < 0) { + pci_free_irq_vectors(pdev); + return ret; + } + + for (i = 0; i < MAX_AE4_HW_QUEUES; i++) + ae4->ae4_irq[i] = ret; + + } else { + ae4_msix->msix_count = ret; + for (i = 0; i < MAX_AE4_HW_QUEUES; i++) + ae4->ae4_irq[i] = ae4_msix->msix_entry[i].vector; + } + + return ret; +} + +static void ae4_free_irqs(struct ae4_device *ae4) +{ + struct ae4_msix *ae4_msix = ae4->ae4_msix; + struct pt_device *pt = &ae4->pt; + struct device *dev = pt->dev; + struct pci_dev *pdev; + + pdev = to_pci_dev(dev); + + if (ae4_msix && (ae4_msix->msix_count || ae4->ae4_irq[MAX_AE4_HW_QUEUES - 1])) + pci_free_irq_vectors(pdev); +} + +static void ae4_deinit(struct ae4_device *ae4) +{ + ae4_free_irqs(ae4); +} + +static int ae4_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct ae4_device *ae4; + struct pt_device *pt; + int bar_mask; + int ret = 0; + + ae4 = devm_kzalloc(dev, sizeof(*ae4), GFP_KERNEL); + if (!ae4) + return -ENOMEM; + + ae4->ae4_msix = devm_kzalloc(dev, sizeof(struct ae4_msix), GFP_KERNEL); + if (!ae4->ae4_msix) + return -ENOMEM; + + ret = pcim_enable_device(pdev); + if (ret) + goto ae4_error; + + bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); + ret = pcim_iomap_regions(pdev, bar_mask, "ae4dma"); + if (ret) + goto ae4_error; + + pt = &ae4->pt; + pt->dev = dev; + pt->ver = AE4_DMA_VERSION; + + pt->io_regs = pcim_iomap_table(pdev)[0]; + if (!pt->io_regs) { + ret = -ENOMEM; + goto ae4_error; + } + + ret = ae4_get_irqs(ae4); + if (ret < 0) + goto ae4_error; + + pci_set_master(pdev); + + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); + + dev_set_drvdata(dev, ae4); + + ret = ae4_core_init(ae4); + if (ret) + goto ae4_error; + + return 0; + +ae4_error: + ae4_deinit(ae4); + + return ret; +} + +static void ae4_pci_remove(struct pci_dev *pdev) +{ + struct ae4_device *ae4 = dev_get_drvdata(&pdev->dev); + + ae4_destroy_work(ae4); + ae4_deinit(ae4); +} + +static const struct pci_device_id ae4_pci_table[] = { + { PCI_VDEVICE(AMD, 0x14C8), }, + { PCI_VDEVICE(AMD, 0x14DC), }, + { PCI_VDEVICE(AMD, 0x149B), }, + /* Last entry must be zero */ + { 0, } +}; +MODULE_DEVICE_TABLE(pci, ae4_pci_table); + +static struct pci_driver ae4_pci_driver = { + .name = "ae4dma", + .id_table = ae4_pci_table, + .probe = ae4_pci_probe, + .remove = ae4_pci_remove, +}; + +module_pci_driver(ae4_pci_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("AMD AE4DMA driver"); diff --git a/drivers/dma/amd/ae4dma/ae4dma.h b/drivers/dma/amd/ae4dma/ae4dma.h new file mode 100644 index 000000000000..265c5d436008 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar <Basavaraj.Natikar@amd.com> + */ +#ifndef __AE4DMA_H__ +#define __AE4DMA_H__ + +#include <linux/device.h> +#include <linux/dmaengine.h> +#include <linux/dmapool.h> +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/pci.h> +#include <linux/spinlock.h> +#include <linux/wait.h> + +#include "../ptdma/ptdma.h" +#include "../../virt-dma.h" + +#define MAX_AE4_HW_QUEUES 16 + +#define AE4_DESC_COMPLETED 0x03 + +#define AE4_MAX_IDX_OFF 0x08 +#define AE4_RD_IDX_OFF 0x0c +#define AE4_WR_IDX_OFF 0x10 +#define AE4_INTR_STS_OFF 0x14 +#define AE4_Q_BASE_L_OFF 0x18 +#define AE4_Q_BASE_H_OFF 0x1c +#define AE4_Q_SZ 0x20 + +#define AE4_DMA_VERSION 4 +#define CMD_AE4_DESC_DW0_VAL 2 + +struct ae4_msix { + int msix_count; + struct msix_entry msix_entry[MAX_AE4_HW_QUEUES]; +}; + +struct ae4_cmd_queue { + struct ae4_device *ae4; + struct pt_cmd_queue cmd_q; + struct list_head cmd; + /* protect command operations */ + struct mutex cmd_lock; + struct delayed_work p_work; + struct workqueue_struct *pws; + struct completion cmp; + wait_queue_head_t q_w; + atomic64_t intr_cnt; + atomic64_t done_cnt; + u64 q_cmd_count; + u32 dridx; + u32 tail_wi; + u32 id; +}; + +union dwou { + u32 dw0; + struct dword0 { + u8 byte0; + u8 byte1; + u16 timestamp; + } dws; +}; + +struct dword1 { + u8 status; + u8 err_code; + u16 desc_id; +}; + +struct ae4dma_desc { + union dwou dwouv; + struct dword1 dw1; + u32 length; + u32 rsvd; + u32 src_hi; + u32 src_lo; + u32 dst_hi; + u32 dst_lo; +}; + +struct ae4_device { + struct pt_device pt; + struct ae4_msix *ae4_msix; + struct ae4_cmd_queue ae4cmd_q[MAX_AE4_HW_QUEUES]; + unsigned int ae4_irq[MAX_AE4_HW_QUEUES]; + unsigned int cmd_q_count; +}; + +int ae4_core_init(struct ae4_device *ae4); +void ae4_destroy_work(struct ae4_device *ae4); +void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx); +#endif diff --git a/drivers/dma/ptdma/Makefile b/drivers/dma/amd/ptdma/Makefile index ce5410268a9a..ce5410268a9a 100644 --- a/drivers/dma/ptdma/Makefile +++ b/drivers/dma/amd/ptdma/Makefile diff --git a/drivers/dma/ptdma/ptdma-debugfs.c b/drivers/dma/amd/ptdma/ptdma-debugfs.c index c8307d3044a3..c7c90bbf6fd8 100644 --- a/drivers/dma/ptdma/ptdma-debugfs.c +++ b/drivers/dma/amd/ptdma/ptdma-debugfs.c @@ -13,6 +13,7 @@ #include <linux/seq_file.h> #include "ptdma.h" +#include "../ae4dma/ae4dma.h" /* DebugFS helpers */ #define RI_VERSION_NUM 0x0000003F @@ -23,11 +24,19 @@ static int pt_debugfs_info_show(struct seq_file *s, void *p) { struct pt_device *pt = s->private; + struct ae4_device *ae4; unsigned int regval; seq_printf(s, "Device name: %s\n", dev_name(pt->dev)); - seq_printf(s, " # Queues: %d\n", 1); - seq_printf(s, " # Cmds: %d\n", pt->cmd_count); + + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + seq_printf(s, " # Queues: %d\n", ae4->cmd_q_count); + seq_printf(s, " # Cmds per queue: %d\n", CMD_Q_LEN); + } else { + seq_printf(s, " # Queues: %d\n", 1); + seq_printf(s, " # Cmds: %d\n", pt->cmd_count); + } regval = ioread32(pt->io_regs + CMD_PT_VERSION); @@ -55,6 +64,7 @@ static int pt_debugfs_stats_show(struct seq_file *s, void *p) static int pt_debugfs_queue_show(struct seq_file *s, void *p) { struct pt_cmd_queue *cmd_q = s->private; + struct pt_device *pt; unsigned int regval; if (!cmd_q) @@ -62,18 +72,24 @@ static int pt_debugfs_queue_show(struct seq_file *s, void *p) seq_printf(s, " Pass-Thru: %ld\n", cmd_q->total_pt_ops); - regval = ioread32(cmd_q->reg_control + 0x000C); - - seq_puts(s, " Enabled Interrupts:"); - if (regval & INT_EMPTY_QUEUE) - seq_puts(s, " EMPTY"); - if (regval & INT_QUEUE_STOPPED) - seq_puts(s, " STOPPED"); - if (regval & INT_ERROR) - seq_puts(s, " ERROR"); - if (regval & INT_COMPLETION) - seq_puts(s, " COMPLETION"); - seq_puts(s, "\n"); + pt = cmd_q->pt; + if (pt->ver == AE4_DMA_VERSION) { + regval = readl(cmd_q->reg_control + 0x4); + seq_printf(s, " Enabled Interrupts:: status 0x%x\n", regval); + } else { + regval = ioread32(cmd_q->reg_control + 0x000C); + + seq_puts(s, " Enabled Interrupts:"); + if (regval & INT_EMPTY_QUEUE) + seq_puts(s, " EMPTY"); + if (regval & INT_QUEUE_STOPPED) + seq_puts(s, " STOPPED"); + if (regval & INT_ERROR) + seq_puts(s, " ERROR"); + if (regval & INT_COMPLETION) + seq_puts(s, " COMPLETION"); + seq_puts(s, "\n"); + } return 0; } @@ -84,8 +100,12 @@ DEFINE_SHOW_ATTRIBUTE(pt_debugfs_stats); void ptdma_debugfs_setup(struct pt_device *pt) { - struct pt_cmd_queue *cmd_q; struct dentry *debugfs_q_instance; + struct ae4_cmd_queue *ae4cmd_q; + struct pt_cmd_queue *cmd_q; + struct ae4_device *ae4; + char name[30]; + int i; if (!debugfs_initialized()) return; @@ -96,11 +116,28 @@ void ptdma_debugfs_setup(struct pt_device *pt) debugfs_create_file("stats", 0400, pt->dma_dev.dbg_dev_root, pt, &pt_debugfs_stats_fops); - cmd_q = &pt->cmd_q; - - debugfs_q_instance = - debugfs_create_dir("q", pt->dma_dev.dbg_dev_root); - debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q, - &pt_debugfs_queue_fops); + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + cmd_q = &ae4cmd_q->cmd_q; + + memset(name, 0, sizeof(name)); + snprintf(name, 29, "q%d", ae4cmd_q->id); + + debugfs_q_instance = + debugfs_create_dir(name, pt->dma_dev.dbg_dev_root); + + debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q, + &pt_debugfs_queue_fops); + } + } else { + debugfs_q_instance = + debugfs_create_dir("q", pt->dma_dev.dbg_dev_root); + cmd_q = &pt->cmd_q; + debugfs_create_file("stats", 0400, debugfs_q_instance, cmd_q, + &pt_debugfs_queue_fops); + } } +EXPORT_SYMBOL_GPL(ptdma_debugfs_setup); diff --git a/drivers/dma/ptdma/ptdma-dev.c b/drivers/dma/amd/ptdma/ptdma-dev.c index a2bf13ff18b6..a2bf13ff18b6 100644 --- a/drivers/dma/ptdma/ptdma-dev.c +++ b/drivers/dma/amd/ptdma/ptdma-dev.c diff --git a/drivers/dma/ptdma/ptdma-dmaengine.c b/drivers/dma/amd/ptdma/ptdma-dmaengine.c index f79240734807..35c84ec9608b 100644 --- a/drivers/dma/ptdma/ptdma-dmaengine.c +++ b/drivers/dma/amd/ptdma/ptdma-dmaengine.c @@ -9,9 +9,58 @@ * Author: Gary R Hook <gary.hook@amd.com> */ +#include <linux/bitfield.h> #include "ptdma.h" -#include "../dmaengine.h" -#include "../virt-dma.h" +#include "../ae4dma/ae4dma.h" +#include "../../dmaengine.h" + +static char *ae4_error_codes[] = { + "", + "ERR 01: INVALID HEADER DW0", + "ERR 02: INVALID STATUS", + "ERR 03: INVALID LENGTH - 4 BYTE ALIGNMENT", + "ERR 04: INVALID SRC ADDR - 4 BYTE ALIGNMENT", + "ERR 05: INVALID DST ADDR - 4 BYTE ALIGNMENT", + "ERR 06: INVALID ALIGNMENT", + "ERR 07: INVALID DESCRIPTOR", +}; + +static void ae4_log_error(struct pt_device *d, int e) +{ + /* ERR 01 - 07 represents Invalid AE4 errors */ + if (e <= 7) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", ae4_error_codes[e], e); + /* ERR 08 - 15 represents Invalid Descriptor errors */ + else if (e > 7 && e <= 15) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "INVALID DESCRIPTOR", e); + /* ERR 16 - 31 represents Firmware errors */ + else if (e > 15 && e <= 31) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FIRMWARE ERROR", e); + /* ERR 32 - 63 represents Fatal errors */ + else if (e > 31 && e <= 63) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "FATAL ERROR", e); + /* ERR 64 - 255 represents PTE errors */ + else if (e > 63 && e <= 255) + dev_info(d->dev, "AE4DMA error: %s (0x%x)\n", "PTE ERROR", e); + else + dev_info(d->dev, "Unknown AE4DMA error"); +} + +void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx) +{ + struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q; + struct ae4dma_desc desc; + u8 status; + + memcpy(&desc, &cmd_q->qbase[idx], sizeof(struct ae4dma_desc)); + status = desc.dw1.status; + if (status && status != AE4_DESC_COMPLETED) { + cmd_q->cmd_error = desc.dw1.err_code; + if (cmd_q->cmd_error) + ae4_log_error(cmd_q->pt, cmd_q->cmd_error); + } +} +EXPORT_SYMBOL_GPL(ae4_check_status_error); static inline struct pt_dma_chan *to_pt_chan(struct dma_chan *dma_chan) { @@ -45,7 +94,71 @@ static void pt_do_cleanup(struct virt_dma_desc *vd) kmem_cache_free(pt->dma_desc_cache, desc); } -static int pt_dma_start_desc(struct pt_dma_desc *desc) +static struct pt_cmd_queue *pt_get_cmd_queue(struct pt_device *pt, struct pt_dma_chan *chan) +{ + struct ae4_cmd_queue *ae4cmd_q; + struct pt_cmd_queue *cmd_q; + struct ae4_device *ae4; + + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + ae4cmd_q = &ae4->ae4cmd_q[chan->id]; + cmd_q = &ae4cmd_q->cmd_q; + } else { + cmd_q = &pt->cmd_q; + } + + return cmd_q; +} + +static int ae4_core_execute_cmd(struct ae4dma_desc *desc, struct ae4_cmd_queue *ae4cmd_q) +{ + bool soc = FIELD_GET(DWORD0_SOC, desc->dwouv.dw0); + struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q; + + if (soc) { + desc->dwouv.dw0 |= FIELD_PREP(DWORD0_IOC, desc->dwouv.dw0); + desc->dwouv.dw0 &= ~DWORD0_SOC; + } + + mutex_lock(&ae4cmd_q->cmd_lock); + memcpy(&cmd_q->qbase[ae4cmd_q->tail_wi], desc, sizeof(struct ae4dma_desc)); + ae4cmd_q->q_cmd_count++; + ae4cmd_q->tail_wi = (ae4cmd_q->tail_wi + 1) % CMD_Q_LEN; + writel(ae4cmd_q->tail_wi, cmd_q->reg_control + AE4_WR_IDX_OFF); + mutex_unlock(&ae4cmd_q->cmd_lock); + + wake_up(&ae4cmd_q->q_w); + + return 0; +} + +static int pt_core_perform_passthru_ae4(struct pt_cmd_queue *cmd_q, + struct pt_passthru_engine *pt_engine) +{ + struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q); + struct ae4dma_desc desc; + + cmd_q->cmd_error = 0; + cmd_q->total_pt_ops++; + memset(&desc, 0, sizeof(desc)); + desc.dwouv.dws.byte0 = CMD_AE4_DESC_DW0_VAL; + + desc.dw1.status = 0; + desc.dw1.err_code = 0; + desc.dw1.desc_id = 0; + + desc.length = pt_engine->src_len; + + desc.src_lo = upper_32_bits(pt_engine->src_dma); + desc.src_hi = lower_32_bits(pt_engine->src_dma); + desc.dst_lo = upper_32_bits(pt_engine->dst_dma); + desc.dst_hi = lower_32_bits(pt_engine->dst_dma); + + return ae4_core_execute_cmd(&desc, ae4cmd_q); +} + +static int pt_dma_start_desc(struct pt_dma_desc *desc, struct pt_dma_chan *chan) { struct pt_passthru_engine *pt_engine; struct pt_device *pt; @@ -56,13 +169,18 @@ static int pt_dma_start_desc(struct pt_dma_desc *desc) pt_cmd = &desc->pt_cmd; pt = pt_cmd->pt; - cmd_q = &pt->cmd_q; + + cmd_q = pt_get_cmd_queue(pt, chan); + pt_engine = &pt_cmd->passthru; pt->tdata.cmd = pt_cmd; /* Execute the command */ - pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine); + if (pt->ver == AE4_DMA_VERSION) + pt_cmd->ret = pt_core_perform_passthru_ae4(cmd_q, pt_engine); + else + pt_cmd->ret = pt_core_perform_passthru(cmd_q, pt_engine); return 0; } @@ -151,7 +269,7 @@ static void pt_cmd_callback(void *data, int err) if (!desc) break; - ret = pt_dma_start_desc(desc); + ret = pt_dma_start_desc(desc, chan); if (!ret) break; @@ -186,7 +304,10 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan, { struct pt_dma_chan *chan = to_pt_chan(dma_chan); struct pt_passthru_engine *pt_engine; + struct pt_device *pt = chan->pt; + struct ae4_cmd_queue *ae4cmd_q; struct pt_dma_desc *desc; + struct ae4_device *ae4; struct pt_cmd *pt_cmd; desc = pt_alloc_dma_desc(chan, flags); @@ -194,7 +315,7 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan, return NULL; pt_cmd = &desc->pt_cmd; - pt_cmd->pt = chan->pt; + pt_cmd->pt = pt; pt_engine = &pt_cmd->passthru; pt_cmd->engine = PT_ENGINE_PASSTHRU; pt_engine->src_dma = src; @@ -205,6 +326,14 @@ static struct pt_dma_desc *pt_create_desc(struct dma_chan *dma_chan, desc->len = len; + if (pt->ver == AE4_DMA_VERSION) { + ae4 = container_of(pt, struct ae4_device, pt); + ae4cmd_q = &ae4->ae4cmd_q[chan->id]; + mutex_lock(&ae4cmd_q->cmd_lock); + list_add_tail(&pt_cmd->entry, &ae4cmd_q->cmd); + mutex_unlock(&ae4cmd_q->cmd_lock); + } + return desc; } @@ -258,24 +387,43 @@ static void pt_issue_pending(struct dma_chan *dma_chan) pt_cmd_callback(desc, 0); } +static void pt_check_status_trans_ae4(struct pt_device *pt, struct pt_cmd_queue *cmd_q) +{ + struct ae4_cmd_queue *ae4cmd_q = container_of(cmd_q, struct ae4_cmd_queue, cmd_q); + int i; + + for (i = 0; i < CMD_Q_LEN; i++) + ae4_check_status_error(ae4cmd_q, i); +} + static enum dma_status pt_tx_status(struct dma_chan *c, dma_cookie_t cookie, struct dma_tx_state *txstate) { - struct pt_device *pt = to_pt_chan(c)->pt; - struct pt_cmd_queue *cmd_q = &pt->cmd_q; + struct pt_dma_chan *chan = to_pt_chan(c); + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; + + cmd_q = pt_get_cmd_queue(pt, chan); + + if (pt->ver == AE4_DMA_VERSION) + pt_check_status_trans_ae4(pt, cmd_q); + else + pt_check_status_trans(pt, cmd_q); - pt_check_status_trans(pt, cmd_q); return dma_cookie_status(c, cookie, txstate); } static int pt_pause(struct dma_chan *dma_chan) { struct pt_dma_chan *chan = to_pt_chan(dma_chan); + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; unsigned long flags; spin_lock_irqsave(&chan->vc.lock, flags); - pt_stop_queue(&chan->pt->cmd_q); + cmd_q = pt_get_cmd_queue(pt, chan); + pt_stop_queue(cmd_q); spin_unlock_irqrestore(&chan->vc.lock, flags); return 0; @@ -285,10 +433,13 @@ static int pt_resume(struct dma_chan *dma_chan) { struct pt_dma_chan *chan = to_pt_chan(dma_chan); struct pt_dma_desc *desc = NULL; + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; unsigned long flags; spin_lock_irqsave(&chan->vc.lock, flags); - pt_start_queue(&chan->pt->cmd_q); + cmd_q = pt_get_cmd_queue(pt, chan); + pt_start_queue(cmd_q); desc = pt_next_dma_desc(chan); spin_unlock_irqrestore(&chan->vc.lock, flags); @@ -302,11 +453,17 @@ static int pt_resume(struct dma_chan *dma_chan) static int pt_terminate_all(struct dma_chan *dma_chan) { struct pt_dma_chan *chan = to_pt_chan(dma_chan); + struct pt_device *pt = chan->pt; + struct pt_cmd_queue *cmd_q; unsigned long flags; - struct pt_cmd_queue *cmd_q = &chan->pt->cmd_q; LIST_HEAD(head); - iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010); + cmd_q = pt_get_cmd_queue(pt, chan); + if (pt->ver == AE4_DMA_VERSION) + pt_stop_queue(cmd_q); + else + iowrite32(SUPPORTED_INTERRUPTS, cmd_q->reg_control + 0x0010); + spin_lock_irqsave(&chan->vc.lock, flags); vchan_get_all_descriptors(&chan->vc, &head); spin_unlock_irqrestore(&chan->vc.lock, flags); @@ -319,14 +476,24 @@ static int pt_terminate_all(struct dma_chan *dma_chan) int pt_dmaengine_register(struct pt_device *pt) { - struct pt_dma_chan *chan; struct dma_device *dma_dev = &pt->dma_dev; - char *cmd_cache_name; + struct ae4_cmd_queue *ae4cmd_q = NULL; + struct ae4_device *ae4 = NULL; + struct pt_dma_chan *chan; char *desc_cache_name; - int ret; + char *cmd_cache_name; + int ret, i; + + if (pt->ver == AE4_DMA_VERSION) + ae4 = container_of(pt, struct ae4_device, pt); + + if (ae4) + pt->pt_dma_chan = devm_kcalloc(pt->dev, ae4->cmd_q_count, + sizeof(*pt->pt_dma_chan), GFP_KERNEL); + else + pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan), + GFP_KERNEL); - pt->pt_dma_chan = devm_kzalloc(pt->dev, sizeof(*pt->pt_dma_chan), - GFP_KERNEL); if (!pt->pt_dma_chan) return -ENOMEM; @@ -368,9 +535,6 @@ int pt_dmaengine_register(struct pt_device *pt) INIT_LIST_HEAD(&dma_dev->channels); - chan = pt->pt_dma_chan; - chan->pt = pt; - /* Set base and prep routines */ dma_dev->device_free_chan_resources = pt_free_chan_resources; dma_dev->device_prep_dma_memcpy = pt_prep_dma_memcpy; @@ -382,8 +546,21 @@ int pt_dmaengine_register(struct pt_device *pt) dma_dev->device_terminate_all = pt_terminate_all; dma_dev->device_synchronize = pt_synchronize; - chan->vc.desc_free = pt_do_cleanup; - vchan_init(&chan->vc, dma_dev); + if (ae4) { + for (i = 0; i < ae4->cmd_q_count; i++) { + chan = pt->pt_dma_chan + i; + ae4cmd_q = &ae4->ae4cmd_q[i]; + chan->id = ae4cmd_q->id; + chan->pt = pt; + chan->vc.desc_free = pt_do_cleanup; + vchan_init(&chan->vc, dma_dev); + } + } else { + chan = pt->pt_dma_chan; + chan->pt = pt; + chan->vc.desc_free = pt_do_cleanup; + vchan_init(&chan->vc, dma_dev); + } ret = dma_async_device_register(dma_dev); if (ret) @@ -399,6 +576,7 @@ err_cache: return ret; } +EXPORT_SYMBOL_GPL(pt_dmaengine_register); void pt_dmaengine_unregister(struct pt_device *pt) { diff --git a/drivers/dma/ptdma/ptdma-pci.c b/drivers/dma/amd/ptdma/ptdma-pci.c index 22739ff0c3c5..22739ff0c3c5 100644 --- a/drivers/dma/ptdma/ptdma-pci.c +++ b/drivers/dma/amd/ptdma/ptdma-pci.c diff --git a/drivers/dma/ptdma/ptdma.h b/drivers/dma/amd/ptdma/ptdma.h index 39bc37268235..0a7939105e51 100644 --- a/drivers/dma/ptdma/ptdma.h +++ b/drivers/dma/amd/ptdma/ptdma.h @@ -22,7 +22,7 @@ #include <linux/wait.h> #include <linux/dmapool.h> -#include "../virt-dma.h" +#include "../../virt-dma.h" #define MAX_PT_NAME_LEN 16 #define MAX_DMAPOOL_NAME_LEN 32 @@ -184,6 +184,7 @@ struct pt_dma_desc { struct pt_dma_chan { struct virt_dma_chan vc; struct pt_device *pt; + u32 id; }; struct pt_cmd_queue { @@ -262,6 +263,7 @@ struct pt_device { unsigned long total_interrupts; struct pt_tasklet_data tdata; + int ver; }; /* diff --git a/drivers/dma/amd/qdma/qdma.c b/drivers/dma/amd/qdma/qdma.c index 66f00ad67351..8fb2d5e1df20 100644 --- a/drivers/dma/amd/qdma/qdma.c +++ b/drivers/dma/amd/qdma/qdma.c @@ -283,16 +283,20 @@ static int qdma_check_queue_status(struct qdma_device *qdev, static int qdma_clear_queue_context(const struct qdma_queue *queue) { - enum qdma_ctxt_type h2c_types[] = { QDMA_CTXT_DESC_SW_H2C, - QDMA_CTXT_DESC_HW_H2C, - QDMA_CTXT_DESC_CR_H2C, - QDMA_CTXT_PFTCH, }; - enum qdma_ctxt_type c2h_types[] = { QDMA_CTXT_DESC_SW_C2H, - QDMA_CTXT_DESC_HW_C2H, - QDMA_CTXT_DESC_CR_C2H, - QDMA_CTXT_PFTCH, }; + static const enum qdma_ctxt_type h2c_types[] = { + QDMA_CTXT_DESC_SW_H2C, + QDMA_CTXT_DESC_HW_H2C, + QDMA_CTXT_DESC_CR_H2C, + QDMA_CTXT_PFTCH, + }; + static const enum qdma_ctxt_type c2h_types[] = { + QDMA_CTXT_DESC_SW_C2H, + QDMA_CTXT_DESC_HW_C2H, + QDMA_CTXT_DESC_CR_C2H, + QDMA_CTXT_PFTCH, + }; struct qdma_device *qdev = queue->qdev; - enum qdma_ctxt_type *type; + const enum qdma_ctxt_type *type; int ret, num, i; if (queue->dir == DMA_MEM_TO_DEV) { diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 7ba52dee40a9..20b10c15c696 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -875,6 +875,27 @@ static struct dma_chan *bcm2835_dma_xlate(struct of_phandle_args *spec, return chan; } +static int bcm2835_dma_suspend_late(struct device *dev) +{ + struct bcm2835_dmadev *od = dev_get_drvdata(dev); + struct bcm2835_chan *c, *next; + + list_for_each_entry_safe(c, next, &od->ddev.channels, + vc.chan.device_node) { + void __iomem *chan_base = c->chan_base; + + /* Check if DMA channel is busy */ + if (readl(chan_base + BCM2835_DMA_ADDR)) + return -EBUSY; + } + + return 0; +} + +static const struct dev_pm_ops bcm2835_dma_pm_ops = { + SET_LATE_SYSTEM_SLEEP_PM_OPS(bcm2835_dma_suspend_late, NULL) +}; + static int bcm2835_dma_probe(struct platform_device *pdev) { struct bcm2835_dmadev *od; @@ -1033,6 +1054,7 @@ static struct platform_driver bcm2835_dma_driver = { .driver = { .name = "bcm2835-dma", .of_match_table = of_match_ptr(bcm2835_dma_of_match), + .pm = pm_ptr(&bcm2835_dma_pm_ops), }, }; diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index b7f15ab96855..443b2430466c 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -480,8 +480,8 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan, bool disable_req, bool enable_sg) { struct dma_slave_config *cfg = &fsl_chan->cfg; + u32 burst = 0; u16 csr = 0; - u32 burst; /* * eDMA hardware SGs require the TCDs to be stored in little @@ -496,16 +496,30 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan, fsl_edma_set_tcd_to_le(fsl_chan, tcd, soff, soff); - if (fsl_chan->is_multi_fifo) { - /* set mloff to support multiple fifo */ - burst = cfg->direction == DMA_DEV_TO_MEM ? - cfg->src_maxburst : cfg->dst_maxburst; - nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-(burst * 4)); - /* enable DMLOE/SMLOE */ - if (cfg->direction == DMA_MEM_TO_DEV) { + /* If we expect to have either multi_fifo or a port window size, + * we will use minor loop offset, meaning bits 29-10 will be used for + * address offset, while bits 9-0 will be used to tell DMA how much + * data to read from addr. + * If we don't have either of those, will use a major loop reading from addr + * nbytes (29bits). + */ + if (cfg->direction == DMA_MEM_TO_DEV) { + if (fsl_chan->is_multi_fifo) + burst = cfg->dst_maxburst * 4; + if (cfg->dst_port_window_size) + burst = cfg->dst_port_window_size * cfg->dst_addr_width; + if (burst) { + nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-burst); nbytes |= EDMA_V3_TCD_NBYTES_DMLOE; nbytes &= ~EDMA_V3_TCD_NBYTES_SMLOE; - } else { + } + } else { + if (fsl_chan->is_multi_fifo) + burst = cfg->src_maxburst * 4; + if (cfg->src_port_window_size) + burst = cfg->src_port_window_size * cfg->src_addr_width; + if (burst) { + nbytes |= EDMA_V3_TCD_NBYTES_MLOFF(-burst); nbytes |= EDMA_V3_TCD_NBYTES_SMLOE; nbytes &= ~EDMA_V3_TCD_NBYTES_DMLOE; } @@ -623,11 +637,15 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic( dst_addr = fsl_chan->dma_dev_addr; soff = fsl_chan->cfg.dst_addr_width; doff = fsl_chan->is_multi_fifo ? 4 : 0; + if (fsl_chan->cfg.dst_port_window_size) + doff = fsl_chan->cfg.dst_addr_width; } else if (direction == DMA_DEV_TO_MEM) { src_addr = fsl_chan->dma_dev_addr; dst_addr = dma_buf_next; soff = fsl_chan->is_multi_fifo ? 4 : 0; doff = fsl_chan->cfg.src_addr_width; + if (fsl_chan->cfg.src_port_window_size) + soff = fsl_chan->cfg.src_addr_width; } else { /* DMA_DEV_TO_DEV */ src_addr = fsl_chan->cfg.src_addr; diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index fe8f103d4a63..10a5565ddfd7 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -68,6 +68,8 @@ #define EDMA_V3_CH_CSR_EEI BIT(2) #define EDMA_V3_CH_CSR_DONE BIT(30) #define EDMA_V3_CH_CSR_ACTIVE BIT(31) +#define EDMA_V3_CH_ES_ERR BIT(31) +#define EDMA_V3_MP_ES_VLD BIT(31) enum fsl_edma_pm_state { RUNNING = 0, @@ -241,6 +243,7 @@ struct fsl_edma_engine { const struct fsl_edma_drvdata *drvdata; u32 n_chans; int txirq; + int txirq_16_31; int errirq; bool big_endian; struct edma_regs regs; diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 1a613236b3e4..f989b6c9c0a9 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -3,10 +3,11 @@ * drivers/dma/fsl-edma.c * * Copyright 2013-2014 Freescale Semiconductor, Inc. + * Copyright 2024 NXP * * Driver for the Freescale eDMA engine with flexible channel multiplexing * capability for DMA request sources. The eDMA block can be found on some - * Vybrid and Layerscape SoCs. + * Vybrid, Layerscape and S32G SoCs. */ #include <dt-bindings/dma/fsl-edma.h> @@ -72,6 +73,60 @@ static irqreturn_t fsl_edma2_tx_handler(int irq, void *devi_id) return fsl_edma_tx_handler(irq, fsl_chan->edma); } +static irqreturn_t fsl_edma3_or_tx_handler(int irq, void *dev_id, + u8 start, u8 end) +{ + struct fsl_edma_engine *fsl_edma = dev_id; + struct fsl_edma_chan *chan; + int i; + + end = min(end, fsl_edma->n_chans); + + for (i = start; i < end; i++) { + chan = &fsl_edma->chans[i]; + + fsl_edma3_tx_handler(irq, chan); + } + + return IRQ_HANDLED; +} + +static irqreturn_t fsl_edma3_tx_0_15_handler(int irq, void *dev_id) +{ + return fsl_edma3_or_tx_handler(irq, dev_id, 0, 16); +} + +static irqreturn_t fsl_edma3_tx_16_31_handler(int irq, void *dev_id) +{ + return fsl_edma3_or_tx_handler(irq, dev_id, 16, 32); +} + +static irqreturn_t fsl_edma3_or_err_handler(int irq, void *dev_id) +{ + struct fsl_edma_engine *fsl_edma = dev_id; + struct edma_regs *regs = &fsl_edma->regs; + unsigned int err, ch, ch_es; + struct fsl_edma_chan *chan; + + err = edma_readl(fsl_edma, regs->es); + if (!(err & EDMA_V3_MP_ES_VLD)) + return IRQ_NONE; + + for (ch = 0; ch < fsl_edma->n_chans; ch++) { + chan = &fsl_edma->chans[ch]; + + ch_es = edma_readl_chreg(chan, ch_es); + if (!(ch_es & EDMA_V3_CH_ES_ERR)) + continue; + + edma_writel_chreg(chan, EDMA_V3_CH_ES_ERR, ch_es); + fsl_edma_disable_request(chan); + fsl_edma->chans[ch].status = DMA_ERROR; + } + + return IRQ_HANDLED; +} + static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id) { struct fsl_edma_engine *fsl_edma = dev_id; @@ -274,6 +329,49 @@ static int fsl_edma3_irq_init(struct platform_device *pdev, struct fsl_edma_engi return 0; } +static int fsl_edma3_or_irq_init(struct platform_device *pdev, + struct fsl_edma_engine *fsl_edma) +{ + int ret; + + fsl_edma->txirq = platform_get_irq_byname(pdev, "tx-0-15"); + if (fsl_edma->txirq < 0) + return fsl_edma->txirq; + + fsl_edma->txirq_16_31 = platform_get_irq_byname(pdev, "tx-16-31"); + if (fsl_edma->txirq_16_31 < 0) + return fsl_edma->txirq_16_31; + + fsl_edma->errirq = platform_get_irq_byname(pdev, "err"); + if (fsl_edma->errirq < 0) + return fsl_edma->errirq; + + ret = devm_request_irq(&pdev->dev, fsl_edma->txirq, + fsl_edma3_tx_0_15_handler, 0, "eDMA tx0_15", + fsl_edma); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Can't register eDMA tx0_15 IRQ.\n"); + + if (fsl_edma->n_chans > 16) { + ret = devm_request_irq(&pdev->dev, fsl_edma->txirq_16_31, + fsl_edma3_tx_16_31_handler, 0, + "eDMA tx16_31", fsl_edma); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Can't register eDMA tx16_31 IRQ.\n"); + } + + ret = devm_request_irq(&pdev->dev, fsl_edma->errirq, + fsl_edma3_or_err_handler, 0, "eDMA err", + fsl_edma); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Can't register eDMA err IRQ.\n"); + + return 0; +} + static int fsl_edma2_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma) @@ -404,6 +502,14 @@ static struct fsl_edma_drvdata imx95_data5 = { .setup_irq = fsl_edma3_irq_init, }; +static const struct fsl_edma_drvdata s32g2_data = { + .dmamuxs = DMAMUX_NR, + .chreg_space_sz = EDMA_TCD, + .chreg_off = 0x4000, + .flags = FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MUX_SWAP, + .setup_irq = fsl_edma3_or_irq_init, +}; + static const struct of_device_id fsl_edma_dt_ids[] = { { .compatible = "fsl,vf610-edma", .data = &vf610_data}, { .compatible = "fsl,ls1028a-edma", .data = &ls1028a_data}, @@ -413,6 +519,7 @@ static const struct of_device_id fsl_edma_dt_ids[] = { { .compatible = "fsl,imx93-edma3", .data = &imx93_data3}, { .compatible = "fsl,imx93-edma4", .data = &imx93_data4}, { .compatible = "fsl,imx95-edma5", .data = &imx95_data5}, + { .compatible = "nxp,s32g2-edma", .data = &s32g2_data}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids); @@ -545,10 +652,6 @@ static int fsl_edma_probe(struct platform_device *pdev) for (i = 0; i < fsl_edma->drvdata->dmamuxs; i++) { char clkname[32]; - /* eDMAv3 mux register move to TCD area if ch_mux exist */ - if (drvdata->flags & FSL_EDMA_DRV_SPLIT_REG) - break; - fsl_edma->muxbase[i] = devm_platform_ioremap_resource(pdev, 1 + i); if (IS_ERR(fsl_edma->muxbase[i])) { @@ -677,7 +780,7 @@ static int fsl_edma_probe(struct platform_device *pdev) } ret = of_dma_controller_register(np, - drvdata->flags & FSL_EDMA_DRV_SPLIT_REG ? fsl_edma3_xlate : fsl_edma_xlate, + drvdata->dmamuxs ? fsl_edma_xlate : fsl_edma3_xlate, fsl_edma); if (ret) { dev_err(&pdev->dev, diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index 57f1bf2ab20b..ff94ee892339 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -28,7 +28,6 @@ struct idxd_cdev_context { * global to avoid conflict file names. */ static DEFINE_IDA(file_ida); -static DEFINE_MUTEX(ida_lock); /* * ictx is an array based off of accelerator types. enum idxd_type @@ -123,9 +122,7 @@ static void idxd_file_dev_release(struct device *dev) struct idxd_device *idxd = wq->idxd; int rc; - mutex_lock(&ida_lock); ida_free(&file_ida, ctx->id); - mutex_unlock(&ida_lock); /* Wait for in-flight operations to complete. */ if (wq_shared(wq)) { @@ -284,9 +281,7 @@ static int idxd_cdev_open(struct inode *inode, struct file *filp) } idxd_cdev = wq->idxd_cdev; - mutex_lock(&ida_lock); ctx->id = ida_alloc(&file_ida, GFP_KERNEL); - mutex_unlock(&ida_lock); if (ctx->id < 0) { dev_warn(dev, "ida alloc failure\n"); goto failed_ida; diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index d84e21daa991..214b8039439f 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -374,6 +374,17 @@ struct idxd_device { struct dentry *dbgfs_evl_file; bool user_submission_safe; + + struct idxd_saved_states *idxd_saved; +}; + +struct idxd_saved_states { + struct idxd_device saved_idxd; + struct idxd_evl saved_evl; + struct idxd_engine **saved_engines; + struct idxd_wq **saved_wqs; + struct idxd_group **saved_groups; + unsigned long *saved_wq_enable_map; }; static inline unsigned int evl_ent_size(struct idxd_device *idxd) @@ -725,8 +736,6 @@ static inline void idxd_desc_complete(struct idxd_desc *desc, &desc->txd, &status); } -int idxd_register_bus_type(void); -void idxd_unregister_bus_type(void); int idxd_register_devices(struct idxd_device *idxd); void idxd_unregister_devices(struct idxd_device *idxd); void idxd_wqs_quiesce(struct idxd_device *idxd); @@ -742,6 +751,8 @@ void idxd_unmask_error_interrupts(struct idxd_device *idxd); /* device control */ int idxd_device_drv_probe(struct idxd_dev *idxd_dev); +int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev, + const struct pci_device_id *id); void idxd_device_drv_remove(struct idxd_dev *idxd_dev); int idxd_drv_enable_wq(struct idxd_wq *wq); void idxd_drv_disable_wq(struct idxd_wq *wq); diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 140f8d772bee..b946f78f85e1 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -78,6 +78,8 @@ static struct pci_device_id idxd_pci_tbl[] = { { PCI_DEVICE_DATA(INTEL, IAX_SPR0, &idxd_driver_data[IDXD_TYPE_IAX]) }, /* IAA on DMR platforms */ { PCI_DEVICE_DATA(INTEL, IAA_DMR, &idxd_driver_data[IDXD_TYPE_IAX]) }, + /* IAA PTL platforms */ + { PCI_DEVICE_DATA(INTEL, IAA_PTL, &idxd_driver_data[IDXD_TYPE_IAX]) }, { 0, } }; MODULE_DEVICE_TABLE(pci, idxd_pci_tbl); @@ -723,67 +725,464 @@ static void idxd_cleanup(struct idxd_device *idxd) idxd_disable_sva(idxd->pdev); } -static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +/* + * Attach IDXD device to IDXD driver. + */ +static int idxd_bind(struct device_driver *drv, const char *buf) { - struct device *dev = &pdev->dev; - struct idxd_device *idxd; - struct idxd_driver_data *data = (struct idxd_driver_data *)id->driver_data; + const struct bus_type *bus = drv->bus; + struct device *dev; + int err = -ENODEV; + + dev = bus_find_device_by_name(bus, NULL, buf); + if (dev) + err = device_driver_attach(drv, dev); + + put_device(dev); + + return err; +} + +/* + * Detach IDXD device from driver. + */ +static void idxd_unbind(struct device_driver *drv, const char *buf) +{ + const struct bus_type *bus = drv->bus; + struct device *dev; + + dev = bus_find_device_by_name(bus, NULL, buf); + if (dev && dev->driver == drv) + device_release_driver(dev); + + put_device(dev); +} + +#define idxd_free_saved_configs(saved_configs, count) \ + do { \ + int i; \ + \ + for (i = 0; i < (count); i++) \ + kfree(saved_configs[i]); \ + } while (0) + +static void idxd_free_saved(struct idxd_group **saved_groups, + struct idxd_engine **saved_engines, + struct idxd_wq **saved_wqs, + struct idxd_device *idxd) +{ + if (saved_groups) + idxd_free_saved_configs(saved_groups, idxd->max_groups); + if (saved_engines) + idxd_free_saved_configs(saved_engines, idxd->max_engines); + if (saved_wqs) + idxd_free_saved_configs(saved_wqs, idxd->max_wqs); +} + +/* + * Save IDXD device configurations including engines, groups, wqs etc. + * The saved configurations can be restored when needed. + */ +static int idxd_device_config_save(struct idxd_device *idxd, + struct idxd_saved_states *idxd_saved) +{ + struct device *dev = &idxd->pdev->dev; + int i; + + memcpy(&idxd_saved->saved_idxd, idxd, sizeof(*idxd)); + + if (idxd->evl) { + memcpy(&idxd_saved->saved_evl, idxd->evl, + sizeof(struct idxd_evl)); + } + + struct idxd_group **saved_groups __free(kfree) = + kcalloc_node(idxd->max_groups, + sizeof(struct idxd_group *), + GFP_KERNEL, dev_to_node(dev)); + if (!saved_groups) + return -ENOMEM; + + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *saved_group __free(kfree) = + kzalloc_node(sizeof(*saved_group), GFP_KERNEL, + dev_to_node(dev)); + + if (!saved_group) { + /* Free saved groups */ + idxd_free_saved(saved_groups, NULL, NULL, idxd); + + return -ENOMEM; + } + + memcpy(saved_group, idxd->groups[i], sizeof(*saved_group)); + saved_groups[i] = no_free_ptr(saved_group); + } + + struct idxd_engine **saved_engines = + kcalloc_node(idxd->max_engines, + sizeof(struct idxd_engine *), + GFP_KERNEL, dev_to_node(dev)); + if (!saved_engines) { + /* Free saved groups */ + idxd_free_saved(saved_groups, NULL, NULL, idxd); + + return -ENOMEM; + } + for (i = 0; i < idxd->max_engines; i++) { + struct idxd_engine *saved_engine __free(kfree) = + kzalloc_node(sizeof(*saved_engine), GFP_KERNEL, + dev_to_node(dev)); + if (!saved_engine) { + /* Free saved groups and engines */ + idxd_free_saved(saved_groups, saved_engines, NULL, + idxd); + + return -ENOMEM; + } + + memcpy(saved_engine, idxd->engines[i], sizeof(*saved_engine)); + saved_engines[i] = no_free_ptr(saved_engine); + } + + unsigned long *saved_wq_enable_map __free(bitmap) = + bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, + dev_to_node(dev)); + if (!saved_wq_enable_map) { + /* Free saved groups and engines */ + idxd_free_saved(saved_groups, saved_engines, NULL, idxd); + + return -ENOMEM; + } + + bitmap_copy(saved_wq_enable_map, idxd->wq_enable_map, idxd->max_wqs); + + struct idxd_wq **saved_wqs __free(kfree) = + kcalloc_node(idxd->max_wqs, sizeof(struct idxd_wq *), + GFP_KERNEL, dev_to_node(dev)); + if (!saved_wqs) { + /* Free saved groups and engines */ + idxd_free_saved(saved_groups, saved_engines, NULL, idxd); + + return -ENOMEM; + } + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *saved_wq __free(kfree) = + kzalloc_node(sizeof(*saved_wq), GFP_KERNEL, + dev_to_node(dev)); + struct idxd_wq *wq; + + if (!saved_wq) { + /* Free saved groups, engines, and wqs */ + idxd_free_saved(saved_groups, saved_engines, saved_wqs, + idxd); + + return -ENOMEM; + } + + if (!test_bit(i, saved_wq_enable_map)) + continue; + + wq = idxd->wqs[i]; + mutex_lock(&wq->wq_lock); + memcpy(saved_wq, wq, sizeof(*saved_wq)); + saved_wqs[i] = no_free_ptr(saved_wq); + mutex_unlock(&wq->wq_lock); + } + + /* Save configurations */ + idxd_saved->saved_groups = no_free_ptr(saved_groups); + idxd_saved->saved_engines = no_free_ptr(saved_engines); + idxd_saved->saved_wq_enable_map = no_free_ptr(saved_wq_enable_map); + idxd_saved->saved_wqs = no_free_ptr(saved_wqs); + + return 0; +} + +/* + * Restore IDXD device configurations including engines, groups, wqs etc + * that were saved before. + */ +static void idxd_device_config_restore(struct idxd_device *idxd, + struct idxd_saved_states *idxd_saved) +{ + struct idxd_evl *saved_evl = &idxd_saved->saved_evl; + int i; + + idxd->rdbuf_limit = idxd_saved->saved_idxd.rdbuf_limit; + + if (saved_evl) + idxd->evl->size = saved_evl->size; + + for (i = 0; i < idxd->max_groups; i++) { + struct idxd_group *saved_group, *group; + + saved_group = idxd_saved->saved_groups[i]; + group = idxd->groups[i]; + + group->rdbufs_allowed = saved_group->rdbufs_allowed; + group->rdbufs_reserved = saved_group->rdbufs_reserved; + group->tc_a = saved_group->tc_a; + group->tc_b = saved_group->tc_b; + group->use_rdbuf_limit = saved_group->use_rdbuf_limit; + + kfree(saved_group); + } + kfree(idxd_saved->saved_groups); + + for (i = 0; i < idxd->max_engines; i++) { + struct idxd_engine *saved_engine, *engine; + + saved_engine = idxd_saved->saved_engines[i]; + engine = idxd->engines[i]; + + engine->group = saved_engine->group; + + kfree(saved_engine); + } + kfree(idxd_saved->saved_engines); + + bitmap_copy(idxd->wq_enable_map, idxd_saved->saved_wq_enable_map, + idxd->max_wqs); + bitmap_free(idxd_saved->saved_wq_enable_map); + + for (i = 0; i < idxd->max_wqs; i++) { + struct idxd_wq *saved_wq, *wq; + size_t len; + + if (!test_bit(i, idxd->wq_enable_map)) + continue; + + saved_wq = idxd_saved->saved_wqs[i]; + wq = idxd->wqs[i]; + + mutex_lock(&wq->wq_lock); + + wq->group = saved_wq->group; + wq->flags = saved_wq->flags; + wq->threshold = saved_wq->threshold; + wq->size = saved_wq->size; + wq->priority = saved_wq->priority; + wq->type = saved_wq->type; + len = strlen(saved_wq->name) + 1; + strscpy(wq->name, saved_wq->name, len); + wq->max_xfer_bytes = saved_wq->max_xfer_bytes; + wq->max_batch_size = saved_wq->max_batch_size; + wq->enqcmds_retries = saved_wq->enqcmds_retries; + wq->descs = saved_wq->descs; + wq->idxd_chan = saved_wq->idxd_chan; + len = strlen(saved_wq->driver_name) + 1; + strscpy(wq->driver_name, saved_wq->driver_name, len); + + mutex_unlock(&wq->wq_lock); + + kfree(saved_wq); + } + + kfree(idxd_saved->saved_wqs); +} + +static void idxd_reset_prepare(struct pci_dev *pdev) +{ + struct idxd_device *idxd = pci_get_drvdata(pdev); + struct device *dev = &idxd->pdev->dev; + const char *idxd_name; int rc; - rc = pci_enable_device(pdev); - if (rc) - return rc; + dev = &idxd->pdev->dev; + idxd_name = dev_name(idxd_confdev(idxd)); - dev_dbg(dev, "Alloc IDXD context\n"); - idxd = idxd_alloc(pdev, data); - if (!idxd) { - rc = -ENOMEM; - goto err_idxd_alloc; + struct idxd_saved_states *idxd_saved __free(kfree) = + kzalloc_node(sizeof(*idxd_saved), GFP_KERNEL, + dev_to_node(&pdev->dev)); + if (!idxd_saved) { + dev_err(dev, "HALT: no memory\n"); + + return; } - dev_dbg(dev, "Mapping BARs\n"); - idxd->reg_base = pci_iomap(pdev, IDXD_MMIO_BAR, 0); - if (!idxd->reg_base) { - rc = -ENOMEM; - goto err_iomap; + /* Save IDXD configurations. */ + rc = idxd_device_config_save(idxd, idxd_saved); + if (rc < 0) { + dev_err(dev, "HALT: cannot save %s configs\n", idxd_name); + + return; + } + + idxd->idxd_saved = no_free_ptr(idxd_saved); + + /* Save PCI device state. */ + pci_save_state(idxd->pdev); +} + +static void idxd_reset_done(struct pci_dev *pdev) +{ + struct idxd_device *idxd = pci_get_drvdata(pdev); + const char *idxd_name; + struct device *dev; + int rc, i; + + if (!idxd->idxd_saved) + return; + + dev = &idxd->pdev->dev; + idxd_name = dev_name(idxd_confdev(idxd)); + + /* Restore PCI device state. */ + pci_restore_state(idxd->pdev); + + /* Unbind idxd device from driver. */ + idxd_unbind(&idxd_drv.drv, idxd_name); + + /* + * Probe PCI device without allocating or changing + * idxd software data which keeps the same as before FLR. + */ + idxd_pci_probe_alloc(idxd, NULL, NULL); + + /* Restore IDXD configurations. */ + idxd_device_config_restore(idxd, idxd->idxd_saved); + + /* Re-configure IDXD device if allowed. */ + if (test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) { + rc = idxd_device_config(idxd); + if (rc < 0) { + dev_err(dev, "HALT: %s config fails\n", idxd_name); + goto out; + } + } + + /* Bind IDXD device to driver. */ + rc = idxd_bind(&idxd_drv.drv, idxd_name); + if (rc < 0) { + dev_err(dev, "HALT: binding %s to driver fails\n", idxd_name); + goto out; } - dev_dbg(dev, "Set DMA masks\n"); - rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + /* Bind enabled wq in the IDXD device to driver. */ + for (i = 0; i < idxd->max_wqs; i++) { + if (test_bit(i, idxd->wq_enable_map)) { + struct idxd_wq *wq = idxd->wqs[i]; + char wq_name[32]; + + wq->state = IDXD_WQ_DISABLED; + sprintf(wq_name, "wq%d.%d", idxd->id, wq->id); + /* + * Bind to user driver depending on wq type. + * + * Currently only support user type WQ. Will support + * kernel type WQ in the future. + */ + if (wq->type == IDXD_WQT_USER) + rc = idxd_bind(&idxd_user_drv.drv, wq_name); + else + rc = -EINVAL; + if (rc < 0) { + clear_bit(i, idxd->wq_enable_map); + dev_err(dev, + "HALT: unable to re-enable wq %s\n", + dev_name(wq_confdev(wq))); + } + } + } +out: + kfree(idxd->idxd_saved); +} + +static const struct pci_error_handlers idxd_error_handler = { + .reset_prepare = idxd_reset_prepare, + .reset_done = idxd_reset_done, +}; + +/* + * Probe idxd PCI device. + * If idxd is not given, need to allocate idxd and set up its data. + * + * If idxd is given, idxd was allocated and setup already. Just need to + * configure device without re-allocating and re-configuring idxd data. + * This is useful for recovering from FLR. + */ +int idxd_pci_probe_alloc(struct idxd_device *idxd, struct pci_dev *pdev, + const struct pci_device_id *id) +{ + bool alloc_idxd = idxd ? false : true; + struct idxd_driver_data *data; + struct device *dev; + int rc; + + pdev = idxd ? idxd->pdev : pdev; + dev = &pdev->dev; + data = id ? (struct idxd_driver_data *)id->driver_data : NULL; + rc = pci_enable_device(pdev); if (rc) - goto err; + return rc; + + if (alloc_idxd) { + dev_dbg(dev, "Alloc IDXD context\n"); + idxd = idxd_alloc(pdev, data); + if (!idxd) { + rc = -ENOMEM; + goto err_idxd_alloc; + } + + dev_dbg(dev, "Mapping BARs\n"); + idxd->reg_base = pci_iomap(pdev, IDXD_MMIO_BAR, 0); + if (!idxd->reg_base) { + rc = -ENOMEM; + goto err_iomap; + } + + dev_dbg(dev, "Set DMA masks\n"); + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (rc) + goto err; + } dev_dbg(dev, "Set PCI master\n"); pci_set_master(pdev); pci_set_drvdata(pdev, idxd); - idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET); - rc = idxd_probe(idxd); - if (rc) { - dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n"); - goto err; - } + if (alloc_idxd) { + idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET); + rc = idxd_probe(idxd); + if (rc) { + dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n"); + goto err; + } + + if (data->load_device_defaults) { + rc = data->load_device_defaults(idxd); + if (rc) + dev_warn(dev, "IDXD loading device defaults failed\n"); + } + + rc = idxd_register_devices(idxd); + if (rc) { + dev_err(dev, "IDXD sysfs setup failed\n"); + goto err_dev_register; + } - if (data->load_device_defaults) { - rc = data->load_device_defaults(idxd); + rc = idxd_device_init_debugfs(idxd); if (rc) - dev_warn(dev, "IDXD loading device defaults failed\n"); + dev_warn(dev, "IDXD debugfs failed to setup\n"); } - rc = idxd_register_devices(idxd); - if (rc) { - dev_err(dev, "IDXD sysfs setup failed\n"); - goto err_dev_register; - } + if (!alloc_idxd) { + /* Release interrupts in the IDXD device. */ + idxd_cleanup_interrupts(idxd); - rc = idxd_device_init_debugfs(idxd); - if (rc) - dev_warn(dev, "IDXD debugfs failed to setup\n"); + /* Re-enable interrupts in the IDXD device. */ + rc = idxd_setup_interrupts(idxd); + if (rc) + dev_warn(dev, "IDXD interrupts failed to setup\n"); + } dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n", idxd->hw.version); - idxd->user_submission_safe = data->user_submission_safe; + if (data) + idxd->user_submission_safe = data->user_submission_safe; return 0; @@ -798,6 +1197,11 @@ static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) return rc; } +static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + return idxd_pci_probe_alloc(NULL, pdev, id); +} + void idxd_wqs_quiesce(struct idxd_device *idxd) { struct idxd_wq *wq; @@ -864,6 +1268,7 @@ static struct pci_driver idxd_pci_driver = { .probe = idxd_pci_probe, .remove = idxd_remove, .shutdown = idxd_shutdown, + .err_handler = &idxd_error_handler, }; static int __init idxd_init_module(void) diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index fc049c9c9892..1107db3ce0a3 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -383,15 +383,65 @@ static void process_evl_entries(struct idxd_device *idxd) mutex_unlock(&evl->lock); } +static void idxd_device_flr(struct work_struct *work) +{ + struct idxd_device *idxd = container_of(work, struct idxd_device, work); + int rc; + + /* + * IDXD device requires a Function Level Reset (FLR). + * pci_reset_function() will reset the device with FLR. + */ + rc = pci_reset_function(idxd->pdev); + if (rc) + dev_err(&idxd->pdev->dev, "FLR failed\n"); +} + +static irqreturn_t idxd_halt(struct idxd_device *idxd) +{ + union gensts_reg gensts; + + gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); + if (gensts.state == IDXD_DEVICE_STATE_HALT) { + idxd->state = IDXD_DEV_HALTED; + if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) { + /* + * If we need a software reset, we will throw the work + * on a system workqueue in order to allow interrupts + * for the device command completions. + */ + INIT_WORK(&idxd->work, idxd_device_reinit); + queue_work(idxd->wq, &idxd->work); + } else if (gensts.reset_type == IDXD_DEVICE_RESET_FLR) { + idxd->state = IDXD_DEV_HALTED; + idxd_mask_error_interrupts(idxd); + dev_dbg(&idxd->pdev->dev, + "idxd halted, doing FLR. After FLR, configs are restored\n"); + INIT_WORK(&idxd->work, idxd_device_flr); + queue_work(idxd->wq, &idxd->work); + + } else { + idxd->state = IDXD_DEV_HALTED; + idxd_wqs_quiesce(idxd); + idxd_wqs_unmap_portal(idxd); + idxd_device_clear_state(idxd); + dev_err(&idxd->pdev->dev, + "idxd halted, need system reset"); + + return -ENXIO; + } + } + + return IRQ_HANDLED; +} + irqreturn_t idxd_misc_thread(int vec, void *data) { struct idxd_irq_entry *irq_entry = data; struct idxd_device *idxd = ie_to_idxd(irq_entry); struct device *dev = &idxd->pdev->dev; - union gensts_reg gensts; u32 val = 0; int i; - bool err = false; u32 cause; cause = ioread32(idxd->reg_base + IDXD_INTCAUSE_OFFSET); @@ -401,7 +451,7 @@ irqreturn_t idxd_misc_thread(int vec, void *data) iowrite32(cause, idxd->reg_base + IDXD_INTCAUSE_OFFSET); if (cause & IDXD_INTC_HALT_STATE) - goto halt; + return idxd_halt(idxd); if (cause & IDXD_INTC_ERR) { spin_lock(&idxd->dev_lock); @@ -435,7 +485,6 @@ irqreturn_t idxd_misc_thread(int vec, void *data) for (i = 0; i < 4; i++) dev_warn_ratelimited(dev, "err[%d]: %#16.16llx\n", i, idxd->sw_err.bits[i]); - err = true; } if (cause & IDXD_INTC_INT_HANDLE_REVOKED) { @@ -480,34 +529,6 @@ irqreturn_t idxd_misc_thread(int vec, void *data) dev_warn_once(dev, "Unexpected interrupt cause bits set: %#x\n", val); - if (!err) - goto out; - -halt: - gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET); - if (gensts.state == IDXD_DEVICE_STATE_HALT) { - idxd->state = IDXD_DEV_HALTED; - if (gensts.reset_type == IDXD_DEVICE_RESET_SOFTWARE) { - /* - * If we need a software reset, we will throw the work - * on a system workqueue in order to allow interrupts - * for the device command completions. - */ - INIT_WORK(&idxd->work, idxd_device_reinit); - queue_work(idxd->wq, &idxd->work); - } else { - idxd->state = IDXD_DEV_HALTED; - idxd_wqs_quiesce(idxd); - idxd_wqs_unmap_portal(idxd); - idxd_device_clear_state(idxd); - dev_err(&idxd->pdev->dev, - "idxd halted, need %s.\n", - gensts.reset_type == IDXD_DEVICE_RESET_FLR ? - "FLR" : "system reset"); - } - } - -out: return IRQ_HANDLED; } diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h index c426511f2104..006ba206ab1b 100644 --- a/drivers/dma/idxd/registers.h +++ b/drivers/dma/idxd/registers.h @@ -9,6 +9,7 @@ #define PCI_DEVICE_ID_INTEL_DSA_GNRD 0x11fb #define PCI_DEVICE_ID_INTEL_DSA_DMR 0x1212 #define PCI_DEVICE_ID_INTEL_IAA_DMR 0x1216 +#define PCI_DEVICE_ID_INTEL_IAA_PTL 0xb02d #define DEVICE_VERSION_1 0x100 #define DEVICE_VERSION_2 0x200 diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index f706eae0e76b..6af493f6ba77 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -1979,13 +1979,3 @@ void idxd_unregister_devices(struct idxd_device *idxd) device_unregister(group_confdev(group)); } } - -int idxd_register_bus_type(void) -{ - return bus_register(&dsa_bus_type); -} - -void idxd_unregister_bus_type(void) -{ - bus_unregister(&dsa_bus_type); -} diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c index 40b76b40bc30..fa6e4646fdc2 100644 --- a/drivers/dma/mv_xor.c +++ b/drivers/dma/mv_xor.c @@ -1369,10 +1369,9 @@ static int mv_xor_probe(struct platform_device *pdev) return 0; if (pdev->dev.of_node) { - struct device_node *np; int i = 0; - for_each_child_of_node(pdev->dev.of_node, np) { + for_each_child_of_node_scoped(pdev->dev.of_node, np) { struct mv_xor_chan *chan; dma_cap_mask_t cap_mask; int irq; @@ -1388,7 +1387,6 @@ static int mv_xor_probe(struct platform_device *pdev) irq = irq_of_parse_and_map(np, 0); if (!irq) { ret = -ENODEV; - of_node_put(np); goto err_channel_add; } @@ -1397,7 +1395,6 @@ static int mv_xor_probe(struct platform_device *pdev) if (IS_ERR(chan)) { ret = PTR_ERR(chan); irq_dispose_mapping(irq); - of_node_put(np); goto err_channel_add; } diff --git a/drivers/dma/ptdma/Kconfig b/drivers/dma/ptdma/Kconfig deleted file mode 100644 index b430edd709f9..000000000000 --- a/drivers/dma/ptdma/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -config AMD_PTDMA - tristate "AMD PassThru DMA Engine" - depends on X86_64 && PCI - select DMA_ENGINE - select DMA_VIRTUAL_CHANNELS - help - Enable support for the AMD PTDMA controller. This controller - provides DMA capabilities to perform high bandwidth memory to - memory and IO copy operations. It performs DMA transfer through - queue-based descriptor management. This DMA controller is intended - to be used with AMD Non-Transparent Bridge devices and not for - general purpose peripheral DMA. diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index bbc3276992bb..c14557efd577 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -59,6 +59,9 @@ struct bam_desc_hw { #define DESC_FLAG_NWD BIT(12) #define DESC_FLAG_CMD BIT(11) +#define BAM_NDP_REVISION_START 0x20 +#define BAM_NDP_REVISION_END 0x27 + struct bam_async_desc { struct virt_dma_desc vd; @@ -398,6 +401,7 @@ struct bam_device { /* dma start transaction tasklet */ struct tasklet_struct task; + u32 bam_revision; }; /** @@ -441,8 +445,10 @@ static void bam_reset(struct bam_device *bdev) writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL)); /* set descriptor threshold, start with 4 bytes */ - writel_relaxed(DEFAULT_CNT_THRSHLD, - bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); + if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START, + BAM_NDP_REVISION_END)) + writel_relaxed(DEFAULT_CNT_THRSHLD, + bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); /* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */ writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS)); @@ -1000,9 +1006,10 @@ static void bam_apply_new_config(struct bam_chan *bchan, maxburst = bchan->slave.src_maxburst; else maxburst = bchan->slave.dst_maxburst; - - writel_relaxed(maxburst, - bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); + if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START, + BAM_NDP_REVISION_END)) + writel_relaxed(maxburst, + bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD)); } bchan->reconfigure = 0; @@ -1192,10 +1199,11 @@ static int bam_init(struct bam_device *bdev) u32 val; /* read revision and configuration information */ - if (!bdev->num_ees) { - val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION)); + val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION)); + if (!bdev->num_ees) bdev->num_ees = (val >> NUM_EES_SHIFT) & NUM_EES_MASK; - } + + bdev->bam_revision = val & REVISION_MASK; /* check that configured EE is within range */ if (bdev->ee >= bdev->num_ees) diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 52a7c8f2498f..b1f0001cc99c 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -18,6 +18,7 @@ #include "../virt-dma.h" #define TRE_TYPE_DMA 0x10 +#define TRE_TYPE_IMMEDIATE_DMA 0x11 #define TRE_TYPE_GO 0x20 #define TRE_TYPE_CONFIG0 0x22 @@ -64,6 +65,7 @@ /* DMA TRE */ #define TRE_DMA_LEN GENMASK(23, 0) +#define TRE_DMA_IMMEDIATE_LEN GENMASK(3, 0) /* Register offsets from gpi-top */ #define GPII_n_CH_k_CNTXT_0_OFFS(n, k) (0x20000 + (0x4000 * (n)) + (0x80 * (k))) @@ -1711,6 +1713,7 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc, dma_addr_t address; struct gpi_tre *tre; unsigned int i; + int len; /* first create config tre if applicable */ if (direction == DMA_MEM_TO_DEV && spi->set_config) { @@ -1763,14 +1766,30 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc, tre_idx++; address = sg_dma_address(sgl); - tre->dword[0] = lower_32_bits(address); - tre->dword[1] = upper_32_bits(address); + len = sg_dma_len(sgl); - tre->dword[2] = u32_encode_bits(sg_dma_len(sgl), TRE_DMA_LEN); + /* Support Immediate dma for write transfers for data length up to 8 bytes */ + if (direction == DMA_MEM_TO_DEV && len <= 2 * sizeof(tre->dword[0])) { + /* + * For Immediate dma, data length may not always be length of 8 bytes, + * it can be length less than 8, hence initialize both dword's with 0 + */ + tre->dword[0] = 0; + tre->dword[1] = 0; + memcpy(&tre->dword[0], sg_virt(sgl), len); - tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE); - if (direction == DMA_MEM_TO_DEV) - tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOT); + tre->dword[2] = u32_encode_bits(len, TRE_DMA_IMMEDIATE_LEN); + tre->dword[3] = u32_encode_bits(TRE_TYPE_IMMEDIATE_DMA, TRE_FLAGS_TYPE); + } else { + tre->dword[0] = lower_32_bits(address); + tre->dword[1] = upper_32_bits(address); + + tre->dword[2] = u32_encode_bits(len, TRE_DMA_LEN); + tre->dword[3] = u32_encode_bits(TRE_TYPE_DMA, TRE_FLAGS_TYPE); + } + + tre->dword[3] |= u32_encode_bits(direction == DMA_MEM_TO_DEV, + TRE_FLAGS_IEOT); for (i = 0; i < tre_idx; i++) dev_dbg(dev, "TRE:%d %x:%x:%x:%x\n", i, desc->tre[i].dword[0], diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c index 2679c1f09faf..0c45ce8c74aa 100644 --- a/drivers/dma/sh/rcar-dmac.c +++ b/drivers/dma/sh/rcar-dmac.c @@ -2023,6 +2023,10 @@ static const struct of_device_id rcar_dmac_of_ids[] = { .compatible = "renesas,rcar-gen4-dmac", .data = &rcar_gen4_dmac_data, }, { + /* + * Backward compatibility for between v5.12 - v5.19 + * which didn't combined with "renesas,rcar-gen4-dmac" + */ .compatible = "renesas,dmac-r8a779a0", .data = &rcar_gen4_dmac_data, }, diff --git a/drivers/dma/sun4i-dma.c b/drivers/dma/sun4i-dma.c index f37cdf6f2179..24796aaaddfa 100644 --- a/drivers/dma/sun4i-dma.c +++ b/drivers/dma/sun4i-dma.c @@ -13,7 +13,9 @@ #include <linux/interrupt.h> #include <linux/module.h> #include <linux/of_dma.h> +#include <linux/of_device.h> #include <linux/platform_device.h> +#include <linux/reset.h> #include <linux/slab.h> #include <linux/spinlock.h> @@ -31,12 +33,21 @@ #define SUN4I_DMA_CFG_SRC_ADDR_MODE(mode) ((mode) << 5) #define SUN4I_DMA_CFG_SRC_DRQ_TYPE(type) (type) +#define SUNIV_DMA_CFG_DST_DATA_WIDTH(width) ((width) << 24) +#define SUNIV_DMA_CFG_SRC_DATA_WIDTH(width) ((width) << 8) + +#define SUN4I_MAX_BURST 8 +#define SUNIV_MAX_BURST 4 + /** Normal DMA register values **/ /* Normal DMA source/destination data request type values */ #define SUN4I_NDMA_DRQ_TYPE_SDRAM 0x16 #define SUN4I_NDMA_DRQ_TYPE_LIMIT (0x1F + 1) +#define SUNIV_NDMA_DRQ_TYPE_SDRAM 0x11 +#define SUNIV_NDMA_DRQ_TYPE_LIMIT (0x17 + 1) + /** Normal DMA register layout **/ /* Dedicated DMA source/destination address mode values */ @@ -50,6 +61,9 @@ #define SUN4I_NDMA_CFG_BYTE_COUNT_MODE_REMAIN BIT(15) #define SUN4I_NDMA_CFG_SRC_NON_SECURE BIT(6) +#define SUNIV_NDMA_CFG_CONT_MODE BIT(29) +#define SUNIV_NDMA_CFG_WAIT_STATE(n) ((n) << 26) + /** Dedicated DMA register values **/ /* Dedicated DMA source/destination address mode values */ @@ -62,6 +76,9 @@ #define SUN4I_DDMA_DRQ_TYPE_SDRAM 0x1 #define SUN4I_DDMA_DRQ_TYPE_LIMIT (0x1F + 1) +#define SUNIV_DDMA_DRQ_TYPE_SDRAM 0x1 +#define SUNIV_DDMA_DRQ_TYPE_LIMIT (0x9 + 1) + /** Dedicated DMA register layout **/ /* Dedicated DMA configuration register layout */ @@ -115,6 +132,11 @@ #define SUN4I_DMA_NR_MAX_VCHANS \ (SUN4I_NDMA_NR_MAX_VCHANS + SUN4I_DDMA_NR_MAX_VCHANS) +#define SUNIV_NDMA_NR_MAX_CHANNELS 4 +#define SUNIV_DDMA_NR_MAX_CHANNELS 4 +#define SUNIV_NDMA_NR_MAX_VCHANS (24 * 2 - 1) +#define SUNIV_DDMA_NR_MAX_VCHANS 10 + /* This set of SUN4I_DDMA timing parameters were found experimentally while * working with the SPI driver and seem to make it behave correctly */ #define SUN4I_DDMA_MAGIC_SPI_PARAMETERS \ @@ -132,6 +154,33 @@ #define SUN4I_DDMA_MAX_SEG_SIZE SZ_16M #define SUN4I_DMA_MAX_SEG_SIZE SUN4I_NDMA_MAX_SEG_SIZE +/* + * Hardware channels / ports representation + * + * The hardware is used in several SoCs, with differing numbers + * of channels and endpoints. This structure ties those numbers + * to a certain compatible string. + */ +struct sun4i_dma_config { + u32 ndma_nr_max_channels; + u32 ndma_nr_max_vchans; + + u32 ddma_nr_max_channels; + u32 ddma_nr_max_vchans; + + u32 dma_nr_max_channels; + + void (*set_dst_data_width)(u32 *p_cfg, s8 data_width); + void (*set_src_data_width)(u32 *p_cfg, s8 data_width); + int (*convert_burst)(u32 maxburst); + + u8 ndma_drq_sdram; + u8 ddma_drq_sdram; + + u8 max_burst; + bool has_reset; +}; + struct sun4i_dma_pchan { /* Register base of channel */ void __iomem *base; @@ -170,7 +219,7 @@ struct sun4i_dma_contract { }; struct sun4i_dma_dev { - DECLARE_BITMAP(pchans_used, SUN4I_DMA_NR_MAX_CHANNELS); + unsigned long *pchans_used; struct dma_device slave; struct sun4i_dma_pchan *pchans; struct sun4i_dma_vchan *vchans; @@ -178,6 +227,8 @@ struct sun4i_dma_dev { struct clk *clk; int irq; spinlock_t lock; + const struct sun4i_dma_config *cfg; + struct reset_control *rst; }; static struct sun4i_dma_dev *to_sun4i_dma_dev(struct dma_device *dev) @@ -200,7 +251,27 @@ static struct device *chan2dev(struct dma_chan *chan) return &chan->dev->device; } -static int convert_burst(u32 maxburst) +static void set_dst_data_width_a10(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(data_width); +} + +static void set_src_data_width_a10(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(data_width); +} + +static void set_dst_data_width_f1c100s(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUNIV_DMA_CFG_DST_DATA_WIDTH(data_width); +} + +static void set_src_data_width_f1c100s(u32 *p_cfg, s8 data_width) +{ + *p_cfg |= SUNIV_DMA_CFG_SRC_DATA_WIDTH(data_width); +} + +static int convert_burst_a10(u32 maxburst) { if (maxburst > 8) return -EINVAL; @@ -209,6 +280,15 @@ static int convert_burst(u32 maxburst) return (maxburst >> 2); } +static int convert_burst_f1c100s(u32 maxburst) +{ + if (maxburst > 4) + return -EINVAL; + + /* 1 -> 0, 4 -> 1 */ + return (maxburst >> 2); +} + static int convert_buswidth(enum dma_slave_buswidth addr_width) { if (addr_width > DMA_SLAVE_BUSWIDTH_4_BYTES) @@ -233,15 +313,15 @@ static struct sun4i_dma_pchan *find_and_use_pchan(struct sun4i_dma_dev *priv, int i, max; /* - * pchans 0-SUN4I_NDMA_NR_MAX_CHANNELS are normal, and - * SUN4I_NDMA_NR_MAX_CHANNELS+ are dedicated ones + * pchans 0-priv->cfg->ndma_nr_max_channels are normal, and + * priv->cfg->ndma_nr_max_channels+ are dedicated ones */ if (vchan->is_dedicated) { - i = SUN4I_NDMA_NR_MAX_CHANNELS; - max = SUN4I_DMA_NR_MAX_CHANNELS; + i = priv->cfg->ndma_nr_max_channels; + max = priv->cfg->dma_nr_max_channels; } else { i = 0; - max = SUN4I_NDMA_NR_MAX_CHANNELS; + max = priv->cfg->ndma_nr_max_channels; } spin_lock_irqsave(&priv->lock, flags); @@ -444,6 +524,7 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, size_t len, struct dma_slave_config *sconfig, enum dma_transfer_direction direction) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_promise *promise; int ret; @@ -467,13 +548,13 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, sconfig->src_addr_width, sconfig->dst_addr_width); /* Source burst */ - ret = convert_burst(sconfig->src_maxburst); + ret = priv->cfg->convert_burst(sconfig->src_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret); /* Destination burst */ - ret = convert_burst(sconfig->dst_maxburst); + ret = priv->cfg->convert_burst(sconfig->dst_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret); @@ -482,13 +563,13 @@ generate_ndma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, ret = convert_buswidth(sconfig->src_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret); + priv->cfg->set_src_data_width(&promise->cfg, ret); /* Destination bus width */ ret = convert_buswidth(sconfig->dst_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret); + priv->cfg->set_dst_data_width(&promise->cfg, ret); return promise; @@ -510,6 +591,7 @@ static struct sun4i_dma_promise * generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, size_t len, struct dma_slave_config *sconfig) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_promise *promise; int ret; @@ -524,13 +606,13 @@ generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, SUN4I_DDMA_CFG_BYTE_COUNT_MODE_REMAIN; /* Source burst */ - ret = convert_burst(sconfig->src_maxburst); + ret = priv->cfg->convert_burst(sconfig->src_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_SRC_BURST_LENGTH(ret); /* Destination burst */ - ret = convert_burst(sconfig->dst_maxburst); + ret = priv->cfg->convert_burst(sconfig->dst_maxburst); if (ret < 0) goto fail; promise->cfg |= SUN4I_DMA_CFG_DST_BURST_LENGTH(ret); @@ -539,13 +621,13 @@ generate_ddma_promise(struct dma_chan *chan, dma_addr_t src, dma_addr_t dest, ret = convert_buswidth(sconfig->src_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_SRC_DATA_WIDTH(ret); + priv->cfg->set_src_data_width(&promise->cfg, ret); /* Destination bus width */ ret = convert_buswidth(sconfig->dst_addr_width); if (ret < 0) goto fail; - promise->cfg |= SUN4I_DMA_CFG_DST_DATA_WIDTH(ret); + priv->cfg->set_dst_data_width(&promise->cfg, ret); return promise; @@ -622,6 +704,7 @@ static struct dma_async_tx_descriptor * sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, size_t len, unsigned long flags) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan); struct dma_slave_config *sconfig = &vchan->cfg; struct sun4i_dma_promise *promise; @@ -638,8 +721,8 @@ sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, */ sconfig->src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; sconfig->dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; - sconfig->src_maxburst = 8; - sconfig->dst_maxburst = 8; + sconfig->src_maxburst = priv->cfg->max_burst; + sconfig->dst_maxburst = priv->cfg->max_burst; if (vchan->is_dedicated) promise = generate_ddma_promise(chan, src, dest, len, sconfig); @@ -654,11 +737,13 @@ sun4i_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, /* Configure memcpy mode */ if (vchan->is_dedicated) { - promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM) | - SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_DDMA_DRQ_TYPE_SDRAM); + promise->cfg |= + SUN4I_DMA_CFG_SRC_DRQ_TYPE(priv->cfg->ddma_drq_sdram) | + SUN4I_DMA_CFG_DST_DRQ_TYPE(priv->cfg->ddma_drq_sdram); } else { - promise->cfg |= SUN4I_DMA_CFG_SRC_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM) | - SUN4I_DMA_CFG_DST_DRQ_TYPE(SUN4I_NDMA_DRQ_TYPE_SDRAM); + promise->cfg |= + SUN4I_DMA_CFG_SRC_DRQ_TYPE(priv->cfg->ndma_drq_sdram) | + SUN4I_DMA_CFG_DST_DRQ_TYPE(priv->cfg->ndma_drq_sdram); } /* Fill the contract with our only promise */ @@ -673,6 +758,7 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len, size_t period_len, enum dma_transfer_direction dir, unsigned long flags) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan); struct dma_slave_config *sconfig = &vchan->cfg; struct sun4i_dma_promise *promise; @@ -696,11 +782,11 @@ sun4i_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf, size_t len, if (vchan->is_dedicated) { io_mode = SUN4I_DDMA_ADDR_MODE_IO; linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ddma_drq_sdram; } else { io_mode = SUN4I_NDMA_ADDR_MODE_IO; linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ndma_drq_sdram; } if (dir == DMA_MEM_TO_DEV) { @@ -793,6 +879,7 @@ sun4i_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, enum dma_transfer_direction dir, unsigned long flags, void *context) { + struct sun4i_dma_dev *priv = to_sun4i_dma_dev(chan->device); struct sun4i_dma_vchan *vchan = to_sun4i_dma_vchan(chan); struct dma_slave_config *sconfig = &vchan->cfg; struct sun4i_dma_promise *promise; @@ -818,11 +905,11 @@ sun4i_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, if (vchan->is_dedicated) { io_mode = SUN4I_DDMA_ADDR_MODE_IO; linear_mode = SUN4I_DDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_DDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ddma_drq_sdram; } else { io_mode = SUN4I_NDMA_ADDR_MODE_IO; linear_mode = SUN4I_NDMA_ADDR_MODE_LINEAR; - ram_type = SUN4I_NDMA_DRQ_TYPE_SDRAM; + ram_type = priv->cfg->ndma_drq_sdram; } if (dir == DMA_MEM_TO_DEV) @@ -1150,6 +1237,10 @@ static int sun4i_dma_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; + priv->cfg = of_device_get_match_data(&pdev->dev); + if (!priv->cfg) + return -ENODEV; + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); @@ -1164,6 +1255,13 @@ static int sun4i_dma_probe(struct platform_device *pdev) return PTR_ERR(priv->clk); } + if (priv->cfg->has_reset) { + priv->rst = devm_reset_control_get_exclusive_deasserted(&pdev->dev, NULL); + if (IS_ERR(priv->rst)) + return dev_err_probe(&pdev->dev, PTR_ERR(priv->rst), + "Failed to get reset control\n"); + } + platform_set_drvdata(pdev, priv); spin_lock_init(&priv->lock); @@ -1197,23 +1295,26 @@ static int sun4i_dma_probe(struct platform_device *pdev) priv->slave.dev = &pdev->dev; - priv->pchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_CHANNELS, + priv->pchans = devm_kcalloc(&pdev->dev, priv->cfg->dma_nr_max_channels, sizeof(struct sun4i_dma_pchan), GFP_KERNEL); priv->vchans = devm_kcalloc(&pdev->dev, SUN4I_DMA_NR_MAX_VCHANS, sizeof(struct sun4i_dma_vchan), GFP_KERNEL); - if (!priv->vchans || !priv->pchans) + priv->pchans_used = devm_kcalloc(&pdev->dev, + BITS_TO_LONGS(priv->cfg->dma_nr_max_channels), + sizeof(unsigned long), GFP_KERNEL); + if (!priv->vchans || !priv->pchans || !priv->pchans_used) return -ENOMEM; /* - * [0..SUN4I_NDMA_NR_MAX_CHANNELS) are normal pchans, and - * [SUN4I_NDMA_NR_MAX_CHANNELS..SUN4I_DMA_NR_MAX_CHANNELS) are + * [0..priv->cfg->ndma_nr_max_channels) are normal pchans, and + * [priv->cfg->ndma_nr_max_channels..priv->cfg->dma_nr_max_channels) are * dedicated ones */ - for (i = 0; i < SUN4I_NDMA_NR_MAX_CHANNELS; i++) + for (i = 0; i < priv->cfg->ndma_nr_max_channels; i++) priv->pchans[i].base = priv->base + SUN4I_NDMA_CHANNEL_REG_BASE(i); - for (j = 0; i < SUN4I_DMA_NR_MAX_CHANNELS; i++, j++) { + for (j = 0; i < priv->cfg->dma_nr_max_channels; i++, j++) { priv->pchans[i].base = priv->base + SUN4I_DDMA_CHANNEL_REG_BASE(j); priv->pchans[i].is_dedicated = 1; @@ -1284,8 +1385,51 @@ static void sun4i_dma_remove(struct platform_device *pdev) clk_disable_unprepare(priv->clk); } +static struct sun4i_dma_config sun4i_a10_dma_cfg = { + .ndma_nr_max_channels = SUN4I_NDMA_NR_MAX_CHANNELS, + .ndma_nr_max_vchans = SUN4I_NDMA_NR_MAX_VCHANS, + + .ddma_nr_max_channels = SUN4I_DDMA_NR_MAX_CHANNELS, + .ddma_nr_max_vchans = SUN4I_DDMA_NR_MAX_VCHANS, + + .dma_nr_max_channels = SUN4I_DMA_NR_MAX_CHANNELS, + + .set_dst_data_width = set_dst_data_width_a10, + .set_src_data_width = set_src_data_width_a10, + .convert_burst = convert_burst_a10, + + .ndma_drq_sdram = SUN4I_NDMA_DRQ_TYPE_SDRAM, + .ddma_drq_sdram = SUN4I_DDMA_DRQ_TYPE_SDRAM, + + .max_burst = SUN4I_MAX_BURST, + .has_reset = false, +}; + +static struct sun4i_dma_config suniv_f1c100s_dma_cfg = { + .ndma_nr_max_channels = SUNIV_NDMA_NR_MAX_CHANNELS, + .ndma_nr_max_vchans = SUNIV_NDMA_NR_MAX_VCHANS, + + .ddma_nr_max_channels = SUNIV_DDMA_NR_MAX_CHANNELS, + .ddma_nr_max_vchans = SUNIV_DDMA_NR_MAX_VCHANS, + + .dma_nr_max_channels = SUNIV_NDMA_NR_MAX_CHANNELS + + SUNIV_DDMA_NR_MAX_CHANNELS, + + .set_dst_data_width = set_dst_data_width_f1c100s, + .set_src_data_width = set_src_data_width_f1c100s, + .convert_burst = convert_burst_f1c100s, + + .ndma_drq_sdram = SUNIV_NDMA_DRQ_TYPE_SDRAM, + .ddma_drq_sdram = SUNIV_DDMA_DRQ_TYPE_SDRAM, + + .max_burst = SUNIV_MAX_BURST, + .has_reset = true, +}; + static const struct of_device_id sun4i_dma_match[] = { - { .compatible = "allwinner,sun4i-a10-dma" }, + { .compatible = "allwinner,sun4i-a10-dma", .data = &sun4i_a10_dma_cfg }, + { .compatible = "allwinner,suniv-f1c100s-dma", + .data = &suniv_f1c100s_dma_cfg }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, sun4i_dma_match); diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index 2953008d42ef..5c6a5b358987 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -43,6 +43,10 @@ #define ADMA_CH_CONFIG_MAX_BUFS 8 #define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs) (reqs << 4) +#define TEGRA186_ADMA_GLOBAL_PAGE_CHGRP 0x30 +#define TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ 0x70 +#define TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ 0x84 + #define ADMA_CH_FIFO_CTRL 0x2c #define ADMA_CH_TX_FIFO_SIZE_SHIFT 8 #define ADMA_CH_RX_FIFO_SIZE_SHIFT 0 @@ -96,6 +100,7 @@ struct tegra_adma_chip_data { unsigned int ch_fifo_size_mask; unsigned int sreq_index_offset; bool has_outstanding_reqs; + void (*set_global_pg_config)(struct tegra_adma *tdma); }; /* @@ -151,6 +156,7 @@ struct tegra_adma { struct dma_device dma_dev; struct device *dev; void __iomem *base_addr; + void __iomem *ch_base_addr; struct clk *ahub_clk; unsigned int nr_channels; unsigned long *dma_chan_mask; @@ -159,6 +165,7 @@ struct tegra_adma { /* Used to store global command register state when suspending */ unsigned int global_cmd; + unsigned int ch_page_no; const struct tegra_adma_chip_data *cdata; @@ -176,6 +183,11 @@ static inline u32 tdma_read(struct tegra_adma *tdma, u32 reg) return readl(tdma->base_addr + tdma->cdata->global_reg_offset + reg); } +static inline void tdma_ch_global_write(struct tegra_adma *tdma, u32 reg, u32 val) +{ + writel(val, tdma->ch_base_addr + tdma->cdata->global_reg_offset + reg); +} + static inline void tdma_ch_write(struct tegra_adma_chan *tdc, u32 reg, u32 val) { writel(val, tdc->chan_addr + reg); @@ -217,13 +229,30 @@ static int tegra_adma_slave_config(struct dma_chan *dc, return 0; } +static void tegra186_adma_global_page_config(struct tegra_adma *tdma) +{ + /* + * Clear the default page1 channel group configs and program + * the global registers based on the actual page usage + */ + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_CHGRP, 0); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ, 0); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ, 0); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_CHGRP + (tdma->ch_page_no * 0x4), 0xff); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_RX_REQ + (tdma->ch_page_no * 0x4), 0x1ffffff); + tdma_write(tdma, TEGRA186_ADMA_GLOBAL_PAGE_TX_REQ + (tdma->ch_page_no * 0x4), 0xffffff); +} + static int tegra_adma_init(struct tegra_adma *tdma) { u32 status; int ret; - /* Clear any interrupts */ - tdma_write(tdma, tdma->cdata->ch_base_offset + tdma->cdata->global_int_clear, 0x1); + /* Clear any channels group global interrupts */ + tdma_ch_global_write(tdma, tdma->cdata->global_int_clear, 0x1); + + if (!tdma->base_addr) + return 0; /* Assert soft reset */ tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1); @@ -237,6 +266,9 @@ static int tegra_adma_init(struct tegra_adma *tdma) if (ret) return ret; + if (tdma->cdata->set_global_pg_config) + tdma->cdata->set_global_pg_config(tdma); + /* Enable global ADMA registers */ tdma_write(tdma, ADMA_GLOBAL_CMD, 1); @@ -736,7 +768,9 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev) struct tegra_adma_chan *tdc; int i; - tdma->global_cmd = tdma_read(tdma, ADMA_GLOBAL_CMD); + if (tdma->base_addr) + tdma->global_cmd = tdma_read(tdma, ADMA_GLOBAL_CMD); + if (!tdma->global_cmd) goto clk_disable; @@ -777,7 +811,11 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev) dev_err(dev, "ahub clk_enable failed: %d\n", ret); return ret; } - tdma_write(tdma, ADMA_GLOBAL_CMD, tdma->global_cmd); + if (tdma->base_addr) { + tdma_write(tdma, ADMA_GLOBAL_CMD, tdma->global_cmd); + if (tdma->cdata->set_global_pg_config) + tdma->cdata->set_global_pg_config(tdma); + } if (!tdma->global_cmd) return 0; @@ -817,6 +855,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = { .ch_fifo_size_mask = 0xf, .sreq_index_offset = 2, .has_outstanding_reqs = false, + .set_global_pg_config = NULL, }; static const struct tegra_adma_chip_data tegra186_chip_data = { @@ -833,6 +872,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = { .ch_fifo_size_mask = 0x1f, .sreq_index_offset = 4, .has_outstanding_reqs = true, + .set_global_pg_config = tegra186_adma_global_page_config, }; static const struct of_device_id tegra_adma_of_match[] = { @@ -846,6 +886,7 @@ static int tegra_adma_probe(struct platform_device *pdev) { const struct tegra_adma_chip_data *cdata; struct tegra_adma *tdma; + struct resource *res_page, *res_base; int ret, i; cdata = of_device_get_match_data(&pdev->dev); @@ -865,9 +906,46 @@ static int tegra_adma_probe(struct platform_device *pdev) tdma->nr_channels = cdata->nr_channels; platform_set_drvdata(pdev, tdma); - tdma->base_addr = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(tdma->base_addr)) - return PTR_ERR(tdma->base_addr); + res_page = platform_get_resource_byname(pdev, IORESOURCE_MEM, "page"); + if (res_page) { + tdma->ch_base_addr = devm_ioremap_resource(&pdev->dev, res_page); + if (IS_ERR(tdma->ch_base_addr)) + return PTR_ERR(tdma->ch_base_addr); + + res_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "global"); + if (res_base) { + resource_size_t page_offset, page_no; + unsigned int ch_base_offset; + + if (res_page->start < res_base->start) + return -EINVAL; + page_offset = res_page->start - res_base->start; + ch_base_offset = cdata->ch_base_offset; + if (!ch_base_offset) + return -EINVAL; + + page_no = div_u64(page_offset, ch_base_offset); + if (!page_no || page_no > INT_MAX) + return -EINVAL; + + tdma->ch_page_no = page_no - 1; + tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base); + if (IS_ERR(tdma->base_addr)) + return PTR_ERR(tdma->base_addr); + } + } else { + /* If no 'page' property found, then reg DT binding would be legacy */ + res_base = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (res_base) { + tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base); + if (IS_ERR(tdma->base_addr)) + return PTR_ERR(tdma->base_addr); + } else { + return -ENODEV; + } + + tdma->ch_base_addr = tdma->base_addr + cdata->ch_base_offset; + } tdma->ahub_clk = devm_clk_get(&pdev->dev, "d_audio"); if (IS_ERR(tdma->ahub_clk)) { @@ -900,8 +978,7 @@ static int tegra_adma_probe(struct platform_device *pdev) if (!test_bit(i, tdma->dma_chan_mask)) continue; - tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset - + (cdata->ch_reg_size * i); + tdc->chan_addr = tdma->ch_base_addr + (cdata->ch_reg_size * i); tdc->irq = of_irq_get(pdev->dev.of_node, i); if (tdc->irq <= 0) { diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 343e986e66e7..4ece125b2ae7 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -208,7 +208,6 @@ struct edma_desc { struct edma_cc; struct edma_tc { - struct device_node *node; u16 id; }; @@ -2460,19 +2459,19 @@ static int edma_probe(struct platform_device *pdev) goto err_reg1; } - for (i = 0;; i++) { + for (i = 0; i < ecc->num_tc; i++) { ret = of_parse_phandle_with_fixed_args(node, "ti,tptcs", 1, i, &tc_args); - if (ret || i == ecc->num_tc) + if (ret) break; - ecc->tc_list[i].node = tc_args.np; ecc->tc_list[i].id = i; queue_priority_mapping[i][1] = tc_args.args[0]; if (queue_priority_mapping[i][1] > lowest_priority) { lowest_priority = queue_priority_mapping[i][1]; info->default_queue = i; } + of_node_put(tc_args.np); } /* See if we have optional dma-channel-mask array */ diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index b3f27b3f9209..7ed1956b4642 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4404,6 +4404,18 @@ static struct udma_match_data j721s2_bcdma_csi_data = { .soc_data = &j721s2_bcdma_csi_soc_data, }; +static struct udma_match_data j722s_bcdma_csi_data = { + .type = DMA_TYPE_BCDMA, + .psil_base = 0x3100, + .enable_memcpy_support = false, + .burst_size = { + TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */ + 0, /* No H Channels */ + 0, /* No UH Channels */ + }, + .soc_data = &j721s2_bcdma_csi_soc_data, +}; + static const struct of_device_id udma_of_match[] = { { .compatible = "ti,am654-navss-main-udmap", @@ -4435,6 +4447,10 @@ static const struct of_device_id udma_of_match[] = { .compatible = "ti,j721s2-dmss-bcdma-csi", .data = &j721s2_bcdma_csi_data, }, + { + .compatible = "ti,j722s-dmss-bcdma-csi", + .data = &j722s_bcdma_csi_data, + }, { /* Sentinel */ }, }; MODULE_DEVICE_TABLE(of, udma_of_match); diff --git a/drivers/dma/xilinx/xdma.c b/drivers/dma/xilinx/xdma.c index 93772abc3b49..0d88b1a670e1 100644 --- a/drivers/dma/xilinx/xdma.c +++ b/drivers/dma/xilinx/xdma.c @@ -390,15 +390,11 @@ static int xdma_xfer_start(struct xdma_chan *xchan) */ static int xdma_xfer_stop(struct xdma_chan *xchan) { - int ret; struct xdma_device *xdev = xchan->xdev_hdl; /* clear run stop bit to prevent any further auto-triggering */ - ret = regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C, - CHAN_CTRL_RUN_STOP); - if (ret) - return ret; - return ret; + return regmap_write(xdev->rmap, xchan->base + XDMA_CHAN_CONTROL_W1C, + CHAN_CTRL_RUN_STOP); } /** diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index 1bdd57de87a6..108a7287f4cd 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -1404,16 +1404,18 @@ static void xilinx_vdma_start_transfer(struct xilinx_dma_chan *chan) dma_ctrl_write(chan, XILINX_DMA_REG_DMACR, reg); - j = chan->desc_submitcount; - reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR); - if (chan->direction == DMA_MEM_TO_DEV) { - reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK; - reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT; - } else { - reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK; - reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT; + if (config->park) { + j = chan->desc_submitcount; + reg = dma_read(chan, XILINX_DMA_REG_PARK_PTR); + if (chan->direction == DMA_MEM_TO_DEV) { + reg &= ~XILINX_DMA_PARK_PTR_RD_REF_MASK; + reg |= j << XILINX_DMA_PARK_PTR_RD_REF_SHIFT; + } else { + reg &= ~XILINX_DMA_PARK_PTR_WR_REF_MASK; + reg |= j << XILINX_DMA_PARK_PTR_WR_REF_SHIFT; + } + dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg); } - dma_write(chan, XILINX_DMA_REG_PARK_PTR, reg); /* Start the hardware */ xilinx_dma_start(chan); diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 71d8b26c4103..9f35f69e0f9e 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -106,7 +106,7 @@ config ISCSI_IBFT select ISCSI_BOOT_SYSFS select ISCSI_IBFT_FIND if X86 depends on ACPI && SCSI && SCSI_LOWLEVEL - default n + default n help This option enables support for detection and exposing of iSCSI Boot Firmware Table (iBFT) via sysfs to userspace. If you wish to diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig index ee09269c63b5..0a883091259a 100644 --- a/drivers/firmware/cirrus/Kconfig +++ b/drivers/firmware/cirrus/Kconfig @@ -6,15 +6,13 @@ config FW_CS_DSP config FW_CS_DSP_KUNIT_TEST_UTILS tristate - depends on KUNIT - select REGMAP + depends on KUNIT && REGMAP select FW_CS_DSP config FW_CS_DSP_KUNIT_TEST tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS - depends on KUNIT + depends on KUNIT && REGMAP default KUNIT_ALL_TESTS - select REGMAP select FW_CS_DSP select FW_CS_DSP_KUNIT_TEST_UTILS help diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 8296bf985d1d..7309394b8fc9 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -934,13 +934,15 @@ char * __init efi_md_typeattr_format(char *buf, size_t size, EFI_MEMORY_WB | EFI_MEMORY_UCE | EFI_MEMORY_RO | EFI_MEMORY_WP | EFI_MEMORY_RP | EFI_MEMORY_XP | EFI_MEMORY_NV | EFI_MEMORY_SP | EFI_MEMORY_CPU_CRYPTO | - EFI_MEMORY_RUNTIME | EFI_MEMORY_MORE_RELIABLE)) + EFI_MEMORY_MORE_RELIABLE | EFI_MEMORY_HOT_PLUGGABLE | + EFI_MEMORY_RUNTIME)) snprintf(pos, size, "|attr=0x%016llx]", (unsigned long long)attr); else snprintf(pos, size, - "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]", + "|%3s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%2s|%3s|%2s|%2s|%2s|%2s]", attr & EFI_MEMORY_RUNTIME ? "RUN" : "", + attr & EFI_MEMORY_HOT_PLUGGABLE ? "HP" : "", attr & EFI_MEMORY_MORE_RELIABLE ? "MR" : "", attr & EFI_MEMORY_CPU_CRYPTO ? "CC" : "", attr & EFI_MEMORY_SP ? "SP" : "", diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index e5872e38d9a4..5a732018be36 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -25,6 +25,9 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, if (md->type != EFI_CONVENTIONAL_MEMORY) return 0; + if (md->attribute & EFI_MEMORY_HOT_PLUGGABLE) + return 0; + if (efi_soft_reserve_enabled() && (md->attribute & EFI_MEMORY_SP)) return 0; diff --git a/drivers/firmware/efi/libstub/relocate.c b/drivers/firmware/efi/libstub/relocate.c index 99b45d1cd624..d4264bfb6dc1 100644 --- a/drivers/firmware/efi/libstub/relocate.c +++ b/drivers/firmware/efi/libstub/relocate.c @@ -53,6 +53,9 @@ efi_status_t efi_low_alloc_above(unsigned long size, unsigned long align, if (desc->type != EFI_CONVENTIONAL_MEMORY) continue; + if (desc->attribute & EFI_MEMORY_HOT_PLUGGABLE) + continue; + if (efi_soft_reserve_enabled() && (desc->attribute & EFI_MEMORY_SP)) continue; diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c index 6e9788324fea..371f24569b3b 100644 --- a/drivers/firmware/iscsi_ibft.c +++ b/drivers/firmware/iscsi_ibft.c @@ -310,7 +310,10 @@ static ssize_t ibft_attr_show_nic(void *data, int type, char *buf) str += sprintf_ipaddr(str, nic->ip_addr); break; case ISCSI_BOOT_ETH_SUBNET_MASK: - val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1)); + if (nic->subnet_mask_prefix > 32) + val = cpu_to_be32(~0); + else + val = cpu_to_be32(~((1 << (32-nic->subnet_mask_prefix))-1)); str += sprintf(str, "%pI4", &val); break; case ISCSI_BOOT_ETH_PREFIX_LEN: diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index add5ad29a673..98b4d1633b25 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -338,6 +338,7 @@ config GPIO_GRANITERAPIDS config GPIO_GRGPIO tristate "Aeroflex Gaisler GRGPIO support" + depends on OF || COMPILE_TEST select GPIO_GENERIC select IRQ_DOMAIN help diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c index 5321ef98f442..64908f1a5e7f 100644 --- a/drivers/gpio/gpio-bcm-kona.c +++ b/drivers/gpio/gpio-bcm-kona.c @@ -69,6 +69,22 @@ struct bcm_kona_gpio { struct bcm_kona_gpio_bank { int id; int irq; + /* + * Used to keep track of lock/unlock operations for each GPIO in the + * bank. + * + * All GPIOs are locked by default (see bcm_kona_gpio_reset), and the + * unlock count for all GPIOs is 0 by default. Each unlock increments + * the counter, and each lock decrements the counter. + * + * The lock function only locks the GPIO once its unlock counter is + * down to 0. This is necessary because the GPIO is unlocked in two + * places in this driver: once for requested GPIOs, and once for + * requested IRQs. Since it is possible for a GPIO to be requested + * as both a GPIO and an IRQ, we need to ensure that we don't lock it + * too early. + */ + u8 gpio_unlock_count[GPIO_PER_BANK]; /* Used in the interrupt handler */ struct bcm_kona_gpio *kona_gpio; }; @@ -86,14 +102,24 @@ static void bcm_kona_gpio_lock_gpio(struct bcm_kona_gpio *kona_gpio, u32 val; unsigned long flags; int bank_id = GPIO_BANK(gpio); + int bit = GPIO_BIT(gpio); + struct bcm_kona_gpio_bank *bank = &kona_gpio->banks[bank_id]; - raw_spin_lock_irqsave(&kona_gpio->lock, flags); + if (bank->gpio_unlock_count[bit] == 0) { + dev_err(kona_gpio->gpio_chip.parent, + "Unbalanced locks for GPIO %u\n", gpio); + return; + } - val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); - val |= BIT(gpio); - bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); + if (--bank->gpio_unlock_count[bit] == 0) { + raw_spin_lock_irqsave(&kona_gpio->lock, flags); - raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); + val |= BIT(bit); + bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); + + raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + } } static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio, @@ -102,14 +128,20 @@ static void bcm_kona_gpio_unlock_gpio(struct bcm_kona_gpio *kona_gpio, u32 val; unsigned long flags; int bank_id = GPIO_BANK(gpio); + int bit = GPIO_BIT(gpio); + struct bcm_kona_gpio_bank *bank = &kona_gpio->banks[bank_id]; - raw_spin_lock_irqsave(&kona_gpio->lock, flags); + if (bank->gpio_unlock_count[bit] == 0) { + raw_spin_lock_irqsave(&kona_gpio->lock, flags); - val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); - val &= ~BIT(gpio); - bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); + val = readl(kona_gpio->reg_base + GPIO_PWD_STATUS(bank_id)); + val &= ~BIT(bit); + bcm_kona_gpio_write_lock_regs(kona_gpio->reg_base, bank_id, val); - raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + raw_spin_unlock_irqrestore(&kona_gpio->lock, flags); + } + + ++bank->gpio_unlock_count[bit]; } static int bcm_kona_gpio_get_dir(struct gpio_chip *chip, unsigned gpio) @@ -360,6 +392,7 @@ static void bcm_kona_gpio_irq_mask(struct irq_data *d) kona_gpio = irq_data_get_irq_chip_data(d); reg_base = kona_gpio->reg_base; + raw_spin_lock_irqsave(&kona_gpio->lock, flags); val = readl(reg_base + GPIO_INT_MASK(bank_id)); @@ -382,6 +415,7 @@ static void bcm_kona_gpio_irq_unmask(struct irq_data *d) kona_gpio = irq_data_get_irq_chip_data(d); reg_base = kona_gpio->reg_base; + raw_spin_lock_irqsave(&kona_gpio->lock, flags); val = readl(reg_base + GPIO_INT_MSKCLR(bank_id)); @@ -477,15 +511,26 @@ static void bcm_kona_gpio_irq_handler(struct irq_desc *desc) static int bcm_kona_gpio_irq_reqres(struct irq_data *d) { struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d); + unsigned int gpio = d->hwirq; - return gpiochip_reqres_irq(&kona_gpio->gpio_chip, d->hwirq); + /* + * We need to unlock the GPIO before any other operations are performed + * on the relevant GPIO configuration registers + */ + bcm_kona_gpio_unlock_gpio(kona_gpio, gpio); + + return gpiochip_reqres_irq(&kona_gpio->gpio_chip, gpio); } static void bcm_kona_gpio_irq_relres(struct irq_data *d) { struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d); + unsigned int gpio = d->hwirq; + + /* Once we no longer use it, lock the GPIO again */ + bcm_kona_gpio_lock_gpio(kona_gpio, gpio); - gpiochip_relres_irq(&kona_gpio->gpio_chip, d->hwirq); + gpiochip_relres_irq(&kona_gpio->gpio_chip, gpio); } static struct irq_chip bcm_gpio_irq_chip = { @@ -614,7 +659,7 @@ static int bcm_kona_gpio_probe(struct platform_device *pdev) bank->irq = platform_get_irq(pdev, i); bank->kona_gpio = kona_gpio; if (bank->irq < 0) { - dev_err(dev, "Couldn't get IRQ for bank %d", i); + dev_err(dev, "Couldn't get IRQ for bank %d\n", i); ret = -ENOENT; goto err_irq_domain; } diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index 4cb455b2bdee..619b6fb9d833 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -490,8 +490,7 @@ static int mxc_gpio_probe(struct platform_device *pdev) port->gc.request = mxc_gpio_request; port->gc.free = mxc_gpio_free; port->gc.to_irq = mxc_gpio_to_irq; - port->gc.base = (pdev->id < 0) ? of_alias_get_id(np, "gpio") * 32 : - pdev->id * 32; + port->gc.base = of_alias_get_id(np, "gpio") * 32; err = devm_gpiochip_add_data(&pdev->dev, &port->gc, port); if (err) diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index be4c9981ebc4..d63c1030e6ac 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -841,25 +841,6 @@ static bool pca953x_irq_pending(struct pca953x_chip *chip, unsigned long *pendin DECLARE_BITMAP(trigger, MAX_LINE); int ret; - if (chip->driver_data & PCA_PCAL) { - /* Read the current interrupt status from the device */ - ret = pca953x_read_regs(chip, PCAL953X_INT_STAT, trigger); - if (ret) - return false; - - /* Check latched inputs and clear interrupt status */ - ret = pca953x_read_regs(chip, chip->regs->input, cur_stat); - if (ret) - return false; - - /* Apply filter for rising/falling edge selection */ - bitmap_replace(new_stat, chip->irq_trig_fall, chip->irq_trig_raise, cur_stat, gc->ngpio); - - bitmap_and(pending, new_stat, trigger, gc->ngpio); - - return !bitmap_empty(pending, gc->ngpio); - } - ret = pca953x_read_regs(chip, chip->regs->input, cur_stat); if (ret) return false; diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index a086087ada17..b6c230fab840 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -1028,20 +1028,23 @@ gpio_sim_device_lockup_configfs(struct gpio_sim_device *dev, bool lock) struct configfs_subsystem *subsys = dev->group.cg_subsys; struct gpio_sim_bank *bank; struct gpio_sim_line *line; + struct config_item *item; /* - * The device only needs to depend on leaf line entries. This is + * The device only needs to depend on leaf entries. This is * sufficient to lock up all the configfs entries that the * instantiated, alive device depends on. */ list_for_each_entry(bank, &dev->bank_list, siblings) { list_for_each_entry(line, &bank->line_list, siblings) { + item = line->hog ? &line->hog->item + : &line->group.cg_item; + if (lock) - WARN_ON(configfs_depend_item_unlocked( - subsys, &line->group.cg_item)); + WARN_ON(configfs_depend_item_unlocked(subsys, + item)); else - configfs_undepend_item_unlocked( - &line->group.cg_item); + configfs_undepend_item_unlocked(item); } } } diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c index 75a3633ceddb..222279a9d82b 100644 --- a/drivers/gpio/gpio-stmpe.c +++ b/drivers/gpio/gpio-stmpe.c @@ -191,7 +191,7 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d) [REG_IE][CSB] = STMPE_IDX_IEGPIOR_CSB, [REG_IE][MSB] = STMPE_IDX_IEGPIOR_MSB, }; - int i, j; + int ret, i, j; /* * STMPE1600: to be able to get IRQ from pins, @@ -199,8 +199,16 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d) * GPSR or GPCR registers */ if (stmpe->partnum == STMPE1600) { - stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_LSB]); - stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_CSB]); + ret = stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_LSB]); + if (ret < 0) { + dev_err(stmpe->dev, "Failed to read GPMR_LSB: %d\n", ret); + goto err; + } + ret = stmpe_reg_read(stmpe, stmpe->regs[STMPE_IDX_GPMR_CSB]); + if (ret < 0) { + dev_err(stmpe->dev, "Failed to read GPMR_CSB: %d\n", ret); + goto err; + } } for (i = 0; i < CACHE_NR_REGS; i++) { @@ -222,6 +230,7 @@ static void stmpe_gpio_irq_sync_unlock(struct irq_data *d) } } +err: mutex_unlock(&stmpe_gpio->irq_lock); } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 1f9fe50bba00..f7746c57ba76 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1689,6 +1689,20 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_wake = "PNP0C50:00@8", }, }, + { + /* + * Spurious wakeups from GPIO 11 + * Found in BIOS 1.04 + * https://gitlab.freedesktop.org/drm/amd/-/issues/3954 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "Acer Nitro V 14"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_interrupt = "AMDI0030:00@11", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 679ed764cb14..ca2f58a2cd45 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -904,13 +904,13 @@ int gpiochip_get_ngpios(struct gpio_chip *gc, struct device *dev) } if (gc->ngpio == 0) { - chip_err(gc, "tried to insert a GPIO chip with zero lines\n"); + dev_err(dev, "tried to insert a GPIO chip with zero lines\n"); return -EINVAL; } if (gc->ngpio > FASTPATH_NGPIO) - chip_warn(gc, "line cnt %u is greater than fast path cnt %u\n", - gc->ngpio, FASTPATH_NGPIO); + dev_warn(dev, "line cnt %u is greater than fast path cnt %u\n", + gc->ngpio, FASTPATH_NGPIO); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 817116e53d44..95a05b03f799 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -119,9 +119,11 @@ * - 3.57.0 - Compute tunneling on GFX10+ * - 3.58.0 - Add GFX12 DCC support * - 3.59.0 - Cleared VRAM + * - 3.60.0 - Add AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE (Vulkan requirement) + * - 3.61.0 - Contains fix for RV/PCO compute queues */ #define KMS_DRIVER_MAJOR 3 -#define KMS_DRIVER_MINOR 59 +#define KMS_DRIVER_MINOR 61 #define KMS_DRIVER_PATCHLEVEL 0 /* diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index babe94ade247..e5fc80ed06ea 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -3815,9 +3815,10 @@ int psp_init_cap_microcode(struct psp_context *psp, const char *chip_name) if (err == -ENODEV) { dev_warn(adev->dev, "cap microcode does not exist, skip\n"); err = 0; - goto out; + } else { + dev_err(adev->dev, "fail to initialize cap microcode\n"); } - dev_err(adev->dev, "fail to initialize cap microcode\n"); + goto out; } info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CAP]; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index ff286940ab43..01ae2f88dec8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -309,7 +309,7 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, mutex_lock(&adev->mman.gtt_window_lock); while (src_mm.remaining) { uint64_t from, to, cur_size, tiling_flags; - uint32_t num_type, data_format, max_com; + uint32_t num_type, data_format, max_com, write_compress_disable; struct dma_fence *next; /* Never copy more than 256MiB at once to avoid a timeout */ @@ -340,9 +340,13 @@ int amdgpu_ttm_copy_mem_to_mem(struct amdgpu_device *adev, max_com = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_MAX_COMPRESSED_BLOCK); num_type = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_NUMBER_TYPE); data_format = AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_DATA_FORMAT); + write_compress_disable = + AMDGPU_TILING_GET(tiling_flags, GFX12_DCC_WRITE_COMPRESS_DISABLE); copy_flags |= (AMDGPU_COPY_FLAGS_SET(MAX_COMPRESSED, max_com) | AMDGPU_COPY_FLAGS_SET(NUMBER_TYPE, num_type) | - AMDGPU_COPY_FLAGS_SET(DATA_FORMAT, data_format)); + AMDGPU_COPY_FLAGS_SET(DATA_FORMAT, data_format) | + AMDGPU_COPY_FLAGS_SET(WRITE_COMPRESS_DISABLE, + write_compress_disable)); } r = amdgpu_copy_buffer(ring, from, to, cur_size, resv, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h index 461fb8090ae0..208b7d1d8a27 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h @@ -119,6 +119,8 @@ struct amdgpu_copy_mem { #define AMDGPU_COPY_FLAGS_NUMBER_TYPE_MASK 0x07 #define AMDGPU_COPY_FLAGS_DATA_FORMAT_SHIFT 8 #define AMDGPU_COPY_FLAGS_DATA_FORMAT_MASK 0x3f +#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_SHIFT 14 +#define AMDGPU_COPY_FLAGS_WRITE_COMPRESS_DISABLE_MASK 0x1 #define AMDGPU_COPY_FLAGS_SET(field, value) \ (((__u32)(value) & AMDGPU_COPY_FLAGS_##field##_MASK) << AMDGPU_COPY_FLAGS_##field##_SHIFT) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index c1772f44b1d7..2523221a2519 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -4021,17 +4021,6 @@ static void gfx_v12_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade if (def != data) WREG32_SOC15(GC, 0, regRLC_CGCG_CGLS_CTRL_3D, data); - - data = RREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL); - data &= ~SDMA0_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; - WREG32_SOC15(GC, 0, regSDMA0_RLC_CGCG_CTRL, data); - - /* Some ASICs only have one SDMA instance, not need to configure SDMA1 */ - if (adev->sdma.num_instances > 1) { - data = RREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL); - data &= ~SDMA1_RLC_CGCG_CTRL__CGCG_INT_ENABLE_MASK; - WREG32_SOC15(GC, 0, regSDMA1_RLC_CGCG_CTRL, data); - } } } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index fa572b40989e..0dce4421418c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -7437,6 +7437,38 @@ static void gfx_v9_0_ring_emit_cleaner_shader(struct amdgpu_ring *ring) amdgpu_ring_write(ring, 0); /* RESERVED field, programmed to zero */ } +static void gfx_v9_0_ring_begin_use_compute(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ip_block *gfx_block = + amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX); + + amdgpu_gfx_enforce_isolation_ring_begin_use(ring); + + /* Raven and PCO APUs seem to have stability issues + * with compute and gfxoff and gfx pg. Disable gfx pg during + * submission and allow again afterwards. + */ + if (gfx_block && amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 1, 0)) + gfx_v9_0_set_powergating_state(gfx_block, AMD_PG_STATE_UNGATE); +} + +static void gfx_v9_0_ring_end_use_compute(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + struct amdgpu_ip_block *gfx_block = + amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_GFX); + + /* Raven and PCO APUs seem to have stability issues + * with compute and gfxoff and gfx pg. Disable gfx pg during + * submission and allow again afterwards. + */ + if (gfx_block && amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 1, 0)) + gfx_v9_0_set_powergating_state(gfx_block, AMD_PG_STATE_GATE); + + amdgpu_gfx_enforce_isolation_ring_end_use(ring); +} + static const struct amd_ip_funcs gfx_v9_0_ip_funcs = { .name = "gfx_v9_0", .early_init = gfx_v9_0_early_init, @@ -7613,8 +7645,8 @@ static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_compute = { .emit_wave_limit = gfx_v9_0_emit_wave_limit, .reset = gfx_v9_0_reset_kcq, .emit_cleaner_shader = gfx_v9_0_ring_emit_cleaner_shader, - .begin_use = amdgpu_gfx_enforce_isolation_ring_begin_use, - .end_use = amdgpu_gfx_enforce_isolation_ring_end_use, + .begin_use = gfx_v9_0_ring_begin_use_compute, + .end_use = gfx_v9_0_ring_end_use_compute, }; static const struct amdgpu_ring_funcs gfx_v9_0_ring_funcs_kiq = { diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c index 9c17df2cf37b..7e10e94624e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v7_0.c @@ -1741,11 +1741,12 @@ static void sdma_v7_0_emit_copy_buffer(struct amdgpu_ib *ib, uint32_t byte_count, uint32_t copy_flags) { - uint32_t num_type, data_format, max_com; + uint32_t num_type, data_format, max_com, write_cm; max_com = AMDGPU_COPY_FLAGS_GET(copy_flags, MAX_COMPRESSED); data_format = AMDGPU_COPY_FLAGS_GET(copy_flags, DATA_FORMAT); num_type = AMDGPU_COPY_FLAGS_GET(copy_flags, NUMBER_TYPE); + write_cm = AMDGPU_COPY_FLAGS_GET(copy_flags, WRITE_COMPRESS_DISABLE) ? 2 : 1; ib->ptr[ib->length_dw++] = SDMA_PKT_COPY_LINEAR_HEADER_OP(SDMA_OP_COPY) | SDMA_PKT_COPY_LINEAR_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR) | @@ -1762,7 +1763,7 @@ static void sdma_v7_0_emit_copy_buffer(struct amdgpu_ib *ib, if ((copy_flags & (AMDGPU_COPY_FLAGS_READ_DECOMPRESSED | AMDGPU_COPY_FLAGS_WRITE_COMPRESSED))) ib->ptr[ib->length_dw++] = SDMA_DCC_DATA_FORMAT(data_format) | SDMA_DCC_NUM_TYPE(num_type) | ((copy_flags & AMDGPU_COPY_FLAGS_READ_DECOMPRESSED) ? SDMA_DCC_READ_CM(2) : 0) | - ((copy_flags & AMDGPU_COPY_FLAGS_WRITE_COMPRESSED) ? SDMA_DCC_WRITE_CM(1) : 0) | + ((copy_flags & AMDGPU_COPY_FLAGS_WRITE_COMPRESSED) ? SDMA_DCC_WRITE_CM(write_cm) : 0) | SDMA_DCC_MAX_COM(max_com) | SDMA_DCC_MAX_UCOM(1); else ib->ptr[ib->length_dw++] = 0; diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h index 984f0e705078..651660958e5b 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h @@ -4121,7 +4121,8 @@ static const uint32_t cwsr_trap_gfx12_hex[] = { 0x0000ffff, 0x8bfe7e7e, 0x8bea6a6a, 0xb97af804, 0xbe804ec2, 0xbf94fffe, - 0xbe804a6c, 0xbfb10000, + 0xbe804a6c, 0xbe804ec2, + 0xbf94fffe, 0xbfb10000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0xbf9f0000, 0x00000000, diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm index 1740e98c6719..7b9d36e5fa43 100644 --- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm +++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx12.asm @@ -1049,6 +1049,10 @@ L_SKIP_BARRIER_RESTORE: s_rfe_b64 s_restore_pc_lo //Return to the main shader program and resume execution L_END_PGM: + // Make sure that no wave of the workgroup can exit the trap handler + // before the workgroup barrier state is saved. + s_barrier_signal -2 + s_barrier_wait -2 s_endpgm_saved end diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 1405e8affd48..d4593374e7a1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -2325,9 +2325,9 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, */ mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ]; if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) { + while (halt_if_hws_hang) + schedule(); if (reset_queues_on_hws_hang(dqm)) { - while (halt_if_hws_hang) - schedule(); dqm->is_hws_hang = true; kfd_hws_hang(dqm); retval = -ETIME; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 9df56f8e09f9..bd36a75309e1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -86,9 +86,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd) if (pdd->already_dequeued) return; - + /* The MES context flush needs to filter out the case which the + * KFD process is created without setting up the MES context and + * queue for creating a compute queue. + */ dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd); - if (dev->kfd->shared_resources.enable_mes && + if (dev->kfd->shared_resources.enable_mes && !!pdd->proc_ctx_gpu_addr && down_read_trylock(&dev->adev->reset_domain->sem)) { amdgpu_mes_flush_shader_debugger(dev->adev, pdd->proc_ctx_gpu_addr); @@ -297,7 +300,7 @@ static int init_user_queue(struct process_queue_manager *pqm, return 0; free_gang_ctx_bo: - amdgpu_amdkfd_free_gtt_mem(dev->adev, (*q)->gang_ctx_bo); + amdgpu_amdkfd_free_gtt_mem(dev->adev, &(*q)->gang_ctx_bo); cleanup: uninit_queue(*q); *q = NULL; 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 b0e66c05d811..ac3fd81fecef 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -12326,10 +12326,14 @@ void amdgpu_dm_update_freesync_caps(struct drm_connector *connector, if (edid && (sink->sink_signal == SIGNAL_TYPE_DISPLAY_PORT || sink->sink_signal == SIGNAL_TYPE_EDP)) { - amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq; - amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq; - if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) - freesync_capable = true; + if (amdgpu_dm_connector->dc_link && + amdgpu_dm_connector->dc_link->dpcd_caps.allow_invalid_MSA_timing_param) { + amdgpu_dm_connector->min_vfreq = connector->display_info.monitor_range.min_vfreq; + amdgpu_dm_connector->max_vfreq = connector->display_info.monitor_range.max_vfreq; + if (amdgpu_dm_connector->max_vfreq - amdgpu_dm_connector->min_vfreq > 10) + freesync_capable = true; + } + parse_amd_vsdb(amdgpu_dm_connector, edid, &vsdb_info); if (vsdb_info.replay_mode) { diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 1f974ea3b0c6..1648226586e2 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -89,7 +89,7 @@ #define mmCLK1_CLK4_ALLOW_DS 0x16EA8 #define mmCLK1_CLK5_ALLOW_DS 0x16EB1 -#define mmCLK5_spll_field_8 0x1B04B +#define mmCLK5_spll_field_8 0x1B24B #define mmDENTIST_DISPCLK_CNTL 0x0124 #define regDENTIST_DISPCLK_CNTL 0x0064 #define regDENTIST_DISPCLK_CNTL_BASE_IDX 1 diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index cecaadf741ad..f84e795e35f5 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2133,7 +2133,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c dc_enable_stereo(dc, context, dc_streams, context->stream_count); - if (context->stream_count > get_seamless_boot_stream_count(context) || + if (get_seamless_boot_stream_count(context) == 0 || context->stream_count == 0) { /* Must wait for no flips to be pending before doing optimize bw */ hwss_wait_for_no_pipes_pending(dc, context); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c index 5bb8b78bf250..bf636b28e3e1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c @@ -63,8 +63,7 @@ void dmub_hw_lock_mgr_inbox0_cmd(struct dc_dmub_srv *dmub_srv, bool should_use_dmub_lock(struct dc_link *link) { - if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1 || - link->psr_settings.psr_version == DC_PSR_VERSION_1) + if (link->psr_settings.psr_version == DC_PSR_VERSION_SU_1) return true; if (link->replay_settings.replay_feature_enabled) diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 46f9c05de16e..e1d500633dfa 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -29,11 +29,15 @@ dml_ccflags := $(CC_FLAGS_FPU) dml_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) -ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) -frame_warn_flag := -Wframe-larger-than=3072 -else -frame_warn_flag := -Wframe-larger-than=2048 -endif + ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) + frame_warn_limit := 3072 + else + frame_warn_limit := 2048 + endif + + ifeq ($(call test-lt, $(CONFIG_FRAME_WARN), $(frame_warn_limit)),y) + frame_warn_flag := -Wframe-larger-than=$(frame_warn_limit) + endif endif CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) diff --git a/drivers/gpu/drm/amd/display/dc/dml2/Makefile b/drivers/gpu/drm/amd/display/dc/dml2/Makefile index 91c4f3b4bd5f..21fd466dba26 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml2/Makefile @@ -28,15 +28,19 @@ dml2_ccflags := $(CC_FLAGS_FPU) dml2_rcflags := $(CC_FLAGS_NO_FPU) ifneq ($(CONFIG_FRAME_WARN),0) -ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) -ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy) -frame_warn_flag := -Wframe-larger-than=4096 -else -frame_warn_flag := -Wframe-larger-than=3072 -endif -else -frame_warn_flag := -Wframe-larger-than=2048 -endif + ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) + ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_COMPILE_TEST),yy) + frame_warn_limit := 4096 + else + frame_warn_limit := 3072 + endif + else + frame_warn_limit := 2048 + endif + + ifeq ($(call test-lt, $(CONFIG_FRAME_WARN), $(frame_warn_limit)),y) + frame_warn_flag := -Wframe-larger-than=$(frame_warn_limit) + endif endif subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc/dml2 diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c index b9c6b45f6872..0c8ec30ea672 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c @@ -1017,7 +1017,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s if (disp_cfg_stream_location < 0) disp_cfg_stream_location = dml_dispcfg->num_streams++; - ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__); + ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__); populate_dml21_timing_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, context->streams[stream_index], dml_ctx); adjust_dml21_hblank_timing_config_from_pipe_ctx(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].timing, &context->res_ctx.pipe_ctx[stream_index]); populate_dml21_output_config_from_stream_state(&dml_dispcfg->stream_descriptors[disp_cfg_stream_location].output, context->streams[stream_index], &context->res_ctx.pipe_ctx[stream_index]); @@ -1042,7 +1042,7 @@ bool dml21_map_dc_state_into_dml_display_cfg(const struct dc *in_dc, struct dc_s if (disp_cfg_plane_location < 0) disp_cfg_plane_location = dml_dispcfg->num_planes++; - ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__); + ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__); populate_dml21_surface_config_from_plane_state(in_dc, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location].surface, context->stream_status[stream_index].plane_states[plane_index]); populate_dml21_plane_config_from_plane_state(dml_ctx, &dml_dispcfg->plane_descriptors[disp_cfg_plane_location], context->stream_status[stream_index].plane_states[plane_index], context, stream_index); diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c index b416320873e1..b8a34abaf519 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c @@ -786,7 +786,7 @@ static void populate_dml_output_cfg_from_stream_state(struct dml_output_cfg_st * case SIGNAL_TYPE_DISPLAY_PORT_MST: case SIGNAL_TYPE_DISPLAY_PORT: out->OutputEncoder[location] = dml_dp; - if (dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location] != -1) + if (location < MAX_HPO_DP2_ENCODERS && dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location] != -1) out->OutputEncoder[dml2->v20.scratch.hpo_stream_to_link_encoder_mapping[location]] = dml_dp2p0; break; case SIGNAL_TYPE_EDP: @@ -1343,7 +1343,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat if (disp_cfg_stream_location < 0) disp_cfg_stream_location = dml_dispcfg->num_timings++; - ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__); + ASSERT(disp_cfg_stream_location >= 0 && disp_cfg_stream_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__); populate_dml_timing_cfg_from_stream_state(&dml_dispcfg->timing, disp_cfg_stream_location, context->streams[i]); populate_dml_output_cfg_from_stream_state(&dml_dispcfg->output, disp_cfg_stream_location, context->streams[i], current_pipe_context, dml2); @@ -1383,7 +1383,7 @@ void map_dc_state_into_dml_display_cfg(struct dml2_context *dml2, struct dc_stat if (disp_cfg_plane_location < 0) disp_cfg_plane_location = dml_dispcfg->num_surfaces++; - ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location <= __DML2_WRAPPER_MAX_STREAMS_PLANES__); + ASSERT(disp_cfg_plane_location >= 0 && disp_cfg_plane_location < __DML2_WRAPPER_MAX_STREAMS_PLANES__); populate_dml_surface_cfg_from_plane_state(dml2->v20.dml_core_ctx.project, &dml_dispcfg->surface, disp_cfg_plane_location, context->stream_status[i].plane_states[j]); populate_dml_plane_cfg_from_plane_state( diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c index fe741100c0f8..d347bb06577a 100644 --- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn30/dcn30_hubbub.c @@ -129,7 +129,8 @@ bool hubbub3_program_watermarks( REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF); - hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); + if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter) + hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); return wm_pending; } diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c index 7fb5523f9722..b98505b240a7 100644 --- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn31/dcn31_hubbub.c @@ -750,7 +750,8 @@ static bool hubbub31_program_watermarks( REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/ - hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); + if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter) + hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); return wm_pending; } diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c index 5264dc26cce1..32a6be543105 100644 --- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn32/dcn32_hubbub.c @@ -786,7 +786,8 @@ static bool hubbub32_program_watermarks( REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 0x1FF);*/ - hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); + if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter) + hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow); diff --git a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c index 5eb3da8d5206..dce7269959ce 100644 --- a/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c +++ b/drivers/gpu/drm/amd/display/dc/hubbub/dcn35/dcn35_hubbub.c @@ -326,7 +326,8 @@ static bool hubbub35_program_watermarks( DCHUBBUB_ARB_MIN_REQ_OUTSTAND_COMMIT_THRESHOLD, 0xA);/*hw delta*/ REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DCHUBBUB_ARB_MAX_QOS_COMMIT_THRESHOLD, 0xF); - hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); + if (safe_to_lower || hubbub->ctx->dc->debug.disable_stutter) + hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter); hubbub32_force_usr_retraining_allow(hubbub, hubbub->ctx->dc->debug.force_usr_allow); diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c index be0ac613675a..0da70b50e86d 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn30/dcn30_hubp.c @@ -500,6 +500,8 @@ void hubp3_init(struct hubp *hubp) //hubp[i].HUBPREQ_DEBUG.HUBPREQ_DEBUG[26] = 1; REG_WRITE(HUBPREQ_DEBUG, 1 << 26); + REG_UPDATE(DCHUBP_CNTL, HUBP_TTU_DISABLE, 0); + hubp_reset(hubp); } diff --git a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c index edd37898d550..f3a21c623f44 100644 --- a/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/hubp/dcn32/dcn32_hubp.c @@ -168,6 +168,8 @@ void hubp32_init(struct hubp *hubp) { struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); REG_WRITE(HUBPREQ_DEBUG_DB, 1 << 8); + + REG_UPDATE(DCHUBP_CNTL, HUBP_TTU_DISABLE, 0); } static struct hubp_funcs dcn32_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, 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 623cde76debf..b907ad1acedd 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 @@ -236,7 +236,8 @@ void dcn35_init_hw(struct dc *dc) } hws->funcs.init_pipes(dc, dc->current_state); - if (dc->res_pool->hubbub->funcs->allow_self_refresh_control) + 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, !dc->res_pool->hubbub->ctx->dc->debug.disable_stutter); } diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 6a9e26905edf..7a22aef6e59c 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -78,7 +78,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev, int ret = 0; const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON; - bool is_vcn = (block_type == AMD_IP_BLOCK_TYPE_UVD || block_type == AMD_IP_BLOCK_TYPE_VCN); + bool is_vcn = block_type == AMD_IP_BLOCK_TYPE_VCN; if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state && (!is_vcn || adev->vcn.num_vcn_inst == 1)) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 8ca793c222ff..ed9dac00ebfb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -612,7 +612,8 @@ static int smu_sys_set_pp_table(void *handle, return -EIO; } - if (!smu_table->hardcode_pptable) { + if (!smu_table->hardcode_pptable || smu_table->power_play_table_size < size) { + kfree(smu_table->hardcode_pptable); smu_table->hardcode_pptable = kzalloc(size, GFP_KERNEL); if (!smu_table->hardcode_pptable) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index f6b029354327..83163d7c7f00 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1732,7 +1732,6 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity; gpu_metrics->average_umc_activity = metrics.AverageUclkActivity; - gpu_metrics->average_mm_activity = 0; /* Valid power data is available only from primary die */ if (aldebaran_is_primary(smu)) { diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c index ebccb74306a7..f30b3d5eeca5 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_wb_connector.c @@ -160,6 +160,10 @@ static int komeda_wb_connector_add(struct komeda_kms_dev *kms, formats = komeda_get_layer_fourcc_list(&mdev->fmt_tbl, kwb_conn->wb_layer->layer_type, &n_formats); + if (!formats) { + kfree(kwb_conn); + return -ENOMEM; + } err = drm_writeback_connector_init(&kms->base, wb_conn, &komeda_wb_connector_funcs, diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c index 0e282b7b167c..b9eb67e3fa90 100644 --- a/drivers/gpu/drm/ast/ast_dp.c +++ b/drivers/gpu/drm/ast/ast_dp.c @@ -195,7 +195,7 @@ static bool __ast_dp_wait_enable(struct ast_device *ast, bool enabled) if (enabled) vgacrdf_test |= AST_IO_VGACRDF_DP_VIDEO_ENABLE; - for (i = 0; i < 200; ++i) { + for (i = 0; i < 1000; ++i) { if (i) mdelay(1); vgacrdf = ast_get_index_reg_mask(ast, AST_IO_VGACRI, 0xdf, diff --git a/drivers/gpu/drm/display/drm_dp_cec.c b/drivers/gpu/drm/display/drm_dp_cec.c index 007ceb281d00..56a4965e518c 100644 --- a/drivers/gpu/drm/display/drm_dp_cec.c +++ b/drivers/gpu/drm/display/drm_dp_cec.c @@ -311,16 +311,6 @@ void drm_dp_cec_attach(struct drm_dp_aux *aux, u16 source_physical_address) if (!aux->transfer) return; -#ifndef CONFIG_MEDIA_CEC_RC - /* - * CEC_CAP_RC is part of CEC_CAP_DEFAULTS, but it is stripped by - * cec_allocate_adapter() if CONFIG_MEDIA_CEC_RC is undefined. - * - * Do this here as well to ensure the tests against cec_caps are - * correct. - */ - cec_caps &= ~CEC_CAP_RC; -#endif cancel_delayed_work_sync(&aux->cec.unregister_work); mutex_lock(&aux->cec.lock); @@ -337,7 +327,9 @@ void drm_dp_cec_attach(struct drm_dp_aux *aux, u16 source_physical_address) num_las = CEC_MAX_LOG_ADDRS; if (aux->cec.adap) { - if (aux->cec.adap->capabilities == cec_caps && + /* Check if the adapter properties have changed */ + if ((aux->cec.adap->capabilities & CEC_CAP_MONITOR_ALL) == + (cec_caps & CEC_CAP_MONITOR_ALL) && aux->cec.adap->available_log_addrs == num_las) { /* Unchanged, so just set the phys addr */ cec_s_phys_addr(aux->cec.adap, source_physical_address, false); diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index da3c8521a7fa..61c7c2c588c6 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -2544,7 +2544,7 @@ u8 drm_dp_dsc_sink_bpp_incr(const u8 dsc_dpcd[DP_DSC_RECEIVER_CAP_SIZE]) { u8 bpp_increment_dpcd = dsc_dpcd[DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT]; - switch (bpp_increment_dpcd) { + switch (bpp_increment_dpcd & DP_DSC_BITS_PER_PIXEL_MASK) { case DP_DSC_BITS_PER_PIXEL_1_16: return 16; case DP_DSC_BITS_PER_PIXEL_1_8: diff --git a/drivers/gpu/drm/hisilicon/hibmc/Kconfig b/drivers/gpu/drm/hisilicon/hibmc/Kconfig index 93b8d32e3be1..98d77d74999d 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Kconfig +++ b/drivers/gpu/drm/hisilicon/hibmc/Kconfig @@ -4,6 +4,8 @@ config DRM_HISI_HIBMC depends on DRM && PCI depends on MMU select DRM_CLIENT_SELECTION + select DRM_DISPLAY_HELPER + select DRM_DISPLAY_DP_HELPER select DRM_KMS_HELPER select DRM_VRAM_HELPER select DRM_TTM diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c index fc1e517e074a..7e6ce905bdaf 100644 --- a/drivers/gpu/drm/i915/display/intel_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_backlight.c @@ -41,8 +41,9 @@ static u32 scale(u32 source_val, { u64 target_val; - WARN_ON(source_min > source_max); - WARN_ON(target_min > target_max); + if (WARN_ON(source_min >= source_max) || + WARN_ON(target_min > target_max)) + return target_min; /* defensive */ source_val = clamp(source_val, source_min, source_max); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index f1f3b1bb1e89..aa77ddcee42c 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1791,7 +1791,7 @@ int intel_dp_dsc_max_src_input_bpc(struct intel_display *display) if (DISPLAY_VER(display) == 11) return 10; - return 0; + return intel_dp_dsc_min_src_input_bpc(); } int intel_dp_dsc_compute_max_bpp(const struct intel_connector *connector, @@ -2072,11 +2072,10 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp, /* Compressed BPP should be less than the Input DSC bpp */ dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1); - for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) { - if (valid_dsc_bpp[i] < dsc_min_bpp) + for (i = ARRAY_SIZE(valid_dsc_bpp) - 1; i >= 0; i--) { + if (valid_dsc_bpp[i] < dsc_min_bpp || + valid_dsc_bpp[i] > dsc_max_bpp) continue; - if (valid_dsc_bpp[i] > dsc_max_bpp) - break; ret = dsc_compute_link_config(intel_dp, pipe_config, @@ -2829,7 +2828,6 @@ static void intel_dp_compute_as_sdp(struct intel_dp *intel_dp, crtc_state->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_ADAPTIVE_SYNC); - /* Currently only DP_AS_SDP_AVT_FIXED_VTOTAL mode supported */ as_sdp->sdp_type = DP_SDP_ADAPTIVE_SYNC; as_sdp->length = 0x9; as_sdp->duration_incr_ms = 0; @@ -2840,7 +2838,7 @@ static void intel_dp_compute_as_sdp(struct intel_dp *intel_dp, as_sdp->target_rr = drm_mode_vrefresh(adjusted_mode); as_sdp->target_rr_divider = true; } else { - as_sdp->mode = DP_AS_SDP_AVT_FIXED_VTOTAL; + as_sdp->mode = DP_AS_SDP_AVT_DYNAMIC_VTOTAL; as_sdp->vtotal = adjusted_mode->vtotal; as_sdp->target_rr = 0; } diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 0c44fc7dd86c..a65cf97ad12d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -341,6 +341,10 @@ int intel_dp_mtp_tu_compute_config(struct intel_dp *intel_dp, break; } + + /* Allow using zero step to indicate one try */ + if (!step) + break; } if (slots < 0) { diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 7464b44c8bb3..1bab7c34a794 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -41,7 +41,7 @@ intel_hdcp_adjust_hdcp_line_rekeying(struct intel_encoder *encoder, u32 rekey_bit = 0; /* Here we assume HDMI is in TMDS mode of operation */ - if (encoder->type != INTEL_OUTPUT_HDMI) + if (!intel_encoder_is_hdmi(encoder)) return; if (DISPLAY_VER(display) >= 30) { @@ -2188,6 +2188,19 @@ static int intel_hdcp2_check_link(struct intel_connector *connector) drm_dbg_kms(display->drm, "HDCP2.2 Downstream topology change\n"); + + ret = hdcp2_authenticate_repeater_topology(connector); + if (!ret) { + intel_hdcp_update_value(connector, + DRM_MODE_CONTENT_PROTECTION_ENABLED, + true); + goto out; + } + + drm_dbg_kms(display->drm, + "[CONNECTOR:%d:%s] Repeater topology auth failed.(%d)\n", + connector->base.base.id, connector->base.name, + ret); } else { drm_dbg_kms(display->drm, "[CONNECTOR:%d:%s] HDCP2.2 link failed, retrying auth\n", diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index ff9764cac1e7..80e558042d97 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -106,8 +106,6 @@ static const u32 icl_sdr_y_plane_formats[] = { DRM_FORMAT_Y216, DRM_FORMAT_XYUV8888, DRM_FORMAT_XVYU2101010, - DRM_FORMAT_XVYU12_16161616, - DRM_FORMAT_XVYU16161616, }; static const u32 icl_sdr_uv_plane_formats[] = { @@ -134,8 +132,6 @@ static const u32 icl_sdr_uv_plane_formats[] = { DRM_FORMAT_Y216, DRM_FORMAT_XYUV8888, DRM_FORMAT_XVYU2101010, - DRM_FORMAT_XVYU12_16161616, - DRM_FORMAT_XVYU16161616, }; static const u32 icl_hdr_plane_formats[] = { diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index fe69f2c8527d..ae3343c81a64 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -209,8 +209,6 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj) struct address_space *mapping = obj->base.filp->f_mapping; unsigned int max_segment = i915_sg_segment_size(i915->drm.dev); struct sg_table *st; - struct sgt_iter sgt_iter; - struct page *page; int ret; /* @@ -239,9 +237,7 @@ rebuild_st: * for PAGE_SIZE chunks instead may be helpful. */ if (max_segment > PAGE_SIZE) { - for_each_sgt_page(page, sgt_iter, st) - put_page(page); - sg_free_table(st); + shmem_sg_free_table(st, mapping, false, false); kfree(st); max_segment = PAGE_SIZE; diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 12f1ba7ca9c1..cc05bd9e43b4 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1469,6 +1469,19 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc) spin_unlock_irqrestore(&guc->timestamp.lock, flags); } +static void __update_guc_busyness_running_state(struct intel_guc *guc) +{ + struct intel_gt *gt = guc_to_gt(guc); + struct intel_engine_cs *engine; + enum intel_engine_id id; + unsigned long flags; + + spin_lock_irqsave(&guc->timestamp.lock, flags); + for_each_engine(engine, gt, id) + engine->stats.guc.running = false; + spin_unlock_irqrestore(&guc->timestamp.lock, flags); +} + static void __update_guc_busyness_stats(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); @@ -1619,6 +1632,9 @@ void intel_guc_busyness_park(struct intel_gt *gt) if (!guc_submission_initialized(guc)) return; + /* Assume no engines are running and set running state to false */ + __update_guc_busyness_running_state(guc); + /* * There is a race with suspend flow where the worker runs after suspend * and causes an unclaimed register access warning. Cancel the worker @@ -5519,12 +5535,20 @@ static inline void guc_log_context(struct drm_printer *p, { drm_printf(p, "GuC lrc descriptor %u:\n", ce->guc_id.id); drm_printf(p, "\tHW Context Desc: 0x%08x\n", ce->lrc.lrca); - drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", - ce->ring->head, - ce->lrc_reg_state[CTX_RING_HEAD]); - drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", - ce->ring->tail, - ce->lrc_reg_state[CTX_RING_TAIL]); + if (intel_context_pin_if_active(ce)) { + drm_printf(p, "\t\tLRC Head: Internal %u, Memory %u\n", + ce->ring->head, + ce->lrc_reg_state[CTX_RING_HEAD]); + drm_printf(p, "\t\tLRC Tail: Internal %u, Memory %u\n", + ce->ring->tail, + ce->lrc_reg_state[CTX_RING_TAIL]); + intel_context_unpin(ce); + } else { + drm_printf(p, "\t\tLRC Head: Internal %u, Memory not pinned\n", + ce->ring->head); + drm_printf(p, "\t\tLRC Tail: Internal %u, Memory not pinned\n", + ce->ring->tail); + } drm_printf(p, "\t\tContext Pin Count: %u\n", atomic_read(&ce->pin_count)); drm_printf(p, "\t\tGuC ID Ref Count: %u\n", diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 2406cda75b7b..5384d1bb4923 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -4802,7 +4802,7 @@ err_unlock: return ret; } -static struct ctl_table oa_table[] = { +static const struct ctl_table oa_table[] = { { .procname = "perf_stream_paranoid", .data = &i915_perf_stream_paranoid, diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 5c397a2df70e..5d27e1c733c5 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -168,7 +168,7 @@ static int igt_ppgtt_alloc(void *arg) return PTR_ERR(ppgtt); if (!ppgtt->vm.allocate_va_range) - goto err_ppgtt_cleanup; + goto ppgtt_vm_put; /* * While we only allocate the page tables here and so we could @@ -236,7 +236,7 @@ err_ppgtt_cleanup: goto retry; } i915_gem_ww_ctx_fini(&ww); - +ppgtt_vm_put: i915_vm_put(&ppgtt->vm); return err; } diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index d5dcd3d1b33a..08136e790ca0 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -802,6 +802,7 @@ static void panthor_query_group_priorities_info(struct drm_file *file, { int prio; + memset(arg, 0, sizeof(*arg)); for (prio = PANTHOR_GROUP_PRIORITY_REALTIME; prio >= 0; prio--) { if (!group_priority_permit(file, prio)) arg->allowed_mask |= BIT(prio); diff --git a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c index b976a5e9aef5..23ecc00accb2 100644 --- a/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c +++ b/drivers/gpu/drm/tests/drm_hdmi_state_helper_test.c @@ -70,10 +70,17 @@ static int light_up_connector(struct kunit *test, state = drm_kunit_helper_atomic_state_alloc(test, drm, ctx); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, state); +retry: conn_state = drm_atomic_get_connector_state(state, connector); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, conn_state); ret = drm_atomic_set_crtc_for_connector(conn_state, crtc); + if (ret == -EDEADLK) { + drm_atomic_state_clear(state); + ret = drm_modeset_backoff(ctx); + if (!ret) + goto retry; + } KUNIT_EXPECT_EQ(test, ret, 0); crtc_state = drm_atomic_get_crtc_state(state, crtc); @@ -282,15 +289,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_changed(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; + preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -345,15 +353,16 @@ static void drm_test_check_broadcast_rgb_crtc_mode_not_changed(struct kunit *tes 8); KUNIT_ASSERT_NOT_NULL(test, priv); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; + preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -408,18 +417,18 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -474,7 +483,6 @@ static void drm_test_check_broadcast_rgb_auto_cea_mode_vic_1(struct kunit *test) mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); - drm = &priv->drm; crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -520,18 +528,18 @@ static void drm_test_check_broadcast_rgb_full_cea_mode(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -588,7 +596,6 @@ static void drm_test_check_broadcast_rgb_full_cea_mode_vic_1(struct kunit *test) mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); - drm = &priv->drm; crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -636,18 +643,18 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; KUNIT_ASSERT_TRUE(test, conn->display_info.is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_NE(test, drm_match_cea_mode(preferred), 1); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -704,7 +711,6 @@ static void drm_test_check_broadcast_rgb_limited_cea_mode_vic_1(struct kunit *te mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); - drm = &priv->drm; crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -754,20 +760,20 @@ static void drm_test_check_output_bpc_crtc_mode_changed(struct kunit *test) 10); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -828,20 +834,20 @@ static void drm_test_check_output_bpc_crtc_mode_not_changed(struct kunit *test) 10); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -899,6 +905,8 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_dvi_1080p, @@ -908,14 +916,12 @@ static void drm_test_check_output_bpc_dvi(struct kunit *test) info = &conn->display_info; KUNIT_ASSERT_FALSE(test, info->is_hdmi); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -946,21 +952,21 @@ static void drm_test_check_tmds_char_rate_rgb_8bpc(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_max_200mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_max_200mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -993,21 +999,21 @@ static void drm_test_check_tmds_char_rate_rgb_10bpc(struct kunit *test) 10); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -1040,21 +1046,21 @@ static void drm_test_check_tmds_char_rate_rgb_12bpc(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz, ARRAY_SIZE(test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz)); KUNIT_ASSERT_GT(test, ret, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -1091,15 +1097,16 @@ static void drm_test_check_hdmi_funcs_reject_rate(struct kunit *test) 8); KUNIT_ASSERT_NOT_NULL(test, priv); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; + preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_ASSERT_EQ(test, ret, 0); @@ -1147,6 +1154,8 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, @@ -1157,9 +1166,6 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); @@ -1170,8 +1176,9 @@ static void drm_test_check_max_tmds_rate_bpc_fallback(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 10, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1216,6 +1223,8 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, @@ -1226,9 +1235,6 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); KUNIT_ASSERT_FALSE(test, preferred->flags & DRM_MODE_FLAG_DBLCLK); @@ -1242,8 +1248,9 @@ static void drm_test_check_max_tmds_rate_format_fallback(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1290,9 +1297,6 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - mode = drm_kunit_display_mode_from_cea_vic(test, drm, 1); KUNIT_ASSERT_NOT_NULL(test, mode); @@ -1306,7 +1310,9 @@ static void drm_test_check_output_bpc_format_vic_1(struct kunit *test) rate = mode->clock * 1500; KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + crtc = priv->crtc; ret = light_up_connector(test, drm, crtc, conn, mode, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1340,6 +1346,8 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_200mhz, @@ -1350,9 +1358,6 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1371,8 +1376,9 @@ static void drm_test_check_output_bpc_format_driver_rgb_only(struct kunit *test) rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1407,6 +1413,8 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_max_200mhz, @@ -1417,9 +1425,6 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1438,8 +1443,9 @@ static void drm_test_check_output_bpc_format_display_rgb_only(struct kunit *test rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_YUV422); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1473,6 +1479,8 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test 8); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_yuv_dc_max_340mhz, @@ -1483,9 +1491,6 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1496,8 +1501,9 @@ static void drm_test_check_output_bpc_format_driver_8bpc_only(struct kunit *test rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); @@ -1533,6 +1539,8 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes 12); KUNIT_ASSERT_NOT_NULL(test, priv); + drm = &priv->drm; + crtc = priv->crtc; conn = &priv->connector; ret = set_connector_edid(test, conn, test_edid_hdmi_1080p_rgb_max_340mhz, @@ -1543,9 +1551,6 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes KUNIT_ASSERT_TRUE(test, info->is_hdmi); KUNIT_ASSERT_GT(test, info->max_tmds_clock, 0); - ctx = drm_kunit_helper_acquire_ctx_alloc(test); - KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); - preferred = find_preferred_mode(conn); KUNIT_ASSERT_NOT_NULL(test, preferred); @@ -1556,8 +1561,9 @@ static void drm_test_check_output_bpc_format_display_8bpc_only(struct kunit *tes rate = drm_hdmi_compute_mode_clock(preferred, 12, HDMI_COLORSPACE_RGB); KUNIT_ASSERT_LT(test, rate, info->max_tmds_clock * 1000); - drm = &priv->drm; - crtc = priv->crtc; + ctx = drm_kunit_helper_acquire_ctx_alloc(test); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ctx); + ret = light_up_connector(test, drm, crtc, conn, preferred, ctx); KUNIT_EXPECT_EQ(test, ret, 0); diff --git a/drivers/gpu/drm/xe/regs/xe_oa_regs.h b/drivers/gpu/drm/xe/regs/xe_oa_regs.h index a49561e9f3c3..a79ad2da070c 100644 --- a/drivers/gpu/drm/xe/regs/xe_oa_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_oa_regs.h @@ -51,6 +51,10 @@ /* Common to all OA units */ #define OA_OACONTROL_REPORT_BC_MASK REG_GENMASK(9, 9) #define OA_OACONTROL_COUNTER_SIZE_MASK REG_GENMASK(8, 8) +#define OAG_OACONTROL_USED_BITS \ + (OAG_OACONTROL_OA_PES_DISAG_EN | OAG_OACONTROL_OA_CCS_SELECT_MASK | \ + OAG_OACONTROL_OA_COUNTER_SEL_MASK | OAG_OACONTROL_OA_COUNTER_ENABLE | \ + OA_OACONTROL_REPORT_BC_MASK | OA_OACONTROL_COUNTER_SIZE_MASK) #define OAG_OA_DEBUG XE_REG(0xdaf8, XE_REG_OPTION_MASKED) #define OAG_OA_DEBUG_DISABLE_MMIO_TRG REG_BIT(14) @@ -78,6 +82,8 @@ #define OAM_CONTEXT_CONTROL_OFFSET (0x1bc) #define OAM_CONTROL_OFFSET (0x194) #define OAM_CONTROL_COUNTER_SEL_MASK REG_GENMASK(3, 1) +#define OAM_OACONTROL_USED_BITS \ + (OAM_CONTROL_COUNTER_SEL_MASK | OAG_OACONTROL_OA_COUNTER_ENABLE) #define OAM_DEBUG_OFFSET (0x198) #define OAM_STATUS_OFFSET (0x19c) #define OAM_MMIO_TRG_OFFSET (0x1d0) diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c index 81dc7795c065..39fe485d2085 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.c +++ b/drivers/gpu/drm/xe/xe_devcoredump.c @@ -119,11 +119,7 @@ static ssize_t __xe_devcoredump_read(char *buffer, size_t count, drm_puts(&p, "\n**** GuC CT ****\n"); xe_guc_ct_snapshot_print(ss->guc.ct, &p); - /* - * Don't add a new section header here because the mesa debug decoder - * tool expects the context information to be in the 'GuC CT' section. - */ - /* drm_puts(&p, "\n**** Contexts ****\n"); */ + drm_puts(&p, "\n**** Contexts ****\n"); xe_guc_exec_queue_snapshot_print(ss->ge, &p); drm_puts(&p, "\n**** Job ****\n"); @@ -395,42 +391,34 @@ int xe_devcoredump_init(struct xe_device *xe) /** * xe_print_blob_ascii85 - print a BLOB to some useful location in ASCII85 * - * The output is split to multiple lines because some print targets, e.g. dmesg - * cannot handle arbitrarily long lines. Note also that printing to dmesg in - * piece-meal fashion is not possible, each separate call to drm_puts() has a - * line-feed automatically added! Therefore, the entire output line must be - * constructed in a local buffer first, then printed in one atomic output call. + * The output is split into multiple calls to drm_puts() because some print + * targets, e.g. dmesg, cannot handle arbitrarily long lines. These targets may + * add newlines, as is the case with dmesg: each drm_puts() call creates a + * separate line. * * There is also a scheduler yield call to prevent the 'task has been stuck for * 120s' kernel hang check feature from firing when printing to a slow target * such as dmesg over a serial port. * - * TODO: Add compression prior to the ASCII85 encoding to shrink huge buffers down. - * * @p: the printer object to output to * @prefix: optional prefix to add to output string + * @suffix: optional suffix to add at the end. 0 disables it and is + * not added to the output, which is useful when using multiple calls + * to dump data to @p * @blob: the Binary Large OBject to dump out * @offset: offset in bytes to skip from the front of the BLOB, must be a multiple of sizeof(u32) * @size: the size in bytes of the BLOB, must be a multiple of sizeof(u32) */ -void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, +void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix, const void *blob, size_t offset, size_t size) { const u32 *blob32 = (const u32 *)blob; char buff[ASCII85_BUFSZ], *line_buff; size_t line_pos = 0; - /* - * Splitting blobs across multiple lines is not compatible with the mesa - * debug decoder tool. Note that even dropping the explicit '\n' below - * doesn't help because the GuC log is so big some underlying implementation - * still splits the lines at 512K characters. So just bail completely for - * the moment. - */ - return; - #define DMESG_MAX_LINE_LEN 800 -#define MIN_SPACE (ASCII85_BUFSZ + 2) /* 85 + "\n\0" */ + /* Always leave space for the suffix char and the \0 */ +#define MIN_SPACE (ASCII85_BUFSZ + 2) /* 85 + "<suffix>\0" */ if (size & 3) drm_printf(p, "Size not word aligned: %zu", size); @@ -462,7 +450,6 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, line_pos += strlen(line_buff + line_pos); if ((line_pos + MIN_SPACE) >= DMESG_MAX_LINE_LEN) { - line_buff[line_pos++] = '\n'; line_buff[line_pos++] = 0; drm_puts(p, line_buff); @@ -474,10 +461,11 @@ void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, } } + if (suffix) + line_buff[line_pos++] = suffix; + if (line_pos) { - line_buff[line_pos++] = '\n'; line_buff[line_pos++] = 0; - drm_puts(p, line_buff); } diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h index 6a17e6d60102..5391a80a4d1b 100644 --- a/drivers/gpu/drm/xe/xe_devcoredump.h +++ b/drivers/gpu/drm/xe/xe_devcoredump.h @@ -29,7 +29,7 @@ static inline int xe_devcoredump_init(struct xe_device *xe) } #endif -void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, +void xe_print_blob_ascii85(struct drm_printer *p, const char *prefix, char suffix, const void *blob, size_t offset, size_t size); #endif diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c index 63f30b6df70b..2d4874d2b922 100644 --- a/drivers/gpu/drm/xe/xe_drm_client.c +++ b/drivers/gpu/drm/xe/xe_drm_client.c @@ -135,8 +135,8 @@ void xe_drm_client_add_bo(struct xe_drm_client *client, XE_WARN_ON(bo->client); XE_WARN_ON(!list_empty(&bo->client_link)); - spin_lock(&client->bos_lock); bo->client = xe_drm_client_get(client); + spin_lock(&client->bos_lock); list_add_tail(&bo->client_link, &client->bos_list); spin_unlock(&client->bos_lock); } diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 26e64530ada2..5d6fb79957b6 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -532,8 +532,10 @@ static int all_fw_domain_init(struct xe_gt *gt) if (IS_SRIOV_PF(gt_to_xe(gt)) && !xe_gt_is_media_type(gt)) xe_lmtt_init_hw(>_to_tile(gt)->sriov.pf.lmtt); - if (IS_SRIOV_PF(gt_to_xe(gt))) + if (IS_SRIOV_PF(gt_to_xe(gt))) { + xe_gt_sriov_pf_init(gt); xe_gt_sriov_pf_init_hw(gt); + } xe_force_wake_put(gt_to_fw(gt), fw_ref); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c index e71fc3d2bda2..6f906c8e8108 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.c @@ -68,6 +68,19 @@ int xe_gt_sriov_pf_init_early(struct xe_gt *gt) return 0; } +/** + * xe_gt_sriov_pf_init - Prepare SR-IOV PF data structures on PF. + * @gt: the &xe_gt to initialize + * + * Late one-time initialization of the PF data. + * + * Return: 0 on success or a negative error code on failure. + */ +int xe_gt_sriov_pf_init(struct xe_gt *gt) +{ + return xe_gt_sriov_pf_migration_init(gt); +} + static bool pf_needs_enable_ggtt_guest_update(struct xe_device *xe) { return GRAPHICS_VERx100(xe) == 1200; @@ -90,7 +103,6 @@ void xe_gt_sriov_pf_init_hw(struct xe_gt *gt) pf_enable_ggtt_guest_update(gt); xe_gt_sriov_pf_service_update(gt); - xe_gt_sriov_pf_migration_init(gt); } static u32 pf_get_vf_regs_stride(struct xe_device *xe) diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h index 96fab779a906..f474509411c0 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_pf.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf.h @@ -10,6 +10,7 @@ struct xe_gt; #ifdef CONFIG_PCI_IOV int xe_gt_sriov_pf_init_early(struct xe_gt *gt); +int xe_gt_sriov_pf_init(struct xe_gt *gt); void xe_gt_sriov_pf_init_hw(struct xe_gt *gt); void xe_gt_sriov_pf_sanitize_hw(struct xe_gt *gt, unsigned int vfid); void xe_gt_sriov_pf_restart(struct xe_gt *gt); @@ -19,6 +20,11 @@ static inline int xe_gt_sriov_pf_init_early(struct xe_gt *gt) return 0; } +static inline int xe_gt_sriov_pf_init(struct xe_gt *gt) +{ + return 0; +} + static inline void xe_gt_sriov_pf_init_hw(struct xe_gt *gt) { } diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 8b65c5e959cc..50c8076b5158 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -1724,7 +1724,8 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot, snapshot->g2h_outstanding); if (snapshot->ctb) - xe_print_blob_ascii85(p, "CTB data", snapshot->ctb, 0, snapshot->ctb_size); + xe_print_blob_ascii85(p, "CTB data", '\n', + snapshot->ctb, 0, snapshot->ctb_size); } else { drm_puts(p, "CT disabled\n"); } diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c index df4cfb698cdb..2baa4d95571f 100644 --- a/drivers/gpu/drm/xe/xe_guc_log.c +++ b/drivers/gpu/drm/xe/xe_guc_log.c @@ -211,8 +211,10 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_ remain = snapshot->size; for (i = 0; i < snapshot->num_chunks; i++) { size_t size = min(GUC_LOG_CHUNK_SIZE, remain); + const char *prefix = i ? NULL : "Log data"; + char suffix = i == snapshot->num_chunks - 1 ? '\n' : 0; - xe_print_blob_ascii85(p, i ? NULL : "Log data", snapshot->copy[i], 0, size); + xe_print_blob_ascii85(p, prefix, suffix, snapshot->copy[i], 0, size); remain -= size; } } diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c index eeb96b5f49e2..fa873f3d0a9d 100644 --- a/drivers/gpu/drm/xe/xe_oa.c +++ b/drivers/gpu/drm/xe/xe_oa.c @@ -237,7 +237,6 @@ static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream) u32 tail, hw_tail, partial_report_size, available; int report_size = stream->oa_buffer.format->size; unsigned long flags; - bool pollin; spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags); @@ -282,11 +281,11 @@ static bool xe_oa_buffer_check_unlocked(struct xe_oa_stream *stream) stream->oa_buffer.tail = tail; available = xe_oa_circ_diff(stream, stream->oa_buffer.tail, stream->oa_buffer.head); - pollin = available >= stream->wait_num_reports * report_size; + stream->pollin = available >= stream->wait_num_reports * report_size; spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags); - return pollin; + return stream->pollin; } static enum hrtimer_restart xe_oa_poll_check_timer_cb(struct hrtimer *hrtimer) @@ -294,10 +293,8 @@ static enum hrtimer_restart xe_oa_poll_check_timer_cb(struct hrtimer *hrtimer) struct xe_oa_stream *stream = container_of(hrtimer, typeof(*stream), poll_check_timer); - if (xe_oa_buffer_check_unlocked(stream)) { - stream->pollin = true; + if (xe_oa_buffer_check_unlocked(stream)) wake_up(&stream->poll_wq); - } hrtimer_forward_now(hrtimer, ns_to_ktime(stream->poll_period_ns)); @@ -452,6 +449,12 @@ static u32 __oa_ccs_select(struct xe_oa_stream *stream) return val; } +static u32 __oactrl_used_bits(struct xe_oa_stream *stream) +{ + return stream->hwe->oa_unit->type == DRM_XE_OA_UNIT_TYPE_OAG ? + OAG_OACONTROL_USED_BITS : OAM_OACONTROL_USED_BITS; +} + static void xe_oa_enable(struct xe_oa_stream *stream) { const struct xe_oa_format *format = stream->oa_buffer.format; @@ -472,14 +475,14 @@ static void xe_oa_enable(struct xe_oa_stream *stream) stream->hwe->oa_unit->type == DRM_XE_OA_UNIT_TYPE_OAG) val |= OAG_OACONTROL_OA_PES_DISAG_EN; - xe_mmio_write32(&stream->gt->mmio, regs->oa_ctrl, val); + xe_mmio_rmw32(&stream->gt->mmio, regs->oa_ctrl, __oactrl_used_bits(stream), val); } static void xe_oa_disable(struct xe_oa_stream *stream) { struct xe_mmio *mmio = &stream->gt->mmio; - xe_mmio_write32(mmio, __oa_regs(stream)->oa_ctrl, 0); + xe_mmio_rmw32(mmio, __oa_regs(stream)->oa_ctrl, __oactrl_used_bits(stream), 0); if (xe_mmio_wait32(mmio, __oa_regs(stream)->oa_ctrl, OAG_OACONTROL_OA_COUNTER_ENABLE, 0, 50000, NULL, false)) drm_err(&stream->oa->xe->drm, @@ -2534,6 +2537,8 @@ static void __xe_oa_init_oa_units(struct xe_gt *gt) u->type = DRM_XE_OA_UNIT_TYPE_OAM; } + xe_mmio_write32(>->mmio, u->regs.oa_ctrl, 0); + /* Ensure MMIO trigger remains disabled till there is a stream */ xe_mmio_write32(>->mmio, u->regs.oa_debug, oag_configure_mmio_trigger(NULL, false)); diff --git a/drivers/gpu/drm/xe/xe_observation.c b/drivers/gpu/drm/xe/xe_observation.c index 8ec1b84cbb9e..57cf01efc07f 100644 --- a/drivers/gpu/drm/xe/xe_observation.c +++ b/drivers/gpu/drm/xe/xe_observation.c @@ -56,7 +56,7 @@ int xe_observation_ioctl(struct drm_device *dev, void *data, struct drm_file *fi } } -static struct ctl_table observation_ctl_table[] = { +static const struct ctl_table observation_ctl_table[] = { { .procname = "observation_paranoid", .data = &xe_observation_paranoid, diff --git a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c index 423856cc18d4..d414421f8c13 100644 --- a/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c +++ b/drivers/gpu/drm/xe/xe_ttm_stolen_mgr.c @@ -57,12 +57,35 @@ bool xe_ttm_stolen_cpu_access_needs_ggtt(struct xe_device *xe) return GRAPHICS_VERx100(xe) < 1270 && !IS_DGFX(xe); } +static u32 get_wopcm_size(struct xe_device *xe) +{ + u32 wopcm_size; + u64 val; + + val = xe_mmio_read64_2x32(xe_root_tile_mmio(xe), STOLEN_RESERVED); + val = REG_FIELD_GET64(WOPCM_SIZE_MASK, val); + + switch (val) { + case 0x5 ... 0x6: + val--; + fallthrough; + case 0x0 ... 0x3: + wopcm_size = (1U << val) * SZ_1M; + break; + default: + WARN(1, "Missing case wopcm_size=%llx\n", val); + wopcm_size = 0; + } + + return wopcm_size; +} + static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) { struct xe_tile *tile = xe_device_get_root_tile(xe); struct xe_mmio *mmio = xe_root_tile_mmio(xe); struct pci_dev *pdev = to_pci_dev(xe->drm.dev); - u64 stolen_size; + u64 stolen_size, wopcm_size; u64 tile_offset; u64 tile_size; @@ -74,7 +97,13 @@ static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) if (drm_WARN_ON(&xe->drm, tile_size < mgr->stolen_base)) return 0; + /* Carve out the top of DSM as it contains the reserved WOPCM region */ + wopcm_size = get_wopcm_size(xe); + if (drm_WARN_ON(&xe->drm, !wopcm_size)) + return 0; + stolen_size = tile_size - mgr->stolen_base; + stolen_size -= wopcm_size; /* Verify usage fits in the actual resource available */ if (mgr->stolen_base + stolen_size <= pci_resource_len(pdev, LMEM_BAR)) @@ -89,29 +118,6 @@ static s64 detect_bar2_dgfx(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) return ALIGN_DOWN(stolen_size, SZ_1M); } -static u32 get_wopcm_size(struct xe_device *xe) -{ - u32 wopcm_size; - u64 val; - - val = xe_mmio_read64_2x32(xe_root_tile_mmio(xe), STOLEN_RESERVED); - val = REG_FIELD_GET64(WOPCM_SIZE_MASK, val); - - switch (val) { - case 0x5 ... 0x6: - val--; - fallthrough; - case 0x0 ... 0x3: - wopcm_size = (1U << val) * SZ_1M; - break; - default: - WARN(1, "Missing case wopcm_size=%llx\n", val); - wopcm_size = 0; - } - - return wopcm_size; -} - static u32 detect_bar2_integrated(struct xe_device *xe, struct xe_ttm_stolen_mgr *mgr) { struct pci_dev *pdev = to_pci_dev(xe->drm.dev); diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 7b1d091f3c09..46cae925b095 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -619,6 +619,8 @@ static int host1x_probe(struct platform_device *pdev) goto free_contexts; } + mutex_init(&host->intr_mutex); + pm_runtime_enable(&pdev->dev); err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev); diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c index b3285dd10180..f77a678949e9 100644 --- a/drivers/gpu/host1x/intr.c +++ b/drivers/gpu/host1x/intr.c @@ -104,8 +104,6 @@ int host1x_intr_init(struct host1x *host) unsigned int id; int i, err; - mutex_init(&host->intr_mutex); - for (id = 0; id < host1x_syncpt_nb_pts(host); ++id) { struct host1x_syncpt *syncpt = &host->syncpt[id]; diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index b53eb569bd49..dfc245867a46 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -570,6 +570,8 @@ config HID_LED config HID_LENOVO tristate "Lenovo / Thinkpad devices" + depends on ACPI + select ACPI_PLATFORM_PROFILE select NEW_LEDS select LEDS_CLASS help @@ -1167,7 +1169,8 @@ config HID_TOPRE tristate "Topre REALFORCE keyboards" depends on HID help - Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key keyboards. + Say Y for N-key rollover support on Topre REALFORCE R2 108/87 key and + Topre REALFORCE R3S 87 key keyboards. config HID_THINGM tristate "ThingM blink(1) USB RGB LED" @@ -1374,10 +1377,6 @@ endmenu source "drivers/hid/bpf/Kconfig" -endif # HID - -source "drivers/hid/usbhid/Kconfig" - source "drivers/hid/i2c-hid/Kconfig" source "drivers/hid/intel-ish-hid/Kconfig" @@ -1388,4 +1387,10 @@ source "drivers/hid/surface-hid/Kconfig" source "drivers/hid/intel-thc-hid/Kconfig" +endif # HID + +# USB support may be used with HID disabled + +source "drivers/hid/usbhid/Kconfig" + endif # HID_SUPPORT diff --git a/drivers/hid/amd-sfh-hid/Kconfig b/drivers/hid/amd-sfh-hid/Kconfig index 329de5e12c1a..3291786a5ee6 100644 --- a/drivers/hid/amd-sfh-hid/Kconfig +++ b/drivers/hid/amd-sfh-hid/Kconfig @@ -5,7 +5,6 @@ menu "AMD SFH HID Support" config AMD_SFH_HID tristate "AMD Sensor Fusion Hub" - depends on HID depends on X86 help If you say yes to this option, support will be included for the diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 7e1ae2a2bcc2..49812a76b7ed 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -474,6 +474,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2015) table = magic_keyboard_2015_fn_keys; else if (hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021 || + hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024 || hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021 || hid->product == USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021) table = apple2021_fn_keys; @@ -545,6 +546,9 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input, } } + if (usage->hid == 0xc0301) /* Omoton KB066 quirk */ + code = KEY_F6; + if (usage->code != code) { input_event_with_scancode(input, usage->type, code, usage->hid, value); @@ -1150,6 +1154,10 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY }, { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021), .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024), + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024), + .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021), .driver_data = APPLE_HAS_FN | APPLE_ISO_TILDE_QUIRK | APPLE_RDESC_BATTERY }, { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021), diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c index 6ece56b850fc..56e858066c3c 100644 --- a/drivers/hid/hid-corsair-void.c +++ b/drivers/hid/hid-corsair-void.c @@ -553,7 +553,7 @@ static void corsair_void_battery_remove_work_handler(struct work_struct *work) static void corsair_void_battery_add_work_handler(struct work_struct *work) { struct corsair_void_drvdata *drvdata; - struct power_supply_config psy_cfg; + struct power_supply_config psy_cfg = {}; struct power_supply *new_supply; drvdata = container_of(work, struct corsair_void_drvdata, @@ -726,6 +726,7 @@ static void corsair_void_remove(struct hid_device *hid_dev) if (drvdata->battery) power_supply_unregister(drvdata->battery); + cancel_delayed_work_sync(&drvdata->delayed_status_work); cancel_delayed_work_sync(&drvdata->delayed_firmware_work); sysfs_remove_group(&hid_dev->dev.kobj, &corsair_void_attr_group); } diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index c448de53bf91..7e400624908e 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -184,6 +184,7 @@ #define USB_DEVICE_ID_APPLE_IRCONTROL4 0x8242 #define USB_DEVICE_ID_APPLE_IRCONTROL5 0x8243 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2021 0x029c +#define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_2024 0x0320 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_FINGERPRINT_2021 0x029a #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_2021 0x029f #define USB_DEVICE_ID_APPLE_TOUCHBAR_BACKLIGHT 0x8102 @@ -1095,6 +1096,7 @@ #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3001 0x3001 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003 0x3003 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008 0x3008 +#define USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473 0x5473 #define I2C_VENDOR_ID_RAYDIUM 0x2386 #define I2C_PRODUCT_ID_RAYDIUM_4B33 0x4b33 @@ -1301,6 +1303,7 @@ #define USB_VENDOR_ID_TOPRE 0x0853 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_108 0x0148 #define USB_DEVICE_ID_TOPRE_REALFORCE_R2_87 0x0146 +#define USB_DEVICE_ID_TOPRE_REALFORCE_R3S_87 0x0313 #define USB_VENDOR_ID_TOPSEED 0x0766 #define USB_DEVICE_ID_TOPSEED_CYBERLINK 0x0204 diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 4d00bc4d656e..a7d9ca02779e 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -32,9 +32,7 @@ #include <linux/leds.h> #include <linux/workqueue.h> -#if IS_ENABLED(CONFIG_ACPI_PLATFORM_PROFILE) #include <linux/platform_profile.h> -#endif /* CONFIG_ACPI_PLATFORM_PROFILE */ #include "hid-ids.h" @@ -730,13 +728,10 @@ static int lenovo_raw_event_TP_X12_tab(struct hid_device *hdev, u32 raw_data) if (hdev->product == USB_DEVICE_ID_LENOVO_X12_TAB) { report_key_event(input, KEY_RFKILL); return 1; - } -#if IS_ENABLED(CONFIG_ACPI_PLATFORM_PROFILE) - else { + } else { platform_profile_cycle(); return 1; } -#endif /* CONFIG_ACPI_PLATFORM_PROFILE */ return 0; case TP_X12_RAW_HOTKEY_FN_F10: /* TAB1 has PICKUP Phone and TAB2 use Snipping tool*/ diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 82900857bfd8..e50887a6d22c 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1679,9 +1679,12 @@ static int mt_input_configured(struct hid_device *hdev, struct hid_input *hi) break; } - if (suffix) + if (suffix) { hi->input->name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s %s", hdev->name, suffix); + if (!hi->input->name) + return -ENOMEM; + } return 0; } diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index e0bbf0c6345d..5d7a418ccdbe 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -891,6 +891,7 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DPAD) }, #endif { HID_USB_DEVICE(USB_VENDOR_ID_YEALINK, USB_DEVICE_ID_YEALINK_P1K_P4K_B2K) }, + { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_HP_5MP_CAMERA_5473) }, { } }; diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c index af38fc8eb34f..c9e65e9088b3 100644 --- a/drivers/hid/hid-steam.c +++ b/drivers/hid/hid-steam.c @@ -313,6 +313,7 @@ struct steam_device { u16 rumble_left; u16 rumble_right; unsigned int sensor_timestamp_us; + struct work_struct unregister_work; }; static int steam_recv_report(struct steam_device *steam, @@ -1050,10 +1051,10 @@ static void steam_mode_switch_cb(struct work_struct *work) struct steam_device, mode_switch); unsigned long flags; bool client_opened; - steam->gamepad_mode = !steam->gamepad_mode; if (!lizard_mode) return; + steam->gamepad_mode = !steam->gamepad_mode; if (steam->gamepad_mode) steam_set_lizard_mode(steam, false); else { @@ -1072,6 +1073,31 @@ static void steam_mode_switch_cb(struct work_struct *work) } } +static void steam_work_unregister_cb(struct work_struct *work) +{ + struct steam_device *steam = container_of(work, struct steam_device, + unregister_work); + unsigned long flags; + bool connected; + bool opened; + + spin_lock_irqsave(&steam->lock, flags); + opened = steam->client_opened; + connected = steam->connected; + spin_unlock_irqrestore(&steam->lock, flags); + + if (connected) { + if (opened) { + steam_sensors_unregister(steam); + steam_input_unregister(steam); + } else { + steam_set_lizard_mode(steam, lizard_mode); + steam_input_register(steam); + steam_sensors_register(steam); + } + } +} + static bool steam_is_valve_interface(struct hid_device *hdev) { struct hid_report_enum *rep_enum; @@ -1117,8 +1143,7 @@ static int steam_client_ll_open(struct hid_device *hdev) steam->client_opened++; spin_unlock_irqrestore(&steam->lock, flags); - steam_sensors_unregister(steam); - steam_input_unregister(steam); + schedule_work(&steam->unregister_work); return 0; } @@ -1135,11 +1160,7 @@ static void steam_client_ll_close(struct hid_device *hdev) connected = steam->connected && !steam->client_opened; spin_unlock_irqrestore(&steam->lock, flags); - if (connected) { - steam_set_lizard_mode(steam, lizard_mode); - steam_input_register(steam); - steam_sensors_register(steam); - } + schedule_work(&steam->unregister_work); } static int steam_client_ll_raw_request(struct hid_device *hdev, @@ -1231,6 +1252,7 @@ static int steam_probe(struct hid_device *hdev, INIT_LIST_HEAD(&steam->list); INIT_WORK(&steam->rumble_work, steam_haptic_rumble_cb); steam->sensor_timestamp_us = 0; + INIT_WORK(&steam->unregister_work, steam_work_unregister_cb); /* * With the real steam controller interface, do not connect hidraw. @@ -1291,6 +1313,7 @@ err_cancel_work: cancel_work_sync(&steam->work_connect); cancel_delayed_work_sync(&steam->mode_switch); cancel_work_sync(&steam->rumble_work); + cancel_work_sync(&steam->unregister_work); return ret; } @@ -1307,6 +1330,7 @@ static void steam_remove(struct hid_device *hdev) cancel_delayed_work_sync(&steam->mode_switch); cancel_work_sync(&steam->work_connect); cancel_work_sync(&steam->rumble_work); + cancel_work_sync(&steam->unregister_work); hid_destroy_device(steam->client_hdev); steam->client_hdev = NULL; steam->client_opened = 0; @@ -1593,13 +1617,13 @@ static void steam_do_deck_input_event(struct steam_device *steam, if (!(b9 & BIT(6)) && steam->did_mode_switch) { steam->did_mode_switch = false; - cancel_delayed_work_sync(&steam->mode_switch); + cancel_delayed_work(&steam->mode_switch); } else if (!steam->client_opened && (b9 & BIT(6)) && !steam->did_mode_switch) { steam->did_mode_switch = true; schedule_delayed_work(&steam->mode_switch, 45 * HZ / 100); } - if (!steam->gamepad_mode) + if (!steam->gamepad_mode && lizard_mode) return; lpad_touched = b10 & BIT(3); @@ -1669,7 +1693,7 @@ static void steam_do_deck_sensors_event(struct steam_device *steam, */ steam->sensor_timestamp_us += 4000; - if (!steam->gamepad_mode) + if (!steam->gamepad_mode && lizard_mode) return; input_event(sensors, EV_MSC, MSC_TIMESTAMP, steam->sensor_timestamp_us); diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index 6c3e758bbb09..3b81468a1df2 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -171,7 +171,7 @@ static void thrustmaster_interrupts(struct hid_device *hdev) b_ep = ep->desc.bEndpointAddress; /* Are the expected endpoints present? */ - u8 ep_addr[1] = {b_ep}; + u8 ep_addr[2] = {b_ep, 0}; if (!usb_check_int_endpoints(usbif, ep_addr)) { hid_err(hdev, "Unexpected non-int endpoint\n"); diff --git a/drivers/hid/hid-topre.c b/drivers/hid/hid-topre.c index 848361f6225d..ccedf8721722 100644 --- a/drivers/hid/hid-topre.c +++ b/drivers/hid/hid-topre.c @@ -29,6 +29,11 @@ static const __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc, hid_info(hdev, "fixing up Topre REALFORCE keyboard report descriptor\n"); rdesc[72] = 0x02; + } else if (*rsize >= 106 && rdesc[28] == 0x29 && rdesc[29] == 0xe7 && + rdesc[30] == 0x81 && rdesc[31] == 0x00) { + hid_info(hdev, + "fixing up Topre REALFORCE keyboard report descriptor\n"); + rdesc[31] = 0x02; } return rdesc; } @@ -38,6 +43,8 @@ static const struct hid_device_id topre_id_table[] = { USB_DEVICE_ID_TOPRE_REALFORCE_R2_108) }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, USB_DEVICE_ID_TOPRE_REALFORCE_R2_87) }, + { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, + USB_DEVICE_ID_TOPRE_REALFORCE_R3S_87) }, { } }; MODULE_DEVICE_TABLE(hid, topre_id_table); diff --git a/drivers/hid/hid-winwing.c b/drivers/hid/hid-winwing.c index 831b760c66ea..d4afbbd27807 100644 --- a/drivers/hid/hid-winwing.c +++ b/drivers/hid/hid-winwing.c @@ -106,6 +106,8 @@ static int winwing_init_led(struct hid_device *hdev, "%s::%s", dev_name(&input->dev), info->led_name); + if (!led->cdev.name) + return -ENOMEM; ret = devm_led_classdev_register(&hdev->dev, &led->cdev); if (ret) diff --git a/drivers/hid/i2c-hid/Kconfig b/drivers/hid/i2c-hid/Kconfig index ef7c595c9403..e8d51f410cc1 100644 --- a/drivers/hid/i2c-hid/Kconfig +++ b/drivers/hid/i2c-hid/Kconfig @@ -2,7 +2,7 @@ menuconfig I2C_HID tristate "I2C HID support" default y - depends on I2C && INPUT && HID + depends on I2C if I2C_HID diff --git a/drivers/hid/intel-ish-hid/Kconfig b/drivers/hid/intel-ish-hid/Kconfig index 253dc10d35ef..568c8688784e 100644 --- a/drivers/hid/intel-ish-hid/Kconfig +++ b/drivers/hid/intel-ish-hid/Kconfig @@ -6,7 +6,6 @@ config INTEL_ISH_HID tristate "Intel Integrated Sensor Hub" default n depends on X86 - depends on HID help The Integrated Sensor Hub (ISH) enables the ability to offload sensor polling and algorithm processing to a dedicated low power diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index cdd80c653918..07e90d51f073 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -36,6 +36,8 @@ #define PCI_DEVICE_ID_INTEL_ISH_ARL_H 0x7745 #define PCI_DEVICE_ID_INTEL_ISH_ARL_S 0x7F78 #define PCI_DEVICE_ID_INTEL_ISH_LNL_M 0xA845 +#define PCI_DEVICE_ID_INTEL_ISH_PTL_H 0xE345 +#define PCI_DEVICE_ID_INTEL_ISH_PTL_P 0xE445 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/ipc.c b/drivers/hid/intel-ish-hid/ipc/ipc.c index 3cd53fc80634..4c861119e97a 100644 --- a/drivers/hid/intel-ish-hid/ipc/ipc.c +++ b/drivers/hid/intel-ish-hid/ipc/ipc.c @@ -517,6 +517,10 @@ static int ish_fw_reset_handler(struct ishtp_device *dev) /* ISH FW is dead */ if (!ish_is_input_ready(dev)) return -EPIPE; + + /* Send clock sync at once after reset */ + ishtp_dev->prev_sync = 0; + /* * Set HOST2ISH.ILUP. Apparently we need this BEFORE sending * RESET_NOTIFY_ACK - FW will be checking for it @@ -577,15 +581,14 @@ static void fw_reset_work_fn(struct work_struct *work) */ static void _ish_sync_fw_clock(struct ishtp_device *dev) { - static unsigned long prev_sync; - uint64_t usec; + struct ipc_time_update_msg time = {}; - if (prev_sync && time_before(jiffies, prev_sync + 20 * HZ)) + if (dev->prev_sync && time_before(jiffies, dev->prev_sync + 20 * HZ)) return; - prev_sync = jiffies; - usec = ktime_to_us(ktime_get_boottime()); - ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &usec, sizeof(uint64_t)); + dev->prev_sync = jiffies; + /* The fields of time would be updated while sending message */ + ipc_send_mng_msg(dev, MNG_SYNC_FW_CLOCK, &time, sizeof(time)); } /** diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 9e2401291a2f..ff0fc8010072 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -26,9 +26,11 @@ enum ishtp_driver_data_index { ISHTP_DRIVER_DATA_NONE, ISHTP_DRIVER_DATA_LNL_M, + ISHTP_DRIVER_DATA_PTL, }; #define ISH_FW_GEN_LNL_M "lnlm" +#define ISH_FW_GEN_PTL "ptl" #define ISH_FIRMWARE_PATH(gen) "intel/ish/ish_" gen ".bin" #define ISH_FIRMWARE_PATH_ALL "intel/ish/ish_*.bin" @@ -37,6 +39,9 @@ static struct ishtp_driver_data ishtp_driver_data[] = { [ISHTP_DRIVER_DATA_LNL_M] = { .fw_generation = ISH_FW_GEN_LNL_M, }, + [ISHTP_DRIVER_DATA_PTL] = { + .fw_generation = ISH_FW_GEN_PTL, + }, }; static const struct pci_device_id ish_pci_tbl[] = { @@ -63,6 +68,8 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_H)}, {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_ARL_S)}, {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_LNL_M), .driver_data = ISHTP_DRIVER_DATA_LNL_M}, + {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_H), .driver_data = ISHTP_DRIVER_DATA_PTL}, + {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ISH_PTL_P), .driver_data = ISHTP_DRIVER_DATA_PTL}, {} }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h index 44eddc411e97..ec9f6e87aaf2 100644 --- a/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h +++ b/drivers/hid/intel-ish-hid/ishtp/ishtp-dev.h @@ -253,6 +253,8 @@ struct ishtp_device { unsigned int ipc_tx_cnt; unsigned long long ipc_tx_bytes_cnt; + /* Time of the last clock sync */ + unsigned long prev_sync; const struct ishtp_hw_ops *ops; size_t mtu; uint32_t ishtp_msg_hdr; diff --git a/drivers/hid/intel-thc-hid/Kconfig b/drivers/hid/intel-thc-hid/Kconfig index 91ec84902db8..0351d1137607 100644 --- a/drivers/hid/intel-thc-hid/Kconfig +++ b/drivers/hid/intel-thc-hid/Kconfig @@ -7,7 +7,6 @@ menu "Intel THC HID Support" config INTEL_THC_HID tristate "Intel Touch Host Controller" depends on ACPI - select HID help THC (Touch Host Controller) is the name of the IP block in PCH that interfaces with Touch Devices (ex: touchscreen, touchpad etc.). It diff --git a/drivers/hid/surface-hid/Kconfig b/drivers/hid/surface-hid/Kconfig index 7ce9b5d641eb..d0cfd0d29926 100644 --- a/drivers/hid/surface-hid/Kconfig +++ b/drivers/hid/surface-hid/Kconfig @@ -1,7 +1,6 @@ # SPDX-License-Identifier: GPL-2.0+ menu "Surface System Aggregator Module HID support" depends on SURFACE_AGGREGATOR - depends on INPUT config SURFACE_HID tristate "HID transport driver for Surface System Aggregator Module" @@ -39,4 +38,3 @@ endmenu config SURFACE_HID_CORE tristate - select HID diff --git a/drivers/hid/usbhid/Kconfig b/drivers/hid/usbhid/Kconfig index 7c2032f7f44d..f3194767a45e 100644 --- a/drivers/hid/usbhid/Kconfig +++ b/drivers/hid/usbhid/Kconfig @@ -5,8 +5,7 @@ menu "USB HID support" config USB_HID tristate "USB HID transport layer" default y - depends on USB && INPUT - select HID + depends on HID help Say Y here if you want to connect USB keyboards, mice, joysticks, graphic tablets, or any other HID based devices diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index af5d1dc451f6..f2e6f55d6ca6 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -141,7 +141,7 @@ static int sysctl_record_panic_msg = 1; * sysctl option to allow the user to control whether kmsg data should be * reported to Hyper-V on panic. */ -static struct ctl_table hv_ctl_table[] = { +static const struct ctl_table hv_ctl_table[] = { { .procname = "hyperv_record_panic_msg", .data = &sysctl_record_panic_msg, diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index eec95c724b25..fc438f445771 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -756,6 +756,7 @@ config I2C_IMX config I2C_IMX_LPI2C tristate "IMX Low Power I2C interface" depends on ARCH_MXC || COMPILE_TEST + select I2C_SLAVE help Say Y here if you want to use the Low Power IIC bus controller on the Freescale i.MX processors. diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index e2c2a2ef1c12..35a221e2c11c 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -583,6 +583,9 @@ static int i2c_device_probe(struct device *dev) goto err_detach_pm_domain; } + client->debugfs = debugfs_create_dir(dev_name(&client->dev), + client->adapter->debugfs); + if (driver->probe) status = driver->probe(client); else @@ -602,6 +605,7 @@ static int i2c_device_probe(struct device *dev) return 0; err_release_driver_resources: + debugfs_remove_recursive(client->debugfs); devres_release_group(&client->dev, client->devres_group_id); err_detach_pm_domain: dev_pm_domain_detach(&client->dev, do_power_on); @@ -627,6 +631,8 @@ static void i2c_device_remove(struct device *dev) driver->remove(client); } + debugfs_remove_recursive(client->debugfs); + devres_release_group(&client->dev, client->devres_group_id); dev_pm_domain_detach(&client->dev, true); @@ -1015,8 +1021,6 @@ i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *inf if (status) goto out_remove_swnode; - client->debugfs = debugfs_create_dir(dev_name(&client->dev), adap->debugfs); - dev_dbg(&adap->dev, "client [%s] registered with bus id %s\n", client->name, dev_name(&client->dev)); @@ -1061,7 +1065,6 @@ void i2c_unregister_device(struct i2c_client *client) if (ACPI_COMPANION(&client->dev)) acpi_device_clear_enumerated(ACPI_COMPANION(&client->dev)); - debugfs_remove_recursive(client->debugfs); device_remove_software_node(&client->dev); device_unregister(&client->dev); } @@ -1297,12 +1300,14 @@ new_device_store(struct device *dev, struct device_attribute *attr, info.flags |= I2C_CLIENT_SLAVE; } - info.flags |= I2C_CLIENT_USER; - client = i2c_new_client_device(adap, &info); if (IS_ERR(client)) return PTR_ERR(client); + /* Keep track of the added device */ + mutex_lock(&adap->userspace_clients_lock); + list_add_tail(&client->detected, &adap->userspace_clients); + mutex_unlock(&adap->userspace_clients_lock); dev_info(dev, "%s: Instantiated device %s at 0x%02hx\n", "new_device", info.type, info.addr); @@ -1310,15 +1315,6 @@ new_device_store(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_WO(new_device); -static int __i2c_find_user_addr(struct device *dev, const void *addrp) -{ - struct i2c_client *client = i2c_verify_client(dev); - unsigned short addr = *(unsigned short *)addrp; - - return client && client->flags & I2C_CLIENT_USER && - i2c_encode_flags_to_addr(client) == addr; -} - /* * And of course let the users delete the devices they instantiated, if * they got it wrong. This interface can only be used to delete devices @@ -1333,7 +1329,7 @@ delete_device_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct i2c_adapter *adap = to_i2c_adapter(dev); - struct device *child_dev; + struct i2c_client *client, *next; unsigned short addr; char end; int res; @@ -1349,19 +1345,28 @@ delete_device_store(struct device *dev, struct device_attribute *attr, return -EINVAL; } - mutex_lock(&core_lock); /* Make sure the device was added through sysfs */ - child_dev = device_find_child(&adap->dev, &addr, __i2c_find_user_addr); - if (child_dev) { - i2c_unregister_device(i2c_verify_client(child_dev)); - put_device(child_dev); - } else { - dev_err(dev, "Can't find userspace-created device at %#x\n", addr); - count = -ENOENT; + res = -ENOENT; + mutex_lock_nested(&adap->userspace_clients_lock, + i2c_adapter_depth(adap)); + list_for_each_entry_safe(client, next, &adap->userspace_clients, + detected) { + if (i2c_encode_flags_to_addr(client) == addr) { + dev_info(dev, "%s: Deleting device %s at 0x%02hx\n", + "delete_device", client->name, client->addr); + + list_del(&client->detected); + i2c_unregister_device(client); + res = count; + break; + } } - mutex_unlock(&core_lock); + mutex_unlock(&adap->userspace_clients_lock); - return count; + if (res < 0) + dev_err(dev, "%s: Can't find device in list\n", + "delete_device"); + return res; } static DEVICE_ATTR_IGNORE_LOCKDEP(delete_device, S_IWUSR, NULL, delete_device_store); @@ -1532,6 +1537,8 @@ static int i2c_register_adapter(struct i2c_adapter *adap) adap->locked_flags = 0; rt_mutex_init(&adap->bus_lock); rt_mutex_init(&adap->mux_lock); + mutex_init(&adap->userspace_clients_lock); + INIT_LIST_HEAD(&adap->userspace_clients); /* Set default timeout to 1 second if not already set */ if (adap->timeout == 0) @@ -1697,6 +1704,23 @@ int i2c_add_numbered_adapter(struct i2c_adapter *adap) } EXPORT_SYMBOL_GPL(i2c_add_numbered_adapter); +static void i2c_do_del_adapter(struct i2c_driver *driver, + struct i2c_adapter *adapter) +{ + struct i2c_client *client, *_n; + + /* Remove the devices we created ourselves as the result of hardware + * probing (using a driver's detect method) */ + list_for_each_entry_safe(client, _n, &driver->clients, detected) { + if (client->adapter == adapter) { + dev_dbg(&adapter->dev, "Removing %s at 0x%x\n", + client->name, client->addr); + list_del(&client->detected); + i2c_unregister_device(client); + } + } +} + static int __unregister_client(struct device *dev, void *dummy) { struct i2c_client *client = i2c_verify_client(dev); @@ -1712,6 +1736,12 @@ static int __unregister_dummy(struct device *dev, void *dummy) return 0; } +static int __process_removed_adapter(struct device_driver *d, void *data) +{ + i2c_do_del_adapter(to_i2c_driver(d), data); + return 0; +} + /** * i2c_del_adapter - unregister I2C adapter * @adap: the adapter being unregistered @@ -1723,6 +1753,7 @@ static int __unregister_dummy(struct device *dev, void *dummy) void i2c_del_adapter(struct i2c_adapter *adap) { struct i2c_adapter *found; + struct i2c_client *client, *next; /* First make sure that this adapter was ever added */ mutex_lock(&core_lock); @@ -1734,16 +1765,31 @@ void i2c_del_adapter(struct i2c_adapter *adap) } i2c_acpi_remove_space_handler(adap); + /* Tell drivers about this removal */ + mutex_lock(&core_lock); + bus_for_each_drv(&i2c_bus_type, NULL, adap, + __process_removed_adapter); + mutex_unlock(&core_lock); + + /* Remove devices instantiated from sysfs */ + mutex_lock_nested(&adap->userspace_clients_lock, + i2c_adapter_depth(adap)); + list_for_each_entry_safe(client, next, &adap->userspace_clients, + detected) { + dev_dbg(&adap->dev, "Removing %s at 0x%x\n", client->name, + client->addr); + list_del(&client->detected); + i2c_unregister_device(client); + } + mutex_unlock(&adap->userspace_clients_lock); /* Detach any active clients. This can't fail, thus we do not * check the returned value. This is a two-pass process, because * we can't remove the dummy devices during the first pass: they * could have been instantiated by real devices wishing to clean * them up properly, so we give them a chance to do that first. */ - mutex_lock(&core_lock); device_for_each_child(&adap->dev, NULL, __unregister_client); device_for_each_child(&adap->dev, NULL, __unregister_dummy); - mutex_unlock(&core_lock); /* device name is gone after device_unregister */ dev_dbg(&adap->dev, "adapter [%s] unregistered\n", adap->name); @@ -1963,6 +2009,7 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver) /* add the driver to the list of i2c drivers in the driver core */ driver->driver.owner = owner; driver->driver.bus = &i2c_bus_type; + INIT_LIST_HEAD(&driver->clients); /* When registration returns, the driver core * will have called probe() for all matching-but-unbound devices. @@ -1980,13 +2027,10 @@ int i2c_register_driver(struct module *owner, struct i2c_driver *driver) } EXPORT_SYMBOL(i2c_register_driver); -static int __i2c_unregister_detected_client(struct device *dev, void *argp) +static int __process_removed_driver(struct device *dev, void *data) { - struct i2c_client *client = i2c_verify_client(dev); - - if (client && client->flags & I2C_CLIENT_AUTO) - i2c_unregister_device(client); - + if (dev->type == &i2c_adapter_type) + i2c_do_del_adapter(data, to_i2c_adapter(dev)); return 0; } @@ -1997,12 +2041,7 @@ static int __i2c_unregister_detected_client(struct device *dev, void *argp) */ void i2c_del_driver(struct i2c_driver *driver) { - mutex_lock(&core_lock); - /* Satisfy __must_check, function can't fail */ - if (driver_for_each_device(&driver->driver, NULL, NULL, - __i2c_unregister_detected_client)) { - } - mutex_unlock(&core_lock); + i2c_for_each_dev(driver, __process_removed_driver); driver_unregister(&driver->driver); pr_debug("driver [%s] unregistered\n", driver->driver.name); @@ -2429,7 +2468,6 @@ static int i2c_detect_address(struct i2c_client *temp_client, /* Finally call the custom detection function */ memset(&info, 0, sizeof(struct i2c_board_info)); info.addr = addr; - info.flags = I2C_CLIENT_AUTO; err = driver->detect(temp_client, &info); if (err) { /* -ENODEV is returned if the detection fails. We catch it @@ -2456,7 +2494,9 @@ static int i2c_detect_address(struct i2c_client *temp_client, dev_dbg(&adapter->dev, "Creating %s at 0x%02x\n", info.type, info.addr); client = i2c_new_client_device(adapter, &info); - if (IS_ERR(client)) + if (!IS_ERR(client)) + list_add_tail(&client->detected, &driver->clients); + else dev_err(&adapter->dev, "Failed creating %s at 0x%02x\n", info.type, info.addr); } diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index 0bbda60d3cdc..23caea22f8dc 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -175,6 +175,7 @@ #define CONTROL_GAM_EN 25 #define CONTROL_GALOG_EN 28 #define CONTROL_GAINT_EN 29 +#define CONTROL_EPH_EN 45 #define CONTROL_XT_EN 50 #define CONTROL_INTCAPXT_EN 51 #define CONTROL_IRTCACHEDIS 59 diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index c5cd92edada0..cb536d372b12 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -2653,6 +2653,10 @@ static void iommu_init_flags(struct amd_iommu *iommu) /* Set IOTLB invalidation timeout to 1s */ iommu_set_inv_tlb_timeout(iommu, CTRL_INV_TO_1S); + + /* Enable Enhanced Peripheral Page Request Handling */ + if (check_feature(FEATURE_EPHSUP)) + iommu_feature_enable(iommu, CONTROL_EPH_EN); } static void iommu_apply_resume_quirks(struct amd_iommu *iommu) @@ -3194,7 +3198,7 @@ out: return true; } -static void iommu_snp_enable(void) +static __init void iommu_snp_enable(void) { #ifdef CONFIG_KVM_AMD_SEV if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) @@ -3219,6 +3223,14 @@ static void iommu_snp_enable(void) goto disable_snp; } + /* + * Enable host SNP support once SNP support is checked on IOMMU. + */ + if (snp_rmptable_init()) { + pr_warn("SNP: RMP initialization failed, SNP cannot be supported.\n"); + goto disable_snp; + } + pr_info("IOMMU SNP support enabled.\n"); return; @@ -3318,6 +3330,19 @@ static int __init iommu_go_to_state(enum iommu_init_state state) ret = state_next(); } + /* + * SNP platform initilazation requires IOMMUs to be fully configured. + * If the SNP support on IOMMUs has NOT been checked, simply mark SNP + * as unsupported. If the SNP support on IOMMUs has been checked and + * host SNP support enabled but RMP enforcement has not been enabled + * in IOMMUs, then the system is in a half-baked state, but can limp + * along as all memory should be Hypervisor-Owned in the RMP. WARN, + * but leave SNP as "supported" to avoid confusing the kernel. + */ + if (ret && cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !WARN_ON_ONCE(amd_iommu_snp_en)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + return ret; } @@ -3426,18 +3451,23 @@ void __init amd_iommu_detect(void) int ret; if (no_iommu || (iommu_detected && !gart_iommu_aperture)) - return; + goto disable_snp; if (!amd_iommu_sme_check()) - return; + goto disable_snp; ret = iommu_go_to_state(IOMMU_IVRS_DETECTED); if (ret) - return; + goto disable_snp; amd_iommu_detected = true; iommu_detected = 1; x86_init.iommu.iommu_init = amd_iommu_init; + return; + +disable_snp: + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); } /**************************************************************************** diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index c666ecab955d..69e23e017d9e 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -249,7 +249,7 @@ struct exynos_iommu_domain { struct list_head clients; /* list of sysmmu_drvdata.domain_node */ sysmmu_pte_t *pgtable; /* lv1 page table, 16KB */ short *lv2entcnt; /* free lv2 entry counter for each section */ - spinlock_t lock; /* lock for modyfying list of clients */ + spinlock_t lock; /* lock for modifying list of clients */ spinlock_t pgtablelock; /* lock for modifying page table @ pgtable */ struct iommu_domain domain; /* generic domain data structure */ }; @@ -292,7 +292,7 @@ struct sysmmu_drvdata { struct clk *aclk; /* SYSMMU's aclk clock */ struct clk *pclk; /* SYSMMU's pclk clock */ struct clk *clk_master; /* master's device clock */ - spinlock_t lock; /* lock for modyfying state */ + spinlock_t lock; /* lock for modifying state */ bool active; /* current status */ struct exynos_iommu_domain *domain; /* domain we belong to */ struct list_head domain_node; /* node for domain clients list */ @@ -746,7 +746,7 @@ static int exynos_sysmmu_probe(struct platform_device *pdev) ret = devm_request_irq(dev, irq, exynos_sysmmu_irq, 0, dev_name(dev), data); if (ret) { - dev_err(dev, "Unabled to register handler of irq %d\n", irq); + dev_err(dev, "Unable to register handler of irq %d\n", irq); return ret; } diff --git a/drivers/iommu/intel/prq.c b/drivers/iommu/intel/prq.c index c2d792db52c3..064194399b38 100644 --- a/drivers/iommu/intel/prq.c +++ b/drivers/iommu/intel/prq.c @@ -87,7 +87,9 @@ prq_retry: struct page_req_dsc *req; req = &iommu->prq[head / sizeof(*req)]; - if (!req->pasid_present || req->pasid != pasid) { + if (req->rid != sid || + (req->pasid_present && pasid != req->pasid) || + (!req->pasid_present && pasid != IOMMU_NO_PASID)) { head = (head + sizeof(*req)) & PRQ_RING_MASK; continue; } diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c index 4674e618797c..8b5926c1452e 100644 --- a/drivers/iommu/io-pgfault.c +++ b/drivers/iommu/io-pgfault.c @@ -478,6 +478,7 @@ void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev) ops->page_response(dev, iopf, &resp); list_del_init(&group->pending_node); + iopf_free_group(group); } mutex_unlock(&fault_param->lock); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 870c3cdbd0f6..60aed01e54f2 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -1756,7 +1756,7 @@ static int iommu_get_def_domain_type(struct iommu_group *group, group->id); /* - * Try to recover, drivers are allowed to force IDENITY or DMA, IDENTITY + * Try to recover, drivers are allowed to force IDENTITY or DMA, IDENTITY * takes precedence. */ if (type == IOMMU_DOMAIN_IDENTITY) diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index be063bfb50c4..c11b9965c4ad 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -169,6 +169,7 @@ config IXP4XX_IRQ config LAN966X_OIC tristate "Microchip LAN966x OIC Support" + depends on MCHP_LAN966X_PCI || COMPILE_TEST select GENERIC_IRQ_CHIP select IRQ_DOMAIN help diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c index da5250f0155c..2b1684c60e3c 100644 --- a/drivers/irqchip/irq-apple-aic.c +++ b/drivers/irqchip/irq-apple-aic.c @@ -577,7 +577,8 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs) AIC_FIQ_HWIRQ(AIC_TMR_EL02_VIRT)); } - if (read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & PMCR0_IACT) { + if ((read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & (PMCR0_IMODE | PMCR0_IACT)) == + (FIELD_PREP(PMCR0_IMODE, PMCR0_IMODE_FIQ) | PMCR0_IACT)) { int irq; if (cpumask_test_cpu(smp_processor_id(), &aic_irqc->fiq_aff[AIC_CPU_PMU_P]->aff)) diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c index b337f6c05f18..4eebed39880a 100644 --- a/drivers/irqchip/irq-mvebu-icu.c +++ b/drivers/irqchip/irq-mvebu-icu.c @@ -68,7 +68,8 @@ static int mvebu_icu_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { unsigned int param_count = static_branch_unlikely(&legacy_bindings) ? 3 : 2; - struct mvebu_icu_msi_data *msi_data = d->host_data; + struct msi_domain_info *info = d->host_data; + struct mvebu_icu_msi_data *msi_data = info->chip_data; struct mvebu_icu *icu = msi_data->icu; /* Check the count of the parameters in dt */ diff --git a/drivers/irqchip/irq-partition-percpu.c b/drivers/irqchip/irq-partition-percpu.c index 8e76d2913e6b..4441ffe149ea 100644 --- a/drivers/irqchip/irq-partition-percpu.c +++ b/drivers/irqchip/irq-partition-percpu.c @@ -98,7 +98,7 @@ static void partition_irq_print_chip(struct irq_data *d, struct seq_file *p) struct irq_chip *chip = irq_desc_get_chip(part->chained_desc); struct irq_data *data = irq_desc_get_irq_data(part->chained_desc); - seq_printf(p, " %5s-%lu", chip->name, data->hwirq); + seq_printf(p, "%5s-%lu", chip->name, data->hwirq); } static struct irq_chip partition_irq_chip = { diff --git a/drivers/irqchip/irq-riscv-imsic-early.c b/drivers/irqchip/irq-riscv-imsic-early.c index c5c2e6929a2f..275df5005705 100644 --- a/drivers/irqchip/irq-riscv-imsic-early.c +++ b/drivers/irqchip/irq-riscv-imsic-early.c @@ -27,7 +27,7 @@ static void imsic_ipi_send(unsigned int cpu) { struct imsic_local_config *local = per_cpu_ptr(imsic->global.local, cpu); - writel_relaxed(IMSIC_IPI_ID, local->msi_va); + writel(IMSIC_IPI_ID, local->msi_va); } static void imsic_ipi_starting_cpu(void) diff --git a/drivers/irqchip/irq-thead-c900-aclint-sswi.c b/drivers/irqchip/irq-thead-c900-aclint-sswi.c index b0e366ade427..8ff6e7a1363b 100644 --- a/drivers/irqchip/irq-thead-c900-aclint-sswi.c +++ b/drivers/irqchip/irq-thead-c900-aclint-sswi.c @@ -31,7 +31,7 @@ static DEFINE_PER_CPU(void __iomem *, sswi_cpu_regs); static void thead_aclint_sswi_ipi_send(unsigned int cpu) { - writel_relaxed(0x1, per_cpu(sswi_cpu_regs, cpu)); + writel(0x1, per_cpu(sswi_cpu_regs, cpu)); } static void thead_aclint_sswi_ipi_clear(void) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index ec4ecd96e6b1..23c09d22fcdb 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -2355,7 +2355,10 @@ static int bitmap_get_stats(void *data, struct md_bitmap_stats *stats) if (!bitmap) return -ENOENT; - + if (bitmap->mddev->bitmap_info.external) + return -ENOENT; + if (!bitmap->storage.sb_page) /* no superblock */ + return -EINVAL; sb = kmap_local_page(bitmap->storage.sb_page); stats->sync_size = le64_to_cpu(sb->sync_size); kunmap_local(sb); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index a382929ce7ba..369aed044b40 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -76,10 +76,8 @@ static int linear_set_limits(struct mddev *mddev) lim.max_write_zeroes_sectors = mddev->chunk_sectors; lim.io_min = mddev->chunk_sectors << 9; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); - if (err) { - queue_limits_cancel_update(mddev->gendisk->queue); + if (err) return err; - } return queue_limits_set(mddev->gendisk->queue, &lim); } diff --git a/drivers/md/md.c b/drivers/md/md.c index 866015b681af..30b3dbbce2d2 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -294,7 +294,7 @@ void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev) static struct ctl_table_header *raid_table_header; -static struct ctl_table raid_table[] = { +static const struct ctl_table raid_table[] = { { .procname = "speed_limit_min", .data = &sysctl_speed_limit_min, @@ -8376,6 +8376,10 @@ static int md_seq_show(struct seq_file *seq, void *v) return 0; spin_unlock(&all_mddevs_lock); + + /* prevent bitmap to be freed after checking */ + mutex_lock(&mddev->bitmap_info.mutex); + spin_lock(&mddev->lock); if (mddev->pers || mddev->raid_disks || !list_empty(&mddev->disks)) { seq_printf(seq, "%s : ", mdname(mddev)); @@ -8451,6 +8455,7 @@ static int md_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "\n"); } spin_unlock(&mddev->lock); + mutex_unlock(&mddev->bitmap_info.mutex); spin_lock(&all_mddevs_lock); if (mddev == list_last_entry(&all_mddevs, struct mddev, all_mddevs)) diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index a10d4f4d9f95..deadbcea5e22 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -790,27 +790,14 @@ static const u8 uvc_media_transport_input_guid[16] = UVC_GUID_UVC_MEDIA_TRANSPORT_INPUT; static const u8 uvc_processing_guid[16] = UVC_GUID_UVC_PROCESSING; -static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type, - u16 id, unsigned int num_pads, - unsigned int extra_size) +static struct uvc_entity *uvc_alloc_entity(u16 type, u16 id, + unsigned int num_pads, unsigned int extra_size) { struct uvc_entity *entity; unsigned int num_inputs; unsigned int size; unsigned int i; - /* Per UVC 1.1+ spec 3.7.2, the ID should be non-zero. */ - if (id == 0) { - dev_err(&dev->udev->dev, "Found Unit with invalid ID 0.\n"); - return ERR_PTR(-EINVAL); - } - - /* Per UVC 1.1+ spec 3.7.2, the ID is unique. */ - if (uvc_entity_by_id(dev, id)) { - dev_err(&dev->udev->dev, "Found multiple Units with ID %u\n", id); - return ERR_PTR(-EINVAL); - } - extra_size = roundup(extra_size, sizeof(*entity->pads)); if (num_pads) num_inputs = type & UVC_TERM_OUTPUT ? num_pads : num_pads - 1; @@ -820,7 +807,7 @@ static struct uvc_entity *uvc_alloc_new_entity(struct uvc_device *dev, u16 type, + num_inputs; entity = kzalloc(size, GFP_KERNEL); if (entity == NULL) - return ERR_PTR(-ENOMEM); + return NULL; entity->id = id; entity->type = type; @@ -932,10 +919,10 @@ static int uvc_parse_vendor_control(struct uvc_device *dev, break; } - unit = uvc_alloc_new_entity(dev, UVC_VC_EXTENSION_UNIT, - buffer[3], p + 1, 2 * n); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(UVC_VC_EXTENSION_UNIT, buffer[3], + p + 1, 2*n); + if (unit == NULL) + return -ENOMEM; memcpy(unit->guid, &buffer[4], 16); unit->extension.bNumControls = buffer[20]; @@ -1044,10 +1031,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - term = uvc_alloc_new_entity(dev, type | UVC_TERM_INPUT, - buffer[3], 1, n + p); - if (IS_ERR(term)) - return PTR_ERR(term); + term = uvc_alloc_entity(type | UVC_TERM_INPUT, buffer[3], + 1, n + p); + if (term == NULL) + return -ENOMEM; if (UVC_ENTITY_TYPE(term) == UVC_ITT_CAMERA) { term->camera.bControlSize = n; @@ -1103,10 +1090,10 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return 0; } - term = uvc_alloc_new_entity(dev, type | UVC_TERM_OUTPUT, - buffer[3], 1, 0); - if (IS_ERR(term)) - return PTR_ERR(term); + term = uvc_alloc_entity(type | UVC_TERM_OUTPUT, buffer[3], + 1, 0); + if (term == NULL) + return -ENOMEM; memcpy(term->baSourceID, &buffer[7], 1); @@ -1125,10 +1112,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], - p + 1, 0); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, 0); + if (unit == NULL) + return -ENOMEM; memcpy(unit->baSourceID, &buffer[5], p); @@ -1148,9 +1134,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], 2, n); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(buffer[2], buffer[3], 2, n); + if (unit == NULL) + return -ENOMEM; memcpy(unit->baSourceID, &buffer[4], 1); unit->processing.wMaxMultiplier = @@ -1177,10 +1163,9 @@ static int uvc_parse_standard_control(struct uvc_device *dev, return -EINVAL; } - unit = uvc_alloc_new_entity(dev, buffer[2], buffer[3], - p + 1, n); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(buffer[2], buffer[3], p + 1, n); + if (unit == NULL) + return -ENOMEM; memcpy(unit->guid, &buffer[4], 16); unit->extension.bNumControls = buffer[20]; @@ -1320,10 +1305,9 @@ static int uvc_gpio_parse(struct uvc_device *dev) return dev_err_probe(&dev->intf->dev, irq, "No IRQ for privacy GPIO\n"); - unit = uvc_alloc_new_entity(dev, UVC_EXT_GPIO_UNIT, - UVC_EXT_GPIO_UNIT_ID, 0, 1); - if (IS_ERR(unit)) - return PTR_ERR(unit); + unit = uvc_alloc_entity(UVC_EXT_GPIO_UNIT, UVC_EXT_GPIO_UNIT_ID, 0, 1); + if (!unit) + return -ENOMEM; unit->gpio.gpio_privacy = gpio_privacy; unit->gpio.irq = irq; diff --git a/drivers/mfd/syscon.c b/drivers/mfd/syscon.c index 226915ca3c93..aa4a9940b569 100644 --- a/drivers/mfd/syscon.c +++ b/drivers/mfd/syscon.c @@ -159,6 +159,7 @@ err_regmap: } static struct regmap *device_node_get_regmap(struct device_node *np, + bool create_regmap, bool check_res) { struct syscon *entry, *syscon = NULL; @@ -172,7 +173,7 @@ static struct regmap *device_node_get_regmap(struct device_node *np, } if (!syscon) { - if (of_device_is_compatible(np, "syscon")) + if (create_regmap) syscon = of_syscon_register(np, check_res); else syscon = ERR_PTR(-EINVAL); @@ -233,15 +234,37 @@ err_unlock: } EXPORT_SYMBOL_GPL(of_syscon_register_regmap); +/** + * device_node_to_regmap() - Get or create a regmap for specified device node + * @np: Device tree node + * + * Get a regmap for the specified device node. If there's not an existing + * regmap, then one is instantiated. This function should not be used if the + * device node has a custom regmap driver or has resources (clocks, resets) to + * be managed. Use syscon_node_to_regmap() instead for those cases. + * + * Return: regmap ptr on success, negative error code on failure. + */ struct regmap *device_node_to_regmap(struct device_node *np) { - return device_node_get_regmap(np, false); + return device_node_get_regmap(np, true, false); } EXPORT_SYMBOL_GPL(device_node_to_regmap); +/** + * syscon_node_to_regmap() - Get or create a regmap for specified syscon device node + * @np: Device tree node + * + * Get a regmap for the specified device node. If there's not an existing + * regmap, then one is instantiated if the node is a generic "syscon". This + * function is safe to use for a syscon registered with + * of_syscon_register_regmap(). + * + * Return: regmap ptr on success, negative error code on failure. + */ struct regmap *syscon_node_to_regmap(struct device_node *np) { - return device_node_get_regmap(np, true); + return device_node_get_regmap(np, of_device_is_compatible(np, "syscon"), true); } EXPORT_SYMBOL_GPL(syscon_node_to_regmap); diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c index 61b66e318488..7a3c34306de9 100644 --- a/drivers/misc/sgi-xp/xpc_main.c +++ b/drivers/misc/sgi-xp/xpc_main.c @@ -93,7 +93,7 @@ int xpc_disengage_timelimit = XPC_DISENGAGE_DEFAULT_TIMELIMIT; static int xpc_disengage_min_timelimit; /* = 0 */ static int xpc_disengage_max_timelimit = 120; -static struct ctl_table xpc_sys_xpc_hb[] = { +static const struct ctl_table xpc_sys_xpc_hb[] = { { .procname = "hb_interval", .data = &xpc_hb_interval, @@ -111,7 +111,7 @@ static struct ctl_table xpc_sys_xpc_hb[] = { .extra1 = &xpc_hb_check_min_interval, .extra2 = &xpc_hb_check_max_interval}, }; -static struct ctl_table xpc_sys_xpc[] = { +static const struct ctl_table xpc_sys_xpc[] = { { .procname = "disengage_timelimit", .data = &xpc_disengage_timelimit, diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 4b6e91372526..345ea91629e0 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -273,6 +273,7 @@ #define MSDC_PAD_TUNE_CMD2_SEL BIT(21) /* RW */ #define PAD_DS_TUNE_DLY_SEL BIT(0) /* RW */ +#define PAD_DS_TUNE_DLY2_SEL BIT(1) /* RW */ #define PAD_DS_TUNE_DLY1 GENMASK(6, 2) /* RW */ #define PAD_DS_TUNE_DLY2 GENMASK(11, 7) /* RW */ #define PAD_DS_TUNE_DLY3 GENMASK(16, 12) /* RW */ @@ -318,6 +319,7 @@ /* EMMC50_PAD_DS_TUNE mask */ #define PAD_DS_DLY_SEL BIT(16) /* RW */ +#define PAD_DS_DLY2_SEL BIT(15) /* RW */ #define PAD_DS_DLY1 GENMASK(14, 10) /* RW */ #define PAD_DS_DLY3 GENMASK(4, 0) /* RW */ @@ -2504,13 +2506,23 @@ tune_done: static int msdc_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios) { struct msdc_host *host = mmc_priv(mmc); + host->hs400_mode = true; - if (host->top_base) - writel(host->hs400_ds_delay, - host->top_base + EMMC50_PAD_DS_TUNE); - else - writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE); + if (host->top_base) { + if (host->hs400_ds_dly3) + sdr_set_field(host->top_base + EMMC50_PAD_DS_TUNE, + PAD_DS_DLY3, host->hs400_ds_dly3); + if (host->hs400_ds_delay) + writel(host->hs400_ds_delay, + host->top_base + EMMC50_PAD_DS_TUNE); + } else { + if (host->hs400_ds_dly3) + sdr_set_field(host->base + PAD_DS_TUNE, + PAD_DS_TUNE_DLY3, host->hs400_ds_dly3); + if (host->hs400_ds_delay) + writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE); + } /* hs400 mode must set it to 0 */ sdr_clr_bits(host->base + MSDC_PATCH_BIT2, MSDC_PATCH_BIT2_CFGCRCSTS); /* to improve read performance, set outstanding to 2 */ @@ -2530,14 +2542,11 @@ static int msdc_execute_hs400_tuning(struct mmc_host *mmc, struct mmc_card *card if (host->top_base) { sdr_set_bits(host->top_base + EMMC50_PAD_DS_TUNE, PAD_DS_DLY_SEL); - if (host->hs400_ds_dly3) - sdr_set_field(host->top_base + EMMC50_PAD_DS_TUNE, - PAD_DS_DLY3, host->hs400_ds_dly3); + sdr_clr_bits(host->top_base + EMMC50_PAD_DS_TUNE, + PAD_DS_DLY2_SEL); } else { sdr_set_bits(host->base + PAD_DS_TUNE, PAD_DS_TUNE_DLY_SEL); - if (host->hs400_ds_dly3) - sdr_set_field(host->base + PAD_DS_TUNE, - PAD_DS_TUNE_DLY3, host->hs400_ds_dly3); + sdr_clr_bits(host->base + PAD_DS_TUNE, PAD_DS_TUNE_DLY2_SEL); } host->hs400_tuning = true; diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index b73f673db92b..f75c31815ab0 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -155,7 +155,6 @@ struct sdhci_am654_data { u32 tuning_loop; #define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0) -#define SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA BIT(1) }; struct window { @@ -357,29 +356,6 @@ static void sdhci_j721e_4bit_set_clock(struct sdhci_host *host, sdhci_set_clock(host, clock); } -static int sdhci_am654_start_signal_voltage_switch(struct mmc_host *mmc, struct mmc_ios *ios) -{ - struct sdhci_host *host = mmc_priv(mmc); - struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); - struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host); - int ret; - - if ((sdhci_am654->quirks & SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA) && - ios->signal_voltage == MMC_SIGNAL_VOLTAGE_180) { - if (!IS_ERR(mmc->supply.vqmmc)) { - ret = mmc_regulator_set_vqmmc(mmc, ios); - if (ret < 0) { - pr_err("%s: Switching to 1.8V signalling voltage failed,\n", - mmc_hostname(mmc)); - return -EIO; - } - } - return 0; - } - - return sdhci_start_signal_voltage_switch(mmc, ios); -} - static u8 sdhci_am654_write_power_on(struct sdhci_host *host, u8 val, int reg) { writeb(val, host->ioaddr + reg); @@ -868,11 +844,6 @@ static int sdhci_am654_get_of_property(struct platform_device *pdev, if (device_property_read_bool(dev, "ti,fails-without-test-cd")) sdhci_am654->quirks |= SDHCI_AM654_QUIRK_FORCE_CDTEST; - /* Suppress v1p8 ena for eMMC and SD with vqmmc supply */ - if (!!of_parse_phandle(dev->of_node, "vmmc-supply", 0) == - !!of_parse_phandle(dev->of_node, "vqmmc-supply", 0)) - sdhci_am654->quirks |= SDHCI_AM654_QUIRK_SUPPRESS_V1P8_ENA; - sdhci_get_of_property(pdev); return 0; @@ -969,7 +940,6 @@ static int sdhci_am654_probe(struct platform_device *pdev) goto err_pltfm_free; } - host->mmc_host_ops.start_signal_voltage_switch = sdhci_am654_start_signal_voltage_switch; host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning; pm_runtime_get_noresume(dev); diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index ee7e1d908986..847c11542f02 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -404,6 +404,7 @@ out_list_del: int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old) { unsigned long flags; + unsigned int memflags; lockdep_assert_held(&mtd_table_mutex); @@ -420,10 +421,10 @@ int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old) spin_unlock_irqrestore(&old->queue_lock, flags); /* freeze+quiesce queue to ensure all requests are flushed */ - blk_mq_freeze_queue(old->rq); + memflags = blk_mq_freeze_queue(old->rq); blk_mq_quiesce_queue(old->rq); blk_mq_unquiesce_queue(old->rq); - blk_mq_unfreeze_queue(old->rq); + blk_mq_unfreeze_queue(old->rq, memflags); /* If the device is currently open, tell trans driver to close it, then put mtd device, and don't touch it again */ diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c index 30be4ed68fad..ef6a22f372f9 100644 --- a/drivers/mtd/ubi/build.c +++ b/drivers/mtd/ubi/build.c @@ -1537,7 +1537,7 @@ static int ubi_mtd_param_parse(const char *val, const struct kernel_param *kp) if (token) { int err = kstrtoint(token, 10, &p->ubi_num); - if (err) { + if (err || p->ubi_num < UBI_DEV_NUM_AUTO) { pr_err("UBI error: bad value for ubi_num parameter: %s\n", token); return -EINVAL; diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 6bb80d7714bc..b700a0efaa93 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -828,6 +828,70 @@ out_free: return err; } +static int ubi_get_ec_info(struct ubi_device *ubi, struct ubi_ecinfo_req __user *ureq) +{ + struct ubi_ecinfo_req req; + struct ubi_wl_entry *wl; + int read_cnt; + int peb; + int end_peb; + + /* Copy the input arguments */ + if (copy_from_user(&req, ureq, sizeof(struct ubi_ecinfo_req))) + return -EFAULT; + + /* Check input arguments */ + if (req.length <= 0 || req.start < 0 || req.start >= ubi->peb_count) + return -EINVAL; + + if (check_add_overflow(req.start, req.length, &end_peb)) + return -EINVAL; + + if (end_peb > ubi->peb_count) + end_peb = ubi->peb_count; + + /* Check access rights before filling erase_counters array */ + if (!access_ok((void __user *)ureq->erase_counters, + (end_peb-req.start) * sizeof(int32_t))) + return -EFAULT; + + /* Fill erase counter array */ + read_cnt = 0; + for (peb = req.start; peb < end_peb; read_cnt++, peb++) { + int ec; + + if (ubi_io_is_bad(ubi, peb)) { + if (__put_user(UBI_UNKNOWN, ureq->erase_counters+read_cnt)) + return -EFAULT; + + continue; + } + + spin_lock(&ubi->wl_lock); + + wl = ubi->lookuptbl[peb]; + if (wl) + ec = wl->ec; + else + ec = UBI_UNKNOWN; + + spin_unlock(&ubi->wl_lock); + + if (__put_user(ec, ureq->erase_counters+read_cnt)) + return -EFAULT; + + } + + /* Return actual read length */ + req.read_length = read_cnt; + + /* Copy everything except erase counter array */ + if (copy_to_user(ureq, &req, sizeof(struct ubi_ecinfo_req))) + return -EFAULT; + + return 0; +} + static long ubi_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -991,6 +1055,12 @@ static long ubi_cdev_ioctl(struct file *file, unsigned int cmd, break; } + case UBI_IOCECNFO: + { + err = ubi_get_ec_info(ubi, argp); + break; + } + default: err = -ENOTTY; break; diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index 26cc53ad34ec..c792b9bcab9b 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -549,7 +549,6 @@ struct ubi_debug_info { * @peb_buf: a buffer of PEB size used for different purposes * @buf_mutex: protects @peb_buf * @ckvol_mutex: serializes static volume checking when opening - * @wl_reboot_notifier: close all wear-leveling work before reboot * * @dbg: debugging information for this UBI device */ @@ -652,7 +651,6 @@ struct ubi_device { void *peb_buf; struct mutex buf_mutex; struct mutex ckvol_mutex; - struct notifier_block wl_reboot_notifier; struct ubi_debug_info dbg; }; diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 4f6f339d8fb8..fbd399cf6503 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -89,7 +89,6 @@ #include <linux/crc32.h> #include <linux/freezer.h> #include <linux/kthread.h> -#include <linux/reboot.h> #include "ubi.h" #include "wl.h" @@ -128,8 +127,6 @@ static int self_check_in_wl_tree(const struct ubi_device *ubi, struct ubi_wl_entry *e, struct rb_root *root); static int self_check_in_pq(const struct ubi_device *ubi, struct ubi_wl_entry *e); -static int ubi_wl_reboot_notifier(struct notifier_block *n, - unsigned long state, void *cmd); /** * wl_tree_add - add a wear-leveling entry to a WL RB-tree. @@ -1953,13 +1950,6 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) if (!ubi->ro_mode && !ubi->fm_disabled) ubi_ensure_anchor_pebs(ubi); #endif - - if (!ubi->wl_reboot_notifier.notifier_call) { - ubi->wl_reboot_notifier.notifier_call = ubi_wl_reboot_notifier; - ubi->wl_reboot_notifier.priority = 1; /* Higher than MTD */ - register_reboot_notifier(&ubi->wl_reboot_notifier); - } - return 0; out_free: @@ -2005,17 +1995,6 @@ void ubi_wl_close(struct ubi_device *ubi) kfree(ubi->lookuptbl); } -static int ubi_wl_reboot_notifier(struct notifier_block *n, - unsigned long state, void *cmd) -{ - struct ubi_device *ubi; - - ubi = container_of(n, struct ubi_device, wl_reboot_notifier); - ubi_wl_close(ubi); - - return NOTIFY_DONE; -} - /** * self_check_ec - make sure that the erase counter of a PEB is correct. * @ubi: UBI device description object diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 7b78c2bada81..e45bba240cbc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1538,17 +1538,20 @@ static netdev_features_t bond_fix_features(struct net_device *dev, NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) + NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \ + NETIF_F_GSO_PARTIAL) #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_GSO_SOFTWARE) +#define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP) + static void bond_compute_features(struct bonding *bond) { + netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES; unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; - netdev_features_t gso_partial_features = NETIF_F_GSO_ESP; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; #ifdef CONFIG_XFRM_OFFLOAD @@ -1582,8 +1585,9 @@ static void bond_compute_features(struct bonding *bond) BOND_XFRM_FEATURES); #endif /* CONFIG_XFRM_OFFLOAD */ - if (slave->dev->hw_enc_features & NETIF_F_GSO_PARTIAL) - gso_partial_features &= slave->dev->gso_partial_features; + gso_partial_features = netdev_increment_features(gso_partial_features, + slave->dev->gso_partial_features, + BOND_GSO_PARTIAL_FEATURES); mpls_features = netdev_increment_features(mpls_features, slave->dev->mpls_features, @@ -1598,12 +1602,8 @@ static void bond_compute_features(struct bonding *bond) } bond_dev->hard_header_len = max_hard_header_len; - if (gso_partial_features & NETIF_F_GSO_ESP) - bond_dev->gso_partial_features |= NETIF_F_GSO_ESP; - else - bond_dev->gso_partial_features &= ~NETIF_F_GSO_ESP; - done: + bond_dev->gso_partial_features = gso_partial_features; bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | @@ -6046,6 +6046,7 @@ void bond_setup(struct net_device *bond_dev) bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; bond_dev->features |= bond_dev->hw_features; bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; + bond_dev->features |= NETIF_F_GSO_PARTIAL; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_features |= BOND_XFRM_FEATURES; /* Only enable XFRM features if this is an active-backup config */ diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index 6cba9717a6d8..399844809bbe 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -385,15 +385,16 @@ static int c_can_plat_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "registering %s failed (err=%d)\n", KBUILD_MODNAME, ret); - goto exit_free_device; + goto exit_pm_runtime; } dev_info(&pdev->dev, "%s device registered (regs=%p, irq=%d)\n", KBUILD_MODNAME, priv->base, dev->irq); return 0; -exit_free_device: +exit_pm_runtime: pm_runtime_disable(priv->device); +exit_free_device: free_c_can_dev(dev); exit: dev_err(&pdev->dev, "probe failed\n"); diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 64c349fd4600..f65c1a1e05cc 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -867,10 +867,12 @@ static void ctucan_err_interrupt(struct net_device *ndev, u32 isr) } break; case CAN_STATE_ERROR_ACTIVE: - cf->can_id |= CAN_ERR_CNT; - cf->data[1] = CAN_ERR_CRTL_ACTIVE; - cf->data[6] = bec.txerr; - cf->data[7] = bec.rxerr; + if (skb) { + cf->can_id |= CAN_ERR_CNT; + cf->data[1] = CAN_ERR_CRTL_ACTIVE; + cf->data[6] = bec.txerr; + cf->data[7] = bec.rxerr; + } break; default: netdev_warn(ndev, "unhandled error state (%d:%s)!\n", diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c index df18c85fc078..d9a937ba126c 100644 --- a/drivers/net/can/rockchip/rockchip_canfd-core.c +++ b/drivers/net/can/rockchip/rockchip_canfd-core.c @@ -622,7 +622,7 @@ rkcanfd_handle_rx_fifo_overflow_int(struct rkcanfd_priv *priv) netdev_dbg(priv->ndev, "RX-FIFO overflow\n"); skb = rkcanfd_alloc_can_err_skb(priv, &cf, ×tamp); - if (skb) + if (!skb) return 0; rkcanfd_get_berr_counter_corrected(priv, &bec); diff --git a/drivers/net/can/usb/etas_es58x/es58x_devlink.c b/drivers/net/can/usb/etas_es58x/es58x_devlink.c index eee20839d96f..0d155eb1b9e9 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_devlink.c +++ b/drivers/net/can/usb/etas_es58x/es58x_devlink.c @@ -248,7 +248,11 @@ static int es58x_devlink_info_get(struct devlink *devlink, return ret; } - return devlink_info_serial_number_put(req, es58x_dev->udev->serial); + if (es58x_dev->udev->serial) + ret = devlink_info_serial_number_put(req, + es58x_dev->udev->serial); + + return ret; } const struct devlink_ops es58x_dl_ops = { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index fe0e3e2a8117..71e50fc65c14 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -1441,7 +1441,9 @@ void aq_nic_deinit(struct aq_nic_s *self, bool link_down) aq_ptp_ring_free(self); aq_ptp_free(self); - if (likely(self->aq_fw_ops->deinit) && link_down) { + /* May be invoked during hot unplug. */ + if (pci_device_is_present(self->pdev) && + likely(self->aq_fw_ops->deinit) && link_down) { mutex_lock(&self->fwreq_mutex); self->aq_fw_ops->deinit(self->aq_hw); mutex_unlock(&self->fwreq_mutex); diff --git a/drivers/net/ethernet/broadcom/bgmac.h b/drivers/net/ethernet/broadcom/bgmac.h index d73ef262991d..6fee9a41839c 100644 --- a/drivers/net/ethernet/broadcom/bgmac.h +++ b/drivers/net/ethernet/broadcom/bgmac.h @@ -328,8 +328,7 @@ #define BGMAC_RX_FRAME_OFFSET 30 /* There are 2 unused bytes between header and real data */ #define BGMAC_RX_BUF_OFFSET (NET_SKB_PAD + NET_IP_ALIGN - \ BGMAC_RX_FRAME_OFFSET) -/* Jumbo frame size with FCS */ -#define BGMAC_RX_MAX_FRAME_SIZE 9724 +#define BGMAC_RX_MAX_FRAME_SIZE 1536 #define BGMAC_RX_BUF_SIZE (BGMAC_RX_FRAME_OFFSET + BGMAC_RX_MAX_FRAME_SIZE) #define BGMAC_RX_ALLOC_SIZE (SKB_DATA_ALIGN(BGMAC_RX_BUF_SIZE + BGMAC_RX_BUF_OFFSET) + \ SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index 0715ea5bf13e..3b082114f2e5 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -41,9 +41,12 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bcmgenet_priv *priv = netdev_priv(dev); struct device *kdev = &priv->pdev->dev; + u32 phy_wolopts = 0; - if (dev->phydev) + if (dev->phydev) { phy_ethtool_get_wol(dev->phydev, wol); + phy_wolopts = wol->wolopts; + } /* MAC is not wake-up capable, return what the PHY does */ if (!device_can_wakeup(kdev)) @@ -51,9 +54,14 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) /* Overlay MAC capabilities with that of the PHY queried before */ wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; - wol->wolopts = priv->wolopts; - memset(wol->sopass, 0, sizeof(wol->sopass)); + wol->wolopts |= priv->wolopts; + /* Return the PHY configured magic password */ + if (phy_wolopts & WAKE_MAGICSECURE) + return; + + /* Otherwise the MAC one */ + memset(wol->sopass, 0, sizeof(wol->sopass)); if (wol->wolopts & WAKE_MAGICSECURE) memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass)); } @@ -70,7 +78,7 @@ int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) /* Try Wake-on-LAN from the PHY first */ if (dev->phydev) { ret = phy_ethtool_set_wol(dev->phydev, wol); - if (ret != -EOPNOTSUPP) + if (ret != -EOPNOTSUPP && wol->wolopts) return ret; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 9cc8db10a8d6..d9d675f1ebfe 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -55,6 +55,7 @@ #include <linux/hwmon.h> #include <linux/hwmon-sysfs.h> #include <linux/crc32poly.h> +#include <linux/dmi.h> #include <net/checksum.h> #include <net/gso.h> @@ -7424,7 +7425,7 @@ static void tg3_napi_enable(struct tg3 *tp) for (i = 0; i < tp->irq_cnt; i++) { tnapi = &tp->napi[i]; - napi_enable(&tnapi->napi); + napi_enable_locked(&tnapi->napi); if (tnapi->tx_buffers) { netif_queue_set_napi(tp->dev, txq_idx, NETDEV_QUEUE_TYPE_TX, @@ -7445,9 +7446,10 @@ static void tg3_napi_init(struct tg3 *tp) int i; for (i = 0; i < tp->irq_cnt; i++) { - netif_napi_add(tp->dev, &tp->napi[i].napi, - i ? tg3_poll_msix : tg3_poll); - netif_napi_set_irq(&tp->napi[i].napi, tp->napi[i].irq_vec); + netif_napi_add_locked(tp->dev, &tp->napi[i].napi, + i ? tg3_poll_msix : tg3_poll); + netif_napi_set_irq_locked(&tp->napi[i].napi, + tp->napi[i].irq_vec); } } @@ -11259,6 +11261,8 @@ static void tg3_timer_stop(struct tg3 *tp) static int tg3_restart_hw(struct tg3 *tp, bool reset_phy) __releases(tp->lock) __acquires(tp->lock) + __releases(tp->dev->lock) + __acquires(tp->dev->lock) { int err; @@ -11271,7 +11275,9 @@ static int tg3_restart_hw(struct tg3 *tp, bool reset_phy) tg3_timer_stop(tp); tp->irq_sync = 0; tg3_napi_enable(tp); + netdev_unlock(tp->dev); dev_close(tp->dev); + netdev_lock(tp->dev); tg3_full_lock(tp, 0); } return err; @@ -11299,6 +11305,7 @@ static void tg3_reset_task(struct work_struct *work) tg3_netif_stop(tp); + netdev_lock(tp->dev); tg3_full_lock(tp, 1); if (tg3_flag(tp, TX_RECOVERY_PENDING)) { @@ -11318,12 +11325,14 @@ static void tg3_reset_task(struct work_struct *work) * call cancel_work_sync() and wait forever. */ tg3_flag_clear(tp, RESET_TASK_PENDING); + netdev_unlock(tp->dev); dev_close(tp->dev); goto out; } tg3_netif_start(tp); tg3_full_unlock(tp); + netdev_unlock(tp->dev); tg3_phy_start(tp); tg3_flag_clear(tp, RESET_TASK_PENDING); out: @@ -11683,9 +11692,11 @@ static int tg3_start(struct tg3 *tp, bool reset_phy, bool test_irq, if (err) goto out_ints_fini; + netdev_lock(dev); tg3_napi_init(tp); tg3_napi_enable(tp); + netdev_unlock(dev); for (i = 0; i < tp->irq_cnt; i++) { err = tg3_request_irq(tp, i); @@ -12569,6 +12580,7 @@ static int tg3_set_ringparam(struct net_device *dev, irq_sync = 1; } + netdev_lock(dev); tg3_full_lock(tp, irq_sync); tp->rx_pending = ering->rx_pending; @@ -12597,6 +12609,7 @@ static int tg3_set_ringparam(struct net_device *dev, } tg3_full_unlock(tp); + netdev_unlock(dev); if (irq_sync && !err) tg3_phy_start(tp); @@ -12678,6 +12691,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam irq_sync = 1; } + netdev_lock(dev); tg3_full_lock(tp, irq_sync); if (epause->autoneg) @@ -12707,6 +12721,7 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam } tg3_full_unlock(tp); + netdev_unlock(dev); } tp->phy_flags |= TG3_PHYFLG_USER_CONFIGURED; @@ -13911,6 +13926,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest, data[TG3_INTERRUPT_TEST] = 1; } + netdev_lock(dev); tg3_full_lock(tp, 0); tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); @@ -13922,6 +13938,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest, } tg3_full_unlock(tp); + netdev_unlock(dev); if (irq_sync && !err2) tg3_phy_start(tp); @@ -14365,6 +14382,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) tg3_set_mtu(dev, tp, new_mtu); + netdev_lock(dev); tg3_full_lock(tp, 1); tg3_halt(tp, RESET_KIND_SHUTDOWN, 1); @@ -14384,6 +14402,7 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu) tg3_netif_start(tp); tg3_full_unlock(tp); + netdev_unlock(dev); if (!err) tg3_phy_start(tp); @@ -18164,6 +18183,7 @@ static int tg3_resume(struct device *device) netif_device_attach(dev); + netdev_lock(dev); tg3_full_lock(tp, 0); tg3_ape_driver_state_change(tp, RESET_KIND_INIT); @@ -18180,6 +18200,7 @@ static int tg3_resume(struct device *device) out: tg3_full_unlock(tp); + netdev_unlock(dev); if (!err) tg3_phy_start(tp); @@ -18192,6 +18213,50 @@ unlock: static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume); +/* Systems where ACPI _PTS (Prepare To Sleep) S5 will result in a fatal + * PCIe AER event on the tg3 device if the tg3 device is not, or cannot + * be, powered down. + */ +static const struct dmi_system_id tg3_restart_aer_quirk_table[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R440"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R540"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R640"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R650"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R740"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge R750"), + }, + }, + {} +}; + static void tg3_shutdown(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); @@ -18208,6 +18273,19 @@ static void tg3_shutdown(struct pci_dev *pdev) if (system_state == SYSTEM_POWER_OFF) tg3_power_down(tp); + else if (system_state == SYSTEM_RESTART && + dmi_first_match(tg3_restart_aer_quirk_table) && + pdev->current_state != PCI_D3cold && + pdev->current_state != PCI_UNKNOWN) { + /* Disable PCIe AER on the tg3 to avoid a fatal + * error during this system restart. + */ + pcie_capability_clear_word(pdev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_CERE | + PCI_EXP_DEVCTL_NFERE | + PCI_EXP_DEVCTL_FERE | + PCI_EXP_DEVCTL_URRE); + } rtnl_unlock(); @@ -18260,7 +18338,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, done: if (state == pci_channel_io_perm_failure) { if (netdev) { + netdev_lock(netdev); tg3_napi_enable(tp); + netdev_unlock(netdev); dev_close(netdev); } err = PCI_ERS_RESULT_DISCONNECT; @@ -18314,7 +18394,9 @@ static pci_ers_result_t tg3_io_slot_reset(struct pci_dev *pdev) done: if (rc != PCI_ERS_RESULT_RECOVERED && netdev && netif_running(netdev)) { + netdev_lock(netdev); tg3_napi_enable(tp); + netdev_unlock(netdev); dev_close(netdev); } rtnl_unlock(); @@ -18340,12 +18422,14 @@ static void tg3_io_resume(struct pci_dev *pdev) if (!netdev || !netif_running(netdev)) goto done; + netdev_lock(netdev); tg3_full_lock(tp, 0); tg3_ape_driver_state_change(tp, RESET_KIND_INIT); tg3_flag_set(tp, INIT_COMPLETE); err = tg3_restart_hw(tp, true); if (err) { tg3_full_unlock(tp); + netdev_unlock(netdev); netdev_err(netdev, "Cannot restart hardware after reset.\n"); goto done; } @@ -18357,6 +18441,7 @@ static void tg3_io_resume(struct pci_dev *pdev) tg3_netif_start(tp); tg3_full_unlock(tp); + netdev_unlock(netdev); tg3_phy_start(tp); diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 8735e333034c..b87eaf0c250c 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1777,10 +1777,11 @@ static void dm9000_drv_remove(struct platform_device *pdev) unregister_netdev(ndev); dm9000_release_board(pdev, dm); - free_netdev(ndev); /* free device structure */ if (dm->power_supply) regulator_disable(dm->power_supply); + free_netdev(ndev); /* free device structure */ + dev_dbg(&pdev->dev, "released and freed device\n"); } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 68725506a095..f7c4ce8e9a26 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -840,6 +840,8 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq, struct fec_enet_private *fep = netdev_priv(ndev); int hdr_len, total_len, data_left; struct bufdesc *bdp = txq->bd.cur; + struct bufdesc *tmp_bdp; + struct bufdesc_ex *ebdp; struct tso_t tso; unsigned int index = 0; int ret; @@ -913,7 +915,34 @@ static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq, return 0; err_release: - /* TODO: Release all used data descriptors for TSO */ + /* Release all used data descriptors for TSO */ + tmp_bdp = txq->bd.cur; + + while (tmp_bdp != bdp) { + /* Unmap data buffers */ + if (tmp_bdp->cbd_bufaddr && + !IS_TSO_HEADER(txq, fec32_to_cpu(tmp_bdp->cbd_bufaddr))) + dma_unmap_single(&fep->pdev->dev, + fec32_to_cpu(tmp_bdp->cbd_bufaddr), + fec16_to_cpu(tmp_bdp->cbd_datlen), + DMA_TO_DEVICE); + + /* Clear standard buffer descriptor fields */ + tmp_bdp->cbd_sc = 0; + tmp_bdp->cbd_datlen = 0; + tmp_bdp->cbd_bufaddr = 0; + + /* Handle extended descriptor if enabled */ + if (fep->bufdesc_ex) { + ebdp = (struct bufdesc_ex *)tmp_bdp; + ebdp->cbd_esc = 0; + } + + tmp_bdp = fec_enet_get_nextdesc(tmp_bdp, &txq->bd); + } + + dev_kfree_skb_any(skb); + return ret; } diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 8167cc5fb0df..78d2a19593d1 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1116,6 +1116,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv) return gve_xdp_tx_queue_id(priv, 0); } +static inline bool gve_supports_xdp_xmit(struct gve_priv *priv) +{ + switch (priv->queue_format) { + case GVE_GQI_QPL_FORMAT: + return true; + default: + return false; + } +} + /* gqi napi handler defined in gve_main.c */ int gve_napi_poll(struct napi_struct *napi, int budget); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 533e659b15b3..92237fb0b60c 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1903,6 +1903,8 @@ static void gve_turndown(struct gve_priv *priv) /* Stop tx queues */ netif_tx_disable(priv->dev); + xdp_features_clear_redirect_target(priv->dev); + gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); @@ -1972,6 +1974,9 @@ static void gve_turnup(struct gve_priv *priv) napi_schedule(&block->napi); } + if (priv->num_xdp_queues && gve_supports_xdp_xmit(priv)) + xdp_features_set_redirect_target(priv->dev, false); + gve_set_napi_enabled(priv); } @@ -2246,7 +2251,6 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv) if (priv->queue_format == GVE_GQI_QPL_FORMAT) { xdp_features = NETDEV_XDP_ACT_BASIC; xdp_features |= NETDEV_XDP_ACT_REDIRECT; - xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { xdp_features = 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 9a63fbc69408..b25fb400f476 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -40,6 +40,21 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare); */ static DEFINE_MUTEX(hnae3_common_lock); +/* ensure the drivers being unloaded one by one */ +static DEFINE_MUTEX(hnae3_unload_lock); + +void hnae3_acquire_unload_lock(void) +{ + mutex_lock(&hnae3_unload_lock); +} +EXPORT_SYMBOL(hnae3_acquire_unload_lock); + +void hnae3_release_unload_lock(void) +{ + mutex_unlock(&hnae3_unload_lock); +} +EXPORT_SYMBOL(hnae3_release_unload_lock); + static bool hnae3_client_match(enum hnae3_client_type client_type) { if (client_type == HNAE3_CLIENT_KNIC || diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 12ba380eb701..4e44f28288f9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -963,4 +963,6 @@ int hnae3_register_client(struct hnae3_client *client); void hnae3_set_client_init_flag(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev, unsigned int inited); +void hnae3_acquire_unload_lock(void); +void hnae3_release_unload_lock(void); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index a7e3b22f641c..9ff797fb36c4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -6002,9 +6002,11 @@ module_init(hns3_init_module); */ static void __exit hns3_exit_module(void) { + hnae3_acquire_unload_lock(); pci_unregister_driver(&hns3_driver); hnae3_unregister_client(&client); hns3_dbg_unregister_debugfs(); + hnae3_release_unload_lock(); } module_exit(hns3_exit_module); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index db7845009252..3f17b3073e50 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -12919,9 +12919,11 @@ static int __init hclge_init(void) static void __exit hclge_exit(void) { + hnae3_acquire_unload_lock(); hnae3_unregister_ae_algo_prepare(&ae_algo); hnae3_unregister_ae_algo(&ae_algo); destroy_workqueue(hclge_wq); + hnae3_release_unload_lock(); } module_init(hclge_init); module_exit(hclge_exit); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 163c6e59ea4c..9ba767740a04 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3410,8 +3410,10 @@ static int __init hclgevf_init(void) static void __exit hclgevf_exit(void) { + hnae3_acquire_unload_lock(); hnae3_unregister_ae_algo(&ae_algovf); destroy_workqueue(hclgevf_wq); + hnae3_release_unload_lock(); } module_init(hclgevf_init); module_exit(hclgevf_exit); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index e95ae0d39948..0676fc547b6f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2408,6 +2408,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) dma_addr_t data_dma_addr; struct netdev_queue *txq; unsigned long lpar_rc; + unsigned int skblen; union sub_crq tx_crq; unsigned int offset; bool use_scrq_send_direct = false; @@ -2522,6 +2523,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->skb = skb; tx_buff->index = bufidx; tx_buff->pool_index = queue_num; + skblen = skb->len; memset(&tx_crq, 0, sizeof(tx_crq)); tx_crq.v1.first = IBMVNIC_CRQ_CMD; @@ -2614,7 +2616,7 @@ early_exit: netif_stop_subqueue(netdev, queue_num); } - tx_bytes += skb->len; + tx_bytes += skblen; txq_trans_cond_update(txq); ret = NETDEV_TX_OK; goto out; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index cbfaaa5b7d02..852e5b62f0a5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -773,6 +773,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->state = IAVF_VLAN_ADD; adapter->num_vlan_filters++; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); + } else if (f->state == IAVF_VLAN_REMOVE) { + /* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed. + * We can safely only change the state here. + */ + f->state = IAVF_VLAN_ACTIVE; } clearout: @@ -793,8 +798,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->state = IAVF_VLAN_REMOVE; - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); + /* IAVF_ADD_VLAN means that VLAN wasn't even added yet. + * Remove it from the list. + */ + if (f->state == IAVF_VLAN_ADD) { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } else { + f->state = IAVF_VLAN_REMOVE; + iavf_schedule_aq_request(adapter, + IAVF_FLAG_AQ_DEL_VLAN_FILTER); + } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -2888,8 +2903,8 @@ static void iavf_watchdog_task(struct work_struct *work) } mutex_unlock(&adapter->crit_lock); - netdev_unlock(netdev); restart_watchdog: + netdev_unlock(netdev); if (adapter->state >= __IAVF_DOWN) queue_work(adapter->wq, &adapter->adminq_task); if (adapter->aq_required) diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index d116e2b10bce..dbdb83567364 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -981,6 +981,9 @@ static int ice_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv /* preallocate memory for ice_sched_node */ node = devm_kzalloc(ice_hw_to_dev(pi->hw), sizeof(*node), GFP_KERNEL); + if (!node) + return -ENOMEM; + *priv = node; return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 01536a382e54..bdee499f991a 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -1498,7 +1498,6 @@ struct ice_aqc_dnl_equa_param { #define ICE_AQC_RX_EQU_POST1 (0x12 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_BFLF (0x13 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_BFHF (0x14 << ICE_AQC_RX_EQU_SHIFT) -#define ICE_AQC_RX_EQU_DRATE (0x15 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINHF (0x20 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINLF (0x21 << ICE_AQC_RX_EQU_SHIFT) #define ICE_AQC_RX_EQU_CTLE_GAINDC (0x22 << ICE_AQC_RX_EQU_SHIFT) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 3072634bf049..f241493a6ac8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -710,7 +710,6 @@ static int ice_get_tx_rx_equa(struct ice_hw *hw, u8 serdes_num, { ICE_AQC_RX_EQU_POST1, rx, &ptr->rx_equ_post1 }, { ICE_AQC_RX_EQU_BFLF, rx, &ptr->rx_equ_bflf }, { ICE_AQC_RX_EQU_BFHF, rx, &ptr->rx_equ_bfhf }, - { ICE_AQC_RX_EQU_DRATE, rx, &ptr->rx_equ_drate }, { ICE_AQC_RX_EQU_CTLE_GAINHF, rx, &ptr->rx_equ_ctle_gainhf }, { ICE_AQC_RX_EQU_CTLE_GAINLF, rx, &ptr->rx_equ_ctle_gainlf }, { ICE_AQC_RX_EQU_CTLE_GAINDC, rx, &ptr->rx_equ_ctle_gaindc }, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.h b/drivers/net/ethernet/intel/ice/ice_ethtool.h index 8f2ad1c172c0..23b2cfbc9684 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.h +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.h @@ -15,7 +15,6 @@ struct ice_serdes_equalization_to_ethtool { int rx_equ_post1; int rx_equ_bflf; int rx_equ_bfhf; - int rx_equ_drate; int rx_equ_ctle_gainhf; int rx_equ_ctle_gainlf; int rx_equ_ctle_gaindc; diff --git a/drivers/net/ethernet/intel/ice/ice_parser.h b/drivers/net/ethernet/intel/ice/ice_parser.h index 6509d807627c..4f56d53d56b9 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser.h +++ b/drivers/net/ethernet/intel/ice/ice_parser.h @@ -257,7 +257,6 @@ ice_pg_nm_cam_match(struct ice_pg_nm_cam_item *table, int size, /*** ICE_SID_RXPARSER_BOOST_TCAM and ICE_SID_LBL_RXPARSER_TMEM sections ***/ #define ICE_BST_TCAM_TABLE_SIZE 256 #define ICE_BST_TCAM_KEY_SIZE 20 -#define ICE_BST_KEY_TCAM_SIZE 19 /* Boost TCAM item */ struct ice_bst_tcam_item { @@ -401,7 +400,6 @@ u16 ice_xlt_kb_flag_get(struct ice_xlt_kb *kb, u64 pkt_flag); #define ICE_PARSER_GPR_NUM 128 #define ICE_PARSER_FLG_NUM 64 #define ICE_PARSER_ERR_NUM 16 -#define ICE_BST_KEY_SIZE 10 #define ICE_MARKER_ID_SIZE 9 #define ICE_MARKER_MAX_SIZE \ (ICE_MARKER_ID_SIZE * BITS_PER_BYTE - 1) @@ -431,13 +429,13 @@ struct ice_parser_rt { u8 pkt_buf[ICE_PARSER_MAX_PKT_LEN + ICE_PARSER_PKT_REV]; u16 pkt_len; u16 po; - u8 bst_key[ICE_BST_KEY_SIZE]; + u8 bst_key[ICE_BST_TCAM_KEY_SIZE]; struct ice_pg_cam_key pg_key; + u8 pg_prio; struct ice_alu *alu0; struct ice_alu *alu1; struct ice_alu *alu2; struct ice_pg_cam_action *action; - u8 pg_prio; struct ice_gpr_pu pu; u8 markers[ICE_MARKER_ID_SIZE]; bool protocols[ICE_PO_PAIR_SIZE]; diff --git a/drivers/net/ethernet/intel/ice/ice_parser_rt.c b/drivers/net/ethernet/intel/ice/ice_parser_rt.c index dedf5e854e4b..3995d662e050 100644 --- a/drivers/net/ethernet/intel/ice/ice_parser_rt.c +++ b/drivers/net/ethernet/intel/ice/ice_parser_rt.c @@ -125,22 +125,20 @@ static void ice_bst_key_init(struct ice_parser_rt *rt, else key[idd] = imem->b_kb.prio; - idd = ICE_BST_KEY_TCAM_SIZE - 1; + idd = ICE_BST_TCAM_KEY_SIZE - 2; for (i = idd; i >= 0; i--) { int j; j = ho + idd - i; if (j < ICE_PARSER_MAX_PKT_LEN) - key[i] = rt->pkt_buf[ho + idd - i]; + key[i] = rt->pkt_buf[j]; else key[i] = 0; } - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "Generated Boost TCAM Key:\n"); - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "%02X %02X %02X %02X %02X %02X %02X %02X %02X %02X\n", - key[0], key[1], key[2], key[3], key[4], - key[5], key[6], key[7], key[8], key[9]); - ice_debug(rt->psr->hw, ICE_DBG_PARSER, "\n"); + ice_debug_array_w_prefix(rt->psr->hw, ICE_DBG_PARSER, + KBUILD_MODNAME ": Generated Boost TCAM Key", + key, ICE_BST_TCAM_KEY_SIZE); } static u16 ice_bit_rev_u16(u16 v, int len) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 5d2d7736fd5f..9c9ea4c1b93b 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -527,15 +527,14 @@ err: * @xdp: xdp_buff used as input to the XDP program * @xdp_prog: XDP program to run * @xdp_ring: ring to be used for XDP_TX action - * @rx_buf: Rx buffer to store the XDP action * @eop_desc: Last descriptor in packet to read metadata from * * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ -static void +static u32 ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, - struct ice_rx_buf *rx_buf, union ice_32b_rx_flex_desc *eop_desc) + union ice_32b_rx_flex_desc *eop_desc) { unsigned int ret = ICE_XDP_PASS; u32 act; @@ -574,7 +573,7 @@ out_failure: ret = ICE_XDP_CONSUMED; } exit: - ice_set_rx_bufs_act(xdp, rx_ring, ret); + return ret; } /** @@ -860,10 +859,8 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, xdp_buff_set_frags_flag(xdp); } - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) { - ice_set_rx_bufs_act(xdp, rx_ring, ICE_XDP_CONSUMED); + if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) return -ENOMEM; - } __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, rx_buf->page_offset, size); @@ -924,7 +921,6 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, struct ice_rx_buf *rx_buf; rx_buf = &rx_ring->rx_buf[ntc]; - rx_buf->pgcnt = page_count(rx_buf->page); prefetchw(rx_buf->page); if (!size) @@ -941,6 +937,31 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, } /** + * ice_get_pgcnts - grab page_count() for gathered fragments + * @rx_ring: Rx descriptor ring to store the page counts on + * + * This function is intended to be called right before running XDP + * program so that the page recycling mechanism will be able to take + * a correct decision regarding underlying pages; this is done in such + * way as XDP program can change the refcount of page + */ +static void ice_get_pgcnts(struct ice_rx_ring *rx_ring) +{ + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; + struct ice_rx_buf *rx_buf; + u32 cnt = rx_ring->count; + + for (int i = 0; i < nr_frags; i++) { + rx_buf = &rx_ring->rx_buf[idx]; + rx_buf->pgcnt = page_count(rx_buf->page); + + if (++idx == cnt) + idx = 0; + } +} + +/** * ice_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on * @xdp: xdp_buff pointing to the data @@ -1051,12 +1072,12 @@ ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) rx_buf->page_offset + headlen, size, xdp->frame_sz); } else { - /* buffer is unused, change the act that should be taken later - * on; data was copied onto skb's linear part so there's no + /* buffer is unused, restore biased page count in Rx buffer; + * data was copied onto skb's linear part so there's no * need for adjusting page offset and we can reuse this buffer * as-is */ - rx_buf->act = ICE_SKB_CONSUMED; + rx_buf->pagecnt_bias++; } if (unlikely(xdp_buff_has_frags(xdp))) { @@ -1104,6 +1125,65 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) } /** + * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags + * @rx_ring: Rx ring with all the auxiliary data + * @xdp: XDP buffer carrying linear + frags part + * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage + * @ntc: a current next_to_clean value to be stored at rx_ring + * @verdict: return code from XDP program execution + * + * Walk through gathered fragments and satisfy internal page + * recycle mechanism; we take here an action related to verdict + * returned by XDP program; + */ +static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, + u32 *xdp_xmit, u32 ntc, u32 verdict) +{ + u32 nr_frags = rx_ring->nr_frags + 1; + u32 idx = rx_ring->first_desc; + u32 cnt = rx_ring->count; + u32 post_xdp_frags = 1; + struct ice_rx_buf *buf; + int i; + + if (unlikely(xdp_buff_has_frags(xdp))) + post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags; + + for (i = 0; i < post_xdp_frags; i++) { + buf = &rx_ring->rx_buf[idx]; + + if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + *xdp_xmit |= verdict; + } else if (verdict & ICE_XDP_CONSUMED) { + buf->pagecnt_bias++; + } else if (verdict == ICE_XDP_PASS) { + ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); + } + + ice_put_rx_buf(rx_ring, buf); + + if (++idx == cnt) + idx = 0; + } + /* handle buffers that represented frags released by XDP prog; + * for these we keep pagecnt_bias as-is; refcount from struct page + * has been decremented within XDP prog and we do not have to increase + * the biased refcnt + */ + for (; i < nr_frags; i++) { + buf = &rx_ring->rx_buf[idx]; + ice_put_rx_buf(rx_ring, buf); + if (++idx == cnt) + idx = 0; + } + + xdp->data = NULL; + rx_ring->first_desc = ntc; + rx_ring->nr_frags = 0; +} + +/** * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: Rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1120,15 +1200,13 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; - u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; + u32 cached_ntu, xdp_verdict; u32 cnt = rx_ring->count; u32 xdp_xmit = 0; - u32 cached_ntu; bool failure; - u32 first; xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { @@ -1190,6 +1268,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); xdp_buff_clear_frags_flag(xdp); } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { + ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED); break; } if (++ntc == cnt) @@ -1199,15 +1278,15 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) if (ice_is_non_eop(rx_ring, rx_desc)) continue; - ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_buf, rx_desc); - if (rx_buf->act == ICE_XDP_PASS) + ice_get_pgcnts(rx_ring); + xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc); + if (xdp_verdict == ICE_XDP_PASS) goto construct_skb; total_rx_bytes += xdp_get_buff_len(xdp); total_rx_pkts++; - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + continue; construct_skb: if (likely(ice_ring_uses_build_skb(rx_ring))) @@ -1217,18 +1296,12 @@ construct_skb: /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->ring_stats->rx_stats.alloc_page_failed++; - rx_buf->act = ICE_XDP_CONSUMED; - if (unlikely(xdp_buff_has_frags(xdp))) - ice_set_rx_bufs_act(xdp, rx_ring, - ICE_XDP_CONSUMED); - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; - break; + xdp_verdict = ICE_XDP_CONSUMED; } - xdp->data = NULL; - rx_ring->first_desc = ntc; - rx_ring->nr_frags = 0; + ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict); + + if (!skb) + break; stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, @@ -1257,23 +1330,6 @@ construct_skb: total_rx_pkts++; } - first = rx_ring->first_desc; - while (cached_ntc != first) { - struct ice_rx_buf *buf = &rx_ring->rx_buf[cached_ntc]; - - if (buf->act & (ICE_XDP_TX | ICE_XDP_REDIR)) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - xdp_xmit |= buf->act; - } else if (buf->act & ICE_XDP_CONSUMED) { - buf->pagecnt_bias++; - } else if (buf->act == ICE_XDP_PASS) { - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - } - - ice_put_rx_buf(rx_ring, buf); - if (++cached_ntc >= cnt) - cached_ntc = 0; - } rx_ring->next_to_clean = ntc; /* return up to cleaned_count buffers to hardware */ failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index cb347c852ba9..806bce701df3 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -201,7 +201,6 @@ struct ice_rx_buf { struct page *page; unsigned int page_offset; unsigned int pgcnt; - unsigned int act; unsigned int pagecnt_bias; }; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 79f960c6680d..6cf32b404127 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -6,49 +6,6 @@ #include "ice.h" /** - * ice_set_rx_bufs_act - propagate Rx buffer action to frags - * @xdp: XDP buffer representing frame (linear and frags part) - * @rx_ring: Rx ring struct - * act: action to store onto Rx buffers related to XDP buffer parts - * - * Set action that should be taken before putting Rx buffer from first frag - * to the last. - */ -static inline void -ice_set_rx_bufs_act(struct xdp_buff *xdp, const struct ice_rx_ring *rx_ring, - const unsigned int act) -{ - u32 sinfo_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; - u32 nr_frags = rx_ring->nr_frags + 1; - u32 idx = rx_ring->first_desc; - u32 cnt = rx_ring->count; - struct ice_rx_buf *buf; - - for (int i = 0; i < nr_frags; i++) { - buf = &rx_ring->rx_buf[idx]; - buf->act = act; - - if (++idx == cnt) - idx = 0; - } - - /* adjust pagecnt_bias on frags freed by XDP prog */ - if (sinfo_frags < rx_ring->nr_frags && act == ICE_XDP_CONSUMED) { - u32 delta = rx_ring->nr_frags - sinfo_frags; - - while (delta) { - if (idx == 0) - idx = cnt - 1; - else - idx--; - buf = &rx_ring->rx_buf[idx]; - buf->pagecnt_bias--; - delta--; - } - } -} - -/** * ice_test_staterr - tests bits in Rx descriptor status and error fields * @status_err_n: Rx descriptor status_error0 or status_error1 bits * @stat_err_bits: value to mask diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c index 4849590a5591..b28991dd1870 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c +++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c @@ -376,6 +376,9 @@ int idpf_ctlq_clean_sq(struct idpf_ctlq_info *cq, u16 *clean_count, if (!(le16_to_cpu(desc->flags) & IDPF_CTLQ_FLAG_DD)) break; + /* Ensure no other fields are read until DD flag is checked */ + dma_rmb(); + /* strip off FW internal code */ desc_err = le16_to_cpu(desc->ret_val) & 0xff; @@ -563,6 +566,9 @@ int idpf_ctlq_recv(struct idpf_ctlq_info *cq, u16 *num_q_msg, if (!(flags & IDPF_CTLQ_FLAG_DD)) break; + /* Ensure no other fields are read until DD flag is checked */ + dma_rmb(); + q_msg[i].vmvf_type = (flags & (IDPF_CTLQ_FLAG_FTYPE_VM | IDPF_CTLQ_FLAG_FTYPE_PF)) >> diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index b4fbb99bfad2..a3d6b8f198a8 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -2159,8 +2159,13 @@ static int idpf_open(struct net_device *netdev) idpf_vport_ctrl_lock(netdev); vport = idpf_netdev_to_vport(netdev); + err = idpf_set_real_num_queues(vport); + if (err) + goto unlock; + err = idpf_vport_open(vport); +unlock: idpf_vport_ctrl_unlock(netdev); return err; diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index f71d3182580b..b6c515d14cbf 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -174,7 +174,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); pci_set_drvdata(pdev, adapter); - adapter->init_wq = alloc_workqueue("%s-%s-init", 0, 0, + adapter->init_wq = alloc_workqueue("%s-%s-init", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->init_wq) { @@ -183,7 +184,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_free; } - adapter->serv_wq = alloc_workqueue("%s-%s-service", 0, 0, + adapter->serv_wq = alloc_workqueue("%s-%s-service", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->serv_wq) { @@ -192,7 +194,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_serv_wq_alloc; } - adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", 0, 0, + adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->mbx_wq) { @@ -201,7 +204,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_mbx_wq_alloc; } - adapter->stats_wq = alloc_workqueue("%s-%s-stats", 0, 0, + adapter->stats_wq = alloc_workqueue("%s-%s-stats", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->stats_wq) { @@ -210,7 +214,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_stats_wq_alloc; } - adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", 0, 0, + adapter->vc_event_wq = alloc_workqueue("%s-%s-vc_event", + WQ_UNBOUND | WQ_MEM_RECLAIM, 0, dev_driver_string(dev), dev_name(dev)); if (!adapter->vc_event_wq) { diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 2fa9c36e33c9..9be6a6b59c4e 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -3008,8 +3008,6 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb, return -EINVAL; rsc_segments = DIV_ROUND_UP(skb->data_len, rsc_seg_len); - if (unlikely(rsc_segments == 1)) - return 0; NAPI_GRO_CB(skb)->count = rsc_segments; skb_shinfo(skb)->gso_size = rsc_seg_len; @@ -3072,6 +3070,7 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb, idpf_rx_hash(rxq, skb, rx_desc, decoded); skb->protocol = eth_type_trans(skb, rxq->netdev); + skb_record_rx_queue(skb, rxq->idx); if (le16_get_bits(rx_desc->hdrlen_flags, VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M)) @@ -3080,8 +3079,6 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb, csum_bits = idpf_rx_splitq_extract_csum_bits(rx_desc); idpf_rx_csum(rxq, skb, csum_bits, decoded); - skb_record_rx_queue(skb, rxq->idx); - return 0; } diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index d46c95f91b0d..3d2413b8684f 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -517,8 +517,10 @@ static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter, retval = -ENXIO; goto only_unlock; case IDPF_VC_XN_WAITING: - dev_notice_ratelimited(&adapter->pdev->dev, "Transaction timed-out (op %d, %dms)\n", - params->vc_op, params->timeout_ms); + dev_notice_ratelimited(&adapter->pdev->dev, + "Transaction timed-out (op:%d cookie:%04x vc_op:%d salt:%02x timeout:%dms)\n", + params->vc_op, cookie, xn->vc_op, + xn->salt, params->timeout_ms); retval = -ETIME; break; case IDPF_VC_XN_COMPLETED_SUCCESS: @@ -612,14 +614,16 @@ idpf_vc_xn_forward_reply(struct idpf_adapter *adapter, return -EINVAL; } xn = &adapter->vcxn_mngr->ring[xn_idx]; + idpf_vc_xn_lock(xn); salt = FIELD_GET(IDPF_VC_XN_SALT_M, msg_info); if (xn->salt != salt) { - dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (%02x != %02x)\n", - xn->salt, salt); + dev_err_ratelimited(&adapter->pdev->dev, "Transaction salt does not match (exp:%d@%02x(%d) != got:%d@%02x)\n", + xn->vc_op, xn->salt, xn->state, + ctlq_msg->cookie.mbx.chnl_opcode, salt); + idpf_vc_xn_unlock(xn); return -EINVAL; } - idpf_vc_xn_lock(xn); switch (xn->state) { case IDPF_VC_XN_WAITING: /* success */ @@ -3077,12 +3081,21 @@ init_failed: */ void idpf_vc_core_deinit(struct idpf_adapter *adapter) { + bool remove_in_prog; + if (!test_bit(IDPF_VC_CORE_INIT, adapter->flags)) return; + /* Avoid transaction timeouts when called during reset */ + remove_in_prog = test_bit(IDPF_REMOVE_IN_PROG, adapter->flags); + if (!remove_in_prog) + idpf_vc_xn_shutdown(adapter->vcxn_mngr); + idpf_deinit_task(adapter); idpf_intr_rel(adapter); - idpf_vc_xn_shutdown(adapter->vcxn_mngr); + + if (remove_in_prog) + idpf_vc_xn_shutdown(adapter->vcxn_mngr); cancel_delayed_work_sync(&adapter->serv_task); cancel_delayed_work_sync(&adapter->mbx_task); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 56a35d58e7a6..84307bb7313e 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1096,6 +1096,7 @@ static int igc_init_empty_frame(struct igc_ring *ring, return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_SKB; buffer->skb = skb; buffer->protocol = 0; buffer->bytecount = skb->len; @@ -2701,8 +2702,9 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) } static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, - struct xdp_buff *xdp) + struct igc_xdp_buff *ctx) { + struct xdp_buff *xdp = &ctx->xdp; unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; @@ -2721,27 +2723,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, __skb_pull(skb, metasize); } + if (ctx->rx_ts) { + skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV; + skb_hwtstamps(skb)->netdev_data = ctx->rx_ts; + } + return skb; } static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector, union igc_adv_rx_desc *desc, - struct xdp_buff *xdp, - ktime_t timestamp) + struct igc_xdp_buff *ctx) { struct igc_ring *ring = q_vector->rx.ring; struct sk_buff *skb; - skb = igc_construct_skb_zc(ring, xdp); + skb = igc_construct_skb_zc(ring, ctx); if (!skb) { ring->rx_stats.alloc_failed++; set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags); return; } - if (timestamp) - skb_hwtstamps(skb)->hwtstamp = timestamp; - if (igc_cleanup_headers(ring, desc, skb)) return; @@ -2777,7 +2780,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) union igc_adv_rx_desc *desc; struct igc_rx_buffer *bi; struct igc_xdp_buff *ctx; - ktime_t timestamp = 0; unsigned int size; int res; @@ -2807,6 +2809,8 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) */ bi->xdp->data_meta += IGC_TS_HDR_LEN; size -= IGC_TS_HDR_LEN; + } else { + ctx->rx_ts = NULL; } bi->xdp->data_end = bi->xdp->data + size; @@ -2815,7 +2819,7 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) res = __igc_xdp_run_prog(adapter, prog, bi->xdp); switch (res) { case IGC_XDP_PASS: - igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp); + igc_dispatch_skb_zc(q_vector, desc, ctx); fallthrough; case IGC_XDP_CONSUMED: xsk_buff_free(bi->xdp); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 7236f20c9a30..467f81239e12 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2105,7 +2105,7 @@ static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, /* hand second half of page back to the ring */ ixgbe_reuse_rx_page(rx_ring, rx_buffer); } else { - if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) { + if (skb && IXGBE_CB(skb)->dma == rx_buffer->dma) { /* the page has been released from the ring */ IXGBE_CB(skb)->page_released = true; } else { diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 82f4333fb426..4fe121b9f94b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4432,6 +4432,7 @@ static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node) */ if (pp->is_stopped) { spin_unlock(&pp->lock); + netdev_unlock(port->napi.dev); return 0; } netif_tx_stop_all_queues(pp->dev); diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c index 415d784de741..09f448f29124 100644 --- a/drivers/net/ethernet/mediatek/airoha_eth.c +++ b/drivers/net/ethernet/mediatek/airoha_eth.c @@ -266,11 +266,11 @@ #define REG_GDM3_FWD_CFG GDM3_BASE #define GDM3_PAD_EN_MASK BIT(28) -#define REG_GDM4_FWD_CFG (GDM4_BASE + 0x100) +#define REG_GDM4_FWD_CFG GDM4_BASE #define GDM4_PAD_EN_MASK BIT(28) #define GDM4_SPORT_OFFSET0_MASK GENMASK(11, 8) -#define REG_GDM4_SRC_PORT_SET (GDM4_BASE + 0x33c) +#define REG_GDM4_SRC_PORT_SET (GDM4_BASE + 0x23c) #define GDM4_SPORT_OFF2_MASK GENMASK(19, 16) #define GDM4_SPORT_OFF1_MASK GENMASK(15, 12) #define GDM4_SPORT_OFF0_MASK GENMASK(11, 8) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bd41b75d246e..a814b63ed97e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2087,7 +2087,7 @@ static struct mlx5e_xdpsq *mlx5e_open_xdpredirect_sq(struct mlx5e_channel *c, struct mlx5e_xdpsq *xdpsq; int err; - xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, c->cpu); + xdpsq = kvzalloc_node(sizeof(*xdpsq), GFP_KERNEL, cpu_to_node(c->cpu)); if (!xdpsq) return ERR_PTR(-ENOMEM); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 2bed8c86b7cf..3f64cdbabfa3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -768,7 +768,9 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev, err = mlxsw_sp_get_hw_stats_by_group(&hw_stats, &len, grp); if (err) return; - mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl); + err = mlxsw_sp_port_get_stats_raw(dev, grp, prio, ppcnt_pl); + if (err) + return; for (i = 0; i < len; i++) { data[data_index + i] = hw_stats[i].getter(ppcnt_pl); if (!hw_stats[i].cells_bytes) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index 2ec62c8d86e1..59486fe2ad18 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -20,6 +20,8 @@ nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size) struct sk_buff *skb; skb = nfp_app_ctrl_msg_alloc(bpf->app, size, GFP_KERNEL); + if (!skb) + return NULL; skb_put(skb, size); return skb; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 720f577929db..499e5e39d513 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -1120,20 +1120,6 @@ static void nv_disable_hw_interrupts(struct net_device *dev, u32 mask) } } -static void nv_napi_enable(struct net_device *dev) -{ - struct fe_priv *np = get_nvpriv(dev); - - napi_enable(&np->napi); -} - -static void nv_napi_disable(struct net_device *dev) -{ - struct fe_priv *np = get_nvpriv(dev); - - napi_disable(&np->napi); -} - #define MII_READ (-1) /* mii_rw: read/write a register on the PHY. * @@ -3114,7 +3100,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu) * Changing the MTU is a rare event, it shouldn't matter. */ nv_disable_irq(dev); - nv_napi_disable(dev); + napi_disable(&np->napi); netif_tx_lock_bh(dev); netif_addr_lock(dev); spin_lock(&np->lock); @@ -3143,7 +3129,7 @@ static int nv_change_mtu(struct net_device *dev, int new_mtu) spin_unlock(&np->lock); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); - nv_napi_enable(dev); + napi_enable(&np->napi); nv_enable_irq(dev); } return 0; @@ -4731,7 +4717,7 @@ static int nv_set_ringparam(struct net_device *dev, if (netif_running(dev)) { nv_disable_irq(dev); - nv_napi_disable(dev); + napi_disable(&np->napi); netif_tx_lock_bh(dev); netif_addr_lock(dev); spin_lock(&np->lock); @@ -4784,7 +4770,7 @@ static int nv_set_ringparam(struct net_device *dev, spin_unlock(&np->lock); netif_addr_unlock(dev); netif_tx_unlock_bh(dev); - nv_napi_enable(dev); + napi_enable(&np->napi); nv_enable_irq(dev); } return 0; @@ -5277,7 +5263,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64 if (test->flags & ETH_TEST_FL_OFFLINE) { if (netif_running(dev)) { netif_stop_queue(dev); - nv_napi_disable(dev); + napi_disable(&np->napi); netif_tx_lock_bh(dev); netif_addr_lock(dev); spin_lock_irq(&np->lock); @@ -5334,7 +5320,7 @@ static void nv_self_test(struct net_device *dev, struct ethtool_test *test, u64 /* restart rx engine */ nv_start_rxtx(dev); netif_start_queue(dev); - nv_napi_enable(dev); + napi_enable(&np->napi); nv_enable_hw_interrupts(dev, np->irqmask); } } @@ -5576,6 +5562,7 @@ static int nv_open(struct net_device *dev) /* ask for interrupts */ nv_enable_hw_interrupts(dev, np->irqmask); + netdev_lock(dev); spin_lock_irq(&np->lock); writel(NVREG_MCASTADDRA_FORCE, base + NvRegMulticastAddrA); writel(0, base + NvRegMulticastAddrB); @@ -5594,7 +5581,7 @@ static int nv_open(struct net_device *dev) ret = nv_update_linkspeed(dev); nv_start_rxtx(dev); netif_start_queue(dev); - nv_napi_enable(dev); + napi_enable_locked(&np->napi); if (ret) { netif_carrier_on(dev); @@ -5611,6 +5598,7 @@ static int nv_open(struct net_device *dev) round_jiffies(jiffies + STATS_INTERVAL)); spin_unlock_irq(&np->lock); + netdev_unlock(dev); /* If the loopback feature was set while the device was down, make sure * that it's set correctly now. @@ -5632,7 +5620,7 @@ static int nv_close(struct net_device *dev) spin_lock_irq(&np->lock); np->in_shutdown = 1; spin_unlock_irq(&np->lock); - nv_napi_disable(dev); + napi_disable(&np->napi); synchronize_irq(np->pci_dev->irq); del_timer_sync(&np->oom_kick); diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index 9ce0e8a64ba8..a73dcaffa8c5 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -1684,6 +1684,7 @@ static void rtl8139_tx_timeout_task (struct work_struct *work) if (tmp8 & CmdTxEnb) RTL_W8 (ChipCmd, CmdRxEnb); + netdev_lock(dev); spin_lock_bh(&tp->rx_lock); /* Disable interrupts by clearing the interrupt mask. */ RTL_W16 (IntrMask, 0x0000); @@ -1694,11 +1695,12 @@ static void rtl8139_tx_timeout_task (struct work_struct *work) spin_unlock_irq(&tp->lock); /* ...and finally, reset everything */ - napi_enable(&tp->napi); + napi_enable_locked(&tp->napi); rtl8139_hw_start(dev); netif_wake_queue(dev); spin_unlock_bh(&tp->rx_lock); + netdev_unlock(dev); } static void rtl8139_tx_timeout(struct net_device *dev, unsigned int txqueue) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index bc395294a32d..c9f4976a3527 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -3217,10 +3217,15 @@ static int ravb_suspend(struct device *dev) netif_device_detach(ndev); - if (priv->wol_enabled) - return ravb_wol_setup(ndev); + rtnl_lock(); + if (priv->wol_enabled) { + ret = ravb_wol_setup(ndev); + rtnl_unlock(); + return ret; + } ret = ravb_close(ndev); + rtnl_unlock(); if (ret) return ret; @@ -3245,19 +3250,20 @@ static int ravb_resume(struct device *dev) if (!netif_running(ndev)) return 0; + rtnl_lock(); /* If WoL is enabled restore the interface. */ - if (priv->wol_enabled) { + if (priv->wol_enabled) ret = ravb_wol_restore(ndev); - if (ret) - return ret; - } else { + else ret = pm_runtime_force_resume(dev); - if (ret) - return ret; + if (ret) { + rtnl_unlock(); + return ret; } /* Reopening the interface will restore the device to the working state. */ ret = ravb_open(ndev); + rtnl_unlock(); if (ret < 0) goto out_rpm_put; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 8887b8921009..5fc8027c92c7 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -3494,10 +3494,12 @@ static int sh_eth_suspend(struct device *dev) netif_device_detach(ndev); + rtnl_lock(); if (mdp->wol_enabled) ret = sh_eth_wol_setup(ndev); else ret = sh_eth_close(ndev); + rtnl_unlock(); return ret; } @@ -3511,10 +3513,12 @@ static int sh_eth_resume(struct device *dev) if (!netif_running(ndev)) return 0; + rtnl_lock(); if (mdp->wol_enabled) ret = sh_eth_wol_restore(ndev); else ret = sh_eth_open(ndev); + rtnl_unlock(); if (ret < 0) return ret; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5212dc439b1d..c0ae7db96f46 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2094,6 +2094,11 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv, pp_params.offset = stmmac_rx_offset(priv); pp_params.max_len = dma_conf->dma_buf_sz; + if (priv->sph) { + pp_params.offset = 0; + pp_params.max_len += stmmac_rx_offset(priv); + } + rx_q->page_pool = page_pool_create(&pp_params); if (IS_ERR(rx_q->page_pool)) { ret = PTR_ERR(rx_q->page_pool); @@ -7217,6 +7222,36 @@ static int stmmac_hw_init(struct stmmac_priv *priv) if (priv->dma_cap.tsoen) dev_info(priv->device, "TSO supported\n"); + if (priv->dma_cap.number_rx_queues && + priv->plat->rx_queues_to_use > priv->dma_cap.number_rx_queues) { + dev_warn(priv->device, + "Number of Rx queues (%u) exceeds dma capability\n", + priv->plat->rx_queues_to_use); + priv->plat->rx_queues_to_use = priv->dma_cap.number_rx_queues; + } + if (priv->dma_cap.number_tx_queues && + priv->plat->tx_queues_to_use > priv->dma_cap.number_tx_queues) { + dev_warn(priv->device, + "Number of Tx queues (%u) exceeds dma capability\n", + priv->plat->tx_queues_to_use); + priv->plat->tx_queues_to_use = priv->dma_cap.number_tx_queues; + } + + if (priv->dma_cap.rx_fifo_size && + priv->plat->rx_fifo_size > priv->dma_cap.rx_fifo_size) { + dev_warn(priv->device, + "Rx FIFO size (%u) exceeds dma capability\n", + priv->plat->rx_fifo_size); + priv->plat->rx_fifo_size = priv->dma_cap.rx_fifo_size; + } + if (priv->dma_cap.tx_fifo_size && + priv->plat->tx_fifo_size > priv->dma_cap.tx_fifo_size) { + dev_warn(priv->device, + "Tx FIFO size (%u) exceeds dma capability\n", + priv->plat->tx_fifo_size); + priv->plat->tx_fifo_size = priv->dma_cap.tx_fifo_size; + } + priv->hw->vlan_fail_q_en = (priv->plat->flags & STMMAC_FLAG_VLAN_FAIL_Q_EN); priv->hw->vlan_fail_q = priv->plat->vlan_fail_q; diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index d7459866d24c..72177fea1cfb 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6086,7 +6086,7 @@ static void niu_enable_napi(struct niu *np) int i; for (i = 0; i < np->num_ldg; i++) - napi_enable(&np->ldg[i].napi); + napi_enable_locked(&np->ldg[i].napi); } static void niu_disable_napi(struct niu *np) @@ -6116,7 +6116,9 @@ static int niu_open(struct net_device *dev) if (err) goto out_free_channels; + netdev_lock(dev); niu_enable_napi(np); + netdev_unlock(dev); spin_lock_irq(&np->lock); @@ -6521,6 +6523,7 @@ static void niu_reset_task(struct work_struct *work) niu_reset_buffers(np); + netdev_lock(np->dev); spin_lock_irqsave(&np->lock, flags); err = niu_init_hw(np); @@ -6531,6 +6534,7 @@ static void niu_reset_task(struct work_struct *work) } spin_unlock_irqrestore(&np->lock, flags); + netdev_unlock(np->dev); } static void niu_tx_timeout(struct net_device *dev, unsigned int txqueue) @@ -6761,7 +6765,9 @@ static int niu_change_mtu(struct net_device *dev, int new_mtu) niu_free_channels(np); + netdev_lock(dev); niu_enable_napi(np); + netdev_unlock(dev); err = niu_alloc_channels(np); if (err) @@ -9937,6 +9943,7 @@ static int __maybe_unused niu_resume(struct device *dev_d) spin_lock_irqsave(&np->lock, flags); + netdev_lock(dev); err = niu_init_hw(np); if (!err) { np->timer.expires = jiffies + HZ; @@ -9945,6 +9952,7 @@ static int __maybe_unused niu_resume(struct device *dev_d) } spin_unlock_irqrestore(&np->lock, flags); + netdev_unlock(dev); return err; } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index b663271e79f7..2806238629f8 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -828,21 +828,30 @@ static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn, static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma) { struct am65_cpsw_tx_chn *tx_chn = data; + enum am65_cpsw_tx_buf_type buf_type; struct cppi5_host_desc_t *desc_tx; + struct xdp_frame *xdpf; struct sk_buff *skb; void **swdata; desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma); swdata = cppi5_hdesc_get_swdata(desc_tx); - skb = *(swdata); - am65_cpsw_nuss_xmit_free(tx_chn, desc_tx); + buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma); + if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) { + skb = *(swdata); + dev_kfree_skb_any(skb); + } else { + xdpf = *(swdata); + xdp_return_frame(xdpf); + } - dev_kfree_skb_any(skb); + am65_cpsw_nuss_xmit_free(tx_chn, desc_tx); } static struct sk_buff *am65_cpsw_build_skb(void *page_addr, struct net_device *ndev, - unsigned int len) + unsigned int len, + unsigned int headroom) { struct sk_buff *skb; @@ -852,7 +861,7 @@ static struct sk_buff *am65_cpsw_build_skb(void *page_addr, if (unlikely(!skb)) return NULL; - skb_reserve(skb, AM65_CPSW_HEADROOM); + skb_reserve(skb, headroom); skb->dev = ndev; return skb; @@ -1169,9 +1178,11 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow, struct xdp_frame *xdpf; struct bpf_prog *prog; struct page *page; + int pkt_len; u32 act; int err; + pkt_len = *len; prog = READ_ONCE(port->xdp_prog); if (!prog) return AM65_CPSW_XDP_PASS; @@ -1189,8 +1200,10 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow, netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) + if (unlikely(!xdpf)) { + ndev->stats.tx_dropped++; goto drop; + } __netif_tx_lock(netif_txq, cpu); err = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf, @@ -1199,14 +1212,14 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow, if (err) goto drop; - dev_sw_netstats_tx_add(ndev, 1, *len); + dev_sw_netstats_rx_add(ndev, pkt_len); ret = AM65_CPSW_XDP_CONSUMED; goto out; case XDP_REDIRECT: if (unlikely(xdp_do_redirect(ndev, xdp, prog))) goto drop; - dev_sw_netstats_rx_add(ndev, *len); + dev_sw_netstats_rx_add(ndev, pkt_len); ret = AM65_CPSW_XDP_REDIRECT; goto out; default: @@ -1315,16 +1328,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, dev_dbg(dev, "%s rx csum_info:%#x\n", __func__, csum_info); dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - skb = am65_cpsw_build_skb(page_addr, ndev, - AM65_CPSW_MAX_PACKET_SIZE); - if (unlikely(!skb)) { - new_page = page; - goto requeue; - } - if (port->xdp_prog) { xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]); xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM, @@ -1334,9 +1339,16 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow, if (*xdp_state != AM65_CPSW_XDP_PASS) goto allocate; - /* Compute additional headroom to be reserved */ - headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb); - skb_reserve(skb, headroom); + headroom = xdp.data - xdp.data_hard_start; + } else { + headroom = AM65_CPSW_HEADROOM; + } + + skb = am65_cpsw_build_skb(page_addr, ndev, + AM65_CPSW_MAX_PACKET_SIZE, headroom); + if (unlikely(!skb)) { + new_page = page; + goto requeue; } ndev_priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 894911f3d560..e56ebbdd428d 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -1568,7 +1568,7 @@ static void init_registers(struct net_device *dev) if (rp->quirks & rqMgmt) rhine_init_cam_filter(dev); - napi_enable(&rp->napi); + napi_enable_locked(&rp->napi); iowrite16(RHINE_EVENT & 0xffff, ioaddr + IntrEnable); @@ -1696,7 +1696,10 @@ static int rhine_open(struct net_device *dev) rhine_power_init(dev); rhine_chip_reset(dev); rhine_task_enable(rp); + + netdev_lock(dev); init_registers(dev); + netdev_unlock(dev); netif_dbg(rp, ifup, dev, "%s() Done - status %04x MII status: %04x\n", __func__, ioread16(ioaddr + ChipCmd), @@ -1727,6 +1730,8 @@ static void rhine_reset_task(struct work_struct *work) napi_disable(&rp->napi); netif_tx_disable(dev); + + netdev_lock(dev); spin_lock_bh(&rp->lock); /* clear all descriptors */ @@ -1740,6 +1745,7 @@ static void rhine_reset_task(struct work_struct *work) init_registers(dev); spin_unlock_bh(&rp->lock); + netdev_unlock(dev); netif_trans_update(dev); /* prevent tx timeout */ dev->stats.tx_errors++; @@ -2541,9 +2547,12 @@ static int rhine_resume(struct device *device) alloc_tbufs(dev); rhine_reset_rbufs(rp); rhine_task_enable(rp); + + netdev_lock(dev); spin_lock_bh(&rp->lock); init_registers(dev); spin_unlock_bh(&rp->lock); + netdev_unlock(dev); netif_device_attach(dev); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 9e7fa012e4fa..f33178f90c42 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2897,6 +2897,7 @@ static int axienet_probe(struct platform_device *pdev) lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; + lp->phylink_config.mac_managed_pm = true; lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 642155cb8315..dbb3960126ee 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1902,21 +1902,9 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; - struct net_device *dev, *aux; - /* gather any geneve devices that were moved into this ns */ - for_each_netdev_safe(net, dev, aux) - if (dev->rtnl_link_ops == &geneve_link_ops) - unregister_netdevice_queue(dev, head); - - /* now gather any other geneve devices that were created in this ns */ - list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { - /* If geneve->dev is in the same netns, it was already added - * to the list by the previous loop. - */ - if (!net_eq(dev_net(geneve->dev), net)) - unregister_netdevice_queue(geneve->dev, head); - } + list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) + geneve_dellink(geneve->dev, head); } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index d64740bf44ed..b7b46c5e6399 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -2481,11 +2481,6 @@ static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list, list_for_each_entry(net, net_list, exit_list) { struct gtp_net *gn = net_generic(net, gtp_net_id); struct gtp_dev *gtp, *gtp_next; - struct net_device *dev; - - for_each_netdev(net, dev) - if (dev->rtnl_link_ops == >p_link_ops) - gtp_dellink(dev, dev_to_kill); list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list) gtp_dellink(gtp->dev, dev_to_kill); diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 3b23f3d3ca2b..5c80fbee7913 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -74,7 +74,7 @@ static void nsim_get_ringparam(struct net_device *dev, memcpy(ring, &ns->ethtool.ring, sizeof(ns->ethtool.ring)); kernel_ring->hds_thresh_max = NSIM_HDS_THRESHOLD_MAX; - if (kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) + if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) kernel_ring->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_ENABLED; } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index dcf073bc4802..96d54c08043d 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -134,6 +134,7 @@ struct netdevsim { u32 sleep; u32 __ports[2][NSIM_UDP_TUNNEL_N_PORTS]; u32 (*ports)[NSIM_UDP_TUNNEL_N_PORTS]; + struct dentry *ddir; struct debugfs_u32_array dfs_ports[2]; } udp_ports; diff --git a/drivers/net/netdevsim/udp_tunnels.c b/drivers/net/netdevsim/udp_tunnels.c index 02dc3123eb6c..640b4983a9a0 100644 --- a/drivers/net/netdevsim/udp_tunnels.c +++ b/drivers/net/netdevsim/udp_tunnels.c @@ -112,9 +112,11 @@ nsim_udp_tunnels_info_reset_write(struct file *file, const char __user *data, struct net_device *dev = file->private_data; struct netdevsim *ns = netdev_priv(dev); - memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports)); rtnl_lock(); - udp_tunnel_nic_reset_ntf(dev); + if (dev->reg_state == NETREG_REGISTERED) { + memset(ns->udp_ports.ports, 0, sizeof(ns->udp_ports.__ports)); + udp_tunnel_nic_reset_ntf(dev); + } rtnl_unlock(); return count; @@ -144,23 +146,23 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, else ns->udp_ports.ports = nsim_dev->udp_ports.__ports; - debugfs_create_u32("udp_ports_inject_error", 0600, - ns->nsim_dev_port->ddir, + ns->udp_ports.ddir = debugfs_create_dir("udp_ports", + ns->nsim_dev_port->ddir); + + debugfs_create_u32("inject_error", 0600, ns->udp_ports.ddir, &ns->udp_ports.inject_error); ns->udp_ports.dfs_ports[0].array = ns->udp_ports.ports[0]; ns->udp_ports.dfs_ports[0].n_elements = NSIM_UDP_TUNNEL_N_PORTS; - debugfs_create_u32_array("udp_ports_table0", 0400, - ns->nsim_dev_port->ddir, + debugfs_create_u32_array("table0", 0400, ns->udp_ports.ddir, &ns->udp_ports.dfs_ports[0]); ns->udp_ports.dfs_ports[1].array = ns->udp_ports.ports[1]; ns->udp_ports.dfs_ports[1].n_elements = NSIM_UDP_TUNNEL_N_PORTS; - debugfs_create_u32_array("udp_ports_table1", 0400, - ns->nsim_dev_port->ddir, + debugfs_create_u32_array("table1", 0400, ns->udp_ports.ddir, &ns->udp_ports.dfs_ports[1]); - debugfs_create_file("udp_ports_reset", 0200, ns->nsim_dev_port->ddir, + debugfs_create_file("reset", 0200, ns->udp_ports.ddir, dev, &nsim_udp_tunnels_info_reset_fops); /* Note: it's not normal to allocate the info struct like this! @@ -196,6 +198,9 @@ int nsim_udp_tunnels_info_create(struct nsim_dev *nsim_dev, void nsim_udp_tunnels_info_destroy(struct net_device *dev) { + struct netdevsim *ns = netdev_priv(dev); + + debugfs_remove_recursive(ns->udp_ports.ddir); kfree(dev->udp_tunnel_nic_info); dev->udp_tunnel_nic_info = NULL; } diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c index 4494b3e39ce2..a3996471a1c9 100644 --- a/drivers/net/phy/marvell-88q2xxx.c +++ b/drivers/net/phy/marvell-88q2xxx.c @@ -95,6 +95,10 @@ #define MDIO_MMD_PCS_MV_TDR_OFF_CUTOFF 65246 +struct mv88q2xxx_priv { + bool enable_temp; +}; + struct mmd_val { int devad; u32 regnum; @@ -710,17 +714,12 @@ static const struct hwmon_chip_info mv88q2xxx_hwmon_chip_info = { static int mv88q2xxx_hwmon_probe(struct phy_device *phydev) { + struct mv88q2xxx_priv *priv = phydev->priv; struct device *dev = &phydev->mdio.dev; struct device *hwmon; char *hwmon_name; - int ret; - - /* Enable temperature sense */ - ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_TEMP_SENSOR2, - MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0); - if (ret < 0) - return ret; + priv->enable_temp = true; hwmon_name = devm_hwmon_sanitize_name(dev, dev_name(dev)); if (IS_ERR(hwmon_name)) return PTR_ERR(hwmon_name); @@ -743,6 +742,14 @@ static int mv88q2xxx_hwmon_probe(struct phy_device *phydev) static int mv88q2xxx_probe(struct phy_device *phydev) { + struct mv88q2xxx_priv *priv; + + priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + phydev->priv = priv; + return mv88q2xxx_hwmon_probe(phydev); } @@ -810,6 +817,18 @@ static int mv88q222x_revb1_revb2_config_init(struct phy_device *phydev) static int mv88q222x_config_init(struct phy_device *phydev) { + struct mv88q2xxx_priv *priv = phydev->priv; + int ret; + + /* Enable temperature sense */ + if (priv->enable_temp) { + ret = phy_modify_mmd(phydev, MDIO_MMD_PCS, + MDIO_MMD_PCS_MV_TEMP_SENSOR2, + MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0); + if (ret < 0) + return ret; + } + if (phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] == PHY_ID_88Q2220_REVB0) return mv88q222x_revb0_config_init(phydev); else diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 323717a4821f..34231b5b9175 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -1297,6 +1297,8 @@ static int nxp_c45_soft_reset(struct phy_device *phydev) if (ret) return ret; + usleep_range(2000, 2050); + return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1, VEND1_DEVICE_CONTROL, ret, !(ret & DEVICE_CONTROL_RESET), 20000, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 214b62fba991..b00a315de060 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2265,12 +2265,15 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, /* Allow the MAC to stop its clock if the PHY has the capability */ pl->mac_tx_clk_stop = phy_eee_tx_clock_stop_capable(phy) > 0; - /* Explicitly configure whether the PHY is allowed to stop it's - * receive clock. - */ - ret = phy_eee_rx_clock_stop(phy, pl->config->eee_rx_clk_stop_enable); - if (ret == -EOPNOTSUPP) - ret = 0; + if (pl->mac_supports_eee_ops) { + /* Explicitly configure whether the PHY is allowed to stop it's + * receive clock. + */ + ret = phy_eee_rx_clock_stop(phy, + pl->config->eee_rx_clk_stop_enable); + if (ret == -EOPNOTSUPP) + ret = 0; + } return ret; } diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index fc9e23927b3b..7d60a714ca53 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -1047,7 +1047,7 @@ static int pd692x0_pi_get_pw_limit(struct pse_controller_dev *pcdev, if (ret < 0) return ret; - return pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); + return pd692x0_pi_get_pw_from_table(buf.data[0], buf.data[1]); } static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev, diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index 4f2a54afc4d0..4602e26eb8c8 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -319,7 +319,7 @@ static int pse_pi_get_current_limit(struct regulator_dev *rdev) goto out; mW = ret; - ret = pse_pi_get_voltage(rdev); + ret = _pse_pi_get_voltage(rdev); if (!ret) { dev_err(pcdev->dev, "Voltage null\n"); ret = -ERANGE; @@ -356,7 +356,7 @@ static int pse_pi_set_current_limit(struct regulator_dev *rdev, int min_uA, id = rdev_get_id(rdev); mutex_lock(&pcdev->lock); - ret = pse_pi_get_voltage(rdev); + ret = _pse_pi_get_voltage(rdev); if (!ret) { dev_err(pcdev->dev, "Voltage null\n"); ret = -ERANGE; diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index dc7cbd6a9798..f4019815f473 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -2639,7 +2639,9 @@ int team_nl_options_set_doit(struct sk_buff *skb, struct genl_info *info) ctx.data.u32_val = nla_get_u32(attr_data); break; case TEAM_OPTION_TYPE_STRING: - if (nla_len(attr_data) > TEAM_STRING_MAX_LEN) { + if (nla_len(attr_data) > TEAM_STRING_MAX_LEN || + !memchr(nla_data(attr_data), '\0', + nla_len(attr_data))) { err = -EINVAL; goto team_put; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 28624cca91f8..acf96f262488 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -574,18 +574,14 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, return ret; } -static inline bool tun_capable(struct tun_struct *tun) +static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); struct net *net = dev_net(tun->dev); - if (ns_capable(net->user_ns, CAP_NET_ADMIN)) - return 1; - if (uid_valid(tun->owner) && uid_eq(cred->euid, tun->owner)) - return 1; - if (gid_valid(tun->group) && in_egroup_p(tun->group)) - return 1; - return 0; + return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) || + (gid_valid(tun->group) && !in_egroup_p(tun->group))) && + !ns_capable(net->user_ns, CAP_NET_ADMIN); } static void tun_set_real_num_queues(struct tun_struct *tun) @@ -2782,7 +2778,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) !!(tun->flags & IFF_MULTI_QUEUE)) return -EINVAL; - if (!tun_capable(tun)) + if (tun_not_capable(tun)) return -EPERM; err = security_tun_dev_open(tun->security); if (err < 0) diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 46afb95ffabe..a19789b57190 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -61,7 +61,18 @@ #define IPHETH_USBINTF_PROTO 1 #define IPHETH_IP_ALIGN 2 /* padding at front of URB */ -#define IPHETH_NCM_HEADER_SIZE (12 + 96) /* NCMH + NCM0 */ +/* On iOS devices, NCM headers in RX have a fixed size regardless of DPE count: + * - NTH16 (NCMH): 12 bytes, as per CDC NCM 1.0 spec + * - NDP16 (NCM0): 96 bytes, of which + * - NDP16 fixed header: 8 bytes + * - maximum of 22 DPEs (21 datagrams + trailer), 4 bytes each + */ +#define IPHETH_NDP16_MAX_DPE 22 +#define IPHETH_NDP16_HEADER_SIZE (sizeof(struct usb_cdc_ncm_ndp16) + \ + IPHETH_NDP16_MAX_DPE * \ + sizeof(struct usb_cdc_ncm_dpe16)) +#define IPHETH_NCM_HEADER_SIZE (sizeof(struct usb_cdc_ncm_nth16) + \ + IPHETH_NDP16_HEADER_SIZE) #define IPHETH_TX_BUF_SIZE ETH_FRAME_LEN #define IPHETH_RX_BUF_SIZE_LEGACY (IPHETH_IP_ALIGN + ETH_FRAME_LEN) #define IPHETH_RX_BUF_SIZE_NCM 65536 @@ -207,15 +218,23 @@ static int ipheth_rcvbulk_callback_legacy(struct urb *urb) return ipheth_consume_skb(buf, len, dev); } +/* In "NCM mode", the iOS device encapsulates RX (phone->computer) traffic + * in NCM Transfer Blocks (similarly to CDC NCM). However, unlike reverse + * tethering (handled by the `cdc_ncm` driver), regular tethering is not + * compliant with the CDC NCM spec, as the device is missing the necessary + * descriptors, and TX (computer->phone) traffic is not encapsulated + * at all. Thus `ipheth` implements a very limited subset of the spec with + * the sole purpose of parsing RX URBs. + */ static int ipheth_rcvbulk_callback_ncm(struct urb *urb) { struct usb_cdc_ncm_nth16 *ncmh; struct usb_cdc_ncm_ndp16 *ncm0; struct usb_cdc_ncm_dpe16 *dpe; struct ipheth_device *dev; + u16 dg_idx, dg_len; int retval = -EINVAL; char *buf; - int len; dev = urb->context; @@ -226,40 +245,42 @@ static int ipheth_rcvbulk_callback_ncm(struct urb *urb) ncmh = urb->transfer_buffer; if (ncmh->dwSignature != cpu_to_le32(USB_CDC_NCM_NTH16_SIGN) || - le16_to_cpu(ncmh->wNdpIndex) >= urb->actual_length) { - dev->net->stats.rx_errors++; - return retval; - } + /* On iOS, NDP16 directly follows NTH16 */ + ncmh->wNdpIndex != cpu_to_le16(sizeof(struct usb_cdc_ncm_nth16))) + goto rx_error; - ncm0 = urb->transfer_buffer + le16_to_cpu(ncmh->wNdpIndex); - if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN) || - le16_to_cpu(ncmh->wHeaderLength) + le16_to_cpu(ncm0->wLength) >= - urb->actual_length) { - dev->net->stats.rx_errors++; - return retval; - } + ncm0 = urb->transfer_buffer + sizeof(struct usb_cdc_ncm_nth16); + if (ncm0->dwSignature != cpu_to_le32(USB_CDC_NCM_NDP16_NOCRC_SIGN)) + goto rx_error; dpe = ncm0->dpe16; - while (le16_to_cpu(dpe->wDatagramIndex) != 0 && - le16_to_cpu(dpe->wDatagramLength) != 0) { - if (le16_to_cpu(dpe->wDatagramIndex) >= urb->actual_length || - le16_to_cpu(dpe->wDatagramIndex) + - le16_to_cpu(dpe->wDatagramLength) > urb->actual_length) { + for (int dpe_i = 0; dpe_i < IPHETH_NDP16_MAX_DPE; ++dpe_i, ++dpe) { + dg_idx = le16_to_cpu(dpe->wDatagramIndex); + dg_len = le16_to_cpu(dpe->wDatagramLength); + + /* Null DPE must be present after last datagram pointer entry + * (3.3.1 USB CDC NCM spec v1.0) + */ + if (dg_idx == 0 && dg_len == 0) + return 0; + + if (dg_idx < IPHETH_NCM_HEADER_SIZE || + dg_idx >= urb->actual_length || + dg_len > urb->actual_length - dg_idx) { dev->net->stats.rx_length_errors++; return retval; } - buf = urb->transfer_buffer + le16_to_cpu(dpe->wDatagramIndex); - len = le16_to_cpu(dpe->wDatagramLength); + buf = urb->transfer_buffer + dg_idx; - retval = ipheth_consume_skb(buf, len, dev); + retval = ipheth_consume_skb(buf, dg_len, dev); if (retval != 0) return retval; - - dpe++; } - return 0; +rx_error: + dev->net->stats.rx_errors++; + return retval; } static void ipheth_rcvbulk_callback(struct urb *urb) diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 01a3b2417a54..ddff6f19ff98 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -71,6 +71,14 @@ #define MSR_SPEED (1<<3) #define MSR_LINK (1<<2) +/* USB endpoints */ +enum rtl8150_usb_ep { + RTL8150_USB_EP_CONTROL = 0, + RTL8150_USB_EP_BULK_IN = 1, + RTL8150_USB_EP_BULK_OUT = 2, + RTL8150_USB_EP_INT_IN = 3, +}; + /* Interrupt pipe data */ #define INT_TSR 0x00 #define INT_RSR 0x01 @@ -867,6 +875,13 @@ static int rtl8150_probe(struct usb_interface *intf, struct usb_device *udev = interface_to_usbdev(intf); rtl8150_t *dev; struct net_device *netdev; + static const u8 bulk_ep_addr[] = { + RTL8150_USB_EP_BULK_IN | USB_DIR_IN, + RTL8150_USB_EP_BULK_OUT | USB_DIR_OUT, + 0}; + static const u8 int_ep_addr[] = { + RTL8150_USB_EP_INT_IN | USB_DIR_IN, + 0}; netdev = alloc_etherdev(sizeof(rtl8150_t)); if (!netdev) @@ -880,6 +895,13 @@ static int rtl8150_probe(struct usb_interface *intf, return -ENOMEM; } + /* Verify that all required endpoints are present */ + if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) || + !usb_check_int_endpoints(intf, int_ep_addr)) { + dev_err(&intf->dev, "couldn't find required endpoints\n"); + goto out; + } + tasklet_setup(&dev->tl, rx_fixup); spin_lock_init(&dev->rx_pool_lock); diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c index 1341374a4588..616ecc38d172 100644 --- a/drivers/net/vmxnet3/vmxnet3_xdp.c +++ b/drivers/net/vmxnet3/vmxnet3_xdp.c @@ -28,7 +28,7 @@ vmxnet3_xdp_get_tq(struct vmxnet3_adapter *adapter) if (likely(cpu < tq_number)) tq = &adapter->tx_queue[cpu]; else - tq = &adapter->tx_queue[reciprocal_scale(cpu, tq_number)]; + tq = &adapter->tx_queue[cpu % tq_number]; return tq; } @@ -124,6 +124,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter, u32 buf_size; u32 dw2; + spin_lock_irq(&tq->tx_lock); dw2 = (tq->tx_ring.gen ^ 0x1) << VMXNET3_TXD_GEN_SHIFT; dw2 |= xdpf->len; ctx.sop_txd = tq->tx_ring.base + tq->tx_ring.next2fill; @@ -134,6 +135,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter, if (vmxnet3_cmd_ring_desc_avail(&tq->tx_ring) == 0) { tq->stats.tx_ring_full++; + spin_unlock_irq(&tq->tx_lock); return -ENOSPC; } @@ -142,8 +144,10 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter, tbi->dma_addr = dma_map_single(&adapter->pdev->dev, xdpf->data, buf_size, DMA_TO_DEVICE); - if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) + if (dma_mapping_error(&adapter->pdev->dev, tbi->dma_addr)) { + spin_unlock_irq(&tq->tx_lock); return -EFAULT; + } tbi->map_type |= VMXNET3_MAP_SINGLE; } else { /* XDP buffer from page pool */ page = virt_to_page(xdpf->data); @@ -182,6 +186,7 @@ vmxnet3_xdp_xmit_frame(struct vmxnet3_adapter *adapter, dma_wmb(); gdesc->dword[2] = cpu_to_le32(le32_to_cpu(gdesc->dword[2]) ^ VMXNET3_TXD_GEN); + spin_unlock_irq(&tq->tx_lock); /* No need to handle the case when tx_num_deferred doesn't reach * threshold. Backend driver at hypervisor side will poll and reset @@ -225,6 +230,7 @@ vmxnet3_xdp_xmit(struct net_device *dev, { struct vmxnet3_adapter *adapter = netdev_priv(dev); struct vmxnet3_tx_queue *tq; + struct netdev_queue *nq; int i; if (unlikely(test_bit(VMXNET3_STATE_BIT_QUIESCED, &adapter->state))) @@ -236,6 +242,9 @@ vmxnet3_xdp_xmit(struct net_device *dev, if (tq->stopped) return -ENETDOWN; + nq = netdev_get_tx_queue(adapter->netdev, tq->qid); + + __netif_tx_lock(nq, smp_processor_id()); for (i = 0; i < n; i++) { if (vmxnet3_xdp_xmit_frame(adapter, frames[i], tq, true)) { tq->stats.xdp_xmit_err++; @@ -243,6 +252,7 @@ vmxnet3_xdp_xmit(struct net_device *dev, } } tq->stats.xdp_xmit += i; + __netif_tx_unlock(nq); return i; } diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 05c10acb2a57..92516189e792 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2898,8 +2898,11 @@ static int vxlan_init(struct net_device *dev) struct vxlan_dev *vxlan = netdev_priv(dev); int err; - if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) - vxlan_vnigroup_init(vxlan); + if (vxlan->cfg.flags & VXLAN_F_VNIFILTER) { + err = vxlan_vnigroup_init(vxlan); + if (err) + return err; + } err = gro_cells_init(&vxlan->gro_cells, dev); if (err) diff --git a/drivers/net/vxlan/vxlan_vnifilter.c b/drivers/net/vxlan/vxlan_vnifilter.c index d2023e7131bd..6e6e9f05509a 100644 --- a/drivers/net/vxlan/vxlan_vnifilter.c +++ b/drivers/net/vxlan/vxlan_vnifilter.c @@ -411,6 +411,11 @@ static int vxlan_vnifilter_dump(struct sk_buff *skb, struct netlink_callback *cb struct tunnel_msg *tmsg; struct net_device *dev; + if (cb->nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct tunnel_msg))) { + NL_SET_ERR_MSG(cb->extack, "Invalid msg length"); + return -EINVAL; + } + tmsg = nlmsg_data(cb->nlh); if (tmsg->flags & ~TUNNEL_MSG_VALID_USER_FLAGS) { diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 4dd6cdf84571..abb510d235a5 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -4851,6 +4851,22 @@ static struct ath12k_reg_rule return reg_rule_ptr; } +static u8 ath12k_wmi_ignore_num_extra_rules(struct ath12k_wmi_reg_rule_ext_params *rule, + u32 num_reg_rules) +{ + u8 num_invalid_5ghz_rules = 0; + u32 count, start_freq; + + for (count = 0; count < num_reg_rules; count++) { + start_freq = le32_get_bits(rule[count].freq_info, REG_RULE_START_FREQ); + + if (start_freq >= ATH12K_MIN_6G_FREQ) + num_invalid_5ghz_rules++; + } + + return num_invalid_5ghz_rules; +} + static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab, struct sk_buff *skb, struct ath12k_reg_info *reg_info) @@ -4861,6 +4877,7 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab, u32 num_2g_reg_rules, num_5g_reg_rules; u32 num_6g_reg_rules_ap[WMI_REG_CURRENT_MAX_AP_TYPE]; u32 num_6g_reg_rules_cl[WMI_REG_CURRENT_MAX_AP_TYPE][WMI_REG_MAX_CLIENT_TYPE]; + u8 num_invalid_5ghz_ext_rules; u32 total_reg_rules = 0; int ret, i, j; @@ -4954,20 +4971,6 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab, memcpy(reg_info->alpha2, &ev->alpha2, REG_ALPHA2_LEN); - /* FIXME: Currently FW includes 6G reg rule also in 5G rule - * list for country US. - * Having same 6G reg rule in 5G and 6G rules list causes - * intersect check to be true, and same rules will be shown - * multiple times in iw cmd. So added hack below to avoid - * parsing 6G rule from 5G reg rule list, and this can be - * removed later, after FW updates to remove 6G reg rule - * from 5G rules list. - */ - if (memcmp(reg_info->alpha2, "US", 2) == 0) { - reg_info->num_5g_reg_rules = REG_US_5G_NUM_REG_RULES; - num_5g_reg_rules = reg_info->num_5g_reg_rules; - } - reg_info->dfs_region = le32_to_cpu(ev->dfs_region); reg_info->phybitmap = le32_to_cpu(ev->phybitmap); reg_info->num_phy = le32_to_cpu(ev->num_phy); @@ -5070,8 +5073,29 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab, } } + ext_wmi_reg_rule += num_2g_reg_rules; + + /* Firmware might include 6 GHz reg rule in 5 GHz rule list + * for few countries along with separate 6 GHz rule. + * Having same 6 GHz reg rule in 5 GHz and 6 GHz rules list + * causes intersect check to be true, and same rules will be + * shown multiple times in iw cmd. + * Hence, avoid parsing 6 GHz rule from 5 GHz reg rule list + */ + num_invalid_5ghz_ext_rules = ath12k_wmi_ignore_num_extra_rules(ext_wmi_reg_rule, + num_5g_reg_rules); + + if (num_invalid_5ghz_ext_rules) { + ath12k_dbg(ab, ATH12K_DBG_WMI, + "CC: %s 5 GHz reg rules number %d from fw, %d number of invalid 5 GHz rules", + reg_info->alpha2, reg_info->num_5g_reg_rules, + num_invalid_5ghz_ext_rules); + + num_5g_reg_rules = num_5g_reg_rules - num_invalid_5ghz_ext_rules; + reg_info->num_5g_reg_rules = num_5g_reg_rules; + } + if (num_5g_reg_rules) { - ext_wmi_reg_rule += num_2g_reg_rules; reg_info->reg_rules_5g_ptr = create_ext_reg_rules_from_wmi(num_5g_reg_rules, ext_wmi_reg_rule); @@ -5083,7 +5107,12 @@ static int ath12k_pull_reg_chan_list_ext_update_ev(struct ath12k_base *ab, } } - ext_wmi_reg_rule += num_5g_reg_rules; + /* We have adjusted the number of 5 GHz reg rules above. But still those + * many rules needs to be adjusted in ext_wmi_reg_rule. + * + * NOTE: num_invalid_5ghz_ext_rules will be 0 for rest other cases. + */ + ext_wmi_reg_rule += (num_5g_reg_rules + num_invalid_5ghz_ext_rules); for (i = 0; i < WMI_REG_CURRENT_MAX_AP_TYPE; i++) { reg_info->reg_rules_6g_ap_ptr[i] = diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h index b6a197389277..45fe699ce8a5 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.h +++ b/drivers/net/wireless/ath/ath12k/wmi.h @@ -4073,7 +4073,6 @@ struct ath12k_wmi_eht_rate_set_params { #define MAX_REG_RULES 10 #define REG_ALPHA2_LEN 2 #define MAX_6G_REG_RULES 5 -#define REG_US_5G_NUM_REG_RULES 4 enum wmi_start_event_param { WMI_VDEV_START_RESP_EVENT = 0, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index e4395b1f8c11..d2caa80e9412 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -2712,7 +2712,7 @@ static const struct pci_device_id brcmf_pcie_devid_table[] = { BRCMF_PCIE_DEVICE(BRCM_PCIE_4350_DEVICE_ID, WCC), BRCMF_PCIE_DEVICE_SUB(0x4355, BRCM_PCIE_VENDOR_ID_BROADCOM, 0x4355, WCC), BRCMF_PCIE_DEVICE(BRCM_PCIE_4354_RAW_DEVICE_ID, WCC), - BRCMF_PCIE_DEVICE(BRCM_PCIE_4355_DEVICE_ID, WCC), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4355_DEVICE_ID, WCC_SEED), BRCMF_PCIE_DEVICE(BRCM_PCIE_4356_DEVICE_ID, WCC), BRCMF_PCIE_DEVICE(BRCM_PCIE_43567_DEVICE_ID, WCC), BRCMF_PCIE_DEVICE(BRCM_PCIE_43570_DEVICE_ID, WCC), @@ -2723,7 +2723,7 @@ static const struct pci_device_id brcmf_pcie_devid_table[] = { BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_2G_DEVICE_ID, WCC), BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_5G_DEVICE_ID, WCC), BRCMF_PCIE_DEVICE(BRCM_PCIE_43602_RAW_DEVICE_ID, WCC), - BRCMF_PCIE_DEVICE(BRCM_PCIE_4364_DEVICE_ID, WCC), + BRCMF_PCIE_DEVICE(BRCM_PCIE_4364_DEVICE_ID, WCC_SEED), BRCMF_PCIE_DEVICE(BRCM_PCIE_4365_DEVICE_ID, BCA), BRCMF_PCIE_DEVICE(BRCM_PCIE_4365_2G_DEVICE_ID, BCA), BRCMF_PCIE_DEVICE(BRCM_PCIE_4365_5G_DEVICE_ID, BCA), diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c index a259f4dd9540..413973d05b43 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c @@ -1479,14 +1479,13 @@ static void mt7603_mac_watchdog_reset(struct mt7603_dev *dev) tasklet_enable(&dev->mt76.pre_tbtt_tasklet); mt7603_beacon_set_timer(dev, -1, beacon_int); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - napi_enable(&dev->mt76.napi[0]); - napi_schedule(&dev->mt76.napi[0]); - napi_enable(&dev->mt76.napi[1]); + + local_bh_disable(); + napi_schedule(&dev->mt76.tx_napi); + napi_schedule(&dev->mt76.napi[0]); napi_schedule(&dev->mt76.napi[1]); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c index 9a278589df4e..68010e27f065 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci.c @@ -164,12 +164,16 @@ static int mt7615_pci_resume(struct pci_dev *pdev) dev_err(mdev->dev, "PDMA engine must be reinitialized\n"); mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c index a0ca3bbdfcaf..c2e4e6aabd9f 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/pci_mac.c @@ -262,12 +262,14 @@ void mt7615_mac_reset_work(struct work_struct *work) mt76_worker_enable(&dev->mt76.tx_worker); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + napi_schedule(&dev->mt76.tx_napi); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c index 1eb955f3ca13..b456ccd00d58 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c @@ -282,14 +282,16 @@ static int mt76x0e_resume(struct pci_dev *pdev) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { mt76_queue_rx_reset(dev, i); napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } - napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index 7d840ad4ae65..a82c75ba26e6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -504,12 +504,14 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) mt76_worker_enable(&dev->mt76.tx_worker); tasklet_enable(&dev->mt76.pre_tbtt_tasklet); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); - napi_schedule(&dev->mt76.tx_napi); - mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + napi_schedule(&dev->mt76.tx_napi); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c index 67c9d1caa0bd..727bfdd00b40 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c @@ -151,12 +151,15 @@ mt76x2e_resume(struct pci_dev *pdev) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 13bdc0a7174c..2ba6eb3038ce 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -1356,10 +1356,15 @@ mt7915_mac_restart(struct mt7915_dev *dev) mt7915_dma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { if (mdev->q_rx[i].ndesc) { napi_enable(&dev->mt76.napi[i]); + } + } + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + if (mdev->q_rx[i].ndesc) { napi_schedule(&dev->mt76.napi[i]); } } @@ -1419,8 +1424,9 @@ out: if (phy2) clear_bit(MT76_RESET, &phy2->mt76->state); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); @@ -1570,9 +1576,12 @@ void mt7915_mac_reset_work(struct work_struct *work) if (phy2) clear_bit(MT76_RESET, &phy2->mt76->state); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); @@ -1581,8 +1590,8 @@ void mt7915_mac_reset_work(struct work_struct *work) mt76_worker_enable(&dev->mt76.tx_worker); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c index ba870e1b05fb..a0c9df3c2cc7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci.c @@ -523,12 +523,15 @@ static int mt7921_pci_resume(struct device *device) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c index 2452b1a2d118..881812ba03ff 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/pci_mac.c @@ -81,9 +81,12 @@ int mt7921e_mac_reset(struct mt792x_dev *dev) mt792x_wpdma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); + } + + local_bh_disable(); + mt76_for_each_q_rx(&dev->mt76, i) { napi_schedule(&dev->mt76.napi[i]); } local_bh_enable(); @@ -115,8 +118,8 @@ int mt7921e_mac_reset(struct mt792x_dev *dev) err = __mt7921_start(&dev->phy); out: - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c index f36893e20c61..c7b5dc1dbb34 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci.c @@ -556,12 +556,15 @@ static int mt7925_pci_resume(struct device *device) mt76_worker_enable(&mdev->tx_worker); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { napi_enable(&mdev->napi[i]); - napi_schedule(&mdev->napi[i]); } napi_enable(&mdev->tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(mdev, i) { + napi_schedule(&mdev->napi[i]); + } napi_schedule(&mdev->tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c index faedbf766d1a..4578d16bf456 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/pci_mac.c @@ -101,12 +101,15 @@ int mt7925e_mac_reset(struct mt792x_dev *dev) mt792x_wpdma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { napi_enable(&dev->mt76.napi[i]); - napi_schedule(&dev->mt76.napi[i]); } napi_enable(&dev->mt76.tx_napi); + + local_bh_disable(); + mt76_for_each_q_rx(&dev->mt76, i) { + napi_schedule(&dev->mt76.napi[i]); + } napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index bc8cba4dca47..019c925ae600 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -1695,7 +1695,6 @@ mt7996_mac_restart(struct mt7996_dev *dev) mt7996_dma_reset(dev, true); - local_bh_disable(); mt76_for_each_q_rx(mdev, i) { if (mtk_wed_device_active(&dev->mt76.mmio.wed) && mt76_queue_is_wed_rro(&mdev->q_rx[i])) @@ -1703,10 +1702,11 @@ mt7996_mac_restart(struct mt7996_dev *dev) if (mdev->q_rx[i].ndesc) { napi_enable(&dev->mt76.napi[i]); + local_bh_disable(); napi_schedule(&dev->mt76.napi[i]); + local_bh_enable(); } } - local_bh_enable(); clear_bit(MT76_MCU_RESET, &dev->mphy.state); clear_bit(MT76_STATE_MCU_RUNNING, &dev->mphy.state); @@ -1764,8 +1764,8 @@ out: if (phy3) clear_bit(MT76_RESET, &phy3->mt76->state); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); @@ -1958,23 +1958,23 @@ void mt7996_mac_reset_work(struct work_struct *work) if (phy3) clear_bit(MT76_RESET, &phy3->mt76->state); - local_bh_disable(); mt76_for_each_q_rx(&dev->mt76, i) { if (mtk_wed_device_active(&dev->mt76.mmio.wed) && mt76_queue_is_wed_rro(&dev->mt76.q_rx[i])) continue; napi_enable(&dev->mt76.napi[i]); + local_bh_disable(); napi_schedule(&dev->mt76.napi[i]); + local_bh_enable(); } - local_bh_enable(); tasklet_schedule(&dev->mt76.irq_tasklet); mt76_worker_enable(&dev->mt76.tx_worker); - local_bh_disable(); napi_enable(&dev->mt76.tx_napi); + local_bh_disable(); napi_schedule(&dev->mt76.tx_napi); local_bh_enable(); diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index d5a9360323d2..8755c5e6a65b 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -220,7 +220,7 @@ static int mbim_rx_verify_nth16(struct mhi_mbim_context *mbim, struct sk_buff *s if (mbim->rx_seq + 1 != le16_to_cpu(nth16->wSequence) && (mbim->rx_seq || le16_to_cpu(nth16->wSequence)) && !(mbim->rx_seq == 0xffff && !le16_to_cpu(nth16->wSequence))) { - net_err_ratelimited("sequence number glitch prev=%d curr=%d\n", + net_dbg_ratelimited("sequence number glitch prev=%d curr=%d\n", mbim->rx_seq, le16_to_cpu(nth16->wSequence)); } mbim->rx_seq = le16_to_cpu(nth16->wSequence); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 76b615d4d5b9..818d4e49aab5 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1700,7 +1700,13 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0, &result); - if (status < 0) + + /* + * It's either a kernel error or the host observed a connection + * lost. In either case it's not possible communicate with the + * controller and thus enter the error code path. + */ + if (status < 0 || status == NVME_SC_HOST_PATH_ERROR) return status; /* @@ -2132,15 +2138,16 @@ static int nvme_update_ns_info_generic(struct nvme_ns *ns, struct nvme_ns_info *info) { struct queue_limits lim; + unsigned int memflags; int ret; lim = queue_limits_start_update(ns->disk->queue); nvme_set_ctrl_limits(ns->ctrl, &lim); - blk_mq_freeze_queue(ns->disk->queue); + memflags = blk_mq_freeze_queue(ns->disk->queue); ret = queue_limits_commit_update(ns->disk->queue, &lim); set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); - blk_mq_unfreeze_queue(ns->disk->queue); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); /* Hide the block-interface for these devices */ if (!ret) @@ -2155,6 +2162,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, struct nvme_id_ns_nvm *nvm = NULL; struct nvme_zone_info zi = {}; struct nvme_id_ns *id; + unsigned int memflags; sector_t capacity; unsigned lbaf; int ret; @@ -2186,7 +2194,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, lim = queue_limits_start_update(ns->disk->queue); - blk_mq_freeze_queue(ns->disk->queue); + memflags = blk_mq_freeze_queue(ns->disk->queue); ns->head->lba_shift = id->lbaf[lbaf].ds; ns->head->nuse = le64_to_cpu(id->nuse); capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze)); @@ -2219,7 +2227,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, ret = queue_limits_commit_update(ns->disk->queue, &lim); if (ret) { - blk_mq_unfreeze_queue(ns->disk->queue); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); goto out; } @@ -2235,7 +2243,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns, ns->head->features |= NVME_NS_DEAC; set_disk_ro(ns->disk, nvme_ns_is_readonly(ns, info)); set_bit(NVME_NS_READY, &ns->flags); - blk_mq_unfreeze_queue(ns->disk->queue); + blk_mq_unfreeze_queue(ns->disk->queue, memflags); if (blk_queue_is_zoned(ns->queue)) { ret = blk_revalidate_disk_zones(ns->disk); @@ -2291,9 +2299,10 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) if (!ret && nvme_ns_head_multipath(ns->head)) { struct queue_limits *ns_lim = &ns->disk->queue->limits; struct queue_limits lim; + unsigned int memflags; lim = queue_limits_start_update(ns->head->disk->queue); - blk_mq_freeze_queue(ns->head->disk->queue); + memflags = blk_mq_freeze_queue(ns->head->disk->queue); /* * queue_limits mixes values that are the hardware limitations * for bio splitting with what is the device configuration. @@ -2325,7 +2334,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info) set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info)); nvme_mpath_revalidate_paths(ns); - blk_mq_unfreeze_queue(ns->head->disk->queue); + blk_mq_unfreeze_queue(ns->head->disk->queue, memflags); } return ret; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 094be164ffdc..f4f1866fbd5b 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -781,11 +781,19 @@ restart: static void nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) { + enum nvme_ctrl_state state; + unsigned long flags; + dev_info(ctrl->ctrl.device, "NVME-FC{%d}: controller connectivity lost. Awaiting " "Reconnect", ctrl->cnum); - switch (nvme_ctrl_state(&ctrl->ctrl)) { + spin_lock_irqsave(&ctrl->lock, flags); + set_bit(ASSOC_FAILED, &ctrl->flags); + state = nvme_ctrl_state(&ctrl->ctrl); + spin_unlock_irqrestore(&ctrl->lock, flags); + + switch (state) { case NVME_CTRL_NEW: case NVME_CTRL_LIVE: /* @@ -2079,7 +2087,8 @@ done: nvme_fc_complete_rq(rq); check_error: - if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING) + if (terminate_assoc && + nvme_ctrl_state(&ctrl->ctrl) != NVME_CTRL_RESETTING) queue_work(nvme_reset_wq, &ctrl->ioerr_work); } @@ -2533,6 +2542,8 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues) static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) { + enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl); + /* * if an error (io timeout, etc) while (re)connecting, the remote * port requested terminating of the association (disconnect_ls) @@ -2540,9 +2551,8 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) * the controller. Abort any ios on the association and let the * create_association error path resolve things. */ - if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) { + if (state == NVME_CTRL_CONNECTING) { __nvme_fc_abort_outstanding_ios(ctrl, true); - set_bit(ASSOC_FAILED, &ctrl->flags); dev_warn(ctrl->ctrl.device, "NVME-FC{%d}: transport error during (re)connect\n", ctrl->cnum); @@ -2550,7 +2560,7 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) } /* Otherwise, only proceed if in LIVE state - e.g. on first error */ - if (ctrl->ctrl.state != NVME_CTRL_LIVE) + if (state != NVME_CTRL_LIVE) return; dev_warn(ctrl->ctrl.device, @@ -3167,12 +3177,18 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) else ret = nvme_fc_recreate_io_queues(ctrl); } - if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) - ret = -EIO; if (ret) goto out_term_aen_ops; - changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); + spin_lock_irqsave(&ctrl->lock, flags); + if (!test_bit(ASSOC_FAILED, &ctrl->flags)) + changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); + else + ret = -EIO; + spin_unlock_irqrestore(&ctrl->lock, flags); + + if (ret) + goto out_term_aen_ops; ctrl->ctrl.nr_reconnects = 0; @@ -3578,8 +3594,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list); spin_unlock_irqrestore(&rport->lock, flags); - if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING) || - !nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) { dev_err(ctrl->ctrl.device, "NVME-FC{%d}: failed to init ctrl state\n", ctrl->cnum); goto fail_ctrl; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index a85d190942bd..2a7635565083 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -60,7 +60,7 @@ void nvme_mpath_unfreeze(struct nvme_subsystem *subsys) lockdep_assert_held(&subsys->lock); list_for_each_entry(h, &subsys->nsheads, entry) if (h->disk) - blk_mq_unfreeze_queue(h->disk->queue); + blk_mq_unfreeze_queue_nomemrestore(h->disk->queue); } void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 278bed4e35bb..9197a5b173fd 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2153,14 +2153,6 @@ static int nvme_alloc_host_mem_multi(struct nvme_dev *dev, u64 preferred, return 0; out_free_bufs: - while (--i >= 0) { - size_t size = le32_to_cpu(descs[i].size) * NVME_CTRL_PAGE_SIZE; - - dma_free_attrs(dev->dev, size, bufs[i], - le64_to_cpu(descs[i].addr), - DMA_ATTR_NO_KERNEL_MAPPING | DMA_ATTR_NO_WARN); - } - kfree(bufs); out_free_descs: dma_free_coherent(dev->dev, descs_size, descs, descs_dma); @@ -3147,7 +3139,9 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev) * because of high power consumption (> 2 Watt) in s2idle * sleep. Only some boards with Intel CPU are affected. */ - if (dmi_match(DMI_BOARD_NAME, "GMxPXxx") || + if (dmi_match(DMI_BOARD_NAME, "DN50Z-140HC-YD") || + dmi_match(DMI_BOARD_NAME, "GMxPXxx") || + dmi_match(DMI_BOARD_NAME, "GXxMRXx") || dmi_match(DMI_BOARD_NAME, "PH4PG31") || dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1") || dmi_match(DMI_BOARD_NAME, "PH6PG01_PH6PG71")) diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index b68a9e5f1ea3..3a41b9ab0f13 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -792,7 +792,7 @@ static umode_t nvme_tls_attrs_are_visible(struct kobject *kobj, return a->mode; } -const struct attribute_group nvme_tls_attrs_group = { +static const struct attribute_group nvme_tls_attrs_group = { .attrs = nvme_tls_attrs, .is_visible = nvme_tls_attrs_are_visible, }; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index e670dc185a96..acc138bbf8f2 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -1068,6 +1068,7 @@ static void nvme_execute_identify_ns_nvm(struct nvmet_req *req) goto out; } status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id)); + kfree(id); out: nvmet_req_complete(req, status); } diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index a7ff05b3be29..eb406c90c167 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -287,7 +287,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) args.subsysnqn = d->subsysnqn; args.hostnqn = d->hostnqn; args.hostid = &d->hostid; - args.kato = c->kato; + args.kato = le32_to_cpu(c->kato); ctrl = nvmet_alloc_ctrl(&args); if (!ctrl) diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index c1f574fe3280..83be0657e6df 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -272,7 +272,7 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req) iter_flags = SG_MITER_FROM_SG; } - if (req->cmd->rw.control & NVME_RW_LR) + if (req->cmd->rw.control & cpu_to_le16(NVME_RW_LR)) opf |= REQ_FAILFAST_DEV; if (is_pci_p2pdma_page(sg_page(req->sg))) diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index b540216c0c9a..4be8d22d2d8d 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -589,7 +589,7 @@ struct nvmet_alloc_ctrl_args { const struct nvmet_fabrics_ops *ops; struct device *p2p_client; u32 kato; - u32 result; + __le32 result; u16 error_loc; u16 status; }; diff --git a/drivers/of/address.c b/drivers/of/address.c index 125833e5ce52..d177a2b9edaf 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -16,6 +16,8 @@ #include <linux/string.h> #include <linux/dma-direct.h> /* for bus_dma_region */ +#include <kunit/visibility.h> + /* Uncomment me to enable of_dump_addr() debugging output */ // #define DEBUG @@ -183,7 +185,7 @@ static u64 of_bus_pci_map(__be32 *addr, const __be32 *range, int na, int ns, #endif /* CONFIG_PCI */ -static int __of_address_resource_bounds(struct resource *r, u64 start, u64 size) +VISIBLE_IF_KUNIT int __of_address_resource_bounds(struct resource *r, u64 start, u64 size) { if (overflows_type(start, r->start)) return -EOVERFLOW; @@ -197,6 +199,7 @@ static int __of_address_resource_bounds(struct resource *r, u64 start, u64 size) return 0; } +EXPORT_SYMBOL_IF_KUNIT(__of_address_resource_bounds); /* * of_pci_range_to_resource - Create a resource from an of_pci_range diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index f3e1193c8ded..1bdc7ceef3c5 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -208,4 +208,8 @@ static void __maybe_unused of_dump_addr(const char *s, const __be32 *addr, int n static void __maybe_unused of_dump_addr(const char *s, const __be32 *addr, int na) { } #endif +#if IS_ENABLED(CONFIG_KUNIT) +int __of_address_resource_bounds(struct resource *r, u64 start, u64 size); +#endif + #endif /* _LINUX_OF_PRIVATE_H */ diff --git a/drivers/of/of_test.c b/drivers/of/of_test.c index b0557ded838f..8bba5a72c9c7 100644 --- a/drivers/of/of_test.c +++ b/drivers/of/of_test.c @@ -2,6 +2,7 @@ /* * KUnit tests for OF APIs */ +#include <linux/ioport.h> #include <linux/module.h> #include <linux/of.h> @@ -54,8 +55,124 @@ static struct kunit_suite of_dtb_suite = { .init = of_dtb_test_init, }; +struct of_address_resource_bounds_case { + u64 start; + u64 size; + int ret; + + u64 res_start; + u64 res_end; +}; + +static void of_address_resource_bounds_case_desc(const struct of_address_resource_bounds_case *p, + char *name) +{ + snprintf(name, KUNIT_PARAM_DESC_SIZE, "start=0x%016llx,size=0x%016llx", p->start, p->size); +} + +static const struct of_address_resource_bounds_case of_address_resource_bounds_cases[] = { + { + .start = 0, + .size = 0, + .ret = 0, + .res_start = 0, + .res_end = -1, + }, + { + .start = 0, + .size = 0x1000, + .ret = 0, + .res_start = 0, + .res_end = 0xfff, + }, + { + .start = 0x1000, + .size = 0, + .ret = 0, + .res_start = 0x1000, + .res_end = 0xfff, + }, + { + .start = 0x1000, + .size = 0x1000, + .ret = 0, + .res_start = 0x1000, + .res_end = 0x1fff, + }, + { + .start = 1, + .size = RESOURCE_SIZE_MAX, + .ret = 0, + .res_start = 1, + .res_end = RESOURCE_SIZE_MAX, + }, + { + .start = RESOURCE_SIZE_MAX, + .size = 1, + .ret = 0, + .res_start = RESOURCE_SIZE_MAX, + .res_end = RESOURCE_SIZE_MAX, + }, + { + .start = 2, + .size = RESOURCE_SIZE_MAX, + .ret = -EOVERFLOW, + }, + { + .start = RESOURCE_SIZE_MAX, + .size = 2, + .ret = -EOVERFLOW, + }, + { + .start = ULL(0x100000000), + .size = 1, + .ret = sizeof(resource_size_t) > sizeof(u32) ? 0 : -EOVERFLOW, + .res_start = ULL(0x100000000), + .res_end = ULL(0x100000000), + }, + { + .start = 0x1000, + .size = 0xffffffff, + .ret = sizeof(resource_size_t) > sizeof(u32) ? 0 : -EOVERFLOW, + .res_start = 0x1000, + .res_end = ULL(0x100000ffe), + }, +}; + +KUNIT_ARRAY_PARAM(of_address_resource_bounds, + of_address_resource_bounds_cases, of_address_resource_bounds_case_desc); + +static void of_address_resource_bounds(struct kunit *test) +{ + const struct of_address_resource_bounds_case *param = test->param_value; + struct resource r; /* Intentionally uninitialized */ + int ret; + + if (!IS_ENABLED(CONFIG_OF_ADDRESS)) + kunit_skip(test, "CONFIG_OF_ADDRESS not enabled\n"); + + ret = __of_address_resource_bounds(&r, param->start, param->size); + KUNIT_EXPECT_EQ(test, param->ret, ret); + if (ret == 0) { + KUNIT_EXPECT_EQ(test, (resource_size_t)param->res_start, r.start); + KUNIT_EXPECT_EQ(test, (resource_size_t)param->res_end, r.end); + KUNIT_EXPECT_EQ(test, param->size, resource_size(&r)); + } +} + +static struct kunit_case of_address_test_cases[] = { + KUNIT_CASE_PARAM(of_address_resource_bounds, of_address_resource_bounds_gen_params), + {} +}; + +static struct kunit_suite of_address_suite = { + .name = "of_address", + .test_cases = of_address_test_cases, +}; + kunit_test_suites( - &of_dtb_suite, + &of_dtb_suite, &of_address_suite, ); MODULE_DESCRIPTION("KUnit tests for OF APIs"); +MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING"); MODULE_LICENSE("GPL"); diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index d1d97a4bb36d..3431a7df3e0d 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -419,19 +419,12 @@ static void pcim_intx_restore(struct device *dev, void *data) pci_intx(pdev, res->orig_intx); } -static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev) +static void save_orig_intx(struct pci_dev *pdev, struct pcim_intx_devres *res) { - struct pcim_intx_devres *res; - - res = devres_find(dev, pcim_intx_restore, NULL, NULL); - if (res) - return res; + u16 pci_command; - res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL); - if (res) - devres_add(dev, res); - - return res; + pci_read_config_word(pdev, PCI_COMMAND, &pci_command); + res->orig_intx = !(pci_command & PCI_COMMAND_INTX_DISABLE); } /** @@ -447,12 +440,23 @@ static struct pcim_intx_devres *get_or_create_intx_devres(struct device *dev) int pcim_intx(struct pci_dev *pdev, int enable) { struct pcim_intx_devres *res; + struct device *dev = &pdev->dev; - res = get_or_create_intx_devres(&pdev->dev); - if (!res) - return -ENOMEM; + /* + * pcim_intx() must only restore the INTx value that existed before the + * driver was loaded, i.e., before it called pcim_intx() for the + * first time. + */ + res = devres_find(dev, pcim_intx_restore, NULL, NULL); + if (!res) { + res = devres_alloc(pcim_intx_restore, sizeof(*res), GFP_KERNEL); + if (!res) + return -ENOMEM; + + save_orig_intx(pdev, res); + devres_add(dev, res); + } - res->orig_intx = !enable; pci_intx(pdev, enable); return 0; diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index e0bc90597dca..da3e7edcf49d 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -108,9 +108,6 @@ void pci_save_aspm_l1ss_state(struct pci_dev *pdev) pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL2, cap++); pci_read_config_dword(pdev, pdev->l1ss + PCI_L1SS_CTL1, cap++); - if (parent->state_saved) - return; - /* * Save parent's L1 substate configuration so we have it for * pci_restore_aspm_l1ss_state(pdev) to restore. diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index b6536ed599c3..246744d8d268 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -339,13 +339,14 @@ out: return (res->flags & IORESOURCE_MEM_64) ? 1 : 0; } -static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom) +static __always_inline void pci_read_bases(struct pci_dev *dev, + unsigned int howmany, int rom) { u32 rombar, stdbars[PCI_STD_NUM_BARS]; unsigned int pos, reg; u16 orig_cmd; - BUILD_BUG_ON(howmany > PCI_STD_NUM_BARS); + BUILD_BUG_ON(statically_true(howmany > PCI_STD_NUM_BARS)); if (dev->non_compliant_bars) return; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index b84ff7bade82..82b21e34c545 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5522,7 +5522,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x443, quirk_intel_qat_vf_cap); * AMD Matisse USB 3.0 Host Controller 0x149c * Intel 82579LM Gigabit Ethernet Controller 0x1502 * Intel 82579V Gigabit Ethernet Controller 0x1503 - * + * Mediatek MT7922 802.11ax PCI Express Wireless Network Adapter */ static void quirk_no_flr(struct pci_dev *dev) { @@ -5534,6 +5534,7 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x149c, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_AMD, 0x7901, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1502, quirk_no_flr); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1503, quirk_no_flr); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_MEDIATEK, 0x0616, quirk_no_flr); /* FLR may cause the SolidRun SNET DPU (rev 0x1) to hang */ static void quirk_no_flr_snet(struct pci_dev *dev) diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c index 1e604fbbda65..07de59ca2ebf 100644 --- a/drivers/pci/tph.c +++ b/drivers/pci/tph.c @@ -360,7 +360,7 @@ int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag) return err; } - set_ctrl_reg_req_en(pdev, pdev->tph_mode); + set_ctrl_reg_req_en(pdev, pdev->tph_req_type); pci_dbg(pdev, "set steering tag: %s table, index=%d, tag=%#04x\n", (loc == PCI_TPH_LOC_MSIX) ? "MSI-X" : "ST", index, tag); diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c index b5cc11abc962..0e360feb3432 100644 --- a/drivers/perf/arm_pmuv3.c +++ b/drivers/perf/arm_pmuv3.c @@ -1279,7 +1279,7 @@ static int armv8pmu_proc_user_access_handler(const struct ctl_table *table, int return 0; } -static struct ctl_table armv8_pmu_sysctl_table[] = { +static const struct ctl_table armv8_pmu_sysctl_table[] = { { .procname = "perf_user_access", .data = &sysctl_perf_user_access, diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 194c153e5d71..698de8ddf895 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -1317,7 +1317,7 @@ static int riscv_pmu_proc_user_access_handler(const struct ctl_table *table, return 0; } -static struct ctl_table sbi_pmu_sysctl_table[] = { +static const struct ctl_table sbi_pmu_sysctl_table[] = { { .procname = "perf_user_access", .data = &sysctl_perf_user_access, diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c index cd159a71b23c..29b8fd4b9351 100644 --- a/drivers/phy/allwinner/phy-sun4i-usb.c +++ b/drivers/phy/allwinner/phy-sun4i-usb.c @@ -23,7 +23,6 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/of.h> -#include <linux/of_gpio.h> #include <linux/phy/phy.h> #include <linux/phy/phy-sun4i-usb.h> #include <linux/platform_device.h> diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c index d3ccf547ba1c..45004f598e4d 100644 --- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c +++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c @@ -331,25 +331,17 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy, { u32 pclk = cfg->pixclk; u32 fld_tg_code; - u32 pclk_khz; - u8 div = 1; - - switch (cfg->pixclk) { - case 22250000 ... 47500000: - div = 1; - break; - case 50349650 ... 99000000: - div = 2; - break; - case 100699300 ... 198000000: - div = 4; - break; - case 205000000 ... 297000000: - div = 8; - break; + u32 int_pllclk; + u8 div; + + /* Find int_pllclk speed */ + for (div = 0; div < 4; div++) { + int_pllclk = pclk / (1 << div); + if (int_pllclk < (50 * MHZ)) + break; } - writeb(FIELD_PREP(REG12_CK_DIV_MASK, ilog2(div)), phy->regs + PHY_REG(12)); + writeb(FIELD_PREP(REG12_CK_DIV_MASK, div), phy->regs + PHY_REG(12)); /* * Calculation for the frequency lock detector target code (fld_tg_code) @@ -362,10 +354,8 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy, * settings rounding up always too. TODO: Check if that is * correct. */ - pclk /= div; - pclk_khz = pclk / 1000; - fld_tg_code = 256 * 1000 * 1000 / pclk_khz * 24; - fld_tg_code = DIV_ROUND_UP(fld_tg_code, 1000); + + fld_tg_code = DIV_ROUND_UP(24 * MHZ * 256, int_pllclk); /* FLD_TOL and FLD_RP_CODE taken from downstream driver */ writeb(FIELD_PREP(REG13_TG_CODE_LOW_MASK, fld_tg_code), @@ -406,16 +396,15 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1 continue; /* - * TODO: Ref Manual doesn't state the range of _m - * so this should be further refined if possible. - * This range was set based on the original values - * in the lookup table + * The Ref manual doesn't explicitly state the range of M, + * but it does show it as an 8-bit value, so reject + * any value above 255. */ tmp = (u64)fout * (_p * _s); do_div(tmp, 24 * MHZ); - _m = tmp; - if (_m < 0x30 || _m > 0x7b) + if (tmp > 255) continue; + _m = tmp; /* * Rev 2 of the Ref Manual states the @@ -440,9 +429,13 @@ static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u1 min_delta = delta; best_freq = tmp; } + + /* If we have an exact match, stop looking for a better value */ + if (!delta) + goto done; } } - +done: if (best_freq) { *p = best_p; *m = best_m; diff --git a/drivers/phy/hisilicon/phy-hi3670-pcie.c b/drivers/phy/hisilicon/phy-hi3670-pcie.c index 0ac9634b398d..dbc7dcce682b 100644 --- a/drivers/phy/hisilicon/phy-hi3670-pcie.c +++ b/drivers/phy/hisilicon/phy-hi3670-pcie.c @@ -16,15 +16,20 @@ */ #include <linux/bitfield.h> +#include <linux/bits.h> #include <linux/clk.h> -#include <linux/gpio.h> -#include <linux/kernel.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/io.h> #include <linux/mfd/syscon.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> -#include <linux/of_gpio.h> +#include <linux/of.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> #include <linux/regmap.h> +#include <linux/types.h> #define AXI_CLK_FREQ 207500000 #define REF_CLK_FREQ 100000000 diff --git a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c index fefc02d921e6..71f9c14fb50d 100644 --- a/drivers/phy/marvell/phy-mvebu-cp110-comphy.c +++ b/drivers/phy/marvell/phy-mvebu-cp110-comphy.c @@ -422,7 +422,7 @@ static int mvebu_comphy_ethernet_init_reset(struct mvebu_comphy_lane *lane) /* wait until clocks are ready */ mdelay(1); - /* exlicitly disable 40B, the bits isn't clear on reset */ + /* explicitly disable 40B, the bits isn't clear on reset */ regmap_read(priv->regmap, MVEBU_COMPHY_CONF6(lane->id), &val); val &= ~MVEBU_COMPHY_CONF6_40B; regmap_write(priv->regmap, MVEBU_COMPHY_CONF6(lane->id), val); diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c index bbfe11d6a69d..b38f3ae26b3f 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.c @@ -9,6 +9,8 @@ #include <linux/module.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/of_regulator.h> #include <linux/types.h> #include <linux/units.h> #include <linux/nvmem-consumer.h> @@ -478,8 +480,50 @@ static int mtk_hdmi_phy_configure(struct phy *phy, union phy_configure_opts *opt return ret; } +static int mtk_hdmi_phy_pwr5v_enable(struct regulator_dev *rdev) +{ + struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev); + + mtk_phy_set_bits(hdmi_phy->regs + HDMI_CTL_1, RG_HDMITX_PWR5V_O); + + return 0; +} + +static int mtk_hdmi_phy_pwr5v_disable(struct regulator_dev *rdev) +{ + struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev); + + mtk_phy_clear_bits(hdmi_phy->regs + HDMI_CTL_1, RG_HDMITX_PWR5V_O); + + return 0; +} + +static int mtk_hdmi_phy_pwr5v_is_enabled(struct regulator_dev *rdev) +{ + struct mtk_hdmi_phy *hdmi_phy = rdev_get_drvdata(rdev); + + return !!(readl(hdmi_phy->regs + HDMI_CTL_1) & RG_HDMITX_PWR5V_O); +} + +static const struct regulator_ops mtk_hdmi_pwr5v_regulator_ops = { + .enable = mtk_hdmi_phy_pwr5v_enable, + .disable = mtk_hdmi_phy_pwr5v_disable, + .is_enabled = mtk_hdmi_phy_pwr5v_is_enabled +}; + +static const struct regulator_desc mtk_hdmi_phy_pwr5v_desc = { + .name = "hdmi-pwr5v", + .id = -1, + .n_voltages = 1, + .fixed_uV = 5000000, + .ops = &mtk_hdmi_pwr5v_regulator_ops, + .type = REGULATOR_VOLTAGE, + .owner = THIS_MODULE, +}; + struct mtk_hdmi_phy_conf mtk_hdmi_phy_8195_conf = { .flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE, + .hdmi_phy_regulator_desc = &mtk_hdmi_phy_pwr5v_desc, .hdmi_phy_clk_ops = &mtk_hdmi_pll_ops, .hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds, .hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds, diff --git a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h index 22a68dc9550c..e26caaf4d104 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h +++ b/drivers/phy/mediatek/phy-mtk-hdmi-mt8195.h @@ -103,6 +103,9 @@ #define HDMI_ANA_CTL 0x7c #define REG_ANA_HDMI20_FIFO_EN BIT(16) +#define HDMI_CTL_1 0xc4 +#define RG_HDMITX_PWR5V_O BIT(9) + #define HDMI_CTL_3 0xcc #define REG_HDMITXPLL_DIV GENMASK(4, 0) #define REG_HDMITX_REF_XTAL_SEL BIT(7) diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.c b/drivers/phy/mediatek/phy-mtk-hdmi.c index d2e824771f9d..52a7d525ff9b 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.c +++ b/drivers/phy/mediatek/phy-mtk-hdmi.c @@ -75,6 +75,28 @@ static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy, clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops; } +static int mtk_hdmi_phy_register_regulators(struct mtk_hdmi_phy *hdmi_phy) +{ + const struct regulator_desc *vreg_desc = hdmi_phy->conf->hdmi_phy_regulator_desc; + const struct regulator_init_data vreg_init_data = { + .constraints = { + .valid_ops_mask = REGULATOR_CHANGE_STATUS, + } + }; + struct regulator_config vreg_config = { + .dev = hdmi_phy->dev, + .driver_data = hdmi_phy, + .init_data = &vreg_init_data, + .of_node = hdmi_phy->dev->of_node + }; + + hdmi_phy->rdev = devm_regulator_register(hdmi_phy->dev, vreg_desc, &vreg_config); + if (IS_ERR(hdmi_phy->rdev)) + return PTR_ERR(hdmi_phy->rdev); + + return 0; +} + static int mtk_hdmi_phy_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -150,6 +172,12 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev) if (hdmi_phy->conf->pll_default_off) hdmi_phy->conf->hdmi_phy_disable_tmds(hdmi_phy); + if (hdmi_phy->conf->hdmi_phy_regulator_desc) { + ret = mtk_hdmi_phy_register_regulators(hdmi_phy); + if (ret) + return ret; + } + return of_clk_add_provider(dev->of_node, of_clk_src_simple_get, hdmi_phy->pll); } diff --git a/drivers/phy/mediatek/phy-mtk-hdmi.h b/drivers/phy/mediatek/phy-mtk-hdmi.h index 71c02d043485..99d917e0036a 100644 --- a/drivers/phy/mediatek/phy-mtk-hdmi.h +++ b/drivers/phy/mediatek/phy-mtk-hdmi.h @@ -13,6 +13,8 @@ #include <linux/module.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/regulator/driver.h> +#include <linux/regulator/machine.h> #include <linux/types.h> struct mtk_hdmi_phy; @@ -20,6 +22,7 @@ struct mtk_hdmi_phy; struct mtk_hdmi_phy_conf { unsigned long flags; bool pll_default_off; + const struct regulator_desc *hdmi_phy_regulator_desc; const struct clk_ops *hdmi_phy_clk_ops; void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy); void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy); @@ -32,6 +35,7 @@ struct mtk_hdmi_phy { struct mtk_hdmi_phy_conf *conf; struct clk *pll; struct clk_hw pll_hw; + struct regulator_dev *rdev; unsigned long pll_rate; unsigned char drv_imp_clk; unsigned char drv_imp_d2; diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c index 413f76e2d174..8dfdce605a90 100644 --- a/drivers/phy/phy-core.c +++ b/drivers/phy/phy-core.c @@ -749,8 +749,8 @@ EXPORT_SYMBOL_GPL(devm_phy_put); /** * of_phy_simple_xlate() - returns the phy instance from phy provider - * @dev: the PHY provider device - * @args: of_phandle_args (not used here) + * @dev: the PHY provider device (not used here) + * @args: of_phandle_args * * Intended to be used by phy provider for the common case where #phy-cells is * 0. For other cases where #phy-cells is greater than '0', the phy provider @@ -760,21 +760,14 @@ EXPORT_SYMBOL_GPL(devm_phy_put); struct phy *of_phy_simple_xlate(struct device *dev, const struct of_phandle_args *args) { - struct phy *phy; - struct class_dev_iter iter; - - class_dev_iter_init(&iter, &phy_class, NULL, NULL); - while ((dev = class_dev_iter_next(&iter))) { - phy = to_phy(dev); - if (args->np != phy->dev.of_node) - continue; + struct device *target_dev; - class_dev_iter_exit(&iter); - return phy; - } + target_dev = class_find_device_by_of_node(&phy_class, args->np); + if (!target_dev) + return ERR_PTR(-ENODEV); - class_dev_iter_exit(&iter); - return ERR_PTR(-ENODEV); + put_device(target_dev); + return to_phy(target_dev); } EXPORT_SYMBOL_GPL(of_phy_simple_xlate); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index 3bae39381fd0..b09fa00e9fe7 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -400,6 +400,57 @@ static const struct qmp_phy_init_tbl qmp_v3_usb3_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V3_PCS_RXEQTRAINING_RUN_TIME, 0x13), }; +static const struct qmp_phy_init_tbl sar2130p_usb3_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x2e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xd5), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE1, 0xb7), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE1, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE1_MODE0, 0xb7), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BIN_VCOCAL_CMP_CODE2_MODE0, 0x1e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x12), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MSB_MODE0, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xd5), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x05), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0x25), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_BUF_ENABLE, 0x0c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_CFG, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0x20), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_1, 0xb6), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_2, 0x4b), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_AUTO_GAIN_ADJ_CTRL_3, 0x37), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC, 0x0c), +}; + static const struct qmp_phy_init_tbl sm6350_usb3_rx_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V3_RX_UCDR_FASTLOCK_FO_GAIN, 0x0b), QMP_PHY_INIT_CFG(QSERDES_V3_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0f), @@ -1730,6 +1781,51 @@ static const struct qmp_combo_offsets qmp_combo_offsets_v5 = { .dp_dp_phy = 0x2200, }; +static const struct qmp_phy_cfg sar2130p_usb3dpphy_cfg = { + .offsets = &qmp_combo_offsets_v3, + + .serdes_tbl = sar2130p_usb3_serdes_tbl, + .serdes_tbl_num = ARRAY_SIZE(sar2130p_usb3_serdes_tbl), + .tx_tbl = sm8550_usb3_tx_tbl, + .tx_tbl_num = ARRAY_SIZE(sm8550_usb3_tx_tbl), + .rx_tbl = sm8550_usb3_rx_tbl, + .rx_tbl_num = ARRAY_SIZE(sm8550_usb3_rx_tbl), + .pcs_tbl = sm8550_usb3_pcs_tbl, + .pcs_tbl_num = ARRAY_SIZE(sm8550_usb3_pcs_tbl), + .pcs_usb_tbl = sm8550_usb3_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(sm8550_usb3_pcs_usb_tbl), + + .dp_serdes_tbl = qmp_v6_dp_serdes_tbl, + .dp_serdes_tbl_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl), + .dp_tx_tbl = qmp_v6_dp_tx_tbl, + .dp_tx_tbl_num = ARRAY_SIZE(qmp_v6_dp_tx_tbl), + + .serdes_tbl_rbr = qmp_v6_dp_serdes_tbl_rbr, + .serdes_tbl_rbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_rbr), + .serdes_tbl_hbr = qmp_v6_dp_serdes_tbl_hbr, + .serdes_tbl_hbr_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr), + .serdes_tbl_hbr2 = qmp_v6_dp_serdes_tbl_hbr2, + .serdes_tbl_hbr2_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr2), + .serdes_tbl_hbr3 = qmp_v6_dp_serdes_tbl_hbr3, + .serdes_tbl_hbr3_num = ARRAY_SIZE(qmp_v6_dp_serdes_tbl_hbr3), + + .swing_hbr_rbr = &qmp_dp_v5_voltage_swing_hbr_rbr, + .pre_emphasis_hbr_rbr = &qmp_dp_v6_pre_emphasis_hbr_rbr, + .swing_hbr3_hbr2 = &qmp_dp_v5_voltage_swing_hbr3_hbr2, + .pre_emphasis_hbr3_hbr2 = &qmp_dp_v5_pre_emphasis_hbr3_hbr2, + + .dp_aux_init = qmp_v4_dp_aux_init, + .configure_dp_tx = qmp_v4_configure_dp_tx, + .configure_dp_phy = qmp_v4_configure_dp_phy, + .calibrate_dp_phy = qmp_v4_calibrate_dp_phy, + + .regs = qmp_v6_usb3phy_regs_layout, + .reset_list = msm8996_usb3phy_reset_l, + .num_resets = ARRAY_SIZE(msm8996_usb3phy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), +}; + static const struct qmp_phy_cfg sc7180_usb3dpphy_cfg = { .offsets = &qmp_combo_offsets_v3, @@ -3768,6 +3864,10 @@ err_node_put: static const struct of_device_id qmp_combo_of_match_table[] = { { + .compatible = "qcom,sar2130p-qmp-usb3-dp-phy", + .data = &sar2130p_usb3dpphy_cfg, + }, + { .compatible = "qcom,sc7180-qmp-usb3-dp-phy", .data = &sc7180_usb3dpphy_cfg, }, diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index 873f2f9844c6..018bbb300830 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -728,6 +728,83 @@ static const struct qmp_phy_init_tbl ipq9574_gen3x2_pcie_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xc1), }; +static const struct qmp_phy_init_tbl qcs615_pcie_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CLKBUFLR_EN, 0x18), + QMP_PHY_INIT_CFG(QSERDES_COM_CLK_ENABLE1, 0x10), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TRIM, 0xf), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP_EN, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_MAP, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER1, 0xff), + QMP_PHY_INIT_CFG(QSERDES_COM_VCO_TUNE_TIMER2, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_COM_CMN_CONFIG, 0x6), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_IVCO, 0xf), + QMP_PHY_INIT_CFG(QSERDES_COM_HSCLK_SEL, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_SVS_MODE_CLK_SEL, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_CORE_CLK_EN, 0x20), + QMP_PHY_INIT_CFG(QSERDES_COM_CORECLK_DIV, 0xa), + QMP_PHY_INIT_CFG(QSERDES_COM_RESETSM_CNTRL, 0x20), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0x9), + QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_EN_SEL, 0x4), + QMP_PHY_INIT_CFG(QSERDES_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START3_MODE0, 0x3), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START2_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_COM_DIV_FRAC_START1_MODE0, 0x55), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP3_MODE0, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP2_MODE0, 0xd), + QMP_PHY_INIT_CFG(QSERDES_COM_LOCK_CMP1_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_COM_CLK_SELECT, 0x35), + QMP_PHY_INIT_CFG(QSERDES_COM_SYS_CLK_CTRL, 0x2), + QMP_PHY_INIT_CFG(QSERDES_COM_SYSCLK_BUF_ENABLE, 0x1f), + QMP_PHY_INIT_CFG(QSERDES_COM_CP_CTRL_MODE0, 0x4), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_COM_PLL_CCTRL_MODE0, 0x30), + QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN1_MODE0, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_INTEGLOOP_GAIN0_MODE0, 0x80), + QMP_PHY_INIT_CFG(QSERDES_COM_BIAS_EN_CTRL_BY_PSM, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_BG_TIMER, 0xa), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_EN_CENTER, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_PER2, 0x1), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER1, 0x2), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_ADJ_PER2, 0x0), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE1, 0x2f), + QMP_PHY_INIT_CFG(QSERDES_COM_SSC_STEP_SIZE2, 0x19), + QMP_PHY_INIT_CFG(QSERDES_COM_CLK_EP_DIV, 0x19), +}; + +static const struct qmp_phy_init_tbl qcs615_pcie_rx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_ENABLES, 0x1c), + QMP_PHY_INIT_CFG(QSERDES_RX_SIGDET_DEGLITCH_CNTRL, 0x14), + QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL2, 0x1), + QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL3, 0x0), + QMP_PHY_INIT_CFG(QSERDES_RX_RX_EQU_ADAPTOR_CNTRL4, 0xdb), + QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x4b), + QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN, 0x4), + QMP_PHY_INIT_CFG(QSERDES_RX_UCDR_SO_GAIN_HALF, 0x4), +}; + +static const struct qmp_phy_init_tbl qcs615_pcie_tx_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_TX_HIGHZ_TRANSCEIVEREN_BIAS_DRVR_EN, 0x45), + QMP_PHY_INIT_CFG(QSERDES_TX_LANE_MODE, 0x6), + QMP_PHY_INIT_CFG(QSERDES_TX_RES_CODE_LANE_OFFSET, 0x2), + QMP_PHY_INIT_CFG(QSERDES_TX_RCV_DETECT_LVL_2, 0x12), +}; + +static const struct qmp_phy_init_tbl qcs615_pcie_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V2_PCS_ENDPOINT_REFCLK_DRIVE, 0x4), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_OSC_DTCT_ACTIONS, 0x0), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_PWRUP_RESET_DLY_TIME_AUXCLK, 0x40), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_MSB, 0x0), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_LSB, 0x40), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME_AUXCLK_LSB, 0x0), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_LP_WAKEUP_DLY_TIME_AUXCLK, 0x40), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME, 0x73), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_SIGDET_CNTRL, 0x7), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_RX_SIGDET_LVL, 0x99), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_TXDEEMPH_M6DB_V0, 0x15), + QMP_PHY_INIT_CFG(QPHY_V2_PCS_TXDEEMPH_M3P5DB_V0, 0xe), +}; + static const struct qmp_phy_init_tbl sdm845_qmp_pcie_serdes_tbl[] = { QMP_PHY_INIT_CFG(QSERDES_V3_COM_BIAS_EN_CLKBUFLR_EN, 0x14), QMP_PHY_INIT_CFG(QSERDES_V3_COM_CLK_SELECT, 0x30), @@ -1773,7 +1850,7 @@ static const struct qmp_phy_init_tbl sdx55_qmp_pcie_rc_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_PCIE_OSC_DTCT_ACTIONS, 0x00), }; -static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_misc_tbl[] = { +static const struct qmp_phy_init_tbl sdx55_qmp_pcie_ep_pcs_lane1_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), }; @@ -1907,6 +1984,9 @@ static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_misc_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG2, 0x0d), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5, 0x02), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN, 0x2e), +}; + +static const struct qmp_phy_init_tbl sdx65_qmp_pcie_pcs_lane1_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), }; @@ -2582,8 +2662,6 @@ static const struct qmp_phy_init_tbl sa8775p_qmp_gen4_pcie_rc_pcs_misc_tbl[] = { static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_pcs_alt_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG4, 0x16), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_EQ_CONFIG5, 0x22), - QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2, 0x00), - QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2, 0x00), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_G3S2_PRE_GAIN, 0x2e), QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_RX_SIGDET_LVL, 0x66), }; @@ -2724,10 +2802,106 @@ static const struct qmp_phy_init_tbl sa8775p_qmp_gen4x2_pcie_ep_pcs_alt_tbl[] = QMP_PHY_INIT_CFG(QPHY_V5_20_PCS_INSIG_SW_CTRL7, 0x00), }; +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x31), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x4c), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_ENABLE1, 0x90), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0e), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x42), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x08), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x1a), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x82), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x68), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xea), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0xab), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0xaa), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x02), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_SELECT, 0x34), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC_3, 0x0f), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_LANE1_INSIG_SW_CTRL2, 0x01), + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_LANE1_INSIG_MX_CTRL2, 0x01), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_tx_tbl[] = { + QMP_PHY_INIT_CFG_LANE(QSERDES_V6_TX_BIST_MODE_LANENO, 0x00, 2), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB, 0x17), + QMP_PHY_INIT_CFG(QPHY_V6_PCS_G3S2_PRE_GAIN, 0x2e), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl[] = { + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x06), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x28), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x28), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x0d), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x00), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x42), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0xff), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x09), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x19), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE0, 0xfb), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE0, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN0_MODE1, 0xfb), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_INTEGLOOP_GAIN1_MODE1, 0x03), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_MODE, 0x14), + QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xa0), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB, 0x17), +}; + +static const struct qmp_phy_init_tbl sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_EQ_CONFIG1, 0x1e), + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG2, 0x14), + QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG4, 0x07), +}; + struct qmp_pcie_offsets { u16 serdes; u16 pcs; u16 pcs_misc; + u16 pcs_lane1; u16 tx; u16 rx; u16 tx2; @@ -2752,6 +2926,8 @@ struct qmp_phy_cfg_tbls { int pcs_num; const struct qmp_phy_init_tbl *pcs_misc; int pcs_misc_num; + const struct qmp_phy_init_tbl *pcs_lane1; + int pcs_lane1_num; const struct qmp_phy_init_tbl *ln_shrd; int ln_shrd_num; }; @@ -2811,6 +2987,7 @@ struct qmp_pcie { void __iomem *serdes; void __iomem *pcs; void __iomem *pcs_misc; + void __iomem *pcs_lane1; void __iomem *tx; void __iomem *rx; void __iomem *tx2; @@ -2927,6 +3104,7 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v4_20 = { .serdes = 0x1000, .pcs = 0x1200, .pcs_misc = 0x1600, + .pcs_lane1 = 0x1e00, .tx = 0x0000, .rx = 0x0200, .tx2 = 0x0800, @@ -2957,6 +3135,7 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v5_20 = { .serdes = 0x1000, .pcs = 0x1200, .pcs_misc = 0x1400, + .pcs_lane1 = 0x1e00, .tx = 0x0000, .rx = 0x0200, .tx2 = 0x0800, @@ -3132,6 +3311,31 @@ static const struct qmp_phy_cfg ipq9574_gen3x2_pciephy_cfg = { .pipe_clock_rate = 250000000, }; +static const struct qmp_phy_cfg qcs615_pciephy_cfg = { + .lanes = 1, + + .offsets = &qmp_pcie_offsets_v2, + + .tbls = { + .serdes = qcs615_pcie_serdes_tbl, + .serdes_num = ARRAY_SIZE(qcs615_pcie_serdes_tbl), + .tx = qcs615_pcie_tx_tbl, + .tx_num = ARRAY_SIZE(qcs615_pcie_tx_tbl), + .rx = qcs615_pcie_rx_tbl, + .rx_num = ARRAY_SIZE(qcs615_pcie_rx_tbl), + .pcs = qcs615_pcie_pcs_tbl, + .pcs_num = ARRAY_SIZE(qcs615_pcie_pcs_tbl), + }, + .reset_list = sdm845_pciephy_reset_l, + .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = pciephy_v2_regs_layout, + + .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, + .phy_status = PHYSTATUS, +}; + static const struct qmp_phy_cfg sdm845_qmp_pciephy_cfg = { .lanes = 1, @@ -3283,6 +3487,49 @@ static const struct qmp_phy_cfg msm8998_pciephy_cfg = { .skip_start_delay = true, }; +static const struct qmp_phy_cfg sar2130p_qmp_gen3x2_pciephy_cfg = { + .lanes = 2, + + .offsets = &qmp_pcie_offsets_v5, + + .tbls = { + .tx = sm8550_qmp_gen3x2_pcie_tx_tbl, + .tx_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_tx_tbl), + .rx = sm8550_qmp_gen3x2_pcie_rx_tbl, + .rx_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_rx_tbl), + .pcs = sm8550_qmp_gen3x2_pcie_pcs_tbl, + .pcs_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_pcs_tbl), + .pcs_lane1 = sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_pcs_lane1_tbl), + }, + .tbls_rc = &(const struct qmp_phy_cfg_tbls) { + .serdes = sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl, + .serdes_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_serdes_tbl), + .tx = sar2130p_qmp_gen3x2_pcie_rc_tx_tbl, + .tx_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_tx_tbl), + .pcs = sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl, + .pcs_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_rc_pcs_tbl), + .pcs_misc = sm8550_qmp_gen3x2_pcie_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sm8550_qmp_gen3x2_pcie_pcs_misc_tbl), + }, + .tbls_ep = &(const struct qmp_phy_cfg_tbls) { + .serdes = sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl, + .serdes_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_serdes_tbl), + .pcs = sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl, + .pcs_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_pcs_tbl), + .pcs_misc = sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl, + .pcs_misc_num = ARRAY_SIZE(sar2130p_qmp_gen3x2_pcie_ep_pcs_misc_tbl), + }, + .reset_list = sdm845_pciephy_reset_l, + .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), + .vreg_list = qmp_phy_vreg_l, + .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l), + .regs = pciephy_v5_regs_layout, + + .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL, + .phy_status = PHYSTATUS, +}; + static const struct qmp_phy_cfg sc8180x_pciephy_cfg = { .lanes = 2, @@ -3440,8 +3687,8 @@ static const struct qmp_phy_cfg sdx55_qmp_pciephy_cfg = { .tbls_ep = &(const struct qmp_phy_cfg_tbls) { .serdes = sdx55_qmp_pcie_ep_serdes_tbl, .serdes_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_serdes_tbl), - .pcs_misc = sdx55_qmp_pcie_ep_pcs_misc_tbl, - .pcs_misc_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_pcs_misc_tbl), + .pcs_lane1 = sdx55_qmp_pcie_ep_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sdx55_qmp_pcie_ep_pcs_lane1_tbl), }, .reset_list = sdm845_pciephy_reset_l, @@ -3540,6 +3787,8 @@ static const struct qmp_phy_cfg sdx65_qmp_pciephy_cfg = { .pcs_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_tbl), .pcs_misc = sdx65_qmp_pcie_pcs_misc_tbl, .pcs_misc_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_misc_tbl), + .pcs_lane1 = sdx65_qmp_pcie_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_lane1_tbl), }, .reset_list = sdm845_pciephy_reset_l, .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l), @@ -3739,6 +3988,8 @@ static const struct qmp_phy_cfg sa8775p_qmp_gen4x2_pciephy_cfg = { .pcs_num = ARRAY_SIZE(sa8775p_qmp_gen4x2_pcie_pcs_alt_tbl), .pcs_misc = sa8775p_qmp_gen4_pcie_pcs_misc_tbl, .pcs_misc_num = ARRAY_SIZE(sa8775p_qmp_gen4_pcie_pcs_misc_tbl), + .pcs_lane1 = sdx65_qmp_pcie_pcs_lane1_tbl, + .pcs_lane1_num = ARRAY_SIZE(sdx65_qmp_pcie_pcs_lane1_tbl), }, .tbls_rc = &(const struct qmp_phy_cfg_tbls) { @@ -3945,6 +4196,7 @@ static void qmp_pcie_init_registers(struct qmp_pcie *qmp, const struct qmp_phy_c void __iomem *rx2 = qmp->rx2; void __iomem *pcs = qmp->pcs; void __iomem *pcs_misc = qmp->pcs_misc; + void __iomem *pcs_lane1 = qmp->pcs_lane1; void __iomem *ln_shrd = qmp->ln_shrd; if (!tbls) @@ -3969,6 +4221,7 @@ static void qmp_pcie_init_registers(struct qmp_pcie *qmp, const struct qmp_phy_c qmp_configure(qmp->dev, pcs, tbls->pcs, tbls->pcs_num); qmp_configure(qmp->dev, pcs_misc, tbls->pcs_misc, tbls->pcs_misc_num); + qmp_configure(qmp->dev, pcs_lane1, tbls->pcs_lane1, tbls->pcs_lane1_num); if (cfg->lanes >= 4 && qmp->tcsr_4ln_config) { qmp_configure(qmp->dev, serdes, cfg->serdes_4ln_tbl, @@ -4420,6 +4673,14 @@ static int qmp_pcie_parse_dt_legacy(struct qmp_pcie *qmp, struct device_node *np } } + /* + * For all platforms where legacy bindings existed, PCS_LANE1 was + * mapped as a part of the PCS_MISC region. + */ + if (!IS_ERR(qmp->pcs_misc) && cfg->offsets->pcs_lane1 != 0) + qmp->pcs_lane1 = qmp->pcs_misc + + (cfg->offsets->pcs_lane1 - cfg->offsets->pcs_misc); + clk = devm_get_clk_from_child(dev, np, NULL); if (IS_ERR(clk)) { return dev_err_probe(dev, PTR_ERR(clk), @@ -4487,6 +4748,7 @@ static int qmp_pcie_parse_dt(struct qmp_pcie *qmp) qmp->serdes = base + offs->serdes; qmp->pcs = base + offs->pcs; qmp->pcs_misc = base + offs->pcs_misc; + qmp->pcs_lane1 = base + offs->pcs_lane1; qmp->tx = base + offs->tx; qmp->rx = base + offs->rx; @@ -4612,12 +4874,18 @@ static const struct of_device_id qmp_pcie_of_match_table[] = { .compatible = "qcom,msm8998-qmp-pcie-phy", .data = &msm8998_pciephy_cfg, }, { + .compatible = "qcom,qcs615-qmp-gen3x1-pcie-phy", + .data = &qcs615_pciephy_cfg, + }, { .compatible = "qcom,sa8775p-qmp-gen4x2-pcie-phy", .data = &sa8775p_qmp_gen4x2_pciephy_cfg, }, { .compatible = "qcom,sa8775p-qmp-gen4x4-pcie-phy", .data = &sa8775p_qmp_gen4x4_pciephy_cfg, }, { + .compatible = "qcom,sar2130p-qmp-gen3x2-pcie-phy", + .data = &sar2130p_qmp_gen3x2_pciephy_cfg, + }, { .compatible = "qcom,sc8180x-qmp-pcie-phy", .data = &sc8180x_pciephy_cfg, }, { diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h index ac872a9eff9a..ab892d1067c2 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v4_20.h @@ -13,7 +13,8 @@ #define QPHY_V4_20_PCS_PCIE_G4_RXEQEVAL_TIME 0x0f4 #define QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG2 0x0fc #define QPHY_V4_20_PCS_PCIE_G4_EQ_CONFIG5 0x108 -#define QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2 0x824 -#define QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2 0x828 + +#define QPHY_V4_20_PCS_LANE1_INSIG_SW_CTRL2 0x024 +#define QPHY_V4_20_PCS_LANE1_INSIG_MX_CTRL2 0x028 #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h index cdf8c04ea078..283d63c81593 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v5_20.h @@ -17,7 +17,8 @@ #define QPHY_V5_20_PCS_PCIE_G4_EQ_CONFIG5 0x108 #define QPHY_V5_20_PCS_PCIE_G4_PRE_GAIN 0x15c #define QPHY_V5_20_PCS_PCIE_RX_MARGINING_CONFIG3 0x184 -#define QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2 0xa24 -#define QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2 0xa28 + +#define QPHY_V5_20_PCS_LANE1_INSIG_SW_CTRL2 0x024 +#define QPHY_V5_20_PCS_LANE1_INSIG_MX_CTRL2 0x028 #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h index 0ca79333d942..45397cb3c0c6 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h @@ -14,4 +14,7 @@ #define QPHY_PCIE_V6_PCS_PCIE_ENDPOINT_REFCLK_DRIVE 0x20 #define QPHY_PCIE_V6_PCS_PCIE_OSC_DTCT_ACTIONS 0x94 +#define QPHY_PCIE_V6_PCS_LANE1_INSIG_SW_CTRL2 0x024 +#define QPHY_PCIE_V6_PCS_LANE1_INSIG_MX_CTRL2 0x028 + #endif diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h index bf36399d0057..1ecf4b5beba6 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v2.h @@ -34,6 +34,7 @@ #define QPHY_V2_PCS_USB_PCS_STATUS 0x17c /* USB */ #define QPHY_V2_PCS_PLL_LOCK_CHK_DLY_TIME_AUXCLK_LSB 0x1a8 #define QPHY_V2_PCS_OSC_DTCT_ACTIONS 0x1ac +#define QPHY_V2_PCS_SIGDET_CNTRL 0x1b0 #define QPHY_V2_PCS_RX_SIGDET_LVL 0x1d8 #define QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_LSB 0x1dc #define QPHY_V2_PCS_L1SS_WAKEUP_DLY_TIME_AUXCLK_MSB 0x1e0 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h index 08299d2b78f0..aa5afb921f12 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-v6.h @@ -17,6 +17,8 @@ #define QPHY_V6_PCS_LOCK_DETECT_CONFIG3 0x0cc #define QPHY_V6_PCS_LOCK_DETECT_CONFIG6 0x0d8 #define QPHY_V6_PCS_REFGEN_REQ_CONFIG1 0x0dc +#define QPHY_V6_PCS_G12S1_TXDEEMPH_M6DB 0x168 +#define QPHY_V6_PCS_G3S2_PRE_GAIN 0x170 #define QPHY_V6_PCS_RX_SIGDET_LVL 0x188 #define QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_L 0x190 #define QPHY_V6_PCS_RCVR_DTCT_DLY_P1U2_H 0x194 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h index 23ffcfae9efa..f47fdc9cecda 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-qserdes-txrx-v6.h @@ -6,6 +6,7 @@ #ifndef QCOM_PHY_QMP_QSERDES_TXRX_USB_V6_H_ #define QCOM_PHY_QMP_QSERDES_TXRX_USB_V6_H_ +#define QSERDES_V6_TX_BIST_MODE_LANENO 0x00 #define QSERDES_V6_TX_CLKBUF_ENABLE 0x08 #define QSERDES_V6_TX_TX_EMP_POST1_LVL 0x0c #define QSERDES_V6_TX_TX_DRV_LVL 0x14 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index c9c337840715..787721570457 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -2298,6 +2298,9 @@ err_node_put: static const struct of_device_id qmp_usb_of_match_table[] = { { + .compatible = "qcom,ipq5424-qmp-usb3-phy", + .data = &ipq9574_usb3phy_cfg, + }, { .compatible = "qcom,ipq6018-qmp-usb3-phy", .data = &ipq6018_usb3phy_cfg, }, { diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index c52655a383ce..1f5f7df14d5a 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -151,6 +151,34 @@ static const struct qusb2_phy_init_tbl ipq6018_init_tbl[] = { QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9F), }; +static const struct qusb2_phy_init_tbl ipq5424_init_tbl[] = { + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL, 0x14), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0x00), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0x53), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE4, 0xc3), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TUNE, 0x30), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL1, 0x79), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL2, 0x21), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE5, 0x00), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TEST2, 0x14), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TEST, 0x80), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9f), +}; + +static const struct qusb2_phy_init_tbl qcs615_init_tbl[] = { + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE1, 0xc8), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE2, 0xb3), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE3, 0x83), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TUNE4, 0xc0), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_TUNE, 0x30), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL1, 0x79), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_USER_CTL2, 0x21), + QUSB2_PHY_INIT_CFG_L(QUSB2PHY_PORT_TEST2, 0x14), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_AUTOPGM_CTL1, 0x9f), + QUSB2_PHY_INIT_CFG(QUSB2PHY_PLL_PWR_CTRL, 0x00), +}; + static const unsigned int ipq6018_regs_layout[] = { [QUSB2PHY_PLL_STATUS] = 0x38, [QUSB2PHY_PORT_TUNE1] = 0x80, @@ -331,6 +359,27 @@ static const struct qusb2_phy_cfg ipq6018_phy_cfg = { .autoresume_en = BIT(0), }; +static const struct qusb2_phy_cfg ipq5424_phy_cfg = { + .tbl = ipq5424_init_tbl, + .tbl_num = ARRAY_SIZE(ipq5424_init_tbl), + .regs = ipq6018_regs_layout, + + .disable_ctrl = POWER_DOWN, + .mask_core_ready = PLL_LOCKED, + .autoresume_en = BIT(0), +}; + +static const struct qusb2_phy_cfg qcs615_phy_cfg = { + .tbl = qcs615_init_tbl, + .tbl_num = ARRAY_SIZE(qcs615_init_tbl), + .regs = ipq6018_regs_layout, + + .disable_ctrl = (CLAMP_N_EN | FREEZIO_N | POWER_DOWN), + .mask_core_ready = PLL_LOCKED, + /* autoresume not used */ + .autoresume_en = BIT(0), +}; + static const struct qusb2_phy_cfg qusb2_v2_phy_cfg = { .tbl = qusb2_v2_init_tbl, .tbl_num = ARRAY_SIZE(qusb2_v2_init_tbl), @@ -905,6 +954,9 @@ static const struct phy_ops qusb2_phy_gen_ops = { static const struct of_device_id qusb2_phy_of_match_table[] = { { + .compatible = "qcom,ipq5424-qusb2-phy", + .data = &ipq5424_phy_cfg, + }, { .compatible = "qcom,ipq6018-qusb2-phy", .data = &ipq6018_phy_cfg, }, { @@ -923,6 +975,9 @@ static const struct of_device_id qusb2_phy_of_match_table[] = { .compatible = "qcom,msm8998-qusb2-phy", .data = &msm8998_phy_cfg, }, { + .compatible = "qcom,qcs615-qusb2-phy", + .data = &qcs615_phy_cfg, + }, { .compatible = "qcom,qcm2290-qusb2-phy", .data = &sm6115_phy_cfg, }, { diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c index 2eb3329ca23f..a1532ef8bbe9 100644 --- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c +++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c @@ -37,6 +37,10 @@ #define PHYREG8 0x1C #define PHYREG8_SSC_EN BIT(4) +#define PHYREG10 0x24 +#define PHYREG10_SSC_PCM_MASK GENMASK(3, 0) +#define PHYREG10_SSC_PCM_3500PPM 7 + #define PHYREG11 0x28 #define PHYREG11_SU_TRIM_0_7 0xF0 @@ -61,17 +65,26 @@ #define PHYREG16 0x3C #define PHYREG16_SSC_CNT_VALUE 0x5f +#define PHYREG17 0x40 + #define PHYREG18 0x44 #define PHYREG18_PLL_LOOP 0x32 +#define PHYREG21 0x50 +#define PHYREG21_RX_SQUELCH_VAL 0x0D + #define PHYREG27 0x6C #define PHYREG27_RX_TRIM_RK3588 0x4C +#define PHYREG30 0x74 + #define PHYREG32 0x7C #define PHYREG32_SSC_MASK GENMASK(7, 4) +#define PHYREG32_SSC_DIR_MASK GENMASK(5, 4) #define PHYREG32_SSC_DIR_SHIFT 4 #define PHYREG32_SSC_UPWARD 0 #define PHYREG32_SSC_DOWNWARD 1 +#define PHYREG32_SSC_OFFSET_MASK GENMASK(7, 6) #define PHYREG32_SSC_OFFSET_SHIFT 6 #define PHYREG32_SSC_OFFSET_500PPM 1 @@ -79,6 +92,7 @@ #define PHYREG33_PLL_KVCO_MASK GENMASK(4, 2) #define PHYREG33_PLL_KVCO_SHIFT 2 #define PHYREG33_PLL_KVCO_VALUE 2 +#define PHYREG33_PLL_KVCO_VALUE_RK3576 4 struct rockchip_combphy_priv; @@ -98,6 +112,7 @@ struct rockchip_combphy_grfcfg { struct combphy_reg pipe_rxterm_set; struct combphy_reg pipe_txelec_set; struct combphy_reg pipe_txcomp_set; + struct combphy_reg pipe_clk_24m; struct combphy_reg pipe_clk_25m; struct combphy_reg pipe_clk_100m; struct combphy_reg pipe_phymode_sel; @@ -584,6 +599,266 @@ static const struct rockchip_combphy_cfg rk3568_combphy_cfgs = { .combphy_cfg = rk3568_combphy_cfg, }; +static int rk3576_combphy_cfg(struct rockchip_combphy_priv *priv) +{ + const struct rockchip_combphy_grfcfg *cfg = priv->cfg->grfcfg; + unsigned long rate; + u32 val; + + switch (priv->type) { + case PHY_TYPE_PCIE: + /* Set SSC downward spread spectrum */ + val = FIELD_PREP(PHYREG32_SSC_MASK, PHYREG32_SSC_DOWNWARD); + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_pcie, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_pcie, true); + break; + + case PHY_TYPE_USB3: + /* Set SSC downward spread spectrum */ + val = FIELD_PREP(PHYREG32_SSC_MASK, PHYREG32_SSC_DOWNWARD); + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32); + + /* Enable adaptive CTLE for USB3.0 Rx */ + val = readl(priv->mmio + PHYREG15); + val |= PHYREG15_CTLE_EN; + writel(val, priv->mmio + PHYREG15); + + /* Set PLL KVCO fine tuning signals */ + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, BIT(3), PHYREG33); + + /* Set PLL LPF R1 to su_trim[10:7]=1001 */ + writel(PHYREG12_PLL_LPF_ADJ_VALUE, priv->mmio + PHYREG12); + + /* Set PLL input clock divider 1/2 */ + val = FIELD_PREP(PHYREG6_PLL_DIV_MASK, PHYREG6_PLL_DIV_2); + rockchip_combphy_updatel(priv, PHYREG6_PLL_DIV_MASK, val, PHYREG6); + + /* Set PLL loop divider */ + writel(PHYREG18_PLL_LOOP, priv->mmio + PHYREG18); + + /* Set PLL KVCO to min and set PLL charge pump current to max */ + writel(PHYREG11_SU_TRIM_0_7, priv->mmio + PHYREG11); + + /* Set Rx squelch input filler bandwidth */ + writel(PHYREG21_RX_SQUELCH_VAL, priv->mmio + PHYREG21); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txcomp_sel, false); + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_txelec_sel, false); + rockchip_combphy_param_write(priv->phy_grf, &cfg->usb_mode_set, true); + break; + + case PHY_TYPE_SATA: + /* Enable adaptive CTLE for SATA Rx */ + val = readl(priv->mmio + PHYREG15); + val |= PHYREG15_CTLE_EN; + writel(val, priv->mmio + PHYREG15); + + /* Set tx_rterm = 50 ohm and rx_rterm = 43.5 ohm */ + val = PHYREG7_TX_RTERM_50OHM << PHYREG7_TX_RTERM_SHIFT; + val |= PHYREG7_RX_RTERM_44OHM << PHYREG7_RX_RTERM_SHIFT; + writel(val, priv->mmio + PHYREG7); + + rockchip_combphy_param_write(priv->phy_grf, &cfg->con0_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con1_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con2_for_sata, true); + rockchip_combphy_param_write(priv->phy_grf, &cfg->con3_for_sata, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con0_for_sata, true); + rockchip_combphy_param_write(priv->pipe_grf, &cfg->pipe_con1_for_sata, true); + break; + + default: + dev_err(priv->dev, "incompatible PHY type\n"); + return -EINVAL; + } + + rate = clk_get_rate(priv->refclk); + + switch (rate) { + case REF_CLOCK_24MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_24m, true); + if (priv->type == PHY_TYPE_USB3 || priv->type == PHY_TYPE_SATA) { + /* Set ssc_cnt[9:0]=0101111101 & 31.5KHz */ + val = FIELD_PREP(PHYREG15_SSC_CNT_MASK, PHYREG15_SSC_CNT_VALUE); + rockchip_combphy_updatel(priv, PHYREG15_SSC_CNT_MASK, + val, PHYREG15); + + writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16); + } else if (priv->type == PHY_TYPE_PCIE) { + /* PLL KVCO tuning fine */ + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + val, PHYREG33); + + /* Set up rx_pck invert and rx msb to disable */ + writel(0x00, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], PLL LPF R1 adujst bits[9:7]=3'b011 + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x02, priv->mmio + PHYREG12); + writel(0x57, priv->mmio + PHYREG14); + + writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16); + } + break; + + case REF_CLOCK_25MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_25m, true); + break; + + case REF_CLOCK_100MHz: + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_100m, true); + if (priv->type == PHY_TYPE_PCIE) { + /* gate_tx_pck_sel length select work for L1SS */ + writel(0xc0, priv->mmio + PHYREG30); + + /* PLL KVCO tuning fine */ + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + val, PHYREG33); + + /* Set up rx_trim: PLL LPF C1 85pf R1 1.25kohm */ + writel(0x4c, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], bypass PLL loop divider code, and + * PLL LPF R1 adujst bits[9:7]=3'b101 + * su_trim[23:16], CKRCV adjust + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x43, priv->mmio + PHYREG12); + writel(0x88, priv->mmio + PHYREG13); + writel(0x56, priv->mmio + PHYREG14); + } else if (priv->type == PHY_TYPE_SATA) { + /* downward spread spectrum +500ppm */ + val = FIELD_PREP(PHYREG32_SSC_DIR_MASK, PHYREG32_SSC_DOWNWARD); + val |= FIELD_PREP(PHYREG32_SSC_OFFSET_MASK, PHYREG32_SSC_OFFSET_500PPM); + rockchip_combphy_updatel(priv, PHYREG32_SSC_MASK, val, PHYREG32); + + /* ssc ppm adjust to 3500ppm */ + rockchip_combphy_updatel(priv, PHYREG10_SSC_PCM_MASK, + PHYREG10_SSC_PCM_3500PPM, + PHYREG10); + } + break; + + default: + dev_err(priv->dev, "Unsupported rate: %lu\n", rate); + return -EINVAL; + } + + if (priv->ext_refclk) { + rockchip_combphy_param_write(priv->phy_grf, &cfg->pipe_clk_ext, true); + if (priv->type == PHY_TYPE_PCIE && rate == REF_CLOCK_100MHz) { + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + rockchip_combphy_updatel(priv, PHYREG33_PLL_KVCO_MASK, + val, PHYREG33); + + /* Set up rx_trim: PLL LPF C1 85pf R1 2.5kohm */ + writel(0x0c, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], bypass PLL loop divider code, and + * PLL LPF R1 adujst bits[9:7]=3'b101. + * su_trim[23:16], CKRCV adjust + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x43, priv->mmio + PHYREG12); + writel(0x88, priv->mmio + PHYREG13); + writel(0x56, priv->mmio + PHYREG14); + } + } + + if (priv->enable_ssc) { + val = readl(priv->mmio + PHYREG8); + val |= PHYREG8_SSC_EN; + writel(val, priv->mmio + PHYREG8); + + if (priv->type == PHY_TYPE_PCIE && rate == REF_CLOCK_24MHz) { + /* Set PLL loop divider */ + writel(0x00, priv->mmio + PHYREG17); + writel(PHYREG18_PLL_LOOP, priv->mmio + PHYREG18); + + /* Set up rx_pck invert and rx msb to disable */ + writel(0x00, priv->mmio + PHYREG27); + + /* + * Set up SU adjust signal: + * su_trim[7:0], PLL KVCO adjust bits[2:0] to min + * su_trim[15:8], PLL LPF R1 adujst bits[9:7]=3'b101 + * su_trim[23:16], CKRCV adjust + * su_trim[31:24], CKDRV adjust + */ + writel(0x90, priv->mmio + PHYREG11); + writel(0x02, priv->mmio + PHYREG12); + writel(0x08, priv->mmio + PHYREG13); + writel(0x57, priv->mmio + PHYREG14); + writel(0x40, priv->mmio + PHYREG15); + + writel(PHYREG16_SSC_CNT_VALUE, priv->mmio + PHYREG16); + + val = FIELD_PREP(PHYREG33_PLL_KVCO_MASK, PHYREG33_PLL_KVCO_VALUE_RK3576); + writel(val, priv->mmio + PHYREG33); + } + } + + return 0; +} + +static const struct rockchip_combphy_grfcfg rk3576_combphy_grfcfgs = { + /* pipe-phy-grf */ + .pcie_mode_set = { 0x0000, 5, 0, 0x00, 0x11 }, + .usb_mode_set = { 0x0000, 5, 0, 0x00, 0x04 }, + .pipe_rxterm_set = { 0x0000, 12, 12, 0x00, 0x01 }, + .pipe_txelec_set = { 0x0004, 1, 1, 0x00, 0x01 }, + .pipe_txcomp_set = { 0x0004, 4, 4, 0x00, 0x01 }, + .pipe_clk_24m = { 0x0004, 14, 13, 0x00, 0x00 }, + .pipe_clk_25m = { 0x0004, 14, 13, 0x00, 0x01 }, + .pipe_clk_100m = { 0x0004, 14, 13, 0x00, 0x02 }, + .pipe_phymode_sel = { 0x0008, 1, 1, 0x00, 0x01 }, + .pipe_rate_sel = { 0x0008, 2, 2, 0x00, 0x01 }, + .pipe_rxterm_sel = { 0x0008, 8, 8, 0x00, 0x01 }, + .pipe_txelec_sel = { 0x0008, 12, 12, 0x00, 0x01 }, + .pipe_txcomp_sel = { 0x0008, 15, 15, 0x00, 0x01 }, + .pipe_clk_ext = { 0x000c, 9, 8, 0x02, 0x01 }, + .pipe_phy_status = { 0x0034, 6, 6, 0x01, 0x00 }, + .con0_for_pcie = { 0x0000, 15, 0, 0x00, 0x1000 }, + .con1_for_pcie = { 0x0004, 15, 0, 0x00, 0x0000 }, + .con2_for_pcie = { 0x0008, 15, 0, 0x00, 0x0101 }, + .con3_for_pcie = { 0x000c, 15, 0, 0x00, 0x0200 }, + .con0_for_sata = { 0x0000, 15, 0, 0x00, 0x0129 }, + .con1_for_sata = { 0x0004, 15, 0, 0x00, 0x0000 }, + .con2_for_sata = { 0x0008, 15, 0, 0x00, 0x80c1 }, + .con3_for_sata = { 0x000c, 15, 0, 0x00, 0x0407 }, + /* php-grf */ + .pipe_con0_for_sata = { 0x001C, 2, 0, 0x00, 0x2 }, + .pipe_con1_for_sata = { 0x0020, 2, 0, 0x00, 0x2 }, +}; + +static const struct rockchip_combphy_cfg rk3576_combphy_cfgs = { + .num_phys = 2, + .phy_ids = { + 0x2b050000, + 0x2b060000 + }, + .grfcfg = &rk3576_combphy_grfcfgs, + .combphy_cfg = rk3576_combphy_cfg, +}; + static int rk3588_combphy_cfg(struct rockchip_combphy_priv *priv) { const struct rockchip_combphy_grfcfg *cfg = priv->cfg->grfcfg; @@ -776,6 +1051,10 @@ static const struct of_device_id rockchip_combphy_of_match[] = { .data = &rk3568_combphy_cfgs, }, { + .compatible = "rockchip,rk3576-naneng-combphy", + .data = &rk3576_combphy_cfgs, + }, + { .compatible = "rockchip,rk3588-naneng-combphy", .data = &rk3588_combphy_cfgs, }, diff --git a/drivers/phy/rockchip/phy-rockchip-pcie.c b/drivers/phy/rockchip/phy-rockchip-pcie.c index 51cc5ece0e63..bd44af36c67a 100644 --- a/drivers/phy/rockchip/phy-rockchip-pcie.c +++ b/drivers/phy/rockchip/phy-rockchip-pcie.c @@ -124,7 +124,7 @@ static int rockchip_pcie_phy_power_off(struct phy *phy) struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); int err = 0; - mutex_lock(&rk_phy->pcie_mutex); + guard(mutex)(&rk_phy->pcie_mutex); regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_laneoff, @@ -132,27 +132,22 @@ static int rockchip_pcie_phy_power_off(struct phy *phy) PHY_LANE_IDLE_MASK, PHY_LANE_IDLE_A_SHIFT + inst->index)); - if (--rk_phy->pwr_cnt) - goto err_out; + if (--rk_phy->pwr_cnt) { + return 0; + } err = reset_control_assert(rk_phy->phy_rst); if (err) { dev_err(&phy->dev, "assert phy_rst err %d\n", err); - goto err_restore; + rk_phy->pwr_cnt++; + regmap_write(rk_phy->reg_base, + rk_phy->phy_data->pcie_laneoff, + HIWORD_UPDATE(!PHY_LANE_IDLE_OFF, + PHY_LANE_IDLE_MASK, + PHY_LANE_IDLE_A_SHIFT + inst->index)); + return err; } -err_out: - mutex_unlock(&rk_phy->pcie_mutex); - return 0; - -err_restore: - rk_phy->pwr_cnt++; - regmap_write(rk_phy->reg_base, - rk_phy->phy_data->pcie_laneoff, - HIWORD_UPDATE(!PHY_LANE_IDLE_OFF, - PHY_LANE_IDLE_MASK, - PHY_LANE_IDLE_A_SHIFT + inst->index)); - mutex_unlock(&rk_phy->pcie_mutex); return err; } @@ -162,17 +157,18 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); int err = 0; u32 status; - unsigned long timeout; - mutex_lock(&rk_phy->pcie_mutex); + guard(mutex)(&rk_phy->pcie_mutex); - if (rk_phy->pwr_cnt++) - goto err_out; + if (rk_phy->pwr_cnt++) { + return 0; + } err = reset_control_deassert(rk_phy->phy_rst); if (err) { dev_err(&phy->dev, "deassert phy_rst err %d\n", err); - goto err_pwr_cnt; + rk_phy->pwr_cnt--; + return err; } regmap_write(rk_phy->reg_base, rk_phy->phy_data->pcie_conf, @@ -191,21 +187,11 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) * so we make it large enough here. And we use loop-break * method which should not be harmful. */ - timeout = jiffies + msecs_to_jiffies(1000); - - err = -EINVAL; - while (time_before(jiffies, timeout)) { - regmap_read(rk_phy->reg_base, - rk_phy->phy_data->pcie_status, - &status); - if (status & PHY_PLL_LOCKED) { - dev_dbg(&phy->dev, "pll locked!\n"); - err = 0; - break; - } - msleep(20); - } - + err = regmap_read_poll_timeout(rk_phy->reg_base, + rk_phy->phy_data->pcie_status, + status, + status & PHY_PLL_LOCKED, + 200, 100000); if (err) { dev_err(&phy->dev, "pll lock timeout!\n"); goto err_pll_lock; @@ -214,19 +200,11 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) phy_wr_cfg(rk_phy, PHY_CFG_CLK_TEST, PHY_CFG_SEPE_RATE); phy_wr_cfg(rk_phy, PHY_CFG_CLK_SCC, PHY_CFG_PLL_100M); - err = -ETIMEDOUT; - while (time_before(jiffies, timeout)) { - regmap_read(rk_phy->reg_base, - rk_phy->phy_data->pcie_status, - &status); - if (!(status & PHY_PLL_OUTPUT)) { - dev_dbg(&phy->dev, "pll output enable done!\n"); - err = 0; - break; - } - msleep(20); - } - + err = regmap_read_poll_timeout(rk_phy->reg_base, + rk_phy->phy_data->pcie_status, + status, + !(status & PHY_PLL_OUTPUT), + 200, 100000); if (err) { dev_err(&phy->dev, "pll output enable timeout!\n"); goto err_pll_lock; @@ -236,33 +214,22 @@ static int rockchip_pcie_phy_power_on(struct phy *phy) HIWORD_UPDATE(PHY_CFG_PLL_LOCK, PHY_CFG_ADDR_MASK, PHY_CFG_ADDR_SHIFT)); - err = -EINVAL; - while (time_before(jiffies, timeout)) { - regmap_read(rk_phy->reg_base, - rk_phy->phy_data->pcie_status, - &status); - if (status & PHY_PLL_LOCKED) { - dev_dbg(&phy->dev, "pll relocked!\n"); - err = 0; - break; - } - msleep(20); - } + err = regmap_read_poll_timeout(rk_phy->reg_base, + rk_phy->phy_data->pcie_status, + status, + status & PHY_PLL_LOCKED, + 200, 100000); if (err) { dev_err(&phy->dev, "pll relock timeout!\n"); goto err_pll_lock; } -err_out: - mutex_unlock(&rk_phy->pcie_mutex); - return 0; + return err; err_pll_lock: reset_control_assert(rk_phy->phy_rst); -err_pwr_cnt: rk_phy->pwr_cnt--; - mutex_unlock(&rk_phy->pcie_mutex); return err; } @@ -272,33 +239,19 @@ static int rockchip_pcie_phy_init(struct phy *phy) struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); int err = 0; - mutex_lock(&rk_phy->pcie_mutex); - - if (rk_phy->init_cnt++) - goto err_out; + guard(mutex)(&rk_phy->pcie_mutex); - err = clk_prepare_enable(rk_phy->clk_pciephy_ref); - if (err) { - dev_err(&phy->dev, "Fail to enable pcie ref clock.\n"); - goto err_refclk; + if (rk_phy->init_cnt++) { + return 0; } err = reset_control_assert(rk_phy->phy_rst); if (err) { dev_err(&phy->dev, "assert phy_rst err %d\n", err); - goto err_reset; + rk_phy->init_cnt--; + return err; } -err_out: - mutex_unlock(&rk_phy->pcie_mutex); - return 0; - -err_reset: - - clk_disable_unprepare(rk_phy->clk_pciephy_ref); -err_refclk: - rk_phy->init_cnt--; - mutex_unlock(&rk_phy->pcie_mutex); return err; } @@ -307,15 +260,12 @@ static int rockchip_pcie_phy_exit(struct phy *phy) struct phy_pcie_instance *inst = phy_get_drvdata(phy); struct rockchip_pcie_phy *rk_phy = to_pcie_phy(inst); - mutex_lock(&rk_phy->pcie_mutex); + guard(mutex)(&rk_phy->pcie_mutex); if (--rk_phy->init_cnt) goto err_init_cnt; - clk_disable_unprepare(rk_phy->clk_pciephy_ref); - err_init_cnt: - mutex_unlock(&rk_phy->pcie_mutex); return 0; } @@ -371,18 +321,14 @@ static int rockchip_pcie_phy_probe(struct platform_device *pdev) mutex_init(&rk_phy->pcie_mutex); rk_phy->phy_rst = devm_reset_control_get(dev, "phy"); - if (IS_ERR(rk_phy->phy_rst)) { - if (PTR_ERR(rk_phy->phy_rst) != -EPROBE_DEFER) - dev_err(dev, - "missing phy property for reset controller\n"); - return PTR_ERR(rk_phy->phy_rst); - } - - rk_phy->clk_pciephy_ref = devm_clk_get(dev, "refclk"); - if (IS_ERR(rk_phy->clk_pciephy_ref)) { - dev_err(dev, "refclk not found.\n"); - return PTR_ERR(rk_phy->clk_pciephy_ref); - } + if (IS_ERR(rk_phy->phy_rst)) + return dev_err_probe(&pdev->dev, PTR_ERR(rk_phy->phy_rst), + "missing phy property for reset controller\n"); + + rk_phy->clk_pciephy_ref = devm_clk_get_enabled(dev, "refclk"); + if (IS_ERR(rk_phy->clk_pciephy_ref)) + return dev_err_probe(&pdev->dev, PTR_ERR(rk_phy->clk_pciephy_ref), + "failed to get phyclk\n"); /* parse #phy-cells to see if it's legacy PHY model */ if (of_property_read_u32(dev->of_node, "#phy-cells", &phy_num)) diff --git a/drivers/phy/rockchip/phy-rockchip-typec.c b/drivers/phy/rockchip/phy-rockchip-typec.c index 122ae0fdc785..d9701b6106d5 100644 --- a/drivers/phy/rockchip/phy-rockchip-typec.c +++ b/drivers/phy/rockchip/phy-rockchip-typec.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd + * Copyright (C) Rockchip Electronics Co., Ltd. * Author: Chris Zhong <zyw@rock-chips.com> * Kever Yang <kever.yang@rock-chips.com> * diff --git a/drivers/phy/samsung/Kconfig b/drivers/phy/samsung/Kconfig index f10afa3d7ff5..e2330b0894d6 100644 --- a/drivers/phy/samsung/Kconfig +++ b/drivers/phy/samsung/Kconfig @@ -33,6 +33,7 @@ config PHY_SAMSUNG_UFS tristate "Exynos SoC series UFS PHY driver" depends on OF && (ARCH_EXYNOS || COMPILE_TEST) select GENERIC_PHY + select MFD_SYSCON help Enable this to support the Samsung Exynos SoC UFS PHY driver for Samsung Exynos SoCs. This driver provides the interface for UFS host diff --git a/drivers/phy/samsung/phy-samsung-ufs.c b/drivers/phy/samsung/phy-samsung-ufs.c index 6c5d41552649..8e9ccd39f97e 100644 --- a/drivers/phy/samsung/phy-samsung-ufs.c +++ b/drivers/phy/samsung/phy-samsung-ufs.c @@ -13,11 +13,11 @@ #include <linux/of.h> #include <linux/io.h> #include <linux/iopoll.h> +#include <linux/mfd/syscon.h> #include <linux/module.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> #include <linux/regmap.h> -#include <linux/soc/samsung/exynos-pmu.h> #include "phy-samsung-ufs.h" @@ -268,8 +268,8 @@ static int samsung_ufs_phy_probe(struct platform_device *pdev) goto out; } - phy->reg_pmu = exynos_get_pmu_regmap_by_phandle(dev->of_node, - "samsung,pmu-syscon"); + phy->reg_pmu = syscon_regmap_lookup_by_phandle(dev->of_node, + "samsung,pmu-syscon"); if (IS_ERR(phy->reg_pmu)) { err = PTR_ERR(phy->reg_pmu); dev_err(dev, "failed syscon remap for pmu\n"); diff --git a/drivers/phy/tegra/Kconfig b/drivers/phy/tegra/Kconfig index c591c958f1eb..f30cfb42b210 100644 --- a/drivers/phy/tegra/Kconfig +++ b/drivers/phy/tegra/Kconfig @@ -13,7 +13,8 @@ config PHY_TEGRA_XUSB config PHY_TEGRA194_P2U tristate "NVIDIA Tegra194 PIPE2UPHY PHY driver" - depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on ARCH_TEGRA_194_SOC || ARCH_TEGRA_234_SOC || COMPILE_TEST select GENERIC_PHY help - Enable this to support the P2U (PIPE to UPHY) that is part of Tegra 19x SOCs. + Enable this to support the P2U (PIPE to UPHY) that is part of Tegra 19x + and 234 SOCs. diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index 0b13d7f17b32..42547f64453e 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -89,12 +89,12 @@ static void pinconf_generic_dump_one(struct pinctrl_dev *pctldev, seq_puts(s, items[i].display); /* Print unit if available */ if (items[i].has_arg) { - seq_printf(s, " (0x%x", - pinconf_to_config_argument(config)); + u32 val = pinconf_to_config_argument(config); + if (items[i].format) - seq_printf(s, " %s)", items[i].format); + seq_printf(s, " (%u %s)", val, items[i].format); else - seq_puts(s, ")"); + seq_printf(s, " (0x%x)", val); } } } diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index 0d6c2027d4c1..d73004b4a45e 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -42,7 +42,7 @@ #define CY8C95X0_PORTSEL 0x18 /* Port settings, write PORTSEL first */ #define CY8C95X0_INTMASK 0x19 -#define CY8C95X0_PWMSEL 0x1A +#define CY8C95X0_SELPWM 0x1A #define CY8C95X0_INVERT 0x1B #define CY8C95X0_DIRECTION 0x1C /* Drive mode register change state on writing '1' */ @@ -328,14 +328,14 @@ static int cypress_get_pin_mask(struct cy8c95x0_pinctrl *chip, unsigned int pin) static bool cy8c95x0_readable_register(struct device *dev, unsigned int reg) { /* - * Only 12 registers are present per port (see Table 6 in the - * datasheet). + * Only 12 registers are present per port (see Table 6 in the datasheet). */ - if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) < 12) - return true; + if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) >= 12) + return false; switch (reg) { case 0x24 ... 0x27: + case 0x31 ... 0x3f: return false; default: return true; @@ -344,8 +344,11 @@ static bool cy8c95x0_readable_register(struct device *dev, unsigned int reg) static bool cy8c95x0_writeable_register(struct device *dev, unsigned int reg) { - if (reg >= CY8C95X0_VIRTUAL) - return true; + /* + * Only 12 registers are present per port (see Table 6 in the datasheet). + */ + if (reg >= CY8C95X0_VIRTUAL && (reg % MUXED_STRIDE) >= 12) + return false; switch (reg) { case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7): @@ -353,6 +356,7 @@ static bool cy8c95x0_writeable_register(struct device *dev, unsigned int reg) case CY8C95X0_DEVID: return false; case 0x24 ... 0x27: + case 0x31 ... 0x3f: return false; default: return true; @@ -365,8 +369,8 @@ static bool cy8c95x0_volatile_register(struct device *dev, unsigned int reg) case CY8C95X0_INPUT_(0) ... CY8C95X0_INPUT_(7): case CY8C95X0_INTSTATUS_(0) ... CY8C95X0_INTSTATUS_(7): case CY8C95X0_INTMASK: + case CY8C95X0_SELPWM: case CY8C95X0_INVERT: - case CY8C95X0_PWMSEL: case CY8C95X0_DIRECTION: case CY8C95X0_DRV_PU: case CY8C95X0_DRV_PD: @@ -395,7 +399,7 @@ static bool cy8c95x0_muxed_register(unsigned int reg) { switch (reg) { case CY8C95X0_INTMASK: - case CY8C95X0_PWMSEL: + case CY8C95X0_SELPWM: case CY8C95X0_INVERT: case CY8C95X0_DIRECTION: case CY8C95X0_DRV_PU: @@ -466,7 +470,11 @@ static const struct regmap_config cy8c9520_i2c_regmap = { .max_register = 0, /* Updated at runtime */ .num_reg_defaults_raw = 0, /* Updated at runtime */ .use_single_read = true, /* Workaround for regcache bug */ +#if IS_ENABLED(CONFIG_DEBUG_PINCTRL) + .disable_locking = false, +#else .disable_locking = true, +#endif }; static inline int cy8c95x0_regmap_update_bits_base(struct cy8c95x0_pinctrl *chip, @@ -789,7 +797,7 @@ static int cy8c95x0_gpio_get_pincfg(struct cy8c95x0_pinctrl *chip, reg = CY8C95X0_DIRECTION; break; case PIN_CONFIG_MODE_PWM: - reg = CY8C95X0_PWMSEL; + reg = CY8C95X0_SELPWM; break; case PIN_CONFIG_OUTPUT: reg = CY8C95X0_OUTPUT; @@ -868,7 +876,7 @@ static int cy8c95x0_gpio_set_pincfg(struct cy8c95x0_pinctrl *chip, reg = CY8C95X0_DRV_PP_FAST; break; case PIN_CONFIG_MODE_PWM: - reg = CY8C95X0_PWMSEL; + reg = CY8C95X0_SELPWM; break; case PIN_CONFIG_OUTPUT_ENABLE: return cy8c95x0_pinmux_direction(chip, off, !arg); @@ -1153,7 +1161,7 @@ static void cy8c95x0_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file * bitmap_zero(mask, MAX_LINE); __set_bit(pin, mask); - if (cy8c95x0_read_regs_mask(chip, CY8C95X0_PWMSEL, pwm, mask)) { + if (cy8c95x0_read_regs_mask(chip, CY8C95X0_SELPWM, pwm, mask)) { seq_puts(s, "not available"); return; } @@ -1198,7 +1206,7 @@ static int cy8c95x0_set_mode(struct cy8c95x0_pinctrl *chip, unsigned int off, bo u8 port = cypress_get_port(chip, off); u8 bit = cypress_get_pin_mask(chip, off); - return cy8c95x0_regmap_write_bits(chip, CY8C95X0_PWMSEL, port, bit, mode ? bit : 0); + return cy8c95x0_regmap_write_bits(chip, CY8C95X0_SELPWM, port, bit, mode ? bit : 0); } static int cy8c95x0_pinmux_mode(struct cy8c95x0_pinctrl *chip, @@ -1347,7 +1355,7 @@ static int cy8c95x0_irq_setup(struct cy8c95x0_pinctrl *chip, int irq) ret = devm_request_threaded_irq(chip->dev, irq, NULL, cy8c95x0_irq_handler, - IRQF_ONESHOT | IRQF_SHARED | IRQF_TRIGGER_HIGH, + IRQF_ONESHOT | IRQF_SHARED, dev_name(chip->dev), chip); if (ret) { dev_err(chip->dev, "failed to request irq %d\n", irq); @@ -1438,15 +1446,15 @@ static int cy8c95x0_probe(struct i2c_client *client) switch (chip->tpin) { case 20: strscpy(chip->name, cy8c95x0_id[0].name); - regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 3 * MUXED_STRIDE; + regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 3 * MUXED_STRIDE - 1; break; case 40: strscpy(chip->name, cy8c95x0_id[1].name); - regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 6 * MUXED_STRIDE; + regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 6 * MUXED_STRIDE - 1; break; case 60: strscpy(chip->name, cy8c95x0_id[2].name); - regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 8 * MUXED_STRIDE; + regmap_range_conf.range_max = CY8C95X0_VIRTUAL + 8 * MUXED_STRIDE - 1; break; default: return -ENODEV; diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index dfb5d4b8c046..30bd366d7b58 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1121,7 +1121,7 @@ static int ideapad_dytc_profile_init(struct ideapad_private *priv) /* Create platform_profile structure and register */ priv->dytc->ppdev = devm_platform_profile_register(&priv->platform_device->dev, - "ideapad-laptop", &priv->dytc, + "ideapad-laptop", priv->dytc, &dytc_profile_ops); if (IS_ERR(priv->dytc->ppdev)) { err = PTR_ERR(priv->dytc->ppdev); diff --git a/drivers/platform/x86/intel/ifs/ifs.h b/drivers/platform/x86/intel/ifs/ifs.h index 5c3c0dfa1bf8..f369fb0d3d82 100644 --- a/drivers/platform/x86/intel/ifs/ifs.h +++ b/drivers/platform/x86/intel/ifs/ifs.h @@ -23,12 +23,14 @@ * IFS Image * --------- * - * Intel provides a firmware file containing the scan tests via - * github [#f1]_. Similar to microcode there is a separate file for each + * Intel provides firmware files containing the scan tests via the webpage [#f1]_. + * Look under "In-Field Scan Test Images Download" section towards the + * end of the page. Similar to microcode, there are separate files for each * family-model-stepping. IFS Images are not applicable for some test types. * Wherever applicable the sysfs directory would provide a "current_batch" file * (see below) for loading the image. * + * .. [#f1] https://intel.com/InFieldScan * * IFS Image Loading * ----------------- @@ -125,9 +127,6 @@ * 2) Hardware allows for some number of cores to be tested in parallel. * The driver does not make use of this, it only tests one core at a time. * - * .. [#f1] https://github.com/intel/TBD - * - * * Structural Based Functional Test at Field (SBAF): * ------------------------------------------------- * diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c index 31015ebe20d8..092252eb95a8 100644 --- a/drivers/platform/x86/intel/int3472/discrete.c +++ b/drivers/platform/x86/intel/int3472/discrete.c @@ -2,6 +2,7 @@ /* Author: Dan Scally <djrscally@gmail.com> */ #include <linux/acpi.h> +#include <linux/array_size.h> #include <linux/bitfield.h> #include <linux/device.h> #include <linux/gpio/consumer.h> @@ -55,7 +56,7 @@ static void skl_int3472_log_sensor_module_name(struct int3472_discrete_device *i static int skl_int3472_fill_gpiod_lookup(struct gpiod_lookup *table_entry, struct acpi_resource_gpio *agpio, - const char *func, u32 polarity) + const char *func, unsigned long gpio_flags) { char *path = agpio->resource_source.string_ptr; struct acpi_device *adev; @@ -70,14 +71,14 @@ static int skl_int3472_fill_gpiod_lookup(struct gpiod_lookup *table_entry, if (!adev) return -ENODEV; - *table_entry = GPIO_LOOKUP(acpi_dev_name(adev), agpio->pin_table[0], func, polarity); + *table_entry = GPIO_LOOKUP(acpi_dev_name(adev), agpio->pin_table[0], func, gpio_flags); return 0; } static int skl_int3472_map_gpio_to_sensor(struct int3472_discrete_device *int3472, struct acpi_resource_gpio *agpio, - const char *func, u32 polarity) + const char *func, unsigned long gpio_flags) { int ret; @@ -87,7 +88,7 @@ static int skl_int3472_map_gpio_to_sensor(struct int3472_discrete_device *int347 } ret = skl_int3472_fill_gpiod_lookup(&int3472->gpios.table[int3472->n_sensor_gpios], - agpio, func, polarity); + agpio, func, gpio_flags); if (ret) return ret; @@ -100,7 +101,7 @@ static int skl_int3472_map_gpio_to_sensor(struct int3472_discrete_device *int347 static struct gpio_desc * skl_int3472_gpiod_get_from_temp_lookup(struct int3472_discrete_device *int3472, struct acpi_resource_gpio *agpio, - const char *func, u32 polarity) + const char *func, unsigned long gpio_flags) { struct gpio_desc *desc; int ret; @@ -111,7 +112,7 @@ skl_int3472_gpiod_get_from_temp_lookup(struct int3472_discrete_device *int3472, return ERR_PTR(-ENOMEM); lookup->dev_id = dev_name(int3472->dev); - ret = skl_int3472_fill_gpiod_lookup(&lookup->table[0], agpio, func, polarity); + ret = skl_int3472_fill_gpiod_lookup(&lookup->table[0], agpio, func, gpio_flags); if (ret) return ERR_PTR(ret); @@ -122,32 +123,76 @@ skl_int3472_gpiod_get_from_temp_lookup(struct int3472_discrete_device *int3472, return desc; } -static void int3472_get_func_and_polarity(u8 type, const char **func, u32 *polarity) +/** + * struct int3472_gpio_map - Map GPIOs to whatever is expected by the + * sensor driver (as in DT bindings) + * @hid: The ACPI HID of the device without the instance number e.g. INT347E + * @type_from: The GPIO type from ACPI ?SDT + * @type_to: The assigned GPIO type, typically same as @type_from + * @func: The function, e.g. "enable" + * @polarity_low: GPIO_ACTIVE_LOW true if the @polarity_low is true, + * GPIO_ACTIVE_HIGH otherwise + */ +struct int3472_gpio_map { + const char *hid; + u8 type_from; + u8 type_to; + bool polarity_low; + const char *func; +}; + +static const struct int3472_gpio_map int3472_gpio_map[] = { + { "INT347E", INT3472_GPIO_TYPE_RESET, INT3472_GPIO_TYPE_RESET, false, "enable" }, +}; + +static void int3472_get_func_and_polarity(struct acpi_device *adev, u8 *type, + const char **func, unsigned long *gpio_flags) { - switch (type) { + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(int3472_gpio_map); i++) { + /* + * Map the firmware-provided GPIO to whatever a driver expects + * (as in DT bindings). First check if the type matches with the + * GPIO map, then further check that the device _HID matches. + */ + if (*type != int3472_gpio_map[i].type_from) + continue; + + if (!acpi_dev_hid_uid_match(adev, int3472_gpio_map[i].hid, NULL)) + continue; + + *type = int3472_gpio_map[i].type_to; + *gpio_flags = int3472_gpio_map[i].polarity_low ? + GPIO_ACTIVE_LOW : GPIO_ACTIVE_HIGH; + *func = int3472_gpio_map[i].func; + return; + } + + switch (*type) { case INT3472_GPIO_TYPE_RESET: *func = "reset"; - *polarity = GPIO_ACTIVE_LOW; + *gpio_flags = GPIO_ACTIVE_LOW; break; case INT3472_GPIO_TYPE_POWERDOWN: *func = "powerdown"; - *polarity = GPIO_ACTIVE_LOW; + *gpio_flags = GPIO_ACTIVE_LOW; break; case INT3472_GPIO_TYPE_CLK_ENABLE: *func = "clk-enable"; - *polarity = GPIO_ACTIVE_HIGH; + *gpio_flags = GPIO_ACTIVE_HIGH; break; case INT3472_GPIO_TYPE_PRIVACY_LED: *func = "privacy-led"; - *polarity = GPIO_ACTIVE_HIGH; + *gpio_flags = GPIO_ACTIVE_HIGH; break; case INT3472_GPIO_TYPE_POWER_ENABLE: *func = "power-enable"; - *polarity = GPIO_ACTIVE_HIGH; + *gpio_flags = GPIO_ACTIVE_HIGH; break; default: *func = "unknown"; - *polarity = GPIO_ACTIVE_HIGH; + *gpio_flags = GPIO_ACTIVE_HIGH; break; } } @@ -194,7 +239,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, struct gpio_desc *gpio; const char *err_msg; const char *func; - u32 polarity; + unsigned long gpio_flags; int ret; if (!acpi_gpio_get_io_resource(ares, &agpio)) @@ -217,7 +262,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, type = FIELD_GET(INT3472_GPIO_DSM_TYPE, obj->integer.value); - int3472_get_func_and_polarity(type, &func, &polarity); + int3472_get_func_and_polarity(int3472->sensor, &type, &func, &gpio_flags); pin = FIELD_GET(INT3472_GPIO_DSM_PIN, obj->integer.value); /* Pin field is not really used under Windows and wraps around at 8 bits */ @@ -227,16 +272,16 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, active_value = FIELD_GET(INT3472_GPIO_DSM_SENSOR_ON_VAL, obj->integer.value); if (!active_value) - polarity ^= GPIO_ACTIVE_LOW; + gpio_flags ^= GPIO_ACTIVE_LOW; dev_dbg(int3472->dev, "%s %s pin %d active-%s\n", func, agpio->resource_source.string_ptr, agpio->pin_table[0], - str_high_low(polarity == GPIO_ACTIVE_HIGH)); + str_high_low(gpio_flags == GPIO_ACTIVE_HIGH)); switch (type) { case INT3472_GPIO_TYPE_RESET: case INT3472_GPIO_TYPE_POWERDOWN: - ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, func, polarity); + ret = skl_int3472_map_gpio_to_sensor(int3472, agpio, func, gpio_flags); if (ret) err_msg = "Failed to map GPIO pin to sensor\n"; @@ -244,7 +289,7 @@ static int skl_int3472_handle_gpio_resources(struct acpi_resource *ares, case INT3472_GPIO_TYPE_CLK_ENABLE: case INT3472_GPIO_TYPE_PRIVACY_LED: case INT3472_GPIO_TYPE_POWER_ENABLE: - gpio = skl_int3472_gpiod_get_from_temp_lookup(int3472, agpio, func, polarity); + gpio = skl_int3472_gpiod_get_from_temp_lookup(int3472, agpio, func, gpio_flags); if (IS_ERR(gpio)) { ret = PTR_ERR(gpio); err_msg = "Failed to get GPIO\n"; diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 10f04b944117..1ee0fb5f8250 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -626,8 +626,8 @@ static u32 convert_ltr_scale(u32 val) static int pmc_core_ltr_show(struct seq_file *s, void *unused) { struct pmc_dev *pmcdev = s->private; - u64 decoded_snoop_ltr, decoded_non_snoop_ltr; - u32 ltr_raw_data, scale, val; + u64 decoded_snoop_ltr, decoded_non_snoop_ltr, val; + u32 ltr_raw_data, scale; u16 snoop_ltr, nonsnoop_ltr; unsigned int i, index, ltr_index = 0; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 1fcb0f99695a..72a10ed2017c 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -7885,6 +7885,7 @@ static struct ibm_struct volume_driver_data = { #define FAN_NS_CTRL_STATUS BIT(2) /* Bit which determines control is enabled or not */ #define FAN_NS_CTRL BIT(4) /* Bit which determines control is by host or EC */ +#define FAN_CLOCK_TPM (22500*60) /* Ticks per minute for a 22.5 kHz clock */ enum { /* Fan control constants */ fan_status_offset = 0x2f, /* EC register 0x2f */ @@ -7940,6 +7941,7 @@ static int fan_watchdog_maxinterval; static bool fan_with_ns_addr; static bool ecfw_with_fan_dec_rpm; +static bool fan_speed_in_tpr; static struct mutex fan_mutex; @@ -8142,8 +8144,11 @@ static int fan_get_speed(unsigned int *speed) !acpi_ec_read(fan_rpm_offset + 1, &hi))) return -EIO; - if (likely(speed)) + if (likely(speed)) { *speed = (hi << 8) | lo; + if (fan_speed_in_tpr && *speed != 0) + *speed = FAN_CLOCK_TPM / *speed; + } break; case TPACPI_FAN_RD_TPEC_NS: if (!acpi_ec_read(fan_rpm_status_ns, &lo)) @@ -8176,8 +8181,11 @@ static int fan2_get_speed(unsigned int *speed) if (rc) return -EIO; - if (likely(speed)) + if (likely(speed)) { *speed = (hi << 8) | lo; + if (fan_speed_in_tpr && *speed != 0) + *speed = FAN_CLOCK_TPM / *speed; + } break; case TPACPI_FAN_RD_TPEC_NS: @@ -8788,6 +8796,7 @@ static const struct attribute_group fan_driver_attr_group = { #define TPACPI_FAN_NOFAN 0x0008 /* no fan available */ #define TPACPI_FAN_NS 0x0010 /* For EC with non-Standard register addresses */ #define TPACPI_FAN_DECRPM 0x0020 /* For ECFW's with RPM in register as decimal */ +#define TPACPI_FAN_TPR 0x0040 /* Fan speed is in Ticks Per Revolution */ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_QEC_IBM('1', 'Y', TPACPI_FAN_Q1), @@ -8817,6 +8826,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('R', '0', 'V', TPACPI_FAN_NS), /* 11e Gen5 KL-Y */ TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */ TPACPI_Q_LNV3('R', '0', 'Q', TPACPI_FAN_DECRPM),/* L480 */ + TPACPI_Q_LNV('8', 'F', TPACPI_FAN_TPR), /* ThinkPad x120e */ }; static int __init fan_init(struct ibm_init_struct *iibm) @@ -8887,6 +8897,8 @@ static int __init fan_init(struct ibm_init_struct *iibm) if (quirks & TPACPI_FAN_Q1) fan_quirk1_setup(); + if (quirks & TPACPI_FAN_TPR) + fan_speed_in_tpr = true; /* Try and probe the 2nd fan */ tp_features.second_fan = 1; /* needed for get_speed to work */ res = fan2_get_speed(&speed); @@ -10319,6 +10331,10 @@ static struct ibm_struct proxsensor_driver_data = { #define DYTC_MODE_PSC_BALANCE 5 /* Default mode aka balanced */ #define DYTC_MODE_PSC_PERFORM 7 /* High power mode aka performance */ +#define DYTC_MODE_PSCV9_LOWPOWER 1 /* Low power mode */ +#define DYTC_MODE_PSCV9_BALANCE 3 /* Default mode aka balanced */ +#define DYTC_MODE_PSCV9_PERFORM 4 /* High power mode aka performance */ + #define DYTC_ERR_MASK 0xF /* Bits 0-3 in cmd result are the error result */ #define DYTC_ERR_SUCCESS 1 /* CMD completed successful */ @@ -10339,6 +10355,10 @@ static int dytc_capabilities; static bool dytc_mmc_get_available; static int profile_force; +static int platform_psc_profile_lowpower = DYTC_MODE_PSC_LOWPOWER; +static int platform_psc_profile_balanced = DYTC_MODE_PSC_BALANCE; +static int platform_psc_profile_performance = DYTC_MODE_PSC_PERFORM; + static int convert_dytc_to_profile(int funcmode, int dytcmode, enum platform_profile_option *profile) { @@ -10360,19 +10380,15 @@ static int convert_dytc_to_profile(int funcmode, int dytcmode, } return 0; case DYTC_FUNCTION_PSC: - switch (dytcmode) { - case DYTC_MODE_PSC_LOWPOWER: + if (dytcmode == platform_psc_profile_lowpower) *profile = PLATFORM_PROFILE_LOW_POWER; - break; - case DYTC_MODE_PSC_BALANCE: + else if (dytcmode == platform_psc_profile_balanced) *profile = PLATFORM_PROFILE_BALANCED; - break; - case DYTC_MODE_PSC_PERFORM: + else if (dytcmode == platform_psc_profile_performance) *profile = PLATFORM_PROFILE_PERFORMANCE; - break; - default: /* Unknown mode */ + else return -EINVAL; - } + return 0; case DYTC_FUNCTION_AMT: /* For now return balanced. It's the closest we have to 'auto' */ @@ -10393,19 +10409,19 @@ static int convert_profile_to_dytc(enum platform_profile_option profile, int *pe if (dytc_capabilities & BIT(DYTC_FC_MMC)) *perfmode = DYTC_MODE_MMC_LOWPOWER; else if (dytc_capabilities & BIT(DYTC_FC_PSC)) - *perfmode = DYTC_MODE_PSC_LOWPOWER; + *perfmode = platform_psc_profile_lowpower; break; case PLATFORM_PROFILE_BALANCED: if (dytc_capabilities & BIT(DYTC_FC_MMC)) *perfmode = DYTC_MODE_MMC_BALANCE; else if (dytc_capabilities & BIT(DYTC_FC_PSC)) - *perfmode = DYTC_MODE_PSC_BALANCE; + *perfmode = platform_psc_profile_balanced; break; case PLATFORM_PROFILE_PERFORMANCE: if (dytc_capabilities & BIT(DYTC_FC_MMC)) *perfmode = DYTC_MODE_MMC_PERFORM; else if (dytc_capabilities & BIT(DYTC_FC_PSC)) - *perfmode = DYTC_MODE_PSC_PERFORM; + *perfmode = platform_psc_profile_performance; break; default: /* Unknown profile */ return -EOPNOTSUPP; @@ -10599,6 +10615,7 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) if (output & BIT(DYTC_QUERY_ENABLE_BIT)) dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF; + dbg_printk(TPACPI_DBG_INIT, "DYTC version %d\n", dytc_version); /* Check DYTC is enabled and supports mode setting */ if (dytc_version < 5) return -ENODEV; @@ -10637,6 +10654,11 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) } } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) { /* PSC MODE */ pr_debug("PSC is supported\n"); + if (dytc_version >= 9) { /* update profiles for DYTC 9 and up */ + platform_psc_profile_lowpower = DYTC_MODE_PSCV9_LOWPOWER; + platform_psc_profile_balanced = DYTC_MODE_PSCV9_BALANCE; + platform_psc_profile_performance = DYTC_MODE_PSCV9_PERFORM; + } } else { dbg_printk(TPACPI_DBG_INIT, "No DYTC support available\n"); return -ENODEV; @@ -10646,8 +10668,8 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) "DYTC version %d: thermal mode available\n", dytc_version); /* Create platform_profile structure and register */ - tpacpi_pprof = devm_platform_profile_register(&tpacpi_pdev->dev, "thinkpad-acpi", - NULL, &dytc_profile_ops); + tpacpi_pprof = platform_profile_register(&tpacpi_pdev->dev, "thinkpad-acpi-profile", + NULL, &dytc_profile_ops); /* * If for some reason platform_profiles aren't enabled * don't quit terminally. @@ -10665,8 +10687,15 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) return 0; } +static void dytc_profile_exit(void) +{ + if (!IS_ERR_OR_NULL(tpacpi_pprof)) + platform_profile_remove(tpacpi_pprof); +} + static struct ibm_struct dytc_profile_driver_data = { .name = "dytc-profile", + .exit = dytc_profile_exit, }; /************************************************************************* diff --git a/drivers/powercap/powercap_sys.c b/drivers/powercap/powercap_sys.c index 52c32dcbf7d8..4112a0097338 100644 --- a/drivers/powercap/powercap_sys.c +++ b/drivers/powercap/powercap_sys.c @@ -627,8 +627,7 @@ struct powercap_control_type *powercap_register_control_type( dev_set_name(&control_type->dev, "%s", name); result = device_register(&control_type->dev); if (result) { - if (control_type->allocated) - kfree(control_type); + put_device(&control_type->dev); return ERR_PTR(result); } idr_init(&control_type->idr); diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c index ea96a14d72d1..bf6468c56419 100644 --- a/drivers/ptp/ptp_chardev.c +++ b/drivers/ptp/ptp_chardev.c @@ -4,6 +4,7 @@ * * Copyright (C) 2010 OMICRON electronics GmbH */ +#include <linux/compat.h> #include <linux/module.h> #include <linux/posix-clock.h> #include <linux/poll.h> @@ -176,6 +177,9 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd, struct timespec64 ts; int enable, err = 0; + if (in_compat_syscall() && cmd != PTP_ENABLE_PPS && cmd != PTP_ENABLE_PPS2) + arg = (unsigned long)compat_ptr(arg); + tsevq = pccontext->private_clkdata; switch (cmd) { diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index b932425ddc6a..35a5994bf64f 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -217,6 +217,11 @@ static int ptp_getcycles64(struct ptp_clock_info *info, struct timespec64 *ts) return info->gettime64(info, ts); } +static int ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on) +{ + return -EOPNOTSUPP; +} + static void ptp_aux_kworker(struct kthread_work *work) { struct ptp_clock *ptp = container_of(work, struct ptp_clock, @@ -294,6 +299,9 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, ptp->info->getcrosscycles = ptp->info->getcrosststamp; } + if (!ptp->info->enable) + ptp->info->enable = ptp_enable; + if (ptp->info->do_aux_work) { kthread_init_delayed_work(&ptp->aux_work, ptp_aux_kworker); ptp->kworker = kthread_run_worker(0, "ptp%d", ptp->index); diff --git a/drivers/ptp/ptp_vmclock.c b/drivers/ptp/ptp_vmclock.c index 0a2cfc8ad3c5..b3a83b03d9c1 100644 --- a/drivers/ptp/ptp_vmclock.c +++ b/drivers/ptp/ptp_vmclock.c @@ -414,16 +414,16 @@ static ssize_t vmclock_miscdev_read(struct file *fp, char __user *buf, } static const struct file_operations vmclock_miscdev_fops = { + .owner = THIS_MODULE, .mmap = vmclock_miscdev_mmap, .read = vmclock_miscdev_read, }; /* module operations */ -static void vmclock_remove(struct platform_device *pdev) +static void vmclock_remove(void *data) { - struct device *dev = &pdev->dev; - struct vmclock_state *st = dev_get_drvdata(dev); + struct vmclock_state *st = data; if (st->ptp_clock) ptp_clock_unregister(st->ptp_clock); @@ -506,14 +506,13 @@ static int vmclock_probe(struct platform_device *pdev) if (ret) { dev_info(dev, "Failed to obtain physical address: %d\n", ret); - goto out; + return ret; } if (resource_size(&st->res) < VMCLOCK_MIN_SIZE) { dev_info(dev, "Region too small (0x%llx)\n", resource_size(&st->res)); - ret = -EINVAL; - goto out; + return -EINVAL; } st->clk = devm_memremap(dev, st->res.start, resource_size(&st->res), MEMREMAP_WB | MEMREMAP_DEC); @@ -521,31 +520,34 @@ static int vmclock_probe(struct platform_device *pdev) ret = PTR_ERR(st->clk); dev_info(dev, "failed to map shared memory\n"); st->clk = NULL; - goto out; + return ret; } if (le32_to_cpu(st->clk->magic) != VMCLOCK_MAGIC || le32_to_cpu(st->clk->size) > resource_size(&st->res) || le16_to_cpu(st->clk->version) != 1) { dev_info(dev, "vmclock magic fields invalid\n"); - ret = -EINVAL; - goto out; + return -EINVAL; } ret = ida_alloc(&vmclock_ida, GFP_KERNEL); if (ret < 0) - goto out; + return ret; st->index = ret; ret = devm_add_action_or_reset(&pdev->dev, vmclock_put_idx, st); if (ret) - goto out; + return ret; st->name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "vmclock%d", st->index); - if (!st->name) { - ret = -ENOMEM; - goto out; - } + if (!st->name) + return -ENOMEM; + + st->miscdev.minor = MISC_DYNAMIC_MINOR; + + ret = devm_add_action_or_reset(&pdev->dev, vmclock_remove, st); + if (ret) + return ret; /* * If the structure is big enough, it can be mapped to userspace. @@ -554,13 +556,12 @@ static int vmclock_probe(struct platform_device *pdev) * cross that bridge if/when we come to it. */ if (le32_to_cpu(st->clk->size) >= PAGE_SIZE) { - st->miscdev.minor = MISC_DYNAMIC_MINOR; st->miscdev.fops = &vmclock_miscdev_fops; st->miscdev.name = st->name; ret = misc_register(&st->miscdev); if (ret) - goto out; + return ret; } /* If there is valid clock information, register a PTP clock */ @@ -570,16 +571,14 @@ static int vmclock_probe(struct platform_device *pdev) if (IS_ERR(st->ptp_clock)) { ret = PTR_ERR(st->ptp_clock); st->ptp_clock = NULL; - vmclock_remove(pdev); - goto out; + return ret; } } if (!st->miscdev.minor && !st->ptp_clock) { /* Neither miscdev nor PTP registered */ dev_info(dev, "vmclock: Neither miscdev nor PTP available; not registering\n"); - ret = -ENODEV; - goto out; + return -ENODEV; } dev_info(dev, "%s: registered %s%s%s\n", st->name, @@ -587,10 +586,7 @@ static int vmclock_probe(struct platform_device *pdev) (st->miscdev.minor && st->ptp_clock) ? ", " : "", st->ptp_clock ? "PTP" : ""); - dev_set_drvdata(dev, st); - - out: - return ret; + return 0; } static const struct acpi_device_id vmclock_acpi_ids[] = { @@ -601,7 +597,6 @@ MODULE_DEVICE_TABLE(acpi, vmclock_acpi_ids); static struct platform_driver vmclock_platform_driver = { .probe = vmclock_probe, - .remove = vmclock_remove, .driver = { .name = "vmclock", .acpi_match_table = vmclock_acpi_ids, diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index 6c0ef1182248..4ddf0efead68 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5033,7 +5033,7 @@ int _regulator_bulk_get(struct device *dev, int num_consumers, consumers[i].supply, get_type); if (IS_ERR(consumers[i].consumer)) { ret = dev_err_probe(dev, PTR_ERR(consumers[i].consumer), - "Failed to get supply '%s'", + "Failed to get supply '%s'\n", consumers[i].supply); consumers[i].consumer = NULL; goto err; @@ -5774,43 +5774,36 @@ regulator_register(struct device *dev, goto clean; } - if (config->init_data) { - /* - * Providing of_match means the framework is expected to parse - * DT to get the init_data. This would conflict with provided - * init_data, if set. Warn if it happens. - */ - if (regulator_desc->of_match) - dev_warn(dev, "Using provided init data - OF match ignored\n"); + /* + * DT may override the config->init_data provided if the platform + * needs to do so. If so, config->init_data is completely ignored. + */ + init_data = regulator_of_get_init_data(dev, regulator_desc, config, + &rdev->dev.of_node); + /* + * Sometimes not all resources are probed already so we need to take + * that into account. This happens most the time if the ena_gpiod comes + * from a gpio extender or something else. + */ + if (PTR_ERR(init_data) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto clean; + } + + /* + * We need to keep track of any GPIO descriptor coming from the + * device tree until we have handled it over to the core. If the + * config that was passed in to this function DOES NOT contain + * a descriptor, and the config after this call DOES contain + * a descriptor, we definitely got one from parsing the device + * tree. + */ + if (!cfg->ena_gpiod && config->ena_gpiod) + dangling_of_gpiod = true; + if (!init_data) { init_data = config->init_data; rdev->dev.of_node = of_node_get(config->of_node); - - } else { - init_data = regulator_of_get_init_data(dev, regulator_desc, - config, - &rdev->dev.of_node); - - /* - * Sometimes not all resources are probed already so we need to - * take that into account. This happens most the time if the - * ena_gpiod comes from a gpio extender or something else. - */ - if (PTR_ERR(init_data) == -EPROBE_DEFER) { - ret = -EPROBE_DEFER; - goto clean; - } - - /* - * We need to keep track of any GPIO descriptor coming from the - * device tree until we have handled it over to the core. If the - * config that was passed in to this function DOES NOT contain a - * descriptor, and the config after this call DOES contain a - * descriptor, we definitely got one from parsing the device - * tree. - */ - if (!cfg->ena_gpiod && config->ena_gpiod) - dangling_of_gpiod = true; } ww_mutex_init(&rdev->mutex, ®ulator_ww_class); diff --git a/drivers/regulator/tps6287x-regulator.c b/drivers/regulator/tps6287x-regulator.c index 97f5ce138548..c0f5f0a186a3 100644 --- a/drivers/regulator/tps6287x-regulator.c +++ b/drivers/regulator/tps6287x-regulator.c @@ -44,10 +44,35 @@ static const unsigned int tps6287x_voltage_range_sel[] = { 0x0, 0x1, 0x2, 0x3 }; +static const unsigned int tps6287x_voltage_range_prefix[] = { + 0x000, 0x100, 0x200, 0x300 +}; + static const unsigned int tps6287x_ramp_table[] = { 10000, 5000, 1250, 500 }; +struct tps6287x_reg_data { + int range; +}; + +static int tps6287x_best_range(struct regulator_config *config, const struct regulator_desc *desc) +{ + const struct linear_range *r; + int i; + + if (!config->init_data->constraints.apply_uV) + return -1; + + for (i = 0; i < desc->n_linear_ranges; i++) { + r = &desc->linear_ranges[i]; + if (r->min <= config->init_data->constraints.min_uV && + config->init_data->constraints.max_uV <= linear_range_get_max_value(r)) + return i; + } + return -1; +} + static int tps6287x_set_mode(struct regulator_dev *rdev, unsigned int mode) { unsigned int val; @@ -91,6 +116,28 @@ static unsigned int tps6287x_of_map_mode(unsigned int mode) } } +static int tps6287x_map_voltage(struct regulator_dev *rdev, int min_uV, int max_uV) +{ + struct tps6287x_reg_data *data = (struct tps6287x_reg_data *)rdev->reg_data; + struct linear_range selected_range; + int selector, voltage; + + if (!data || data->range == -1) + return regulator_map_voltage_pickable_linear_range(rdev, min_uV, max_uV); + + selected_range = rdev->desc->linear_ranges[data->range]; + selector = DIV_ROUND_UP(min_uV - selected_range.min, selected_range.step); + if (selector < selected_range.min_sel || selector > selected_range.max_sel) + return -EINVAL; + + selector |= tps6287x_voltage_range_prefix[data->range]; + voltage = rdev->desc->ops->list_voltage(rdev, selector); + if (voltage < min_uV || voltage > max_uV) + return -EINVAL; + + return selector; +} + static const struct regulator_ops tps6287x_regulator_ops = { .enable = regulator_enable_regmap, .disable = regulator_disable_regmap, @@ -100,6 +147,7 @@ static const struct regulator_ops tps6287x_regulator_ops = { .get_voltage_sel = regulator_get_voltage_sel_pickable_regmap, .set_voltage_sel = regulator_set_voltage_sel_pickable_regmap, .list_voltage = regulator_list_voltage_pickable_linear_range, + .map_voltage = tps6287x_map_voltage, .set_ramp_delay = regulator_set_ramp_delay_regmap, }; @@ -130,8 +178,14 @@ static int tps6287x_i2c_probe(struct i2c_client *i2c) { struct device *dev = &i2c->dev; struct regulator_config config = {}; + struct tps6287x_reg_data *reg_data; struct regulator_dev *rdev; + reg_data = devm_kzalloc(dev, sizeof(struct tps6287x_reg_data), GFP_KERNEL); + + if (!reg_data) + return -ENOMEM; + config.regmap = devm_regmap_init_i2c(i2c, &tps6287x_regmap_config); if (IS_ERR(config.regmap)) { dev_err(dev, "Failed to init i2c\n"); @@ -143,12 +197,15 @@ static int tps6287x_i2c_probe(struct i2c_client *i2c) config.init_data = of_get_regulator_init_data(dev, dev->of_node, &tps6287x_reg); + reg_data->range = tps6287x_best_range(&config, &tps6287x_reg); + rdev = devm_regulator_register(dev, &tps6287x_reg, &config); if (IS_ERR(rdev)) { dev_err(dev, "Failed to register regulator\n"); return PTR_ERR(rdev); } + rdev->reg_data = (void *)reg_data; dev_dbg(dev, "Probed regulator\n"); return 0; diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig index a60bcc791a48..0bbbf778ecfa 100644 --- a/drivers/rtc/Kconfig +++ b/drivers/rtc/Kconfig @@ -1316,7 +1316,7 @@ config RTC_DRV_SC27XX config RTC_DRV_SPEAR tristate "SPEAR ST RTC" depends on PLAT_SPEAR || COMPILE_TEST - default y + default PLAT_SPEAR help If you say Y here you will get support for the RTC found on spear diff --git a/drivers/rtc/rtc-88pm80x.c b/drivers/rtc/rtc-88pm80x.c index 5c39cf252392..a3e52a5a708f 100644 --- a/drivers/rtc/rtc-88pm80x.c +++ b/drivers/rtc/rtc-88pm80x.c @@ -308,7 +308,7 @@ static int pm80x_rtc_probe(struct platform_device *pdev) /* remember whether this power up is caused by PMIC RTC or not */ info->rtc_dev->dev.platform_data = &pdata->rtc_wakeup; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; out_rtc: diff --git a/drivers/rtc/rtc-88pm860x.c b/drivers/rtc/rtc-88pm860x.c index 814230d61842..964cd048fcdb 100644 --- a/drivers/rtc/rtc-88pm860x.c +++ b/drivers/rtc/rtc-88pm860x.c @@ -326,7 +326,7 @@ static int pm860x_rtc_probe(struct platform_device *pdev) schedule_delayed_work(&info->calib_work, VRTC_CALIB_INTERVAL); #endif /* VRTC_CALIBRATION */ - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; } diff --git a/drivers/rtc/rtc-amlogic-a4.c b/drivers/rtc/rtc-amlogic-a4.c index 2278b4c98a71..09d78c2cc691 100644 --- a/drivers/rtc/rtc-amlogic-a4.c +++ b/drivers/rtc/rtc-amlogic-a4.c @@ -361,7 +361,7 @@ static int aml_rtc_probe(struct platform_device *pdev) "failed to get_enable rtc sys clk\n"); aml_rtc_init(rtc); - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); platform_set_drvdata(pdev, rtc); rtc->rtc_dev = devm_rtc_allocate_device(dev); @@ -391,7 +391,7 @@ static int aml_rtc_probe(struct platform_device *pdev) return 0; err_clk: clk_disable_unprepare(rtc->sys_clk); - device_init_wakeup(dev, 0); + device_init_wakeup(dev, false); return ret; } @@ -426,7 +426,7 @@ static void aml_rtc_remove(struct platform_device *pdev) struct aml_rtc_data *rtc = dev_get_drvdata(&pdev->dev); clk_disable_unprepare(rtc->sys_clk); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); } static const struct aml_rtc_config a5_rtc_config = { diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c index 569c1054d6b0..713fa0d077cd 100644 --- a/drivers/rtc/rtc-armada38x.c +++ b/drivers/rtc/rtc-armada38x.c @@ -527,7 +527,7 @@ static __init int armada38x_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); if (rtc->irq != -1) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); else clear_bit(RTC_FEATURE_ALARM, rtc->rtc_dev->features); diff --git a/drivers/rtc/rtc-as3722.c b/drivers/rtc/rtc-as3722.c index 0f21af27f4cf..9682d6457b7f 100644 --- a/drivers/rtc/rtc-as3722.c +++ b/drivers/rtc/rtc-as3722.c @@ -187,7 +187,7 @@ static int as3722_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); as3722_rtc->rtc = devm_rtc_device_register(&pdev->dev, "as3722-rtc", &as3722_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-at91rm9200.c b/drivers/rtc/rtc-at91rm9200.c index 9b3898b8de7c..f6b0102a843a 100644 --- a/drivers/rtc/rtc-at91rm9200.c +++ b/drivers/rtc/rtc-at91rm9200.c @@ -528,7 +528,7 @@ static int __init at91_rtc_probe(struct platform_device *pdev) * being wake-capable; if it didn't, do that here. */ if (!device_can_wakeup(&pdev->dev)) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); if (at91_rtc_config->has_correction) rtc->ops = &sama5d4_rtc_ops; diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c index 15b21da2788f..38991cca5930 100644 --- a/drivers/rtc/rtc-at91sam9.c +++ b/drivers/rtc/rtc-at91sam9.c @@ -353,7 +353,7 @@ static int at91_rtc_probe(struct platform_device *pdev) /* platform setup code should have handled this; sigh */ if (!device_can_wakeup(&pdev->dev)) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); platform_set_drvdata(pdev, rtc); diff --git a/drivers/rtc/rtc-cadence.c b/drivers/rtc/rtc-cadence.c index bf2a9a1fdea7..8634eea799ab 100644 --- a/drivers/rtc/rtc-cadence.c +++ b/drivers/rtc/rtc-cadence.c @@ -359,7 +359,7 @@ static void cdns_rtc_remove(struct platform_device *pdev) struct cdns_rtc *crtc = platform_get_drvdata(pdev); cdns_rtc_alarm_irq_enable(&pdev->dev, 0); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); clk_disable_unprepare(crtc->pclk); clk_disable_unprepare(crtc->ref_clk); diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index 78f2ce12c75a..8172869bd3d7 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -151,11 +151,6 @@ static inline int hpet_set_periodic_freq(unsigned long freq) return 0; } -static inline int hpet_rtc_dropped_irq(void) -{ - return 0; -} - static inline int hpet_rtc_timer_init(void) { return 0; @@ -864,7 +859,7 @@ static void acpi_cmos_wake_setup(struct device *dev) dev_info(dev, "RTC can wake from S4\n"); /* RTC always wakes from S1/S2/S3, and often S4/STD */ - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); } static void cmos_check_acpi_rtc_status(struct device *dev, diff --git a/drivers/rtc/rtc-cpcap.c b/drivers/rtc/rtc-cpcap.c index afc8fcba8f88..568a89e79c11 100644 --- a/drivers/rtc/rtc-cpcap.c +++ b/drivers/rtc/rtc-cpcap.c @@ -295,7 +295,7 @@ static int cpcap_rtc_probe(struct platform_device *pdev) } disable_irq(rtc->update_irq); - err = device_init_wakeup(dev, 1); + err = device_init_wakeup(dev, true); if (err) { dev_err(dev, "wakeup initialization failed (%d)\n", err); /* ignore error and continue without wakeup support */ diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c index 60a48c3ba3ca..865c2e82c7a5 100644 --- a/drivers/rtc/rtc-cros-ec.c +++ b/drivers/rtc/rtc-cros-ec.c @@ -337,7 +337,7 @@ static int cros_ec_rtc_probe(struct platform_device *pdev) return ret; } - ret = device_init_wakeup(&pdev->dev, 1); + ret = device_init_wakeup(&pdev->dev, true); if (ret) { dev_err(&pdev->dev, "failed to initialize wakeup\n"); return ret; diff --git a/drivers/rtc/rtc-da9055.c b/drivers/rtc/rtc-da9055.c index 844168fcae1e..05adec6b77bf 100644 --- a/drivers/rtc/rtc-da9055.c +++ b/drivers/rtc/rtc-da9055.c @@ -288,7 +288,7 @@ static int da9055_rtc_probe(struct platform_device *pdev) if (ret & DA9055_RTC_ALM_EN) rtc->alarm_enable = 1; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &da9055_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-ds3232.c b/drivers/rtc/rtc-ds3232.c index dd37b055693c..19c09c418746 100644 --- a/drivers/rtc/rtc-ds3232.c +++ b/drivers/rtc/rtc-ds3232.c @@ -508,7 +508,7 @@ static int ds3232_probe(struct device *dev, struct regmap *regmap, int irq, return ret; if (ds3232->irq > 0) - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); ds3232_hwmon_register(dev, name); diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c index 7b82e4a14b7a..f71a6bb77b2a 100644 --- a/drivers/rtc/rtc-isl1208.c +++ b/drivers/rtc/rtc-isl1208.c @@ -830,7 +830,7 @@ static int isl1208_setup_irq(struct i2c_client *client, int irq) isl1208_driver.driver.name, client); if (!rc) { - device_init_wakeup(&client->dev, 1); + device_init_wakeup(&client->dev, true); enable_irq_wake(irq); } else { dev_err(&client->dev, diff --git a/drivers/rtc/rtc-jz4740.c b/drivers/rtc/rtc-jz4740.c index bafa7d1b9b88..44bba356268c 100644 --- a/drivers/rtc/rtc-jz4740.c +++ b/drivers/rtc/rtc-jz4740.c @@ -367,7 +367,7 @@ static int jz4740_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc); - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); ret = dev_pm_set_wake_irq(dev, irq); if (ret) diff --git a/drivers/rtc/rtc-loongson.c b/drivers/rtc/rtc-loongson.c index 8d713e563d7c..97e5625c064c 100644 --- a/drivers/rtc/rtc-loongson.c +++ b/drivers/rtc/rtc-loongson.c @@ -114,6 +114,13 @@ static irqreturn_t loongson_rtc_isr(int irq, void *id) struct loongson_rtc_priv *priv = (struct loongson_rtc_priv *)id; rtc_update_irq(priv->rtcdev, 1, RTC_AF | RTC_IRQF); + + /* + * The TOY_MATCH0_REG should be cleared 0 here, + * otherwise the interrupt cannot be cleared. + */ + regmap_write(priv->regmap, TOY_MATCH0_REG, 0); + return IRQ_HANDLED; } @@ -131,11 +138,7 @@ static u32 loongson_rtc_handler(void *id) writel(RTC_STS, priv->pm_base + PM1_STS_REG); spin_unlock(&priv->lock); - /* - * The TOY_MATCH0_REG should be cleared 0 here, - * otherwise the interrupt cannot be cleared. - */ - return regmap_write(priv->regmap, TOY_MATCH0_REG, 0); + return ACPI_INTERRUPT_HANDLED; } static int loongson_rtc_set_enabled(struct device *dev) @@ -329,7 +332,7 @@ static int loongson_rtc_probe(struct platform_device *pdev) alarm_irq); priv->pm_base = regs - priv->config->pm_offset; - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); if (has_acpi_companion(dev)) acpi_install_fixed_event_handler(ACPI_EVENT_RTC, @@ -360,7 +363,7 @@ static void loongson_rtc_remove(struct platform_device *pdev) acpi_remove_fixed_event_handler(ACPI_EVENT_RTC, loongson_rtc_handler); - device_init_wakeup(dev, 0); + device_init_wakeup(dev, false); loongson_rtc_alarm_irq_enable(dev, 0); } diff --git a/drivers/rtc/rtc-lp8788.c b/drivers/rtc/rtc-lp8788.c index c0b8fbce1082..0793d70507f7 100644 --- a/drivers/rtc/rtc-lp8788.c +++ b/drivers/rtc/rtc-lp8788.c @@ -293,7 +293,7 @@ static int lp8788_rtc_probe(struct platform_device *pdev) rtc->alarm = lp->pdata ? lp->pdata->alarm_sel : DEFAULT_ALARM_SEL; platform_set_drvdata(pdev, rtc); - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); rtc->rdev = devm_rtc_device_register(dev, "lp8788_rtc", &lp8788_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-lpc32xx.c b/drivers/rtc/rtc-lpc32xx.c index 76ad7031a13d..74280bffe1b0 100644 --- a/drivers/rtc/rtc-lpc32xx.c +++ b/drivers/rtc/rtc-lpc32xx.c @@ -257,7 +257,7 @@ static int lpc32xx_rtc_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "Can't request interrupt.\n"); rtc->irq = -1; } else { - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); } } diff --git a/drivers/rtc/rtc-max77686.c b/drivers/rtc/rtc-max77686.c index a8f4b645c09d..7bb044d2ac25 100644 --- a/drivers/rtc/rtc-max77686.c +++ b/drivers/rtc/rtc-max77686.c @@ -770,7 +770,7 @@ static int max77686_rtc_probe(struct platform_device *pdev) goto err_rtc; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc_dev = devm_rtc_device_register(&pdev->dev, id->name, &max77686_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-max8925.c b/drivers/rtc/rtc-max8925.c index 64bb8ac6ef62..6ce8afbeac68 100644 --- a/drivers/rtc/rtc-max8925.c +++ b/drivers/rtc/rtc-max8925.c @@ -270,7 +270,7 @@ static int max8925_rtc_probe(struct platform_device *pdev) /* XXX - isn't this redundant? */ platform_set_drvdata(pdev, info); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max8925-rtc", &max8925_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-max8997.c b/drivers/rtc/rtc-max8997.c index 20e50d9fdf88..e7618d715bd8 100644 --- a/drivers/rtc/rtc-max8997.c +++ b/drivers/rtc/rtc-max8997.c @@ -473,7 +473,7 @@ static int max8997_rtc_probe(struct platform_device *pdev) max8997_rtc_enable_wtsr(info, true); max8997_rtc_enable_smpl(info, true); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc_dev = devm_rtc_device_register(&pdev->dev, "max8997-rtc", &max8997_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-meson-vrtc.c b/drivers/rtc/rtc-meson-vrtc.c index 648fa362ec44..5849729f7d01 100644 --- a/drivers/rtc/rtc-meson-vrtc.c +++ b/drivers/rtc/rtc-meson-vrtc.c @@ -74,7 +74,7 @@ static int meson_vrtc_probe(struct platform_device *pdev) if (IS_ERR(vrtc->io_alarm)) return PTR_ERR(vrtc->io_alarm); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); platform_set_drvdata(pdev, vrtc); diff --git a/drivers/rtc/rtc-mpc5121.c b/drivers/rtc/rtc-mpc5121.c index 600328131603..b90f8337a7e6 100644 --- a/drivers/rtc/rtc-mpc5121.c +++ b/drivers/rtc/rtc-mpc5121.c @@ -303,7 +303,7 @@ static int mpc5121_rtc_probe(struct platform_device *op) return PTR_ERR(rtc->regs); } - device_init_wakeup(&op->dev, 1); + device_init_wakeup(&op->dev, true); platform_set_drvdata(op, rtc); diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c index 152699219a2b..6979d225a78e 100644 --- a/drivers/rtc/rtc-mt6397.c +++ b/drivers/rtc/rtc-mt6397.c @@ -286,7 +286,7 @@ static int mtk_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc->rtc_dev->ops = &mtk_rtc_ops; rtc->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_1900; diff --git a/drivers/rtc/rtc-mv.c b/drivers/rtc/rtc-mv.c index 51029c536244..c27ad626d09f 100644 --- a/drivers/rtc/rtc-mv.c +++ b/drivers/rtc/rtc-mv.c @@ -264,7 +264,7 @@ static int __init mv_rtc_probe(struct platform_device *pdev) } if (pdata->irq >= 0) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); else clear_bit(RTC_FEATURE_ALARM, pdata->rtc->features); @@ -287,7 +287,7 @@ static void __exit mv_rtc_remove(struct platform_device *pdev) struct rtc_plat_data *pdata = platform_get_drvdata(pdev); if (pdata->irq >= 0) - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); if (!IS_ERR(pdata->clk)) clk_disable_unprepare(pdata->clk); diff --git a/drivers/rtc/rtc-mxc.c b/drivers/rtc/rtc-mxc.c index dbb935dbbd8a..608db97d450c 100644 --- a/drivers/rtc/rtc-mxc.c +++ b/drivers/rtc/rtc-mxc.c @@ -377,7 +377,7 @@ static int mxc_rtc_probe(struct platform_device *pdev) } if (pdata->irq >= 0) { - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ret = dev_pm_set_wake_irq(&pdev->dev, pdata->irq); if (ret) dev_err(&pdev->dev, "failed to enable irq wake\n"); diff --git a/drivers/rtc/rtc-mxc_v2.c b/drivers/rtc/rtc-mxc_v2.c index 13c041bb79f1..570f27af4732 100644 --- a/drivers/rtc/rtc-mxc_v2.c +++ b/drivers/rtc/rtc-mxc_v2.c @@ -302,7 +302,7 @@ static int mxc_rtc_probe(struct platform_device *pdev) if (pdata->irq < 0) return pdata->irq; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ret = dev_pm_set_wake_irq(&pdev->dev, pdata->irq); if (ret) dev_err(&pdev->dev, "failed to enable irq wake\n"); diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c index c123778e2d9b..0f90065e352c 100644 --- a/drivers/rtc/rtc-omap.c +++ b/drivers/rtc/rtc-omap.c @@ -920,7 +920,7 @@ static void omap_rtc_remove(struct platform_device *pdev) omap_rtc_power_off_rtc = NULL; } - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); if (!IS_ERR(rtc->clk)) clk_disable_unprepare(rtc->clk); diff --git a/drivers/rtc/rtc-palmas.c b/drivers/rtc/rtc-palmas.c index 7256a88b490c..aecada6bcf8b 100644 --- a/drivers/rtc/rtc-palmas.c +++ b/drivers/rtc/rtc-palmas.c @@ -287,7 +287,7 @@ static int palmas_rtc_probe(struct platform_device *pdev) palmas_rtc->irq = platform_get_irq(pdev, 0); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); palmas_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &palmas_rtc_ops, THIS_MODULE); if (IS_ERR(palmas_rtc->rtc)) { diff --git a/drivers/rtc/rtc-pcf2127.c b/drivers/rtc/rtc-pcf2127.c index 9c04c4e1a49c..31c7dca8f469 100644 --- a/drivers/rtc/rtc-pcf2127.c +++ b/drivers/rtc/rtc-pcf2127.c @@ -20,6 +20,7 @@ #include <linux/i2c.h> #include <linux/spi/spi.h> #include <linux/bcd.h> +#include <linux/bitfield.h> #include <linux/rtc.h> #include <linux/slab.h> #include <linux/module.h> @@ -48,6 +49,7 @@ #define PCF2127_BIT_CTRL3_BLF BIT(2) #define PCF2127_BIT_CTRL3_BF BIT(3) #define PCF2127_BIT_CTRL3_BTSE BIT(4) +#define PCF2127_CTRL3_PM GENMASK(7, 5) /* Time and date registers */ #define PCF2127_REG_TIME_BASE 0x03 #define PCF2127_BIT_SC_OSF BIT(7) @@ -331,6 +333,84 @@ static int pcf2127_rtc_set_time(struct device *dev, struct rtc_time *tm) return 0; } +static int pcf2127_param_get(struct device *dev, struct rtc_param *param) +{ + struct pcf2127 *pcf2127 = dev_get_drvdata(dev); + u32 value; + int ret; + + switch (param->param) { + case RTC_PARAM_BACKUP_SWITCH_MODE: + ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL3, &value); + if (ret < 0) + return ret; + + value = FIELD_GET(PCF2127_CTRL3_PM, value); + + if (value < 0x3) + param->uvalue = RTC_BSM_LEVEL; + else if (value < 0x6) + param->uvalue = RTC_BSM_DIRECT; + else + param->uvalue = RTC_BSM_DISABLED; + + break; + + default: + return -EINVAL; + } + + return 0; +} + +static int pcf2127_param_set(struct device *dev, struct rtc_param *param) +{ + struct pcf2127 *pcf2127 = dev_get_drvdata(dev); + u8 mode = 0; + u32 value; + int ret; + + switch (param->param) { + case RTC_PARAM_BACKUP_SWITCH_MODE: + ret = regmap_read(pcf2127->regmap, PCF2127_REG_CTRL3, &value); + if (ret < 0) + return ret; + + value = FIELD_GET(PCF2127_CTRL3_PM, value); + + if (value > 5) + value -= 5; + else if (value > 2) + value -= 3; + + switch (param->uvalue) { + case RTC_BSM_LEVEL: + break; + case RTC_BSM_DIRECT: + mode = 3; + break; + case RTC_BSM_DISABLED: + if (value == 0) + value = 1; + mode = 5; + break; + default: + return -EINVAL; + } + + return regmap_update_bits(pcf2127->regmap, PCF2127_REG_CTRL3, + PCF2127_CTRL3_PM, + FIELD_PREP(PCF2127_CTRL3_PM, mode + value)); + + break; + + default: + return -EINVAL; + } + + return 0; +} + static int pcf2127_rtc_ioctl(struct device *dev, unsigned int cmd, unsigned long arg) { @@ -741,6 +821,8 @@ static const struct rtc_class_ops pcf2127_rtc_ops = { .read_alarm = pcf2127_rtc_read_alarm, .set_alarm = pcf2127_rtc_set_alarm, .alarm_irq_enable = pcf2127_rtc_alarm_irq_enable, + .param_get = pcf2127_param_get, + .param_set = pcf2127_param_set, }; /* sysfs interface */ diff --git a/drivers/rtc/rtc-pcf85063.c b/drivers/rtc/rtc-pcf85063.c index fdbc07f14036..905986c61655 100644 --- a/drivers/rtc/rtc-pcf85063.c +++ b/drivers/rtc/rtc-pcf85063.c @@ -322,7 +322,16 @@ static const struct rtc_class_ops pcf85063_rtc_ops = { static int pcf85063_nvmem_read(void *priv, unsigned int offset, void *val, size_t bytes) { - return regmap_read(priv, PCF85063_REG_RAM, val); + unsigned int tmp; + int ret; + + ret = regmap_read(priv, PCF85063_REG_RAM, &tmp); + if (ret < 0) + return ret; + + *(u8 *)val = tmp; + + return 0; } static int pcf85063_nvmem_write(void *priv, unsigned int offset, diff --git a/drivers/rtc/rtc-pic32.c b/drivers/rtc/rtc-pic32.c index bed3c27e665f..2812da2c50c5 100644 --- a/drivers/rtc/rtc-pic32.c +++ b/drivers/rtc/rtc-pic32.c @@ -330,7 +330,7 @@ static int pic32_rtc_probe(struct platform_device *pdev) pic32_rtc_enable(pdata, 1); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); pdata->rtc->ops = &pic32_rtcops; pdata->rtc->range_min = RTC_TIMESTAMP_BEGIN_2000; diff --git a/drivers/rtc/rtc-pm8xxx.c b/drivers/rtc/rtc-pm8xxx.c index 2f32187ecc8d..b2518aea4218 100644 --- a/drivers/rtc/rtc-pm8xxx.c +++ b/drivers/rtc/rtc-pm8xxx.c @@ -503,7 +503,7 @@ static int pm8xxx_rtc_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rtc_dd); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc_dd->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(rtc_dd->rtc)) diff --git a/drivers/rtc/rtc-pxa.c b/drivers/rtc/rtc-pxa.c index 34d8545c8e15..62ee6b8f9bcd 100644 --- a/drivers/rtc/rtc-pxa.c +++ b/drivers/rtc/rtc-pxa.c @@ -360,7 +360,7 @@ static int __init pxa_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(dev, 1); + device_init_wakeup(dev, true); return 0; } diff --git a/drivers/rtc/rtc-rc5t583.c b/drivers/rtc/rtc-rc5t583.c index eecb49bab56a..8ba9cda74acf 100644 --- a/drivers/rtc/rtc-rc5t583.c +++ b/drivers/rtc/rtc-rc5t583.c @@ -245,7 +245,7 @@ static int rc5t583_rtc_probe(struct platform_device *pdev) dev_err(&pdev->dev, "IRQ is not free.\n"); return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ricoh_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &rc5t583_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-rc5t619.c b/drivers/rtc/rtc-rc5t619.c index 711f62eecd79..74d169102074 100644 --- a/drivers/rtc/rtc-rc5t619.c +++ b/drivers/rtc/rtc-rc5t619.c @@ -414,7 +414,7 @@ static int rc5t619_rtc_probe(struct platform_device *pdev) } else { /* enable wake */ - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); enable_irq_wake(rtc->irq); } } else { diff --git a/drivers/rtc/rtc-renesas-rtca3.c b/drivers/rtc/rtc-renesas-rtca3.c index d127933bfc8a..a056291d3887 100644 --- a/drivers/rtc/rtc-renesas-rtca3.c +++ b/drivers/rtc/rtc-renesas-rtca3.c @@ -768,7 +768,7 @@ static int rtca3_probe(struct platform_device *pdev) if (ret) return ret; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); priv->rtc_dev = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(priv->rtc_dev)) diff --git a/drivers/rtc/rtc-rk808.c b/drivers/rtc/rtc-rk808.c index 2d9bcb3ce1e3..59b8e9a30fe6 100644 --- a/drivers/rtc/rtc-rk808.c +++ b/drivers/rtc/rtc-rk808.c @@ -418,7 +418,7 @@ static int rk808_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rk808_rtc->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(rk808_rtc->rtc)) diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c index c0ac3bdb2f42..58c957eb753d 100644 --- a/drivers/rtc/rtc-s3c.c +++ b/drivers/rtc/rtc-s3c.c @@ -456,7 +456,7 @@ static int s3c_rtc_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "s3c2410_rtc: RTCCON=%02x\n", readw(info->base + S3C2410_RTCCON)); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); info->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(info->rtc)) { diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c index dad294a0ce2a..36acca5b2639 100644 --- a/drivers/rtc/rtc-s5m.c +++ b/drivers/rtc/rtc-s5m.c @@ -729,7 +729,7 @@ static int s5m_rtc_probe(struct platform_device *pdev) info->irq, ret); return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); } return devm_rtc_register_device(info->rtc_dev); diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index 13799b1abca1..1ad93648d69c 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -292,7 +292,7 @@ static int sa1100_rtc_probe(struct platform_device *pdev) } platform_set_drvdata(pdev, info); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return sa1100_rtc_init(pdev, info); } diff --git a/drivers/rtc/rtc-sc27xx.c b/drivers/rtc/rtc-sc27xx.c index ce7a2ddbbc16..2b83561d4d28 100644 --- a/drivers/rtc/rtc-sc27xx.c +++ b/drivers/rtc/rtc-sc27xx.c @@ -613,14 +613,14 @@ static int sprd_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); rtc->rtc->ops = &sprd_rtc_ops; rtc->rtc->range_min = 0; rtc->rtc->range_max = 5662310399LL; ret = devm_rtc_register_device(rtc->rtc); if (ret) { - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); return ret; } diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c index a5df521876ba..9ea40f40188f 100644 --- a/drivers/rtc/rtc-sh.c +++ b/drivers/rtc/rtc-sh.c @@ -611,7 +611,7 @@ static int __init sh_rtc_probe(struct platform_device *pdev) if (ret) goto err_unmap; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; err_unmap: diff --git a/drivers/rtc/rtc-spear.c b/drivers/rtc/rtc-spear.c index 26eed927f8b3..959acff8faff 100644 --- a/drivers/rtc/rtc-spear.c +++ b/drivers/rtc/rtc-spear.c @@ -395,7 +395,7 @@ static int spear_rtc_probe(struct platform_device *pdev) goto err_disable_clock; if (!device_can_wakeup(&pdev->dev)) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return 0; @@ -411,7 +411,7 @@ static void spear_rtc_remove(struct platform_device *pdev) spear_rtc_disable_interrupt(config); clk_disable_unprepare(config->clk); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/rtc/rtc-stm32.c b/drivers/rtc/rtc-stm32.c index 9f1a019ec8af..a0564d443569 100644 --- a/drivers/rtc/rtc-stm32.c +++ b/drivers/rtc/rtc-stm32.c @@ -1074,26 +1074,18 @@ static int stm32_rtc_probe(struct platform_device *pdev) regs = &rtc->data->regs; if (rtc->data->need_dbp) { - rtc->dbp = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, - "st,syscfg"); + unsigned int args[2]; + + rtc->dbp = syscon_regmap_lookup_by_phandle_args(pdev->dev.of_node, + "st,syscfg", + 2, args); if (IS_ERR(rtc->dbp)) { dev_err(&pdev->dev, "no st,syscfg\n"); return PTR_ERR(rtc->dbp); } - ret = of_property_read_u32_index(pdev->dev.of_node, "st,syscfg", - 1, &rtc->dbp_reg); - if (ret) { - dev_err(&pdev->dev, "can't read DBP register offset\n"); - return ret; - } - - ret = of_property_read_u32_index(pdev->dev.of_node, "st,syscfg", - 2, &rtc->dbp_mask); - if (ret) { - dev_err(&pdev->dev, "can't read DBP register mask\n"); - return ret; - } + rtc->dbp_reg = args[0]; + rtc->dbp_mask = args[1]; } if (!rtc->data->has_pclk) { diff --git a/drivers/rtc/rtc-sun6i.c b/drivers/rtc/rtc-sun6i.c index e681c1745866..e5e6013d080e 100644 --- a/drivers/rtc/rtc-sun6i.c +++ b/drivers/rtc/rtc-sun6i.c @@ -826,7 +826,7 @@ static int sun6i_rtc_probe(struct platform_device *pdev) clk_prepare_enable(chip->losc); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); chip->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(chip->rtc)) diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c index 9b1ce0e8ba27..519a06e728d6 100644 --- a/drivers/rtc/rtc-sunplus.c +++ b/drivers/rtc/rtc-sunplus.c @@ -269,7 +269,7 @@ static int sp_rtc_probe(struct platform_device *plat_dev) if (ret) goto free_reset_assert; - device_init_wakeup(&plat_dev->dev, 1); + device_init_wakeup(&plat_dev->dev, true); dev_set_drvdata(&plat_dev->dev, sp_rtc); sp_rtc->rtc = devm_rtc_allocate_device(&plat_dev->dev); @@ -307,7 +307,7 @@ static void sp_rtc_remove(struct platform_device *plat_dev) { struct sunplus_rtc *sp_rtc = dev_get_drvdata(&plat_dev->dev); - device_init_wakeup(&plat_dev->dev, 0); + device_init_wakeup(&plat_dev->dev, false); reset_control_assert(sp_rtc->rstc); clk_disable_unprepare(sp_rtc->rtcclk); } diff --git a/drivers/rtc/rtc-tegra.c b/drivers/rtc/rtc-tegra.c index 79a3102c8354..46788db89953 100644 --- a/drivers/rtc/rtc-tegra.c +++ b/drivers/rtc/rtc-tegra.c @@ -319,7 +319,7 @@ static int tegra_rtc_probe(struct platform_device *pdev) writel(0xffffffff, info->base + TEGRA_RTC_REG_INTR_STATUS); writel(0, info->base + TEGRA_RTC_REG_INTR_MASK); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); ret = devm_request_irq(&pdev->dev, info->irq, tegra_rtc_irq_handler, IRQF_TRIGGER_HIGH, dev_name(&pdev->dev), diff --git a/drivers/rtc/rtc-test.c b/drivers/rtc/rtc-test.c index 7e0d8fb26465..a68b8c884102 100644 --- a/drivers/rtc/rtc-test.c +++ b/drivers/rtc/rtc-test.c @@ -132,7 +132,7 @@ static int test_probe(struct platform_device *plat_dev) break; default: rtd->rtc->ops = &test_rtc_ops; - device_init_wakeup(&plat_dev->dev, 1); + device_init_wakeup(&plat_dev->dev, true); } timer_setup(&rtd->alarm, test_rtc_alarm_handler, 0); diff --git a/drivers/rtc/rtc-tps6586x.c b/drivers/rtc/rtc-tps6586x.c index e796729fc817..54c8429b16bf 100644 --- a/drivers/rtc/rtc-tps6586x.c +++ b/drivers/rtc/rtc-tps6586x.c @@ -241,7 +241,7 @@ static int tps6586x_rtc_probe(struct platform_device *pdev) return ret; } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); platform_set_drvdata(pdev, rtc); rtc->rtc = devm_rtc_allocate_device(&pdev->dev); diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c index 2ea1bbfbbc2a..284aa2f0392b 100644 --- a/drivers/rtc/rtc-tps65910.c +++ b/drivers/rtc/rtc-tps65910.c @@ -418,7 +418,7 @@ static int tps65910_rtc_probe(struct platform_device *pdev) tps_rtc->irq = irq; if (irq != -1) { if (device_property_present(tps65910->dev, "wakeup-source")) - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); else device_set_wakeup_capable(&pdev->dev, 1); } else { diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c index e69667634137..7c6246e3f029 100644 --- a/drivers/rtc/rtc-tps6594.c +++ b/drivers/rtc/rtc-tps6594.c @@ -37,7 +37,7 @@ #define MAX_OFFSET (277774) // Number of ticks per hour -#define TICKS_PER_HOUR (32768 * 3600) +#define TICKS_PER_HOUR (32768 * 3600LL) // Multiplier for ppb conversions #define PPB_MULT NANO diff --git a/drivers/rtc/rtc-twl.c b/drivers/rtc/rtc-twl.c index 794429182b34..e6106e67e1f4 100644 --- a/drivers/rtc/rtc-twl.c +++ b/drivers/rtc/rtc-twl.c @@ -572,7 +572,7 @@ static int twl_rtc_probe(struct platform_device *pdev) return ret; platform_set_drvdata(pdev, twl_rtc); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); twl_rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &twl_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c index 640833e21057..218316be942a 100644 --- a/drivers/rtc/rtc-wm831x.c +++ b/drivers/rtc/rtc-wm831x.c @@ -420,7 +420,7 @@ static int wm831x_rtc_probe(struct platform_device *pdev) if (ret & WM831X_RTC_ALM_ENA) wm831x_rtc->alarm_enabled = 1; - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); wm831x_rtc->rtc = devm_rtc_allocate_device(&pdev->dev); if (IS_ERR(wm831x_rtc->rtc)) diff --git a/drivers/rtc/rtc-wm8350.c b/drivers/rtc/rtc-wm8350.c index 6797eb4d2e49..3bd60d067a5e 100644 --- a/drivers/rtc/rtc-wm8350.c +++ b/drivers/rtc/rtc-wm8350.c @@ -420,7 +420,7 @@ static int wm8350_rtc_probe(struct platform_device *pdev) } } - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); wm_rtc->rtc = devm_rtc_device_register(&pdev->dev, "wm8350", &wm8350_rtc_ops, THIS_MODULE); diff --git a/drivers/rtc/rtc-xgene.c b/drivers/rtc/rtc-xgene.c index 0813ea1a03c2..6660b664e8dd 100644 --- a/drivers/rtc/rtc-xgene.c +++ b/drivers/rtc/rtc-xgene.c @@ -174,7 +174,7 @@ static int xgene_rtc_probe(struct platform_device *pdev) /* Turn on the clock and the crystal */ writel(RTC_CCR_EN, pdata->csr_base + RTC_CCR); - ret = device_init_wakeup(&pdev->dev, 1); + ret = device_init_wakeup(&pdev->dev, true); if (ret) { clk_disable_unprepare(pdata->clk); return ret; @@ -197,7 +197,7 @@ static void xgene_rtc_remove(struct platform_device *pdev) struct xgene_rtc_dev *pdata = platform_get_drvdata(pdev); xgene_rtc_alarm_irq_enable(&pdev->dev, 0); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); clk_disable_unprepare(pdata->clk); } diff --git a/drivers/rtc/rtc-zynqmp.c b/drivers/rtc/rtc-zynqmp.c index af1abb69d1e3..f39102b66eac 100644 --- a/drivers/rtc/rtc-zynqmp.c +++ b/drivers/rtc/rtc-zynqmp.c @@ -318,8 +318,8 @@ static int xlnx_rtc_probe(struct platform_device *pdev) return ret; } - /* Getting the rtc_clk info */ - xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc_clk"); + /* Getting the rtc info */ + xrtcdev->rtc_clk = devm_clk_get_optional(&pdev->dev, "rtc"); if (IS_ERR(xrtcdev->rtc_clk)) { if (PTR_ERR(xrtcdev->rtc_clk) != -EPROBE_DEFER) dev_warn(&pdev->dev, "Device clock not found.\n"); @@ -337,7 +337,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev) xlnx_init_rtc(xrtcdev); - device_init_wakeup(&pdev->dev, 1); + device_init_wakeup(&pdev->dev, true); return devm_rtc_register_device(xrtcdev->rtc); } @@ -345,7 +345,7 @@ static int xlnx_rtc_probe(struct platform_device *pdev) static void xlnx_rtc_remove(struct platform_device *pdev) { xlnx_rtc_alarm_irq_enable(&pdev->dev, 0); - device_init_wakeup(&pdev->dev, 0); + device_init_wakeup(&pdev->dev, false); } static int __maybe_unused xlnx_rtc_suspend(struct device *dev) diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c index fbffd451031f..45bd001206a2 100644 --- a/drivers/s390/char/sclp.c +++ b/drivers/s390/char/sclp.c @@ -245,7 +245,6 @@ static void sclp_request_timeout(bool force_restart); static void sclp_process_queue(void); static void __sclp_make_read_req(void); static int sclp_init_mask(int calculate); -static int sclp_init(void); static void __sclp_queue_read_req(void) @@ -1251,8 +1250,7 @@ static struct platform_driver sclp_pdrv = { /* Initialize SCLP driver. Return zero if driver is operational, non-zero * otherwise. */ -static int -sclp_init(void) +int sclp_init(void) { unsigned long flags; int rc = 0; @@ -1305,13 +1303,7 @@ fail_unlock: static __init int sclp_initcall(void) { - int rc; - - rc = platform_driver_register(&sclp_pdrv); - if (rc) - return rc; - - return sclp_init(); + return platform_driver_register(&sclp_pdrv); } arch_initcall(sclp_initcall); diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index 3dd50ac9c5b0..b2d93a6e36c4 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -123,7 +123,7 @@ static DECLARE_WAIT_QUEUE_HEAD(read_wait_queue); */ static struct vmlogrdr_priv_t sys_ser[] = { - { .system_service = "*LOGREC ", + { .system_service = { '*', 'L', 'O', 'G', 'R', 'E', 'C', ' ' }, .internal_name = "logrec", .recording_name = "EREP", .minor_num = 0, @@ -132,7 +132,7 @@ static struct vmlogrdr_priv_t sys_ser[] = { .autorecording = 1, .autopurge = 1, }, - { .system_service = "*ACCOUNT", + { .system_service = { '*', 'A', 'C', 'C', 'O', 'U', 'N', 'T' }, .internal_name = "account", .recording_name = "ACCOUNT", .minor_num = 1, @@ -141,7 +141,7 @@ static struct vmlogrdr_priv_t sys_ser[] = { .autorecording = 1, .autopurge = 1, }, - { .system_service = "*SYMPTOM", + { .system_service = { '*', 'S', 'Y', 'M', 'P', 'T', 'O', 'M' }, .internal_name = "symptom", .recording_name = "SYMPTOM", .minor_num = 2, @@ -356,7 +356,7 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp) if (connect_rc) { pr_err("vmlogrdr: iucv connection to %s " "failed with rc %i \n", - logptr->system_service, connect_rc); + logptr->internal_name, connect_rc); goto out_path; } diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c index 4a0b3f19bd8e..4f01b1929240 100644 --- a/drivers/s390/cio/chp.c +++ b/drivers/s390/cio/chp.c @@ -695,7 +695,8 @@ static int info_update(void) if (time_after(jiffies, chp_info_expires)) { /* Data is too old, update. */ rc = sclp_chp_read_info(&chp_info); - chp_info_expires = jiffies + CHP_INFO_UPDATE_INTERVAL ; + if (!rc) + chp_info_expires = jiffies + CHP_INFO_UPDATE_INTERVAL; } mutex_unlock(&info_lock); diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index e36e3ea165d3..2f34761e6413 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -588,6 +588,15 @@ out: return ret; } +static void ism_dev_release(struct device *dev) +{ + struct ism_dev *ism; + + ism = container_of(dev, struct ism_dev, dev); + + kfree(ism); +} + static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct ism_dev *ism; @@ -601,6 +610,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_set_drvdata(&pdev->dev, ism); ism->pdev = pdev; ism->dev.parent = &pdev->dev; + ism->dev.release = ism_dev_release; device_initialize(&ism->dev); dev_set_name(&ism->dev, dev_name(&pdev->dev)); ret = device_add(&ism->dev); @@ -637,7 +647,7 @@ err: device_del(&ism->dev); err_dev: dev_set_drvdata(&pdev->dev, NULL); - kfree(ism); + put_device(&ism->dev); return ret; } @@ -682,7 +692,7 @@ static void ism_remove(struct pci_dev *pdev) pci_disable_device(pdev); device_del(&ism->dev); dev_set_drvdata(&pdev->dev, NULL); - kfree(ism); + put_device(&ism->dev); } static struct pci_driver ism_driver = { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index a3adaec5504e..20328d695ef9 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -7050,14 +7050,16 @@ int qeth_open(struct net_device *dev) card->data.state = CH_STATE_UP; netif_tx_start_all_queues(dev); - local_bh_disable(); qeth_for_each_output_queue(card, queue, i) { netif_napi_add_tx(dev, &queue->napi, qeth_tx_poll); napi_enable(&queue->napi); - napi_schedule(&queue->napi); } - napi_enable(&card->napi); + + local_bh_disable(); + qeth_for_each_output_queue(card, queue, i) { + napi_schedule(&queue->napi); + } napi_schedule(&card->napi); /* kick-start the NAPI softirq: */ local_bh_enable(); diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c index 1fd2da0264e3..47d74f881948 100644 --- a/drivers/scsi/qla1280.c +++ b/drivers/scsi/qla1280.c @@ -2867,7 +2867,7 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp) dprintk(3, "S/G Segment phys_addr=%x %x, len=0x%x\n", cpu_to_le32(upper_32_bits(dma_handle)), cpu_to_le32(lower_32_bits(dma_handle)), - cpu_to_le32(sg_dma_len(sg_next(s)))); + cpu_to_le32(sg_dma_len(s))); remseg--; } dprintk(5, "qla1280_64bit_start_scsi: Scatter/gather " diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index e7ea1f04164a..be0890e4e706 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -872,13 +872,18 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) case 0x1a: /* start stop unit in progress */ case 0x1b: /* sanitize in progress */ case 0x1d: /* configuration in progress */ - case 0x24: /* depopulation in progress */ - case 0x25: /* depopulation restore in progress */ action = ACTION_DELAYED_RETRY; break; case 0x0a: /* ALUA state transition */ action = ACTION_DELAYED_REPREP; break; + /* + * Depopulation might take many hours, + * thus it is not worthwhile to retry. + */ + case 0x24: /* depopulation in progress */ + case 0x25: /* depopulation restore in progress */ + fallthrough; default: action = ACTION_FAIL; break; @@ -2736,6 +2741,7 @@ int scsi_device_quiesce(struct scsi_device *sdev) { struct request_queue *q = sdev->request_queue; + unsigned int memflags; int err; /* @@ -2750,7 +2756,7 @@ scsi_device_quiesce(struct scsi_device *sdev) blk_set_pm_only(q); - blk_mq_freeze_queue(q); + memflags = blk_mq_freeze_queue(q); /* * Ensure that the effect of blk_set_pm_only() will be visible * for percpu_ref_tryget() callers that occur after the queue @@ -2758,7 +2764,7 @@ scsi_device_quiesce(struct scsi_device *sdev) * was called. See also https://lwn.net/Articles/573497/. */ synchronize_rcu(); - blk_mq_unfreeze_queue(q); + blk_mq_unfreeze_queue(q, memflags); mutex_lock(&sdev->state_mutex); err = scsi_device_set_state(sdev, SDEV_QUIESCE); diff --git a/drivers/scsi/scsi_lib_test.c b/drivers/scsi/scsi_lib_test.c index 99834426a100..ae8af0e0047a 100644 --- a/drivers/scsi/scsi_lib_test.c +++ b/drivers/scsi/scsi_lib_test.c @@ -67,6 +67,13 @@ static void scsi_lib_test_multiple_sense(struct kunit *test) }; int i; + /* Success */ + sc.result = 0; + KUNIT_EXPECT_EQ(test, 0, scsi_check_passthrough(&sc, &failures)); + KUNIT_EXPECT_EQ(test, 0, scsi_check_passthrough(&sc, NULL)); + /* Command failed but caller did not pass in a failures array */ + scsi_build_sense(&sc, 0, ILLEGAL_REQUEST, 0x91, 0x36); + KUNIT_EXPECT_EQ(test, 0, scsi_check_passthrough(&sc, NULL)); /* Match end of array */ scsi_build_sense(&sc, 0, ILLEGAL_REQUEST, 0x91, 0x36); KUNIT_EXPECT_EQ(test, -EAGAIN, scsi_check_passthrough(&sc, &failures)); diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index f2093982b3db..96d7e1a9a7c7 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -220,6 +220,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, int new_shift = sbitmap_calculate_shift(depth); bool need_alloc = !sdev->budget_map.map; bool need_free = false; + unsigned int memflags; int ret; struct sbitmap sb_backup; @@ -240,12 +241,12 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, * and here disk isn't added yet, so freezing is pretty fast */ if (need_free) { - blk_mq_freeze_queue(sdev->request_queue); + memflags = blk_mq_freeze_queue(sdev->request_queue); sb_backup = sdev->budget_map; } ret = sbitmap_init_node(&sdev->budget_map, scsi_device_max_queue_depth(sdev), - new_shift, GFP_KERNEL, + new_shift, GFP_NOIO, sdev->request_queue->node, false, true); if (!ret) sbitmap_resize(&sdev->budget_map, depth); @@ -256,7 +257,7 @@ static int scsi_realloc_sdev_budget_map(struct scsi_device *sdev, else sbitmap_free(&sb_backup); ret = 0; - blk_mq_unfreeze_queue(sdev->request_queue); + blk_mq_unfreeze_queue(sdev->request_queue, memflags); } return ret; } diff --git a/drivers/scsi/scsi_sysctl.c b/drivers/scsi/scsi_sysctl.c index 093774d77534..be4aef0f4f99 100644 --- a/drivers/scsi/scsi_sysctl.c +++ b/drivers/scsi/scsi_sysctl.c @@ -12,7 +12,7 @@ #include "scsi_priv.h" -static struct ctl_table scsi_table[] = { +static const struct ctl_table scsi_table[] = { { .procname = "logging_level", .data = &scsi_logging_level, .maxlen = sizeof(scsi_logging_level), diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 94127868bedf..effb7e768165 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1639,7 +1639,7 @@ MODULE_PARM_DESC(allow_dio, "allow direct I/O (default: 0 (disallow))"); #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> -static struct ctl_table sg_sysctls[] = { +static const struct ctl_table sg_sysctls[] = { { .procname = "sg-big-buff", .data = &sg_big_buff, diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 5a101ac06c47..a8614e54544e 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1800,6 +1800,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) length = scsi_bufflen(scmnd); payload = (struct vmbus_packet_mpb_array *)&cmd_request->mpb; + payload->range.len = 0; payload_sz = 0; if (scsi_sg_count(scmnd)) { diff --git a/drivers/soc/qcom/smp2p.c b/drivers/soc/qcom/smp2p.c index 4783ab1adb8d..a3e88ced328a 100644 --- a/drivers/soc/qcom/smp2p.c +++ b/drivers/soc/qcom/smp2p.c @@ -365,7 +365,7 @@ static void smp2p_irq_print_chip(struct irq_data *irqd, struct seq_file *p) { struct smp2p_entry *entry = irq_data_get_irq_chip_data(irqd); - seq_printf(p, " %8s", dev_name(entry->smp2p->dev)); + seq_printf(p, "%8s", dev_name(entry->smp2p->dev)); } static struct irq_chip smp2p_irq_chip = { diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c index 96a7f9709720..5a54b10daf77 100644 --- a/drivers/soundwire/amd_manager.c +++ b/drivers/soundwire/amd_manager.c @@ -384,7 +384,7 @@ static u32 amd_sdw_read_ping_status(struct sdw_bus *bus) return slave_stat; } -static int amd_sdw_compute_params(struct sdw_bus *bus) +static int amd_sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { struct sdw_transport_data t_data = {0}; struct sdw_master_runtime *m_rt; @@ -410,7 +410,7 @@ static int amd_sdw_compute_params(struct sdw_bus *bus) sdw_fill_xport_params(&p_rt->transport_params, p_rt->num, false, SDW_BLK_GRP_CNT_1, sample_int, port_bo, port_bo >> 8, hstart, hstop, - SDW_BLK_PKG_PER_PORT, 0x0); + SDW_BLK_PKG_PER_PORT, p_rt->lane); sdw_fill_port_params(&p_rt->port_params, p_rt->num, bps, @@ -1190,6 +1190,7 @@ static int __maybe_unused amd_resume_runtime(struct device *dev) if (amd_manager->power_mode_mask & AMD_SDW_CLK_STOP_MODE) { return amd_sdw_clock_stop_exit(amd_manager); } else if (amd_manager->power_mode_mask & AMD_SDW_POWER_OFF_MODE) { + writel(0x00, amd_manager->acp_mmio + ACP_SW_WAKE_EN(amd_manager->instance)); val = readl(amd_manager->mmio + ACP_SW_CLK_RESUME_CTRL); if (val) { val |= AMD_SDW_CLK_RESUME_REQ; diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index d1dc62c34f1c..9b295fc9acd5 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -813,6 +813,16 @@ void sdw_extract_slave_id(struct sdw_bus *bus, } EXPORT_SYMBOL(sdw_extract_slave_id); +bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave) +{ + /* + * Dynamic scaling is a defined by SDCA. However, some devices expose the class ID but + * can't support dynamic scaling. We might need a quirk to handle such devices. + */ + return slave->id.class_id; +} +EXPORT_SYMBOL(is_clock_scaling_supported_by_slave); + static int sdw_program_device_num(struct sdw_bus *bus, bool *programmed) { u8 buf[SDW_NUM_DEV_ID_REGISTERS] = {0}; @@ -1276,23 +1286,12 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave, return ret; } -static int sdw_slave_set_frequency(struct sdw_slave *slave) +int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base) { u32 mclk_freq = slave->bus->prop.mclk_freq; u32 curr_freq = slave->bus->params.curr_dr_freq >> 1; unsigned int scale; u8 scale_index; - u8 base; - int ret; - - /* - * frequency base and scale registers are required for SDCA - * devices. They may also be used for 1.2+/non-SDCA devices. - * Driver can set the property, we will need a DisCo property - * to discover this case from platform firmware. - */ - if (!slave->id.class_id && !slave->prop.clock_reg_supported) - return 0; if (!mclk_freq) { dev_err(&slave->dev, @@ -1311,19 +1310,19 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave) */ if (!(19200000 % mclk_freq)) { mclk_freq = 19200000; - base = SDW_SCP_BASE_CLOCK_19200000_HZ; + *base = SDW_SCP_BASE_CLOCK_19200000_HZ; } else if (!(22579200 % mclk_freq)) { mclk_freq = 22579200; - base = SDW_SCP_BASE_CLOCK_22579200_HZ; + *base = SDW_SCP_BASE_CLOCK_22579200_HZ; } else if (!(24576000 % mclk_freq)) { mclk_freq = 24576000; - base = SDW_SCP_BASE_CLOCK_24576000_HZ; + *base = SDW_SCP_BASE_CLOCK_24576000_HZ; } else if (!(32000000 % mclk_freq)) { mclk_freq = 32000000; - base = SDW_SCP_BASE_CLOCK_32000000_HZ; + *base = SDW_SCP_BASE_CLOCK_32000000_HZ; } else if (!(96000000 % mclk_freq)) { mclk_freq = 24000000; - base = SDW_SCP_BASE_CLOCK_24000000_HZ; + *base = SDW_SCP_BASE_CLOCK_24000000_HZ; } else { dev_err(&slave->dev, "Unsupported clock base, mclk %d\n", @@ -1354,6 +1353,34 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave) } scale_index++; + dev_dbg(&slave->dev, + "Configured bus base %d, scale %d, mclk %d, curr_freq %d\n", + *base, scale_index, mclk_freq, curr_freq); + + return scale_index; +} +EXPORT_SYMBOL(sdw_slave_get_scale_index); + +static int sdw_slave_set_frequency(struct sdw_slave *slave) +{ + int scale_index; + u8 base; + int ret; + + /* + * frequency base and scale registers are required for SDCA + * devices. They may also be used for 1.2+/non-SDCA devices. + * Driver can set the property directly, for now there's no + * DisCo property to discover support for the scaling registers + * from platform firmware. + */ + if (!slave->id.class_id && !slave->prop.clock_reg_supported) + return 0; + + scale_index = sdw_slave_get_scale_index(slave, &base); + if (scale_index < 0) + return scale_index; + ret = sdw_write_no_pm(slave, SDW_SCP_BUS_CLOCK_BASE, base); if (ret < 0) { dev_err(&slave->dev, @@ -1373,10 +1400,6 @@ static int sdw_slave_set_frequency(struct sdw_slave *slave) dev_err(&slave->dev, "SDW_SCP_BUSCLOCK_SCALE_B1 write failed:%d\n", ret); - dev_dbg(&slave->dev, - "Configured bus base %d, scale %d, mclk %d, curr_freq %d\n", - base, scale_index, mclk_freq, curr_freq); - return ret; } diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h index fda6b24ac2da..fc990171b3f7 100644 --- a/drivers/soundwire/bus.h +++ b/drivers/soundwire/bus.h @@ -90,6 +90,7 @@ int sdw_find_col_index(int col); * @transport_params: Transport parameters * @port_params: Port parameters * @port_node: List node for Master or Slave port_list + * @lane: Which lane is used * * SoundWire spec has no mention of ports for Master interface but the * concept is logically extended. @@ -100,6 +101,7 @@ struct sdw_port_runtime { struct sdw_transport_params transport_params; struct sdw_port_params port_params; struct list_head port_node; + unsigned int lane; }; /** @@ -149,6 +151,7 @@ struct sdw_transport_data { int hstop; int block_offset; int sub_block_offset; + unsigned int lane; }; struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave, diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 77dc094075e1..e98d5db81b1c 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -167,9 +167,6 @@ static int sdw_drv_remove(struct device *dev) slave->probed = false; - if (slave->prop.use_domain_irq) - sdw_irq_dispose_mapping(slave); - mutex_unlock(&slave->sdw_dev_lock); if (drv->remove) diff --git a/drivers/soundwire/generic_bandwidth_allocation.c b/drivers/soundwire/generic_bandwidth_allocation.c index b9316207c3ab..59965f43c2fb 100644 --- a/drivers/soundwire/generic_bandwidth_allocation.c +++ b/drivers/soundwire/generic_bandwidth_allocation.c @@ -18,6 +18,7 @@ struct sdw_group_params { unsigned int rate; + unsigned int lane; int full_bw; int payload_bw; int hwidth; @@ -27,6 +28,7 @@ struct sdw_group { unsigned int count; unsigned int max_size; unsigned int *rates; + unsigned int *lanes; }; void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, @@ -48,6 +50,9 @@ void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, slave_total_ch = 0; list_for_each_entry(p_rt, &s_rt->port_list, port_node) { + if (p_rt->lane != t_data->lane) + continue; + ch = hweight32(p_rt->ch_mask); sdw_fill_xport_params(&p_rt->transport_params, @@ -56,7 +61,7 @@ void sdw_compute_slave_ports(struct sdw_master_runtime *m_rt, sample_int, port_bo, port_bo >> 8, t_data->hstart, t_data->hstop, - SDW_BLK_PKG_PER_PORT, 0x0); + SDW_BLK_PKG_PER_PORT, p_rt->lane); sdw_fill_port_params(&p_rt->port_params, p_rt->num, bps, @@ -105,11 +110,13 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt, t_data.hstart = hstart; list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + if (p_rt->lane != params->lane) + continue; sdw_fill_xport_params(&p_rt->transport_params, p_rt->num, false, SDW_BLK_GRP_CNT_1, sample_int, *port_bo, (*port_bo) >> 8, hstart, hstop, - SDW_BLK_PKG_PER_PORT, 0x0); + SDW_BLK_PKG_PER_PORT, p_rt->lane); sdw_fill_port_params(&p_rt->port_params, p_rt->num, bps, @@ -131,6 +138,7 @@ static void sdw_compute_master_ports(struct sdw_master_runtime *m_rt, (*port_bo) += bps * ch; } + t_data.lane = params->lane; sdw_compute_slave_ports(m_rt, &t_data); } @@ -138,69 +146,107 @@ static void _sdw_compute_port_params(struct sdw_bus *bus, struct sdw_group_params *params, int count) { struct sdw_master_runtime *m_rt; - int hstop = bus->params.col - 1; - int port_bo, i; + int port_bo, i, l; + int hstop; /* Run loop for all groups to compute transport parameters */ - for (i = 0; i < count; i++) { - port_bo = 1; + for (l = 0; l < SDW_MAX_LANES; l++) { + if (l > 0 && !bus->lane_used_bandwidth[l]) + continue; + /* reset hstop for each lane */ + hstop = bus->params.col - 1; + for (i = 0; i < count; i++) { + if (params[i].lane != l) + continue; + port_bo = 1; - list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { - sdw_compute_master_ports(m_rt, ¶ms[i], &port_bo, hstop); - } + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { + sdw_compute_master_ports(m_rt, ¶ms[i], &port_bo, hstop); + } - hstop = hstop - params[i].hwidth; + hstop = hstop - params[i].hwidth; + } } } static int sdw_compute_group_params(struct sdw_bus *bus, + struct sdw_stream_runtime *stream, struct sdw_group_params *params, - int *rates, int count) + struct sdw_group *group) { struct sdw_master_runtime *m_rt; + struct sdw_port_runtime *p_rt; int sel_col = bus->params.col; unsigned int rate, bps, ch; - int i, column_needed = 0; + int i, l, column_needed; /* Calculate bandwidth per group */ - for (i = 0; i < count; i++) { - params[i].rate = rates[i]; + for (i = 0; i < group->count; i++) { + params[i].rate = group->rates[i]; + params[i].lane = group->lanes[i]; params[i].full_bw = bus->params.curr_dr_freq / params[i].rate; } list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { - rate = m_rt->stream->params.rate; - bps = m_rt->stream->params.bps; - ch = m_rt->ch_count; + if (m_rt->stream == stream) { + /* Only runtime during prepare should be added */ + if (stream->state != SDW_STREAM_CONFIGURED) + continue; + } else { + /* + * Include runtimes with running (ENABLED state) and paused (DISABLED state) + * streams + */ + if (m_rt->stream->state != SDW_STREAM_ENABLED && + m_rt->stream->state != SDW_STREAM_DISABLED) + continue; + } + list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + rate = m_rt->stream->params.rate; + bps = m_rt->stream->params.bps; + ch = hweight32(p_rt->ch_mask); - for (i = 0; i < count; i++) { - if (rate == params[i].rate) - params[i].payload_bw += bps * ch; + for (i = 0; i < group->count; i++) { + if (rate == params[i].rate && p_rt->lane == params[i].lane) + params[i].payload_bw += bps * ch; + } } } - for (i = 0; i < count; i++) { - params[i].hwidth = (sel_col * - params[i].payload_bw + params[i].full_bw - 1) / - params[i].full_bw; + for (l = 0; l < SDW_MAX_LANES; l++) { + if (l > 0 && !bus->lane_used_bandwidth[l]) + continue; + /* reset column_needed for each lane */ + column_needed = 0; + for (i = 0; i < group->count; i++) { + if (params[i].lane != l) + continue; + + params[i].hwidth = (sel_col * params[i].payload_bw + + params[i].full_bw - 1) / params[i].full_bw; - column_needed += params[i].hwidth; + column_needed += params[i].hwidth; + /* There is no control column for lane 1 and above */ + if (column_needed > sel_col) + return -EINVAL; + /* Column 0 is control column on lane 0 */ + if (params[i].lane == 0 && column_needed > sel_col - 1) + return -EINVAL; + } } - if (column_needed > sel_col - 1) - return -EINVAL; return 0; } static int sdw_add_element_group_count(struct sdw_group *group, - unsigned int rate) + unsigned int rate, unsigned int lane) { int num = group->count; int i; for (i = 0; i <= num; i++) { - if (rate == group->rates[i]) + if (rate == group->rates[i] && lane == group->lanes[i]) break; if (i != num) @@ -208,6 +254,7 @@ static int sdw_add_element_group_count(struct sdw_group *group, if (group->count >= group->max_size) { unsigned int *rates; + unsigned int *lanes; group->max_size += 1; rates = krealloc(group->rates, @@ -215,10 +262,20 @@ static int sdw_add_element_group_count(struct sdw_group *group, GFP_KERNEL); if (!rates) return -ENOMEM; + group->rates = rates; + + lanes = krealloc(group->lanes, + (sizeof(int) * group->max_size), + GFP_KERNEL); + if (!lanes) + return -ENOMEM; + + group->lanes = lanes; } - group->rates[group->count++] = rate; + group->rates[group->count] = rate; + group->lanes[group->count++] = lane; } return 0; @@ -228,6 +285,7 @@ static int sdw_get_group_count(struct sdw_bus *bus, struct sdw_group *group) { struct sdw_master_runtime *m_rt; + struct sdw_port_runtime *p_rt; unsigned int rate; int ret = 0; @@ -237,17 +295,32 @@ static int sdw_get_group_count(struct sdw_bus *bus, if (!group->rates) return -ENOMEM; + group->lanes = kcalloc(group->max_size, sizeof(int), GFP_KERNEL); + if (!group->lanes) { + kfree(group->rates); + group->rates = NULL; + return -ENOMEM; + } + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { + if (m_rt->stream->state == SDW_STREAM_DEPREPARED) + continue; + rate = m_rt->stream->params.rate; if (m_rt == list_first_entry(&bus->m_rt_list, struct sdw_master_runtime, bus_node)) { group->rates[group->count++] = rate; - - } else { - ret = sdw_add_element_group_count(group, rate); + } + /* + * Different ports could use different lane, add group element + * even if m_rt is the first entry + */ + list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + ret = sdw_add_element_group_count(group, rate, p_rt->lane); if (ret < 0) { kfree(group->rates); + kfree(group->lanes); return ret; } } @@ -260,8 +333,9 @@ static int sdw_get_group_count(struct sdw_bus *bus, * sdw_compute_port_params: Compute transport and port parameters * * @bus: SDW Bus instance + * @stream: Soundwire stream */ -static int sdw_compute_port_params(struct sdw_bus *bus) +static int sdw_compute_port_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { struct sdw_group_params *params = NULL; struct sdw_group group; @@ -281,8 +355,7 @@ static int sdw_compute_port_params(struct sdw_bus *bus) } /* Compute transport parameters for grouped streams */ - ret = sdw_compute_group_params(bus, params, - &group.rates[0], group.count); + ret = sdw_compute_group_params(bus, stream, params, &group); if (ret < 0) goto free_params; @@ -292,6 +365,7 @@ free_params: kfree(params); out: kfree(group.rates); + kfree(group.lanes); return ret; } @@ -299,7 +373,6 @@ out: static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) { struct sdw_master_prop *prop = &bus->prop; - int frame_int, frame_freq; int r, c; for (c = 0; c < SDW_FRAME_COLS; c++) { @@ -308,11 +381,8 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) sdw_cols[c] != prop->default_col) continue; - frame_int = sdw_rows[r] * sdw_cols[c]; - frame_freq = clk_freq / frame_int; - - if ((clk_freq - (frame_freq * SDW_FRAME_CTRL_BITS)) < - bus->params.bandwidth) + if (clk_freq * (sdw_cols[c] - 1) < + bus->params.bandwidth * sdw_cols[c]) continue; bus->params.row = sdw_rows[r]; @@ -324,6 +394,95 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) return -EINVAL; } +static bool is_clock_scaling_supported(struct sdw_bus *bus) +{ + struct sdw_master_runtime *m_rt; + struct sdw_slave_runtime *s_rt; + + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) + list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) + if (!is_clock_scaling_supported_by_slave(s_rt->slave)) + return false; + + return true; +} + +/** + * is_lane_connected_to_all_peripherals: Check if the given manager lane connects to all peripherals + * So that all peripherals can use the manager lane. + * + * @m_rt: Manager runtime + * @lane: Lane number + */ +static bool is_lane_connected_to_all_peripherals(struct sdw_master_runtime *m_rt, unsigned int lane) +{ + struct sdw_slave_prop *slave_prop; + struct sdw_slave_runtime *s_rt; + int i; + + list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { + slave_prop = &s_rt->slave->prop; + for (i = 1; i < SDW_MAX_LANES; i++) { + if (slave_prop->lane_maps[i] == lane) { + dev_dbg(&s_rt->slave->dev, + "M lane %d is connected to P lane %d\n", + lane, i); + break; + } + } + if (i == SDW_MAX_LANES) { + dev_dbg(&s_rt->slave->dev, "M lane %d is not connected\n", lane); + return false; + } + } + return true; +} + +static int get_manager_lane(struct sdw_bus *bus, struct sdw_master_runtime *m_rt, + struct sdw_slave_runtime *s_rt, unsigned int curr_dr_freq) +{ + struct sdw_slave_prop *slave_prop = &s_rt->slave->prop; + struct sdw_port_runtime *m_p_rt; + unsigned int required_bandwidth; + int m_lane; + int l; + + for (l = 1; l < SDW_MAX_LANES; l++) { + if (!slave_prop->lane_maps[l]) + continue; + + required_bandwidth = 0; + list_for_each_entry(m_p_rt, &m_rt->port_list, port_node) { + required_bandwidth += m_rt->stream->params.rate * + hweight32(m_p_rt->ch_mask) * + m_rt->stream->params.bps; + } + if (required_bandwidth <= + curr_dr_freq - bus->lane_used_bandwidth[l]) { + /* Check if m_lane is connected to all Peripherals */ + if (!is_lane_connected_to_all_peripherals(m_rt, + slave_prop->lane_maps[l])) { + dev_dbg(bus->dev, + "Not all Peripherals are connected to M lane %d\n", + slave_prop->lane_maps[l]); + continue; + } + m_lane = slave_prop->lane_maps[l]; + dev_dbg(&s_rt->slave->dev, "M lane %d is used\n", m_lane); + bus->lane_used_bandwidth[l] += required_bandwidth; + /* + * Use non-zero manager lane, subtract the lane 0 + * bandwidth that is already calculated + */ + bus->params.bandwidth -= required_bandwidth; + return m_lane; + } + } + + /* No available multi lane found, only lane 0 can be used */ + return 0; +} + /** * sdw_compute_bus_params: Compute bus parameters * @@ -331,10 +490,16 @@ static int sdw_select_row_col(struct sdw_bus *bus, int clk_freq) */ static int sdw_compute_bus_params(struct sdw_bus *bus) { - unsigned int curr_dr_freq = 0; struct sdw_master_prop *mstr_prop = &bus->prop; - int i, clk_values, ret; + struct sdw_slave_prop *slave_prop; + struct sdw_port_runtime *m_p_rt; + struct sdw_port_runtime *s_p_rt; + struct sdw_master_runtime *m_rt; + struct sdw_slave_runtime *s_rt; + unsigned int curr_dr_freq = 0; + int i, l, clk_values, ret; bool is_gear = false; + int m_lane = 0; u32 *clk_buf; if (mstr_prop->num_clk_gears) { @@ -349,6 +514,10 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) clk_buf = NULL; } + /* If dynamic scaling is not supported, don't try higher freq */ + if (!is_clock_scaling_supported(bus)) + clk_values = 1; + for (i = 0; i < clk_values; i++) { if (!clk_buf) curr_dr_freq = bus->params.max_dr_freq; @@ -357,10 +526,26 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) (bus->params.max_dr_freq >> clk_buf[i]) : clk_buf[i] * SDW_DOUBLE_RATE_FACTOR; - if (curr_dr_freq <= bus->params.bandwidth) - continue; + if (curr_dr_freq * (mstr_prop->default_col - 1) >= + bus->params.bandwidth * mstr_prop->default_col) + break; - break; + list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { + /* + * Get the first s_rt that will be used to find the available lane that + * can be used. No need to check all Peripherals because we can't use + * multi-lane if we can't find any available lane for the first Peripheral. + */ + s_rt = list_first_entry(&m_rt->slave_rt_list, + struct sdw_slave_runtime, m_rt_node); + + /* + * Find the available Manager lane that connected to the first Peripheral. + */ + m_lane = get_manager_lane(bus, m_rt, s_rt, curr_dr_freq); + if (m_lane > 0) + goto out; + } /* * TODO: Check all the Slave(s) port(s) audio modes and find @@ -374,6 +559,38 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) __func__, bus->params.bandwidth); return -EINVAL; } +out: + /* multilane can be used */ + if (m_lane > 0) { + /* Set Peripheral lanes */ + list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { + slave_prop = &s_rt->slave->prop; + for (l = 1; l < SDW_MAX_LANES; l++) { + if (slave_prop->lane_maps[l] == m_lane) { + list_for_each_entry(s_p_rt, &s_rt->port_list, port_node) { + s_p_rt->lane = l; + dev_dbg(&s_rt->slave->dev, + "Set P lane %d for port %d\n", + l, s_p_rt->num); + } + break; + } + } + } + /* + * Set Manager lanes. Configure the last m_rt in bus->m_rt_list only since + * we don't want to touch other m_rts that are already working. + */ + list_for_each_entry(m_p_rt, &m_rt->port_list, port_node) { + m_p_rt->lane = m_lane; + } + } + + if (!mstr_prop->default_frame_rate || !mstr_prop->default_row) + return -EINVAL; + + mstr_prop->default_col = curr_dr_freq / mstr_prop->default_frame_rate / + mstr_prop->default_row; ret = sdw_select_row_col(bus, curr_dr_freq); if (ret < 0) { @@ -390,8 +607,9 @@ static int sdw_compute_bus_params(struct sdw_bus *bus) * sdw_compute_params: Compute bus, transport and port parameters * * @bus: SDW Bus instance + * @stream: Soundwire stream */ -int sdw_compute_params(struct sdw_bus *bus) +int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { int ret; @@ -401,7 +619,7 @@ int sdw_compute_params(struct sdw_bus *bus) return ret; /* Compute transport and port params */ - ret = sdw_compute_port_params(bus); + ret = sdw_compute_port_params(bus, stream); if (ret < 0) { dev_err(bus->dev, "Compute transport params failed: %d\n", ret); return ret; diff --git a/drivers/soundwire/irq.c b/drivers/soundwire/irq.c index 0c08cebb1235..c237e6d0766b 100644 --- a/drivers/soundwire/irq.c +++ b/drivers/soundwire/irq.c @@ -46,14 +46,18 @@ void sdw_irq_delete(struct sdw_bus *bus) irq_domain_remove(bus->domain); } +static void sdw_irq_dispose_mapping(void *data) +{ + struct sdw_slave *slave = data; + + irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num)); +} + void sdw_irq_create_mapping(struct sdw_slave *slave) { slave->irq = irq_create_mapping(slave->bus->domain, slave->dev_num); if (!slave->irq) dev_warn(&slave->dev, "Failed to map IRQ\n"); -} -void sdw_irq_dispose_mapping(struct sdw_slave *slave) -{ - irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num)); + devm_add_action_or_reset(&slave->dev, sdw_irq_dispose_mapping, slave); } diff --git a/drivers/soundwire/irq.h b/drivers/soundwire/irq.h index 58a58046d92b..86e2318409da 100644 --- a/drivers/soundwire/irq.h +++ b/drivers/soundwire/irq.h @@ -16,7 +16,6 @@ int sdw_irq_create(struct sdw_bus *bus, struct fwnode_handle *fwnode); void sdw_irq_delete(struct sdw_bus *bus); void sdw_irq_create_mapping(struct sdw_slave *slave); -void sdw_irq_dispose_mapping(struct sdw_slave *slave); #else /* CONFIG_IRQ_DOMAIN */ @@ -34,10 +33,6 @@ static inline void sdw_irq_create_mapping(struct sdw_slave *slave) { } -static inline void sdw_irq_dispose_mapping(struct sdw_slave *slave) -{ -} - #endif /* CONFIG_IRQ_DOMAIN */ #endif /* __SDW_IRQ_H */ diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c index 9d59f486edbe..65afb28ef8fa 100644 --- a/drivers/soundwire/mipi_disco.c +++ b/drivers/soundwire/mipi_disco.c @@ -366,6 +366,44 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, return 0; } +/* + * In MIPI DisCo spec for SoundWire, lane mapping for a slave device is done with + * mipi-sdw-lane-x-mapping properties, where x is 1..7, and the values for those + * properties are mipi-sdw-manager-lane-x or mipi-sdw-peripheral-link-y, where x + * is an integer between 1 to 7 if the lane is connected to a manager lane, y is a + * character between A to E if the lane is connected to another peripheral lane. + */ +int sdw_slave_read_lane_mapping(struct sdw_slave *slave) +{ + struct sdw_slave_prop *prop = &slave->prop; + struct device *dev = &slave->dev; + char prop_name[30]; + const char *prop_val; + size_t len; + int ret, i; + u8 lane; + + for (i = 0; i < SDW_MAX_LANES; i++) { + snprintf(prop_name, sizeof(prop_name), "mipi-sdw-lane-%d-mapping", i); + ret = device_property_read_string(dev, prop_name, &prop_val); + if (ret) + continue; + + len = strlen(prop_val); + if (len < 1) + return -EINVAL; + + /* The last character is enough to identify the connection */ + ret = kstrtou8(&prop_val[len - 1], 10, &lane); + if (ret) + return ret; + if (in_range(lane, 1, SDW_MAX_LANES - 1)) + prop->lane_maps[i] = lane; + } + return 0; +} +EXPORT_SYMBOL(sdw_slave_read_lane_mapping); + /** * sdw_slave_read_prop() - Read Slave properties * @slave: SDW Slave @@ -486,6 +524,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave) sdw_slave_read_dpn(slave, prop->sink_dpn_prop, nval, prop->sink_ports, "sink"); - return 0; + return sdw_slave_read_lane_mapping(slave); } EXPORT_SYMBOL(sdw_slave_read_prop); diff --git a/drivers/soundwire/qcom.c b/drivers/soundwire/qcom.c index e00c5ac496a6..0f45e3404756 100644 --- a/drivers/soundwire/qcom.c +++ b/drivers/soundwire/qcom.c @@ -1072,7 +1072,7 @@ static const struct sdw_master_ops qcom_swrm_ops = { .pre_bank_switch = qcom_swrm_pre_bank_switch, }; -static int qcom_swrm_compute_params(struct sdw_bus *bus) +static int qcom_swrm_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream) { struct qcom_swrm_ctrl *ctrl = to_qcom_sdw(bus); struct sdw_master_runtime *m_rt; diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 7aa4900dcf31..e9df503332bb 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -629,8 +629,44 @@ static int sdw_notify_config(struct sdw_master_runtime *m_rt) static int sdw_program_params(struct sdw_bus *bus, bool prepare) { struct sdw_master_runtime *m_rt; + struct sdw_slave *slave; int ret = 0; + u32 addr1; + + /* Check if all Peripherals comply with SDCA */ + list_for_each_entry(slave, &bus->slaves, node) { + if (!slave->dev_num_sticky) + continue; + if (!is_clock_scaling_supported_by_slave(slave)) { + dev_dbg(&slave->dev, "The Peripheral doesn't comply with SDCA\n"); + goto manager_runtime; + } + } + + if (bus->params.next_bank) + addr1 = SDW_SCP_BUSCLOCK_SCALE_B1; + else + addr1 = SDW_SCP_BUSCLOCK_SCALE_B0; + + /* Program SDW_SCP_BUSCLOCK_SCALE if all Peripherals comply with SDCA */ + list_for_each_entry(slave, &bus->slaves, node) { + int scale_index; + u8 base; + + if (!slave->dev_num_sticky) + continue; + scale_index = sdw_slave_get_scale_index(slave, &base); + if (scale_index < 0) + return scale_index; + + ret = sdw_write_no_pm(slave, addr1, scale_index); + if (ret < 0) { + dev_err(&slave->dev, "SDW_SCP_BUSCLOCK_SCALE register write failed\n"); + return ret; + } + } +manager_runtime: list_for_each_entry(m_rt, &bus->m_rt_list, bus_node) { /* @@ -1383,7 +1419,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream, /* Compute params */ if (bus->compute_params) { - ret = bus->compute_params(bus); + ret = bus->compute_params(bus, stream); if (ret < 0) { dev_err(bus->dev, "Compute params failed: %d\n", ret); @@ -1642,9 +1678,19 @@ EXPORT_SYMBOL(sdw_disable_stream); static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) { struct sdw_master_runtime *m_rt; + struct sdw_port_runtime *p_rt; + unsigned int multi_lane_bandwidth; + unsigned int bandwidth; struct sdw_bus *bus; + int state = stream->state; int ret = 0; + /* + * first mark the state as DEPREPARED so that it is not taken into account + * for bit allocation + */ + stream->state = SDW_STREAM_DEPREPARED; + list_for_each_entry(m_rt, &stream->master_list, stream_node) { bus = m_rt->bus; /* De-prepare port(s) */ @@ -1652,19 +1698,34 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) if (ret < 0) { dev_err(bus->dev, "De-prepare port(s) failed: %d\n", ret); + stream->state = state; return ret; } + multi_lane_bandwidth = 0; + + list_for_each_entry(p_rt, &m_rt->port_list, port_node) { + if (!p_rt->lane) + continue; + + bandwidth = m_rt->stream->params.rate * hweight32(p_rt->ch_mask) * + m_rt->stream->params.bps; + multi_lane_bandwidth += bandwidth; + bus->lane_used_bandwidth[p_rt->lane] -= bandwidth; + if (!bus->lane_used_bandwidth[p_rt->lane]) + p_rt->lane = 0; + } /* TODO: Update this during Device-Device support */ - bus->params.bandwidth -= m_rt->stream->params.rate * - m_rt->ch_count * m_rt->stream->params.bps; + bandwidth = m_rt->stream->params.rate * m_rt->ch_count * m_rt->stream->params.bps; + bus->params.bandwidth -= bandwidth - multi_lane_bandwidth; /* Compute params */ if (bus->compute_params) { - ret = bus->compute_params(bus); + ret = bus->compute_params(bus, stream); if (ret < 0) { dev_err(bus->dev, "Compute params failed: %d\n", ret); + stream->state = state; return ret; } } @@ -1673,11 +1734,11 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) ret = sdw_program_params(bus, false); if (ret < 0) { dev_err(bus->dev, "%s: Program params failed: %d\n", __func__, ret); + stream->state = state; return ret; } } - stream->state = SDW_STREAM_DEPREPARED; return do_bank_switch(stream); } diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c index abdc49d9d940..d8c9be64d006 100644 --- a/drivers/spi/atmel-quadspi.c +++ b/drivers/spi/atmel-quadspi.c @@ -235,8 +235,8 @@ /** * struct atmel_qspi_pcal - Pad Calibration Clock Division * @pclk_rate: peripheral clock rate. - * @pclkdiv: calibration clock division. The clock applied to the calibration - * cell is divided by pclkdiv + 1. + * @pclk_div: calibration clock division. The clock applied to the calibration + * cell is divided by pclk_div + 1. */ struct atmel_qspi_pcal { u32 pclk_rate; diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 5f9cac41baff..06711a62fa3d 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -399,7 +399,7 @@ static void lpss_ssp_cs_control(struct spi_device *spi, bool enable) lpss_ssp_select_cs(spi, config); mask = LPSS_CS_CONTROL_CS_HIGH; - __lpss_ssp_update_priv(drv_data, config->reg_cs_ctrl, mask, enable ? mask : 0); + __lpss_ssp_update_priv(drv_data, config->reg_cs_ctrl, mask, enable ? 0 : mask); if (config->cs_clk_stays_gated) { /* * Changing CS alone when dynamic clock gating is on won't diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c index 6ad4b729897e..c4969f66a0ba 100644 --- a/drivers/spi/spi-sn-f-ospi.c +++ b/drivers/spi/spi-sn-f-ospi.c @@ -116,6 +116,9 @@ struct f_ospi { static u32 f_ospi_get_dummy_cycle(const struct spi_mem_op *op) { + if (!op->dummy.nbytes) + return 0; + return (op->dummy.nbytes * 8) / op->dummy.buswidth; } diff --git a/drivers/target/target_core_stat.c b/drivers/target/target_core_stat.c index c42cbde8a31b..210648a0092e 100644 --- a/drivers/target/target_core_stat.c +++ b/drivers/target/target_core_stat.c @@ -117,9 +117,9 @@ static ssize_t target_stat_tgt_status_show(struct config_item *item, char *page) { if (to_stat_tgt_dev(item)->export_count) - return snprintf(page, PAGE_SIZE, "activated"); + return snprintf(page, PAGE_SIZE, "activated\n"); else - return snprintf(page, PAGE_SIZE, "deactivated"); + return snprintf(page, PAGE_SIZE, "deactivated\n"); } static ssize_t target_stat_tgt_non_access_lus_show(struct config_item *item, diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index 280071be30b1..6b7ab1814c12 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -57,8 +57,6 @@ struct time_in_idle { * @max_level: maximum cooling level. One less than total number of valid * cpufreq frequencies. * @em: Reference on the Energy Model of the device - * @cdev: thermal_cooling_device pointer to keep track of the - * registered cooling device. * @policy: cpufreq policy. * @cooling_ops: cpufreq callbacks to thermal cooling device ops * @idle_time: idle time stats diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index df08f13052ff..8bb1a01fef2a 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -798,7 +798,7 @@ static int ptmx_open(struct inode *inode, struct file *filp) nonseekable_open(inode, filp); /* We refuse fsnotify events on ptmx, since it's a shared resource */ - filp->f_mode |= FMODE_NONOTIFY; + file_set_fsnotify_mode(filp, FMODE_NONOTIFY); retval = tty_alloc_file(filp); if (retval) diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 11e05aa014e5..b861585ca02a 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -374,6 +374,7 @@ static inline int is_omap1510_8250(struct uart_8250_port *pt) #ifdef CONFIG_SERIAL_8250_DMA extern int serial8250_tx_dma(struct uart_8250_port *); +extern void serial8250_tx_dma_flush(struct uart_8250_port *); extern int serial8250_rx_dma(struct uart_8250_port *); extern void serial8250_rx_dma_flush(struct uart_8250_port *); extern int serial8250_request_dma(struct uart_8250_port *); @@ -406,6 +407,7 @@ static inline int serial8250_tx_dma(struct uart_8250_port *p) { return -1; } +static inline void serial8250_tx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_rx_dma(struct uart_8250_port *p) { return -1; diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index d215c494ee24..f245a84f4a50 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -149,6 +149,22 @@ err: return ret; } +void serial8250_tx_dma_flush(struct uart_8250_port *p) +{ + struct uart_8250_dma *dma = p->dma; + + if (!dma->tx_running) + return; + + /* + * kfifo_reset() has been called by the serial core, avoid + * advancing and underflowing in __dma_tx_complete(). + */ + dma->tx_size = 0; + + dmaengine_terminate_async(dma->rxchan); +} + int serial8250_rx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; diff --git a/drivers/tty/serial/8250/8250_of.c b/drivers/tty/serial/8250/8250_of.c index 64aed7efc569..11c860ea80f6 100644 --- a/drivers/tty/serial/8250/8250_of.c +++ b/drivers/tty/serial/8250/8250_of.c @@ -110,7 +110,6 @@ static int of_platform_serial_setup(struct platform_device *ofdev, spin_lock_init(&port->lock); if (resource_type(&resource) == IORESOURCE_IO) { - port->iotype = UPIO_PORT; port->iobase = resource.start; } else { port->mapbase = resource.start; diff --git a/drivers/tty/serial/8250/8250_platform.c b/drivers/tty/serial/8250/8250_platform.c index 8bdc1879d952..c0343bfb8064 100644 --- a/drivers/tty/serial/8250/8250_platform.c +++ b/drivers/tty/serial/8250/8250_platform.c @@ -112,7 +112,6 @@ static int serial8250_probe_acpi(struct platform_device *pdev) struct device *dev = &pdev->dev; struct uart_8250_port uart = { }; struct resource *regs; - unsigned char iotype; int ret, line; regs = platform_get_mem_or_io(pdev, 0); @@ -122,13 +121,11 @@ static int serial8250_probe_acpi(struct platform_device *pdev) switch (resource_type(regs)) { case IORESOURCE_IO: uart.port.iobase = regs->start; - iotype = UPIO_PORT; break; case IORESOURCE_MEM: uart.port.mapbase = regs->start; uart.port.mapsize = resource_size(regs); uart.port.flags = UPF_IOREMAP; - iotype = UPIO_MEM; break; default: return -EINVAL; @@ -147,12 +144,6 @@ static int serial8250_probe_acpi(struct platform_device *pdev) if (ret) return ret; - /* - * The previous call may not set iotype correctly when reg-io-width - * property is absent and it doesn't support IO port resource. - */ - uart.port.iotype = iotype; - line = serial8250_register_8250_port(&uart); if (line < 0) return line; diff --git a/drivers/tty/serial/8250/8250_pnp.c b/drivers/tty/serial/8250/8250_pnp.c index 7c06ae79d8e2..7a837fdf9df1 100644 --- a/drivers/tty/serial/8250/8250_pnp.c +++ b/drivers/tty/serial/8250/8250_pnp.c @@ -436,7 +436,6 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) { struct uart_8250_port uart, *port; int ret, flags = dev_id->driver_data; - unsigned char iotype; long line; if (flags & UNKNOWN_DEV) { @@ -448,14 +447,11 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) memset(&uart, 0, sizeof(uart)); if ((flags & CIR_PORT) && pnp_port_valid(dev, 2)) { uart.port.iobase = pnp_port_start(dev, 2); - iotype = UPIO_PORT; } else if (pnp_port_valid(dev, 0)) { uart.port.iobase = pnp_port_start(dev, 0); - iotype = UPIO_PORT; } else if (pnp_mem_valid(dev, 0)) { uart.port.mapbase = pnp_mem_start(dev, 0); uart.port.mapsize = pnp_mem_len(dev, 0); - iotype = UPIO_MEM; uart.port.flags = UPF_IOREMAP; } else return -ENODEV; @@ -471,12 +467,6 @@ serial_pnp_probe(struct pnp_dev *dev, const struct pnp_device_id *dev_id) if (ret) return ret; - /* - * The previous call may not set iotype correctly when reg-io-width - * property is absent and it doesn't support IO port resource. - */ - uart.port.iotype = iotype; - if (flags & CIR_PORT) { uart.port.flags |= UPF_FIXED_PORT | UPF_FIXED_TYPE; uart.port.type = PORT_8250_CIR; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index d7976a21cca9..442967a6cd52 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2555,6 +2555,14 @@ static void serial8250_shutdown(struct uart_port *port) serial8250_do_shutdown(port); } +static void serial8250_flush_buffer(struct uart_port *port) +{ + struct uart_8250_port *up = up_to_u8250p(port); + + if (up->dma) + serial8250_tx_dma_flush(up); +} + static unsigned int serial8250_do_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) @@ -3244,6 +3252,7 @@ static const struct uart_ops serial8250_pops = { .break_ctl = serial8250_break_ctl, .startup = serial8250_startup, .shutdown = serial8250_shutdown, + .flush_buffer = serial8250_flush_buffer, .set_termios = serial8250_set_termios, .set_ldisc = serial8250_set_ldisc, .pm = serial8250_pm, diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 7b51cdc274fd..560f45ed19ae 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1561,7 +1561,7 @@ int sc16is7xx_probe(struct device *dev, const struct sc16is7xx_devtype *devtype, /* Always ask for fixed clock rate from a property. */ device_property_read_u32(dev, "clock-frequency", &uartclk); - s->polling = !!irq; + s->polling = (irq <= 0); if (s->polling) dev_dbg(dev, "No interrupt pin definition, falling back to polling mode\n"); diff --git a/drivers/tty/serial/serial_port.c b/drivers/tty/serial/serial_port.c index d35f1d24156c..2fc48cd63f6c 100644 --- a/drivers/tty/serial/serial_port.c +++ b/drivers/tty/serial/serial_port.c @@ -173,6 +173,7 @@ EXPORT_SYMBOL(uart_remove_one_port); * The caller is responsible to initialize the following fields of the @port * ->dev (must be valid) * ->flags + * ->iobase * ->mapbase * ->mapsize * ->regshift (if @use_defaults is false) @@ -214,7 +215,7 @@ static int __uart_read_properties(struct uart_port *port, bool use_defaults) /* Read the registers I/O access type (default: MMIO 8-bit) */ ret = device_property_read_u32(dev, "reg-io-width", &value); if (ret) { - port->iotype = UPIO_MEM; + port->iotype = port->iobase ? UPIO_PORT : UPIO_MEM; } else { switch (value) { case 1: @@ -227,15 +228,16 @@ static int __uart_read_properties(struct uart_port *port, bool use_defaults) port->iotype = device_is_big_endian(dev) ? UPIO_MEM32BE : UPIO_MEM32; break; default: - if (!use_defaults) { - dev_err(dev, "Unsupported reg-io-width (%u)\n", value); - return -EINVAL; - } port->iotype = UPIO_UNKNOWN; break; } } + if (!use_defaults && port->iotype == UPIO_UNKNOWN) { + dev_err(dev, "Unsupported reg-io-width (%u)\n", value); + return -EINVAL; + } + /* Read the address mapping base offset (default: no offset) */ ret = device_property_read_u32(dev, "reg-offset", &value); if (ret) diff --git a/drivers/ufs/core/ufs-sysfs.c b/drivers/ufs/core/ufs-sysfs.c index 796e37a1d859..3438269a5440 100644 --- a/drivers/ufs/core/ufs-sysfs.c +++ b/drivers/ufs/core/ufs-sysfs.c @@ -1439,6 +1439,7 @@ static ssize_t max_number_of_rtt_store(struct device *dev, struct ufs_hba *hba = dev_get_drvdata(dev); struct ufs_dev_info *dev_info = &hba->dev_info; struct scsi_device *sdev; + unsigned int memflags; unsigned int rtt; int ret; @@ -1458,14 +1459,16 @@ static ssize_t max_number_of_rtt_store(struct device *dev, ufshcd_rpm_get_sync(hba); + memflags = memalloc_noio_save(); shost_for_each_device(sdev, hba->host) - blk_mq_freeze_queue(sdev->request_queue); + blk_mq_freeze_queue_nomemsave(sdev->request_queue); ret = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_MAX_NUM_OF_RTT, 0, 0, &rtt); shost_for_each_device(sdev, hba->host) - blk_mq_unfreeze_queue(sdev->request_queue); + blk_mq_unfreeze_queue_nomemrestore(sdev->request_queue); + memalloc_noio_restore(memflags); ufshcd_rpm_put_sync(hba); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index cd404ade48dc..1893a7ad9531 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -2120,8 +2120,6 @@ static void ufshcd_init_clk_gating(struct ufs_hba *hba) INIT_DELAYED_WORK(&hba->clk_gating.gate_work, ufshcd_gate_work); INIT_WORK(&hba->clk_gating.ungate_work, ufshcd_ungate_work); - spin_lock_init(&hba->clk_gating.lock); - hba->clk_gating.clk_gating_workq = alloc_ordered_workqueue( "ufs_clk_gating_%d", WQ_MEM_RECLAIM | WQ_HIGHPRI, hba->host->host_no); @@ -3106,8 +3104,13 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) case UPIU_TRANSACTION_QUERY_RSP: { u8 response = lrbp->ucd_rsp_ptr->header.response; - if (response == 0) + if (response == 0) { err = ufshcd_copy_query_response(hba, lrbp); + } else { + err = -EINVAL; + dev_err(hba->dev, "%s: unexpected response in Query RSP: %x\n", + __func__, response); + } break; } case UPIU_TRANSACTION_REJECT_UPIU: @@ -5976,24 +5979,6 @@ out: __func__, err); } -static void ufshcd_temp_exception_event_handler(struct ufs_hba *hba, u16 status) -{ - u32 value; - - if (ufshcd_query_attr_retry(hba, UPIU_QUERY_OPCODE_READ_ATTR, - QUERY_ATTR_IDN_CASE_ROUGH_TEMP, 0, 0, &value)) - return; - - dev_info(hba->dev, "exception Tcase %d\n", value - 80); - - ufs_hwmon_notify_event(hba, status & MASK_EE_URGENT_TEMP); - - /* - * A placeholder for the platform vendors to add whatever additional - * steps required - */ -} - static int __ufshcd_wb_toggle(struct ufs_hba *hba, bool set, enum flag_idn idn) { u8 index; @@ -6214,7 +6199,7 @@ static void ufshcd_exception_event_handler(struct work_struct *work) ufshcd_bkops_exception_event_handler(hba); if (status & hba->ee_drv_mask & MASK_EE_URGENT_TEMP) - ufshcd_temp_exception_event_handler(hba, status); + ufs_hwmon_notify_event(hba, status & MASK_EE_URGENT_TEMP); ufs_debugfs_exception_event(hba, status); } @@ -9160,7 +9145,7 @@ out: if (!IS_ERR_OR_NULL(clki->clk) && clki->enabled) clk_disable_unprepare(clki->clk); } - } else if (!ret && on) { + } else if (!ret && on && hba->clk_gating.is_initialized) { scoped_guard(spinlock_irqsave, &hba->clk_gating.lock) hba->clk_gating.state = CLKS_ON; trace_ufshcd_clk_gating(dev_name(hba->dev), @@ -10247,16 +10232,6 @@ EXPORT_SYMBOL_GPL(ufshcd_system_thaw); #endif /* CONFIG_PM_SLEEP */ /** - * ufshcd_dealloc_host - deallocate Host Bus Adapter (HBA) - * @hba: pointer to Host Bus Adapter (HBA) - */ -void ufshcd_dealloc_host(struct ufs_hba *hba) -{ - scsi_host_put(hba->host); -} -EXPORT_SYMBOL_GPL(ufshcd_dealloc_host); - -/** * ufshcd_set_dma_mask - Set dma mask based on the controller * addressing capability * @hba: per adapter instance @@ -10275,11 +10250,25 @@ static int ufshcd_set_dma_mask(struct ufs_hba *hba) } /** + * ufshcd_devres_release - devres cleanup handler, invoked during release of + * hba->dev + * @host: pointer to SCSI host + */ +static void ufshcd_devres_release(void *host) +{ + scsi_host_put(host); +} + +/** * ufshcd_alloc_host - allocate Host Bus Adapter (HBA) * @dev: pointer to device handle * @hba_handle: driver private handle * * Return: 0 on success, non-zero value on failure. + * + * NOTE: There is no corresponding ufshcd_dealloc_host() because this function + * keeps track of its allocations using devres and deallocates everything on + * device removal automatically. */ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) { @@ -10301,6 +10290,13 @@ int ufshcd_alloc_host(struct device *dev, struct ufs_hba **hba_handle) err = -ENOMEM; goto out_error; } + + err = devm_add_action_or_reset(dev, ufshcd_devres_release, + host); + if (err) + return dev_err_probe(dev, err, + "failed to add ufshcd dealloc action\n"); + host->nr_maps = HCTX_TYPE_POLL + 1; hba = shost_priv(host); hba->host = host; @@ -10429,6 +10425,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) hba->irq = irq; hba->vps = &ufs_hba_vps; + /* + * Initialize clk_gating.lock early since it is being used in + * ufshcd_setup_clocks() + */ + spin_lock_init(&hba->clk_gating.lock); + err = ufshcd_hba_init(hba); if (err) goto out_error; diff --git a/drivers/ufs/host/ufshcd-pci.c b/drivers/ufs/host/ufshcd-pci.c index ea39c5d5b8cf..9cfcaad23cf9 100644 --- a/drivers/ufs/host/ufshcd-pci.c +++ b/drivers/ufs/host/ufshcd-pci.c @@ -562,7 +562,6 @@ static void ufshcd_pci_remove(struct pci_dev *pdev) pm_runtime_forbid(&pdev->dev); pm_runtime_get_noresume(&pdev->dev); ufshcd_remove(hba); - ufshcd_dealloc_host(hba); } /** @@ -605,7 +604,6 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) err = ufshcd_init(hba, mmio_base, pdev->irq); if (err) { dev_err(&pdev->dev, "Initialization failed\n"); - ufshcd_dealloc_host(hba); return err; } diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c index 505572d4fa87..ffe5d1d2b215 100644 --- a/drivers/ufs/host/ufshcd-pltfrm.c +++ b/drivers/ufs/host/ufshcd-pltfrm.c @@ -465,21 +465,17 @@ int ufshcd_pltfrm_init(struct platform_device *pdev, struct device *dev = &pdev->dev; mmio_base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(mmio_base)) { - err = PTR_ERR(mmio_base); - goto out; - } + if (IS_ERR(mmio_base)) + return PTR_ERR(mmio_base); irq = platform_get_irq(pdev, 0); - if (irq < 0) { - err = irq; - goto out; - } + if (irq < 0) + return irq; err = ufshcd_alloc_host(dev, &hba); if (err) { dev_err(dev, "Allocation failed\n"); - goto out; + return err; } hba->vops = vops; @@ -488,13 +484,13 @@ int ufshcd_pltfrm_init(struct platform_device *pdev, if (err) { dev_err(dev, "%s: clock parse failed %d\n", __func__, err); - goto dealloc_host; + return err; } err = ufshcd_parse_regulator_info(hba); if (err) { dev_err(dev, "%s: regulator init failed %d\n", __func__, err); - goto dealloc_host; + return err; } ufshcd_init_lanes_per_dir(hba); @@ -502,25 +498,20 @@ int ufshcd_pltfrm_init(struct platform_device *pdev, err = ufshcd_parse_operating_points(hba); if (err) { dev_err(dev, "%s: OPP parse failed %d\n", __func__, err); - goto dealloc_host; + return err; } err = ufshcd_init(hba, mmio_base, irq); if (err) { dev_err_probe(dev, err, "Initialization failed with error %d\n", err); - goto dealloc_host; + return err; } pm_runtime_set_active(dev); pm_runtime_enable(dev); return 0; - -dealloc_host: - ufshcd_dealloc_host(hba); -out: - return err; } EXPORT_SYMBOL_GPL(ufshcd_pltfrm_init); @@ -534,7 +525,6 @@ void ufshcd_pltfrm_remove(struct platform_device *pdev) pm_runtime_get_sync(&pdev->dev); ufshcd_remove(hba); - ufshcd_dealloc_host(hba); pm_runtime_disable(&pdev->dev); pm_runtime_put_noidle(&pdev->dev); } diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 6b37d1c47fce..c2ecfa3c8349 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -371,7 +371,7 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf) static void acm_ctrl_irq(struct urb *urb) { struct acm *acm = urb->context; - struct usb_cdc_notification *dr = urb->transfer_buffer; + struct usb_cdc_notification *dr; unsigned int current_size = urb->actual_length; unsigned int expected_size, copy_size, alloc_size; int retval; @@ -398,14 +398,25 @@ static void acm_ctrl_irq(struct urb *urb) usb_mark_last_busy(acm->dev); - if (acm->nb_index) + if (acm->nb_index == 0) { + /* + * The first chunk of a message must contain at least the + * notification header with the length field, otherwise we + * can't get an expected_size. + */ + if (current_size < sizeof(struct usb_cdc_notification)) { + dev_dbg(&acm->control->dev, "urb too short\n"); + goto exit; + } + dr = urb->transfer_buffer; + } else { dr = (struct usb_cdc_notification *)acm->notification_buffer; - + } /* size = notification-header + (optional) data */ expected_size = sizeof(struct usb_cdc_notification) + le16_to_cpu(dr->wLength); - if (current_size < expected_size) { + if (acm->nb_index != 0 || current_size < expected_size) { /* notification is transmitted fragmented, reassemble */ if (acm->nb_size < expected_size) { u8 *new_buffer; @@ -1727,13 +1738,16 @@ static const struct usb_device_id acm_ids[] = { { USB_DEVICE(0x0870, 0x0001), /* Metricom GS Modem */ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */ }, - { USB_DEVICE(0x045b, 0x023c), /* Renesas USB Download mode */ + { USB_DEVICE(0x045b, 0x023c), /* Renesas R-Car H3 USB Download mode */ + .driver_info = DISABLE_ECHO, /* Don't echo banner */ + }, + { USB_DEVICE(0x045b, 0x0247), /* Renesas R-Car D3 USB Download mode */ .driver_info = DISABLE_ECHO, /* Don't echo banner */ }, - { USB_DEVICE(0x045b, 0x0248), /* Renesas USB Download mode */ + { USB_DEVICE(0x045b, 0x0248), /* Renesas R-Car M3-N USB Download mode */ .driver_info = DISABLE_ECHO, /* Don't echo banner */ }, - { USB_DEVICE(0x045b, 0x024D), /* Renesas USB Download mode */ + { USB_DEVICE(0x045b, 0x024D), /* Renesas R-Car E3 USB Download mode */ .driver_info = DISABLE_ECHO, /* Don't echo banner */ }, { USB_DEVICE(0x0e8d, 0x0003), /* FIREFLY, MediaTek Inc; andrey.arapov@gmail.com */ diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index c3f839637cb5..a76bb50b6202 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1849,6 +1849,17 @@ static int hub_probe(struct usb_interface *intf, const struct usb_device_id *id) hdev = interface_to_usbdev(intf); /* + * The USB 2.0 spec prohibits hubs from having more than one + * configuration or interface, and we rely on this prohibition. + * Refuse to accept a device that violates it. + */ + if (hdev->descriptor.bNumConfigurations > 1 || + hdev->actconfig->desc.bNumInterfaces > 1) { + dev_err(&intf->dev, "Invalid hub with more than one config or interface\n"); + return -EINVAL; + } + + /* * Set default autosuspend delay as 0 to speedup bus suspend, * based on the below considerations: * @@ -4698,7 +4709,6 @@ void usb_ep0_reinit(struct usb_device *udev) EXPORT_SYMBOL_GPL(usb_ep0_reinit); #define usb_sndaddr0pipe() (PIPE_CONTROL << 30) -#define usb_rcvaddr0pipe() ((PIPE_CONTROL << 30) | USB_DIR_IN) static int hub_set_address(struct usb_device *udev, int devnum) { @@ -4804,7 +4814,7 @@ static int get_bMaxPacketSize0(struct usb_device *udev, for (i = 0; i < GET_MAXPACKET0_TRIES; ++i) { /* Start with invalid values in case the transfer fails */ buf->bDescriptorType = buf->bMaxPacketSize0 = 0; - rc = usb_control_msg(udev, usb_rcvaddr0pipe(), + rc = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), USB_REQ_GET_DESCRIPTOR, USB_DIR_IN, USB_DT_DEVICE << 8, 0, buf, size, diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 67732c791c93..dfcfc142bd5e 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -435,6 +435,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x0c45, 0x7056), .driver_info = USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* Sony Xperia XZ1 Compact (lilac) smartphone in fastboot mode */ + { USB_DEVICE(0x0fce, 0x0dde), .driver_info = USB_QUIRK_NO_LPM }, + /* Action Semiconductor flash disk */ { USB_DEVICE(0x10d6, 0x2200), .driver_info = USB_QUIRK_STRING_FETCH_255 }, @@ -525,6 +528,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Blackmagic Design UltraStudio SDI */ { USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM }, + /* Teclast disk */ + { USB_DEVICE(0x1f75, 0x0917), .driver_info = USB_QUIRK_NO_LPM }, + /* Hauppauge HVR-950q */ { USB_DEVICE(0x2040, 0x7200), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index e7bf9cc635be..bd4c788f03bc 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -4615,6 +4615,7 @@ static int dwc2_hsotg_udc_stop(struct usb_gadget *gadget) spin_lock_irqsave(&hsotg->lock, flags); hsotg->driver = NULL; + hsotg->gadget.dev.of_node = NULL; hsotg->gadget.speed = USB_SPEED_UNKNOWN; hsotg->enabled = 0; diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index ac7c730f81ac..c955039bb4f6 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -717,6 +717,7 @@ struct dwc3_event_buffer { /** * struct dwc3_ep - device side endpoint representation * @endpoint: usb endpoint + * @nostream_work: work for handling bulk NoStream * @cancelled_list: list of cancelled requests for this endpoint * @pending_list: list of pending requests for this endpoint * @started_list: list of started requests on this endpoint diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index d27af65eb08a..ddd6b2ce5710 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2629,10 +2629,38 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) { u32 reg; u32 timeout = 2000; + u32 saved_config = 0; if (pm_runtime_suspended(dwc->dev)) return 0; + /* + * When operating in USB 2.0 speeds (HS/FS), ensure that + * GUSB2PHYCFG.ENBLSLPM and GUSB2PHYCFG.SUSPHY are cleared before starting + * or stopping the controller. This resolves timeout issues that occur + * during frequent role switches between host and device modes. + * + * Save and clear these settings, then restore them after completing the + * controller start or stop sequence. + * + * This solution was discovered through experimentation as it is not + * mentioned in the dwc3 programming guide. It has been tested on an + * Exynos platforms. + */ + reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + if (reg & DWC3_GUSB2PHYCFG_SUSPHY) { + saved_config |= DWC3_GUSB2PHYCFG_SUSPHY; + reg &= ~DWC3_GUSB2PHYCFG_SUSPHY; + } + + if (reg & DWC3_GUSB2PHYCFG_ENBLSLPM) { + saved_config |= DWC3_GUSB2PHYCFG_ENBLSLPM; + reg &= ~DWC3_GUSB2PHYCFG_ENBLSLPM; + } + + if (saved_config) + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + reg = dwc3_readl(dwc->regs, DWC3_DCTL); if (is_on) { if (DWC3_VER_IS_WITHIN(DWC3, ANY, 187A)) { @@ -2660,6 +2688,12 @@ static int dwc3_gadget_run_stop(struct dwc3 *dwc, int is_on) reg &= DWC3_DSTS_DEVCTRLHLT; } while (--timeout && !(!is_on ^ !reg)); + if (saved_config) { + reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + reg |= saved_config; + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg); + } + if (!timeout) return -ETIMEDOUT; diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c index 837fcdfa3840..da82598fcef8 100644 --- a/drivers/usb/gadget/function/f_midi.c +++ b/drivers/usb/gadget/function/f_midi.c @@ -283,7 +283,7 @@ f_midi_complete(struct usb_ep *ep, struct usb_request *req) /* Our transmit completed. See if there's more to go. * f_midi_transmit eats req, don't queue it again. */ req->length = 0; - f_midi_transmit(midi); + queue_work(system_highpri_wq, &midi->work); return; } break; @@ -907,6 +907,15 @@ static int f_midi_bind(struct usb_configuration *c, struct usb_function *f) status = -ENODEV; + /* + * Reset wMaxPacketSize with maximum packet size of FS bulk transfer before + * endpoint claim. This ensures that the wMaxPacketSize does not exceed the + * limit during bind retries where configured dwc3 TX/RX FIFO's maxpacket + * size of 512 bytes for IN/OUT endpoints in support HS speed only. + */ + bulk_in_desc.wMaxPacketSize = cpu_to_le16(64); + bulk_out_desc.wMaxPacketSize = cpu_to_le16(64); + /* allocate instance-specific endpoints */ midi->in_ep = usb_ep_autoconfig(cdev->gadget, &bulk_in_desc); if (!midi->in_ep) @@ -1000,11 +1009,11 @@ static int f_midi_bind(struct usb_configuration *c, struct usb_function *f) } /* configure the endpoint descriptors ... */ - ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports); - ms_out_desc.bNumEmbMIDIJack = midi->in_ports; + ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports); + ms_out_desc.bNumEmbMIDIJack = midi->out_ports; - ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports); - ms_in_desc.bNumEmbMIDIJack = midi->out_ports; + ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports); + ms_in_desc.bNumEmbMIDIJack = midi->in_ports; /* ... and add them to the list */ endpoint_descriptor_index = i; diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c index 79e223713d8b..fb77b0b21790 100644 --- a/drivers/usb/gadget/function/uvc_video.c +++ b/drivers/usb/gadget/function/uvc_video.c @@ -818,7 +818,7 @@ int uvcg_video_init(struct uvc_video *video, struct uvc_device *uvc) return -EINVAL; /* Allocate a kthread for asynchronous hw submit handler. */ - video->kworker = kthread_create_worker(0, "UVCG"); + video->kworker = kthread_run_worker(0, "UVCG"); if (IS_ERR(video->kworker)) { uvcg_err(&video->uvc->func, "failed to create UVCG kworker\n"); return PTR_ERR(video->kworker); diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index a6f46364be65..4b3d5075621a 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1543,8 +1543,8 @@ void usb_del_gadget(struct usb_gadget *gadget) kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE); sysfs_remove_link(&udc->dev.kobj, "gadget"); - flush_work(&gadget->work); device_del(&gadget->dev); + flush_work(&gadget->work); ida_free(&gadget_id_numbers, gadget->id_number); cancel_work_sync(&udc->vbus_work); device_unregister(&udc->dev); diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index fce5c41d9f29..89b304cf6d03 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -310,7 +310,7 @@ struct renesas_usb3_request { struct list_head queue; }; -#define USB3_EP_NAME_SIZE 8 +#define USB3_EP_NAME_SIZE 16 struct renesas_usb3_ep { struct usb_ep ep; struct renesas_usb3 *usb3; diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c index 1f9c1b1435d8..0404489c2f6a 100644 --- a/drivers/usb/host/pci-quirks.c +++ b/drivers/usb/host/pci-quirks.c @@ -958,6 +958,15 @@ static void quirk_usb_disable_ehci(struct pci_dev *pdev) * booting from USB disk or using a usb keyboard */ hcc_params = readl(base + EHCI_HCC_PARAMS); + + /* LS7A EHCI controller doesn't have extended capabilities, the + * EECP (EHCI Extended Capabilities Pointer) field of HCCPARAMS + * register should be 0x0 but it reads as 0xa0. So clear it to + * avoid error messages on boot. + */ + if (pdev->vendor == PCI_VENDOR_ID_LOONGSON && pdev->device == 0x7a14) + hcc_params &= ~(0xffL << 8); + offset = (hcc_params >> 8) & 0xff; while (offset && --count) { pci_read_config_dword(pdev, offset, &cap); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 2d1e205c14c6..ad0ff356f6fa 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -653,8 +653,8 @@ put_runtime_pm: } EXPORT_SYMBOL_NS_GPL(xhci_pci_common_probe, "xhci"); -static const struct pci_device_id pci_ids_reject[] = { - /* handled by xhci-pci-renesas */ +/* handled by xhci-pci-renesas if enabled */ +static const struct pci_device_id pci_ids_renesas[] = { { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0014) }, { PCI_DEVICE(PCI_VENDOR_ID_RENESAS, 0x0015) }, { /* end: all zeroes */ } @@ -662,7 +662,8 @@ static const struct pci_device_id pci_ids_reject[] = { static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) { - if (pci_match_id(pci_ids_reject, dev)) + if (IS_ENABLED(CONFIG_USB_XHCI_PCI_RENESAS) && + pci_match_id(pci_ids_renesas, dev)) return -ENODEV; return xhci_pci_common_probe(dev, id); diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c index 6c3ececf9137..8423be59ec0f 100644 --- a/drivers/usb/phy/phy-generic.c +++ b/drivers/usb/phy/phy-generic.c @@ -212,7 +212,7 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop) if (of_property_read_u32(node, "clock-frequency", &clk_rate)) clk_rate = 0; - needs_clk = of_property_read_bool(node, "clocks"); + needs_clk = of_property_present(node, "clocks"); } nop->gpiod_reset = devm_gpiod_get_optional(dev, "reset", GPIOD_ASIS); diff --git a/drivers/usb/roles/class.c b/drivers/usb/roles/class.c index c58a12c147f4..30482d4cf826 100644 --- a/drivers/usb/roles/class.c +++ b/drivers/usb/roles/class.c @@ -387,8 +387,11 @@ usb_role_switch_register(struct device *parent, dev_set_name(&sw->dev, "%s-role-switch", desc->name ? desc->name : dev_name(parent)); + sw->registered = true; + ret = device_register(&sw->dev); if (ret) { + sw->registered = false; put_device(&sw->dev); return ERR_PTR(ret); } @@ -399,8 +402,6 @@ usb_role_switch_register(struct device *parent, dev_warn(&sw->dev, "failed to add component\n"); } - sw->registered = true; - /* TODO: Symlinks for the host port and the device controller. */ return sw; diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 1e2ae0c6c41c..58bd54e8c483 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -619,15 +619,6 @@ static void option_instat_callback(struct urb *urb); /* Luat Air72*U series based on UNISOC UIS8910 uses UNISOC's vendor ID */ #define LUAT_PRODUCT_AIR720U 0x4e00 -/* MeiG Smart Technology products */ -#define MEIGSMART_VENDOR_ID 0x2dee -/* MeiG Smart SRM815/SRM825L based on Qualcomm 315 */ -#define MEIGSMART_PRODUCT_SRM825L 0x4d22 -/* MeiG Smart SLM320 based on UNISOC UIS8910 */ -#define MEIGSMART_PRODUCT_SLM320 0x4d41 -/* MeiG Smart SLM770A based on ASR1803 */ -#define MEIGSMART_PRODUCT_SLM770A 0x4d57 - /* Device flags */ /* Highest interface number which can be used with NCTRL() and RSVD() */ @@ -1367,15 +1358,15 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff), /* Telit LN920 (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff), /* Telit FN990 (rmnet) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff), /* Telit FN990A (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff), /* Telit FN990 (MBIM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff), /* Telit FN990A (MBIM) */ .driver_info = NCTRL(0) | RSVD(1) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff), /* Telit FN990 (RNDIS) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff), /* Telit FN990A (RNDIS) */ .driver_info = NCTRL(2) | RSVD(3) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990A (ECM) */ .driver_info = NCTRL(0) | RSVD(1) }, - { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990 (PCIe) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990A (PCIe) */ .driver_info = RSVD(0) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990 (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, @@ -1403,6 +1394,22 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | NCTRL(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff), /* Telit FE910C04 (rmnet) */ .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x60) }, /* Telit FN990B (rmnet) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x30), + .driver_info = NCTRL(5) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x60) }, /* Telit FN990B (MBIM) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x30), + .driver_info = NCTRL(6) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x60) }, /* Telit FN990B (RNDIS) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x30), + .driver_info = NCTRL(6) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x60) }, /* Telit FN990B (ECM) */ + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x40) }, + { USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x30), + .driver_info = NCTRL(6) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910), .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM), @@ -2347,6 +2354,14 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a05, 0xff) }, /* Fibocom FM650-CN (NCM mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a06, 0xff) }, /* Fibocom FM650-CN (RNDIS mode) */ { USB_DEVICE_INTERFACE_CLASS(0x2cb7, 0x0a07, 0xff) }, /* Fibocom FM650-CN (MBIM mode) */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d41, 0xff, 0, 0) }, /* MeiG Smart SLM320 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d57, 0xff, 0, 0) }, /* MeiG Smart SLM770A */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0, 0) }, /* MeiG Smart SRM815 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0x10, 0x02) }, /* MeiG Smart SLM828 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0x10, 0x03) }, /* MeiG Smart SLM828 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x30) }, /* MeiG Smart SRM815 and SRM825L */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x40) }, /* MeiG Smart SRM825L */ + { USB_DEVICE_AND_INTERFACE_INFO(0x2dee, 0x4d22, 0xff, 0xff, 0x60) }, /* MeiG Smart SRM825L */ { USB_DEVICE_INTERFACE_CLASS(0x2df3, 0x9d03, 0xff) }, /* LongSung M5710 */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1404, 0xff) }, /* GosunCn GM500 RNDIS */ { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1405, 0xff) }, /* GosunCn GM500 MBIM */ @@ -2403,12 +2418,6 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) }, - { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) }, - { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM770A, 0xff, 0, 0) }, - { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0, 0) }, - { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) }, - { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) }, - { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) }, { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0530, 0xff), /* TCL IK512 MBIM */ .driver_info = NCTRL(1) }, { USB_DEVICE_INTERFACE_CLASS(0x1bbb, 0x0640, 0xff), /* TCL IK512 ECM */ diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 47be450d2be3..6bf1a22c785a 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5591,8 +5591,7 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_auto_vbus_discharge_threshold(port, TYPEC_PWR_MODE_USB, port->pps_data.active, 0); tcpm_set_charge(port, false); - tcpm_set_state(port, hard_reset_state(port), - port->timings.ps_src_off_time); + tcpm_set_state(port, ERROR_RECOVERY, port->timings.ps_src_off_time); break; case PR_SWAP_SNK_SRC_SOURCE_ON: tcpm_enable_auto_vbus_discharge(port, true); diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index 528395133b4f..163f7f1d70f1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -84,7 +84,7 @@ module_param(balloon_boot_timeout, uint, 0444); #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG static int xen_hotplug_unpopulated; -static struct ctl_table balloon_table[] = { +static const struct ctl_table balloon_table[] = { { .procname = "hotplug_unpopulated", .data = &xen_hotplug_unpopulated, diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index c63f317e3df3..093ad4a08672 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -105,7 +105,7 @@ static ssize_t online_show(struct device *dev, return sprintf(buf, "%u\n", !!(cpu->flags & XEN_PCPU_FLAGS_ONLINE)); } -static ssize_t __ref online_store(struct device *dev, +static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index b72ee9379d77..4926d4badc57 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -341,6 +341,7 @@ int pvcalls_front_socket(struct socket *sock) pvcalls_exit(); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_socket); static void free_active_ring(struct sock_mapping *map) { @@ -486,6 +487,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_connect); static int __write_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -581,6 +583,7 @@ again: pvcalls_exit_sock(sock); return tot_sent; } +EXPORT_SYMBOL_GPL(pvcalls_front_sendmsg); static int __read_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -666,6 +669,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_recvmsg); int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { @@ -719,6 +723,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) pvcalls_exit_sock(sock); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_bind); int pvcalls_front_listen(struct socket *sock, int backlog) { @@ -768,8 +773,10 @@ int pvcalls_front_listen(struct socket *sock, int backlog) pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_listen); -int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) +int pvcalls_front_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct pvcalls_bedata *bedata; struct sock_mapping *map; @@ -788,7 +795,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) return -EINVAL; } - nonblock = flags & SOCK_NONBLOCK; + nonblock = arg->flags & SOCK_NONBLOCK; /* * Backend only supports 1 inflight accept request, will return * errors for the others @@ -904,6 +911,7 @@ received: pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_accept); static __poll_t pvcalls_front_poll_passive(struct file *file, struct pvcalls_bedata *bedata, @@ -1004,6 +1012,7 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_poll); int pvcalls_front_release(struct socket *sock) { @@ -1087,6 +1096,7 @@ int pvcalls_front_release(struct socket *sock) pvcalls_exit(); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_release); static const struct xenbus_device_id pvcalls_front_ids[] = { { "pvcalls" }, diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index f694ad77379f..881ef14660bc 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -12,7 +12,7 @@ int pvcalls_front_bind(struct socket *sock, int pvcalls_front_listen(struct socket *sock, int backlog); int pvcalls_front_accept(struct socket *sock, struct socket *newsock, - int flags); + struct proto_accept_arg *arg); int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index a337edcf8faf..1f65795cf5d7 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -74,19 +74,21 @@ static inline phys_addr_t xen_dma_to_phys(struct device *dev, return xen_bus_to_phys(dev, dma_to_phys(dev, dma_addr)); } +static inline bool range_requires_alignment(phys_addr_t p, size_t size) +{ + phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); + phys_addr_t bus_addr = pfn_to_bfn(XEN_PFN_DOWN(p)) << XEN_PAGE_SHIFT; + + return IS_ALIGNED(p, algn) && !IS_ALIGNED(bus_addr, algn); +} + static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) { unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p); unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size); - phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); next_bfn = pfn_to_bfn(xen_pfn); - /* If buffer is physically aligned, ensure DMA alignment. */ - if (IS_ALIGNED(p, algn) && - !IS_ALIGNED((phys_addr_t)next_bfn << XEN_PAGE_SHIFT, algn)) - return 1; - for (i = 1; i < nr_pages; i++) if (pfn_to_bfn(++xen_pfn) != ++next_bfn) return 1; @@ -111,7 +113,7 @@ static struct io_tlb_pool *xen_swiotlb_find_pool(struct device *dev, } #ifdef CONFIG_X86 -int xen_swiotlb_fixup(void *buf, unsigned long nslabs) +int __init xen_swiotlb_fixup(void *buf, unsigned long nslabs) { int rc; unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT); @@ -156,7 +158,8 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size, *dma_handle = xen_phys_to_dma(dev, phys); if (*dma_handle + size - 1 > dma_mask || - range_straddles_page_boundary(phys, size)) { + range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size)) { if (xen_create_contiguous_region(phys, order, fls64(dma_mask), dma_handle) != 0) goto out_free_pages; @@ -182,7 +185,8 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, size = ALIGN(size, XEN_PAGE_SIZE); if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) || - WARN_ON_ONCE(range_straddles_page_boundary(phys, size))) + WARN_ON_ONCE(range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size))) return; if (TestClearPageXenRemapped(virt_to_page(vaddr))) diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h index 698c43dd5dc8..f28bc763847a 100644 --- a/fs/9p/v9fs.h +++ b/fs/9p/v9fs.h @@ -202,7 +202,7 @@ static inline struct v9fs_session_info *v9fs_inode2v9ses(struct inode *inode) return inode->i_sb->s_fs_info; } -static inline struct v9fs_session_info *v9fs_dentry2v9ses(struct dentry *dentry) +static inline struct v9fs_session_info *v9fs_dentry2v9ses(const struct dentry *dentry) { return dentry->d_sb->s_fs_info; } diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index 01338d4c2d9e..5061f192eafd 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -61,7 +61,7 @@ static void v9fs_dentry_release(struct dentry *dentry) p9_fid_put(hlist_entry(p, struct p9_fid, dlist)); } -static int v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) +static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { struct p9_fid *fid; struct inode *inode; @@ -99,14 +99,36 @@ out_valid: return 1; } +static int v9fs_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) +{ + return __v9fs_lookup_revalidate(dentry, flags); +} + +static bool v9fs_dentry_unalias_trylock(const struct dentry *dentry) +{ + struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry); + return down_write_trylock(&v9ses->rename_sem); +} + +static void v9fs_dentry_unalias_unlock(const struct dentry *dentry) +{ + struct v9fs_session_info *v9ses = v9fs_dentry2v9ses(dentry); + up_write(&v9ses->rename_sem); +} + const struct dentry_operations v9fs_cached_dentry_operations = { .d_revalidate = v9fs_lookup_revalidate, - .d_weak_revalidate = v9fs_lookup_revalidate, + .d_weak_revalidate = __v9fs_lookup_revalidate, .d_delete = v9fs_cached_dentry_delete, .d_release = v9fs_dentry_release, + .d_unalias_trylock = v9fs_dentry_unalias_trylock, + .d_unalias_unlock = v9fs_dentry_unalias_unlock, }; const struct dentry_operations v9fs_dentry_operations = { .d_delete = always_delete_dentry, .d_release = v9fs_dentry_release, + .d_unalias_trylock = v9fs_dentry_unalias_trylock, + .d_unalias_unlock = v9fs_dentry_unalias_unlock, }; diff --git a/fs/afs/dir.c b/fs/afs/dir.c index a843c36fc471..02cbf38e1a77 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -23,7 +23,8 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags); static int afs_dir_open(struct inode *inode, struct file *file); static int afs_readdir(struct file *file, struct dir_context *ctx); -static int afs_d_revalidate(struct dentry *dentry, unsigned int flags); +static int afs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags); static int afs_d_delete(const struct dentry *dentry); static void afs_d_iput(struct dentry *dentry, struct inode *inode); static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, int nlen, @@ -597,19 +598,19 @@ static bool afs_lookup_one_filldir(struct dir_context *ctx, const char *name, * Do a lookup of a single name in a directory * - just returns the FID the dentry name maps to if found */ -static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry, +static int afs_do_lookup_one(struct inode *dir, const struct qstr *name, struct afs_fid *fid, afs_dataversion_t *_dir_version) { struct afs_super_info *as = dir->i_sb->s_fs_info; struct afs_lookup_one_cookie cookie = { .ctx.actor = afs_lookup_one_filldir, - .name = dentry->d_name, + .name = *name, .fid.vid = as->volume->vid }; int ret; - _enter("{%lu},%p{%pd},", dir->i_ino, dentry, dentry); + _enter("{%lu},{%.*s},", dir->i_ino, name->len, name->name); /* search the directory */ ret = afs_dir_iterate(dir, &cookie.ctx, NULL, _dir_version); @@ -1023,21 +1024,12 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry, /* * Check the validity of a dentry under RCU conditions. */ -static int afs_d_revalidate_rcu(struct dentry *dentry) +static int afs_d_revalidate_rcu(struct afs_vnode *dvnode, struct dentry *dentry) { - struct afs_vnode *dvnode; - struct dentry *parent; - struct inode *dir; long dir_version, de_version; _enter("%p", dentry); - /* Check the parent directory is still valid first. */ - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - dvnode = AFS_FS_I(dir); if (test_bit(AFS_VNODE_DELETED, &dvnode->flags)) return -ECHILD; @@ -1065,11 +1057,11 @@ static int afs_d_revalidate_rcu(struct dentry *dentry) * - NOTE! the hit can be a negative hit too, so we can't assume we have an * inode */ -static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int afs_d_revalidate(struct inode *parent_dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - struct afs_vnode *vnode, *dir; + struct afs_vnode *vnode, *dir = AFS_FS_I(parent_dir); struct afs_fid fid; - struct dentry *parent; struct inode *inode; struct key *key; afs_dataversion_t dir_version, invalid_before; @@ -1077,7 +1069,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) int ret; if (flags & LOOKUP_RCU) - return afs_d_revalidate_rcu(dentry); + return afs_d_revalidate_rcu(dir, dentry); if (d_really_is_positive(dentry)) { vnode = AFS_FS_I(d_inode(dentry)); @@ -1092,14 +1084,9 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) if (IS_ERR(key)) key = NULL; - /* Hold the parent dentry so we can peer at it */ - parent = dget_parent(dentry); - dir = AFS_FS_I(d_inode(parent)); - /* validate the parent directory */ ret = afs_validate(dir, key); if (ret == -ERESTARTSYS) { - dput(parent); key_put(key); return ret; } @@ -1127,7 +1114,7 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) afs_stat_v(dir, n_reval); /* search the directory for this vnode */ - ret = afs_do_lookup_one(&dir->netfs.inode, dentry, &fid, &dir_version); + ret = afs_do_lookup_one(&dir->netfs.inode, name, &fid, &dir_version); switch (ret) { case 0: /* the filename maps to something */ @@ -1171,22 +1158,19 @@ static int afs_d_revalidate(struct dentry *dentry, unsigned int flags) goto out_valid; default: - _debug("failed to iterate dir %pd: %d", - parent, ret); + _debug("failed to iterate parent %pd2: %d", dentry, ret); goto not_found; } out_valid: dentry->d_fsdata = (void *)(unsigned long)dir_version; out_valid_noupdate: - dput(parent); key_put(key); _leave(" = 1 [valid]"); return 1; not_found: _debug("dropping dentry %pd2", dentry); - dput(parent); key_put(key); _leave(" = 0 [bad]"); @@ -224,7 +224,7 @@ static unsigned long aio_nr; /* current system wide number of aio requests */ static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ #ifdef CONFIG_SYSCTL -static struct ctl_table aio_sysctls[] = { +static const struct ctl_table aio_sysctls[] = { { .procname = "aio-nr", .data = &aio_nr, diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 42bd1cb7c9cd..583ac81669c2 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -60,14 +60,14 @@ static struct inode *anon_inode_make_secure_inode( const struct inode *context_inode) { struct inode *inode; - const struct qstr qname = QSTR_INIT(name, strlen(name)); int error; inode = alloc_anon_inode(anon_inode_mnt->mnt_sb); if (IS_ERR(inode)) return inode; inode->i_flags &= ~S_PRIVATE; - error = security_inode_init_security_anon(inode, &qname, context_inode); + error = security_inode_init_security_anon(inode, &QSTR(name), + context_inode); if (error) { iput(inode); return ERR_PTR(error); diff --git a/fs/bcachefs/Kconfig b/fs/bcachefs/Kconfig index 85eea7a4dea3..fc7efd0a7525 100644 --- a/fs/bcachefs/Kconfig +++ b/fs/bcachefs/Kconfig @@ -61,6 +61,13 @@ config BCACHEFS_DEBUG The resulting code will be significantly slower than normal; you probably shouldn't select this option unless you're a developer. +config BCACHEFS_INJECT_TRANSACTION_RESTARTS + bool "Randomly inject transaction restarts" + depends on BCACHEFS_DEBUG + help + Randomly inject transaction restarts in a few core paths - may have a + significant performance penalty + config BCACHEFS_TESTS bool "bcachefs unit and performance tests" depends on BCACHEFS_FS diff --git a/fs/bcachefs/alloc_background.c b/fs/bcachefs/alloc_background.c index fc2ef33b67b3..3ea809990ef1 100644 --- a/fs/bcachefs/alloc_background.c +++ b/fs/bcachefs/alloc_background.c @@ -1803,7 +1803,6 @@ struct discard_buckets_state { u64 open; u64 need_journal_commit; u64 discarded; - u64 need_journal_commit_this_dev; }; static int bch2_discard_one_bucket(struct btree_trans *trans, @@ -1827,11 +1826,11 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, goto out; } - if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, - c->journal.flushed_seq_ondisk, - pos.inode, pos.offset)) { - s->need_journal_commit++; - s->need_journal_commit_this_dev++; + u64 seq_ready = bch2_bucket_journal_seq_ready(&c->buckets_waiting_for_journal, + pos.inode, pos.offset); + if (seq_ready > c->journal.flushed_seq_ondisk) { + if (seq_ready > c->journal.flushing_seq) + s->need_journal_commit++; goto out; } @@ -1865,23 +1864,24 @@ static int bch2_discard_one_bucket(struct btree_trans *trans, discard_locked = true; } - if (!bkey_eq(*discard_pos_done, iter.pos) && - ca->mi.discard && !c->opts.nochanges) { - /* - * This works without any other locks because this is the only - * thread that removes items from the need_discard tree - */ - bch2_trans_unlock_long(trans); - blkdev_issue_discard(ca->disk_sb.bdev, - k.k->p.offset * ca->mi.bucket_size, - ca->mi.bucket_size, - GFP_KERNEL); - *discard_pos_done = iter.pos; + if (!bkey_eq(*discard_pos_done, iter.pos)) { s->discarded++; + *discard_pos_done = iter.pos; - ret = bch2_trans_relock_notrace(trans); - if (ret) - goto out; + if (ca->mi.discard && !c->opts.nochanges) { + /* + * This works without any other locks because this is the only + * thread that removes items from the need_discard tree + */ + bch2_trans_unlock_long(trans); + blkdev_issue_discard(ca->disk_sb.bdev, + k.k->p.offset * ca->mi.bucket_size, + ca->mi.bucket_size, + GFP_KERNEL); + ret = bch2_trans_relock_notrace(trans); + if (ret) + goto out; + } } SET_BCH_ALLOC_V4_NEED_DISCARD(&a->v, false); @@ -1929,6 +1929,9 @@ static void bch2_do_discards_work(struct work_struct *work) POS(ca->dev_idx, U64_MAX), 0, k, bch2_discard_one_bucket(trans, ca, &iter, &discard_pos_done, &s, false))); + if (s.need_journal_commit > dev_buckets_available(ca, BCH_WATERMARK_normal)) + bch2_journal_flush_async(&c->journal, NULL); + trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); @@ -2024,7 +2027,7 @@ static void bch2_do_discards_fast_work(struct work_struct *work) break; } - trace_discard_buckets(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); + trace_discard_buckets_fast(c, s.seen, s.open, s.need_journal_commit, s.discarded, bch2_err_str(ret)); bch2_trans_put(trans); percpu_ref_put(&ca->io_ref); diff --git a/fs/bcachefs/alloc_foreground.c b/fs/bcachefs/alloc_foreground.c index 6df41c331a52..5a781fb4c794 100644 --- a/fs/bcachefs/alloc_foreground.c +++ b/fs/bcachefs/alloc_foreground.c @@ -205,8 +205,12 @@ static inline bool may_alloc_bucket(struct bch_fs *c, return false; } - if (bch2_bucket_needs_journal_commit(&c->buckets_waiting_for_journal, - c->journal.flushed_seq_ondisk, bucket.inode, bucket.offset)) { + u64 journal_seq_ready = + bch2_bucket_journal_seq_ready(&c->buckets_waiting_for_journal, + bucket.inode, bucket.offset); + if (journal_seq_ready > c->journal.flushed_seq_ondisk) { + if (journal_seq_ready > c->journal.flushing_seq) + s->need_journal_commit++; s->skipped_need_journal_commit++; return false; } @@ -570,7 +574,7 @@ alloc: ? bch2_bucket_alloc_freelist(trans, ca, watermark, &s, cl) : bch2_bucket_alloc_early(trans, ca, watermark, &s, cl); - if (s.skipped_need_journal_commit * 2 > avail) + if (s.need_journal_commit * 2 > avail) bch2_journal_flush_async(&c->journal, NULL); if (!ob && s.btree_bitmap != BTREE_BITMAP_ANY) { diff --git a/fs/bcachefs/alloc_types.h b/fs/bcachefs/alloc_types.h index 9bbb28e90b93..4aa8ee026cb8 100644 --- a/fs/bcachefs/alloc_types.h +++ b/fs/bcachefs/alloc_types.h @@ -18,6 +18,7 @@ struct bucket_alloc_state { u64 buckets_seen; u64 skipped_open; u64 skipped_need_journal_commit; + u64 need_journal_commit; u64 skipped_nocow; u64 skipped_nouse; u64 skipped_mi_btree_bitmap; diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c index 672ca2c1d37d..ca755e8d1a37 100644 --- a/fs/bcachefs/btree_cache.c +++ b/fs/bcachefs/btree_cache.c @@ -24,7 +24,10 @@ do { \ } while (0) const char * const bch2_btree_node_flags[] = { -#define x(f) #f, + "typebit", + "typebit", + "typebit", +#define x(f) [BTREE_NODE_##f] = #f, BTREE_FLAGS() #undef x NULL diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index 367231ab1980..e32fce4fd258 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -2239,8 +2239,6 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos if (unlikely(ret)) return bkey_s_c_err(ret); - btree_path_set_should_be_locked(trans, trans->paths + iter->key_cache_path); - k = bch2_btree_path_peek_slot(trans->paths + iter->key_cache_path, &u); if (!k.k) return k; @@ -2251,6 +2249,7 @@ struct bkey_s_c btree_trans_peek_key_cache(struct btree_iter *iter, struct bpos iter->k = u; k.k = &iter->k; + btree_path_set_should_be_locked(trans, trans->paths + iter->key_cache_path); return k; } @@ -2358,6 +2357,12 @@ struct bkey_s_c bch2_btree_iter_peek_max(struct btree_iter *iter, struct bpos en bch2_btree_iter_verify_entry_exit(iter); EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bkey_eq(end, POS_MAX)); + ret = trans_maybe_inject_restart(trans, _RET_IP_); + if (unlikely(ret)) { + k = bkey_s_c_err(ret); + goto out_no_locked; + } + if (iter->update_path) { bch2_path_put_nokeep(trans, iter->update_path, iter->flags & BTREE_ITER_intent); @@ -2623,6 +2628,12 @@ struct bkey_s_c bch2_btree_iter_peek_prev_min(struct btree_iter *iter, struct bp bch2_btree_iter_verify_entry_exit(iter); EBUG_ON((iter->flags & BTREE_ITER_filter_snapshots) && bpos_eq(end, POS_MIN)); + int ret = trans_maybe_inject_restart(trans, _RET_IP_); + if (unlikely(ret)) { + k = bkey_s_c_err(ret); + goto out_no_locked; + } + while (1) { k = __bch2_btree_iter_peek_prev(iter, search_key); if (unlikely(!k.k)) @@ -2750,6 +2761,12 @@ struct bkey_s_c bch2_btree_iter_peek_slot(struct btree_iter *iter) bch2_btree_iter_verify_entry_exit(iter); EBUG_ON(btree_iter_path(trans, iter)->level && (iter->flags & BTREE_ITER_with_key_cache)); + ret = trans_maybe_inject_restart(trans, _RET_IP_); + if (unlikely(ret)) { + k = bkey_s_c_err(ret); + goto out_no_locked; + } + /* extents can't span inode numbers: */ if ((iter->flags & BTREE_ITER_is_extents) && unlikely(iter->pos.offset == KEY_OFFSET_MAX)) { @@ -3107,6 +3124,10 @@ void *__bch2_trans_kmalloc(struct btree_trans *trans, size_t size) WARN_ON_ONCE(new_bytes > BTREE_TRANS_MEM_MAX); + ret = trans_maybe_inject_restart(trans, _RET_IP_); + if (ret) + return ERR_PTR(ret); + struct btree_transaction_stats *s = btree_trans_stats(trans); s->max_mem = max(s->max_mem, new_bytes); @@ -3164,7 +3185,8 @@ out_new_mem: if (old_bytes) { trace_and_count(c, trans_restart_mem_realloced, trans, _RET_IP_, new_bytes); - return ERR_PTR(btree_trans_restart(trans, BCH_ERR_transaction_restart_mem_realloced)); + return ERR_PTR(btree_trans_restart_ip(trans, + BCH_ERR_transaction_restart_mem_realloced, _RET_IP_)); } out_change_top: p = trans->mem + trans->mem_top; @@ -3272,6 +3294,14 @@ u32 bch2_trans_begin(struct btree_trans *trans) trans->last_begin_ip = _RET_IP_; +#ifdef CONFIG_BCACHEFS_INJECT_TRANSACTION_RESTARTS + if (trans->restarted) { + trans->restart_count_this_trans++; + } else { + trans->restart_count_this_trans = 0; + } +#endif + trans_set_locked(trans, false); if (trans->restarted) { diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h index b9538e6e6d65..b96157f3dc9c 100644 --- a/fs/bcachefs/btree_iter.h +++ b/fs/bcachefs/btree_iter.h @@ -355,6 +355,18 @@ static int btree_trans_restart(struct btree_trans *trans, int err) return btree_trans_restart_ip(trans, err, _THIS_IP_); } +static inline int trans_maybe_inject_restart(struct btree_trans *trans, unsigned long ip) +{ +#ifdef CONFIG_BCACHEFS_INJECT_TRANSACTION_RESTARTS + if (!(ktime_get_ns() & ~(~0ULL << min(63, (10 + trans->restart_count_this_trans))))) { + trace_and_count(trans->c, trans_restart_injected, trans, ip); + return btree_trans_restart_ip(trans, + BCH_ERR_transaction_restart_fault_inject, ip); + } +#endif + return 0; +} + bool bch2_btree_node_upgrade(struct btree_trans *, struct btree_path *, unsigned); @@ -739,7 +751,7 @@ transaction_restart: \ if (!_ret2) \ bch2_trans_verify_not_restarted(_trans, _restart_count);\ \ - _ret2 ?: trans_was_restarted(_trans, _restart_count); \ + _ret2 ?: trans_was_restarted(_trans, _orig_restart_count); \ }) #define for_each_btree_key_max_continue(_trans, _iter, \ diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 3b62296c3100..1821f40c161a 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -291,8 +291,10 @@ static noinline int btree_key_cache_fill(struct btree_trans *trans, struct btree_path *ck_path, unsigned flags) { - if (flags & BTREE_ITER_cached_nofill) + if (flags & BTREE_ITER_cached_nofill) { + ck_path->l[0].b = NULL; return 0; + } struct bch_fs *c = trans->c; struct btree_iter iter; @@ -746,7 +748,6 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc) rcu_read_unlock(); mutex_lock(&bc->table.mutex); mutex_unlock(&bc->table.mutex); - rcu_read_lock(); continue; } for (i = 0; i < tbl->size; i++) diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index 6b79b672e0b1..c4f524b2ca9a 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -348,7 +348,7 @@ static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans, unsigned flags) { return bch2_journal_res_get(&trans->c->journal, &trans->journal_res, - trans->journal_u64s, flags); + trans->journal_u64s, flags, trans); } #define JSET_ENTRY_LOG_U64s 4 @@ -999,6 +999,10 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) bch2_trans_verify_not_unlocked_or_in_restart(trans); + ret = trans_maybe_inject_restart(trans, _RET_IP_); + if (unlikely(ret)) + goto out_reset; + if (!trans->nr_updates && !trans->journal_entries_u64s) goto out_reset; diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index a6f251eb4164..a09cbe9cd94f 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -509,6 +509,9 @@ struct btree_trans { bool notrace_relock_fail:1; enum bch_errcode restarted:16; u32 restart_count; +#ifdef CONFIG_BCACHEFS_INJECT_TRANSACTION_RESTARTS + u32 restart_count_this_trans; +#endif u64 last_begin_time; unsigned long last_begin_ip; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index f4aeadbe53c1..e4e7c804625e 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -681,9 +681,11 @@ static void btree_update_nodes_written(struct btree_update *as) b = as->old_nodes[i]; + bch2_trans_begin(trans); btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); seq = b->data ? b->data->keys.seq : 0; six_unlock_read(&b->c.lock); + bch2_trans_unlock_long(trans); if (seq == as->old_nodes_seq[i]) wait_on_bit_io(&b->flags, BTREE_NODE_write_in_flight_inner, diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index 7930ffea3075..26d646e1275c 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -278,12 +278,12 @@ static inline struct btree_node_entry *want_new_bset(struct bch_fs *c, struct bt { struct bset_tree *t = bset_tree_last(b); struct btree_node_entry *bne = max(write_block(b), - (void *) btree_bkey_last(b, bset_tree_last(b))); + (void *) btree_bkey_last(b, t)); ssize_t remaining_space = __bch2_btree_u64s_remaining(b, bne->keys.start); if (unlikely(bset_written(b, bset(b, t)))) { - if (remaining_space > (ssize_t) (block_bytes(c) >> 3)) + if (b->written + block_sectors(c) <= btree_sectors(c)) return bne; } else { if (unlikely(bset_u64s(t) * sizeof(u64) > btree_write_set_buffer(b)) && diff --git a/fs/bcachefs/buckets_waiting_for_journal.c b/fs/bcachefs/buckets_waiting_for_journal.c index f9fb150eda70..c8a488e6b7b8 100644 --- a/fs/bcachefs/buckets_waiting_for_journal.c +++ b/fs/bcachefs/buckets_waiting_for_journal.c @@ -22,23 +22,21 @@ static void bucket_table_init(struct buckets_waiting_for_journal_table *t, size_ memset(t->d, 0, sizeof(t->d[0]) << t->bits); } -bool bch2_bucket_needs_journal_commit(struct buckets_waiting_for_journal *b, - u64 flushed_seq, - unsigned dev, u64 bucket) +u64 bch2_bucket_journal_seq_ready(struct buckets_waiting_for_journal *b, + unsigned dev, u64 bucket) { struct buckets_waiting_for_journal_table *t; u64 dev_bucket = (u64) dev << 56 | bucket; - bool ret = false; - unsigned i; + u64 ret = 0; mutex_lock(&b->lock); t = b->t; - for (i = 0; i < ARRAY_SIZE(t->hash_seeds); i++) { + for (unsigned i = 0; i < ARRAY_SIZE(t->hash_seeds); i++) { struct bucket_hashed *h = bucket_hash(t, i, dev_bucket); if (h->dev_bucket == dev_bucket) { - ret = h->journal_seq > flushed_seq; + ret = h->journal_seq; break; } } diff --git a/fs/bcachefs/buckets_waiting_for_journal.h b/fs/bcachefs/buckets_waiting_for_journal.h index d2ae19cbe18c..365619ca44c8 100644 --- a/fs/bcachefs/buckets_waiting_for_journal.h +++ b/fs/bcachefs/buckets_waiting_for_journal.h @@ -4,8 +4,8 @@ #include "buckets_waiting_for_journal_types.h" -bool bch2_bucket_needs_journal_commit(struct buckets_waiting_for_journal *, - u64, unsigned, u64); +u64 bch2_bucket_journal_seq_ready(struct buckets_waiting_for_journal *, + unsigned, u64); int bch2_set_bucket_needs_journal_commit(struct buckets_waiting_for_journal *, u64, unsigned, u64, u64); diff --git a/fs/bcachefs/compress.c b/fs/bcachefs/compress.c index f99ff1819597..114bf2f3879f 100644 --- a/fs/bcachefs/compress.c +++ b/fs/bcachefs/compress.c @@ -4,6 +4,7 @@ #include "compress.h" #include "error.h" #include "extents.h" +#include "io_write.h" #include "opts.h" #include "super-io.h" @@ -254,11 +255,14 @@ err: goto out; } -int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio, - struct bch_extent_crc_unpacked *crc) +int bch2_bio_uncompress_inplace(struct bch_write_op *op, + struct bio *bio) { + struct bch_fs *c = op->c; + struct bch_extent_crc_unpacked *crc = &op->crc; struct bbuf data = { NULL }; size_t dst_len = crc->uncompressed_size << 9; + int ret = 0; /* bio must own its pages: */ BUG_ON(!bio->bi_vcnt); @@ -266,17 +270,26 @@ int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio, if (crc->uncompressed_size << 9 > c->opts.encoded_extent_max || crc->compressed_size << 9 > c->opts.encoded_extent_max) { - bch_err(c, "error rewriting existing data: extent too big"); + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "error rewriting existing data: extent too big"); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); return -EIO; } data = __bounce_alloc(c, dst_len, WRITE); if (__bio_uncompress(c, bio, data.b, *crc)) { - if (!c->opts.no_data_io) - bch_err(c, "error rewriting existing data: decompression error"); - bio_unmap_or_unbounce(c, data); - return -EIO; + if (!c->opts.no_data_io) { + struct printbuf buf = PRINTBUF; + bch2_write_op_error(&buf, op); + prt_printf(&buf, "error rewriting existing data: decompression error"); + bch_err_ratelimited(c, "%s", buf.buf); + printbuf_exit(&buf); + } + ret = -EIO; + goto err; } /* @@ -293,9 +306,9 @@ int bch2_bio_uncompress_inplace(struct bch_fs *c, struct bio *bio, crc->uncompressed_size = crc->live_size; crc->offset = 0; crc->csum = (struct bch_csum) { 0, 0 }; - +err: bio_unmap_or_unbounce(c, data); - return 0; + return ret; } int bch2_bio_uncompress(struct bch_fs *c, struct bio *src, diff --git a/fs/bcachefs/compress.h b/fs/bcachefs/compress.h index 607fd5e232c9..bec2f05bfd52 100644 --- a/fs/bcachefs/compress.h +++ b/fs/bcachefs/compress.h @@ -47,8 +47,8 @@ static inline enum bch_compression_type bch2_compression_opt_to_type(unsigned v) return __bch2_compression_opt_to_type[bch2_compression_decode(v).type]; } -int bch2_bio_uncompress_inplace(struct bch_fs *, struct bio *, - struct bch_extent_crc_unpacked *); +struct bch_write_op; +int bch2_bio_uncompress_inplace(struct bch_write_op *, struct bio *); int bch2_bio_uncompress(struct bch_fs *, struct bio *, struct bio *, struct bvec_iter, struct bch_extent_crc_unpacked); unsigned bch2_bio_compress(struct bch_fs *, struct bio *, size_t *, diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 585214931e05..337494facac6 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -91,15 +91,28 @@ static bool bkey_nocow_lock(struct bch_fs *c, struct moving_context *ctxt, struc return true; } -static void trace_move_extent_finish2(struct bch_fs *c, struct bkey_s_c k) +static noinline void trace_move_extent_finish2(struct data_update *u, + struct bkey_i *new, + struct bkey_i *insert) { - if (trace_move_extent_finish_enabled()) { - struct printbuf buf = PRINTBUF; + struct bch_fs *c = u->op.c; + struct printbuf buf = PRINTBUF; - bch2_bkey_val_to_text(&buf, c, k); - trace_move_extent_finish(c, buf.buf); - printbuf_exit(&buf); - } + prt_newline(&buf); + + bch2_data_update_to_text(&buf, u); + prt_newline(&buf); + + prt_str_indented(&buf, "new replicas:\t"); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(new)); + prt_newline(&buf); + + prt_str_indented(&buf, "insert:\t"); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert)); + prt_newline(&buf); + + trace_move_extent_finish(c, buf.buf); + printbuf_exit(&buf); } static void trace_move_extent_fail2(struct data_update *m, @@ -372,7 +385,8 @@ restart_drop_extra_replicas: bch2_btree_iter_set_pos(&iter, next_pos); this_cpu_add(c->counters[BCH_COUNTER_move_extent_finish], new->k.size); - trace_move_extent_finish2(c, bkey_i_to_s_c(&new->k_i)); + if (trace_move_extent_finish_enabled()) + trace_move_extent_finish2(m, &new->k_i, insert); } err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) @@ -525,34 +539,38 @@ void bch2_data_update_opts_to_text(struct printbuf *out, struct bch_fs *c, struct data_update_opts *data_opts) { printbuf_tabstop_push(out, 20); - prt_str(out, "rewrite ptrs:\t"); + + prt_str_indented(out, "rewrite ptrs:\t"); bch2_prt_u64_base2(out, data_opts->rewrite_ptrs); prt_newline(out); - prt_str(out, "kill ptrs:\t"); + prt_str_indented(out, "kill ptrs:\t"); bch2_prt_u64_base2(out, data_opts->kill_ptrs); prt_newline(out); - prt_str(out, "target:\t"); + prt_str_indented(out, "target:\t"); bch2_target_to_text(out, c, data_opts->target); prt_newline(out); - prt_str(out, "compression:\t"); + prt_str_indented(out, "compression:\t"); bch2_compression_opt_to_text(out, io_opts->background_compression); prt_newline(out); - prt_str(out, "opts.replicas:\t"); + prt_str_indented(out, "opts.replicas:\t"); prt_u64(out, io_opts->data_replicas); + prt_newline(out); - prt_str(out, "extra replicas:\t"); + prt_str_indented(out, "extra replicas:\t"); prt_u64(out, data_opts->extra_replicas); } void bch2_data_update_to_text(struct printbuf *out, struct data_update *m) { - bch2_bkey_val_to_text(out, m->op.c, bkey_i_to_s_c(m->k.k)); - prt_newline(out); bch2_data_update_opts_to_text(out, m->op.c, &m->op.opts, &m->data_opts); + prt_newline(out); + + prt_str_indented(out, "old key:\t"); + bch2_bkey_val_to_text(out, m->op.c, bkey_i_to_s_c(m->k.k)); } int bch2_extent_drop_ptrs(struct btree_trans *trans, diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c index b5de52a50d10..55333e82d1fe 100644 --- a/fs/bcachefs/debug.c +++ b/fs/bcachefs/debug.c @@ -20,6 +20,7 @@ #include "extents.h" #include "fsck.h" #include "inode.h" +#include "journal_reclaim.h" #include "super.h" #include <linux/console.h> diff --git a/fs/bcachefs/disk_accounting.h b/fs/bcachefs/disk_accounting.h index 5360cbb3ec29..f4372cafea2e 100644 --- a/fs/bcachefs/disk_accounting.h +++ b/fs/bcachefs/disk_accounting.h @@ -210,11 +210,13 @@ static inline void bch2_accounting_mem_read_counters(struct bch_accounting_mem * static inline void bch2_accounting_mem_read(struct bch_fs *c, struct bpos p, u64 *v, unsigned nr) { + percpu_down_read(&c->mark_lock); struct bch_accounting_mem *acc = &c->accounting; unsigned idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]), accounting_pos_cmp, &p); bch2_accounting_mem_read_counters(acc, idx, v, nr, false); + percpu_up_read(&c->mark_lock); } static inline struct bversion journal_pos_to_bversion(struct journal_res *res, unsigned offset) diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 8fcf7c8e5ede..9bf316e7b845 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -450,7 +450,7 @@ static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked * return ret; struct bch_hash_info dir_hash = bch2_hash_info_init(c, &lostfound); - struct qstr name = (struct qstr) QSTR(name_buf); + struct qstr name = QSTR(name_buf); inode->bi_dir = lostfound.bi_inum; @@ -823,6 +823,7 @@ struct inode_walker_entry { struct bch_inode_unpacked inode; u32 snapshot; u64 count; + u64 i_size; }; struct inode_walker { @@ -910,8 +911,9 @@ found: if (k.k->p.snapshot != i->snapshot && !is_whiteout) { struct inode_walker_entry new = *i; - new.snapshot = k.k->p.snapshot; - new.count = 0; + new.snapshot = k.k->p.snapshot; + new.count = 0; + new.i_size = 0; struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); @@ -1116,37 +1118,6 @@ err: return ret; } -static int check_directory_size(struct btree_trans *trans, - struct bch_inode_unpacked *inode_u, - struct bkey_s_c inode_k, bool *write_inode) -{ - struct btree_iter iter; - struct bkey_s_c k; - u64 new_size = 0; - int ret; - - for_each_btree_key_max_norestart(trans, iter, BTREE_ID_dirents, - SPOS(inode_k.k->p.offset, 0, inode_k.k->p.snapshot), - POS(inode_k.k->p.offset, U64_MAX), - 0, k, ret) { - if (k.k->type != KEY_TYPE_dirent) - continue; - - struct bkey_s_c_dirent dirent = bkey_s_c_to_dirent(k); - struct qstr name = bch2_dirent_get_name(dirent); - - new_size += dirent_occupied_size(&name); - } - bch2_trans_iter_exit(trans, &iter); - - if (!ret && inode_u->bi_size != new_size) { - inode_u->bi_size = new_size; - *write_inode = true; - } - - return ret; -} - static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, @@ -1335,16 +1306,6 @@ static int check_inode(struct btree_trans *trans, u.bi_journal_seq = journal_cur_seq(&c->journal); do_update = true; } - - if (S_ISDIR(u.bi_mode)) { - ret = check_directory_size(trans, &u, k, &do_update); - - fsck_err_on(ret, - trans, directory_size_mismatch, - "directory inode %llu:%u with the mismatch directory size", - u.bi_inum, k.k->p.snapshot); - ret = 0; - } do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u); @@ -2017,10 +1978,31 @@ fsck_err: return ret; } -static int check_subdir_count(struct btree_trans *trans, struct inode_walker *w) +static int check_dir_i_size_notnested(struct btree_trans *trans, struct inode_walker *w) +{ + struct bch_fs *c = trans->c; + int ret = 0; + + darray_for_each(w->inodes, i) + if (fsck_err_on(i->inode.bi_size != i->i_size, + trans, inode_dir_wrong_nlink, + "directory %llu:%u with wrong i_size: got %llu, should be %llu", + w->last_pos.inode, i->snapshot, i->inode.bi_size, i->i_size)) { + i->inode.bi_size = i->i_size; + ret = bch2_fsck_write_inode(trans, &i->inode); + if (ret) + break; + } +fsck_err: + bch_err_fn(c, ret); + return ret; +} + +static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w) { u32 restart_count = trans->restart_count; return check_subdir_count_notnested(trans, w) ?: + check_dir_i_size_notnested(trans, w) ?: trans_was_restarted(trans, restart_count); } @@ -2367,7 +2349,7 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, goto out; if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) { - ret = check_subdir_count(trans, dir); + ret = check_subdir_dirents_count(trans, dir); if (ret) goto err; } @@ -2457,9 +2439,11 @@ static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, if (ret) goto err; - if (d.v->d_type == DT_DIR) - for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) + for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) { + if (d.v->d_type == DT_DIR) i->count++; + i->i_size += bkey_bytes(d.k); + } out: err: fsck_err: diff --git a/fs/bcachefs/inode.h b/fs/bcachefs/inode.h index d2e134528f0e..428b9be6af34 100644 --- a/fs/bcachefs/inode.h +++ b/fs/bcachefs/inode.h @@ -285,12 +285,14 @@ void bch2_inode_opts_get(struct bch_io_opts *, struct bch_fs *, struct bch_inode_unpacked *); int bch2_inum_opts_get(struct btree_trans*, subvol_inum, struct bch_io_opts *); +#include "rebalance.h" + static inline struct bch_extent_rebalance bch2_inode_rebalance_opts_get(struct bch_fs *c, struct bch_inode_unpacked *inode) { struct bch_io_opts io_opts; bch2_inode_opts_get(&io_opts, c, inode); - return io_opts_to_rebalance_opts(&io_opts); + return io_opts_to_rebalance_opts(c, &io_opts); } int bch2_inode_rm_snapshot(struct btree_trans *, u64, u32); diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index 3e71860f66b9..03892388832b 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -406,11 +406,21 @@ static void __bch2_write_op_error(struct printbuf *out, struct bch_write_op *op, op->flags & BCH_WRITE_MOVE ? "(internal move)" : ""); } -static void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op) +void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op) { __bch2_write_op_error(out, op, op->pos.offset); } +static void bch2_write_op_error_trans(struct btree_trans *trans, struct printbuf *out, + struct bch_write_op *op, u64 offset) +{ + bch2_inum_offset_err_msg_trans(trans, out, + (subvol_inum) { op->subvol, op->pos.inode, }, + offset << 9); + prt_printf(out, "write error%s: ", + op->flags & BCH_WRITE_MOVE ? "(internal move)" : ""); +} + void bch2_submit_wbio_replicas(struct bch_write_bio *wbio, struct bch_fs *c, enum bch_data_type type, const struct bkey_i *k, @@ -873,7 +883,7 @@ static enum prep_encoded_ret { if (bch2_crc_cmp(op->crc.csum, csum) && !c->opts.no_data_io) return PREP_ENCODED_CHECKSUM_ERR; - if (bch2_bio_uncompress_inplace(c, bio, &op->crc)) + if (bch2_bio_uncompress_inplace(op, bio)) return PREP_ENCODED_ERR; } @@ -1193,7 +1203,7 @@ static void bch2_nocow_write_convert_unwritten(struct bch_write_op *op) struct bkey_i *insert = bch2_keylist_front(&op->insert_keys); struct printbuf buf = PRINTBUF; - __bch2_write_op_error(&buf, op, bkey_start_offset(&insert->k)); + bch2_write_op_error_trans(trans, &buf, op, bkey_start_offset(&insert->k)); prt_printf(&buf, "btree update error: %s", bch2_err_str(ret)); bch_err_ratelimited(c, "%s", buf.buf); printbuf_exit(&buf); diff --git a/fs/bcachefs/io_write.h b/fs/bcachefs/io_write.h index 5400ce94ee57..b4626013abc8 100644 --- a/fs/bcachefs/io_write.h +++ b/fs/bcachefs/io_write.h @@ -20,6 +20,8 @@ static inline void bch2_latency_acct(struct bch_dev *ca, u64 submit_time, int rw void bch2_submit_wbio_replicas(struct bch_write_bio *, struct bch_fs *, enum bch_data_type, const struct bkey_i *, bool); +void bch2_write_op_error(struct printbuf *out, struct bch_write_op *op); + #define BCH_WRITE_FLAGS() \ x(ALLOC_NOWAIT) \ x(CACHED) \ diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 2cd20114b74b..24c294d4634e 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -113,11 +113,10 @@ journal_seq_to_buf(struct journal *j, u64 seq) static void journal_pin_list_init(struct journal_entry_pin_list *p, int count) { - unsigned i; - - for (i = 0; i < ARRAY_SIZE(p->list); i++) - INIT_LIST_HEAD(&p->list[i]); - INIT_LIST_HEAD(&p->flushed); + for (unsigned i = 0; i < ARRAY_SIZE(p->unflushed); i++) + INIT_LIST_HEAD(&p->unflushed[i]); + for (unsigned i = 0; i < ARRAY_SIZE(p->flushed); i++) + INIT_LIST_HEAD(&p->flushed[i]); atomic_set(&p->count, count); p->devs.nr = 0; } @@ -320,6 +319,16 @@ void bch2_journal_halt(struct journal *j) spin_unlock(&j->lock); } +void bch2_journal_halt_locked(struct journal *j) +{ + lockdep_assert_held(&j->lock); + + __journal_entry_close(j, JOURNAL_ENTRY_ERROR_VAL, true); + if (!j->err_seq) + j->err_seq = journal_cur_seq(j); + journal_wake(j); +} + static bool journal_entry_want_write(struct journal *j) { bool ret = !journal_entry_is_open(j) || @@ -382,9 +391,12 @@ static int journal_entry_open(struct journal *j) if (nr_unwritten_journal_entries(j) == ARRAY_SIZE(j->buf)) return JOURNAL_ERR_max_in_flight; - if (bch2_fs_fatal_err_on(journal_cur_seq(j) >= JOURNAL_SEQ_MAX, - c, "cannot start: journal seq overflow")) + if (journal_cur_seq(j) >= JOURNAL_SEQ_MAX) { + bch_err(c, "cannot start: journal seq overflow"); + if (bch2_fs_emergency_read_only_locked(c)) + bch_err(c, "fatal error - emergency read only"); return JOURNAL_ERR_insufficient_devices; /* -EROFS */ + } BUG_ON(!j->cur_entry_sectors); @@ -601,6 +613,16 @@ out: : -BCH_ERR_journal_res_get_blocked; } +static unsigned max_dev_latency(struct bch_fs *c) +{ + u64 nsecs = 0; + + for_each_rw_member(c, ca) + nsecs = max(nsecs, ca->io_latency[WRITE].stats.max_duration); + + return nsecs_to_jiffies(nsecs); +} + /* * Essentially the entry function to the journaling code. When bcachefs is doing * a btree insert, it calls this function to get the current journal write. @@ -612,17 +634,31 @@ out: * btree node write locks. */ int bch2_journal_res_get_slowpath(struct journal *j, struct journal_res *res, - unsigned flags) + unsigned flags, + struct btree_trans *trans) { int ret; if (closure_wait_event_timeout(&j->async_wait, (ret = __journal_res_get(j, res, flags)) != -BCH_ERR_journal_res_get_blocked || (flags & JOURNAL_RES_GET_NONBLOCK), - HZ * 10)) + HZ)) return ret; + if (trans) + bch2_trans_unlock_long(trans); + struct bch_fs *c = container_of(j, struct bch_fs, journal); + int remaining_wait = max(max_dev_latency(c) * 2, HZ * 10); + + remaining_wait = max(0, remaining_wait - HZ); + + if (closure_wait_event_timeout(&j->async_wait, + (ret = __journal_res_get(j, res, flags)) != -BCH_ERR_journal_res_get_blocked || + (flags & JOURNAL_RES_GET_NONBLOCK), + remaining_wait)) + return ret; + struct printbuf buf = PRINTBUF; bch2_journal_debug_to_text(&buf, j); bch_err(c, "Journal stuck? Waited for 10 seconds...\n%s", @@ -727,7 +763,7 @@ recheck_need_open: * livelock: */ sched_annotate_sleep(); - ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0); + ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL); if (ret) return ret; @@ -760,6 +796,7 @@ recheck_need_open: } buf->must_flush = true; + j->flushing_seq = max(j->flushing_seq, seq); if (parent && !closure_wait(&buf->wait, parent)) BUG(); @@ -848,7 +885,7 @@ out: static int __bch2_journal_meta(struct journal *j) { struct journal_res res = {}; - int ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0); + int ret = bch2_journal_res_get(j, &res, jset_u64s(0), 0, NULL); if (ret) return ret; @@ -1602,54 +1639,3 @@ void bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) __bch2_journal_debug_to_text(out, j); spin_unlock(&j->lock); } - -bool bch2_journal_seq_pins_to_text(struct printbuf *out, struct journal *j, u64 *seq) -{ - struct journal_entry_pin_list *pin_list; - struct journal_entry_pin *pin; - - spin_lock(&j->lock); - if (!test_bit(JOURNAL_running, &j->flags)) { - spin_unlock(&j->lock); - return true; - } - - *seq = max(*seq, j->pin.front); - - if (*seq >= j->pin.back) { - spin_unlock(&j->lock); - return true; - } - - out->atomic++; - - pin_list = journal_seq_pin(j, *seq); - - prt_printf(out, "%llu: count %u\n", *seq, atomic_read(&pin_list->count)); - printbuf_indent_add(out, 2); - - for (unsigned i = 0; i < ARRAY_SIZE(pin_list->list); i++) - list_for_each_entry(pin, &pin_list->list[i], list) - prt_printf(out, "\t%px %ps\n", pin, pin->flush); - - if (!list_empty(&pin_list->flushed)) - prt_printf(out, "flushed:\n"); - - list_for_each_entry(pin, &pin_list->flushed, list) - prt_printf(out, "\t%px %ps\n", pin, pin->flush); - - printbuf_indent_sub(out, 2); - - --out->atomic; - spin_unlock(&j->lock); - - return false; -} - -void bch2_journal_pins_to_text(struct printbuf *out, struct journal *j) -{ - u64 seq = 0; - - while (!bch2_journal_seq_pins_to_text(out, j, &seq)) - seq++; -} diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index cb0df0663946..107f7f901cd9 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -312,7 +312,7 @@ static inline void bch2_journal_res_put(struct journal *j, } int bch2_journal_res_get_slowpath(struct journal *, struct journal_res *, - unsigned); + unsigned, struct btree_trans *); /* First bits for BCH_WATERMARK: */ enum journal_res_flags { @@ -368,7 +368,8 @@ static inline int journal_res_get_fast(struct journal *j, } static inline int bch2_journal_res_get(struct journal *j, struct journal_res *res, - unsigned u64s, unsigned flags) + unsigned u64s, unsigned flags, + struct btree_trans *trans) { int ret; @@ -380,7 +381,7 @@ static inline int bch2_journal_res_get(struct journal *j, struct journal_res *re if (journal_res_get_fast(j, res, flags)) goto out; - ret = bch2_journal_res_get_slowpath(j, res, flags); + ret = bch2_journal_res_get_slowpath(j, res, flags, trans); if (ret) return ret; out: @@ -408,6 +409,7 @@ bool bch2_journal_noflush_seq(struct journal *, u64, u64); int bch2_journal_meta(struct journal *); void bch2_journal_halt(struct journal *); +void bch2_journal_halt_locked(struct journal *); static inline int bch2_journal_error(struct journal *j) { @@ -429,8 +431,6 @@ struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *, u void __bch2_journal_debug_to_text(struct printbuf *, struct journal *); void bch2_journal_debug_to_text(struct printbuf *, struct journal *); -void bch2_journal_pins_to_text(struct printbuf *, struct journal *); -bool bch2_journal_seq_pins_to_text(struct printbuf *, struct journal *, u64 *); int bch2_set_nr_journal_buckets(struct bch_fs *, struct bch_dev *, unsigned nr); diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index 7f2efe85a805..11c39e0c34f4 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -17,6 +17,7 @@ #include "sb-clean.h" #include "trace.h" +#include <linux/ioprio.h> #include <linux/string_choices.h> void bch2_journal_pos_from_member_info_set(struct bch_fs *c) @@ -1763,6 +1764,7 @@ static CLOSURE_CALLBACK(journal_write_submit) bio->bi_iter.bi_sector = ptr->offset; bio->bi_end_io = journal_write_endio; bio->bi_private = ca; + bio->bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_RT, 0); BUG_ON(bio->bi_iter.bi_sector == ca->prev_journal_sector); ca->prev_journal_sector = bio->bi_iter.bi_sector; diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index 3c8242606da7..d373cd181a7f 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -327,8 +327,10 @@ void bch2_journal_reclaim_fast(struct journal *j) popped = true; } - if (popped) + if (popped) { bch2_journal_space_available(j); + __closure_wake_up(&j->reclaim_flush_wait); + } } bool __bch2_journal_pin_put(struct journal *j, u64 seq) @@ -362,6 +364,9 @@ static inline bool __journal_pin_drop(struct journal *j, pin->seq = 0; list_del_init(&pin->list); + if (j->reclaim_flush_wait.list.first) + __closure_wake_up(&j->reclaim_flush_wait); + /* * Unpinning a journal entry may make journal_next_bucket() succeed, if * writing a new last_seq will now make another bucket available: @@ -379,15 +384,19 @@ void bch2_journal_pin_drop(struct journal *j, spin_unlock(&j->lock); } -static enum journal_pin_type journal_pin_type(journal_pin_flush_fn fn) +static enum journal_pin_type journal_pin_type(struct journal_entry_pin *pin, + journal_pin_flush_fn fn) { if (fn == bch2_btree_node_flush0 || - fn == bch2_btree_node_flush1) - return JOURNAL_PIN_btree; - else if (fn == bch2_btree_key_cache_journal_flush) - return JOURNAL_PIN_key_cache; + fn == bch2_btree_node_flush1) { + unsigned idx = fn == bch2_btree_node_flush1; + struct btree *b = container_of(pin, struct btree, writes[idx].journal); + + return JOURNAL_PIN_TYPE_btree0 - b->c.level; + } else if (fn == bch2_btree_key_cache_journal_flush) + return JOURNAL_PIN_TYPE_key_cache; else - return JOURNAL_PIN_other; + return JOURNAL_PIN_TYPE_other; } static inline void bch2_journal_pin_set_locked(struct journal *j, u64 seq, @@ -406,7 +415,12 @@ static inline void bch2_journal_pin_set_locked(struct journal *j, u64 seq, atomic_inc(&pin_list->count); pin->seq = seq; pin->flush = flush_fn; - list_add(&pin->list, &pin_list->list[type]); + + if (list_empty(&pin_list->unflushed[type]) && + j->reclaim_flush_wait.list.first) + __closure_wake_up(&j->reclaim_flush_wait); + + list_add(&pin->list, &pin_list->unflushed[type]); } void bch2_journal_pin_copy(struct journal *j, @@ -431,7 +445,7 @@ void bch2_journal_pin_copy(struct journal *j, bool reclaim = __journal_pin_drop(j, dst); - bch2_journal_pin_set_locked(j, seq, dst, flush_fn, journal_pin_type(flush_fn)); + bch2_journal_pin_set_locked(j, seq, dst, flush_fn, journal_pin_type(dst, flush_fn)); if (reclaim) bch2_journal_reclaim_fast(j); @@ -455,7 +469,7 @@ void bch2_journal_pin_set(struct journal *j, u64 seq, bool reclaim = __journal_pin_drop(j, pin); - bch2_journal_pin_set_locked(j, seq, pin, flush_fn, journal_pin_type(flush_fn)); + bch2_journal_pin_set_locked(j, seq, pin, flush_fn, journal_pin_type(pin, flush_fn)); if (reclaim) bch2_journal_reclaim_fast(j); @@ -499,16 +513,15 @@ journal_get_next_pin(struct journal *j, { struct journal_entry_pin_list *pin_list; struct journal_entry_pin *ret = NULL; - unsigned i; fifo_for_each_entry_ptr(pin_list, &j->pin, *seq) { if (*seq > seq_to_flush && !allowed_above_seq) break; - for (i = 0; i < JOURNAL_PIN_NR; i++) - if ((((1U << i) & allowed_below_seq) && *seq <= seq_to_flush) || - ((1U << i) & allowed_above_seq)) { - ret = list_first_entry_or_null(&pin_list->list[i], + for (unsigned i = 0; i < JOURNAL_PIN_TYPE_NR; i++) + if (((BIT(i) & allowed_below_seq) && *seq <= seq_to_flush) || + (BIT(i) & allowed_above_seq)) { + ret = list_first_entry_or_null(&pin_list->unflushed[i], struct journal_entry_pin, list); if (ret) return ret; @@ -544,8 +557,8 @@ static size_t journal_flush_pins(struct journal *j, } if (min_key_cache) { - allowed_above |= 1U << JOURNAL_PIN_key_cache; - allowed_below |= 1U << JOURNAL_PIN_key_cache; + allowed_above |= BIT(JOURNAL_PIN_TYPE_key_cache); + allowed_below |= BIT(JOURNAL_PIN_TYPE_key_cache); } cond_resched(); @@ -553,7 +566,9 @@ static size_t journal_flush_pins(struct journal *j, j->last_flushed = jiffies; spin_lock(&j->lock); - pin = journal_get_next_pin(j, seq_to_flush, allowed_below, allowed_above, &seq); + pin = journal_get_next_pin(j, seq_to_flush, + allowed_below, + allowed_above, &seq); if (pin) { BUG_ON(j->flush_in_progress); j->flush_in_progress = pin; @@ -576,7 +591,7 @@ static size_t journal_flush_pins(struct journal *j, spin_lock(&j->lock); /* Pin might have been dropped or rearmed: */ if (likely(!err && !j->flush_in_progress_dropped)) - list_move(&pin->list, &journal_seq_pin(j, seq)->flushed); + list_move(&pin->list, &journal_seq_pin(j, seq)->flushed[journal_pin_type(pin, flush_fn)]); j->flush_in_progress = NULL; j->flush_in_progress_dropped = false; spin_unlock(&j->lock); @@ -816,10 +831,41 @@ int bch2_journal_reclaim_start(struct journal *j) return 0; } +static bool journal_pins_still_flushing(struct journal *j, u64 seq_to_flush, + unsigned types) +{ + struct journal_entry_pin_list *pin_list; + u64 seq; + + spin_lock(&j->lock); + fifo_for_each_entry_ptr(pin_list, &j->pin, seq) { + if (seq > seq_to_flush) + break; + + for (unsigned i = 0; i < JOURNAL_PIN_TYPE_NR; i++) + if ((BIT(i) & types) && + (!list_empty(&pin_list->unflushed[i]) || + !list_empty(&pin_list->flushed[i]))) { + spin_unlock(&j->lock); + return true; + } + } + spin_unlock(&j->lock); + + return false; +} + +static bool journal_flush_pins_or_still_flushing(struct journal *j, u64 seq_to_flush, + unsigned types) +{ + return journal_flush_pins(j, seq_to_flush, types, 0, 0, 0) || + journal_pins_still_flushing(j, seq_to_flush, types); +} + static int journal_flush_done(struct journal *j, u64 seq_to_flush, bool *did_work) { - int ret; + int ret = 0; ret = bch2_journal_error(j); if (ret) @@ -827,12 +873,13 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush, mutex_lock(&j->reclaim_lock); - if (journal_flush_pins(j, seq_to_flush, - (1U << JOURNAL_PIN_key_cache)| - (1U << JOURNAL_PIN_other), 0, 0, 0) || - journal_flush_pins(j, seq_to_flush, - (1U << JOURNAL_PIN_btree), 0, 0, 0)) - *did_work = true; + for (int type = JOURNAL_PIN_TYPE_NR - 1; + type >= 0; + --type) + if (journal_flush_pins_or_still_flushing(j, seq_to_flush, BIT(type))) { + *did_work = true; + goto unlock; + } if (seq_to_flush > journal_cur_seq(j)) bch2_journal_entry_close(j); @@ -847,6 +894,7 @@ static int journal_flush_done(struct journal *j, u64 seq_to_flush, !fifo_used(&j->pin); spin_unlock(&j->lock); +unlock: mutex_unlock(&j->reclaim_lock); return ret; @@ -860,7 +908,7 @@ bool bch2_journal_flush_pins(struct journal *j, u64 seq_to_flush) if (!test_bit(JOURNAL_running, &j->flags)) return false; - closure_wait_event(&j->async_wait, + closure_wait_event(&j->reclaim_flush_wait, journal_flush_done(j, seq_to_flush, &did_work)); return did_work; @@ -926,3 +974,54 @@ err: return ret; } + +bool bch2_journal_seq_pins_to_text(struct printbuf *out, struct journal *j, u64 *seq) +{ + struct journal_entry_pin_list *pin_list; + struct journal_entry_pin *pin; + + spin_lock(&j->lock); + if (!test_bit(JOURNAL_running, &j->flags)) { + spin_unlock(&j->lock); + return true; + } + + *seq = max(*seq, j->pin.front); + + if (*seq >= j->pin.back) { + spin_unlock(&j->lock); + return true; + } + + out->atomic++; + + pin_list = journal_seq_pin(j, *seq); + + prt_printf(out, "%llu: count %u\n", *seq, atomic_read(&pin_list->count)); + printbuf_indent_add(out, 2); + + prt_printf(out, "unflushed:\n"); + for (unsigned i = 0; i < ARRAY_SIZE(pin_list->unflushed); i++) + list_for_each_entry(pin, &pin_list->unflushed[i], list) + prt_printf(out, "\t%px %ps\n", pin, pin->flush); + + prt_printf(out, "flushed:\n"); + for (unsigned i = 0; i < ARRAY_SIZE(pin_list->flushed); i++) + list_for_each_entry(pin, &pin_list->flushed[i], list) + prt_printf(out, "\t%px %ps\n", pin, pin->flush); + + printbuf_indent_sub(out, 2); + + --out->atomic; + spin_unlock(&j->lock); + + return false; +} + +void bch2_journal_pins_to_text(struct printbuf *out, struct journal *j) +{ + u64 seq = 0; + + while (!bch2_journal_seq_pins_to_text(out, j, &seq)) + seq++; +} diff --git a/fs/bcachefs/journal_reclaim.h b/fs/bcachefs/journal_reclaim.h index ec84c3345281..0a73d7134e1c 100644 --- a/fs/bcachefs/journal_reclaim.h +++ b/fs/bcachefs/journal_reclaim.h @@ -78,4 +78,7 @@ static inline bool bch2_journal_flush_all_pins(struct journal *j) int bch2_journal_flush_device_pins(struct journal *, int); +void bch2_journal_pins_to_text(struct printbuf *, struct journal *); +bool bch2_journal_seq_pins_to_text(struct printbuf *, struct journal *, u64 *); + #endif /* _BCACHEFS_JOURNAL_RECLAIM_H */ diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h index e9bd716fbb71..1ef3a28ed6ab 100644 --- a/fs/bcachefs/journal_types.h +++ b/fs/bcachefs/journal_types.h @@ -53,15 +53,18 @@ struct journal_buf { */ enum journal_pin_type { - JOURNAL_PIN_btree, - JOURNAL_PIN_key_cache, - JOURNAL_PIN_other, - JOURNAL_PIN_NR, + JOURNAL_PIN_TYPE_btree3, + JOURNAL_PIN_TYPE_btree2, + JOURNAL_PIN_TYPE_btree1, + JOURNAL_PIN_TYPE_btree0, + JOURNAL_PIN_TYPE_key_cache, + JOURNAL_PIN_TYPE_other, + JOURNAL_PIN_TYPE_NR, }; struct journal_entry_pin_list { - struct list_head list[JOURNAL_PIN_NR]; - struct list_head flushed; + struct list_head unflushed[JOURNAL_PIN_TYPE_NR]; + struct list_head flushed[JOURNAL_PIN_TYPE_NR]; atomic_t count; struct bch_devs_list devs; }; @@ -226,6 +229,7 @@ struct journal { /* Used when waiting because the journal was full */ wait_queue_head_t wait; struct closure_waitlist async_wait; + struct closure_waitlist reclaim_flush_wait; struct delayed_work write_work; struct workqueue_struct *wq; @@ -236,6 +240,7 @@ struct journal { /* seq, last_seq from the most recent journal entry successfully written */ u64 seq_ondisk; u64 flushed_seq_ondisk; + u64 flushing_seq; u64 last_seq_ondisk; u64 err_seq; u64 last_empty_seq; diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c index 85c361e78ba5..21805509ab9e 100644 --- a/fs/bcachefs/movinggc.c +++ b/fs/bcachefs/movinggc.c @@ -215,7 +215,8 @@ static int bch2_copygc(struct moving_context *ctxt, }; move_buckets buckets = { 0 }; struct move_bucket_in_flight *f; - u64 moved = atomic64_read(&ctxt->stats->sectors_moved); + u64 sectors_seen = atomic64_read(&ctxt->stats->sectors_seen); + u64 sectors_moved = atomic64_read(&ctxt->stats->sectors_moved); int ret = 0; ret = bch2_copygc_get_buckets(ctxt, buckets_in_flight, &buckets); @@ -245,7 +246,6 @@ static int bch2_copygc(struct moving_context *ctxt, *did_work = true; } err: - darray_exit(&buckets); /* no entries in LRU btree found, or got to end: */ if (bch2_err_matches(ret, ENOENT)) @@ -254,8 +254,11 @@ err: if (ret < 0 && !bch2_err_matches(ret, EROFS)) bch_err_msg(c, ret, "from bch2_move_data()"); - moved = atomic64_read(&ctxt->stats->sectors_moved) - moved; - trace_and_count(c, copygc, c, moved, 0, 0, 0); + sectors_seen = atomic64_read(&ctxt->stats->sectors_seen) - sectors_seen; + sectors_moved = atomic64_read(&ctxt->stats->sectors_moved) - sectors_moved; + trace_and_count(c, copygc, c, buckets.nr, sectors_seen, sectors_moved); + + darray_exit(&buckets); return ret; } diff --git a/fs/bcachefs/opts.h b/fs/bcachefs/opts.h index e763d52e0f38..9d397fc2a1f0 100644 --- a/fs/bcachefs/opts.h +++ b/fs/bcachefs/opts.h @@ -476,13 +476,13 @@ enum fsck_err_opts { NULL, "Enable nocow mode: enables runtime locking in\n"\ "data move path needed if nocow will ever be in use\n")\ x(copygc_enabled, u8, \ - OPT_FS|OPT_MOUNT, \ + OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "Enable copygc: disable for debugging, or to\n"\ "quiet the system when doing performance testing\n")\ x(rebalance_enabled, u8, \ - OPT_FS|OPT_MOUNT, \ + OPT_FS|OPT_MOUNT|OPT_RUNTIME, \ OPT_BOOL(), \ BCH2_NO_SB_OPT, true, \ NULL, "Enable rebalance: disable for debugging, or to\n"\ @@ -659,18 +659,4 @@ static inline void bch2_io_opts_fixups(struct bch_io_opts *opts) struct bch_io_opts bch2_opts_to_inode_opts(struct bch_opts); bool bch2_opt_is_inode_opt(enum bch_opt_id); -/* rebalance opts: */ - -static inline struct bch_extent_rebalance io_opts_to_rebalance_opts(struct bch_io_opts *opts) -{ - return (struct bch_extent_rebalance) { - .type = BIT(BCH_EXTENT_ENTRY_rebalance), -#define x(_name) \ - ._name = opts->_name, \ - ._name##_from_inode = opts->_name##_from_inode, - BCH_REBALANCE_OPTS() -#undef x - }; -}; - #endif /* _BCACHEFS_OPTS_H */ diff --git a/fs/bcachefs/rebalance.c b/fs/bcachefs/rebalance.c index 4adc74cd3f70..d0a1f5cd5c2b 100644 --- a/fs/bcachefs/rebalance.c +++ b/fs/bcachefs/rebalance.c @@ -121,12 +121,10 @@ u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *c, struct bkey_s_c k) } } incompressible: - if (opts->background_target && - bch2_target_accepts_data(c, BCH_DATA_user, opts->background_target)) { + if (opts->background_target) bkey_for_each_ptr_decode(k.k, ptrs, p, entry) if (!p.ptr.cached && !bch2_dev_in_target(c, p.ptr.dev, opts->background_target)) sectors += p.crc.compressed_size; - } return sectors; } @@ -140,7 +138,7 @@ static bool bch2_bkey_rebalance_needs_update(struct bch_fs *c, struct bch_io_opt const struct bch_extent_rebalance *old = bch2_bkey_rebalance_opts(k); if (k.k->type == KEY_TYPE_reflink_v || bch2_bkey_ptrs_need_rebalance(c, opts, k)) { - struct bch_extent_rebalance new = io_opts_to_rebalance_opts(opts); + struct bch_extent_rebalance new = io_opts_to_rebalance_opts(c, opts); return old == NULL || memcmp(old, &new, sizeof(new)); } else { return old != NULL; @@ -163,7 +161,7 @@ int bch2_bkey_set_needs_rebalance(struct bch_fs *c, struct bch_io_opts *opts, k.k->u64s += sizeof(*old) / sizeof(u64); } - *old = io_opts_to_rebalance_opts(opts); + *old = io_opts_to_rebalance_opts(c, opts); } else { if (old) extent_entry_drop(k, (union bch_extent_entry *) old); diff --git a/fs/bcachefs/rebalance.h b/fs/bcachefs/rebalance.h index 0a0821ab895d..62a3859d3823 100644 --- a/fs/bcachefs/rebalance.h +++ b/fs/bcachefs/rebalance.h @@ -4,8 +4,28 @@ #include "compress.h" #include "disk_groups.h" +#include "opts.h" #include "rebalance_types.h" +static inline struct bch_extent_rebalance io_opts_to_rebalance_opts(struct bch_fs *c, + struct bch_io_opts *opts) +{ + struct bch_extent_rebalance r = { + .type = BIT(BCH_EXTENT_ENTRY_rebalance), +#define x(_name) \ + ._name = opts->_name, \ + ._name##_from_inode = opts->_name##_from_inode, + BCH_REBALANCE_OPTS() +#undef x + }; + + if (r.background_target && + !bch2_target_accepts_data(c, BCH_DATA_user, r.background_target)) + r.background_target = 0; + + return r; +}; + u64 bch2_bkey_sectors_need_rebalance(struct bch_fs *, struct bkey_s_c); int bch2_bkey_set_needs_rebalance(struct bch_fs *, struct bch_io_opts *, struct bkey_i *); int bch2_get_update_rebalance_opts(struct btree_trans *, diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c index 98825437381c..71c786cdb192 100644 --- a/fs/bcachefs/recovery.c +++ b/fs/bcachefs/recovery.c @@ -32,7 +32,6 @@ #include <linux/sort.h> #include <linux/stat.h> -#define QSTR(n) { { { .len = strlen(n) } }, .name = n } int bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree) { diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index 93ba4f4e47ca..441e648f28b5 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -172,7 +172,7 @@ static int bch2_indirect_extent_missing_error(struct btree_trans *trans, bool should_commit) { if (REFLINK_P_ERROR(p.v)) - return -BCH_ERR_missing_indirect_extent; + return 0; struct bch_fs *c = trans->c; u64 live_start = REFLINK_P_IDX(p.v); @@ -259,8 +259,6 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, return k; if (unlikely(!bkey_extent_is_reflink_data(k.k))) { - bch2_trans_iter_exit(trans, iter); - unsigned size = min((u64) k.k->size, REFLINK_P_IDX(p.v) + p.k->size + le32_to_cpu(p.v->back_pad) - reflink_offset); @@ -268,14 +266,16 @@ struct bkey_s_c bch2_lookup_indirect_extent(struct btree_trans *trans, int ret = bch2_indirect_extent_missing_error(trans, p, reflink_offset, k.k->p.offset, should_commit); - if (ret) + if (ret) { + bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); + } } else if (unlikely(REFLINK_P_ERROR(p.v))) { - bch2_trans_iter_exit(trans, iter); - int ret = bch2_indirect_extent_not_missing(trans, p, should_commit); - if (ret) + if (ret) { + bch2_trans_iter_exit(trans, iter); return bkey_s_c_err(ret); + } } *offset_into_extent = reflink_offset - bkey_start_offset(k.k); @@ -300,7 +300,7 @@ static int trans_trigger_reflink_p_segment(struct btree_trans *trans, if (ret) return ret; - if (bkey_deleted(k.k)) { + if (!bkey_refcount_c(k)) { if (!(flags & BTREE_TRIGGER_overwrite)) ret = -BCH_ERR_missing_indirect_extent; goto next; diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c index 14f6b6a5fb38..35e07bc8fbd3 100644 --- a/fs/bcachefs/sb-downgrade.c +++ b/fs/bcachefs/sb-downgrade.c @@ -92,7 +92,7 @@ BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0, \ BCH_FSCK_ERR_accounting_key_junk_at_end) \ x(directory_size, \ - BIT_ULL(BCH_RECOVERY_PASS_check_inodes), \ + BIT_ULL(BCH_RECOVERY_PASS_check_dirents), \ BCH_FSCK_ERR_directory_size_mismatch) \ #define DOWNGRADE_TABLE() \ diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h index 0b4fe899209b..b86ec013d7d7 100644 --- a/fs/bcachefs/sb-errors_format.h +++ b/fs/bcachefs/sb-errors_format.h @@ -57,7 +57,7 @@ enum bch_fsck_flags { x(bset_wrong_sector_offset, 44, 0) \ x(bset_empty, 45, 0) \ x(bset_bad_seq, 46, 0) \ - x(bset_blacklisted_journal_seq, 47, 0) \ + x(bset_blacklisted_journal_seq, 47, FSCK_AUTOFIX) \ x(first_bset_blacklisted_journal_seq, 48, FSCK_AUTOFIX) \ x(btree_node_bad_btree, 49, 0) \ x(btree_node_bad_level, 50, 0) \ @@ -180,9 +180,9 @@ enum bch_fsck_flags { x(ptr_crc_nonce_mismatch, 162, 0) \ x(ptr_stripe_redundant, 163, 0) \ x(reservation_key_nr_replicas_invalid, 164, 0) \ - x(reflink_v_refcount_wrong, 165, 0) \ + x(reflink_v_refcount_wrong, 165, FSCK_AUTOFIX) \ x(reflink_v_pos_bad, 292, 0) \ - x(reflink_p_to_missing_reflink_v, 166, 0) \ + x(reflink_p_to_missing_reflink_v, 166, FSCK_AUTOFIX) \ x(reflink_refcount_underflow, 293, 0) \ x(stripe_pos_bad, 167, 0) \ x(stripe_val_size_bad, 168, 0) \ diff --git a/fs/bcachefs/str_hash.c b/fs/bcachefs/str_hash.c index 8c2c5539de2e..d78451c2a0c6 100644 --- a/fs/bcachefs/str_hash.c +++ b/fs/bcachefs/str_hash.c @@ -31,11 +31,11 @@ static int bch2_dirent_has_target(struct btree_trans *trans, struct bkey_s_c_dir } } -static int fsck_rename_dirent(struct btree_trans *trans, - struct snapshots_seen *s, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_s_c_dirent old) +static noinline int fsck_rename_dirent(struct btree_trans *trans, + struct snapshots_seen *s, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_s_c_dirent old) { struct qstr old_name = bch2_dirent_get_name(old); struct bkey_i_dirent *new = bch2_trans_kmalloc(trans, bkey_bytes(old.k) + 32); @@ -71,11 +71,11 @@ static int fsck_rename_dirent(struct btree_trans *trans, return bch2_fsck_update_backpointers(trans, s, desc, hash_info, &new->k_i); } -static int hash_pick_winner(struct btree_trans *trans, - const struct bch_hash_desc desc, - struct bch_hash_info *hash_info, - struct bkey_s_c k1, - struct bkey_s_c k2) +static noinline int hash_pick_winner(struct btree_trans *trans, + const struct bch_hash_desc desc, + struct bch_hash_info *hash_info, + struct bkey_s_c k1, + struct bkey_s_c k2) { if (bkey_val_bytes(k1.k) == bkey_val_bytes(k2.k) && !memcmp(k1.v, k2.v, bkey_val_bytes(k1.k))) @@ -142,8 +142,8 @@ fsck_err: * All versions of the same inode in different snapshots must have the same hash * seed/type: verify that the hash info we're using matches the root */ -static int check_inode_hash_info_matches_root(struct btree_trans *trans, u64 inum, - struct bch_hash_info *hash_info) +static noinline int check_inode_hash_info_matches_root(struct btree_trans *trans, u64 inum, + struct bch_hash_info *hash_info) { struct bch_fs *c = trans->c; struct btree_iter iter; diff --git a/fs/bcachefs/subvolume.c b/fs/bcachefs/subvolume.c index e3d0475232e5..b7b96283c316 100644 --- a/fs/bcachefs/subvolume.c +++ b/fs/bcachefs/subvolume.c @@ -428,7 +428,7 @@ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid) bch2_bkey_get_iter_typed(trans, &snapshot_iter, BTREE_ID_snapshots, POS(0, snapid), 0, snapshot); - ret = bkey_err(subvol); + ret = bkey_err(snapshot); bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, "missing snapshot %u", snapid); if (ret) @@ -440,6 +440,11 @@ static int __bch2_subvolume_delete(struct btree_trans *trans, u32 subvolid) bch2_bkey_get_iter_typed(trans, &snapshot_tree_iter, BTREE_ID_snapshot_trees, POS(0, treeid), 0, snapshot_tree); + ret = bkey_err(snapshot_tree); + bch2_fs_inconsistent_on(bch2_err_matches(ret, ENOENT), trans->c, + "missing snapshot tree %u", treeid); + if (ret) + goto err; if (le32_to_cpu(snapshot_tree.v->master_subvol) == subvolid) { struct bkey_i_snapshot_tree *snapshot_tree_mut = diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c index d97ea7bd1171..6d97d412fed9 100644 --- a/fs/bcachefs/super.c +++ b/fs/bcachefs/super.c @@ -411,6 +411,17 @@ bool bch2_fs_emergency_read_only(struct bch_fs *c) return ret; } +bool bch2_fs_emergency_read_only_locked(struct bch_fs *c) +{ + bool ret = !test_and_set_bit(BCH_FS_emergency_ro, &c->flags); + + bch2_journal_halt_locked(&c->journal); + bch2_fs_read_only_async(c); + + wake_up(&bch2_read_only_wait); + return ret; +} + static int bch2_fs_read_write_late(struct bch_fs *c) { int ret; diff --git a/fs/bcachefs/super.h b/fs/bcachefs/super.h index fa6d52216510..04f8287eff5c 100644 --- a/fs/bcachefs/super.h +++ b/fs/bcachefs/super.h @@ -29,6 +29,7 @@ int bch2_dev_resize(struct bch_fs *, struct bch_dev *, u64); struct bch_dev *bch2_dev_lookup(struct bch_fs *, const char *); bool bch2_fs_emergency_read_only(struct bch_fs *); +bool bch2_fs_emergency_read_only_locked(struct bch_fs *); void bch2_fs_read_only(struct bch_fs *); int bch2_fs_read_write(struct bch_fs *); diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index 9d40b7d4ea29..c1b51009edf6 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -727,7 +727,7 @@ DEFINE_EVENT(fs_str, bucket_alloc_fail, TP_ARGS(c, str) ); -TRACE_EVENT(discard_buckets, +DECLARE_EVENT_CLASS(discard_buckets_class, TP_PROTO(struct bch_fs *c, u64 seen, u64 open, u64 need_journal_commit, u64 discarded, const char *err), TP_ARGS(c, seen, open, need_journal_commit, discarded, err), @@ -759,6 +759,18 @@ TRACE_EVENT(discard_buckets, __entry->err) ); +DEFINE_EVENT(discard_buckets_class, discard_buckets, + TP_PROTO(struct bch_fs *c, u64 seen, u64 open, + u64 need_journal_commit, u64 discarded, const char *err), + TP_ARGS(c, seen, open, need_journal_commit, discarded, err) +); + +DEFINE_EVENT(discard_buckets_class, discard_buckets_fast, + TP_PROTO(struct bch_fs *c, u64 seen, u64 open, + u64 need_journal_commit, u64 discarded, const char *err), + TP_ARGS(c, seen, open, need_journal_commit, discarded, err) +); + TRACE_EVENT(bucket_invalidate, TP_PROTO(struct bch_fs *c, unsigned dev, u64 bucket, u32 sectors), TP_ARGS(c, dev, bucket, sectors), @@ -902,32 +914,30 @@ TRACE_EVENT(evacuate_bucket, TRACE_EVENT(copygc, TP_PROTO(struct bch_fs *c, - u64 sectors_moved, u64 sectors_not_moved, - u64 buckets_moved, u64 buckets_not_moved), - TP_ARGS(c, - sectors_moved, sectors_not_moved, - buckets_moved, buckets_not_moved), + u64 buckets, + u64 sectors_seen, + u64 sectors_moved), + TP_ARGS(c, buckets, sectors_seen, sectors_moved), TP_STRUCT__entry( __field(dev_t, dev ) + __field(u64, buckets ) + __field(u64, sectors_seen ) __field(u64, sectors_moved ) - __field(u64, sectors_not_moved ) - __field(u64, buckets_moved ) - __field(u64, buckets_not_moved ) ), TP_fast_assign( __entry->dev = c->dev; + __entry->buckets = buckets; + __entry->sectors_seen = sectors_seen; __entry->sectors_moved = sectors_moved; - __entry->sectors_not_moved = sectors_not_moved; - __entry->buckets_moved = buckets_moved; - __entry->buckets_not_moved = buckets_moved; ), - TP_printk("%d,%d sectors moved %llu remain %llu buckets moved %llu remain %llu", + TP_printk("%d,%d buckets %llu sectors seen %llu moved %llu", MAJOR(__entry->dev), MINOR(__entry->dev), - __entry->sectors_moved, __entry->sectors_not_moved, - __entry->buckets_moved, __entry->buckets_not_moved) + __entry->buckets, + __entry->sectors_seen, + __entry->sectors_moved) ); TRACE_EVENT(copygc_wait, diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h index 1a1720116071..e7c3541b38f3 100644 --- a/fs/bcachefs/util.h +++ b/fs/bcachefs/util.h @@ -670,8 +670,6 @@ static inline int cmp_le32(__le32 l, __le32 r) #include <linux/uuid.h> -#define QSTR(n) { { { .len = strlen(n) } }, .name = n } - static inline bool qstr_eq(const struct qstr l, const struct qstr r) { return l.len == r.len && !memcmp(l.name, r.name, l.len); diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 92071ca0655f..3dc5a35dd19b 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1496,6 +1496,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, if (!p->skip_locking) { btrfs_unlock_up_safe(p, parent_level + 1); + btrfs_maybe_reset_lockdep_class(root, tmp); tmp_locked = true; btrfs_tree_read_lock(tmp); btrfs_release_path(p); @@ -1539,6 +1540,7 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p, if (!p->skip_locking) { ASSERT(ret == -EAGAIN); + btrfs_maybe_reset_lockdep_class(root, tmp); tmp_locked = true; btrfs_tree_read_lock(tmp); btrfs_release_path(p); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index a2cac9d0a1a9..b2fae67f8fa3 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -523,8 +523,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) u64 end; u32 len; - /* For now only order 0 folios are supported for data. */ - ASSERT(folio_order(folio) == 0); btrfs_debug(fs_info, "%s: bi_sector=%llu, err=%d, mirror=%u", __func__, bio->bi_iter.bi_sector, bio->bi_status, @@ -552,7 +550,6 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) if (likely(uptodate)) { loff_t i_size = i_size_read(inode); - pgoff_t end_index = i_size >> folio_shift(folio); /* * Zero out the remaining part if this range straddles @@ -561,9 +558,11 @@ static void end_bbio_data_read(struct btrfs_bio *bbio) * Here we should only zero the range inside the folio, * not touch anything else. * - * NOTE: i_size is exclusive while end is inclusive. + * NOTE: i_size is exclusive while end is inclusive and + * folio_contains() takes PAGE_SIZE units. */ - if (folio_index(folio) == end_index && i_size <= end) { + if (folio_contains(folio, i_size >> PAGE_SHIFT) && + i_size <= end) { u32 zero_start = max(offset_in_folio(folio, i_size), offset_in_folio(folio, start)); u32 zero_len = offset_in_folio(folio, end) + 1 - @@ -899,7 +898,6 @@ static struct extent_map *get_extent_map(struct btrfs_inode *inode, u64 len, struct extent_map **em_cached) { struct extent_map *em; - struct extent_state *cached_state = NULL; ASSERT(em_cached); @@ -915,14 +913,12 @@ static struct extent_map *get_extent_map(struct btrfs_inode *inode, *em_cached = NULL; } - btrfs_lock_and_flush_ordered_range(inode, start, start + len - 1, &cached_state); em = btrfs_get_extent(inode, folio, start, len); if (!IS_ERR(em)) { BUG_ON(*em_cached); refcount_inc(&em->refs); *em_cached = em; } - unlock_extent(&inode->io_tree, start, start + len - 1, &cached_state); return em; } @@ -956,7 +952,7 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, return ret; } - if (folio->index == last_byte >> folio_shift(folio)) { + if (folio_contains(folio, last_byte >> PAGE_SHIFT)) { size_t zero_offset = offset_in_folio(folio, last_byte); if (zero_offset) { @@ -1079,11 +1075,18 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, int btrfs_read_folio(struct file *file, struct folio *folio) { + struct btrfs_inode *inode = folio_to_inode(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 extent_map *em_cached = NULL; int ret; + btrfs_lock_and_flush_ordered_range(inode, start, end, &cached_state); ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL); + unlock_extent(&inode->io_tree, start, end, &cached_state); + free_extent_map(em_cached); /* @@ -2380,12 +2383,20 @@ void btrfs_readahead(struct readahead_control *rac) { struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD }; struct folio *folio; + struct btrfs_inode *inode = BTRFS_I(rac->mapping->host); + const u64 start = readahead_pos(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; + btrfs_lock_and_flush_ordered_range(inode, start, end, &cached_state); + while ((folio = readahead_folio(rac)) != NULL) btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start); + unlock_extent(&inode->io_tree, start, end, &cached_state); + if (em_cached) free_extent_map(em_cached); submit_one_bio(&bio_ctrl); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 36f51c311bb1..ed3c0d6546c5 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1039,7 +1039,6 @@ int btrfs_write_check(struct kiocb *iocb, size_t count) loff_t pos = iocb->ki_pos; int ret; loff_t oldsize; - loff_t start_pos; /* * Quickly bail out on NOWAIT writes if we don't have the nodatacow or @@ -1066,9 +1065,8 @@ int btrfs_write_check(struct kiocb *iocb, size_t count) inode_inc_iversion(inode); } - start_pos = round_down(pos, fs_info->sectorsize); oldsize = i_size_read(inode); - if (start_pos > oldsize) { + if (pos > oldsize) { /* Expand hole size to cover write data, preventing empty gap */ loff_t end_pos = round_up(pos + count, fs_info->sectorsize); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 30eceaf829a7..4aca7475fd82 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -1229,6 +1229,18 @@ struct btrfs_ordered_extent *btrfs_split_ordered_extent( */ if (WARN_ON_ONCE(len >= ordered->num_bytes)) return ERR_PTR(-EINVAL); + /* + * If our ordered extent had an error there's no point in continuing. + * The error may have come from a transaction abort done either by this + * task or some other concurrent task, and the transaction abort path + * iterates over all existing ordered extents and sets the flag + * BTRFS_ORDERED_IOERR on them. + */ + if (unlikely(flags & (1U << BTRFS_ORDERED_IOERR))) { + const int fs_error = BTRFS_FS_ERROR(fs_info); + + return fs_error ? ERR_PTR(fs_error) : ERR_PTR(-EIO); + } /* We cannot split partially completed ordered extents. */ if (ordered->bytes_left) { ASSERT(!(flags & ~BTRFS_ORDERED_TYPE_FLAGS)); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index b90fabe302e6..f9d3766c809b 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1880,11 +1880,7 @@ int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 su * Commit current transaction to make sure all the rfer/excl numbers * get updated. */ - trans = btrfs_start_transaction(fs_info->quota_root, 0); - if (IS_ERR(trans)) - return PTR_ERR(trans); - - ret = btrfs_commit_transaction(trans); + ret = btrfs_commit_current_transaction(fs_info->quota_root); if (ret < 0) return ret; @@ -1897,8 +1893,11 @@ int btrfs_qgroup_cleanup_dropped_subvolume(struct btrfs_fs_info *fs_info, u64 su /* * It's squota and the subvolume still has numbers needed for future * accounting, in this case we can not delete it. Just skip it. + * + * Or the qgroup is already removed by a qgroup rescan. For both cases we're + * safe to ignore them. */ - if (ret == -EBUSY) + if (ret == -EBUSY || ret == -ENOENT) ret = 0; return ret; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 15312013f2a3..aca83a98b75a 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -274,8 +274,10 @@ loop: cur_trans = fs_info->running_transaction; if (cur_trans) { if (TRANS_ABORTED(cur_trans)) { + const int abort_error = cur_trans->aborted; + spin_unlock(&fs_info->trans_lock); - return cur_trans->aborted; + return abort_error; } if (btrfs_blocked_trans_types[cur_trans->state] & type) { spin_unlock(&fs_info->trans_lock); diff --git a/fs/cachefiles/error_inject.c b/fs/cachefiles/error_inject.c index 1715d5ca2b2d..e341ade47dd8 100644 --- a/fs/cachefiles/error_inject.c +++ b/fs/cachefiles/error_inject.c @@ -11,7 +11,7 @@ unsigned int cachefiles_error_injection_state; static struct ctl_table_header *cachefiles_sysctl; -static struct ctl_table cachefiles_sysctls[] = { +static const struct ctl_table cachefiles_sysctls[] = { { .procname = "error_injection", .data = &cachefiles_error_injection_state, diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fdf9dc15eafa..fdd404fc8112 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -412,7 +412,7 @@ void ceph_fs_debugfs_cleanup(struct ceph_fs_client *fsc) void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) { - char name[100]; + char name[NAME_MAX]; doutc(fsc->client, "begin\n"); fsc->debugfs_congestion_kb = diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 0bf388e07a02..62e99e65250d 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1940,29 +1940,19 @@ static int dir_lease_is_valid(struct inode *dir, struct dentry *dentry, /* * Check if cached dentry can be trusted. */ -static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) +static int ceph_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct ceph_mds_client *mdsc = ceph_sb_to_fs_client(dentry->d_sb)->mdsc; struct ceph_client *cl = mdsc->fsc->client; int valid = 0; - struct dentry *parent; - struct inode *dir, *inode; + struct inode *inode; - valid = fscrypt_d_revalidate(dentry, flags); + valid = fscrypt_d_revalidate(dir, name, dentry, flags); if (valid <= 0) return valid; - if (flags & LOOKUP_RCU) { - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - inode = d_inode_rcu(dentry); - } else { - parent = dget_parent(dentry); - dir = d_inode(parent); - inode = d_inode(dentry); - } + inode = d_inode_rcu(dentry); doutc(cl, "%p '%pd' inode %p offset 0x%llx nokey %d\n", dentry, dentry, inode, ceph_dentry(dentry)->offset, @@ -2008,6 +1998,8 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) req->r_parent = dir; ihold(dir); + req->r_dname = name; + mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED; if (ceph_security_xattr_wanted(dir)) mask |= CEPH_CAP_XATTR_SHARED; @@ -2038,9 +2030,6 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags) doutc(cl, "%p '%pd' %s\n", dentry, dentry, valid ? "valid" : "invalid"); if (!valid) ceph_dir_clear_complete(dir); - - if (!(flags & LOOKUP_RCU)) - dput(parent); return valid; } diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 785fe489ef4b..54b3421501e9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2621,6 +2621,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) { struct inode *dir = req->r_parent; struct dentry *dentry = req->r_dentry; + const struct qstr *name = req->r_dname; u8 *cryptbuf = NULL; u32 len = 0; int ret = 0; @@ -2641,8 +2642,10 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) if (!fscrypt_has_encryption_key(dir)) goto success; - if (!fscrypt_fname_encrypted_size(dir, dentry->d_name.len, NAME_MAX, - &len)) { + if (!name) + name = &dentry->d_name; + + if (!fscrypt_fname_encrypted_size(dir, name->len, NAME_MAX, &len)) { WARN_ON_ONCE(1); return ERR_PTR(-ENAMETOOLONG); } @@ -2657,7 +2660,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) if (!cryptbuf) return ERR_PTR(-ENOMEM); - ret = fscrypt_fname_encrypt(dir, &dentry->d_name, cryptbuf, len); + ret = fscrypt_fname_encrypt(dir, name, cryptbuf, len); if (ret) { kfree(cryptbuf); return ERR_PTR(ret); @@ -2945,12 +2948,12 @@ static struct ceph_mds_request_head_legacy * find_legacy_request_head(void *p, u64 features) { bool legacy = !(features & CEPH_FEATURE_FS_BTIME); - struct ceph_mds_request_head_old *ohead; + struct ceph_mds_request_head *head; if (legacy) return (struct ceph_mds_request_head_legacy *)p; - ohead = (struct ceph_mds_request_head_old *)p; - return (struct ceph_mds_request_head_legacy *)&ohead->oldest_client_tid; + head = (struct ceph_mds_request_head *)p; + return (struct ceph_mds_request_head_legacy *)&head->oldest_client_tid; } /* @@ -3020,7 +3023,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, if (legacy) len = sizeof(struct ceph_mds_request_head_legacy); else if (request_head_version == 1) - len = sizeof(struct ceph_mds_request_head_old); + len = offsetofend(struct ceph_mds_request_head, args); else if (request_head_version == 2) len = offsetofend(struct ceph_mds_request_head, ext_num_fwd); else @@ -3104,11 +3107,11 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, msg->hdr.version = cpu_to_le16(3); p = msg->front.iov_base + sizeof(*lhead); } else if (request_head_version == 1) { - struct ceph_mds_request_head_old *ohead = msg->front.iov_base; + struct ceph_mds_request_head *nhead = msg->front.iov_base; msg->hdr.version = cpu_to_le16(4); - ohead->version = cpu_to_le16(1); - p = msg->front.iov_base + sizeof(*ohead); + nhead->version = cpu_to_le16(1); + p = msg->front.iov_base + offsetofend(struct ceph_mds_request_head, args); } else if (request_head_version == 2) { struct ceph_mds_request_head *nhead = msg->front.iov_base; @@ -3265,7 +3268,7 @@ static int __prepare_send_request(struct ceph_mds_session *session, * so we limit to retry at most 256 times. */ if (req->r_attempts) { - old_max_retry = sizeof_field(struct ceph_mds_request_head_old, + old_max_retry = sizeof_field(struct ceph_mds_request_head, num_retry); old_max_retry = 1 << (old_max_retry * BITS_PER_BYTE); if ((old_version && req->r_attempts >= old_max_retry) || @@ -5690,18 +5693,18 @@ static int ceph_mds_auth_match(struct ceph_mds_client *mdsc, * * All the other cases --> mismatch */ + bool path_matched = true; char *first = strstr(_tpath, auth->match.path); - if (first != _tpath) { - if (free_tpath) - kfree(_tpath); - return 0; + if (first != _tpath || + (tlen > len && _tpath[len] != '/')) { + path_matched = false; } - if (tlen > len && _tpath[len] != '/') { - if (free_tpath) - kfree(_tpath); + if (free_tpath) + kfree(_tpath); + + if (!path_matched) return 0; - } } } diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 38bb7e0d2d79..7c9fee9e80d4 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -299,6 +299,8 @@ struct ceph_mds_request { struct inode *r_target_inode; /* resulting inode */ struct inode *r_new_inode; /* new inode (for creates) */ + const struct qstr *r_dname; /* stable name (for ->d_revalidate) */ + #define CEPH_MDS_R_DIRECT_IS_HASH (1) /* r_direct_hash is valid */ #define CEPH_MDS_R_ABORTED (2) /* call was aborted */ #define CEPH_MDS_R_GOT_UNSAFE (3) /* got an unsafe reply */ diff --git a/fs/coda/dir.c b/fs/coda/dir.c index 4e552ba7bd43..a3e2dfeedfbf 100644 --- a/fs/coda/dir.c +++ b/fs/coda/dir.c @@ -445,7 +445,8 @@ static int coda_readdir(struct file *coda_file, struct dir_context *ctx) } /* called when a cache lookup succeeds */ -static int coda_dentry_revalidate(struct dentry *de, unsigned int flags) +static int coda_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *de, unsigned int flags) { struct inode *inode; struct coda_inode_info *cii; diff --git a/fs/coda/sysctl.c b/fs/coda/sysctl.c index 9f2d5743e2c8..0df46f09b6cc 100644 --- a/fs/coda/sysctl.c +++ b/fs/coda/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *fs_table_header; -static struct ctl_table coda_table[] = { +static const struct ctl_table coda_table[] = { { .procname = "timeout", .data = &coda_timeout, diff --git a/fs/coredump.c b/fs/coredump.c index d48edb37bc35..591700e1b2ce 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -995,7 +995,7 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write, static const unsigned int core_file_note_size_min = CORE_FILE_NOTE_SIZE_DEFAULT; static const unsigned int core_file_note_size_max = CORE_FILE_NOTE_SIZE_MAX; -static struct ctl_table coredump_sysctls[] = { +static const struct ctl_table coredump_sysctls[] = { { .procname = "core_uses_pid", .data = &core_uses_pid, diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 0ad52fbe51c9..010f9c0a4c2f 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -574,11 +574,10 @@ EXPORT_SYMBOL_GPL(fscrypt_fname_siphash); * Validate dentries in encrypted directories to make sure we aren't potentially * caching stale dentries after a key has been added. */ -int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) +int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - struct dentry *dir; int err; - int valid; /* * Plaintext names are always valid, since fscrypt doesn't support @@ -591,30 +590,21 @@ int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) /* * No-key name; valid if the directory's key is still unavailable. * - * Although fscrypt forbids rename() on no-key names, we still must use - * dget_parent() here rather than use ->d_parent directly. That's - * because a corrupted fs image may contain directory hard links, which - * the VFS handles by moving the directory's dentry tree in the dcache - * each time ->lookup() finds the directory and it already has a dentry - * elsewhere. Thus ->d_parent can be changing, and we must safely grab - * a reference to some ->d_parent to prevent it from being freed. + * Note in RCU mode we have to bail if we get here - + * fscrypt_get_encryption_info() may block. */ if (flags & LOOKUP_RCU) return -ECHILD; - dir = dget_parent(dentry); /* * Pass allow_unsupported=true, so that files with an unsupported * encryption policy can be deleted. */ - err = fscrypt_get_encryption_info(d_inode(dir), true); - valid = !fscrypt_has_encryption_key(d_inode(dir)); - dput(dir); - + err = fscrypt_get_encryption_info(dir, true); if (err < 0) return err; - return valid; + return !fscrypt_has_encryption_key(dir); } EXPORT_SYMBOL_GPL(fscrypt_d_revalidate); diff --git a/fs/dcache.c b/fs/dcache.c index 1a01d7a6a7a9..e3634916ffb9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -192,7 +192,7 @@ static int proc_nr_dentry(const struct ctl_table *table, int write, void *buffer return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_dcache_sysctls[] = { +static const struct ctl_table fs_dcache_sysctls[] = { { .procname = "dentry-state", .data = &dentry_stat, @@ -295,12 +295,16 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c return dentry_string_cmp(cs, ct, tcount); } +/* + * long names are allocated separately from dentry and never modified. + * Refcounted, freeing is RCU-delayed. See take_dentry_name_snapshot() + * for the reason why ->count and ->head can't be combined into a union. + * dentry_string_cmp() relies upon ->name[] being word-aligned. + */ struct external_name { - union { - atomic_t count; - struct rcu_head head; - } u; - unsigned char name[]; + atomic_t count; + struct rcu_head head; + unsigned char name[] __aligned(sizeof(unsigned long)); }; static inline struct external_name *external_name(struct dentry *dentry) @@ -324,31 +328,45 @@ static void __d_free_external(struct rcu_head *head) static inline int dname_external(const struct dentry *dentry) { - return dentry->d_name.name != dentry->d_iname; + return dentry->d_name.name != dentry->d_shortname.string; } void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry) { - spin_lock(&dentry->d_lock); - name->name = dentry->d_name; - if (unlikely(dname_external(dentry))) { - atomic_inc(&external_name(dentry)->u.count); + unsigned seq; + const unsigned char *s; + + rcu_read_lock(); +retry: + seq = read_seqcount_begin(&dentry->d_seq); + s = READ_ONCE(dentry->d_name.name); + name->name.hash_len = dentry->d_name.hash_len; + name->name.name = name->inline_name.string; + if (likely(s == dentry->d_shortname.string)) { + name->inline_name = dentry->d_shortname; } else { - memcpy(name->inline_name, dentry->d_iname, - dentry->d_name.len + 1); - name->name.name = name->inline_name; + struct external_name *p; + p = container_of(s, struct external_name, name[0]); + // get a valid reference + if (unlikely(!atomic_inc_not_zero(&p->count))) + goto retry; + name->name.name = s; } - spin_unlock(&dentry->d_lock); + if (read_seqcount_retry(&dentry->d_seq, seq)) { + release_dentry_name_snapshot(name); + goto retry; + } + rcu_read_unlock(); } EXPORT_SYMBOL(take_dentry_name_snapshot); void release_dentry_name_snapshot(struct name_snapshot *name) { - if (unlikely(name->name.name != name->inline_name)) { + if (unlikely(name->name.name != name->inline_name.string)) { struct external_name *p; p = container_of(name->name.name, struct external_name, name[0]); - if (unlikely(atomic_dec_and_test(&p->u.count))) - kfree_rcu(p, u.head); + if (unlikely(atomic_dec_and_test(&p->count))) + kfree_rcu(p, head); } } EXPORT_SYMBOL(release_dentry_name_snapshot); @@ -386,7 +404,7 @@ static void dentry_free(struct dentry *dentry) WARN_ON(!hlist_unhashed(&dentry->d_u.d_alias)); if (unlikely(dname_external(dentry))) { struct external_name *p = external_name(dentry); - if (likely(atomic_dec_and_test(&p->u.count))) { + if (likely(atomic_dec_and_test(&p->count))) { call_rcu(&dentry->d_u.d_rcu, __d_free_external); return; } @@ -1654,10 +1672,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) * will still always have a NUL at the end, even if we might * be overwriting an internal NUL character */ - dentry->d_iname[DNAME_INLINE_LEN-1] = 0; + dentry->d_shortname.string[DNAME_INLINE_LEN-1] = 0; if (unlikely(!name)) { name = &slash_name; - dname = dentry->d_iname; + dname = dentry->d_shortname.string; } else if (name->len > DNAME_INLINE_LEN-1) { size_t size = offsetof(struct external_name, name[1]); struct external_name *p = kmalloc(size + name->len, @@ -1667,10 +1685,10 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) kmem_cache_free(dentry_cache, dentry); return NULL; } - atomic_set(&p->u.count, 1); + atomic_set(&p->count, 1); dname = p->name; } else { - dname = dentry->d_iname; + dname = dentry->d_shortname.string; } dentry->d_name.len = name->len; @@ -1682,7 +1700,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name) smp_store_release(&dentry->d_name.name, dname); /* ^^^ */ dentry->d_flags = 0; - lockref_init(&dentry->d_lockref, 1); + lockref_init(&dentry->d_lockref); seqcount_spinlock_init(&dentry->d_seq, &dentry->d_lock); dentry->d_inode = NULL; dentry->d_parent = dentry; @@ -2728,10 +2746,9 @@ static void swap_names(struct dentry *dentry, struct dentry *target) * dentry:internal, target:external. Steal target's * storage and make target internal. */ - memcpy(target->d_iname, dentry->d_name.name, - dentry->d_name.len + 1); dentry->d_name.name = target->d_name.name; - target->d_name.name = target->d_iname; + target->d_shortname = dentry->d_shortname; + target->d_name.name = target->d_shortname.string; } } else { if (unlikely(dname_external(dentry))) { @@ -2739,20 +2756,16 @@ static void swap_names(struct dentry *dentry, struct dentry *target) * dentry:external, target:internal. Give dentry's * storage to target and make dentry internal */ - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); target->d_name.name = dentry->d_name.name; - dentry->d_name.name = dentry->d_iname; + dentry->d_shortname = target->d_shortname; + dentry->d_name.name = dentry->d_shortname.string; } else { /* * Both are internal. */ - unsigned int i; - BUILD_BUG_ON(!IS_ALIGNED(DNAME_INLINE_LEN, sizeof(long))); - for (i = 0; i < DNAME_INLINE_LEN / sizeof(long); i++) { - swap(((long *) &dentry->d_iname)[i], - ((long *) &target->d_iname)[i]); - } + for (int i = 0; i < DNAME_INLINE_WORDS; i++) + swap(dentry->d_shortname.words[i], + target->d_shortname.words[i]); } } swap(dentry->d_name.hash_len, target->d_name.hash_len); @@ -2764,16 +2777,15 @@ static void copy_name(struct dentry *dentry, struct dentry *target) if (unlikely(dname_external(dentry))) old_name = external_name(dentry); if (unlikely(dname_external(target))) { - atomic_inc(&external_name(target)->u.count); + atomic_inc(&external_name(target)->count); dentry->d_name = target->d_name; } else { - memcpy(dentry->d_iname, target->d_name.name, - target->d_name.len + 1); - dentry->d_name.name = dentry->d_iname; + dentry->d_shortname = target->d_shortname; + dentry->d_name.name = dentry->d_shortname.string; dentry->d_name.hash_len = target->d_name.hash_len; } - if (old_name && likely(atomic_dec_and_test(&old_name->u.count))) - kfree_rcu(old_name, u.head); + if (old_name && likely(atomic_dec_and_test(&old_name->count))) + kfree_rcu(old_name, head); } /* @@ -2954,7 +2966,12 @@ static int __d_unalias(struct dentry *dentry, struct dentry *alias) goto out_err; m2 = &alias->d_parent->d_inode->i_rwsem; out_unalias: + if (alias->d_op && alias->d_op->d_unalias_trylock && + !alias->d_op->d_unalias_trylock(alias)) + goto out_err; __d_move(alias, dentry, false); + if (alias->d_op && alias->d_op->d_unalias_unlock) + alias->d_op->d_unalias_unlock(alias); ret = 0; out_err: if (m2) @@ -3102,12 +3119,12 @@ void d_mark_tmpfile(struct file *file, struct inode *inode) { struct dentry *dentry = file->f_path.dentry; - BUG_ON(dentry->d_name.name != dentry->d_iname || + BUG_ON(dname_external(dentry) || !hlist_unhashed(&dentry->d_u.d_alias) || !d_unlinked(dentry)); spin_lock(&dentry->d_parent->d_lock); spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); - dentry->d_name.len = sprintf(dentry->d_iname, "#%llu", + dentry->d_name.len = sprintf(dentry->d_shortname.string, "#%llu", (unsigned long long)inode->i_ino); spin_unlock(&dentry->d_lock); spin_unlock(&dentry->d_parent->d_lock); @@ -3195,7 +3212,7 @@ static void __init dcache_init(void) */ dentry_cache = KMEM_CACHE_USERCOPY(dentry, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_ACCOUNT, - d_iname); + d_shortname.string); /* Hash may have been set up in dcache_init_early */ if (!hashdist) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index e33cc77699cd..69e9ddcb113d 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -94,6 +94,7 @@ static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) fsd = d_fsd; } else { struct inode *inode = dentry->d_inode; + unsigned int methods = 0; if (WARN_ON(mode == DBGFS_GET_ALREADY)) return -EINVAL; @@ -106,25 +107,28 @@ static int __debugfs_file_get(struct dentry *dentry, enum dbgfs_get_mode mode) const struct debugfs_short_fops *ops; ops = fsd->short_fops = DEBUGFS_I(inode)->short_fops; if (ops->llseek) - fsd->methods |= HAS_LSEEK; + methods |= HAS_LSEEK; if (ops->read) - fsd->methods |= HAS_READ; + methods |= HAS_READ; if (ops->write) - fsd->methods |= HAS_WRITE; + methods |= HAS_WRITE; + fsd->real_fops = NULL; } else { const struct file_operations *ops; ops = fsd->real_fops = DEBUGFS_I(inode)->real_fops; if (ops->llseek) - fsd->methods |= HAS_LSEEK; + methods |= HAS_LSEEK; if (ops->read) - fsd->methods |= HAS_READ; + methods |= HAS_READ; if (ops->write) - fsd->methods |= HAS_WRITE; + methods |= HAS_WRITE; if (ops->unlocked_ioctl) - fsd->methods |= HAS_IOCTL; + methods |= HAS_IOCTL; if (ops->poll) - fsd->methods |= HAS_POLL; + methods |= HAS_POLL; + fsd->short_fops = NULL; } + fsd->methods = methods; refcount_set(&fsd->active_users, 1); init_completion(&fsd->active_users_drained); INIT_LIST_HEAD(&fsd->cancellations); diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index b20e565b9c5e..1096ff8562fa 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -45,7 +45,7 @@ static int pty_limit_min; static int pty_limit_max = INT_MAX; static atomic_t pty_count = ATOMIC_INIT(0); -static struct ctl_table pty_table[] = { +static const struct ctl_table pty_table[] = { { .procname = "max", .maxlen = sizeof(int), diff --git a/fs/ecryptfs/dentry.c b/fs/ecryptfs/dentry.c index acaa0825e9bb..1dfd5b81d831 100644 --- a/fs/ecryptfs/dentry.c +++ b/fs/ecryptfs/dentry.c @@ -17,7 +17,9 @@ /** * ecryptfs_d_revalidate - revalidate an ecryptfs dentry - * @dentry: The ecryptfs dentry + * @dir: inode of expected parent + * @name: expected name + * @dentry: dentry to revalidate * @flags: lookup flags * * Called when the VFS needs to revalidate a dentry. This @@ -28,7 +30,8 @@ * Returns 1 if valid, 0 otherwise. * */ -static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int ecryptfs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry); int rc = 1; @@ -36,8 +39,15 @@ static int ecryptfs_d_revalidate(struct dentry *dentry, unsigned int flags) if (flags & LOOKUP_RCU) return -ECHILD; - if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE) - rc = lower_dentry->d_op->d_revalidate(lower_dentry, flags); + if (lower_dentry->d_flags & DCACHE_OP_REVALIDATE) { + struct inode *lower_dir = ecryptfs_inode_to_lower(dir); + struct name_snapshot n; + + take_dentry_name_snapshot(&n, lower_dentry); + rc = lower_dentry->d_op->d_revalidate(lower_dir, &n.name, + lower_dentry, flags); + release_dentry_name_snapshot(&n); + } if (d_really_is_positive(dentry)) { struct inode *inode = d_inode(dentry); diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 7940241d9355..df2777e05661 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -407,7 +407,7 @@ int erofs_getxattr(struct inode *inode, int index, const char *name, } it.index = index; - it.name = (struct qstr)QSTR_INIT(name, strlen(name)); + it.name = QSTR(name); if (it.name.len > EROFS_NAME_LEN) return -ERANGE; diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 29f8963bb523..d771e06db738 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -726,7 +726,7 @@ static int z_erofs_register_pcluster(struct z_erofs_frontend *fe) if (IS_ERR(pcl)) return PTR_ERR(pcl); - lockref_init(&pcl->lockref, 1); /* one ref for this request */ + lockref_init(&pcl->lockref); /* one ref for this request */ pcl->algorithmformat = map->m_algorithmformat; pcl->length = 0; pcl->partial = true; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index f9898e60dd8b..7c0980db77b3 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -318,7 +318,7 @@ static void unlist_file(struct epitems_head *head) static long long_zero; static long long_max = LONG_MAX; -static struct ctl_table epoll_table[] = { +static const struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, diff --git a/fs/exec.c b/fs/exec.c index a49839174472..506cd411f4ac 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2159,7 +2159,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ return error; } -static struct ctl_table fs_exec_sysctls[] = { +static const struct ctl_table fs_exec_sysctls[] = { { .procname = "suid_dumpable", .data = &suid_dumpable, diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index 099f80645072..691dd77b6ab5 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -31,10 +31,9 @@ static inline void exfat_d_version_set(struct dentry *dentry, * If it happened, the negative dentry isn't actually negative anymore. So, * drop it. */ -static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags) +static int exfat_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - int ret; - if (flags & LOOKUP_RCU) return -ECHILD; @@ -58,11 +57,7 @@ static int exfat_d_revalidate(struct dentry *dentry, unsigned int flags) if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; - spin_lock(&dentry->d_lock); - ret = inode_eq_iversion(d_inode(dentry->d_parent), - exfat_d_version(dentry)); - spin_unlock(&dentry->d_lock); - return ret; + return inode_eq_iversion(dir, exfat_d_version(dentry)); } /* returns the length of a struct qstr, ignoring trailing dots if necessary */ diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 26c4fc37edcf..da4263a14a20 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -322,9 +322,7 @@ restart: WARN_ON(!list_empty(&ei->i_fc_dilist)); spin_unlock(&sbi->s_fc_lock); - if (fc_dentry->fcd_name.name && - fc_dentry->fcd_name.len > DNAME_INLINE_LEN) - kfree(fc_dentry->fcd_name.name); + release_dentry_name_snapshot(&fc_dentry->fcd_name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); return; @@ -449,22 +447,7 @@ static int __track_dentry_update(handle_t *handle, struct inode *inode, node->fcd_op = dentry_update->op; node->fcd_parent = dir->i_ino; node->fcd_ino = inode->i_ino; - if (dentry->d_name.len > DNAME_INLINE_LEN) { - node->fcd_name.name = kmalloc(dentry->d_name.len, GFP_NOFS); - if (!node->fcd_name.name) { - kmem_cache_free(ext4_fc_dentry_cachep, node); - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_NOMEM, handle); - mutex_lock(&ei->i_fc_lock); - return -ENOMEM; - } - memcpy((u8 *)node->fcd_name.name, dentry->d_name.name, - dentry->d_name.len); - } else { - memcpy(node->fcd_iname, dentry->d_name.name, - dentry->d_name.len); - node->fcd_name.name = node->fcd_iname; - } - node->fcd_name.len = dentry->d_name.len; + take_dentry_name_snapshot(&node->fcd_name, dentry); INIT_LIST_HEAD(&node->fcd_dilist); spin_lock(&sbi->s_fc_lock); if (sbi->s_journal->j_flags & JBD2_FULL_COMMIT_ONGOING || @@ -832,7 +815,7 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, { struct ext4_fc_dentry_info fcd; struct ext4_fc_tl tl; - int dlen = fc_dentry->fcd_name.len; + int dlen = fc_dentry->fcd_name.name.len; u8 *dst = ext4_fc_reserve_space(sb, EXT4_FC_TAG_BASE_LEN + sizeof(fcd) + dlen, crc); @@ -847,7 +830,7 @@ static bool ext4_fc_add_dentry_tlv(struct super_block *sb, u32 *crc, dst += EXT4_FC_TAG_BASE_LEN; memcpy(dst, &fcd, sizeof(fcd)); dst += sizeof(fcd); - memcpy(dst, fc_dentry->fcd_name.name, dlen); + memcpy(dst, fc_dentry->fcd_name.name.name, dlen); return true; } @@ -1328,9 +1311,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) list_del_init(&fc_dentry->fcd_dilist); spin_unlock(&sbi->s_fc_lock); - if (fc_dentry->fcd_name.name && - fc_dentry->fcd_name.len > DNAME_INLINE_LEN) - kfree(fc_dentry->fcd_name.name); + release_dentry_name_snapshot(&fc_dentry->fcd_name); kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry); spin_lock(&sbi->s_fc_lock); } diff --git a/fs/ext4/fast_commit.h b/fs/ext4/fast_commit.h index 2fadb2c4780c..3bd534e4dbbf 100644 --- a/fs/ext4/fast_commit.h +++ b/fs/ext4/fast_commit.h @@ -109,8 +109,7 @@ struct ext4_fc_dentry_update { int fcd_op; /* Type of update create / unlink / link */ int fcd_parent; /* Parent inode number */ int fcd_ino; /* Inode number */ - struct qstr fcd_name; /* Dirent name */ - unsigned char fcd_iname[DNAME_INLINE_LEN]; /* Dirent name string */ + struct name_snapshot fcd_name; /* Dirent name */ struct list_head fcd_list; struct list_head fcd_dilist; }; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 15bf32c21ac0..926c26e90ef8 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -43,17 +43,13 @@ static inline void vfat_d_version_set(struct dentry *dentry, * If it happened, the negative dentry isn't actually negative * anymore. So, drop it. */ -static int vfat_revalidate_shortname(struct dentry *dentry) +static bool vfat_revalidate_shortname(struct dentry *dentry, struct inode *dir) { - int ret = 1; - spin_lock(&dentry->d_lock); - if (!inode_eq_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry))) - ret = 0; - spin_unlock(&dentry->d_lock); - return ret; + return inode_eq_iversion(dir, vfat_d_version(dentry)); } -static int vfat_revalidate(struct dentry *dentry, unsigned int flags) +static int vfat_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; @@ -61,10 +57,11 @@ static int vfat_revalidate(struct dentry *dentry, unsigned int flags) /* This is not negative dentry. Always valid. */ if (d_really_is_positive(dentry)) return 1; - return vfat_revalidate_shortname(dentry); + return vfat_revalidate_shortname(dentry, dir); } -static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) +static int vfat_revalidate_ci(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; @@ -97,7 +94,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; - return vfat_revalidate_shortname(dentry); + return vfat_revalidate_shortname(dentry, dir); } /* returns the length of a struct qstr, ignoring trailing dots */ diff --git a/fs/file_table.c b/fs/file_table.c index a32171d2b83f..5c00dc38558d 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -106,7 +106,7 @@ static int proc_nr_files(const struct ctl_table *table, int write, void *buffer, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_stat_sysctls[] = { +static const struct ctl_table fs_stat_sysctls[] = { { .procname = "file-nr", .data = &files_stat, @@ -194,6 +194,11 @@ static int init_file(struct file *f, int flags, const struct cred *cred) * refcount bumps we should reinitialize the reused file first. */ file_ref_init(&f->f_ref, 1); + /* + * Disable permission and pre-content events for all files by default. + * They may be enabled later by file_set_fsnotify_mode_from_watchers(). + */ + file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM); return 0; } @@ -351,9 +356,7 @@ static struct file *alloc_file(const struct path *path, int flags, static inline int alloc_path_pseudo(const char *name, struct inode *inode, struct vfsmount *mnt, struct path *path) { - struct qstr this = QSTR_INIT(name, strlen(name)); - - path->dentry = d_alloc_pseudo(mnt->mnt_sb, &this); + path->dentry = d_alloc_pseudo(mnt->mnt_sb, &QSTR(name)); if (!path->dentry) return -ENOMEM; path->mnt = mntget(mnt); @@ -377,7 +380,13 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt, if (IS_ERR(file)) { ihold(inode); path_put(&path); + return file; } + /* + * Disable all fsnotify events for pseudo files by default. + * They may be enabled by caller with file_set_fsnotify_mode(). + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL(alloc_file_pseudo); @@ -402,6 +411,11 @@ struct file *alloc_file_pseudo_noaccount(struct inode *inode, return file; } file_init_path(file, &path, fops); + /* + * Disable all fsnotify events for pseudo files by default. + * They may be enabled by caller with file_set_fsnotify_mode(). + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY); return file; } EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount); diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig index 8674dbfbe59d..ca215a3cba3e 100644 --- a/fs/fuse/Kconfig +++ b/fs/fuse/Kconfig @@ -63,3 +63,15 @@ config FUSE_PASSTHROUGH to be performed directly on a backing file. If you want to allow passthrough operations, answer Y. + +config FUSE_IO_URING + bool "FUSE communication over io-uring" + default y + depends on FUSE_FS + depends on IO_URING + help + This allows sending FUSE requests over the io-uring interface and + also adds request core affinity. + + If you want to allow fuse server/client communication through io-uring, + answer Y diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile index 2c372180d631..3f0f312a31c1 100644 --- a/fs/fuse/Makefile +++ b/fs/fuse/Makefile @@ -15,5 +15,6 @@ fuse-y += iomode.o fuse-$(CONFIG_FUSE_DAX) += dax.o fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o fuse-$(CONFIG_SYSCTL) += sysctl.o +fuse-$(CONFIG_FUSE_IO_URING) += dev_uring.o virtiofs-y := virtio_fs.o diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index 9abbc2f2894f..0b6ee6dd1fd6 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -240,11 +240,12 @@ static int fuse_send_removemapping(struct inode *inode, args.opcode = FUSE_REMOVEMAPPING; args.nodeid = fi->nodeid; - args.in_numargs = 2; - args.in_args[0].size = sizeof(*inargp); - args.in_args[0].value = inargp; - args.in_args[1].size = inargp->count * sizeof(*remove_one); - args.in_args[1].value = remove_one; + args.in_numargs = 3; + fuse_set_zero_arg0(&args); + args.in_args[1].size = sizeof(*inargp); + args.in_args[1].value = inargp; + args.in_args[2].size = inargp->count * sizeof(*remove_one); + args.in_args[2].value = remove_one; return fuse_simple_request(fm, &args); } diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 27ccae63495d..5b5f789b37eb 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -6,7 +6,9 @@ See the file COPYING. */ +#include "dev_uring_i.h" #include "fuse_i.h" +#include "fuse_dev_i.h" #include <linux/init.h> #include <linux/module.h> @@ -28,23 +30,8 @@ MODULE_ALIAS_MISCDEV(FUSE_MINOR); MODULE_ALIAS("devname:fuse"); -/* Ordinary requests have even IDs, while interrupts IDs are odd */ -#define FUSE_INT_REQ_BIT (1ULL << 0) -#define FUSE_REQ_ID_STEP (1ULL << 1) - static struct kmem_cache *fuse_req_cachep; -static void end_requests(struct list_head *head); - -static struct fuse_dev *fuse_get_dev(struct file *file) -{ - /* - * Lockless access is OK, because file->private data is set - * once during mount and is valid until the file is released. - */ - return READ_ONCE(file->private_data); -} - static void fuse_request_init(struct fuse_mount *fm, struct fuse_req *req) { INIT_LIST_HEAD(&req->list); @@ -89,7 +76,8 @@ void fuse_set_initialized(struct fuse_conn *fc) static bool fuse_block_alloc(struct fuse_conn *fc, bool for_background) { - return !fc->initialized || (for_background && fc->blocked); + return !fc->initialized || (for_background && fc->blocked) || + (fc->io_uring && !fuse_uring_ready(fc)); } static void fuse_drop_waiting(struct fuse_conn *fc) @@ -234,7 +222,7 @@ u64 fuse_get_unique(struct fuse_iqueue *fiq) } EXPORT_SYMBOL_GPL(fuse_get_unique); -static unsigned int fuse_req_hash(u64 unique) +unsigned int fuse_req_hash(u64 unique) { return hash_long(unique & ~FUSE_INT_REQ_BIT, FUSE_PQ_HASH_BITS); } @@ -250,7 +238,8 @@ __releases(fiq->lock) spin_unlock(&fiq->lock); } -static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_link *forget) +void fuse_dev_queue_forget(struct fuse_iqueue *fiq, + struct fuse_forget_link *forget) { spin_lock(&fiq->lock); if (fiq->connected) { @@ -263,7 +252,7 @@ static void fuse_dev_queue_forget(struct fuse_iqueue *fiq, struct fuse_forget_li } } -static void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) +void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { spin_lock(&fiq->lock); if (list_empty(&req->intr_entry)) { @@ -580,7 +569,25 @@ ssize_t __fuse_simple_request(struct mnt_idmap *idmap, return ret; } -static bool fuse_request_queue_background(struct fuse_req *req) +#ifdef CONFIG_FUSE_IO_URING +static bool fuse_request_queue_background_uring(struct fuse_conn *fc, + struct fuse_req *req) +{ + struct fuse_iqueue *fiq = &fc->iq; + + req->in.h.unique = fuse_get_unique(fiq); + req->in.h.len = sizeof(struct fuse_in_header) + + fuse_len_args(req->args->in_numargs, + (struct fuse_arg *) req->args->in_args); + + return fuse_uring_queue_bq_req(req); +} +#endif + +/* + * @return true if queued + */ +static int fuse_request_queue_background(struct fuse_req *req) { struct fuse_mount *fm = req->fm; struct fuse_conn *fc = fm->fc; @@ -592,6 +599,12 @@ static bool fuse_request_queue_background(struct fuse_req *req) atomic_inc(&fc->num_waiting); } __set_bit(FR_ISREPLY, &req->flags); + +#ifdef CONFIG_FUSE_IO_URING + if (fuse_uring_ready(fc)) + return fuse_request_queue_background_uring(fc, req); +#endif + spin_lock(&fc->bg_lock); if (likely(fc->connected)) { fc->num_background++; @@ -692,22 +705,8 @@ static int unlock_request(struct fuse_req *req) return err; } -struct fuse_copy_state { - int write; - struct fuse_req *req; - struct iov_iter *iter; - struct pipe_buffer *pipebufs; - struct pipe_buffer *currbuf; - struct pipe_inode_info *pipe; - unsigned long nr_segs; - struct page *pg; - unsigned len; - unsigned offset; - unsigned move_pages:1; -}; - -static void fuse_copy_init(struct fuse_copy_state *cs, int write, - struct iov_iter *iter) +void fuse_copy_init(struct fuse_copy_state *cs, int write, + struct iov_iter *iter) { memset(cs, 0, sizeof(*cs)); cs->write = write; @@ -814,6 +813,9 @@ static int fuse_copy_do(struct fuse_copy_state *cs, void **val, unsigned *size) *size -= ncpy; cs->len -= ncpy; cs->offset += ncpy; + if (cs->is_uring) + cs->ring.copied_sz += ncpy; + return ncpy; } @@ -1068,9 +1070,9 @@ static int fuse_copy_one(struct fuse_copy_state *cs, void *val, unsigned size) } /* Copy request arguments to/from userspace buffer */ -static int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs, - unsigned argpages, struct fuse_arg *args, - int zeroing) +int fuse_copy_args(struct fuse_copy_state *cs, unsigned numargs, + unsigned argpages, struct fuse_arg *args, + int zeroing) { int err = 0; unsigned i; @@ -1760,7 +1762,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, args = &ap->args; args->nodeid = outarg->nodeid; args->opcode = FUSE_NOTIFY_REPLY; - args->in_numargs = 2; + args->in_numargs = 3; args->in_pages = true; args->end = fuse_retrieve_end; @@ -1788,9 +1790,10 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, } ra->inarg.offset = outarg->offset; ra->inarg.size = total_len; - args->in_args[0].size = sizeof(ra->inarg); - args->in_args[0].value = &ra->inarg; - args->in_args[1].size = total_len; + fuse_set_zero_arg0(args); + args->in_args[1].size = sizeof(ra->inarg); + args->in_args[1].value = &ra->inarg; + args->in_args[2].size = total_len; err = fuse_simple_notify_reply(fm, args, outarg->notify_unique); if (err) @@ -1885,7 +1888,7 @@ static void fuse_resend(struct fuse_conn *fc) spin_unlock(&fiq->lock); list_for_each_entry(req, &to_queue, list) clear_bit(FR_PENDING, &req->flags); - end_requests(&to_queue); + fuse_dev_end_requests(&to_queue); return; } /* iq and pq requests are both oldest to newest */ @@ -1934,7 +1937,7 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code, } /* Look up request on processing list by unique ID */ -static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique) +struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique) { unsigned int hash = fuse_req_hash(unique); struct fuse_req *req; @@ -1946,10 +1949,17 @@ static struct fuse_req *request_find(struct fuse_pqueue *fpq, u64 unique) return NULL; } -static int copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, - unsigned nbytes) +int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, + unsigned nbytes) { - unsigned reqsize = sizeof(struct fuse_out_header); + + unsigned int reqsize = 0; + + /* + * Uring has all headers separated from args - args is payload only + */ + if (!cs->is_uring) + reqsize = sizeof(struct fuse_out_header); reqsize += fuse_len_args(args->out_numargs, args->out_args); @@ -2011,7 +2021,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, spin_lock(&fpq->lock); req = NULL; if (fpq->connected) - req = request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT); + req = fuse_request_find(fpq, oh.unique & ~FUSE_INT_REQ_BIT); err = -ENOENT; if (!req) { @@ -2049,7 +2059,7 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud, if (oh.error) err = nbytes != sizeof(oh) ? -EINVAL : 0; else - err = copy_out_args(cs, req->args, nbytes); + err = fuse_copy_out_args(cs, req->args, nbytes); fuse_copy_finish(cs); spin_lock(&fpq->lock); @@ -2204,7 +2214,7 @@ static __poll_t fuse_dev_poll(struct file *file, poll_table *wait) } /* Abort all requests on the given list (pending or processing) */ -static void end_requests(struct list_head *head) +void fuse_dev_end_requests(struct list_head *head) { while (!list_empty(head)) { struct fuse_req *req; @@ -2307,7 +2317,13 @@ void fuse_abort_conn(struct fuse_conn *fc) wake_up_all(&fc->blocked_waitq); spin_unlock(&fc->lock); - end_requests(&to_end); + fuse_dev_end_requests(&to_end); + + /* + * fc->lock must not be taken to avoid conflicts with io-uring + * locks + */ + fuse_uring_abort(fc); } else { spin_unlock(&fc->lock); } @@ -2319,6 +2335,8 @@ void fuse_wait_aborted(struct fuse_conn *fc) /* matches implicit memory barrier in fuse_drop_waiting() */ smp_mb(); wait_event(fc->blocked_waitq, atomic_read(&fc->num_waiting) == 0); + + fuse_uring_wait_stopped_queues(fc); } int fuse_dev_release(struct inode *inode, struct file *file) @@ -2337,7 +2355,7 @@ int fuse_dev_release(struct inode *inode, struct file *file) list_splice_init(&fpq->processing[i], &to_end); spin_unlock(&fpq->lock); - end_requests(&to_end); + fuse_dev_end_requests(&to_end); /* Are we the last open device? */ if (atomic_dec_and_test(&fc->dev_count)) { @@ -2475,6 +2493,9 @@ const struct file_operations fuse_dev_operations = { .fasync = fuse_dev_fasync, .unlocked_ioctl = fuse_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, +#ifdef CONFIG_FUSE_IO_URING + .uring_cmd = fuse_uring_cmd, +#endif }; EXPORT_SYMBOL_GPL(fuse_dev_operations); diff --git a/fs/fuse/dev_uring.c b/fs/fuse/dev_uring.c new file mode 100644 index 000000000000..ebd2931b4f2a --- /dev/null +++ b/fs/fuse/dev_uring.c @@ -0,0 +1,1319 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * FUSE: Filesystem in Userspace + * Copyright (c) 2023-2024 DataDirect Networks. + */ + +#include "fuse_i.h" +#include "dev_uring_i.h" +#include "fuse_dev_i.h" + +#include <linux/fs.h> +#include <linux/io_uring/cmd.h> + +static bool __read_mostly enable_uring; +module_param(enable_uring, bool, 0644); +MODULE_PARM_DESC(enable_uring, + "Enable userspace communication through io-uring"); + +#define FUSE_URING_IOV_SEGS 2 /* header and payload */ + + +bool fuse_uring_enabled(void) +{ + return enable_uring; +} + +struct fuse_uring_pdu { + struct fuse_ring_ent *ent; +}; + +static const struct fuse_iqueue_ops fuse_io_uring_ops; + +static void uring_cmd_set_ring_ent(struct io_uring_cmd *cmd, + struct fuse_ring_ent *ring_ent) +{ + struct fuse_uring_pdu *pdu = + io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu); + + pdu->ent = ring_ent; +} + +static struct fuse_ring_ent *uring_cmd_to_ring_ent(struct io_uring_cmd *cmd) +{ + struct fuse_uring_pdu *pdu = + io_uring_cmd_to_pdu(cmd, struct fuse_uring_pdu); + + return pdu->ent; +} + +static void fuse_uring_flush_bg(struct fuse_ring_queue *queue) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + + lockdep_assert_held(&queue->lock); + lockdep_assert_held(&fc->bg_lock); + + /* + * Allow one bg request per queue, ignoring global fc limits. + * This prevents a single queue from consuming all resources and + * eliminates the need for remote queue wake-ups when global + * limits are met but this queue has no more waiting requests. + */ + while ((fc->active_background < fc->max_background || + !queue->active_background) && + (!list_empty(&queue->fuse_req_bg_queue))) { + struct fuse_req *req; + + req = list_first_entry(&queue->fuse_req_bg_queue, + struct fuse_req, list); + fc->active_background++; + queue->active_background++; + + list_move_tail(&req->list, &queue->fuse_req_queue); + } +} + +static void fuse_uring_req_end(struct fuse_ring_ent *ent, struct fuse_req *req, + int error) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + + lockdep_assert_not_held(&queue->lock); + spin_lock(&queue->lock); + ent->fuse_req = NULL; + if (test_bit(FR_BACKGROUND, &req->flags)) { + queue->active_background--; + spin_lock(&fc->bg_lock); + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + } + + spin_unlock(&queue->lock); + + if (error) + req->out.h.error = error; + + clear_bit(FR_SENT, &req->flags); + fuse_request_end(req); +} + +/* Abort all list queued request on the given ring queue */ +static void fuse_uring_abort_end_queue_requests(struct fuse_ring_queue *queue) +{ + struct fuse_req *req; + LIST_HEAD(req_list); + + spin_lock(&queue->lock); + list_for_each_entry(req, &queue->fuse_req_queue, list) + clear_bit(FR_PENDING, &req->flags); + list_splice_init(&queue->fuse_req_queue, &req_list); + spin_unlock(&queue->lock); + + /* must not hold queue lock to avoid order issues with fi->lock */ + fuse_dev_end_requests(&req_list); +} + +void fuse_uring_abort_end_requests(struct fuse_ring *ring) +{ + int qid; + struct fuse_ring_queue *queue; + struct fuse_conn *fc = ring->fc; + + for (qid = 0; qid < ring->nr_queues; qid++) { + queue = READ_ONCE(ring->queues[qid]); + if (!queue) + continue; + + queue->stopped = true; + + WARN_ON_ONCE(ring->fc->max_background != UINT_MAX); + spin_lock(&queue->lock); + spin_lock(&fc->bg_lock); + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + spin_unlock(&queue->lock); + fuse_uring_abort_end_queue_requests(queue); + } +} + +void fuse_uring_destruct(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + int qid; + + if (!ring) + return; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = ring->queues[qid]; + struct fuse_ring_ent *ent, *next; + + if (!queue) + continue; + + WARN_ON(!list_empty(&queue->ent_avail_queue)); + WARN_ON(!list_empty(&queue->ent_w_req_queue)); + WARN_ON(!list_empty(&queue->ent_commit_queue)); + WARN_ON(!list_empty(&queue->ent_in_userspace)); + + list_for_each_entry_safe(ent, next, &queue->ent_released, + list) { + list_del_init(&ent->list); + kfree(ent); + } + + kfree(queue->fpq.processing); + kfree(queue); + ring->queues[qid] = NULL; + } + + kfree(ring->queues); + kfree(ring); + fc->ring = NULL; +} + +/* + * Basic ring setup for this connection based on the provided configuration + */ +static struct fuse_ring *fuse_uring_create(struct fuse_conn *fc) +{ + struct fuse_ring *ring; + size_t nr_queues = num_possible_cpus(); + struct fuse_ring *res = NULL; + size_t max_payload_size; + + ring = kzalloc(sizeof(*fc->ring), GFP_KERNEL_ACCOUNT); + if (!ring) + return NULL; + + ring->queues = kcalloc(nr_queues, sizeof(struct fuse_ring_queue *), + GFP_KERNEL_ACCOUNT); + if (!ring->queues) + goto out_err; + + max_payload_size = max(FUSE_MIN_READ_BUFFER, fc->max_write); + max_payload_size = max(max_payload_size, fc->max_pages * PAGE_SIZE); + + spin_lock(&fc->lock); + if (fc->ring) { + /* race, another thread created the ring in the meantime */ + spin_unlock(&fc->lock); + res = fc->ring; + goto out_err; + } + + init_waitqueue_head(&ring->stop_waitq); + + fc->ring = ring; + ring->nr_queues = nr_queues; + ring->fc = fc; + ring->max_payload_sz = max_payload_size; + atomic_set(&ring->queue_refs, 0); + + spin_unlock(&fc->lock); + return ring; + +out_err: + kfree(ring->queues); + kfree(ring); + return res; +} + +static struct fuse_ring_queue *fuse_uring_create_queue(struct fuse_ring *ring, + int qid) +{ + struct fuse_conn *fc = ring->fc; + struct fuse_ring_queue *queue; + struct list_head *pq; + + queue = kzalloc(sizeof(*queue), GFP_KERNEL_ACCOUNT); + if (!queue) + return NULL; + pq = kcalloc(FUSE_PQ_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); + if (!pq) { + kfree(queue); + return NULL; + } + + queue->qid = qid; + queue->ring = ring; + spin_lock_init(&queue->lock); + + INIT_LIST_HEAD(&queue->ent_avail_queue); + INIT_LIST_HEAD(&queue->ent_commit_queue); + INIT_LIST_HEAD(&queue->ent_w_req_queue); + INIT_LIST_HEAD(&queue->ent_in_userspace); + INIT_LIST_HEAD(&queue->fuse_req_queue); + INIT_LIST_HEAD(&queue->fuse_req_bg_queue); + INIT_LIST_HEAD(&queue->ent_released); + + queue->fpq.processing = pq; + fuse_pqueue_init(&queue->fpq); + + spin_lock(&fc->lock); + if (ring->queues[qid]) { + spin_unlock(&fc->lock); + kfree(queue->fpq.processing); + kfree(queue); + return ring->queues[qid]; + } + + /* + * write_once and lock as the caller mostly doesn't take the lock at all + */ + WRITE_ONCE(ring->queues[qid], queue); + spin_unlock(&fc->lock); + + return queue; +} + +static void fuse_uring_stop_fuse_req_end(struct fuse_req *req) +{ + clear_bit(FR_SENT, &req->flags); + req->out.h.error = -ECONNABORTED; + fuse_request_end(req); +} + +/* + * Release a request/entry on connection tear down + */ +static void fuse_uring_entry_teardown(struct fuse_ring_ent *ent) +{ + struct fuse_req *req; + struct io_uring_cmd *cmd; + + struct fuse_ring_queue *queue = ent->queue; + + spin_lock(&queue->lock); + cmd = ent->cmd; + ent->cmd = NULL; + req = ent->fuse_req; + ent->fuse_req = NULL; + if (req) { + /* remove entry from queue->fpq->processing */ + list_del_init(&req->list); + } + + /* + * The entry must not be freed immediately, due to access of direct + * pointer access of entries through IO_URING_F_CANCEL - there is a risk + * of race between daemon termination (which triggers IO_URING_F_CANCEL + * and accesses entries without checking the list state first + */ + list_move(&ent->list, &queue->ent_released); + ent->state = FRRS_RELEASED; + spin_unlock(&queue->lock); + + if (cmd) + io_uring_cmd_done(cmd, -ENOTCONN, 0, IO_URING_F_UNLOCKED); + + if (req) + fuse_uring_stop_fuse_req_end(req); +} + +static void fuse_uring_stop_list_entries(struct list_head *head, + struct fuse_ring_queue *queue, + enum fuse_ring_req_state exp_state) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_ring_ent *ent, *next; + ssize_t queue_refs = SSIZE_MAX; + LIST_HEAD(to_teardown); + + spin_lock(&queue->lock); + list_for_each_entry_safe(ent, next, head, list) { + if (ent->state != exp_state) { + pr_warn("entry teardown qid=%d state=%d expected=%d", + queue->qid, ent->state, exp_state); + continue; + } + + ent->state = FRRS_TEARDOWN; + list_move(&ent->list, &to_teardown); + } + spin_unlock(&queue->lock); + + /* no queue lock to avoid lock order issues */ + list_for_each_entry_safe(ent, next, &to_teardown, list) { + fuse_uring_entry_teardown(ent); + queue_refs = atomic_dec_return(&ring->queue_refs); + WARN_ON_ONCE(queue_refs < 0); + } +} + +static void fuse_uring_teardown_entries(struct fuse_ring_queue *queue) +{ + fuse_uring_stop_list_entries(&queue->ent_in_userspace, queue, + FRRS_USERSPACE); + fuse_uring_stop_list_entries(&queue->ent_avail_queue, queue, + FRRS_AVAILABLE); +} + +/* + * Log state debug info + */ +static void fuse_uring_log_ent_state(struct fuse_ring *ring) +{ + int qid; + struct fuse_ring_ent *ent; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = ring->queues[qid]; + + if (!queue) + continue; + + spin_lock(&queue->lock); + /* + * Log entries from the intermediate queue, the other queues + * should be empty + */ + list_for_each_entry(ent, &queue->ent_w_req_queue, list) { + pr_info(" ent-req-queue ring=%p qid=%d ent=%p state=%d\n", + ring, qid, ent, ent->state); + } + list_for_each_entry(ent, &queue->ent_commit_queue, list) { + pr_info(" ent-commit-queue ring=%p qid=%d ent=%p state=%d\n", + ring, qid, ent, ent->state); + } + spin_unlock(&queue->lock); + } + ring->stop_debug_log = 1; +} + +static void fuse_uring_async_stop_queues(struct work_struct *work) +{ + int qid; + struct fuse_ring *ring = + container_of(work, struct fuse_ring, async_teardown_work.work); + + /* XXX code dup */ + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]); + + if (!queue) + continue; + + fuse_uring_teardown_entries(queue); + } + + /* + * Some ring entries might be in the middle of IO operations, + * i.e. in process to get handled by file_operations::uring_cmd + * or on the way to userspace - we could handle that with conditions in + * run time code, but easier/cleaner to have an async tear down handler + * If there are still queue references left + */ + if (atomic_read(&ring->queue_refs) > 0) { + if (time_after(jiffies, + ring->teardown_time + FUSE_URING_TEARDOWN_TIMEOUT)) + fuse_uring_log_ent_state(ring); + + schedule_delayed_work(&ring->async_teardown_work, + FUSE_URING_TEARDOWN_INTERVAL); + } else { + wake_up_all(&ring->stop_waitq); + } +} + +/* + * Stop the ring queues + */ +void fuse_uring_stop_queues(struct fuse_ring *ring) +{ + int qid; + + for (qid = 0; qid < ring->nr_queues; qid++) { + struct fuse_ring_queue *queue = READ_ONCE(ring->queues[qid]); + + if (!queue) + continue; + + fuse_uring_teardown_entries(queue); + } + + if (atomic_read(&ring->queue_refs) > 0) { + ring->teardown_time = jiffies; + INIT_DELAYED_WORK(&ring->async_teardown_work, + fuse_uring_async_stop_queues); + schedule_delayed_work(&ring->async_teardown_work, + FUSE_URING_TEARDOWN_INTERVAL); + } else { + wake_up_all(&ring->stop_waitq); + } +} + +/* + * Handle IO_URING_F_CANCEL, typically should come on daemon termination. + * + * Releasing the last entry should trigger fuse_dev_release() if + * the daemon was terminated + */ +static void fuse_uring_cancel(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd); + struct fuse_ring_queue *queue; + bool need_cmd_done = false; + + /* + * direct access on ent - it must not be destructed as long as + * IO_URING_F_CANCEL might come up + */ + queue = ent->queue; + spin_lock(&queue->lock); + if (ent->state == FRRS_AVAILABLE) { + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + need_cmd_done = true; + ent->cmd = NULL; + } + spin_unlock(&queue->lock); + + if (need_cmd_done) { + /* no queue lock to avoid lock order issues */ + io_uring_cmd_done(cmd, -ENOTCONN, 0, issue_flags); + } +} + +static void fuse_uring_prepare_cancel(struct io_uring_cmd *cmd, int issue_flags, + struct fuse_ring_ent *ring_ent) +{ + uring_cmd_set_ring_ent(cmd, ring_ent); + io_uring_cmd_mark_cancelable(cmd, issue_flags); +} + +/* + * Checks for errors and stores it into the request + */ +static int fuse_uring_out_header_has_err(struct fuse_out_header *oh, + struct fuse_req *req, + struct fuse_conn *fc) +{ + int err; + + err = -EINVAL; + if (oh->unique == 0) { + /* Not supported through io-uring yet */ + pr_warn_once("notify through fuse-io-uring not supported\n"); + goto err; + } + + if (oh->error <= -ERESTARTSYS || oh->error > 0) + goto err; + + if (oh->error) { + err = oh->error; + goto err; + } + + err = -ENOENT; + if ((oh->unique & ~FUSE_INT_REQ_BIT) != req->in.h.unique) { + pr_warn_ratelimited("unique mismatch, expected: %llu got %llu\n", + req->in.h.unique, + oh->unique & ~FUSE_INT_REQ_BIT); + goto err; + } + + /* + * Is it an interrupt reply ID? + * XXX: Not supported through fuse-io-uring yet, it should not even + * find the request - should not happen. + */ + WARN_ON_ONCE(oh->unique & FUSE_INT_REQ_BIT); + + err = 0; +err: + return err; +} + +static int fuse_uring_copy_from_ring(struct fuse_ring *ring, + struct fuse_req *req, + struct fuse_ring_ent *ent) +{ + struct fuse_copy_state cs; + struct fuse_args *args = req->args; + struct iov_iter iter; + int err; + struct fuse_uring_ent_in_out ring_in_out; + + err = copy_from_user(&ring_in_out, &ent->headers->ring_ent_in_out, + sizeof(ring_in_out)); + if (err) + return -EFAULT; + + err = import_ubuf(ITER_SOURCE, ent->payload, ring->max_payload_sz, + &iter); + if (err) + return err; + + fuse_copy_init(&cs, 0, &iter); + cs.is_uring = 1; + cs.req = req; + + return fuse_copy_out_args(&cs, args, ring_in_out.payload_sz); +} + + /* + * Copy data from the req to the ring buffer + */ +static int fuse_uring_args_to_ring(struct fuse_ring *ring, struct fuse_req *req, + struct fuse_ring_ent *ent) +{ + struct fuse_copy_state cs; + struct fuse_args *args = req->args; + struct fuse_in_arg *in_args = args->in_args; + int num_args = args->in_numargs; + int err; + struct iov_iter iter; + struct fuse_uring_ent_in_out ent_in_out = { + .flags = 0, + .commit_id = req->in.h.unique, + }; + + err = import_ubuf(ITER_DEST, ent->payload, ring->max_payload_sz, &iter); + if (err) { + pr_info_ratelimited("fuse: Import of user buffer failed\n"); + return err; + } + + fuse_copy_init(&cs, 1, &iter); + cs.is_uring = 1; + cs.req = req; + + if (num_args > 0) { + /* + * Expectation is that the first argument is the per op header. + * Some op code have that as zero size. + */ + if (args->in_args[0].size > 0) { + err = copy_to_user(&ent->headers->op_in, in_args->value, + in_args->size); + if (err) { + pr_info_ratelimited( + "Copying the header failed.\n"); + return -EFAULT; + } + } + in_args++; + num_args--; + } + + /* copy the payload */ + err = fuse_copy_args(&cs, num_args, args->in_pages, + (struct fuse_arg *)in_args, 0); + if (err) { + pr_info_ratelimited("%s fuse_copy_args failed\n", __func__); + return err; + } + + ent_in_out.payload_sz = cs.ring.copied_sz; + err = copy_to_user(&ent->headers->ring_ent_in_out, &ent_in_out, + sizeof(ent_in_out)); + return err ? -EFAULT : 0; +} + +static int fuse_uring_copy_to_ring(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + int err; + + err = -EIO; + if (WARN_ON(ent->state != FRRS_FUSE_REQ)) { + pr_err("qid=%d ring-req=%p invalid state %d on send\n", + queue->qid, ent, ent->state); + return err; + } + + err = -EINVAL; + if (WARN_ON(req->in.h.unique == 0)) + return err; + + /* copy the request */ + err = fuse_uring_args_to_ring(ring, req, ent); + if (unlikely(err)) { + pr_info_ratelimited("Copy to ring failed: %d\n", err); + return err; + } + + /* copy fuse_in_header */ + err = copy_to_user(&ent->headers->in_out, &req->in.h, + sizeof(req->in.h)); + if (err) { + err = -EFAULT; + return err; + } + + return 0; +} + +static int fuse_uring_prepare_send(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + int err; + + err = fuse_uring_copy_to_ring(ent, req); + if (!err) + set_bit(FR_SENT, &req->flags); + else + fuse_uring_req_end(ent, req, err); + + return err; +} + +/* + * Write data to the ring buffer and send the request to userspace, + * userspace will read it + * This is comparable with classical read(/dev/fuse) + */ +static int fuse_uring_send_next_to_ring(struct fuse_ring_ent *ent, + struct fuse_req *req, + unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + int err; + struct io_uring_cmd *cmd; + + err = fuse_uring_prepare_send(ent, req); + if (err) + return err; + + spin_lock(&queue->lock); + cmd = ent->cmd; + ent->cmd = NULL; + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + spin_unlock(&queue->lock); + + io_uring_cmd_done(cmd, 0, 0, issue_flags); + return 0; +} + +/* + * Make a ring entry available for fuse_req assignment + */ +static void fuse_uring_ent_avail(struct fuse_ring_ent *ent, + struct fuse_ring_queue *queue) +{ + WARN_ON_ONCE(!ent->cmd); + list_move(&ent->list, &queue->ent_avail_queue); + ent->state = FRRS_AVAILABLE; +} + +/* Used to find the request on SQE commit */ +static void fuse_uring_add_to_pq(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_pqueue *fpq = &queue->fpq; + unsigned int hash; + + req->ring_entry = ent; + hash = fuse_req_hash(req->in.h.unique); + list_move_tail(&req->list, &fpq->processing[hash]); +} + +/* + * Assign a fuse queue entry to the given entry + */ +static void fuse_uring_add_req_to_ring_ent(struct fuse_ring_ent *ent, + struct fuse_req *req) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_conn *fc = req->fm->fc; + struct fuse_iqueue *fiq = &fc->iq; + + lockdep_assert_held(&queue->lock); + + if (WARN_ON_ONCE(ent->state != FRRS_AVAILABLE && + ent->state != FRRS_COMMIT)) { + pr_warn("%s qid=%d state=%d\n", __func__, ent->queue->qid, + ent->state); + } + + spin_lock(&fiq->lock); + clear_bit(FR_PENDING, &req->flags); + spin_unlock(&fiq->lock); + ent->fuse_req = req; + ent->state = FRRS_FUSE_REQ; + list_move(&ent->list, &queue->ent_w_req_queue); + fuse_uring_add_to_pq(ent, req); +} + +/* Fetch the next fuse request if available */ +static struct fuse_req *fuse_uring_ent_assign_req(struct fuse_ring_ent *ent) + __must_hold(&queue->lock) +{ + struct fuse_req *req; + struct fuse_ring_queue *queue = ent->queue; + struct list_head *req_queue = &queue->fuse_req_queue; + + lockdep_assert_held(&queue->lock); + + /* get and assign the next entry while it is still holding the lock */ + req = list_first_entry_or_null(req_queue, struct fuse_req, list); + if (req) + fuse_uring_add_req_to_ring_ent(ent, req); + + return req; +} + +/* + * Read data from the ring buffer, which user space has written to + * This is comparible with handling of classical write(/dev/fuse). + * Also make the ring request available again for new fuse requests. + */ +static void fuse_uring_commit(struct fuse_ring_ent *ent, struct fuse_req *req, + unsigned int issue_flags) +{ + struct fuse_ring *ring = ent->queue->ring; + struct fuse_conn *fc = ring->fc; + ssize_t err = 0; + + err = copy_from_user(&req->out.h, &ent->headers->in_out, + sizeof(req->out.h)); + if (err) { + req->out.h.error = -EFAULT; + goto out; + } + + err = fuse_uring_out_header_has_err(&req->out.h, req, fc); + if (err) { + /* req->out.h.error already set */ + goto out; + } + + err = fuse_uring_copy_from_ring(ring, req, ent); +out: + fuse_uring_req_end(ent, req, err); +} + +/* + * Get the next fuse req and send it + */ +static void fuse_uring_next_fuse_req(struct fuse_ring_ent *ent, + struct fuse_ring_queue *queue, + unsigned int issue_flags) +{ + int err; + struct fuse_req *req; + +retry: + spin_lock(&queue->lock); + fuse_uring_ent_avail(ent, queue); + req = fuse_uring_ent_assign_req(ent); + spin_unlock(&queue->lock); + + if (req) { + err = fuse_uring_send_next_to_ring(ent, req, issue_flags); + if (err) + goto retry; + } +} + +static int fuse_ring_ent_set_commit(struct fuse_ring_ent *ent) +{ + struct fuse_ring_queue *queue = ent->queue; + + lockdep_assert_held(&queue->lock); + + if (WARN_ON_ONCE(ent->state != FRRS_USERSPACE)) + return -EIO; + + ent->state = FRRS_COMMIT; + list_move(&ent->list, &queue->ent_commit_queue); + + return 0; +} + +/* FUSE_URING_CMD_COMMIT_AND_FETCH handler */ +static int fuse_uring_commit_fetch(struct io_uring_cmd *cmd, int issue_flags, + struct fuse_conn *fc) +{ + const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe); + struct fuse_ring_ent *ent; + int err; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + uint64_t commit_id = READ_ONCE(cmd_req->commit_id); + unsigned int qid = READ_ONCE(cmd_req->qid); + struct fuse_pqueue *fpq; + struct fuse_req *req; + + err = -ENOTCONN; + if (!ring) + return err; + + if (qid >= ring->nr_queues) + return -EINVAL; + + queue = ring->queues[qid]; + if (!queue) + return err; + fpq = &queue->fpq; + + if (!READ_ONCE(fc->connected) || READ_ONCE(queue->stopped)) + return err; + + spin_lock(&queue->lock); + /* Find a request based on the unique ID of the fuse request + * This should get revised, as it needs a hash calculation and list + * search. And full struct fuse_pqueue is needed (memory overhead). + * As well as the link from req to ring_ent. + */ + req = fuse_request_find(fpq, commit_id); + err = -ENOENT; + if (!req) { + pr_info("qid=%d commit_id %llu not found\n", queue->qid, + commit_id); + spin_unlock(&queue->lock); + return err; + } + list_del_init(&req->list); + ent = req->ring_entry; + req->ring_entry = NULL; + + err = fuse_ring_ent_set_commit(ent); + if (err != 0) { + pr_info_ratelimited("qid=%d commit_id %llu state %d", + queue->qid, commit_id, ent->state); + spin_unlock(&queue->lock); + req->out.h.error = err; + clear_bit(FR_SENT, &req->flags); + fuse_request_end(req); + return err; + } + + ent->cmd = cmd; + spin_unlock(&queue->lock); + + /* without the queue lock, as other locks are taken */ + fuse_uring_prepare_cancel(cmd, issue_flags, ent); + fuse_uring_commit(ent, req, issue_flags); + + /* + * Fetching the next request is absolutely required as queued + * fuse requests would otherwise not get processed - committing + * and fetching is done in one step vs legacy fuse, which has separated + * read (fetch request) and write (commit result). + */ + fuse_uring_next_fuse_req(ent, queue, issue_flags); + return 0; +} + +static bool is_ring_ready(struct fuse_ring *ring, int current_qid) +{ + int qid; + struct fuse_ring_queue *queue; + bool ready = true; + + for (qid = 0; qid < ring->nr_queues && ready; qid++) { + if (current_qid == qid) + continue; + + queue = ring->queues[qid]; + if (!queue) { + ready = false; + break; + } + + spin_lock(&queue->lock); + if (list_empty(&queue->ent_avail_queue)) + ready = false; + spin_unlock(&queue->lock); + } + + return ready; +} + +/* + * fuse_uring_req_fetch command handling + */ +static void fuse_uring_do_register(struct fuse_ring_ent *ent, + struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + struct fuse_ring *ring = queue->ring; + struct fuse_conn *fc = ring->fc; + struct fuse_iqueue *fiq = &fc->iq; + + fuse_uring_prepare_cancel(cmd, issue_flags, ent); + + spin_lock(&queue->lock); + ent->cmd = cmd; + fuse_uring_ent_avail(ent, queue); + spin_unlock(&queue->lock); + + if (!ring->ready) { + bool ready = is_ring_ready(ring, queue->qid); + + if (ready) { + WRITE_ONCE(fiq->ops, &fuse_io_uring_ops); + WRITE_ONCE(ring->ready, true); + wake_up_all(&fc->blocked_waitq); + } + } +} + +/* + * sqe->addr is a ptr to an iovec array, iov[0] has the headers, iov[1] + * the payload + */ +static int fuse_uring_get_iovec_from_sqe(const struct io_uring_sqe *sqe, + struct iovec iov[FUSE_URING_IOV_SEGS]) +{ + struct iovec __user *uiov = u64_to_user_ptr(READ_ONCE(sqe->addr)); + struct iov_iter iter; + ssize_t ret; + + if (sqe->len != FUSE_URING_IOV_SEGS) + return -EINVAL; + + /* + * Direction for buffer access will actually be READ and WRITE, + * using write for the import should include READ access as well. + */ + ret = import_iovec(WRITE, uiov, FUSE_URING_IOV_SEGS, + FUSE_URING_IOV_SEGS, &iov, &iter); + if (ret < 0) + return ret; + + return 0; +} + +static struct fuse_ring_ent * +fuse_uring_create_ring_ent(struct io_uring_cmd *cmd, + struct fuse_ring_queue *queue) +{ + struct fuse_ring *ring = queue->ring; + struct fuse_ring_ent *ent; + size_t payload_size; + struct iovec iov[FUSE_URING_IOV_SEGS]; + int err; + + err = fuse_uring_get_iovec_from_sqe(cmd->sqe, iov); + if (err) { + pr_info_ratelimited("Failed to get iovec from sqe, err=%d\n", + err); + return ERR_PTR(err); + } + + err = -EINVAL; + if (iov[0].iov_len < sizeof(struct fuse_uring_req_header)) { + pr_info_ratelimited("Invalid header len %zu\n", iov[0].iov_len); + return ERR_PTR(err); + } + + payload_size = iov[1].iov_len; + if (payload_size < ring->max_payload_sz) { + pr_info_ratelimited("Invalid req payload len %zu\n", + payload_size); + return ERR_PTR(err); + } + + err = -ENOMEM; + ent = kzalloc(sizeof(*ent), GFP_KERNEL_ACCOUNT); + if (!ent) + return ERR_PTR(err); + + INIT_LIST_HEAD(&ent->list); + + ent->queue = queue; + ent->headers = iov[0].iov_base; + ent->payload = iov[1].iov_base; + + atomic_inc(&ring->queue_refs); + return ent; +} + +/* + * Register header and payload buffer with the kernel and puts the + * entry as "ready to get fuse requests" on the queue + */ +static int fuse_uring_register(struct io_uring_cmd *cmd, + unsigned int issue_flags, struct fuse_conn *fc) +{ + const struct fuse_uring_cmd_req *cmd_req = io_uring_sqe_cmd(cmd->sqe); + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent; + int err; + unsigned int qid = READ_ONCE(cmd_req->qid); + + err = -ENOMEM; + if (!ring) { + ring = fuse_uring_create(fc); + if (!ring) + return err; + } + + if (qid >= ring->nr_queues) { + pr_info_ratelimited("fuse: Invalid ring qid %u\n", qid); + return -EINVAL; + } + + queue = ring->queues[qid]; + if (!queue) { + queue = fuse_uring_create_queue(ring, qid); + if (!queue) + return err; + } + + /* + * The created queue above does not need to be destructed in + * case of entry errors below, will be done at ring destruction time. + */ + + ent = fuse_uring_create_ring_ent(cmd, queue); + if (IS_ERR(ent)) + return PTR_ERR(ent); + + fuse_uring_do_register(ent, cmd, issue_flags); + + return 0; +} + +/* + * Entry function from io_uring to handle the given passthrough command + * (op code IORING_OP_URING_CMD) + */ +int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) +{ + struct fuse_dev *fud; + struct fuse_conn *fc; + u32 cmd_op = cmd->cmd_op; + int err; + + if ((unlikely(issue_flags & IO_URING_F_CANCEL))) { + fuse_uring_cancel(cmd, issue_flags); + return 0; + } + + /* This extra SQE size holds struct fuse_uring_cmd_req */ + if (!(issue_flags & IO_URING_F_SQE128)) + return -EINVAL; + + fud = fuse_get_dev(cmd->file); + if (!fud) { + pr_info_ratelimited("No fuse device found\n"); + return -ENOTCONN; + } + fc = fud->fc; + + /* Once a connection has io-uring enabled on it, it can't be disabled */ + if (!enable_uring && !fc->io_uring) { + pr_info_ratelimited("fuse-io-uring is disabled\n"); + return -EOPNOTSUPP; + } + + if (fc->aborted) + return -ECONNABORTED; + if (!fc->connected) + return -ENOTCONN; + + /* + * fuse_uring_register() needs the ring to be initialized, + * we need to know the max payload size + */ + if (!fc->initialized) + return -EAGAIN; + + switch (cmd_op) { + case FUSE_IO_URING_CMD_REGISTER: + err = fuse_uring_register(cmd, issue_flags, fc); + if (err) { + pr_info_once("FUSE_IO_URING_CMD_REGISTER failed err=%d\n", + err); + fc->io_uring = 0; + wake_up_all(&fc->blocked_waitq); + return err; + } + break; + case FUSE_IO_URING_CMD_COMMIT_AND_FETCH: + err = fuse_uring_commit_fetch(cmd, issue_flags, fc); + if (err) { + pr_info_once("FUSE_IO_URING_COMMIT_AND_FETCH failed err=%d\n", + err); + return err; + } + break; + default: + return -EINVAL; + } + + return -EIOCBQUEUED; +} + +static void fuse_uring_send(struct fuse_ring_ent *ent, struct io_uring_cmd *cmd, + ssize_t ret, unsigned int issue_flags) +{ + struct fuse_ring_queue *queue = ent->queue; + + spin_lock(&queue->lock); + ent->state = FRRS_USERSPACE; + list_move(&ent->list, &queue->ent_in_userspace); + ent->cmd = NULL; + spin_unlock(&queue->lock); + + io_uring_cmd_done(cmd, ret, 0, issue_flags); +} + +/* + * This prepares and sends the ring request in fuse-uring task context. + * User buffers are not mapped yet - the application does not have permission + * to write to it - this has to be executed in ring task context. + */ +static void fuse_uring_send_in_task(struct io_uring_cmd *cmd, + unsigned int issue_flags) +{ + struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd); + struct fuse_ring_queue *queue = ent->queue; + int err; + + if (!(issue_flags & IO_URING_F_TASK_DEAD)) { + err = fuse_uring_prepare_send(ent, ent->fuse_req); + if (err) { + fuse_uring_next_fuse_req(ent, queue, issue_flags); + return; + } + } else { + err = -ECANCELED; + } + + fuse_uring_send(ent, cmd, err, issue_flags); +} + +static struct fuse_ring_queue *fuse_uring_task_to_queue(struct fuse_ring *ring) +{ + unsigned int qid; + struct fuse_ring_queue *queue; + + qid = task_cpu(current); + + if (WARN_ONCE(qid >= ring->nr_queues, + "Core number (%u) exceeds nr queues (%zu)\n", qid, + ring->nr_queues)) + qid = 0; + + queue = ring->queues[qid]; + WARN_ONCE(!queue, "Missing queue for qid %d\n", qid); + + return queue; +} + +static void fuse_uring_dispatch_ent(struct fuse_ring_ent *ent) +{ + struct io_uring_cmd *cmd = ent->cmd; + + uring_cmd_set_ring_ent(cmd, ent); + io_uring_cmd_complete_in_task(cmd, fuse_uring_send_in_task); +} + +/* queue a fuse request and send it if a ring entry is available */ +void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req) +{ + struct fuse_conn *fc = req->fm->fc; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent = NULL; + int err; + + err = -EINVAL; + queue = fuse_uring_task_to_queue(ring); + if (!queue) + goto err; + + if (req->in.h.opcode != FUSE_NOTIFY_REPLY) + req->in.h.unique = fuse_get_unique(fiq); + + spin_lock(&queue->lock); + err = -ENOTCONN; + if (unlikely(queue->stopped)) + goto err_unlock; + + ent = list_first_entry_or_null(&queue->ent_avail_queue, + struct fuse_ring_ent, list); + if (ent) + fuse_uring_add_req_to_ring_ent(ent, req); + else + list_add_tail(&req->list, &queue->fuse_req_queue); + spin_unlock(&queue->lock); + + if (ent) + fuse_uring_dispatch_ent(ent); + + return; + +err_unlock: + spin_unlock(&queue->lock); +err: + req->out.h.error = err; + clear_bit(FR_PENDING, &req->flags); + fuse_request_end(req); +} + +bool fuse_uring_queue_bq_req(struct fuse_req *req) +{ + struct fuse_conn *fc = req->fm->fc; + struct fuse_ring *ring = fc->ring; + struct fuse_ring_queue *queue; + struct fuse_ring_ent *ent = NULL; + + queue = fuse_uring_task_to_queue(ring); + if (!queue) + return false; + + spin_lock(&queue->lock); + if (unlikely(queue->stopped)) { + spin_unlock(&queue->lock); + return false; + } + + list_add_tail(&req->list, &queue->fuse_req_bg_queue); + + ent = list_first_entry_or_null(&queue->ent_avail_queue, + struct fuse_ring_ent, list); + spin_lock(&fc->bg_lock); + fc->num_background++; + if (fc->num_background == fc->max_background) + fc->blocked = 1; + fuse_uring_flush_bg(queue); + spin_unlock(&fc->bg_lock); + + /* + * Due to bg_queue flush limits there might be other bg requests + * in the queue that need to be handled first. Or no further req + * might be available. + */ + req = list_first_entry_or_null(&queue->fuse_req_queue, struct fuse_req, + list); + if (ent && req) { + fuse_uring_add_req_to_ring_ent(ent, req); + spin_unlock(&queue->lock); + + fuse_uring_dispatch_ent(ent); + } else { + spin_unlock(&queue->lock); + } + + return true; +} + +static const struct fuse_iqueue_ops fuse_io_uring_ops = { + /* should be send over io-uring as enhancement */ + .send_forget = fuse_dev_queue_forget, + + /* + * could be send over io-uring, but interrupts should be rare, + * no need to make the code complex + */ + .send_interrupt = fuse_dev_queue_interrupt, + .send_req = fuse_uring_queue_fuse_req, +}; diff --git a/fs/fuse/dev_uring_i.h b/fs/fuse/dev_uring_i.h new file mode 100644 index 000000000000..2102b3d0c1ae --- /dev/null +++ b/fs/fuse/dev_uring_i.h @@ -0,0 +1,205 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * FUSE: Filesystem in Userspace + * Copyright (c) 2023-2024 DataDirect Networks. + */ + +#ifndef _FS_FUSE_DEV_URING_I_H +#define _FS_FUSE_DEV_URING_I_H + +#include "fuse_i.h" + +#ifdef CONFIG_FUSE_IO_URING + +#define FUSE_URING_TEARDOWN_TIMEOUT (5 * HZ) +#define FUSE_URING_TEARDOWN_INTERVAL (HZ/20) + +enum fuse_ring_req_state { + FRRS_INVALID = 0, + + /* The ring entry received from userspace and it is being processed */ + FRRS_COMMIT, + + /* The ring entry is waiting for new fuse requests */ + FRRS_AVAILABLE, + + /* The ring entry got assigned a fuse req */ + FRRS_FUSE_REQ, + + /* The ring entry is in or on the way to user space */ + FRRS_USERSPACE, + + /* The ring entry is in teardown */ + FRRS_TEARDOWN, + + /* The ring entry is released, but not freed yet */ + FRRS_RELEASED, +}; + +/** A fuse ring entry, part of the ring queue */ +struct fuse_ring_ent { + /* userspace buffer */ + struct fuse_uring_req_header __user *headers; + void __user *payload; + + /* the ring queue that owns the request */ + struct fuse_ring_queue *queue; + + /* fields below are protected by queue->lock */ + + struct io_uring_cmd *cmd; + + struct list_head list; + + enum fuse_ring_req_state state; + + struct fuse_req *fuse_req; +}; + +struct fuse_ring_queue { + /* + * back pointer to the main fuse uring structure that holds this + * queue + */ + struct fuse_ring *ring; + + /* queue id, corresponds to the cpu core */ + unsigned int qid; + + /* + * queue lock, taken when any value in the queue changes _and_ also + * a ring entry state changes. + */ + spinlock_t lock; + + /* available ring entries (struct fuse_ring_ent) */ + struct list_head ent_avail_queue; + + /* + * entries in the process of being committed or in the process + * to be sent to userspace + */ + struct list_head ent_w_req_queue; + struct list_head ent_commit_queue; + + /* entries in userspace */ + struct list_head ent_in_userspace; + + /* entries that are released */ + struct list_head ent_released; + + /* fuse requests waiting for an entry slot */ + struct list_head fuse_req_queue; + + /* background fuse requests */ + struct list_head fuse_req_bg_queue; + + struct fuse_pqueue fpq; + + unsigned int active_background; + + bool stopped; +}; + +/** + * Describes if uring is for communication and holds alls the data needed + * for uring communication + */ +struct fuse_ring { + /* back pointer */ + struct fuse_conn *fc; + + /* number of ring queues */ + size_t nr_queues; + + /* maximum payload/arg size */ + size_t max_payload_sz; + + struct fuse_ring_queue **queues; + + /* + * Log ring entry states on stop when entries cannot be released + */ + unsigned int stop_debug_log : 1; + + wait_queue_head_t stop_waitq; + + /* async tear down */ + struct delayed_work async_teardown_work; + + /* log */ + unsigned long teardown_time; + + atomic_t queue_refs; + + bool ready; +}; + +bool fuse_uring_enabled(void); +void fuse_uring_destruct(struct fuse_conn *fc); +void fuse_uring_stop_queues(struct fuse_ring *ring); +void fuse_uring_abort_end_requests(struct fuse_ring *ring); +int fuse_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); +void fuse_uring_queue_fuse_req(struct fuse_iqueue *fiq, struct fuse_req *req); +bool fuse_uring_queue_bq_req(struct fuse_req *req); + +static inline void fuse_uring_abort(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + + if (ring == NULL) + return; + + if (atomic_read(&ring->queue_refs) > 0) { + fuse_uring_abort_end_requests(ring); + fuse_uring_stop_queues(ring); + } +} + +static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc) +{ + struct fuse_ring *ring = fc->ring; + + if (ring) + wait_event(ring->stop_waitq, + atomic_read(&ring->queue_refs) == 0); +} + +static inline bool fuse_uring_ready(struct fuse_conn *fc) +{ + return fc->ring && fc->ring->ready; +} + +#else /* CONFIG_FUSE_IO_URING */ + +struct fuse_ring; + +static inline void fuse_uring_create(struct fuse_conn *fc) +{ +} + +static inline void fuse_uring_destruct(struct fuse_conn *fc) +{ +} + +static inline bool fuse_uring_enabled(void) +{ + return false; +} + +static inline void fuse_uring_abort(struct fuse_conn *fc) +{ +} + +static inline void fuse_uring_wait_stopped_queues(struct fuse_conn *fc) +{ +} + +static inline bool fuse_uring_ready(struct fuse_conn *fc) +{ + return false; +} + +#endif /* CONFIG_FUSE_IO_URING */ + +#endif /* _FS_FUSE_DEV_URING_I_H */ diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index bf057cf7098d..198862b086ff 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -175,9 +175,12 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args, memset(outarg, 0, sizeof(struct fuse_entry_out)); args->opcode = FUSE_LOOKUP; args->nodeid = nodeid; - args->in_numargs = 1; - args->in_args[0].size = name->len + 1; - args->in_args[0].value = name->name; + args->in_numargs = 3; + fuse_set_zero_arg0(args); + args->in_args[1].size = name->len; + args->in_args[1].value = name->name; + args->in_args[2].size = 1; + args->in_args[2].value = ""; args->out_numargs = 1; args->out_args[0].size = sizeof(struct fuse_entry_out); args->out_args[0].value = outarg; @@ -192,10 +195,10 @@ static void fuse_lookup_init(struct fuse_conn *fc, struct fuse_args *args, * the lookup once more. If the lookup results in the same inode, * then refresh the attributes, timeouts and mark the dentry valid. */ -static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) +static int fuse_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *entry, unsigned int flags) { struct inode *inode; - struct dentry *parent; struct fuse_mount *fm; struct fuse_inode *fi; int ret; @@ -227,11 +230,9 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) attr_version = fuse_get_attr_version(fm->fc); - parent = dget_parent(entry); - fuse_lookup_init(fm->fc, &args, get_node_id(d_inode(parent)), - &entry->d_name, &outarg); + fuse_lookup_init(fm->fc, &args, get_node_id(dir), + name, &outarg); ret = fuse_simple_request(fm, &args); - dput(parent); /* Zero nodeid is same as -ENOENT */ if (!ret && !outarg.nodeid) ret = -ENOENT; @@ -265,9 +266,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) if (test_bit(FUSE_I_INIT_RDPLUS, &fi->state)) return -ECHILD; } else if (test_and_clear_bit(FUSE_I_INIT_RDPLUS, &fi->state)) { - parent = dget_parent(entry); - fuse_advise_use_readdirplus(d_inode(parent)); - dput(parent); + fuse_advise_use_readdirplus(dir); } } ret = 1; @@ -929,11 +928,12 @@ static int fuse_symlink(struct mnt_idmap *idmap, struct inode *dir, FUSE_ARGS(args); args.opcode = FUSE_SYMLINK; - args.in_numargs = 2; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; - args.in_args[1].size = len; - args.in_args[1].value = link; + args.in_numargs = 3; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; + args.in_args[2].size = len; + args.in_args[2].value = link; return create_new_entry(idmap, fm, &args, dir, entry, S_IFLNK); } @@ -993,9 +993,10 @@ static int fuse_unlink(struct inode *dir, struct dentry *entry) args.opcode = FUSE_UNLINK; args.nodeid = get_node_id(dir); - args.in_numargs = 1; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; err = fuse_simple_request(fm, &args); if (!err) { fuse_dir_changed(dir); @@ -1016,9 +1017,10 @@ static int fuse_rmdir(struct inode *dir, struct dentry *entry) args.opcode = FUSE_RMDIR; args.nodeid = get_node_id(dir); - args.in_numargs = 1; - args.in_args[0].size = entry->d_name.len + 1; - args.in_args[0].value = entry->d_name.name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = entry->d_name.len + 1; + args.in_args[1].value = entry->d_name.name; err = fuse_simple_request(fm, &args); if (!err) { fuse_dir_changed(dir); diff --git a/fs/fuse/fuse_dev_i.h b/fs/fuse/fuse_dev_i.h new file mode 100644 index 000000000000..3b2bfe1248d3 --- /dev/null +++ b/fs/fuse/fuse_dev_i.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * FUSE: Filesystem in Userspace + * Copyright (C) 2001-2008 Miklos Szeredi <miklos@szeredi.hu> + */ +#ifndef _FS_FUSE_DEV_I_H +#define _FS_FUSE_DEV_I_H + +#include <linux/types.h> + +/* Ordinary requests have even IDs, while interrupts IDs are odd */ +#define FUSE_INT_REQ_BIT (1ULL << 0) +#define FUSE_REQ_ID_STEP (1ULL << 1) + +struct fuse_arg; +struct fuse_args; +struct fuse_pqueue; +struct fuse_req; +struct fuse_iqueue; +struct fuse_forget_link; + +struct fuse_copy_state { + int write; + struct fuse_req *req; + struct iov_iter *iter; + struct pipe_buffer *pipebufs; + struct pipe_buffer *currbuf; + struct pipe_inode_info *pipe; + unsigned long nr_segs; + struct page *pg; + unsigned int len; + unsigned int offset; + unsigned int move_pages:1; + unsigned int is_uring:1; + struct { + unsigned int copied_sz; /* copied size into the user buffer */ + } ring; +}; + +static inline struct fuse_dev *fuse_get_dev(struct file *file) +{ + /* + * Lockless access is OK, because file->private data is set + * once during mount and is valid until the file is released. + */ + return READ_ONCE(file->private_data); +} + +unsigned int fuse_req_hash(u64 unique); +struct fuse_req *fuse_request_find(struct fuse_pqueue *fpq, u64 unique); + +void fuse_dev_end_requests(struct list_head *head); + +void fuse_copy_init(struct fuse_copy_state *cs, int write, + struct iov_iter *iter); +int fuse_copy_args(struct fuse_copy_state *cs, unsigned int numargs, + unsigned int argpages, struct fuse_arg *args, + int zeroing); +int fuse_copy_out_args(struct fuse_copy_state *cs, struct fuse_args *args, + unsigned int nbytes); +void fuse_dev_queue_forget(struct fuse_iqueue *fiq, + struct fuse_forget_link *forget); +void fuse_dev_queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req); + +#endif + diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 74744c6f2860..fee96fe7887b 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -310,7 +310,7 @@ struct fuse_args { bool is_ext:1; bool is_pinned:1; bool invalidate_vmap:1; - struct fuse_in_arg in_args[3]; + struct fuse_in_arg in_args[4]; struct fuse_arg out_args[2]; void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error); /* Used for kvec iter backed by vmalloc address */ @@ -438,6 +438,10 @@ struct fuse_req { /** fuse_mount this request belongs to */ struct fuse_mount *fm; + +#ifdef CONFIG_FUSE_IO_URING + void *ring_entry; +#endif }; struct fuse_iqueue; @@ -863,6 +867,9 @@ struct fuse_conn { /* Use pages instead of pointer for kernel I/O */ unsigned int use_pages_for_kvec_io:1; + /* Use io_uring for communication */ + unsigned int io_uring; + /** Maximum stack depth for passthrough backing files */ int max_stack_depth; @@ -923,6 +930,11 @@ struct fuse_conn { /** IDR for backing files ids */ struct idr backing_files_map; #endif + +#ifdef CONFIG_FUSE_IO_URING + /** uring connection information*/ + struct fuse_ring *ring; +#endif }; /* @@ -947,6 +959,19 @@ struct fuse_mount { struct rcu_head rcu; }; +/* + * Empty header for FUSE opcodes without specific header needs. + * Used as a placeholder in args->in_args[0] for consistency + * across all FUSE operations, simplifying request handling. + */ +struct fuse_zero_header {}; + +static inline void fuse_set_zero_arg0(struct fuse_args *args) +{ + args->in_args[0].size = sizeof(struct fuse_zero_header); + args->in_args[0].value = NULL; +} + static inline struct fuse_mount *get_fuse_mount_super(struct super_block *sb) { return sb->s_fs_info; @@ -1220,6 +1245,11 @@ void fuse_change_entry_timeout(struct dentry *entry, struct fuse_entry_out *o); struct fuse_conn *fuse_conn_get(struct fuse_conn *fc); /** + * Initialize the fuse processing queue + */ +void fuse_pqueue_init(struct fuse_pqueue *fpq); + +/** * Initialize fuse_conn */ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm, diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 3ce4f4e81d09..e9db2cb8c150 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -7,6 +7,7 @@ */ #include "fuse_i.h" +#include "dev_uring_i.h" #include <linux/pagemap.h> #include <linux/slab.h> @@ -937,7 +938,7 @@ static void fuse_iqueue_init(struct fuse_iqueue *fiq, fiq->priv = priv; } -static void fuse_pqueue_init(struct fuse_pqueue *fpq) +void fuse_pqueue_init(struct fuse_pqueue *fpq) { unsigned int i; @@ -992,6 +993,8 @@ static void delayed_release(struct rcu_head *p) { struct fuse_conn *fc = container_of(p, struct fuse_conn, rcu); + fuse_uring_destruct(fc); + put_user_ns(fc->user_ns); fc->release(fc); } @@ -1387,6 +1390,8 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, else ok = false; } + if (flags & FUSE_OVER_IO_URING && fuse_uring_enabled()) + fc->io_uring = 1; } else { ra_pages = fc->max_read / PAGE_SIZE; fc->no_lock = 1; @@ -1446,6 +1451,13 @@ void fuse_send_init(struct fuse_mount *fm) if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH)) flags |= FUSE_PASSTHROUGH; + /* + * This is just an information flag for fuse server. No need to check + * the reply - server is either sending IORING_OP_URING_CMD or not. + */ + if (fuse_uring_enabled()) + flags |= FUSE_OVER_IO_URING; + ia->in.flags = flags; ia->in.flags2 = flags >> 32; diff --git a/fs/fuse/sysctl.c b/fs/fuse/sysctl.c index b272bb333005..63fb1e5bee30 100644 --- a/fs/fuse/sysctl.c +++ b/fs/fuse/sysctl.c @@ -13,7 +13,7 @@ static struct ctl_table_header *fuse_table_header; /* Bound by fuse_init_out max_pages, which is a u16 */ static unsigned int sysctl_fuse_max_pages_limit = 65535; -static struct ctl_table fuse_sysctl_table[] = { +static const struct ctl_table fuse_sysctl_table[] = { { .procname = "max_pages_limit", .data = &fuse_max_pages_limit, diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 9f568d345c51..93dfb06b6cea 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -164,9 +164,10 @@ int fuse_removexattr(struct inode *inode, const char *name) args.opcode = FUSE_REMOVEXATTR; args.nodeid = get_node_id(inode); - args.in_numargs = 1; - args.in_args[0].size = strlen(name) + 1; - args.in_args[0].value = name; + args.in_numargs = 2; + fuse_set_zero_arg0(&args); + args.in_args[1].size = strlen(name) + 1; + args.in_args[1].value = name; err = fuse_simple_request(fm, &args); if (err == -ENOSYS) { fm->fc->no_removexattr = 1; diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c index 2e215e8c3c88..95050e719233 100644 --- a/fs/gfs2/dentry.c +++ b/fs/gfs2/dentry.c @@ -21,7 +21,9 @@ /** * gfs2_drevalidate - Check directory lookup consistency - * @dentry: the mapping to check + * @dir: expected parent directory inode + * @name: expexted name + * @dentry: dentry to check * @flags: lookup flags * * Check to make sure the lookup necessary to arrive at this inode from its @@ -30,50 +32,43 @@ * Returns: 1 if the dentry is ok, 0 if it isn't */ -static int gfs2_drevalidate(struct dentry *dentry, unsigned int flags) +static int gfs2_drevalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - struct dentry *parent; - struct gfs2_sbd *sdp; - struct gfs2_inode *dip; + struct gfs2_sbd *sdp = GFS2_SB(dir); + struct gfs2_inode *dip = GFS2_I(dir); struct inode *inode; struct gfs2_holder d_gh; struct gfs2_inode *ip = NULL; - int error, valid = 0; + int error, valid; int had_lock = 0; if (flags & LOOKUP_RCU) return -ECHILD; - parent = dget_parent(dentry); - sdp = GFS2_SB(d_inode(parent)); - dip = GFS2_I(d_inode(parent)); inode = d_inode(dentry); if (inode) { if (is_bad_inode(inode)) - goto out; + return 0; ip = GFS2_I(inode); } - if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) { - valid = 1; - goto out; - } + if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL) + return 1; had_lock = (gfs2_glock_is_locked_by_me(dip->i_gl) != NULL); if (!had_lock) { error = gfs2_glock_nq_init(dip->i_gl, LM_ST_SHARED, 0, &d_gh); if (error) - goto out; + return 0; } - error = gfs2_dir_check(d_inode(parent), &dentry->d_name, ip); + error = gfs2_dir_check(dir, name, ip); valid = inode ? !error : (error == -ENOENT); if (!had_lock) gfs2_glock_dq_uninit(&d_gh); -out: - dput(parent); return valid; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 8c4c1f871a88..65c07aa95718 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1201,8 +1201,8 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, if (glops->go_instantiate) gl->gl_flags |= BIT(GLF_INSTANTIATE_NEEDED); gl->gl_name = name; + lockref_init(&gl->gl_lockref); lockdep_set_subclass(&gl->gl_lockref.lock, glops->go_subclass); - gl->gl_lockref.count = 1; gl->gl_state = LM_ST_UNLOCKED; gl->gl_target = LM_ST_UNLOCKED; gl->gl_demote_state = LM_ST_EXCLUSIVE; diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c index 04cadc02e5a6..0727f60ad028 100644 --- a/fs/gfs2/main.c +++ b/fs/gfs2/main.c @@ -51,7 +51,6 @@ static void gfs2_init_glock_once(void *foo) { struct gfs2_glock *gl = foo; - spin_lock_init(&gl->gl_lockref.lock); INIT_LIST_HEAD(&gl->gl_holders); INIT_LIST_HEAD(&gl->gl_lru); INIT_LIST_HEAD(&gl->gl_ail_list); diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index 58bc5013ca49..2298e06797ac 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -236,7 +236,7 @@ static struct gfs2_quota_data *qd_alloc(unsigned hash, struct gfs2_sbd *sdp, str return NULL; qd->qd_sbd = sdp; - lockref_init(&qd->qd_lockref, 0); + lockref_init(&qd->qd_lockref); qd->qd_id = qid; qd->qd_slot = -1; INIT_LIST_HEAD(&qd->qd_lru); @@ -297,7 +297,6 @@ static int qd_get(struct gfs2_sbd *sdp, struct kqid qid, spin_lock_bucket(hash); *qdp = qd = gfs2_qd_search_bucket(hash, sdp, qid); if (qd == NULL) { - new_qd->qd_lockref.count++; *qdp = new_qd; list_add(&new_qd->qd_list, &sdp->sd_quota_list); hlist_bl_add_head_rcu(&new_qd->qd_hlist, &qd_hash_table[hash]); @@ -1450,6 +1449,7 @@ int gfs2_quota_init(struct gfs2_sbd *sdp) if (qd == NULL) goto fail_brelse; + qd->qd_lockref.count = 0; set_bit(QDF_CHANGE, &qd->qd_flags); qd->qd_change = qc_change; qd->qd_slot = slot; diff --git a/fs/hfs/sysdep.c b/fs/hfs/sysdep.c index 76fa02e3835b..ef54fc8093cf 100644 --- a/fs/hfs/sysdep.c +++ b/fs/hfs/sysdep.c @@ -13,7 +13,8 @@ /* dentry case-handling: just lowercase everything */ -static int hfs_revalidate_dentry(struct dentry *dentry, unsigned int flags) +static int hfs_revalidate_dentry(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; int diff; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 7e51d2cec64b..e0741e468956 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -95,32 +95,17 @@ __uml_setup("hostfs=", hostfs_args, static char *__dentry_name(struct dentry *dentry, char *name) { char *p = dentry_path_raw(dentry, name, PATH_MAX); - char *root; - size_t len; - struct hostfs_fs_info *fsi; - - fsi = dentry->d_sb->s_fs_info; - root = fsi->host_root_path; - len = strlen(root); - if (IS_ERR(p)) { - __putname(name); - return NULL; - } + struct hostfs_fs_info *fsi = dentry->d_sb->s_fs_info; + char *root = fsi->host_root_path; + size_t len = strlen(root); - /* - * This function relies on the fact that dentry_path_raw() will place - * the path name at the end of the provided buffer. - */ - BUG_ON(p + strlen(p) + 1 != name + PATH_MAX); - - strscpy(name, root, PATH_MAX); - if (len > p - name) { + if (IS_ERR(p) || len > p - name) { __putname(name); return NULL; } - if (p > name + len) - strcpy(name + len, p); + memcpy(name, root, len); + memmove(name + len, p, name + PATH_MAX - p); return name; } @@ -410,38 +395,33 @@ static const struct file_operations hostfs_dir_fops = { .fsync = hostfs_fsync, }; -static int hostfs_writepage(struct page *page, struct writeback_control *wbc) +static int hostfs_writepages(struct address_space *mapping, + struct writeback_control *wbc) { - struct address_space *mapping = page->mapping; struct inode *inode = mapping->host; - char *buffer; - loff_t base = page_offset(page); - int count = PAGE_SIZE; - int end_index = inode->i_size >> PAGE_SHIFT; - int err; - - if (page->index >= end_index) - count = inode->i_size & (PAGE_SIZE-1); - - buffer = kmap_local_page(page); - - err = write_file(HOSTFS_I(inode)->fd, &base, buffer, count); - if (err != count) { - if (err >= 0) - err = -EIO; - mapping_set_error(mapping, err); - goto out; + struct folio *folio = NULL; + loff_t i_size = i_size_read(inode); + int err = 0; + + while ((folio = writeback_iter(mapping, wbc, folio, &err))) { + loff_t pos = folio_pos(folio); + size_t count = folio_size(folio); + char *buffer; + int ret; + + if (count > i_size - pos) + count = i_size - pos; + + buffer = kmap_local_folio(folio, 0); + ret = write_file(HOSTFS_I(inode)->fd, &pos, buffer, count); + kunmap_local(buffer); + folio_unlock(folio); + if (ret != count) { + err = ret < 0 ? ret : -EIO; + mapping_set_error(mapping, err); + } } - if (base > inode->i_size) - inode->i_size = base; - - err = 0; - - out: - kunmap_local(buffer); - unlock_page(page); - return err; } @@ -506,11 +486,12 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping, } static const struct address_space_operations hostfs_aops = { - .writepage = hostfs_writepage, + .writepages = hostfs_writepages, .read_folio = hostfs_read_folio, .dirty_folio = filemap_dirty_folio, .write_begin = hostfs_write_begin, .write_end = hostfs_write_end, + .migrate_folio = filemap_migrate_folio, }; static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st) diff --git a/fs/inode.c b/fs/inode.c index 6b4c77268fc0..5587aabdaa5e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -184,7 +184,7 @@ static int proc_nr_inodes(const struct ctl_table *table, int write, void *buffer return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table inodes_sysctls[] = { +static const struct ctl_table inodes_sysctls[] = { { .procname = "inode-nr", .data = &inodes_stat, diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index d68a4e6ac345..fc8ede43afde 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -1576,7 +1576,8 @@ out: return result; } -static int jfs_ci_revalidate(struct dentry *dentry, unsigned int flags) +static int jfs_ci_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { /* * This is not negative dentry. Always valid. diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 458519e416fe..5f0f8b95f44c 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1109,7 +1109,8 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, return ERR_PTR(rc); } -static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) +static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct kernfs_node *kn; struct kernfs_root *root; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 8502ef68459b..0eb320617d7b 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -927,7 +927,7 @@ repeat: if (!inode) continue; - name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); + name = QSTR(kn->name); parent = kernfs_get_parent(kn); if (parent) { p_inode = ilookup(info->sb, kernfs_ino(parent)); diff --git a/fs/libfs.c b/fs/libfs.c index 5b6120b19e99..8444f5cc4064 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1782,7 +1782,7 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, { const struct dentry *parent; const struct inode *dir; - char strbuf[DNAME_INLINE_LEN]; + union shortname_store strbuf; struct qstr qstr; /* @@ -1802,22 +1802,23 @@ int generic_ci_d_compare(const struct dentry *dentry, unsigned int len, if (!dir || !IS_CASEFOLDED(dir)) return 1; + qstr.len = len; + qstr.name = str; /* * If the dentry name is stored in-line, then it may be concurrently * modified by a rename. If this happens, the VFS will eventually retry * the lookup, so it doesn't matter what ->d_compare() returns. * However, it's unsafe to call utf8_strncasecmp() with an unstable * string. Therefore, we have to copy the name into a temporary buffer. + * As above, len is guaranteed to match str, so the shortname case + * is exactly when str points to ->d_shortname. */ - if (len <= DNAME_INLINE_LEN - 1) { - memcpy(strbuf, str, len); - strbuf[len] = 0; - str = strbuf; + if (qstr.name == dentry->d_shortname.string) { + strbuf = dentry->d_shortname; // NUL is guaranteed to be in there + qstr.name = strbuf.string; /* prevent compiler from optimizing out the temporary buffer */ barrier(); } - qstr.len = len; - qstr.name = str; return utf8_strncasecmp(dentry->d_sb->s_encoding, name, &qstr); } diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 7ded57ec3a60..2c8eedc6c2cc 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -412,7 +412,7 @@ EXPORT_SYMBOL_GPL(lockd_down); * Sysctl parameters (same as module parameters, different interface). */ -static struct ctl_table nlm_sysctls[] = { +static const struct ctl_table nlm_sysctls[] = { { .procname = "nlm_grace_period", .data = &nlm_grace_period, diff --git a/fs/locks.c b/fs/locks.c index 25afc8d9c9d1..1619cddfa7a4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -97,7 +97,7 @@ static int leases_enable = 1; static int lease_break_time = 45; #ifdef CONFIG_SYSCTL -static struct ctl_table locks_sysctls[] = { +static const struct ctl_table locks_sysctls[] = { { .procname = "leases-enable", .data = &leases_enable, diff --git a/fs/namei.c b/fs/namei.c index e56c29a22d26..3ab9440c5b93 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -921,10 +921,11 @@ out_dput: return false; } -static inline int d_revalidate(struct dentry *dentry, unsigned int flags) +static inline int d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) - return dentry->d_op->d_revalidate(dentry, flags); + return dentry->d_op->d_revalidate(dir, name, dentry, flags); else return 1; } @@ -1099,7 +1100,7 @@ static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; #ifdef CONFIG_SYSCTL -static struct ctl_table namei_sysctls[] = { +static const struct ctl_table namei_sysctls[] = { { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, @@ -1652,7 +1653,7 @@ static struct dentry *lookup_dcache(const struct qstr *name, { struct dentry *dentry = d_lookup(dir, name); if (dentry) { - int error = d_revalidate(dentry, flags); + int error = d_revalidate(dir->d_inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) d_invalidate(dentry); @@ -1737,19 +1738,20 @@ static struct dentry *lookup_fast(struct nameidata *nd) if (read_seqcount_retry(&parent->d_seq, nd->seq)) return ERR_PTR(-ECHILD); - status = d_revalidate(dentry, nd->flags); + status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); if (likely(status > 0)) return dentry; if (!try_to_unlazy_next(nd, dentry)) return ERR_PTR(-ECHILD); if (status == -ECHILD) /* we'd been told to redo it in non-rcu mode */ - status = d_revalidate(dentry, nd->flags); + status = d_revalidate(nd->inode, &nd->last, + dentry, nd->flags); } else { dentry = __d_lookup(parent, &nd->last); if (unlikely(!dentry)) return NULL; - status = d_revalidate(dentry, nd->flags); + status = d_revalidate(nd->inode, &nd->last, dentry, nd->flags); } if (unlikely(status <= 0)) { if (!status) @@ -1777,7 +1779,7 @@ again: if (IS_ERR(dentry)) return dentry; if (unlikely(!d_in_lookup(dentry))) { - int error = d_revalidate(dentry, flags); + int error = d_revalidate(inode, name, dentry, flags); if (unlikely(error <= 0)) { if (!error) { d_invalidate(dentry); @@ -3575,7 +3577,7 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, if (d_in_lookup(dentry)) break; - error = d_revalidate(dentry, nd->flags); + error = d_revalidate(dir_inode, &nd->last, dentry, nd->flags); if (likely(error > 0)) break; if (error) diff --git a/fs/namespace.c b/fs/namespace.c index 4013fbac354a..8f1000f9f3df 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -5087,30 +5087,29 @@ static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq) { struct vfsmount *mnt = s->mnt; struct super_block *sb = mnt->mnt_sb; + size_t start = seq->count; int err; - if (sb->s_op->show_options) { - size_t start = seq->count; - - err = security_sb_show_options(seq, sb); - if (err) - return err; + err = security_sb_show_options(seq, sb); + if (err) + return err; + if (sb->s_op->show_options) { err = sb->s_op->show_options(seq, mnt->mnt_root); if (err) return err; + } - if (unlikely(seq_has_overflowed(seq))) - return -EAGAIN; + if (unlikely(seq_has_overflowed(seq))) + return -EAGAIN; - if (seq->count == start) - return 0; + if (seq->count == start) + return 0; - /* skip leading comma */ - memmove(seq->buf + start, seq->buf + start + 1, - seq->count - start - 1); - seq->count--; - } + /* skip leading comma */ + memmove(seq->buf + start, seq->buf + start + 1, + seq->count - start - 1); + seq->count--; return 0; } @@ -5191,39 +5190,45 @@ static int statmount_string(struct kstatmount *s, u64 flag) size_t kbufsize; struct seq_file *seq = &s->seq; struct statmount *sm = &s->sm; - u32 start = seq->count; + u32 start, *offp; + + /* Reserve an empty string at the beginning for any unset offsets */ + if (!seq->count) + seq_putc(seq, 0); + + start = seq->count; switch (flag) { case STATMOUNT_FS_TYPE: - sm->fs_type = start; + offp = &sm->fs_type; ret = statmount_fs_type(s, seq); break; case STATMOUNT_MNT_ROOT: - sm->mnt_root = start; + offp = &sm->mnt_root; ret = statmount_mnt_root(s, seq); break; case STATMOUNT_MNT_POINT: - sm->mnt_point = start; + offp = &sm->mnt_point; ret = statmount_mnt_point(s, seq); break; case STATMOUNT_MNT_OPTS: - sm->mnt_opts = start; + offp = &sm->mnt_opts; ret = statmount_mnt_opts(s, seq); break; case STATMOUNT_OPT_ARRAY: - sm->opt_array = start; + offp = &sm->opt_array; ret = statmount_opt_array(s, seq); break; case STATMOUNT_OPT_SEC_ARRAY: - sm->opt_sec_array = start; + offp = &sm->opt_sec_array; ret = statmount_opt_sec_array(s, seq); break; case STATMOUNT_FS_SUBTYPE: - sm->fs_subtype = start; + offp = &sm->fs_subtype; statmount_fs_subtype(s, seq); break; case STATMOUNT_SB_SOURCE: - sm->sb_source = start; + offp = &sm->sb_source; ret = statmount_sb_source(s, seq); break; default: @@ -5251,6 +5256,7 @@ static int statmount_string(struct kstatmount *s, u64 flag) seq->buf[seq->count++] = '\0'; sm->mask |= flag; + *offp = start; return 0; } @@ -5985,7 +5991,7 @@ const struct proc_ns_operations mntns_operations = { }; #ifdef CONFIG_SYSCTL -static struct ctl_table fs_namespace_sysctls[] = { +static const struct ctl_table fs_namespace_sysctls[] = { { .procname = "mount-max", .data = &sysctl_mount_max, diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index f761d44b3436..0d1b6d35ff3b 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -155,8 +155,9 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, netfs_cache_read_terminated, subreq); } -static void netfs_issue_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq) +static void netfs_queue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq, + bool last_subreq) { struct netfs_io_stream *stream = &rreq->io_streams[0]; @@ -177,8 +178,17 @@ static void netfs_issue_read(struct netfs_io_request *rreq, } } + if (last_subreq) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } + spin_unlock(&rreq->lock); +} +static void netfs_issue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) +{ switch (subreq->source) { case NETFS_DOWNLOAD_FROM_SERVER: rreq->netfs_ops->issue_read(subreq); @@ -293,11 +303,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq) } size -= slice; start += slice; - if (size <= 0) { - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); - } + netfs_queue_read(rreq, subreq, size <= 0); netfs_issue_read(rreq, subreq); cond_resched(); } while (size > 0); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index eb76f98c894b..1c4f953c3d68 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -135,6 +135,8 @@ extern atomic_t netfs_n_rh_write_begin; extern atomic_t netfs_n_rh_write_done; extern atomic_t netfs_n_rh_write_failed; extern atomic_t netfs_n_rh_write_zskip; +extern atomic_t netfs_n_rh_retry_read_req; +extern atomic_t netfs_n_rh_retry_read_subreq; extern atomic_t netfs_n_wh_buffered_write; extern atomic_t netfs_n_wh_writethrough; extern atomic_t netfs_n_wh_dio_write; @@ -147,6 +149,8 @@ extern atomic_t netfs_n_wh_upload_failed; extern atomic_t netfs_n_wh_write; extern atomic_t netfs_n_wh_write_done; extern atomic_t netfs_n_wh_write_failed; +extern atomic_t netfs_n_wh_retry_write_req; +extern atomic_t netfs_n_wh_retry_write_subreq; extern atomic_t netfs_n_wb_lock_skip; extern atomic_t netfs_n_wb_lock_wait; extern atomic_t netfs_n_folioq; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index f65affa5a9e4..636cc5a98ef5 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -470,7 +470,8 @@ void netfs_read_collection_worker(struct work_struct *work) */ void netfs_wake_read_collector(struct netfs_io_request *rreq) { - if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags)) { + if (test_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &rreq->flags) && + !test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) { if (!work_pending(&rreq->work)) { netfs_get_request(rreq, netfs_rreq_trace_get_work); if (!queue_work(system_unbound_wq, &rreq->work)) @@ -586,7 +587,8 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq) smp_mb__after_atomic(); /* Clear IN_PROGRESS before task state */ /* If we are at the head of the queue, wake up the collector. */ - if (list_is_first(&subreq->rreq_link, &stream->subrequests)) + if (list_is_first(&subreq->rreq_link, &stream->subrequests) || + test_bit(NETFS_RREQ_RETRYING, &rreq->flags)) netfs_wake_read_collector(rreq); netfs_put_subrequest(subreq, true, netfs_sreq_trace_put_terminated); diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index 2290af0d51ac..0f294b26e08c 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -14,7 +14,7 @@ static void netfs_reissue_read(struct netfs_io_request *rreq, { __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + netfs_stat(&netfs_n_rh_retry_read_subreq); subreq->rreq->netfs_ops->issue_read(subreq); } @@ -48,6 +48,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); subreq->retry_count++; netfs_reset_iter(subreq); + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); } } @@ -75,7 +76,7 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) struct iov_iter source; unsigned long long start, len; size_t part; - bool boundary = false; + bool boundary = false, subreq_superfluous = false; /* Go through the subreqs and find the next span of contiguous * buffer that we then rejig (cifs, for example, needs the @@ -116,8 +117,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) /* Work through the sublist. */ subreq = from; list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) { - if (!len) + if (!len) { + subreq_superfluous = true; break; + } subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start - subreq->transferred; subreq->len = len + subreq->transferred; @@ -154,19 +157,21 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); netfs_reissue_read(rreq, subreq); - if (subreq == to) + if (subreq == to) { + subreq_superfluous = false; break; + } } /* If we managed to use fewer subreqs, we can discard the * excess; if we used the same number, then we're done. */ if (!len) { - if (subreq == to) + if (!subreq_superfluous) continue; list_for_each_entry_safe_from(subreq, tmp, &stream->subrequests, rreq_link) { - trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + trace_netfs_sreq(subreq, netfs_sreq_trace_superfluous); list_del(&subreq->rreq_link); netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done); if (subreq == to) @@ -187,14 +192,12 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) subreq->source = NETFS_DOWNLOAD_FROM_SERVER; subreq->start = start; subreq->len = len; - subreq->debug_index = atomic_inc_return(&rreq->subreq_counter); subreq->stream_nr = stream->stream_nr; subreq->retry_count = 1; trace_netfs_sreq_ref(rreq->debug_id, subreq->debug_index, refcount_read(&subreq->ref), netfs_sreq_trace_new); - netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); list_add(&subreq->rreq_link, &to->rreq_link); to = list_next_entry(to, rreq_link); @@ -256,14 +259,34 @@ void netfs_retry_reads(struct netfs_io_request *rreq) { struct netfs_io_subrequest *subreq; struct netfs_io_stream *stream = &rreq->io_streams[0]; + DEFINE_WAIT(myself); + + netfs_stat(&netfs_n_rh_retry_read_req); + + set_bit(NETFS_RREQ_RETRYING, &rreq->flags); /* Wait for all outstanding I/O to quiesce before performing retries as * we may need to renegotiate the I/O sizes. */ list_for_each_entry(subreq, &stream->subrequests, rreq_link) { - wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS, - TASK_UNINTERRUPTIBLE); + if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + continue; + + trace_netfs_rreq(rreq, netfs_rreq_trace_wait_queue); + for (;;) { + prepare_to_wait(&rreq->waitq, &myself, TASK_UNINTERRUPTIBLE); + + if (!test_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags)) + break; + + trace_netfs_sreq(subreq, netfs_sreq_trace_wait_for); + schedule(); + trace_netfs_rreq(rreq, netfs_rreq_trace_woke_queue); + } + + finish_wait(&rreq->waitq, &myself); } + clear_bit(NETFS_RREQ_RETRYING, &rreq->flags); trace_netfs_rreq(rreq, netfs_rreq_trace_resubmit); netfs_retry_read_subrequests(rreq); diff --git a/fs/netfs/stats.c b/fs/netfs/stats.c index f1af344266cc..ab6b916addc4 100644 --- a/fs/netfs/stats.c +++ b/fs/netfs/stats.c @@ -29,6 +29,8 @@ atomic_t netfs_n_rh_write_begin; atomic_t netfs_n_rh_write_done; atomic_t netfs_n_rh_write_failed; atomic_t netfs_n_rh_write_zskip; +atomic_t netfs_n_rh_retry_read_req; +atomic_t netfs_n_rh_retry_read_subreq; atomic_t netfs_n_wh_buffered_write; atomic_t netfs_n_wh_writethrough; atomic_t netfs_n_wh_dio_write; @@ -41,6 +43,8 @@ atomic_t netfs_n_wh_upload_failed; atomic_t netfs_n_wh_write; atomic_t netfs_n_wh_write_done; atomic_t netfs_n_wh_write_failed; +atomic_t netfs_n_wh_retry_write_req; +atomic_t netfs_n_wh_retry_write_subreq; atomic_t netfs_n_wb_lock_skip; atomic_t netfs_n_wb_lock_wait; atomic_t netfs_n_folioq; @@ -81,6 +85,11 @@ int netfs_stats_show(struct seq_file *m, void *v) atomic_read(&netfs_n_wh_write), atomic_read(&netfs_n_wh_write_done), atomic_read(&netfs_n_wh_write_failed)); + seq_printf(m, "Retries: rq=%u rs=%u wq=%u ws=%u\n", + atomic_read(&netfs_n_rh_retry_read_req), + atomic_read(&netfs_n_rh_retry_read_subreq), + atomic_read(&netfs_n_wh_retry_write_req), + atomic_read(&netfs_n_wh_retry_write_subreq)); seq_printf(m, "Objs : rr=%u sr=%u foq=%u wsc=%u\n", atomic_read(&netfs_n_rh_rreq), atomic_read(&netfs_n_rh_sreq), diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 69727411683e..77279fc5b5a7 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -253,6 +253,7 @@ void netfs_reissue_write(struct netfs_io_stream *stream, subreq->retry_count++; __clear_bit(NETFS_SREQ_MADE_PROGRESS, &subreq->flags); __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); netfs_do_issue_write(stream, subreq); } diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index c841a851dd73..545d33079a77 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -203,6 +203,8 @@ void netfs_retry_writes(struct netfs_io_request *wreq) struct netfs_io_stream *stream; int s; + netfs_stat(&netfs_n_wh_retry_write_req); + /* Wait for all outstanding I/O to quiesce before performing retries as * we may need to renegotiate the I/O sizes. */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 492cffd9d3d8..2b04038b0e40 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1672,7 +1672,7 @@ nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry, return nfs_lookup_revalidate_done(dir, dentry, inode, 1); } -static int nfs_lookup_revalidate_dentry(struct inode *dir, +static int nfs_lookup_revalidate_dentry(struct inode *dir, const struct qstr *name, struct dentry *dentry, struct inode *inode, unsigned int flags) { @@ -1690,7 +1690,7 @@ static int nfs_lookup_revalidate_dentry(struct inode *dir, goto out; dir_verifier = nfs_save_change_attribute(dir); - ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); + ret = NFS_PROTO(dir)->lookup(dir, dentry, name, fhandle, fattr); if (ret < 0) goto out; @@ -1732,8 +1732,8 @@ out: * cached dentry and do a new lookup. */ static int -nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, - unsigned int flags) +nfs_do_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; int error = 0; @@ -1775,7 +1775,7 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, if (NFS_STALE(inode)) goto out_bad; - return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); + return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags); out_valid: return nfs_lookup_revalidate_done(dir, dentry, inode, 1); out_bad: @@ -1785,38 +1785,26 @@ out_bad: } static int -__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags, - int (*reval)(struct inode *, struct dentry *, unsigned int)) +__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) { - struct dentry *parent; - struct inode *dir; - int ret; - if (flags & LOOKUP_RCU) { if (dentry->d_fsdata == NFS_FSDATA_BLOCKED) return -ECHILD; - parent = READ_ONCE(dentry->d_parent); - dir = d_inode_rcu(parent); - if (!dir) - return -ECHILD; - ret = reval(dir, dentry, flags); - if (parent != READ_ONCE(dentry->d_parent)) - return -ECHILD; } else { /* Wait for unlink to complete - see unblock_revalidate() */ wait_var_event(&dentry->d_fsdata, smp_load_acquire(&dentry->d_fsdata) != NFS_FSDATA_BLOCKED); - parent = dget_parent(dentry); - ret = reval(d_inode(parent), dentry, flags); - dput(parent); } - return ret; + return 0; } -static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) +static int nfs_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { - return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate); + if (__nfs_lookup_revalidate(dentry, flags)) + return -ECHILD; + return nfs_do_lookup_revalidate(dir, name, dentry, flags); } static void block_revalidate(struct dentry *dentry) @@ -1982,7 +1970,8 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name, + fhandle, fattr); if (error == -ENOENT) { if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE)) dir_verifier = inode_peek_iversion_raw(dir); @@ -2025,7 +2014,8 @@ void nfs_d_prune_case_insensitive_aliases(struct inode *inode) EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases); #if IS_ENABLED(CONFIG_NFS_V4) -static int nfs4_lookup_revalidate(struct dentry *, unsigned int); +static int nfs4_lookup_revalidate(struct inode *, const struct qstr *, + struct dentry *, unsigned int); const struct dentry_operations nfs4_dentry_operations = { .d_revalidate = nfs4_lookup_revalidate, @@ -2214,11 +2204,14 @@ no_open: EXPORT_SYMBOL_GPL(nfs_atomic_open); static int -nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, - unsigned int flags) +nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; + if (__nfs_lookup_revalidate(dentry, flags)) + return -ECHILD; + trace_nfs_lookup_revalidate_enter(dir, dentry, flags); if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY)) @@ -2254,16 +2247,10 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry, reval_dentry: if (flags & LOOKUP_RCU) return -ECHILD; - return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags); + return nfs_lookup_revalidate_dentry(dir, name, dentry, inode, flags); full_reval: - return nfs_do_lookup_revalidate(dir, dentry, flags); -} - -static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) -{ - return __nfs_lookup_revalidate(dentry, flags, - nfs4_do_lookup_revalidate); + return nfs_do_lookup_revalidate(dir, name, dentry, flags); } #endif /* CONFIG_NFSV4 */ @@ -2319,7 +2306,8 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, d_drop(dentry); if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); + error = NFS_PROTO(dir)->lookup(dir, dentry, &dentry->d_name, + fhandle, fattr); if (error) goto out_error; } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 2d53574da605..973aed9cc5fe 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -308,7 +308,7 @@ int nfs_submount(struct fs_context *fc, struct nfs_server *server) int err; /* Look it up again to get its attributes */ - err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, + err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, &dentry->d_name, ctx->mntfh, ctx->clone_data.fattr); dput(parent); if (err != 0) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 7359e1a3bd84..0c3bc98cd999 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -192,7 +192,7 @@ __nfs3_proc_lookup(struct inode *dir, const char *name, size_t len, } static int -nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, +nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { unsigned short task_flags = 0; @@ -202,8 +202,7 @@ nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, task_flags |= RPC_TASK_TIMEOUT; dprintk("NFS call lookup %pd2\n", dentry); - return __nfs3_proc_lookup(dir, dentry->d_name.name, - dentry->d_name.len, fhandle, fattr, + return __nfs3_proc_lookup(dir, name->name, name->len, fhandle, fattr, task_flags); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d615d520f8cf..df9669d4ded7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4544,15 +4544,15 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, - struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr) + struct dentry *dentry, const struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(dir); int status; struct nfs4_lookup_arg args = { .bitmask = server->attr_bitmask, .dir_fh = NFS_FH(dir), - .name = &dentry->d_name, + .name = name, }; struct nfs4_lookup_res res = { .server = server, @@ -4594,17 +4594,16 @@ static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) } static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, - struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr) + struct dentry *dentry, const struct qstr *name, + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs4_exception exception = { .interruptible = true, }; struct rpc_clnt *client = *clnt; - const struct qstr *name = &dentry->d_name; int err; do { - err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr); + err = _nfs4_proc_lookup(client, dir, dentry, name, fhandle, fattr); trace_nfs4_lookup(dir, name, err); switch (err) { case -NFS4ERR_BADNAME: @@ -4639,13 +4638,13 @@ out: return err; } -static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, +static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { int status; struct rpc_clnt *client = NFS_CLIENT(dir); - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); + status = nfs4_proc_lookup_common(&client, dir, dentry, name, fhandle, fattr); if (client != NFS_CLIENT(dir)) { rpc_shutdown_client(client); nfs_fixup_secinfo_attributes(fattr); @@ -4660,7 +4659,8 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry, struct rpc_clnt *client = NFS_CLIENT(dir); int status; - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); + status = nfs4_proc_lookup_common(&client, dir, dentry, &dentry->d_name, + fhandle, fattr); if (status < 0) return ERR_PTR(status); return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c index 886a7c4c60b3..d1a92d8f8ba4 100644 --- a/fs/nfs/nfs4sysctl.c +++ b/fs/nfs/nfs4sysctl.c @@ -17,7 +17,7 @@ static const int nfs_set_port_min; static const int nfs_set_port_max = 65535; static struct ctl_table_header *nfs4_callback_sysctl_table; -static struct ctl_table nfs4_cb_sysctls[] = { +static const struct ctl_table nfs4_cb_sysctls[] = { { .procname = "nfs_callback_tcpport", .data = &nfs_callback_set_tcpport, diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 6c09cd090c34..77920a2e3cef 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -153,13 +153,13 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, } static int -nfs_proc_lookup(struct inode *dir, struct dentry *dentry, +nfs_proc_lookup(struct inode *dir, struct dentry *dentry, const struct qstr *name, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { .fh = NFS_FH(dir), - .name = dentry->d_name.name, - .len = dentry->d_name.len + .name = name->name, + .len = name->len }; struct nfs_diropok res = { .fh = fhandle, diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index e645be1a3381..f579df0e8d67 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *nfs_callback_sysctl_table; -static struct ctl_table nfs_cb_sysctls[] = { +static const struct ctl_table nfs_cb_sysctls[] = { { .procname = "nfs_mountpoint_timeout", .data = &nfs_mountpoint_expiry_timeout, diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 0e552d873eaa..fb9b1656a287 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -446,11 +446,20 @@ nfsd_file_dispose_list_delayed(struct list_head *dispose) struct nfsd_file, nf_gc); struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id); struct nfsd_fcache_disposal *l = nn->fcache_disposal; + struct svc_serv *serv; spin_lock(&l->lock); list_move_tail(&nf->nf_gc, &l->freeme); spin_unlock(&l->lock); - svc_wake_up(nn->nfsd_serv); + + /* + * The filecache laundrette is shut down after the + * nn->nfsd_serv pointer is cleared, but before the + * svc_serv is freed. + */ + serv = nn->nfsd_serv; + if (serv) + svc_wake_up(serv); } } diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 4e3be7201b1c..5fb202acb0fd 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -84,6 +84,8 @@ out: fail: posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); + resp->acl_access = NULL; + resp->acl_default = NULL; goto out; } diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 5e34e98db969..7b5433bd3019 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -76,6 +76,8 @@ out: fail: posix_acl_release(resp->acl_access); posix_acl_release(resp->acl_default); + resp->acl_access = NULL; + resp->acl_default = NULL; goto out; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 50e468bdb8d4..484077200c5d 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -679,7 +679,7 @@ static int nfs4_xdr_dec_cb_getattr(struct rpc_rqst *rqstp, return status; status = decode_cb_op_status(xdr, OP_CB_GETATTR, &cb->cb_status); - if (unlikely(status || cb->cb_seq_status)) + if (unlikely(status || cb->cb_status)) return status; if (xdr_stream_decode_uint32_array(xdr, bitmap, 3) < 0) return -NFSERR_BAD_XDR; @@ -1583,8 +1583,11 @@ nfsd4_run_cb_work(struct work_struct *work) nfsd4_process_cb_update(cb); clnt = clp->cl_cb_client; - if (!clnt) { - /* Callback channel broken, or client killed; give up: */ + if (!clnt || clp->cl_state == NFSD4_COURTESY) { + /* + * Callback channel broken, client killed or + * nfs4_client in courtesy state; give up. + */ nfsd41_destroy_cb(cb); return; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index b7a0cfd05401..153eeea2c7c9 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4459,10 +4459,11 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } } while (slot && --cnt > 0); } + +out: seq->maxslots = max(session->se_target_maxslots, seq->maxslots); seq->target_maxslots = session->se_target_maxslots; -out: switch (clp->cl_cb_state) { case NFSD4_CB_DOWN: seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 32019751a41e..aef474f1b84b 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -380,8 +380,9 @@ __fh_verify(struct svc_rqst *rqstp, error = check_nfsd_access(exp, rqstp, may_bypass_gss); if (error) goto out; - - svc_xprt_set_valid(rqstp->rq_xprt); + /* During LOCALIO call to fh_verify will be called with a NULL rqstp */ + if (rqstp) + svc_xprt_set_valid(rqstp->rq_xprt); /* Finally, check access permissions. */ error = nfsd_permission(cred, exp, dentry, access); diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index e8015d24a82c..6613b8fcceb0 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1186,7 +1186,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, if (size) { if (phys && blkphy << blkbits == phys + size) { /* The current extent goes on */ - size += n << blkbits; + size += (u64)n << blkbits; } else { /* Terminate the current extent */ ret = fiemap_fill_next_extent( @@ -1199,14 +1199,14 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, flags = FIEMAP_EXTENT_MERGED; logical = blkoff << blkbits; phys = blkphy << blkbits; - size = n << blkbits; + size = (u64)n << blkbits; } } else { /* Start a new extent */ flags = FIEMAP_EXTENT_MERGED; logical = blkoff << blkbits; phys = blkphy << blkbits; - size = n << blkbits; + size = (u64)n << blkbits; } blkoff += n; } diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index 6004dfdfdf0f..c4cdaf5fa7ed 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -20,7 +20,7 @@ static int dir_notify_enable __read_mostly = 1; #ifdef CONFIG_SYSCTL -static struct ctl_table dnotify_sysctls[] = { +static const struct ctl_table dnotify_sysctls[] = { { .procname = "dir-notify-enable", .data = &dir_notify_enable, diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 6ff94e312232..ba3e2d09eb44 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -58,7 +58,7 @@ static int fanotify_max_queued_events __read_mostly; static long ft_zero = 0; static long ft_int_max = INT_MAX; -static struct ctl_table fanotify_table[] = { +static const struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 8ee495a58d0a..fae1b6d397ea 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -648,7 +648,7 @@ EXPORT_SYMBOL_GPL(fsnotify); * Later, fsnotify permission hooks do not check if there are permission event * watches, but that there were permission event watches at open time. */ -void file_set_fsnotify_mode(struct file *file) +void file_set_fsnotify_mode_from_watchers(struct file *file) { struct dentry *dentry = file->f_path.dentry, *parent; struct super_block *sb = dentry->d_sb; @@ -665,7 +665,7 @@ void file_set_fsnotify_mode(struct file *file) */ if (likely(!fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_CONTENT))) { - file->f_mode |= FMODE_NONOTIFY_PERM; + file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return; } @@ -676,7 +676,7 @@ void file_set_fsnotify_mode(struct file *file) if ((!d_is_dir(dentry) && !d_is_reg(dentry)) || likely(!fsnotify_sb_has_priority_watchers(sb, FSNOTIFY_PRIO_PRE_CONTENT))) { - file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; + file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM); return; } @@ -686,19 +686,25 @@ void file_set_fsnotify_mode(struct file *file) */ mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask); if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask, - FSNOTIFY_PRE_CONTENT_EVENTS))) + FSNOTIFY_PRE_CONTENT_EVENTS))) { + /* Enable pre-content events */ + file_set_fsnotify_mode(file, 0); return; + } /* Is parent watching for pre-content events on this file? */ if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) { parent = dget_parent(dentry); p_mask = fsnotify_inode_watches_children(d_inode(parent)); dput(parent); - if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) + if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) { + /* Enable pre-content events */ + file_set_fsnotify_mode(file, 0); return; + } } /* Nobody watching for pre-content events from this file */ - file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM; + file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM); } #endif diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index e0c48956608a..b372fb2c56bd 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __ro_after_init; static long it_zero = 0; static long it_int_max = INT_MAX; -static struct ctl_table inotify_table[] = { +static const struct ctl_table inotify_table[] = { { .procname = "max_user_instances", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index 8d789b017fa9..af94e3737470 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -787,7 +787,8 @@ pack_runs: if (err) goto out; - attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); + attr = mi_find_attr(ni, mi, NULL, type, name, name_len, + &le->id); if (!attr) { err = -EINVAL; goto bad_inode; @@ -1181,7 +1182,7 @@ repack: goto out; } - attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, &le->id); + attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; @@ -1406,7 +1407,7 @@ int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, */ if (!attr->non_res) { if (vbo[1] + bytes_per_off > le32_to_cpu(attr->res.data_size)) { - ntfs_inode_err(&ni->vfs_inode, "is corrupted"); + _ntfs_bad_inode(&ni->vfs_inode); return -EINVAL; } addr = resident_data(attr); @@ -1796,7 +1797,7 @@ repack: goto out; } - attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, + attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, &le->id); if (!attr) { err = -EINVAL; @@ -2041,8 +2042,8 @@ int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes) } /* Look for required attribute. */ - attr = mi_find_attr(mi, NULL, ATTR_DATA, NULL, - 0, &le->id); + attr = mi_find_attr(ni, mi, NULL, ATTR_DATA, + NULL, 0, &le->id); if (!attr) { err = -EINVAL; goto out; @@ -2587,7 +2588,7 @@ int attr_force_nonresident(struct ntfs_inode *ni) attr = ni_find_attr(ni, NULL, &le, ATTR_DATA, NULL, 0, NULL, &mi); if (!attr) { - ntfs_bad_inode(&ni->vfs_inode, "no data attribute"); + _ntfs_bad_inode(&ni->vfs_inode); return -ENOENT; } diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index fc6a8aa29e3a..b6da80c69ca6 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -512,7 +512,7 @@ out: ctx->pos = pos; } else if (err < 0) { if (err == -EINVAL) - ntfs_inode_err(dir, "directory corrupted"); + _ntfs_bad_inode(dir); ctx->pos = eod; } diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 8b39d0ce5f28..5df6a0b5add9 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -75,7 +75,7 @@ struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni) { const struct ATTRIB *attr; - attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); + attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_STD, NULL, 0, NULL); return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO)) : NULL; } @@ -89,7 +89,7 @@ struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni) { const struct ATTRIB *attr; - attr = mi_find_attr(&ni->mi, NULL, ATTR_STD, NULL, 0, NULL); + attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_STD, NULL, 0, NULL); return attr ? resident_data_ex(attr, sizeof(struct ATTR_STD_INFO5)) : NULL; @@ -148,8 +148,10 @@ int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi) goto out; err = mi_get(ni->mi.sbi, rno, &r); - if (err) + if (err) { + _ntfs_bad_inode(&ni->vfs_inode); return err; + } ni_add_mi(ni, r); @@ -201,7 +203,8 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, *mi = &ni->mi; /* Look for required attribute in primary record. */ - return mi_find_attr(&ni->mi, attr, type, name, name_len, NULL); + return mi_find_attr(ni, &ni->mi, attr, type, name, name_len, + NULL); } /* First look for list entry of required type. */ @@ -217,7 +220,7 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, return NULL; /* Look for required attribute. */ - attr = mi_find_attr(m, NULL, type, name, name_len, &le->id); + attr = mi_find_attr(ni, m, NULL, type, name, name_len, &le->id); if (!attr) goto out; @@ -238,8 +241,7 @@ struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, return attr; out: - ntfs_inode_err(&ni->vfs_inode, "failed to parse mft record"); - ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(&ni->vfs_inode); return NULL; } @@ -259,7 +261,7 @@ struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, if (mi) *mi = &ni->mi; /* Enum attributes in primary record. */ - return mi_enum_attr(&ni->mi, attr); + return mi_enum_attr(ni, &ni->mi, attr); } /* Get next list entry. */ @@ -275,7 +277,7 @@ struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, *mi = mi2; /* Find attribute in loaded record. */ - return rec_find_attr_le(mi2, le2); + return rec_find_attr_le(ni, mi2, le2); } /* @@ -293,7 +295,8 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, if (!ni->attr_list.size) { if (pmi) *pmi = &ni->mi; - return mi_find_attr(&ni->mi, NULL, type, name, name_len, NULL); + return mi_find_attr(ni, &ni->mi, NULL, type, name, name_len, + NULL); } le = al_find_ex(ni, NULL, type, name, name_len, NULL); @@ -319,7 +322,7 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, if (pmi) *pmi = mi; - attr = mi_find_attr(mi, NULL, type, name, name_len, &le->id); + attr = mi_find_attr(ni, mi, NULL, type, name, name_len, &le->id); if (!attr) return NULL; @@ -330,6 +333,7 @@ struct ATTRIB *ni_load_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, vcn <= le64_to_cpu(attr->nres.evcn)) return attr; + _ntfs_bad_inode(&ni->vfs_inode); return NULL; } @@ -398,7 +402,8 @@ int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, int diff; if (base_only || type == ATTR_LIST || !ni->attr_list.size) { - attr = mi_find_attr(&ni->mi, NULL, type, name, name_len, id); + attr = mi_find_attr(ni, &ni->mi, NULL, type, name, name_len, + id); if (!attr) return -ENOENT; @@ -437,7 +442,7 @@ next_le2: al_remove_le(ni, le); - attr = mi_find_attr(mi, NULL, type, name, name_len, id); + attr = mi_find_attr(ni, mi, NULL, type, name, name_len, id); if (!attr) return -ENOENT; @@ -485,7 +490,7 @@ ni_ins_new_attr(struct ntfs_inode *ni, struct mft_inode *mi, name = le->name; } - attr = mi_insert_attr(mi, type, name, name_len, asize, name_off); + attr = mi_insert_attr(ni, mi, type, name, name_len, asize, name_off); if (!attr) { if (le_added) al_remove_le(ni, le); @@ -673,7 +678,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) if (err) return err; - attr_list = mi_find_attr(&ni->mi, NULL, ATTR_LIST, NULL, 0, NULL); + attr_list = mi_find_attr(ni, &ni->mi, NULL, ATTR_LIST, NULL, 0, NULL); if (!attr_list) return 0; @@ -695,7 +700,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) if (!mi) return 0; - attr = mi_find_attr(mi, NULL, le->type, le_name(le), + attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) return 0; @@ -731,7 +736,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) goto out; } - attr = mi_find_attr(mi, NULL, le->type, le_name(le), + attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) { /* Should never happened, 'cause already checked. */ @@ -740,7 +745,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) asize = le32_to_cpu(attr->size); /* Insert into primary record. */ - attr_ins = mi_insert_attr(&ni->mi, le->type, le_name(le), + attr_ins = mi_insert_attr(ni, &ni->mi, le->type, le_name(le), le->name_len, asize, le16_to_cpu(attr->name_off)); if (!attr_ins) { @@ -768,7 +773,7 @@ static int ni_try_remove_attr_list(struct ntfs_inode *ni) if (!mi) continue; - attr = mi_find_attr(mi, NULL, le->type, le_name(le), + attr = mi_find_attr(ni, mi, NULL, le->type, le_name(le), le->name_len, &le->id); if (!attr) continue; @@ -831,7 +836,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) free_b = 0; attr = NULL; - for (; (attr = mi_enum_attr(&ni->mi, attr)); le = Add2Ptr(le, sz)) { + for (; (attr = mi_enum_attr(ni, &ni->mi, attr)); le = Add2Ptr(le, sz)) { sz = le_size(attr->name_len); le->type = attr->type; le->size = cpu_to_le16(sz); @@ -886,7 +891,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) u32 asize = le32_to_cpu(b->size); u16 name_off = le16_to_cpu(b->name_off); - attr = mi_insert_attr(mi, b->type, Add2Ptr(b, name_off), + attr = mi_insert_attr(ni, mi, b->type, Add2Ptr(b, name_off), b->name_len, asize, name_off); if (!attr) goto out; @@ -909,7 +914,7 @@ int ni_create_attr_list(struct ntfs_inode *ni) goto out; } - attr = mi_insert_attr(&ni->mi, ATTR_LIST, NULL, 0, + attr = mi_insert_attr(ni, &ni->mi, ATTR_LIST, NULL, 0, lsize + SIZEOF_RESIDENT, SIZEOF_RESIDENT); if (!attr) goto out; @@ -993,13 +998,13 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, mi = rb_entry(node, struct mft_inode, node); if (is_mft_data && - (mi_enum_attr(mi, NULL) || + (mi_enum_attr(ni, mi, NULL) || vbo <= ((u64)mi->rno << sbi->record_bits))) { /* We can't accept this record 'cause MFT's bootstrapping. */ continue; } if (is_mft && - mi_find_attr(mi, NULL, ATTR_DATA, NULL, 0, NULL)) { + mi_find_attr(ni, mi, NULL, ATTR_DATA, NULL, 0, NULL)) { /* * This child record already has a ATTR_DATA. * So it can't accept any other records. @@ -1008,7 +1013,7 @@ static int ni_ins_attr_ext(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, } if ((type != ATTR_NAME || name_len) && - mi_find_attr(mi, NULL, type, name, name_len, NULL)) { + mi_find_attr(ni, mi, NULL, type, name, name_len, NULL)) { /* Only indexed attributes can share same record. */ continue; } @@ -1157,7 +1162,7 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, /* Estimate the result of moving all possible attributes away. */ attr = NULL; - while ((attr = mi_enum_attr(&ni->mi, attr))) { + while ((attr = mi_enum_attr(ni, &ni->mi, attr))) { if (attr->type == ATTR_STD) continue; if (attr->type == ATTR_LIST) @@ -1175,7 +1180,7 @@ static int ni_insert_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, attr = NULL; for (;;) { - attr = mi_enum_attr(&ni->mi, attr); + attr = mi_enum_attr(ni, &ni->mi, attr); if (!attr) { /* We should never be here 'cause we have already check this case. */ err = -EINVAL; @@ -1259,7 +1264,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) for (node = rb_first(&ni->mi_tree); node; node = rb_next(node)) { mi = rb_entry(node, struct mft_inode, node); - attr = mi_enum_attr(mi, NULL); + attr = mi_enum_attr(ni, mi, NULL); if (!attr) { mft_min = mi->rno; @@ -1280,7 +1285,7 @@ static int ni_expand_mft_list(struct ntfs_inode *ni) ni_remove_mi(ni, mi_new); } - attr = mi_find_attr(&ni->mi, NULL, ATTR_DATA, NULL, 0, NULL); + attr = mi_find_attr(ni, &ni->mi, NULL, ATTR_DATA, NULL, 0, NULL); if (!attr) { err = -EINVAL; goto out; @@ -1397,7 +1402,7 @@ int ni_expand_list(struct ntfs_inode *ni) continue; /* Find attribute in primary record. */ - attr = rec_find_attr_le(&ni->mi, le); + attr = rec_find_attr_le(ni, &ni->mi, le); if (!attr) { err = -EINVAL; goto out; @@ -1604,8 +1609,8 @@ int ni_delete_all(struct ntfs_inode *ni) roff = le16_to_cpu(attr->nres.run_off); if (roff > asize) { - _ntfs_bad_inode(&ni->vfs_inode); - return -EINVAL; + /* ni_enum_attr_ex checks this case. */ + continue; } /* run==1 means unpack and deallocate. */ @@ -2726,9 +2731,10 @@ int ni_write_frame(struct ntfs_inode *ni, struct page **pages, { int err; struct ntfs_sb_info *sbi = ni->mi.sbi; + struct folio *folio = page_folio(pages[0]); u8 frame_bits = NTFS_LZNT_CUNIT + sbi->cluster_bits; u32 frame_size = sbi->cluster_size << NTFS_LZNT_CUNIT; - u64 frame_vbo = (u64)pages[0]->index << PAGE_SHIFT; + u64 frame_vbo = folio_pos(folio); CLST frame = frame_vbo >> frame_bits; char *frame_ondisk = NULL; struct page **pages_disk = NULL; @@ -3343,7 +3349,7 @@ int ni_write_inode(struct inode *inode, int sync, const char *hint) if (!mi->dirty) continue; - is_empty = !mi_enum_attr(mi, NULL); + is_empty = !mi_enum_attr(ni, mi, NULL); if (is_empty) clear_rec_inuse(mi->mrec); diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 03471bc9371c..938d351ebac7 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -908,7 +908,11 @@ void ntfs_bad_inode(struct inode *inode, const char *hint) ntfs_inode_err(inode, "%s", hint); make_bad_inode(inode); - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + /* Avoid recursion if bad inode is $Volume. */ + if (inode->i_ino != MFT_REC_VOL && + !(sbi->flags & NTFS_FLAGS_LOG_REPLAYING)) { + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + } } /* diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 9089c58a005c..7eb9fae22f8d 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -1094,8 +1094,7 @@ int indx_read(struct ntfs_index *indx, struct ntfs_inode *ni, CLST vbn, ok: if (!index_buf_check(ib, bytes, &vbn)) { - ntfs_inode_err(&ni->vfs_inode, "directory corrupted"); - ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(&ni->vfs_inode); err = -EINVAL; goto out; } @@ -1117,8 +1116,7 @@ ok: out: if (err == -E_NTFS_CORRUPT) { - ntfs_inode_err(&ni->vfs_inode, "directory corrupted"); - ntfs_set_state(ni->mi.sbi, NTFS_DIRTY_ERROR); + _ntfs_bad_inode(&ni->vfs_inode); err = -EINVAL; } diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index be04d2845bb7..a1e11228dafd 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -410,6 +410,9 @@ end_enum: if (!std5) goto out; + if (is_bad_inode(inode)) + goto out; + if (!is_match && name) { err = -ENOENT; goto out; diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index cd8e8374bb5a..382820464dee 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -745,23 +745,24 @@ int mi_get(struct ntfs_sb_info *sbi, CLST rno, struct mft_inode **mi); void mi_put(struct mft_inode *mi); int mi_init(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno); int mi_read(struct mft_inode *mi, bool is_mft); -struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr); -// TODO: id? -struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, - enum ATTR_TYPE type, const __le16 *name, - u8 name_len, const __le16 *id); -static inline struct ATTRIB *rec_find_attr_le(struct mft_inode *rec, +struct ATTRIB *mi_enum_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr); +struct ATTRIB *mi_find_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, const __le16 *id); +static inline struct ATTRIB *rec_find_attr_le(struct ntfs_inode *ni, + struct mft_inode *rec, struct ATTR_LIST_ENTRY *le) { - return mi_find_attr(rec, NULL, le->type, le_name(le), le->name_len, + return mi_find_attr(ni, rec, NULL, le->type, le_name(le), le->name_len, &le->id); } int mi_write(struct mft_inode *mi, int wait); int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, __le16 flags, bool is_mft); -struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, - const __le16 *name, u8 name_len, u32 asize, - u16 name_off); +struct ATTRIB *mi_insert_attr(struct ntfs_inode *ni, struct mft_inode *mi, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, u32 asize, u16 name_off); bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, struct ATTRIB *attr); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index 61d53d39f3b9..714c7ecedca8 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -31,7 +31,7 @@ static inline int compare_attr(const struct ATTRIB *left, enum ATTR_TYPE type, * * Return: Unused attribute id that is less than mrec->next_attr_id. */ -static __le16 mi_new_attt_id(struct mft_inode *mi) +static __le16 mi_new_attt_id(struct ntfs_inode *ni, struct mft_inode *mi) { u16 free_id, max_id, t16; struct MFT_REC *rec = mi->mrec; @@ -52,7 +52,7 @@ static __le16 mi_new_attt_id(struct mft_inode *mi) attr = NULL; for (;;) { - attr = mi_enum_attr(mi, attr); + attr = mi_enum_attr(ni, mi, attr); if (!attr) { rec->next_attr_id = cpu_to_le16(max_id + 1); mi->dirty = true; @@ -195,7 +195,8 @@ out: * NOTE: mi->mrec - memory of size sbi->record_size * here we sure that mi->mrec->total == sbi->record_size (see mi_read) */ -struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) +struct ATTRIB *mi_enum_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr) { const struct MFT_REC *rec = mi->mrec; u32 used = le32_to_cpu(rec->used); @@ -209,11 +210,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) off = le16_to_cpu(rec->attr_off); if (used > total) - return NULL; + goto out; if (off >= used || off < MFTRECORD_FIXUP_OFFSET_1 || !IS_ALIGNED(off, 8)) { - return NULL; + goto out; } /* Skip non-resident records. */ @@ -243,7 +244,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) */ if (off + 8 > used) { static_assert(ALIGN(sizeof(enum ATTR_TYPE), 8) == 8); - return NULL; + goto out; } if (attr->type == ATTR_END) { @@ -254,112 +255,116 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* 0x100 is last known attribute for now. */ t32 = le32_to_cpu(attr->type); if (!t32 || (t32 & 0xf) || (t32 > 0x100)) - return NULL; + goto out; /* attributes in record must be ordered by type */ if (t32 < prev_type) - return NULL; + goto out; asize = le32_to_cpu(attr->size); if (!IS_ALIGNED(asize, 8)) - return NULL; + goto out; /* Check overflow and boundary. */ if (off + asize < off || off + asize > used) - return NULL; + goto out; /* Can we use the field attr->non_res. */ if (off + 9 > used) - return NULL; + goto out; /* Check size of attribute. */ if (!attr->non_res) { /* Check resident fields. */ if (asize < SIZEOF_RESIDENT) - return NULL; + goto out; t16 = le16_to_cpu(attr->res.data_off); if (t16 > asize) - return NULL; + goto out; if (le32_to_cpu(attr->res.data_size) > asize - t16) - return NULL; + goto out; t32 = sizeof(short) * attr->name_len; if (t32 && le16_to_cpu(attr->name_off) + t32 > t16) - return NULL; + goto out; return attr; } /* Check nonresident fields. */ if (attr->non_res != 1) - return NULL; + goto out; /* Can we use memory including attr->nres.valid_size? */ if (asize < SIZEOF_NONRESIDENT) - return NULL; + goto out; t16 = le16_to_cpu(attr->nres.run_off); if (t16 > asize) - return NULL; + goto out; t32 = sizeof(short) * attr->name_len; if (t32 && le16_to_cpu(attr->name_off) + t32 > t16) - return NULL; + goto out; /* Check start/end vcn. */ if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1) - return NULL; + goto out; data_size = le64_to_cpu(attr->nres.data_size); if (le64_to_cpu(attr->nres.valid_size) > data_size) - return NULL; + goto out; alloc_size = le64_to_cpu(attr->nres.alloc_size); if (data_size > alloc_size) - return NULL; + goto out; t32 = mi->sbi->cluster_mask; if (alloc_size & t32) - return NULL; + goto out; if (!attr->nres.svcn && is_attr_ext(attr)) { /* First segment of sparse/compressed attribute */ /* Can we use memory including attr->nres.total_size? */ if (asize < SIZEOF_NONRESIDENT_EX) - return NULL; + goto out; tot_size = le64_to_cpu(attr->nres.total_size); if (tot_size & t32) - return NULL; + goto out; if (tot_size > alloc_size) - return NULL; + goto out; } else { if (attr->nres.c_unit) - return NULL; + goto out; if (alloc_size > mi->sbi->volume.size) - return NULL; + goto out; } return attr; + +out: + _ntfs_bad_inode(&ni->vfs_inode); + return NULL; } /* * mi_find_attr - Find the attribute by type and name and id. */ -struct ATTRIB *mi_find_attr(struct mft_inode *mi, struct ATTRIB *attr, - enum ATTR_TYPE type, const __le16 *name, - u8 name_len, const __le16 *id) +struct ATTRIB *mi_find_attr(struct ntfs_inode *ni, struct mft_inode *mi, + struct ATTRIB *attr, enum ATTR_TYPE type, + const __le16 *name, u8 name_len, const __le16 *id) { u32 type_in = le32_to_cpu(type); u32 atype; next_attr: - attr = mi_enum_attr(mi, attr); + attr = mi_enum_attr(ni, mi, attr); if (!attr) return NULL; @@ -467,9 +472,9 @@ int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, * * Return: Not full constructed attribute or NULL if not possible to create. */ -struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, - const __le16 *name, u8 name_len, u32 asize, - u16 name_off) +struct ATTRIB *mi_insert_attr(struct ntfs_inode *ni, struct mft_inode *mi, + enum ATTR_TYPE type, const __le16 *name, + u8 name_len, u32 asize, u16 name_off) { size_t tail; struct ATTRIB *attr; @@ -488,7 +493,7 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, * at which we should insert it. */ attr = NULL; - while ((attr = mi_enum_attr(mi, attr))) { + while ((attr = mi_enum_attr(ni, mi, attr))) { int diff = compare_attr(attr, type, name, name_len, upcase); if (diff < 0) @@ -508,7 +513,7 @@ struct ATTRIB *mi_insert_attr(struct mft_inode *mi, enum ATTR_TYPE type, tail = used - PtrOffset(rec, attr); } - id = mi_new_attt_id(mi); + id = mi_new_attt_id(ni, mi); memmove(Add2Ptr(attr, asize), attr, tail); memset(attr, 0, asize); diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c index a9b8688aaf30..1873bbbb7e5b 100644 --- a/fs/ocfs2/dcache.c +++ b/fs/ocfs2/dcache.c @@ -32,7 +32,8 @@ void ocfs2_dentry_attach_gen(struct dentry *dentry) } -static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) +static int ocfs2_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; int ret = 0; /* if all else fails, just return false */ @@ -44,8 +45,7 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) inode = d_inode(dentry); osb = OCFS2_SB(dentry->d_sb); - trace_ocfs2_dentry_revalidate(dentry, dentry->d_name.len, - dentry->d_name.name); + trace_ocfs2_dentry_revalidate(dentry, name->len, name->name); /* For a negative dentry - * check the generation number of the parent and compare with the @@ -53,12 +53,8 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry, unsigned int flags) */ if (inode == NULL) { unsigned long gen = (unsigned long) dentry->d_fsdata; - unsigned long pgen; - spin_lock(&dentry->d_lock); - pgen = OCFS2_I(d_inode(dentry->d_parent))->ip_dir_lock_gen; - spin_unlock(&dentry->d_lock); - trace_ocfs2_dentry_revalidate_negative(dentry->d_name.len, - dentry->d_name.name, + unsigned long pgen = OCFS2_I(dir)->ip_dir_lock_gen; + trace_ocfs2_dentry_revalidate_negative(name->len, name->name, pgen, gen); if (gen != pgen) goto bail; diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c index 20aa37b67cfb..ddd761cf44c8 100644 --- a/fs/ocfs2/stackglue.c +++ b/fs/ocfs2/stackglue.c @@ -650,7 +650,7 @@ error: * and easier to preserve the name. */ -static struct ctl_table ocfs2_nm_table[] = { +static const struct ctl_table ocfs2_nm_table[] = { { .procname = "hb_ctl_path", .data = ocfs2_hb_ctl_path, diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index e0b91dbaa0ac..8bb5022f3082 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -2285,7 +2285,7 @@ static int ocfs2_verify_volume(struct ocfs2_dinode *di, mlog(ML_ERROR, "found superblock with incorrect block " "size bits: found %u, should be 9, 10, 11, or 12\n", blksz_bits); - } else if ((1 << le32_to_cpu(blksz_bits)) != blksz) { + } else if ((1 << blksz_bits) != blksz) { mlog(ML_ERROR, "found superblock with incorrect block " "size: found %u, should be %u\n", 1 << blksz_bits, blksz); } else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) != diff --git a/fs/open.c b/fs/open.c index 932e5a6de63b..1be20de9f283 100644 --- a/fs/open.c +++ b/fs/open.c @@ -905,7 +905,8 @@ static int do_dentry_open(struct file *f, f->f_sb_err = file_sample_sb_err(f); if (unlikely(f->f_flags & O_PATH)) { - f->f_mode = FMODE_PATH | FMODE_OPENED | FMODE_NONOTIFY; + f->f_mode = FMODE_PATH | FMODE_OPENED; + file_set_fsnotify_mode(f, FMODE_NONOTIFY); f->f_op = &empty_fops; return 0; } @@ -935,10 +936,10 @@ static int do_dentry_open(struct file *f, /* * Set FMODE_NONOTIFY_* bits according to existing permission watches. - * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't - * change anything. + * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a + * pseudo file, this call will not change the mode. */ - file_set_fsnotify_mode(f); + file_set_fsnotify_mode_from_watchers(f); error = fsnotify_open_perm(f); if (error) goto cleanup_all; @@ -1122,7 +1123,7 @@ struct file *dentry_open_nonotify(const struct path *path, int flags, if (!IS_ERR(f)) { int error; - f->f_mode |= FMODE_NONOTIFY; + file_set_fsnotify_mode(f, FMODE_NONOTIFY); error = vfs_open(path, f); if (error) { fput(f); diff --git a/fs/orangefs/dcache.c b/fs/orangefs/dcache.c index 395a00ed8ac7..a19d1ad705db 100644 --- a/fs/orangefs/dcache.c +++ b/fs/orangefs/dcache.c @@ -13,10 +13,9 @@ #include "orangefs-kernel.h" /* Returns 1 if dentry can still be trusted, else 0. */ -static int orangefs_revalidate_lookup(struct dentry *dentry) +static int orangefs_revalidate_lookup(struct inode *parent_inode, const struct qstr *name, + struct dentry *dentry) { - struct dentry *parent_dentry = dget_parent(dentry); - struct inode *parent_inode = parent_dentry->d_inode; struct orangefs_inode_s *parent = ORANGEFS_I(parent_inode); struct inode *inode = dentry->d_inode; struct orangefs_kernel_op_s *new_op; @@ -26,14 +25,14 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) gossip_debug(GOSSIP_DCACHE_DEBUG, "%s: attempting lookup.\n", __func__); new_op = op_alloc(ORANGEFS_VFS_OP_LOOKUP); - if (!new_op) { - ret = -ENOMEM; - goto out_put_parent; - } + if (!new_op) + return -ENOMEM; new_op->upcall.req.lookup.sym_follow = ORANGEFS_LOOKUP_LINK_NO_FOLLOW; new_op->upcall.req.lookup.parent_refn = parent->refn; - strscpy(new_op->upcall.req.lookup.d_name, dentry->d_name.name); + /* op_alloc() leaves ->upcall zeroed */ + memcpy(new_op->upcall.req.lookup.d_name, name->name, + min(name->len, ORANGEFS_NAME_MAX - 1)); gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d interrupt flag [%d]\n", @@ -78,8 +77,6 @@ static int orangefs_revalidate_lookup(struct dentry *dentry) ret = 1; out_release_op: op_release(new_op); -out_put_parent: - dput(parent_dentry); return ret; out_drop: gossip_debug(GOSSIP_DCACHE_DEBUG, "%s:%s:%d revalidate failed\n", @@ -92,7 +89,8 @@ out_drop: * * Should return 1 if dentry can still be trusted, else 0. */ -static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int orangefs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { int ret; unsigned long time = (unsigned long) dentry->d_fsdata; @@ -114,7 +112,7 @@ static int orangefs_d_revalidate(struct dentry *dentry, unsigned int flags) * If this passes, the positive dentry still exists or the negative * dentry still does not exist. */ - if (!orangefs_revalidate_lookup(dentry)) + if (!orangefs_revalidate_lookup(dir, name, dentry)) return 0; /* We do not need to continue with negative dentries. */ diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c index 9729f071c5aa..f52073022fae 100644 --- a/fs/orangefs/orangefs-debugfs.c +++ b/fs/orangefs/orangefs-debugfs.c @@ -392,9 +392,9 @@ static ssize_t orangefs_debug_write(struct file *file, * Thwart users who try to jamb a ridiculous number * of bytes into the debug file... */ - if (count > ORANGEFS_MAX_DEBUG_STRING_LEN + 1) { + if (count > ORANGEFS_MAX_DEBUG_STRING_LEN) { silly = count; - count = ORANGEFS_MAX_DEBUG_STRING_LEN + 1; + count = ORANGEFS_MAX_DEBUG_STRING_LEN; } buf = kzalloc(ORANGEFS_MAX_DEBUG_STRING_LEN, GFP_KERNEL); diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c index cea820cb3b55..be5c65d6f848 100644 --- a/fs/overlayfs/namei.c +++ b/fs/overlayfs/namei.c @@ -14,8 +14,6 @@ #include <linux/exportfs.h> #include "overlayfs.h" -#include "../internal.h" /* for vfs_path_lookup */ - struct ovl_lookup_data { struct super_block *sb; const struct ovl_layer *layer; diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index fe511192f83c..86ae6f6da36b 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -91,7 +91,24 @@ static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak) if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE) ret = d->d_op->d_weak_revalidate(d, flags); } else if (d->d_flags & DCACHE_OP_REVALIDATE) { - ret = d->d_op->d_revalidate(d, flags); + struct dentry *parent; + struct inode *dir; + struct name_snapshot n; + + if (flags & LOOKUP_RCU) { + parent = READ_ONCE(d->d_parent); + dir = d_inode_rcu(parent); + if (!dir) + return -ECHILD; + } else { + parent = dget_parent(d); + dir = d_inode(parent); + } + take_dentry_name_snapshot(&n, d); + ret = d->d_op->d_revalidate(dir, &n.name, d, flags); + release_dentry_name_snapshot(&n); + if (!(flags & LOOKUP_RCU)) + dput(parent); if (!ret) { if (!(flags & LOOKUP_RCU)) d_invalidate(d); @@ -127,7 +144,8 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry, return ret; } -static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags) +static int ovl_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { return ovl_dentry_revalidate_common(dentry, flags, false); } diff --git a/fs/pidfs.c b/fs/pidfs.c index 049352f973de..63f9699ebac3 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -287,7 +287,6 @@ static bool pidfs_ioctl_valid(unsigned int cmd) switch (cmd) { case FS_IOC_GETVERSION: case PIDFD_GET_CGROUP_NAMESPACE: - case PIDFD_GET_INFO: case PIDFD_GET_IPC_NAMESPACE: case PIDFD_GET_MNT_NAMESPACE: case PIDFD_GET_NET_NAMESPACE: @@ -300,6 +299,17 @@ static bool pidfs_ioctl_valid(unsigned int cmd) return true; } + /* Extensible ioctls require some more careful checks. */ + switch (_IOC_NR(cmd)) { + case _IOC_NR(PIDFD_GET_INFO): + /* + * Try to prevent performing a pidfd ioctl when someone + * erronously mistook the file descriptor for a pidfd. + * This is not perfect but will catch most cases. + */ + return (_IOC_TYPE(cmd) == _IOC_TYPE(PIDFD_GET_INFO)); + } + return false; } diff --git a/fs/pipe.c b/fs/pipe.c index 82fede0f2111..ce1af7592780 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -960,6 +960,12 @@ int create_pipe_files(struct file **res, int flags) res[1] = f; stream_open(inode, res[0]); stream_open(inode, res[1]); + /* + * Disable permission and pre-content events, but enable legacy + * inotify events for legacy users. + */ + file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM); + file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM); return 0; } @@ -1478,7 +1484,7 @@ static int proc_dopipe_max_size(const struct ctl_table *table, int write, do_proc_dopipe_max_size_conv, NULL); } -static struct ctl_table fs_pipe_sysctls[] = { +static const struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, diff --git a/fs/proc/base.c b/fs/proc/base.c index a50b222a5917..cd89e956c322 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2058,7 +2058,8 @@ void pid_update_inode(struct task_struct *task, struct inode *inode) * performed a setuid(), etc. * */ -static int pid_revalidate(struct dentry *dentry, unsigned int flags) +static int pid_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct inode *inode; struct task_struct *task; @@ -2191,7 +2192,8 @@ static int dname_to_vma_addr(struct dentry *dentry, return 0; } -static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) +static int map_files_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { unsigned long vm_start, vm_end; bool exact_vma_exists = false; diff --git a/fs/proc/fd.c b/fs/proc/fd.c index 24baf23e864f..37aa778d1af7 100644 --- a/fs/proc/fd.c +++ b/fs/proc/fd.c @@ -140,7 +140,8 @@ static void tid_fd_update_inode(struct task_struct *task, struct inode *inode, security_task_to_inode(task, inode); } -static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags) +static int tid_fd_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct task_struct *task; struct inode *inode; diff --git a/fs/proc/generic.c b/fs/proc/generic.c index dbe82cf23ee4..8ec90826a49e 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -216,7 +216,8 @@ void proc_free_inum(unsigned int inum) ida_free(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST); } -static int proc_misc_d_revalidate(struct dentry *dentry, unsigned int flags) +static int proc_misc_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; @@ -343,7 +344,8 @@ static const struct file_operations proc_dir_operations = { .iterate_shared = proc_readdir, }; -static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +static int proc_net_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { return 0; } diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 27a283d85a6e..cc9d74a06ff0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -884,7 +884,8 @@ static const struct inode_operations proc_sys_dir_operations = { .getattr = proc_sys_getattr, }; -static int proc_sys_revalidate(struct dentry *dentry, unsigned int flags) +static int proc_sys_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index a00120a3c099..10d01eb09c43 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -1524,7 +1524,7 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) pr_warn_once("Unexpected adding of device dump\n"); if (vmcore_open) { ret = -EBUSY; - goto out_err; + goto unlock; } list_add_tail(&dump->list, &vmcoredd_list); @@ -1532,6 +1532,9 @@ int vmcore_add_device_dump(struct vmcoredd_data *data) mutex_unlock(&vmcore_mutex); return 0; +unlock: + mutex_unlock(&vmcore_mutex); + out_err: vfree(buf); vfree(dump); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index f9578918cfb2..825c5c2e0962 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -2926,7 +2926,7 @@ static int do_proc_dqstats(const struct ctl_table *table, int write, return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table fs_dqstats_table[] = { +static const struct ctl_table fs_dqstats_table[] = { { .procname = "lookups", .data = &dqstats.stat[DQST_LOOKUPS], diff --git a/fs/smb/client/asn1.c b/fs/smb/client/asn1.c index b5724ef9f182..214a44509e7b 100644 --- a/fs/smb/client/asn1.c +++ b/fs/smb/client/asn1.c @@ -52,6 +52,8 @@ int cifs_neg_token_init_mech_type(void *context, size_t hdrlen, server->sec_kerberos = true; else if (oid == OID_ntlmssp) server->sec_ntlmssp = true; + else if (oid == OID_IAKerb) + server->sec_iakerb = true; else { char buf[50]; diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 28f568b5fc27..bc1c1e9b288a 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -138,11 +138,13 @@ cifs_get_spnego_key(struct cifs_ses *sesInfo, dp = description + strlen(description); - /* for now, only sec=krb5 and sec=mskrb5 are valid */ + /* for now, only sec=krb5 and sec=mskrb5 and iakerb are valid */ if (server->sec_kerberos) sprintf(dp, ";sec=krb5"); else if (server->sec_mskerberos) sprintf(dp, ";sec=mskrb5"); + else if (server->sec_iakerb) + sprintf(dp, ";sec=iakerb"); else { cifs_dbg(VFS, "unknown or missing server auth type, use krb5\n"); sprintf(dp, ";sec=krb5"); diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index ba79aa2107cc..699a3f76d083 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -1395,7 +1395,7 @@ chown_chgrp_exit: #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, const struct cifs_fid *cifsfid, u32 *pacllen, - u32 __maybe_unused unused) + u32 info) { struct smb_ntsd *pntsd = NULL; unsigned int xid; @@ -1407,7 +1407,7 @@ struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, xid = get_xid(); rc = CIFSSMBGetCIFSACL(xid, tlink_tcon(tlink), cifsfid->netfid, &pntsd, - pacllen); + pacllen, info); free_xid(xid); cifs_put_tlink(tlink); @@ -1419,7 +1419,7 @@ struct smb_ntsd *get_cifs_acl_by_fid(struct cifs_sb_info *cifs_sb, } static struct smb_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, - const char *path, u32 *pacllen) + const char *path, u32 *pacllen, u32 info) { struct smb_ntsd *pntsd = NULL; int oplock = 0; @@ -1446,9 +1446,12 @@ static struct smb_ntsd *get_cifs_acl_by_path(struct cifs_sb_info *cifs_sb, .fid = &fid, }; + if (info & SACL_SECINFO) + oparms.desired_access |= SYSTEM_SECURITY; + rc = CIFS_open(xid, &oparms, &oplock, NULL); if (!rc) { - rc = CIFSSMBGetCIFSACL(xid, tcon, fid.netfid, &pntsd, pacllen); + rc = CIFSSMBGetCIFSACL(xid, tcon, fid.netfid, &pntsd, pacllen, info); CIFSSMBClose(xid, tcon, fid.netfid); } @@ -1472,7 +1475,7 @@ struct smb_ntsd *get_cifs_acl(struct cifs_sb_info *cifs_sb, if (inode) open_file = find_readable_file(CIFS_I(inode), true); if (!open_file) - return get_cifs_acl_by_path(cifs_sb, path, pacllen); + return get_cifs_acl_by_path(cifs_sb, path, pacllen, info); pntsd = get_cifs_acl_by_fid(cifs_sb, &open_file->fid, pacllen, info); cifsFileInfo_put(open_file); @@ -1485,7 +1488,7 @@ int set_cifs_acl(struct smb_ntsd *pnntsd, __u32 acllen, { int oplock = 0; unsigned int xid; - int rc, access_flags; + int rc, access_flags = 0; struct cifs_tcon *tcon; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct tcon_link *tlink = cifs_sb_tlink(cifs_sb); @@ -1498,10 +1501,12 @@ int set_cifs_acl(struct smb_ntsd *pnntsd, __u32 acllen, tcon = tlink_tcon(tlink); xid = get_xid(); - if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP) - access_flags = WRITE_OWNER; - else - access_flags = WRITE_DAC; + if (aclflag & CIFS_ACL_OWNER || aclflag & CIFS_ACL_GROUP) + access_flags |= WRITE_OWNER; + if (aclflag & CIFS_ACL_SACL) + access_flags |= SYSTEM_SECURITY; + if (aclflag & CIFS_ACL_DACL) + access_flags |= WRITE_DAC; oparms = (struct cifs_open_parms) { .tcon = tcon, diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index b800c9f585d8..6a3bd652d251 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -715,6 +715,12 @@ cifs_show_options(struct seq_file *s, struct dentry *root) cifs_sb->ctx->backupgid)); seq_show_option(s, "reparse", cifs_reparse_type_str(cifs_sb->ctx->reparse_type)); + if (cifs_sb->ctx->nonativesocket) + seq_puts(s, ",nonativesocket"); + else + seq_puts(s, ",nativesocket"); + seq_show_option(s, "symlink", + cifs_symlink_type_str(get_cifs_symlink_type(cifs_sb))); seq_printf(s, ",rsize=%u", cifs_sb->ctx->rsize); seq_printf(s, ",wsize=%u", cifs_sb->ctx->wsize); diff --git a/fs/smb/client/cifsfs.h b/fs/smb/client/cifsfs.h index a762dbbbd959..831fee962c4d 100644 --- a/fs/smb/client/cifsfs.h +++ b/fs/smb/client/cifsfs.h @@ -146,6 +146,6 @@ extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ /* when changing internal version - update following two lines at same time */ -#define SMB3_PRODUCT_BUILD 52 -#define CIFS_VERSION "2.52" +#define SMB3_PRODUCT_BUILD 53 +#define CIFS_VERSION "2.53" #endif /* _CIFSFS_H */ diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 49ffc040f736..cddeb2adbf4a 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -151,6 +151,7 @@ enum securityEnum { NTLMv2, /* Legacy NTLM auth with NTLMv2 hash */ RawNTLMSSP, /* NTLMSSP without SPNEGO, NTLMv2 hash */ Kerberos, /* Kerberos via SPNEGO */ + IAKerb, /* Kerberos proxy */ }; enum upcall_target_enum { @@ -160,6 +161,7 @@ enum upcall_target_enum { }; enum cifs_reparse_type { + CIFS_REPARSE_TYPE_NONE, CIFS_REPARSE_TYPE_NFS, CIFS_REPARSE_TYPE_WSL, CIFS_REPARSE_TYPE_DEFAULT = CIFS_REPARSE_TYPE_NFS, @@ -168,6 +170,8 @@ enum cifs_reparse_type { static inline const char *cifs_reparse_type_str(enum cifs_reparse_type type) { switch (type) { + case CIFS_REPARSE_TYPE_NONE: + return "none"; case CIFS_REPARSE_TYPE_NFS: return "nfs"; case CIFS_REPARSE_TYPE_WSL: @@ -177,6 +181,39 @@ static inline const char *cifs_reparse_type_str(enum cifs_reparse_type type) } } +enum cifs_symlink_type { + CIFS_SYMLINK_TYPE_DEFAULT, + CIFS_SYMLINK_TYPE_NONE, + CIFS_SYMLINK_TYPE_NATIVE, + CIFS_SYMLINK_TYPE_UNIX, + CIFS_SYMLINK_TYPE_MFSYMLINKS, + CIFS_SYMLINK_TYPE_SFU, + CIFS_SYMLINK_TYPE_NFS, + CIFS_SYMLINK_TYPE_WSL, +}; + +static inline const char *cifs_symlink_type_str(enum cifs_symlink_type type) +{ + switch (type) { + case CIFS_SYMLINK_TYPE_NONE: + return "none"; + case CIFS_SYMLINK_TYPE_NATIVE: + return "native"; + case CIFS_SYMLINK_TYPE_UNIX: + return "unix"; + case CIFS_SYMLINK_TYPE_MFSYMLINKS: + return "mfsymlinks"; + case CIFS_SYMLINK_TYPE_SFU: + return "sfu"; + case CIFS_SYMLINK_TYPE_NFS: + return "nfs"; + case CIFS_SYMLINK_TYPE_WSL: + return "wsl"; + default: + return "unknown"; + } +} + struct session_key { unsigned int len; char *response; @@ -215,10 +252,8 @@ struct cifs_cred { struct cifs_open_info_data { bool adjust_tz; - union { - bool reparse_point; - bool symlink; - }; + bool reparse_point; + bool contains_posix_file_info; struct { /* ioctl response buffer */ struct { @@ -226,10 +261,7 @@ struct cifs_open_info_data { struct kvec iov; } io; __u32 tag; - union { - struct reparse_data_buffer *buf; - struct reparse_posix_data *posix; - }; + struct reparse_data_buffer *buf; } reparse; struct { __u8 eas[SMB2_WSL_MAX_QUERY_EA_RESP_SIZE]; @@ -326,7 +358,7 @@ struct smb_version_operations { int (*handle_cancelled_mid)(struct mid_q_entry *, struct TCP_Server_Info *); void (*downgrade_oplock)(struct TCP_Server_Info *server, struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache); + __u16 epoch, bool *purge_cache); /* process transaction2 response */ bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *, char *, int); @@ -521,12 +553,12 @@ struct smb_version_operations { /* if we can do cache read operations */ bool (*is_read_op)(__u32); /* set oplock level for the inode */ - void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int, - bool *); + void (*set_oplock_level)(struct cifsInodeInfo *cinode, __u32 oplock, __u16 epoch, + bool *purge_cache); /* create lease context buffer for CREATE request */ char * (*create_lease_buf)(u8 *lease_key, u8 oplock); /* parse lease context buffer and return oplock/epoch info */ - __u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey); + __u8 (*parse_lease_buf)(void *buf, __u16 *epoch, char *lkey); ssize_t (*copychunk_range)(const unsigned int, struct cifsFileInfo *src_file, struct cifsFileInfo *target_file, @@ -751,6 +783,7 @@ struct TCP_Server_Info { bool sec_kerberosu2u; /* supports U2U Kerberos */ bool sec_kerberos; /* supports plain Kerberos */ bool sec_mskerberos; /* supports legacy MS Kerberos */ + bool sec_iakerb; /* supports pass-through auth for Kerberos (krb5 proxy) */ bool large_buf; /* is current buffer large? */ /* use SMBD connection instead of socket */ bool rdma; @@ -1415,7 +1448,7 @@ struct cifs_fid { __u8 create_guid[16]; __u32 access; struct cifs_pending_open *pending_open; - unsigned int epoch; + __u16 epoch; #ifdef CONFIG_CIFS_DEBUG2 __u64 mid; #endif /* CIFS_DEBUG2 */ @@ -1448,7 +1481,7 @@ struct cifsFileInfo { bool oplock_break_cancelled:1; bool status_file_deleted:1; /* file has been deleted */ bool offload:1; /* offload final part of _put to a wq */ - unsigned int oplock_epoch; /* epoch from the lease break */ + __u16 oplock_epoch; /* epoch from the lease break */ __u32 oplock_level; /* oplock/lease level from the lease break */ int count; spinlock_t file_info_lock; /* protects four flag/count fields above */ @@ -1476,7 +1509,6 @@ struct cifs_io_parms { struct cifs_io_request { struct netfs_io_request rreq; struct cifsFileInfo *cfile; - struct TCP_Server_Info *server; pid_t pid; }; @@ -1545,7 +1577,7 @@ struct cifsInodeInfo { spinlock_t open_file_lock; /* protects openFileList */ __u32 cifsAttrs; /* e.g. DOS archive bit, sparse, compressed, system */ unsigned int oplock; /* oplock/lease level we have */ - unsigned int epoch; /* used to track lease state changes */ + __u16 epoch; /* used to track lease state changes */ #define CIFS_INODE_PENDING_OPLOCK_BREAK (0) /* oplock break in progress */ #define CIFS_INODE_PENDING_WRITERS (1) /* Writes in progress */ #define CIFS_INODE_FLAG_UNUSED (2) /* Unused flag */ @@ -2118,6 +2150,8 @@ static inline char *get_security_type_str(enum securityEnum sectype) return "Kerberos"; case NTLMv2: return "NTLMv2"; + case IAKerb: + return "IAKerb"; default: return "Unknown"; } @@ -2173,11 +2207,13 @@ static inline size_t ntlmssp_workstation_name_size(const struct cifs_ses *ses) static inline void move_cifs_info_to_smb2(struct smb2_file_all_info *dst, const FILE_ALL_INFO *src) { - memcpy(dst, src, (size_t)((u8 *)&src->AccessFlags - (u8 *)src)); - dst->AccessFlags = src->AccessFlags; - dst->CurrentByteOffset = src->CurrentByteOffset; - dst->Mode = src->Mode; - dst->AlignmentRequirement = src->AlignmentRequirement; + memcpy(dst, src, (size_t)((u8 *)&src->EASize - (u8 *)src)); + dst->IndexNumber = 0; + dst->EASize = src->EASize; + dst->AccessFlags = 0; + dst->CurrentByteOffset = 0; + dst->Mode = 0; + dst->AlignmentRequirement = 0; dst->FileNameLength = src->FileNameLength; } @@ -2289,8 +2325,8 @@ struct smb2_compound_vars { struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; struct kvec close_iov; - struct smb2_file_rename_info rename_info; - struct smb2_file_link_info link_info; + struct smb2_file_rename_info_hdr rename_info; + struct smb2_file_link_info_hdr link_info; struct kvec ea_iov; }; diff --git a/fs/smb/client/cifspdu.h b/fs/smb/client/cifspdu.h index 5c047b00516f..48d0d6f439cf 100644 --- a/fs/smb/client/cifspdu.h +++ b/fs/smb/client/cifspdu.h @@ -190,42 +190,82 @@ */ #define FILE_READ_DATA 0x00000001 /* Data can be read from the file */ + /* or directory child entries can */ + /* be listed together with the */ + /* associated child attributes */ + /* (so the FILE_READ_ATTRIBUTES on */ + /* the child entry is not needed) */ #define FILE_WRITE_DATA 0x00000002 /* Data can be written to the file */ + /* or new file can be created in */ + /* the directory */ #define FILE_APPEND_DATA 0x00000004 /* Data can be appended to the file */ + /* (for non-local files over SMB it */ + /* is same as FILE_WRITE_DATA) */ + /* or new subdirectory can be */ + /* created in the directory */ #define FILE_READ_EA 0x00000008 /* Extended attributes associated */ /* with the file can be read */ #define FILE_WRITE_EA 0x00000010 /* Extended attributes associated */ /* with the file can be written */ #define FILE_EXECUTE 0x00000020 /*Data can be read into memory from */ /* the file using system paging I/O */ -#define FILE_DELETE_CHILD 0x00000040 + /* for executing the file / script */ + /* or right to traverse directory */ + /* (but by default all users have */ + /* directory bypass traverse */ + /* privilege and do not need this */ + /* permission on directories at all)*/ +#define FILE_DELETE_CHILD 0x00000040 /* Child entry can be deleted from */ + /* the directory (so the DELETE on */ + /* the child entry is not needed) */ #define FILE_READ_ATTRIBUTES 0x00000080 /* Attributes associated with the */ - /* file can be read */ + /* file or directory can be read */ #define FILE_WRITE_ATTRIBUTES 0x00000100 /* Attributes associated with the */ - /* file can be written */ -#define DELETE 0x00010000 /* The file can be deleted */ -#define READ_CONTROL 0x00020000 /* The access control list and */ - /* ownership associated with the */ - /* file can be read */ -#define WRITE_DAC 0x00040000 /* The access control list and */ - /* ownership associated with the */ - /* file can be written. */ + /* file or directory can be written */ +#define DELETE 0x00010000 /* The file or dir can be deleted */ +#define READ_CONTROL 0x00020000 /* The discretionary access control */ + /* list and ownership associated */ + /* with the file or dir can be read */ +#define WRITE_DAC 0x00040000 /* The discretionary access control */ + /* list associated with the file or */ + /* directory can be written */ #define WRITE_OWNER 0x00080000 /* Ownership information associated */ - /* with the file can be written */ + /* with the file/dir can be written */ #define SYNCHRONIZE 0x00100000 /* The file handle can waited on to */ /* synchronize with the completion */ /* of an input/output request */ #define SYSTEM_SECURITY 0x01000000 /* The system access control list */ - /* can be read and changed */ -#define GENERIC_ALL 0x10000000 -#define GENERIC_EXECUTE 0x20000000 -#define GENERIC_WRITE 0x40000000 -#define GENERIC_READ 0x80000000 - /* In summary - Relevant file */ - /* access flags from CIFS are */ - /* file_read_data, file_write_data */ - /* file_execute, file_read_attributes*/ - /* write_dac, and delete. */ + /* associated with the file or */ + /* directory can be read or written */ + /* (cannot be in DACL, can in SACL) */ +#define MAXIMUM_ALLOWED 0x02000000 /* Maximal subset of GENERIC_ALL */ + /* permissions which can be granted */ + /* (cannot be in DACL nor SACL) */ +#define GENERIC_ALL 0x10000000 /* Same as: GENERIC_EXECUTE | */ + /* GENERIC_WRITE | */ + /* GENERIC_READ | */ + /* FILE_DELETE_CHILD | */ + /* DELETE | */ + /* WRITE_DAC | */ + /* WRITE_OWNER */ + /* So GENERIC_ALL contains all bits */ + /* mentioned above except these two */ + /* SYSTEM_SECURITY MAXIMUM_ALLOWED */ +#define GENERIC_EXECUTE 0x20000000 /* Same as: FILE_EXECUTE | */ + /* FILE_READ_ATTRIBUTES | */ + /* READ_CONTROL | */ + /* SYNCHRONIZE */ +#define GENERIC_WRITE 0x40000000 /* Same as: FILE_WRITE_DATA | */ + /* FILE_APPEND_DATA | */ + /* FILE_WRITE_EA | */ + /* FILE_WRITE_ATTRIBUTES | */ + /* READ_CONTROL | */ + /* SYNCHRONIZE */ +#define GENERIC_READ 0x80000000 /* Same as: FILE_READ_DATA | */ + /* FILE_READ_EA | */ + /* FILE_READ_ATTRIBUTES | */ + /* READ_CONTROL | */ + /* SYNCHRONIZE */ #define FILE_READ_RIGHTS (FILE_READ_DATA | FILE_READ_EA | FILE_READ_ATTRIBUTES) #define FILE_WRITE_RIGHTS (FILE_WRITE_DATA | FILE_APPEND_DATA \ @@ -1484,20 +1524,6 @@ struct file_notify_information { __u8 FileName[]; } __attribute__((packed)); -/* For IO_REPARSE_TAG_NFS */ -#define NFS_SPECFILE_LNK 0x00000000014B4E4C -#define NFS_SPECFILE_CHR 0x0000000000524843 -#define NFS_SPECFILE_BLK 0x00000000004B4C42 -#define NFS_SPECFILE_FIFO 0x000000004F464946 -#define NFS_SPECFILE_SOCK 0x000000004B434F53 -struct reparse_posix_data { - __le32 ReparseTag; - __le16 ReparseDataLength; - __u16 Reserved; - __le64 InodeType; /* LNK, FIFO, CHR etc. */ - __u8 DataBuffer[]; -} __attribute__((packed)); - struct cifs_quota_data { __u32 rsrvd1; /* 0 */ __u32 sid_size; @@ -2264,13 +2290,7 @@ typedef struct { /* data block encoding of response to level 263 QPathInfo */ __u8 DeletePending; __u8 Directory; __u16 Pad2; - __le64 IndexNumber; __le32 EASize; - __le32 AccessFlags; - __u64 IndexNumber1; - __le64 CurrentByteOffset; - __le32 Mode; - __le32 AlignmentRequirement; __le32 FileNameLength; union { char __pad; diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 223e5e231f42..81680001944d 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -557,7 +557,7 @@ extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon, const struct nls_table *nls_codepage, struct cifs_sb_info *cifs_sb); extern int CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, - __u16 fid, struct smb_ntsd **acl_inf, __u32 *buflen); + __u16 fid, struct smb_ntsd **acl_inf, __u32 *buflen, __u32 info); extern int CIFSSMBSetCIFSACL(const unsigned int, struct cifs_tcon *, __u16, struct smb_ntsd *pntsd, __u32 len, int aclflag); extern int cifs_do_get_acl(const unsigned int xid, struct cifs_tcon *tcon, @@ -656,7 +656,7 @@ char *extract_sharename(const char *unc); int parse_reparse_point(struct reparse_data_buffer *buf, u32 plen, struct cifs_sb_info *cifs_sb, const char *full_path, - bool unicode, struct cifs_open_info_data *data); + struct cifs_open_info_data *data); int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, umode_t mode, dev_t dev, diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 7f1cacc89dbb..3feaa0f68169 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -3369,7 +3369,7 @@ validate_ntransact(char *buf, char **ppparm, char **ppdata, /* Get Security Descriptor (by handle) from remote server for a file or dir */ int CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, - struct smb_ntsd **acl_inf, __u32 *pbuflen) + struct smb_ntsd **acl_inf, __u32 *pbuflen, __u32 info) { int rc = 0; int buf_type = 0; @@ -3392,7 +3392,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid, pSMB->MaxSetupCount = 0; pSMB->Fid = fid; /* file handle always le */ pSMB->AclFlags = cpu_to_le32(CIFS_ACL_OWNER | CIFS_ACL_GROUP | - CIFS_ACL_DACL); + CIFS_ACL_DACL | info); pSMB->ByteCount = cpu_to_le16(11); /* 3 bytes pad + 8 bytes parm */ inc_rfc1001_len(pSMB, 11); iov[0].iov_base = (char *)pSMB; diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 880d7cf8b730..f917de020dd5 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -2849,6 +2849,10 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) return 0; if (old->ctx->reparse_type != new->ctx->reparse_type) return 0; + if (old->ctx->nonativesocket != new->ctx->nonativesocket) + return 0; + if (old->ctx->symlink_type != new->ctx->symlink_type) + return 0; return 1; } diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index dad521336b5e..f65a8a90ba27 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -150,25 +150,27 @@ again: if (rc) continue; - if (tgt.flags & DFSREF_STORAGE_SERVER) { - rc = cifs_mount_get_tcon(mnt_ctx); - if (!rc) - rc = cifs_is_path_remote(mnt_ctx); + rc = cifs_mount_get_tcon(mnt_ctx); + if (rc) { + if (tgt.server_type == DFS_TYPE_LINK && + DFS_INTERLINK(tgt.flags)) + rc = -EREMOTE; + } else { + rc = cifs_is_path_remote(mnt_ctx); if (!rc) { ref_walk_set_tgt_hint(rw); break; } - if (rc != -EREMOTE) - continue; } - - rc = ref_walk_advance(rw); - if (!rc) { - rc = setup_dfs_ref(&tgt, rw); - if (rc) - break; - ref_walk_mark_end(rw); - goto again; + if (rc == -EREMOTE) { + rc = ref_walk_advance(rw); + if (!rc) { + rc = setup_dfs_ref(&tgt, rw); + if (rc) + break; + ref_walk_mark_end(rw); + goto again; + } } } } while (rc && ref_walk_descend(rw)); diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h index ed4cd7cf1ec6..e60f0a24a8a1 100644 --- a/fs/smb/client/dfs.h +++ b/fs/smb/client/dfs.h @@ -188,4 +188,11 @@ static inline void dfs_put_root_smb_sessions(struct list_head *head) } } +static inline const char *dfs_ses_refpath(struct cifs_ses *ses) +{ + const char *path = ses->server->leaf_fullpath; + + return path ? path + 1 : ERR_PTR(-ENOENT); +} + #endif /* _CIFS_DFS_H */ diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 5022bb1f122a..4dada26d56b5 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1136,33 +1136,19 @@ static bool is_ses_good(struct cifs_ses *ses) return ret; } -static char *get_ses_refpath(struct cifs_ses *ses) -{ - struct TCP_Server_Info *server = ses->server; - char *path = ERR_PTR(-ENOENT); - - if (server->leaf_fullpath) { - path = kstrdup(server->leaf_fullpath + 1, GFP_KERNEL); - if (!path) - path = ERR_PTR(-ENOMEM); - } - return path; -} - /* Refresh dfs referral of @ses */ static void refresh_ses_referral(struct cifs_ses *ses) { struct cache_entry *ce; unsigned int xid; - char *path; + const char *path; int rc = 0; xid = get_xid(); - path = get_ses_refpath(ses); + path = dfs_ses_refpath(ses); if (IS_ERR(path)) { rc = PTR_ERR(path); - path = NULL; goto out; } @@ -1181,7 +1167,6 @@ static void refresh_ses_referral(struct cifs_ses *ses) out: free_xid(xid); - kfree(path); } static int __refresh_tcon_referral(struct cifs_tcon *tcon, @@ -1231,19 +1216,18 @@ static void refresh_tcon_referral(struct cifs_tcon *tcon, bool force_refresh) struct dfs_info3_param *refs = NULL; struct cache_entry *ce; struct cifs_ses *ses; - unsigned int xid; bool needs_refresh; - char *path; + const char *path; + unsigned int xid; int numrefs = 0; int rc = 0; xid = get_xid(); ses = tcon->ses; - path = get_ses_refpath(ses); + path = dfs_ses_refpath(ses); if (IS_ERR(path)) { rc = PTR_ERR(path); - path = NULL; goto out; } @@ -1271,7 +1255,6 @@ static void refresh_tcon_referral(struct cifs_tcon *tcon, bool force_refresh) out: free_xid(xid); - kfree(path); free_dfs_info_array(refs, numrefs); } diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index 1822493dd084..d1e95632ac54 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -737,7 +737,8 @@ again: } static int -cifs_d_revalidate(struct dentry *direntry, unsigned int flags) +cifs_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *direntry, unsigned int flags) { struct inode *inode; int rc; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 79de2f2f9c41..8582cf61242c 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -147,7 +147,7 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq) struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); - struct TCP_Server_Info *server = req->server; + struct TCP_Server_Info *server; struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); size_t size; int rc = 0; @@ -156,6 +156,8 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq) rdata->xid = get_xid(); rdata->have_xid = true; } + + server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); rdata->server = server; if (cifs_sb->ctx->rsize == 0) @@ -198,7 +200,7 @@ static void cifs_issue_read(struct netfs_io_subrequest *subreq) struct netfs_io_request *rreq = subreq->rreq; struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq); struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq); - struct TCP_Server_Info *server = req->server; + struct TCP_Server_Info *server = rdata->server; int rc = 0; cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n", @@ -266,7 +268,6 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file) open_file = file->private_data; rreq->netfs_priv = file->private_data; req->cfile = cifsFileInfo_get(open_file); - req->server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses); if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) req->pid = req->cfile->pid; } else if (rreq->origin != NETFS_WRITEBACK) { diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 5381f05420bc..e9b286d9a7ba 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -133,6 +133,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_flag("rootfs", Opt_rootfs), fsparam_flag("compress", Opt_compress), fsparam_flag("witness", Opt_witness), + fsparam_flag_no("nativesocket", Opt_nativesocket), /* Mount options which take uid or gid */ fsparam_uid("backupuid", Opt_backupuid), @@ -185,6 +186,8 @@ const struct fs_parameter_spec smb3_fs_parameters[] = { fsparam_string("cache", Opt_cache), fsparam_string("reparse", Opt_reparse), fsparam_string("upcall_target", Opt_upcalltarget), + fsparam_string("symlink", Opt_symlink), + fsparam_string("symlinkroot", Opt_symlinkroot), /* Arguments that should be ignored */ fsparam_flag("guest", Opt_ignore), @@ -332,6 +335,7 @@ cifs_parse_cache_flavor(struct fs_context *fc, char *value, struct smb3_fs_conte static const match_table_t reparse_flavor_tokens = { { Opt_reparse_default, "default" }, + { Opt_reparse_none, "none" }, { Opt_reparse_nfs, "nfs" }, { Opt_reparse_wsl, "wsl" }, { Opt_reparse_err, NULL }, @@ -346,6 +350,9 @@ static int parse_reparse_flavor(struct fs_context *fc, char *value, case Opt_reparse_default: ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; break; + case Opt_reparse_none: + ctx->reparse_type = CIFS_REPARSE_TYPE_NONE; + break; case Opt_reparse_nfs: ctx->reparse_type = CIFS_REPARSE_TYPE_NFS; break; @@ -359,6 +366,55 @@ static int parse_reparse_flavor(struct fs_context *fc, char *value, return 0; } +static const match_table_t symlink_flavor_tokens = { + { Opt_symlink_default, "default" }, + { Opt_symlink_none, "none" }, + { Opt_symlink_native, "native" }, + { Opt_symlink_unix, "unix" }, + { Opt_symlink_mfsymlinks, "mfsymlinks" }, + { Opt_symlink_sfu, "sfu" }, + { Opt_symlink_nfs, "nfs" }, + { Opt_symlink_wsl, "wsl" }, + { Opt_symlink_err, NULL }, +}; + +static int parse_symlink_flavor(struct fs_context *fc, char *value, + struct smb3_fs_context *ctx) +{ + substring_t args[MAX_OPT_ARGS]; + + switch (match_token(value, symlink_flavor_tokens, args)) { + case Opt_symlink_default: + ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; + break; + case Opt_symlink_none: + ctx->symlink_type = CIFS_SYMLINK_TYPE_NONE; + break; + case Opt_symlink_native: + ctx->symlink_type = CIFS_SYMLINK_TYPE_NATIVE; + break; + case Opt_symlink_unix: + ctx->symlink_type = CIFS_SYMLINK_TYPE_UNIX; + break; + case Opt_symlink_mfsymlinks: + ctx->symlink_type = CIFS_SYMLINK_TYPE_MFSYMLINKS; + break; + case Opt_symlink_sfu: + ctx->symlink_type = CIFS_SYMLINK_TYPE_SFU; + break; + case Opt_symlink_nfs: + ctx->symlink_type = CIFS_SYMLINK_TYPE_NFS; + break; + case Opt_symlink_wsl: + ctx->symlink_type = CIFS_SYMLINK_TYPE_WSL; + break; + default: + cifs_errorf(fc, "bad symlink= option: %s\n", value); + return 1; + } + return 0; +} + #define DUP_CTX_STR(field) \ do { \ if (ctx->field) { \ @@ -386,6 +442,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx new_ctx->iocharset = NULL; new_ctx->leaf_fullpath = NULL; new_ctx->dns_dom = NULL; + new_ctx->symlinkroot = NULL; /* * Make sure to stay in sync with smb3_cleanup_fs_context_contents() */ @@ -401,6 +458,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(iocharset); DUP_CTX_STR(leaf_fullpath); DUP_CTX_STR(dns_dom); + DUP_CTX_STR(symlinkroot); return 0; } @@ -1727,6 +1785,23 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, if (parse_reparse_flavor(fc, param->string, ctx)) goto cifs_parse_mount_err; break; + case Opt_nativesocket: + ctx->nonativesocket = result.negated; + break; + case Opt_symlink: + if (parse_symlink_flavor(fc, param->string, ctx)) + goto cifs_parse_mount_err; + break; + case Opt_symlinkroot: + if (param->string[0] != '/') { + cifs_errorf(fc, "symlinkroot mount options must be absolute path\n"); + goto cifs_parse_mount_err; + } + kfree(ctx->symlinkroot); + ctx->symlinkroot = kstrdup(param->string, GFP_KERNEL); + if (!ctx->symlinkroot) + goto cifs_parse_mount_err; + break; } /* case Opt_ignore: - is ignored as expected ... */ @@ -1735,6 +1810,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, goto cifs_parse_mount_err; } + /* + * By default resolve all native absolute symlinks relative to "/mnt/". + * Same default has drvfs driver running in WSL for resolving SMB shares. + */ + if (!ctx->symlinkroot) + ctx->symlinkroot = kstrdup("/mnt/", GFP_KERNEL); + return 0; cifs_parse_mount_err: @@ -1745,6 +1827,24 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, return -EINVAL; } +enum cifs_symlink_type get_cifs_symlink_type(struct cifs_sb_info *cifs_sb) +{ + if (cifs_sb->ctx->symlink_type == CIFS_SYMLINK_TYPE_DEFAULT) { + if (cifs_sb->ctx->mfsymlinks) + return CIFS_SYMLINK_TYPE_MFSYMLINKS; + else if (cifs_sb->ctx->sfu_emul) + return CIFS_SYMLINK_TYPE_SFU; + else if (cifs_sb->ctx->linux_ext && !cifs_sb->ctx->no_linux_ext) + return CIFS_SYMLINK_TYPE_UNIX; + else if (cifs_sb->ctx->reparse_type != CIFS_REPARSE_TYPE_NONE) + return CIFS_SYMLINK_TYPE_NATIVE; + else + return CIFS_SYMLINK_TYPE_NONE; + } else { + return cifs_sb->ctx->symlink_type; + } +} + int smb3_init_fs_context(struct fs_context *fc) { struct smb3_fs_context *ctx; @@ -1821,6 +1921,8 @@ int smb3_init_fs_context(struct fs_context *fc) ctx->retrans = 1; ctx->reparse_type = CIFS_REPARSE_TYPE_DEFAULT; + ctx->symlink_type = CIFS_SYMLINK_TYPE_DEFAULT; + ctx->nonativesocket = 0; /* * short int override_uid = -1; @@ -1867,6 +1969,8 @@ smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx) ctx->leaf_fullpath = NULL; kfree(ctx->dns_dom); ctx->dns_dom = NULL; + kfree(ctx->symlinkroot); + ctx->symlinkroot = NULL; } void diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 8813533345ee..881bfc08667e 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -43,11 +43,24 @@ enum { enum cifs_reparse_parm { Opt_reparse_default, + Opt_reparse_none, Opt_reparse_nfs, Opt_reparse_wsl, Opt_reparse_err }; +enum cifs_symlink_parm { + Opt_symlink_default, + Opt_symlink_none, + Opt_symlink_native, + Opt_symlink_unix, + Opt_symlink_mfsymlinks, + Opt_symlink_sfu, + Opt_symlink_nfs, + Opt_symlink_wsl, + Opt_symlink_err +}; + enum cifs_sec_param { Opt_sec_krb5, Opt_sec_krb5i, @@ -166,6 +179,9 @@ enum cifs_param { Opt_cache, Opt_reparse, Opt_upcalltarget, + Opt_nativesocket, + Opt_symlink, + Opt_symlinkroot, /* Mount options to be ignored */ Opt_ignore, @@ -294,12 +310,17 @@ struct smb3_fs_context { struct cifs_ses *dfs_root_ses; bool dfs_automount:1; /* set for dfs automount only */ enum cifs_reparse_type reparse_type; + enum cifs_symlink_type symlink_type; + bool nonativesocket:1; bool dfs_conn:1; /* set for dfs mounts */ char *dns_dom; + char *symlinkroot; /* top level directory for native SMB symlinks in absolute format */ }; extern const struct fs_parameter_spec smb3_fs_parameters[]; +extern enum cifs_symlink_type get_cifs_symlink_type(struct cifs_sb_info *cifs_sb); + extern int smb3_init_fs_context(struct fs_context *fc); extern void smb3_cleanup_fs_context_contents(struct smb3_fs_context *ctx); extern void smb3_cleanup_fs_context(struct smb3_fs_context *ctx); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 93e9188b2632..616149c7f0a5 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -990,7 +990,7 @@ cifs_get_file_info(struct file *filp) /* TODO: add support to query reparse tag */ data.adjust_tz = false; if (data.symlink_target) { - data.symlink = true; + data.reparse_point = true; data.reparse.tag = IO_REPARSE_TAG_SYMLINK; } path = build_path_from_dentry(dentry, page); @@ -1215,6 +1215,24 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data, rc = server->ops->parse_reparse_point(cifs_sb, full_path, iov, data); + /* + * If the reparse point was not handled but it is the + * name surrogate which points to directory, then treat + * is as a new mount point. Name surrogate reparse point + * represents another named entity in the system. + */ + if (rc == -EOPNOTSUPP && + IS_REPARSE_TAG_NAME_SURROGATE(data->reparse.tag) && + (le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY)) { + rc = 0; + cifs_create_junction_fattr(fattr, sb); + goto out; + } + } + + if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) { + bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY; + rc = smb2_fix_symlink_target_type(&data->symlink_target, directory, cifs_sb); } break; } @@ -1403,7 +1421,7 @@ int cifs_get_inode_info(struct inode **inode, struct cifs_fattr fattr = {}; int rc; - if (is_inode_cache_good(*inode)) { + if (!data && is_inode_cache_good(*inode)) { cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); return 0; } @@ -1502,7 +1520,7 @@ int smb311_posix_get_inode_info(struct inode **inode, struct cifs_fattr fattr = {}; int rc; - if (is_inode_cache_good(*inode)) { + if (!data && is_inode_cache_good(*inode)) { cifs_dbg(FYI, "No need to revalidate cached inode sizes\n"); return 0; } diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c index 47ddeb7fa111..6e6c09cc5ce7 100644 --- a/fs/smb/client/link.c +++ b/fs/smb/client/link.c @@ -18,6 +18,7 @@ #include "cifs_unicode.h" #include "smb2proto.h" #include "cifs_ioctl.h" +#include "fs_context.h" /* * M-F Symlink Functions - Begin @@ -604,22 +605,53 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, cifs_dbg(FYI, "symname is %s\n", symname); /* BB what if DFS and this volume is on different share? BB */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { - rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname); - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { - rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon, - full_path, S_IFLNK, 0, symname); + rc = -EOPNOTSUPP; + switch (get_cifs_symlink_type(cifs_sb)) { + case CIFS_SYMLINK_TYPE_DEFAULT: + /* should not happen, get_cifs_symlink_type() resolves the default */ + break; + + case CIFS_SYMLINK_TYPE_NONE: + break; + + case CIFS_SYMLINK_TYPE_UNIX: #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY - } else if (pTcon->unix_ext) { - rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, symname, - cifs_sb->local_nls, - cifs_remap(cifs_sb)); + if (pTcon->unix_ext) { + rc = CIFSUnixCreateSymLink(xid, pTcon, full_path, + symname, + cifs_sb->local_nls, + cifs_remap(cifs_sb)); + } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - } else if (server->ops->create_reparse_symlink) { - rc = server->ops->create_reparse_symlink(xid, inode, direntry, - pTcon, full_path, - symname); - goto symlink_exit; + break; + + case CIFS_SYMLINK_TYPE_MFSYMLINKS: + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + rc = create_mf_symlink(xid, pTcon, cifs_sb, + full_path, symname); + } + break; + + case CIFS_SYMLINK_TYPE_SFU: + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { + rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon, + full_path, S_IFLNK, + 0, symname); + } + break; + + case CIFS_SYMLINK_TYPE_NATIVE: + case CIFS_SYMLINK_TYPE_NFS: + case CIFS_SYMLINK_TYPE_WSL: + if (server->ops->create_reparse_symlink) { + rc = server->ops->create_reparse_symlink(xid, inode, + direntry, + pTcon, + full_path, + symname); + goto symlink_exit; + } + break; } if (rc == 0) { diff --git a/fs/smb/client/netmisc.c b/fs/smb/client/netmisc.c index 17b3e21ea868..9ec20601cee2 100644 --- a/fs/smb/client/netmisc.c +++ b/fs/smb/client/netmisc.c @@ -313,7 +313,6 @@ static const struct { ERRDOS, 2215, NT_STATUS_NO_LOGON_SERVERS}, { ERRHRD, ERRgeneral, NT_STATUS_NO_SUCH_LOGON_SESSION}, { ERRHRD, ERRgeneral, NT_STATUS_NO_SUCH_PRIVILEGE}, { - ERRDOS, ERRnoaccess, NT_STATUS_PRIVILEGE_NOT_HELD}, { ERRHRD, ERRgeneral, NT_STATUS_INVALID_ACCOUNT_NAME}, { ERRHRD, ERRgeneral, NT_STATUS_USER_EXISTS}, /* { This NT error code was 'sqashed' @@ -871,6 +870,15 @@ map_smb_to_linux_error(char *buf, bool logErr) } /* else ERRHRD class errors or junk - return EIO */ + /* special cases for NT status codes which cannot be translated to DOS codes */ + if (smb->Flags2 & SMBFLG2_ERR_STATUS) { + __u32 err = le32_to_cpu(smb->Status.CifsError); + if (err == (NT_STATUS_NOT_A_REPARSE_POINT)) + rc = -ENODATA; + else if (err == (NT_STATUS_PRIVILEGE_NOT_HELD)) + rc = -EPERM; + } + cifs_dbg(FYI, "Mapping smb error code 0x%x to POSIX err %d\n", le32_to_cpu(smb->Status.CifsError), rc); diff --git a/fs/smb/client/nterr.c b/fs/smb/client/nterr.c index d396a8e98a81..8f0bc441295e 100644 --- a/fs/smb/client/nterr.c +++ b/fs/smb/client/nterr.c @@ -674,6 +674,7 @@ const struct nt_err_code_struct nt_errs[] = { {"NT_STATUS_QUOTA_LIST_INCONSISTENT", NT_STATUS_QUOTA_LIST_INCONSISTENT}, {"NT_STATUS_FILE_IS_OFFLINE", NT_STATUS_FILE_IS_OFFLINE}, + {"NT_STATUS_NOT_A_REPARSE_POINT", NT_STATUS_NOT_A_REPARSE_POINT}, {"NT_STATUS_NO_MORE_ENTRIES", NT_STATUS_NO_MORE_ENTRIES}, {"NT_STATUS_MORE_ENTRIES", NT_STATUS_MORE_ENTRIES}, {"NT_STATUS_SOME_UNMAPPED", NT_STATUS_SOME_UNMAPPED}, diff --git a/fs/smb/client/nterr.h b/fs/smb/client/nterr.h index edd4741cab0a..180602c22355 100644 --- a/fs/smb/client/nterr.h +++ b/fs/smb/client/nterr.h @@ -546,6 +546,7 @@ extern const struct nt_err_code_struct nt_errs[]; #define NT_STATUS_TOO_MANY_LINKS 0xC0000000 | 0x0265 #define NT_STATUS_QUOTA_LIST_INCONSISTENT 0xC0000000 | 0x0266 #define NT_STATUS_FILE_IS_OFFLINE 0xC0000000 | 0x0267 +#define NT_STATUS_NOT_A_REPARSE_POINT 0xC0000000 | 0x0275 #define NT_STATUS_NO_SUCH_JOB 0xC0000000 | 0xEDE /* scheduler */ #endif /* _NTERR_H */ diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index d88b41133e00..2b9e9885dc42 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -14,6 +14,20 @@ #include "fs_context.h" #include "reparse.h" +static int mknod_nfs(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev, + const char *symname); + +static int mknod_wsl(unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, umode_t mode, dev_t dev, + const char *symname); + +static int create_native_symlink(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, const char *symname); + static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb, const unsigned int xid, const char *full_path, @@ -24,37 +38,148 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, const char *symname) { + switch (get_cifs_symlink_type(CIFS_SB(inode->i_sb))) { + case CIFS_SYMLINK_TYPE_NATIVE: + return create_native_symlink(xid, inode, dentry, tcon, full_path, symname); + case CIFS_SYMLINK_TYPE_NFS: + return mknod_nfs(xid, inode, dentry, tcon, full_path, S_IFLNK, 0, symname); + case CIFS_SYMLINK_TYPE_WSL: + return mknod_wsl(xid, inode, dentry, tcon, full_path, S_IFLNK, 0, symname); + default: + return -EOPNOTSUPP; + } +} + +static int create_native_symlink(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path, const char *symname) +{ struct reparse_symlink_data_buffer *buf = NULL; - struct cifs_open_info_data data; + struct cifs_open_info_data data = {}; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct inode *new; struct kvec iov; - __le16 *path; + __le16 *path = NULL; bool directory; - char *sym, sep = CIFS_DIR_SEP(cifs_sb); - u16 len, plen; + char *symlink_target = NULL; + char *sym = NULL; + char sep = CIFS_DIR_SEP(cifs_sb); + u16 len, plen, poff, slen; int rc = 0; if (strlen(symname) > REPARSE_SYM_PATH_MAX) return -ENAMETOOLONG; - sym = kstrdup(symname, GFP_KERNEL); - if (!sym) - return -ENOMEM; + symlink_target = kstrdup(symname, GFP_KERNEL); + if (!symlink_target) { + rc = -ENOMEM; + goto out; + } data = (struct cifs_open_info_data) { .reparse_point = true, .reparse = { .tag = IO_REPARSE_TAG_SYMLINK, }, - .symlink_target = sym, + .symlink_target = symlink_target, }; - convert_delimiter(sym, sep); + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + /* + * This is a request to create an absolute symlink on the server + * which does not support POSIX paths, and expects symlink in + * NT-style path. So convert absolute Linux symlink target path + * to the absolute NT-style path. Root of the NT-style path for + * symlinks is specified in "symlinkroot" mount option. This will + * ensure compatibility of this symlink stored in absolute form + * on the SMB server. + */ + if (!strstarts(symname, cifs_sb->ctx->symlinkroot)) { + /* + * If the absolute Linux symlink target path is not + * inside "symlinkroot" location then there is no way + * to convert such Linux symlink to NT-style path. + */ + cifs_dbg(VFS, + "absolute symlink '%s' cannot be converted to NT format " + "because it is outside of symlinkroot='%s'\n", + symname, cifs_sb->ctx->symlinkroot); + rc = -EINVAL; + goto out; + } + len = strlen(cifs_sb->ctx->symlinkroot); + if (cifs_sb->ctx->symlinkroot[len-1] != '/') + len++; + if (symname[len] >= 'a' && symname[len] <= 'z' && + (symname[len+1] == '/' || symname[len+1] == '\0')) { + /* + * Symlink points to Linux target /symlinkroot/x/path/... + * where 'x' is the lowercase local Windows drive. + * NT-style path for 'x' has common form \??\X:\path\... + * with uppercase local Windows drive. + */ + int common_path_len = strlen(symname+len+1)+1; + sym = kzalloc(6+common_path_len, GFP_KERNEL); + if (!sym) { + rc = -ENOMEM; + goto out; + } + memcpy(sym, "\\??\\", 4); + sym[4] = symname[len] - ('a'-'A'); + sym[5] = ':'; + memcpy(sym+6, symname+len+1, common_path_len); + } else { + /* Unhandled absolute symlink. Report an error. */ + cifs_dbg( + VFS, + "absolute symlink '%s' cannot be converted to NT format " + "because it points to unknown target\n", + symname); + rc = -EINVAL; + goto out; + } + } else { + /* + * This is request to either create an absolute symlink on + * server which expects POSIX paths or it is an request to + * create a relative symlink from the current directory. + * These paths have same format as relative SMB symlinks, + * so no conversion is needed. So just take symname as-is. + */ + sym = kstrdup(symname, GFP_KERNEL); + if (!sym) { + rc = -ENOMEM; + goto out; + } + } + + if (sep == '\\') + convert_delimiter(sym, sep); + + /* + * For absolute NT symlinks it is required to pass also leading + * backslash and to not mangle NT object prefix "\\??\\" and not to + * mangle colon in drive letter. But cifs_convert_path_to_utf16() + * removes leading backslash and replaces '?' and ':'. So temporary + * mask these characters in NT object prefix by '_' and then change + * them back. + */ + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') + sym[0] = sym[1] = sym[2] = sym[5] = '_'; + path = cifs_convert_path_to_utf16(sym, cifs_sb); if (!path) { rc = -ENOMEM; goto out; } + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + sym[0] = '\\'; + sym[1] = sym[2] = '?'; + sym[5] = ':'; + path[0] = cpu_to_le16('\\'); + path[1] = path[2] = cpu_to_le16('?'); + path[5] = cpu_to_le16(':'); + } + /* * SMB distinguish between symlink to directory and symlink to file. * They cannot be exchanged (symlink of file type which points to @@ -67,8 +192,18 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, if (rc < 0) goto out; - plen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX); - len = sizeof(*buf) + plen * 2; + slen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX); + poff = 0; + plen = slen; + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + /* + * For absolute NT symlinks skip leading "\\??\\" in PrintName as + * PrintName is user visible location in DOS/Win32 format (not in NT format). + */ + poff = 4; + plen -= 2 * poff; + } + len = sizeof(*buf) + plen + slen; buf = kzalloc(len, GFP_KERNEL); if (!buf) { rc = -ENOMEM; @@ -77,17 +212,17 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, buf->ReparseTag = cpu_to_le32(IO_REPARSE_TAG_SYMLINK); buf->ReparseDataLength = cpu_to_le16(len - sizeof(struct reparse_data_buffer)); + buf->SubstituteNameOffset = cpu_to_le16(plen); - buf->SubstituteNameLength = cpu_to_le16(plen); - memcpy(&buf->PathBuffer[plen], path, plen); + buf->SubstituteNameLength = cpu_to_le16(slen); + memcpy(&buf->PathBuffer[plen], path, slen); + buf->PrintNameOffset = 0; buf->PrintNameLength = cpu_to_le16(plen); - memcpy(buf->PathBuffer, path, plen); + memcpy(buf->PathBuffer, path+poff, plen); + buf->Flags = cpu_to_le32(*symname != '/' ? SYMLINK_FLAG_RELATIVE : 0); - if (*sym != sep) - buf->Flags = cpu_to_le32(SYMLINK_FLAG_RELATIVE); - convert_delimiter(sym, '/'); iov.iov_base = buf; iov.iov_len = len; new = smb2_get_reparse_inode(&data, inode->i_sb, xid, @@ -98,6 +233,7 @@ int smb2_create_reparse_symlink(const unsigned int xid, struct inode *inode, else rc = PTR_ERR(new); out: + kfree(sym); kfree(path); cifs_free_open_info(&data); kfree(buf); @@ -242,8 +378,39 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb, return 0; } -static int nfs_set_reparse_buf(struct reparse_posix_data *buf, +static int create_native_socket(const unsigned int xid, struct inode *inode, + struct dentry *dentry, struct cifs_tcon *tcon, + const char *full_path) +{ + struct reparse_data_buffer buf = { + .ReparseTag = cpu_to_le32(IO_REPARSE_TAG_AF_UNIX), + .ReparseDataLength = cpu_to_le16(0), + }; + struct cifs_open_info_data data = { + .reparse_point = true, + .reparse = { .tag = IO_REPARSE_TAG_AF_UNIX, .buf = &buf, }, + }; + struct kvec iov = { + .iov_base = &buf, + .iov_len = sizeof(buf), + }; + struct inode *new; + int rc = 0; + + new = smb2_get_reparse_inode(&data, inode->i_sb, xid, + tcon, full_path, false, &iov, NULL); + if (!IS_ERR(new)) + d_instantiate(dentry, new); + else + rc = PTR_ERR(new); + cifs_free_open_info(&data); + return rc; +} + +static int nfs_set_reparse_buf(struct reparse_nfs_data_buffer *buf, mode_t mode, dev_t dev, + __le16 *symname_utf16, + int symname_utf16_len, struct kvec *iov) { u64 type; @@ -254,7 +421,13 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf, switch ((type = reparse_mode_nfs_type(mode))) { case NFS_SPECFILE_BLK: case NFS_SPECFILE_CHR: - dlen = sizeof(__le64); + dlen = 2 * sizeof(__le32); + ((__le32 *)buf->DataBuffer)[0] = cpu_to_le32(MAJOR(dev)); + ((__le32 *)buf->DataBuffer)[1] = cpu_to_le32(MINOR(dev)); + break; + case NFS_SPECFILE_LNK: + dlen = symname_utf16_len; + memcpy(buf->DataBuffer, symname_utf16, symname_utf16_len); break; case NFS_SPECFILE_FIFO: case NFS_SPECFILE_SOCK: @@ -269,8 +442,6 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf, buf->InodeType = cpu_to_le64(type); buf->ReparseDataLength = cpu_to_le16(len + dlen - sizeof(struct reparse_data_buffer)); - *(__le64 *)buf->DataBuffer = cpu_to_le64(((u64)MINOR(dev) << 32) | - MAJOR(dev)); iov->iov_base = buf; iov->iov_len = len + dlen; return 0; @@ -278,23 +449,45 @@ static int nfs_set_reparse_buf(struct reparse_posix_data *buf, static int mknod_nfs(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, - const char *full_path, umode_t mode, dev_t dev) + const char *full_path, umode_t mode, dev_t dev, + const char *symname) { + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_open_info_data data; - struct reparse_posix_data *p; + struct reparse_nfs_data_buffer *p = NULL; + __le16 *symname_utf16 = NULL; + int symname_utf16_len = 0; struct inode *new; struct kvec iov; __u8 buf[sizeof(*p) + sizeof(__le64)]; int rc; - p = (struct reparse_posix_data *)buf; - rc = nfs_set_reparse_buf(p, mode, dev, &iov); + if (S_ISLNK(mode)) { + symname_utf16 = cifs_strndup_to_utf16(symname, strlen(symname), + &symname_utf16_len, + cifs_sb->local_nls, + NO_MAP_UNI_RSVD); + if (!symname_utf16) { + rc = -ENOMEM; + goto out; + } + symname_utf16_len -= 2; /* symlink is without trailing wide-nul */ + p = kzalloc(sizeof(*p) + symname_utf16_len, GFP_KERNEL); + if (!p) { + rc = -ENOMEM; + goto out; + } + } else { + p = (struct reparse_nfs_data_buffer *)buf; + } + rc = nfs_set_reparse_buf(p, mode, dev, symname_utf16, symname_utf16_len, &iov); if (rc) - return rc; + goto out; data = (struct cifs_open_info_data) { .reparse_point = true, - .reparse = { .tag = IO_REPARSE_TAG_NFS, .posix = p, }, + .reparse = { .tag = IO_REPARSE_TAG_NFS, .buf = (struct reparse_data_buffer *)p, }, + .symlink_target = kstrdup(symname, GFP_KERNEL), }; new = smb2_get_reparse_inode(&data, inode->i_sb, xid, @@ -304,12 +497,25 @@ static int mknod_nfs(unsigned int xid, struct inode *inode, else rc = PTR_ERR(new); cifs_free_open_info(&data); +out: + if (S_ISLNK(mode)) { + kfree(symname_utf16); + kfree(p); + } return rc; } -static int wsl_set_reparse_buf(struct reparse_data_buffer *buf, - mode_t mode, struct kvec *iov) +static int wsl_set_reparse_buf(struct reparse_data_buffer **buf, + mode_t mode, const char *symname, + struct cifs_sb_info *cifs_sb, + struct kvec *iov) { + struct reparse_wsl_symlink_data_buffer *symlink_buf; + __le16 *symname_utf16; + int symname_utf16_len; + int symname_utf8_maxlen; + int symname_utf8_len; + size_t buf_len; u32 tag; switch ((tag = reparse_mode_wsl_tag(mode))) { @@ -317,16 +523,45 @@ static int wsl_set_reparse_buf(struct reparse_data_buffer *buf, case IO_REPARSE_TAG_LX_CHR: case IO_REPARSE_TAG_LX_FIFO: case IO_REPARSE_TAG_AF_UNIX: + buf_len = sizeof(struct reparse_data_buffer); + *buf = kzalloc(buf_len, GFP_KERNEL); + if (!*buf) + return -ENOMEM; + break; + case IO_REPARSE_TAG_LX_SYMLINK: + symname_utf16 = cifs_strndup_to_utf16(symname, strlen(symname), + &symname_utf16_len, + cifs_sb->local_nls, + NO_MAP_UNI_RSVD); + if (!symname_utf16) + return -ENOMEM; + symname_utf8_maxlen = symname_utf16_len/2*3; + symlink_buf = kzalloc(sizeof(struct reparse_wsl_symlink_data_buffer) + + symname_utf8_maxlen, GFP_KERNEL); + if (!symlink_buf) { + kfree(symname_utf16); + return -ENOMEM; + } + /* Flag 0x02000000 is unknown, but all wsl symlinks have this value */ + symlink_buf->Flags = cpu_to_le32(0x02000000); + /* PathBuffer is in UTF-8 but without trailing null-term byte */ + symname_utf8_len = utf16s_to_utf8s((wchar_t *)symname_utf16, symname_utf16_len/2, + UTF16_LITTLE_ENDIAN, + symlink_buf->PathBuffer, + symname_utf8_maxlen); + *buf = (struct reparse_data_buffer *)symlink_buf; + buf_len = sizeof(struct reparse_wsl_symlink_data_buffer) + symname_utf8_len; + kfree(symname_utf16); break; default: return -EOPNOTSUPP; } - buf->ReparseTag = cpu_to_le32(tag); - buf->Reserved = 0; - buf->ReparseDataLength = 0; - iov->iov_base = buf; - iov->iov_len = sizeof(*buf); + (*buf)->ReparseTag = cpu_to_le32(tag); + (*buf)->Reserved = 0; + (*buf)->ReparseDataLength = cpu_to_le16(buf_len - sizeof(struct reparse_data_buffer)); + iov->iov_base = *buf; + iov->iov_len = buf_len; return 0; } @@ -415,27 +650,32 @@ static int wsl_set_xattrs(struct inode *inode, umode_t _mode, static int mknod_wsl(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, - const char *full_path, umode_t mode, dev_t dev) + const char *full_path, umode_t mode, dev_t dev, + const char *symname) { + struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_open_info_data data; - struct reparse_data_buffer buf; + struct reparse_data_buffer *buf; struct smb2_create_ea_ctx *cc; struct inode *new; unsigned int len; struct kvec reparse_iov, xattr_iov; int rc; - rc = wsl_set_reparse_buf(&buf, mode, &reparse_iov); + rc = wsl_set_reparse_buf(&buf, mode, symname, cifs_sb, &reparse_iov); if (rc) return rc; rc = wsl_set_xattrs(inode, mode, dev, &xattr_iov); - if (rc) + if (rc) { + kfree(buf); return rc; + } data = (struct cifs_open_info_data) { .reparse_point = true, - .reparse = { .tag = le32_to_cpu(buf.ReparseTag), .buf = &buf, }, + .reparse = { .tag = le32_to_cpu(buf->ReparseTag), .buf = buf, }, + .symlink_target = kstrdup(symname, GFP_KERNEL), }; cc = xattr_iov.iov_base; @@ -452,6 +692,7 @@ static int mknod_wsl(unsigned int xid, struct inode *inode, rc = PTR_ERR(new); cifs_free_open_info(&data); kfree(xattr_iov.iov_base); + kfree(buf); return rc; } @@ -460,21 +701,22 @@ int smb2_mknod_reparse(unsigned int xid, struct inode *inode, const char *full_path, umode_t mode, dev_t dev) { struct smb3_fs_context *ctx = CIFS_SB(inode->i_sb)->ctx; - int rc = -EOPNOTSUPP; + + if (S_ISSOCK(mode) && !ctx->nonativesocket && ctx->reparse_type != CIFS_REPARSE_TYPE_NONE) + return create_native_socket(xid, inode, dentry, tcon, full_path); switch (ctx->reparse_type) { case CIFS_REPARSE_TYPE_NFS: - rc = mknod_nfs(xid, inode, dentry, tcon, full_path, mode, dev); - break; + return mknod_nfs(xid, inode, dentry, tcon, full_path, mode, dev, NULL); case CIFS_REPARSE_TYPE_WSL: - rc = mknod_wsl(xid, inode, dentry, tcon, full_path, mode, dev); - break; + return mknod_wsl(xid, inode, dentry, tcon, full_path, mode, dev, NULL); + default: + return -EOPNOTSUPP; } - return rc; } /* See MS-FSCC 2.1.2.6 for the 'NFS' style reparse tags */ -static int parse_reparse_posix(struct reparse_posix_data *buf, +static int parse_reparse_nfs(struct reparse_nfs_data_buffer *buf, struct cifs_sb_info *cifs_sb, struct cifs_open_info_data *data) { @@ -536,43 +778,160 @@ static int parse_reparse_posix(struct reparse_posix_data *buf, } int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, - bool unicode, bool relative, + bool relative, const char *full_path, struct cifs_sb_info *cifs_sb) { char sep = CIFS_DIR_SEP(cifs_sb); char *linux_target = NULL; char *smb_target = NULL; + int symlinkroot_len; + int abs_path_len; + char *abs_path; int levels; int rc; int i; - /* Check that length it valid for unicode/non-unicode mode */ - if (!len || (unicode && (len % 2))) { + /* Check that length it valid */ + if (!len || (len % 2)) { cifs_dbg(VFS, "srv returned malformed symlink buffer\n"); rc = -EIO; goto out; } /* - * Check that buffer does not contain UTF-16 null codepoint in unicode - * mode or null byte in non-unicode mode because Linux cannot process - * symlink with null byte. + * Check that buffer does not contain UTF-16 null codepoint + * because Linux cannot process symlink with null byte. */ - if ((unicode && UniStrnlen((wchar_t *)buf, len/2) != len/2) || - (!unicode && strnlen(buf, len) != len)) { + if (UniStrnlen((wchar_t *)buf, len/2) != len/2) { cifs_dbg(VFS, "srv returned null byte in native symlink target location\n"); rc = -EIO; goto out; } - smb_target = cifs_strndup_from_utf16(buf, len, unicode, cifs_sb->local_nls); + smb_target = cifs_strndup_from_utf16(buf, len, true, cifs_sb->local_nls); if (!smb_target) { rc = -ENOMEM; goto out; } - if (smb_target[0] == sep && relative) { + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && !relative) { + /* + * This is an absolute symlink from the server which does not + * support POSIX paths, so the symlink is in NT-style path. + * So convert it to absolute Linux symlink target path. Root of + * the NT-style path for symlinks is specified in "symlinkroot" + * mount option. + * + * Root of the DOS and Win32 paths is at NT path \??\ + * It means that DOS/Win32 path C:\folder\file.txt is + * NT path \??\C:\folder\file.txt + * + * NT systems have some well-known object symlinks in their NT + * hierarchy, which is needed to take into account when resolving + * other symlinks. Most commonly used symlink paths are: + * \?? -> \GLOBAL?? + * \DosDevices -> \?? + * \GLOBAL??\GLOBALROOT -> \ + * \GLOBAL??\Global -> \GLOBAL?? + * \GLOBAL??\NUL -> \Device\Null + * \GLOBAL??\UNC -> \Device\Mup + * \GLOBAL??\PhysicalDrive0 -> \Device\Harddisk0\DR0 (for each harddisk) + * \GLOBAL??\A: -> \Device\Floppy0 (if A: is the first floppy) + * \GLOBAL??\C: -> \Device\HarddiskVolume1 (if C: is the first harddisk) + * \GLOBAL??\D: -> \Device\CdRom0 (if D: is first cdrom) + * \SystemRoot -> \Device\Harddisk0\Partition1\WINDOWS (or where is NT system installed) + * \Volume{...} -> \Device\HarddiskVolume1 (where ... is system generated guid) + * + * In most common cases, absolute NT symlinks points to path on + * DOS/Win32 drive letter, system-specific Volume or on UNC share. + * Here are few examples of commonly used absolute NT symlinks + * created by mklink.exe tool: + * \??\C:\folder\file.txt + * \??\\C:\folder\file.txt + * \??\UNC\server\share\file.txt + * \??\\UNC\server\share\file.txt + * \??\Volume{b75e2c83-0000-0000-0000-602f00000000}\folder\file.txt + * + * It means that the most common path prefix \??\ is also NT path + * symlink (to \GLOBAL??). It is less common that second path + * separator is double backslash, but it is valid. + * + * Volume guid is randomly generated by the target system and so + * only the target system knows the mapping between guid and the + * hardisk number. Over SMB it is not possible to resolve this + * mapping, therefore symlinks pointing to target location of + * volume guids are totally unusable over SMB. + * + * For now parse only symlink paths available for DOS and Win32. + * Those are paths with \??\ prefix or paths which points to \??\ + * via other NT symlink (\DosDevices\, \GLOBAL??\, ...). + */ + abs_path = smb_target; +globalroot: + if (strstarts(abs_path, "\\??\\")) + abs_path += sizeof("\\??\\")-1; + else if (strstarts(abs_path, "\\DosDevices\\")) + abs_path += sizeof("\\DosDevices\\")-1; + else if (strstarts(abs_path, "\\GLOBAL??\\")) + abs_path += sizeof("\\GLOBAL??\\")-1; + else { + /* Unhandled absolute symlink, points outside of DOS/Win32 */ + cifs_dbg(VFS, + "absolute symlink '%s' cannot be converted from NT format " + "because points to unknown target\n", + smb_target); + rc = -EIO; + goto out; + } + + /* Sometimes path separator after \?? is double backslash */ + if (abs_path[0] == '\\') + abs_path++; + + while (strstarts(abs_path, "Global\\")) + abs_path += sizeof("Global\\")-1; + + if (strstarts(abs_path, "GLOBALROOT\\")) { + /* Label globalroot requires path with leading '\\', so do not trim '\\' */ + abs_path += sizeof("GLOBALROOT")-1; + goto globalroot; + } + + /* For now parse only paths to drive letters */ + if (((abs_path[0] >= 'A' && abs_path[0] <= 'Z') || + (abs_path[0] >= 'a' && abs_path[0] <= 'z')) && + abs_path[1] == ':' && + (abs_path[2] == '\\' || abs_path[2] == '\0')) { + /* Convert drive letter to lowercase and drop colon */ + char drive_letter = abs_path[0]; + if (drive_letter >= 'A' && drive_letter <= 'Z') + drive_letter += 'a'-'A'; + abs_path++; + abs_path[0] = drive_letter; + } else { + /* Unhandled absolute symlink. Report an error. */ + cifs_dbg(VFS, + "absolute symlink '%s' cannot be converted from NT format " + "because points to unknown target\n", + smb_target); + rc = -EIO; + goto out; + } + + abs_path_len = strlen(abs_path)+1; + symlinkroot_len = strlen(cifs_sb->ctx->symlinkroot); + if (cifs_sb->ctx->symlinkroot[symlinkroot_len-1] == '/') + symlinkroot_len--; + linux_target = kmalloc(symlinkroot_len + 1 + abs_path_len, GFP_KERNEL); + if (!linux_target) { + rc = -ENOMEM; + goto out; + } + memcpy(linux_target, cifs_sb->ctx->symlinkroot, symlinkroot_len); + linux_target[symlinkroot_len] = '/'; + memcpy(linux_target + symlinkroot_len + 1, abs_path, abs_path_len); + } else if (smb_target[0] == sep && relative) { /* * This is a relative SMB symlink from the top of the share, * which is the top level directory of the Linux mount point. @@ -601,6 +960,12 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, } memcpy(linux_target + levels*3, smb_target+1, smb_target_len); /* +1 to skip leading sep */ } else { + /* + * This is either an absolute symlink in POSIX-style format + * or relative SMB symlink from the current directory. + * These paths have same format as Linux symlinks, so no + * conversion is needed. + */ linux_target = smb_target; smb_target = NULL; } @@ -620,8 +985,8 @@ out: return rc; } -static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym, - u32 plen, bool unicode, +static int parse_reparse_native_symlink(struct reparse_symlink_data_buffer *sym, + u32 plen, struct cifs_sb_info *cifs_sb, const char *full_path, struct cifs_open_info_data *data) @@ -641,7 +1006,6 @@ static int parse_reparse_symlink(struct reparse_symlink_data_buffer *sym, return smb2_parse_native_symlink(&data->symlink_target, sym->PathBuffer + offs, len, - unicode, le32_to_cpu(sym->Flags) & SYMLINK_FLAG_RELATIVE, full_path, cifs_sb); @@ -696,7 +1060,7 @@ static int parse_reparse_wsl_symlink(struct reparse_wsl_symlink_data_buffer *buf int parse_reparse_point(struct reparse_data_buffer *buf, u32 plen, struct cifs_sb_info *cifs_sb, const char *full_path, - bool unicode, struct cifs_open_info_data *data) + struct cifs_open_info_data *data) { struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); @@ -705,12 +1069,12 @@ int parse_reparse_point(struct reparse_data_buffer *buf, /* See MS-FSCC 2.1.2 */ switch (le32_to_cpu(buf->ReparseTag)) { case IO_REPARSE_TAG_NFS: - return parse_reparse_posix((struct reparse_posix_data *)buf, + return parse_reparse_nfs((struct reparse_nfs_data_buffer *)buf, cifs_sb, data); case IO_REPARSE_TAG_SYMLINK: - return parse_reparse_symlink( + return parse_reparse_native_symlink( (struct reparse_symlink_data_buffer *)buf, - plen, unicode, cifs_sb, full_path, data); + plen, cifs_sb, full_path, data); case IO_REPARSE_TAG_LX_SYMLINK: return parse_reparse_wsl_symlink( (struct reparse_wsl_symlink_data_buffer *)buf, @@ -724,13 +1088,12 @@ int parse_reparse_point(struct reparse_data_buffer *buf, le32_to_cpu(buf->ReparseTag)); return -EIO; } - break; + return 0; default: cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n", le32_to_cpu(buf->ReparseTag)); - break; + return -EOPNOTSUPP; } - return 0; } int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, @@ -744,14 +1107,15 @@ int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb, buf = (struct reparse_data_buffer *)((u8 *)io + le32_to_cpu(io->OutputOffset)); - return parse_reparse_point(buf, plen, cifs_sb, full_path, true, data); + return parse_reparse_point(buf, plen, cifs_sb, full_path, data); } -static void wsl_to_fattr(struct cifs_open_info_data *data, +static bool wsl_to_fattr(struct cifs_open_info_data *data, struct cifs_sb_info *cifs_sb, u32 tag, struct cifs_fattr *fattr) { struct smb2_file_full_ea_info *ea; + bool have_xattr_dev = false; u32 next = 0; switch (tag) { @@ -794,21 +1158,31 @@ static void wsl_to_fattr(struct cifs_open_info_data *data, fattr->cf_uid = wsl_make_kuid(cifs_sb, v); else if (!strncmp(name, SMB2_WSL_XATTR_GID, nlen)) fattr->cf_gid = wsl_make_kgid(cifs_sb, v); - else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) + else if (!strncmp(name, SMB2_WSL_XATTR_MODE, nlen)) { + /* File type in reparse point tag and in xattr mode must match. */ + if (S_DT(fattr->cf_mode) != S_DT(le32_to_cpu(*(__le32 *)v))) + return false; fattr->cf_mode = (umode_t)le32_to_cpu(*(__le32 *)v); - else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen)) + } else if (!strncmp(name, SMB2_WSL_XATTR_DEV, nlen)) { fattr->cf_rdev = reparse_mkdev(v); + have_xattr_dev = true; + } } while (next); out: + + /* Major and minor numbers for char and block devices are mandatory. */ + if (!have_xattr_dev && (tag == IO_REPARSE_TAG_LX_CHR || tag == IO_REPARSE_TAG_LX_BLK)) + return false; + fattr->cf_dtype = S_DT(fattr->cf_mode); + return true; } static bool posix_reparse_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr, struct cifs_open_info_data *data) { - struct reparse_posix_data *buf = data->reparse.posix; - + struct reparse_nfs_data_buffer *buf = (struct reparse_nfs_data_buffer *)data->reparse.buf; if (buf == NULL) return true; @@ -874,7 +1248,9 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb, case IO_REPARSE_TAG_AF_UNIX: case IO_REPARSE_TAG_LX_CHR: case IO_REPARSE_TAG_LX_BLK: - wsl_to_fattr(data, cifs_sb, tag, fattr); + ok = wsl_to_fattr(data, cifs_sb, tag, fattr); + if (!ok) + return false; break; case IO_REPARSE_TAG_NFS: ok = posix_reparse_to_fattr(cifs_sb, fattr, data); diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h index ff05b0e75c92..c0be5ab45a78 100644 --- a/fs/smb/client/reparse.h +++ b/fs/smb/client/reparse.h @@ -50,6 +50,7 @@ static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb, static inline u64 reparse_mode_nfs_type(mode_t mode) { switch (mode & S_IFMT) { + case S_IFLNK: return NFS_SPECFILE_LNK; case S_IFBLK: return NFS_SPECFILE_BLK; case S_IFCHR: return NFS_SPECFILE_CHR; case S_IFIFO: return NFS_SPECFILE_FIFO; @@ -61,6 +62,7 @@ static inline u64 reparse_mode_nfs_type(mode_t mode) static inline u32 reparse_mode_wsl_tag(mode_t mode) { switch (mode & S_IFMT) { + case S_IFLNK: return IO_REPARSE_TAG_LX_SYMLINK; case S_IFBLK: return IO_REPARSE_TAG_LX_BLK; case S_IFCHR: return IO_REPARSE_TAG_LX_CHR; case S_IFIFO: return IO_REPARSE_TAG_LX_FIFO; @@ -97,14 +99,30 @@ static inline bool reparse_inode_match(struct inode *inode, static inline bool cifs_open_data_reparse(struct cifs_open_info_data *data) { - struct smb2_file_all_info *fi = &data->fi; - u32 attrs = le32_to_cpu(fi->Attributes); + u32 attrs; bool ret; - ret = data->reparse_point || (attrs & ATTR_REPARSE); - if (ret) - attrs |= ATTR_REPARSE; - fi->Attributes = cpu_to_le32(attrs); + if (data->contains_posix_file_info) { + struct smb311_posix_qinfo *fi = &data->posix_fi; + + attrs = le32_to_cpu(fi->DosAttributes); + if (data->reparse_point) { + attrs |= ATTR_REPARSE; + fi->DosAttributes = cpu_to_le32(attrs); + } + + } else { + struct smb2_file_all_info *fi = &data->fi; + + attrs = le32_to_cpu(fi->Attributes); + if (data->reparse_point) { + attrs |= ATTR_REPARSE; + fi->Attributes = cpu_to_le32(attrs); + } + } + + ret = attrs & ATTR_REPARSE; + return ret; } diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 91d4d409cb1d..faa80e7d54a6 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -1235,12 +1235,13 @@ cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) switch (requested) { case Kerberos: case RawNTLMSSP: + case IAKerb: return requested; case Unspecified: if (server->sec_ntlmssp && (global_secflags & CIFSSEC_MAY_NTLMSSP)) return RawNTLMSSP; - if ((server->sec_kerberos || server->sec_mskerberos) && + if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; fallthrough; diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 749a83cd0deb..d6e2fb669c40 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -377,7 +377,7 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr) static void cifs_downgrade_oplock(struct TCP_Server_Info *server, struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache) + __u16 epoch, bool *purge_cache) { cifs_set_oplock_level(cinode, oplock); } @@ -551,7 +551,7 @@ static int cifs_query_path_info(const unsigned int xid, int rc; FILE_ALL_INFO fi = {}; - data->symlink = false; + data->reparse_point = false; data->adjust_tz = false; /* could do find first instead but this returns more info */ @@ -569,32 +569,8 @@ static int cifs_query_path_info(const unsigned int xid, } if (!rc) { - int tmprc; - int oplock = 0; - struct cifs_fid fid; - struct cifs_open_parms oparms; - move_cifs_info_to_smb2(&data->fi, &fi); - - if (!(le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) - return 0; - - oparms = (struct cifs_open_parms) { - .tcon = tcon, - .cifs_sb = cifs_sb, - .desired_access = FILE_READ_ATTRIBUTES, - .create_options = cifs_create_options(cifs_sb, 0), - .disposition = FILE_OPEN, - .path = full_path, - .fid = &fid, - }; - - /* Need to check if this is a symbolic link or not */ - tmprc = CIFS_open(xid, &oparms, &oplock, NULL); - if (tmprc == -EOPNOTSUPP) - data->symlink = true; - else if (tmprc == 0) - CIFSSMBClose(xid, tcon, fid.netfid); + data->reparse_point = le32_to_cpu(fi.Attributes) & ATTR_REPARSE; } return rc; @@ -1010,7 +986,7 @@ static int cifs_parse_reparse_point(struct cifs_sb_info *cifs_sb, buf = (struct reparse_data_buffer *)((__u8 *)&io->hdr.Protocol + le32_to_cpu(io->DataOffset)); - return parse_reparse_point(buf, plen, cifs_sb, full_path, true, data); + return parse_reparse_point(buf, plen, cifs_sb, full_path, data); } static bool diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index 9ec44eab8dbc..d609a20fb98a 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -63,6 +63,52 @@ static struct smb2_symlink_err_rsp *symlink_data(const struct kvec *iov) return sym; } +int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_info *cifs_sb) +{ + char *buf; + int len; + + /* + * POSIX server does not distinguish between symlinks to file and + * symlink directory. So nothing is needed to fix on the client side. + */ + if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) + return 0; + + if (!*target) + return -EIO; + + len = strlen(*target); + if (!len) + return -EIO; + + /* + * If this is directory symlink and it does not have trailing slash then + * append it. Trailing slash simulates Windows/SMB behavior which do not + * allow resolving directory symlink to file. + */ + if (directory && (*target)[len-1] != '/') { + buf = krealloc(*target, len+2, GFP_KERNEL); + if (!buf) + return -ENOMEM; + buf[len] = '/'; + buf[len+1] = '\0'; + *target = buf; + len++; + } + + /* + * If this is a file (non-directory) symlink and it points to path name + * with trailing slash then this is an invalid symlink because file name + * cannot contain slash character. File name with slash is invalid on + * both Windows and Linux systems. So return an error for such symlink. + */ + if (!directory && (*target)[len-1] == '/') + return -EIO; + + return 0; +} + int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec *iov, const char *full_path, char **path) { @@ -89,7 +135,6 @@ int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, const struct kvec return smb2_parse_native_symlink(path, (char *)sym->PathBuffer + sub_offs, sub_len, - true, le32_to_cpu(sym->Flags) & SYMLINK_FLAG_RELATIVE, full_path, cifs_sb); @@ -133,6 +178,11 @@ int smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 NULL, NULL, NULL); oparms->create_options &= ~OPEN_REPARSE_POINT; } + if (!rc) { + bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY; + rc = smb2_fix_symlink_target_type(&data->symlink_target, + directory, oparms->cifs_sb); + } } } diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index c97f14757c27..826b57a5a2a8 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -650,6 +650,7 @@ finished: switch (cmds[i]) { case SMB2_OP_QUERY_INFO: idata = in_iov[i].iov_base; + idata->contains_posix_file_info = false; if (rc == 0 && cfile && cfile->symlink_target) { idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); if (!idata->symlink_target) @@ -673,6 +674,7 @@ finished: break; case SMB2_OP_POSIX_QUERY_INFO: idata = in_iov[i].iov_base; + idata->contains_posix_file_info = true; if (rc == 0 && cfile && cfile->symlink_target) { idata->symlink_target = kstrdup(cfile->symlink_target, GFP_KERNEL); if (!idata->symlink_target) @@ -770,6 +772,7 @@ finished: idata = in_iov[i].iov_base; idata->reparse.io.iov = *iov; idata->reparse.io.buftype = resp_buftype[i + 1]; + idata->contains_posix_file_info = false; /* BB VERIFY */ rbuf = reparse_buf_ptr(iov); if (IS_ERR(rbuf)) { rc = PTR_ERR(rbuf); @@ -791,6 +794,7 @@ finished: case SMB2_OP_QUERY_WSL_EA: if (!rc) { idata = in_iov[i].iov_base; + idata->contains_posix_file_info = false; qi_rsp = rsp_iov[i + 1].iov_base; data[0] = (u8 *)qi_rsp + le16_to_cpu(qi_rsp->OutputBufferOffset); size[0] = le32_to_cpu(qi_rsp->OutputBufferLength); @@ -1010,6 +1014,11 @@ int smb2_query_path_info(const unsigned int xid, else rc = -EOPNOTSUPP; } + + if (data->reparse.tag == IO_REPARSE_TAG_SYMLINK && !rc) { + bool directory = le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY; + rc = smb2_fix_symlink_target_type(&data->symlink_target, directory, cifs_sb); + } break; case -EREMOTE: break; diff --git a/fs/smb/client/smb2maperror.c b/fs/smb/client/smb2maperror.c index b05313acf9b2..12c2b868789f 100644 --- a/fs/smb/client/smb2maperror.c +++ b/fs/smb/client/smb2maperror.c @@ -380,7 +380,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_NO_LOGON_SERVERS, -EIO, "STATUS_NO_LOGON_SERVERS"}, {STATUS_NO_SUCH_LOGON_SESSION, -EIO, "STATUS_NO_SUCH_LOGON_SESSION"}, {STATUS_NO_SUCH_PRIVILEGE, -EIO, "STATUS_NO_SUCH_PRIVILEGE"}, - {STATUS_PRIVILEGE_NOT_HELD, -EIO, "STATUS_PRIVILEGE_NOT_HELD"}, + {STATUS_PRIVILEGE_NOT_HELD, -EPERM, "STATUS_PRIVILEGE_NOT_HELD"}, {STATUS_INVALID_ACCOUNT_NAME, -EIO, "STATUS_INVALID_ACCOUNT_NAME"}, {STATUS_USER_EXISTS, -EIO, "STATUS_USER_EXISTS"}, {STATUS_NO_SUCH_USER, -EIO, "STATUS_NO_SUCH_USER"}, @@ -871,7 +871,7 @@ static const struct status_to_posix_error smb2_error_map_table[] = { {STATUS_VALIDATE_CONTINUE, -EIO, "STATUS_VALIDATE_CONTINUE"}, {STATUS_NO_MATCH, -EIO, "STATUS_NO_MATCH"}, {STATUS_NO_MORE_MATCHES, -EIO, "STATUS_NO_MORE_MATCHES"}, - {STATUS_NOT_A_REPARSE_POINT, -EIO, "STATUS_NOT_A_REPARSE_POINT"}, + {STATUS_NOT_A_REPARSE_POINT, -ENODATA, "STATUS_NOT_A_REPARSE_POINT"}, {STATUS_IO_REPARSE_TAG_INVALID, -EIO, "STATUS_IO_REPARSE_TAG_INVALID"}, {STATUS_IO_REPARSE_TAG_MISMATCH, -EIO, "STATUS_IO_REPARSE_TAG_MISMATCH"}, diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index d640dcabc305..23e0c8be7fb5 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1001,6 +1001,7 @@ static int smb2_query_file_info(const unsigned int xid, struct cifs_tcon *tcon, if (!data->symlink_target) return -ENOMEM; } + data->contains_posix_file_info = false; return SMB2_query_info(xid, tcon, fid->persistent_fid, fid->volatile_fid, &data->fi); } @@ -3904,22 +3905,22 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode, static void smb2_downgrade_oplock(struct TCP_Server_Info *server, struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache) + __u16 epoch, bool *purge_cache) { server->ops->set_oplock_level(cinode, oplock, 0, NULL); } static void smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache); + __u16 epoch, bool *purge_cache); static void smb3_downgrade_oplock(struct TCP_Server_Info *server, struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache) + __u16 epoch, bool *purge_cache) { unsigned int old_state = cinode->oplock; - unsigned int old_epoch = cinode->epoch; + __u16 old_epoch = cinode->epoch; unsigned int new_state; if (epoch > old_epoch) { @@ -3939,7 +3940,7 @@ smb3_downgrade_oplock(struct TCP_Server_Info *server, static void smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache) + __u16 epoch, bool *purge_cache) { oplock &= 0xFF; cinode->lease_granted = false; @@ -3963,7 +3964,7 @@ smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, static void smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache) + __u16 epoch, bool *purge_cache) { char message[5] = {0}; unsigned int new_oplock = 0; @@ -4000,7 +4001,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, static void smb3_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, - unsigned int epoch, bool *purge_cache) + __u16 epoch, bool *purge_cache) { unsigned int old_oplock = cinode->oplock; @@ -4114,7 +4115,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock) } static __u8 -smb2_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key) +smb2_parse_lease_buf(void *buf, __u16 *epoch, char *lease_key) { struct create_lease *lc = (struct create_lease *)buf; @@ -4125,7 +4126,7 @@ smb2_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key) } static __u8 -smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key) +smb3_parse_lease_buf(void *buf, __u16 *epoch, char *lease_key) { struct create_lease_v2 *lc = (struct create_lease_v2 *)buf; @@ -5077,6 +5078,7 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, { struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; + struct cifs_open_info_data idata; struct cifs_io_parms io_parms = {}; struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifs_fid fid; @@ -5145,11 +5147,21 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, FILE_CREATE, CREATE_NOT_DIR | CREATE_OPTION_SPECIAL, ACL_NO_MODE); oparms.fid = &fid; - - rc = server->ops->open(xid, &oparms, &oplock, NULL); + idata.contains_posix_file_info = false; + rc = server->ops->open(xid, &oparms, &oplock, &idata); if (rc) goto out; + /* + * Check if the server honored ATTR_SYSTEM flag by CREATE_OPTION_SPECIAL + * option. If not then server does not support ATTR_SYSTEM and newly + * created file is not SFU compatible, which means that the call failed. + */ + if (!(le32_to_cpu(idata.fi.Attributes) & ATTR_SYSTEM)) { + rc = -EOPNOTSUPP; + goto out_close; + } + if (type_len + data_len > 0) { io_parms.pid = current->tgid; io_parms.tcon = tcon; @@ -5164,8 +5176,18 @@ int __cifs_sfu_make_node(unsigned int xid, struct inode *inode, iov, ARRAY_SIZE(iov)-1); } +out_close: server->ops->close(xid, tcon, &fid); + /* + * If CREATE was successful but either setting ATTR_SYSTEM failed or + * writing type/data information failed then remove the intermediate + * object created by CREATE. Otherwise intermediate empty object stay + * on the server. + */ + if (rc) + server->ops->unlink(xid, tcon, full_path, cifs_sb, NULL); + out: kfree(symname_utf16); return rc; diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 9f54596a6866..ed7812247ebc 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1429,7 +1429,7 @@ smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested) if (server->sec_ntlmssp && (global_secflags & CIFSSEC_MAY_NTLMSSP)) return RawNTLMSSP; - if ((server->sec_kerberos || server->sec_mskerberos) && + if ((server->sec_kerberos || server->sec_mskerberos || server->sec_iakerb) && (global_secflags & CIFSSEC_MAY_KRB5)) return Kerberos; fallthrough; @@ -2169,7 +2169,7 @@ tcon_exit: tcon_error_exit: if (rsp && rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) - cifs_tcon_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree); + cifs_dbg(VFS | ONCE, "BAD_NETWORK_NAME: %s\n", tree); goto tcon_exit; } @@ -2329,7 +2329,7 @@ parse_posix_ctxt(struct create_context *cc, struct smb2_file_all_info *info, int smb2_parse_contexts(struct TCP_Server_Info *server, struct kvec *rsp_iov, - unsigned int *epoch, + __u16 *epoch, char *lease_key, __u8 *oplock, struct smb2_file_all_info *buf, struct create_posix_rsp *posix) diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 09349fa8da03..4662c7e2d259 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -111,8 +111,9 @@ extern int smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, struct cifs_sb_info *cifs_sb, const unsigned char *path, char *pbuf, unsigned int *pbytes_read); +int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_info *cifs_sb); int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, - bool unicode, bool relative, + bool relative, const char *full_path, struct cifs_sb_info *cifs_sb); int smb2_parse_symlink_response(struct cifs_sb_info *cifs_sb, @@ -282,7 +283,7 @@ extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); int smb2_parse_contexts(struct TCP_Server_Info *server, struct kvec *rsp_iov, - unsigned int *epoch, + __u16 *epoch, char *lease_key, __u8 *oplock, struct smb2_file_all_info *buf, struct create_posix_rsp *posix); diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h index 3c7c706c797d..c7a0efda4403 100644 --- a/fs/smb/common/smb2pdu.h +++ b/fs/smb/common/smb2pdu.h @@ -1550,7 +1550,19 @@ struct reparse_symlink_data_buffer { __u8 PathBuffer[]; /* Variable Length */ } __packed; -/* See MS-FSCC 2.1.2.6 and cifspdu.h for struct reparse_posix_data */ +/* For IO_REPARSE_TAG_NFS - see MS-FSCC 2.1.2.6 */ +#define NFS_SPECFILE_LNK 0x00000000014B4E4C +#define NFS_SPECFILE_CHR 0x0000000000524843 +#define NFS_SPECFILE_BLK 0x00000000004B4C42 +#define NFS_SPECFILE_FIFO 0x000000004F464946 +#define NFS_SPECFILE_SOCK 0x000000004B434F53 +struct reparse_nfs_data_buffer { + __le32 ReparseTag; + __le16 ReparseDataLength; + __u16 Reserved; + __le64 InodeType; /* NFS_SPECFILE_* */ + __u8 DataBuffer[]; +} __packed; /* For IO_REPARSE_TAG_LX_SYMLINK */ struct reparse_wsl_symlink_data_buffer { @@ -1695,23 +1707,33 @@ struct smb2_file_internal_info { } __packed; /* level 6 Query */ struct smb2_file_rename_info { /* encoding of request for level 10 */ - __u8 ReplaceIfExists; /* 1 = replace existing target with new */ - /* 0 = fail if target already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; + /* New members MUST be added within the struct_group() macro below. */ + __struct_group(smb2_file_rename_info_hdr, __hdr, __packed, + __u8 ReplaceIfExists; /* 1 = replace existing target with new */ + /* 0 = fail if target already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + ); char FileName[]; /* New name to be assigned */ /* padding - overall struct size must be >= 24 so filename + pad >= 6 */ } __packed; /* level 10 Set */ +static_assert(offsetof(struct smb2_file_rename_info, FileName) == sizeof(struct smb2_file_rename_info_hdr), + "struct member likely outside of __struct_group()"); struct smb2_file_link_info { /* encoding of request for level 11 */ - __u8 ReplaceIfExists; /* 1 = replace existing link with new */ - /* 0 = fail if link already exists */ - __u8 Reserved[7]; - __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ - __le32 FileNameLength; + /* New members MUST be added within the struct_group() macro below. */ + __struct_group(smb2_file_link_info_hdr, __hdr, __packed, + __u8 ReplaceIfExists; /* 1 = replace existing link with new */ + /* 0 = fail if link already exists */ + __u8 Reserved[7]; + __u64 RootDirectory; /* MBZ for network operations (why says spec?) */ + __le32 FileNameLength; + ); char FileName[]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ +static_assert(offsetof(struct smb2_file_link_info, FileName) == sizeof(struct smb2_file_link_info_hdr), + "struct member likely outside of __struct_group()"); /* * This level 18, although with struct with same name is different from cifs diff --git a/fs/smb/common/smbfsctl.h b/fs/smb/common/smbfsctl.h index 4b379e84c46b..3253a18ecb5c 100644 --- a/fs/smb/common/smbfsctl.h +++ b/fs/smb/common/smbfsctl.h @@ -159,6 +159,9 @@ #define IO_REPARSE_TAG_LX_CHR 0x80000025 #define IO_REPARSE_TAG_LX_BLK 0x80000026 +/* If Name Surrogate Bit is set, the file or directory represents another named entity in the system. */ +#define IS_REPARSE_TAG_NAME_SURROGATE(tag) (!!((tag) & 0x20000000)) + /* fsctl flags */ /* If Flags is set to this value, the request is an FSCTL not ioctl request */ #define SMB2_0_IOCTL_IS_FSCTL 0x00000001 diff --git a/fs/stat.c b/fs/stat.c index 2c0e111a098a..f13308bfdc98 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -281,6 +281,8 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat, u32 request_mask) { int error = vfs_getattr(path, stat, request_mask, flags); + if (error) + return error; if (request_mask & STATX_MNT_ID_UNIQUE) { stat->mnt_id = real_mount(path->mnt)->mnt_id_unique; @@ -302,7 +304,7 @@ static int vfs_statx_path(struct path *path, int flags, struct kstat *stat, if (S_ISBLK(stat->mode)) bdev_statx(path, stat, request_mask); - return error; + return 0; } static int vfs_statx_fd(int fd, int flags, struct kstat *stat, diff --git a/fs/sysctls.c b/fs/sysctls.c index 8dbde9a802fa..ad429dffeb4b 100644 --- a/fs/sysctls.c +++ b/fs/sysctls.c @@ -7,7 +7,7 @@ #include <linux/init.h> #include <linux/sysctl.h> -static struct ctl_table fs_shared_sysctls[] = { +static const struct ctl_table fs_shared_sysctls[] = { { .procname = "overflowuid", .data = &fs_overflowuid, diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c index cfc614c638da..53214499e384 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -457,7 +457,8 @@ static void tracefs_d_release(struct dentry *dentry) eventfs_d_release(dentry); } -static int tracefs_d_revalidate(struct dentry *dentry, unsigned int flags) +static int tracefs_d_revalidate(struct inode *inode, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { struct eventfs_inode *ei = dentry->d_fsdata; diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c index 5cc69beaa62e..b01f382ce8db 100644 --- a/fs/ubifs/debug.c +++ b/fs/ubifs/debug.c @@ -863,7 +863,6 @@ void ubifs_dump_leb(const struct ubifs_info *c, int lnum) out: vfree(buf); - return; } void ubifs_dump_znode(const struct ubifs_info *c, @@ -946,16 +945,20 @@ void ubifs_dump_tnc(struct ubifs_info *c) pr_err("\n"); pr_err("(pid %d) start dumping TNC tree\n", current->pid); - znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, NULL); - level = znode->level; - pr_err("== Level %d ==\n", level); - while (znode) { - if (level != znode->level) { - level = znode->level; - pr_err("== Level %d ==\n", level); + if (c->zroot.znode) { + znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, NULL); + level = znode->level; + pr_err("== Level %d ==\n", level); + while (znode) { + if (level != znode->level) { + level = znode->level; + pr_err("== Level %d ==\n", level); + } + ubifs_dump_znode(c, znode); + znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, znode); } - ubifs_dump_znode(c, znode); - znode = ubifs_tnc_levelorder_next(c, c->zroot.znode, znode); + } else { + pr_err("empty TNC tree in memory\n"); } pr_err("(pid %d) finish dumping TNC tree\n", current->pid); } diff --git a/fs/ubifs/lpt_commit.c b/fs/ubifs/lpt_commit.c index aa8837e6247c..f2cb214581fd 100644 --- a/fs/ubifs/lpt_commit.c +++ b/fs/ubifs/lpt_commit.c @@ -1932,7 +1932,6 @@ static void dump_lpt_leb(const struct ubifs_info *c, int lnum) pr_err("(pid %d) finish dumping LEB %d\n", current->pid, lnum); out: vfree(buf); - return; } /** diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 7c0bd0b55f88..97c4d71115d8 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -36,7 +36,7 @@ static int sysctl_unprivileged_userfaultfd __read_mostly; #ifdef CONFIG_SYSCTL -static struct ctl_table vm_userfaultfd_table[] = { +static const struct ctl_table vm_userfaultfd_table[] = { { .procname = "unprivileged_userfaultfd", .data = &sysctl_unprivileged_userfaultfd, diff --git a/fs/vboxsf/dir.c b/fs/vboxsf/dir.c index 5f1a14d5b927..a859ac9b74ba 100644 --- a/fs/vboxsf/dir.c +++ b/fs/vboxsf/dir.c @@ -192,7 +192,8 @@ const struct file_operations vboxsf_dir_fops = { * This is called during name resolution/lookup to check if the @dentry in * the cache is still valid. the job is handled by vboxsf_inode_revalidate. */ -static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags) +static int vboxsf_dentry_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index e95b8a48d8a0..1d94bb784108 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -21,7 +21,8 @@ #define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */ -static const unsigned char VBSF_MOUNT_SIGNATURE[4] = "\000\377\376\375"; +static const unsigned char VBSF_MOUNT_SIGNATURE[4] = { '\000', '\377', '\376', + '\375' }; static int follow_symlinks; module_param(follow_symlinks, int, 0444); diff --git a/fs/verity/init.c b/fs/verity/init.c index f440f0e61e3e..6e8d33b50240 100644 --- a/fs/verity/init.c +++ b/fs/verity/init.c @@ -10,7 +10,7 @@ #include <linux/ratelimit.h> #ifdef CONFIG_SYSCTL -static struct ctl_table fsverity_sysctl_table[] = { +static const struct ctl_table fsverity_sysctl_table[] = { #ifdef CONFIG_FS_VERITY_BUILTIN_SIGNATURES { .procname = "require_signatures", diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 40ad22fb808b..0ef19f1469ec 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3563,12 +3563,12 @@ xfs_bmap_btalloc_at_eof( int error; /* - * If there are already extents in the file, try an exact EOF block - * allocation to extend the file as a contiguous extent. If that fails, - * or it's the first allocation in a file, just try for a stripe aligned - * allocation. + * If there are already extents in the file, and xfs_bmap_adjacent() has + * given a better blkno, try an exact EOF block allocation to extend the + * file as a contiguous extent. If that fails, or it's the first + * allocation in a file, just try for a stripe aligned allocation. */ - if (ap->offset) { + if (ap->eof) { xfs_extlen_t nextminlen = 0; /* @@ -3736,7 +3736,8 @@ xfs_bmap_btalloc_best_length( int error; ap->blkno = XFS_INO_TO_FSB(args->mp, ap->ip->i_ino); - xfs_bmap_adjacent(ap); + if (!xfs_bmap_adjacent(ap)) + ap->eof = false; /* * Search for an allocation group with a single extent large enough for diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h index bdcd40f0ec74..19877d99f255 100644 --- a/fs/xfs/scrub/common.h +++ b/fs/xfs/scrub/common.h @@ -224,7 +224,6 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm) bool xchk_dir_looks_zapped(struct xfs_inode *dp); bool xchk_pptr_looks_zapped(struct xfs_inode *ip); -#ifdef CONFIG_XFS_ONLINE_REPAIR /* Decide if a repair is required. */ static inline bool xchk_needs_repair(const struct xfs_scrub_metadata *sm) { @@ -244,10 +243,6 @@ static inline bool xchk_could_repair(const struct xfs_scrub *sc) return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) && !(sc->flags & XREP_ALREADY_FIXED); } -#else -# define xchk_needs_repair(sc) (false) -# define xchk_could_repair(sc) (false) -#endif /* CONFIG_XFS_ONLINE_REPAIR */ int xchk_metadata_inode_forks(struct xfs_scrub *sc); diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c index 2f641b6d663e..13ff1c933cb8 100644 --- a/fs/xfs/scrub/inode_repair.c +++ b/fs/xfs/scrub/inode_repair.c @@ -1055,9 +1055,17 @@ xrep_dinode_check_dfork( return true; break; case S_IFREG: - if (fmt == XFS_DINODE_FMT_LOCAL) + switch (fmt) { + case XFS_DINODE_FMT_LOCAL: return true; - fallthrough; + case XFS_DINODE_FMT_EXTENTS: + case XFS_DINODE_FMT_BTREE: + case XFS_DINODE_FMT_META_BTREE: + break; + default: + return true; + } + break; case S_IFLNK: case S_IFDIR: switch (fmt) { diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h index 823c00d1a502..af0a3a9e5ed9 100644 --- a/fs/xfs/scrub/repair.h +++ b/fs/xfs/scrub/repair.h @@ -191,7 +191,16 @@ int xrep_reset_metafile_resv(struct xfs_scrub *sc); #else #define xrep_ino_dqattach(sc) (0) -#define xrep_will_attempt(sc) (false) + +/* + * When online repair is not built into the kernel, we still want to attempt + * the repair so that the stub xrep_attempt below will return EOPNOTSUPP. + */ +static inline bool xrep_will_attempt(const struct xfs_scrub *sc) +{ + return (sc->sm->sm_flags & XFS_SCRUB_IFLAG_FORCE_REBUILD) || + xchk_needs_repair(sc->sm); +} static inline int xrep_attempt( diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c index 7567dd5cad14..6fa9e3e5bab7 100644 --- a/fs/xfs/scrub/scrub.c +++ b/fs/xfs/scrub/scrub.c @@ -149,6 +149,18 @@ xchk_probe( if (xchk_should_terminate(sc, &error)) return error; + /* + * If the caller is probing to see if repair works but repair isn't + * built into the kernel, return EOPNOTSUPP because that's the signal + * that userspace expects. If online repair is built in, set the + * CORRUPT flag (without any of the usual tracing/logging) to force us + * into xrep_probe. + */ + if (xchk_could_repair(sc)) { + if (!IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)) + return -EOPNOTSUPP; + sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT; + } return 0; } diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 67877c36ed11..6d9965b546cb 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -19,6 +19,7 @@ #include "xfs_reflink.h" #include "xfs_errortag.h" #include "xfs_error.h" +#include "xfs_icache.h" struct xfs_writepage_ctx { struct iomap_writepage_ctx ctx; @@ -528,12 +529,44 @@ xfs_vm_readahead( } static int -xfs_iomap_swapfile_activate( +xfs_vm_swap_activate( struct swap_info_struct *sis, struct file *swap_file, sector_t *span) { - sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev; + struct xfs_inode *ip = XFS_I(file_inode(swap_file)); + + /* + * Swap file activation can race against concurrent shared extent + * removal in files that have been cloned. If this happens, + * iomap_swapfile_iter() can fail because it encountered a shared + * extent even though an operation is in progress to remove those + * shared extents. + * + * This race becomes problematic when we defer extent removal + * operations beyond the end of a syscall (i.e. use async background + * processing algorithms). Users think the extents are no longer + * shared, but iomap_swapfile_iter() still sees them as shared + * because the refcountbt entries for the extents being removed have + * not yet been updated. Hence the swapon call fails unexpectedly. + * + * The race condition is currently most obvious from the unlink() + * operation as extent removal is deferred until after the last + * reference to the inode goes away. We then process the extent + * removal asynchronously, hence triggers the "syscall completed but + * work not done" condition mentioned above. To close this race + * window, we need to flush any pending inodegc operations to ensure + * they have updated the refcountbt records before we try to map the + * swapfile. + */ + xfs_inodegc_flush(ip->i_mount); + + /* + * Direct the swap code to the correct block device when this file + * sits on the RT device. + */ + sis->bdev = xfs_inode_buftarg(ip)->bt_bdev; + return iomap_swapfile_activate(sis, swap_file, span, &xfs_read_iomap_ops); } @@ -549,11 +582,11 @@ const struct address_space_operations xfs_address_space_operations = { .migrate_folio = filemap_migrate_folio, .is_partially_uptodate = iomap_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; const struct address_space_operations xfs_dax_aops = { .writepages = xfs_dax_writepages, .dirty_folio = noop_dirty_folio, - .swap_activate = xfs_iomap_swapfile_activate, + .swap_activate = xfs_vm_swap_activate, }; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index d1d4a0a22e13..15bb790359f8 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -41,8 +41,7 @@ struct kmem_cache *xfs_buf_cache; * * xfs_buf_rele: * b_lock - * pag_buf_lock - * lru_lock + * lru_lock * * xfs_buftarg_drain_rele * lru_lock @@ -220,23 +219,25 @@ _xfs_buf_alloc( */ flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD); - spin_lock_init(&bp->b_lock); + /* + * A new buffer is held and locked by the owner. This ensures that the + * buffer is owned by the caller and racing RCU lookups right after + * inserting into the hash table are safe (and will have to wait for + * the unlock to do anything non-trivial). + */ bp->b_hold = 1; + sema_init(&bp->b_sema, 0); /* held, no waiters */ + + spin_lock_init(&bp->b_lock); atomic_set(&bp->b_lru_ref, 1); init_completion(&bp->b_iowait); INIT_LIST_HEAD(&bp->b_lru); INIT_LIST_HEAD(&bp->b_list); INIT_LIST_HEAD(&bp->b_li_list); - sema_init(&bp->b_sema, 0); /* held, no waiters */ bp->b_target = target; bp->b_mount = target->bt_mount; bp->b_flags = flags; - /* - * Set length and io_length to the same value initially. - * I/O routines should use io_length, which will be the same in - * most cases but may be reset (e.g. XFS recovery). - */ error = xfs_buf_get_maps(bp, nmaps); if (error) { kmem_cache_free(xfs_buf_cache, bp); @@ -502,7 +503,6 @@ int xfs_buf_cache_init( struct xfs_buf_cache *bch) { - spin_lock_init(&bch->bc_lock); return rhashtable_init(&bch->bc_hash, &xfs_buf_hash_params); } @@ -652,17 +652,20 @@ xfs_buf_find_insert( if (error) goto out_free_buf; - spin_lock(&bch->bc_lock); + /* The new buffer keeps the perag reference until it is freed. */ + new_bp->b_pag = pag; + + rcu_read_lock(); bp = rhashtable_lookup_get_insert_fast(&bch->bc_hash, &new_bp->b_rhash_head, xfs_buf_hash_params); if (IS_ERR(bp)) { + rcu_read_unlock(); error = PTR_ERR(bp); - spin_unlock(&bch->bc_lock); goto out_free_buf; } if (bp && xfs_buf_try_hold(bp)) { /* found an existing buffer */ - spin_unlock(&bch->bc_lock); + rcu_read_unlock(); error = xfs_buf_find_lock(bp, flags); if (error) xfs_buf_rele(bp); @@ -670,10 +673,8 @@ xfs_buf_find_insert( *bpp = bp; goto out_free_buf; } + rcu_read_unlock(); - /* The new buffer keeps the perag reference until it is freed. */ - new_bp->b_pag = pag; - spin_unlock(&bch->bc_lock); *bpp = new_bp; return 0; @@ -1090,7 +1091,6 @@ xfs_buf_rele_cached( } /* we are asked to drop the last reference */ - spin_lock(&bch->bc_lock); __xfs_buf_ioacct_dec(bp); if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) { /* @@ -1102,7 +1102,6 @@ xfs_buf_rele_cached( bp->b_state &= ~XFS_BSTATE_DISPOSE; else bp->b_hold--; - spin_unlock(&bch->bc_lock); } else { bp->b_hold--; /* @@ -1120,7 +1119,6 @@ xfs_buf_rele_cached( ASSERT(!(bp->b_flags & _XBF_DELWRI_Q)); rhashtable_remove_fast(&bch->bc_hash, &bp->b_rhash_head, xfs_buf_hash_params); - spin_unlock(&bch->bc_lock); if (pag) xfs_perag_put(pag); freebuf = true; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 7e73663c5d4a..3b4ed42e11c0 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -80,7 +80,6 @@ typedef unsigned int xfs_buf_flags_t; #define XFS_BSTATE_IN_FLIGHT (1 << 1) /* I/O in flight */ struct xfs_buf_cache { - spinlock_t bc_lock; struct rhashtable bc_hash; }; diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index f340a2015c4c..0b41bdfecdfb 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -329,22 +329,6 @@ out_trans_cancel: * successfully but before locks are dropped. */ -/* Verify that we have security clearance to perform this operation. */ -static int -xfs_exchange_range_verify_area( - struct xfs_exchrange *fxr) -{ - int ret; - - ret = remap_verify_area(fxr->file1, fxr->file1_offset, fxr->length, - true); - if (ret) - return ret; - - return remap_verify_area(fxr->file2, fxr->file2_offset, fxr->length, - true); -} - /* * Performs necessary checks before doing a range exchange, having stabilized * mutable inode attributes via i_rwsem. @@ -355,11 +339,13 @@ xfs_exchange_range_checks( unsigned int alloc_unit) { struct inode *inode1 = file_inode(fxr->file1); + loff_t size1 = i_size_read(inode1); struct inode *inode2 = file_inode(fxr->file2); + loff_t size2 = i_size_read(inode2); uint64_t allocmask = alloc_unit - 1; int64_t test_len; uint64_t blen; - loff_t size1, size2, tmp; + loff_t tmp; int error; /* Don't touch certain kinds of inodes */ @@ -368,24 +354,25 @@ xfs_exchange_range_checks( if (IS_SWAPFILE(inode1) || IS_SWAPFILE(inode2)) return -ETXTBSY; - size1 = i_size_read(inode1); - size2 = i_size_read(inode2); - /* Ranges cannot start after EOF. */ if (fxr->file1_offset > size1 || fxr->file2_offset > size2) return -EINVAL; - /* - * If the caller said to exchange to EOF, we set the length of the - * request large enough to cover everything to the end of both files. - */ if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) { + /* + * If the caller said to exchange to EOF, we set the length of + * the request large enough to cover everything to the end of + * both files. + */ fxr->length = max_t(int64_t, size1 - fxr->file1_offset, size2 - fxr->file2_offset); - - error = xfs_exchange_range_verify_area(fxr); - if (error) - return error; + } else { + /* + * Otherwise we require both ranges to end within EOF. + */ + if (fxr->file1_offset + fxr->length > size1 || + fxr->file2_offset + fxr->length > size2) + return -EINVAL; } /* @@ -402,15 +389,6 @@ xfs_exchange_range_checks( return -EINVAL; /* - * We require both ranges to end within EOF, unless we're exchanging - * to EOF. - */ - if (!(fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) && - (fxr->file1_offset + fxr->length > size1 || - fxr->file2_offset + fxr->length > size2)) - return -EINVAL; - - /* * Make sure we don't hit any file size limits. If we hit any size * limits such that test_length was adjusted, we abort the whole * operation. @@ -747,6 +725,7 @@ xfs_exchange_range( { struct inode *inode1 = file_inode(fxr->file1); struct inode *inode2 = file_inode(fxr->file2); + loff_t check_len = fxr->length; int ret; BUILD_BUG_ON(XFS_EXCHANGE_RANGE_ALL_FLAGS & @@ -779,14 +758,18 @@ xfs_exchange_range( return -EBADF; /* - * If we're not exchanging to EOF, we can check the areas before - * stabilizing both files' i_size. + * If we're exchanging to EOF we can't calculate the length until taking + * the iolock. Pass a 0 length to remap_verify_area similar to the + * FICLONE and FICLONERANGE ioctls that support cloning to EOF as well. */ - if (!(fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF)) { - ret = xfs_exchange_range_verify_area(fxr); - if (ret) - return ret; - } + if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) + check_len = 0; + ret = remap_verify_area(fxr->file1, fxr->file1_offset, check_len, true); + if (ret) + return ret; + ret = remap_verify_area(fxr->file2, fxr->file2_offset, check_len, true); + if (ret) + return ret; /* Update cmtime if the fd/inode don't forbid it. */ if (!(fxr->file1->f_mode & FMODE_NOCMTIME) && !IS_NOCMTIME(inode1)) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c95fe1b1de4e..b1f9f156ec88 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1404,8 +1404,11 @@ xfs_inactive( goto out; /* Try to clean out the cow blocks if there are any. */ - if (xfs_inode_has_cow_data(ip)) - xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true); + if (xfs_inode_has_cow_data(ip)) { + error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true); + if (error) + goto out; + } if (VFS_I(ip)->i_nlink != 0) { /* diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 50fa3ef89f6c..d61460309a78 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -976,10 +976,8 @@ xfs_dax_write_iomap_end( if (!xfs_is_cow_inode(ip)) return 0; - if (!written) { - xfs_reflink_cancel_cow_range(ip, pos, length, true); - return 0; - } + if (!written) + return xfs_reflink_cancel_cow_range(ip, pos, length, true); return xfs_reflink_end_cow(ip, pos, written); } diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c index 37f1230e7584..245d754f382a 100644 --- a/fs/xfs/xfs_qm_bhv.c +++ b/fs/xfs/xfs_qm_bhv.c @@ -78,6 +78,28 @@ xfs_qm_statvfs( } } +STATIC int +xfs_qm_validate_state_change( + struct xfs_mount *mp, + uint uqd, + uint gqd, + uint pqd) +{ + int state; + + /* Is quota state changing? */ + state = ((uqd && !XFS_IS_UQUOTA_ON(mp)) || + (!uqd && XFS_IS_UQUOTA_ON(mp)) || + (gqd && !XFS_IS_GQUOTA_ON(mp)) || + (!gqd && XFS_IS_GQUOTA_ON(mp)) || + (pqd && !XFS_IS_PQUOTA_ON(mp)) || + (!pqd && XFS_IS_PQUOTA_ON(mp))); + + return state && + (xfs_dev_is_read_only(mp, "changing quota state") || + xfs_has_norecovery(mp)); +} + int xfs_qm_newmount( xfs_mount_t *mp, @@ -97,24 +119,25 @@ xfs_qm_newmount( } /* - * If the device itself is read-only, we can't allow - * the user to change the state of quota on the mount - - * this would generate a transaction on the ro device, - * which would lead to an I/O error and shutdown + * If the device itself is read-only and/or in norecovery + * mode, we can't allow the user to change the state of + * quota on the mount - this would generate a transaction + * on the ro device, which would lead to an I/O error and + * shutdown. */ - if (((uquotaondisk && !XFS_IS_UQUOTA_ON(mp)) || - (!uquotaondisk && XFS_IS_UQUOTA_ON(mp)) || - (gquotaondisk && !XFS_IS_GQUOTA_ON(mp)) || - (!gquotaondisk && XFS_IS_GQUOTA_ON(mp)) || - (pquotaondisk && !XFS_IS_PQUOTA_ON(mp)) || - (!pquotaondisk && XFS_IS_PQUOTA_ON(mp))) && - xfs_dev_is_read_only(mp, "changing quota state")) { - xfs_warn(mp, "please mount with%s%s%s%s.", - (!quotaondisk ? "out quota" : ""), - (uquotaondisk ? " usrquota" : ""), - (gquotaondisk ? " grpquota" : ""), - (pquotaondisk ? " prjquota" : "")); + if (xfs_qm_validate_state_change(mp, uquotaondisk, + gquotaondisk, pquotaondisk)) { + + if (xfs_has_metadir(mp)) + xfs_warn(mp, + "metadir enabled, please mount without any quota mount options"); + else + xfs_warn(mp, "please mount with%s%s%s%s.", + (!quotaondisk ? "out quota" : ""), + (uquotaondisk ? " usrquota" : ""), + (gquotaondisk ? " grpquota" : ""), + (pquotaondisk ? " prjquota" : "")); return -EPERM; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index d92d7a07ea89..0055066fb1d9 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1661,8 +1661,12 @@ xfs_fs_fill_super( #endif } - /* Filesystem claims it needs repair, so refuse the mount. */ - if (xfs_has_needsrepair(mp)) { + /* + * Filesystem claims it needs repair, so refuse the mount unless + * norecovery is also specified, in which case the filesystem can + * be mounted with no risk of further damage. + */ + if (xfs_has_needsrepair(mp) && !xfs_has_norecovery(mp)) { xfs_warn(mp, "Filesystem needs repair. Please run xfs_repair."); error = -EFSCORRUPTED; goto out_free_sb; diff --git a/fs/xfs/xfs_sysctl.c b/fs/xfs/xfs_sysctl.c index c84df23b494d..751dc74a3067 100644 --- a/fs/xfs/xfs_sysctl.c +++ b/fs/xfs/xfs_sysctl.c @@ -66,7 +66,7 @@ xfs_deprecated_dointvec_minmax( return proc_dointvec_minmax(ctl, write, buffer, lenp, ppos); } -static struct ctl_table xfs_table[] = { +static const struct ctl_table xfs_table[] = { { .procname = "irix_sgid_inherit", .data = &xfs_params.sgid_inherit.val, diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 54504013c749..02a4adb4a999 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -1038,6 +1038,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) *(.discard) \ *(.discard.*) \ *(.export_symbol) \ + *(.no_trim_symbol) \ *(.modinfo) \ /* ld.bfd warns about .gnu.version* even when not emitted */ \ *(.gnu.version*) \ diff --git a/include/cxl/event.h b/include/cxl/event.h index 0bea1afbd747..04edd44bd26f 100644 --- a/include/cxl/event.h +++ b/include/cxl/event.h @@ -18,7 +18,8 @@ struct cxl_event_record_hdr { __le16 related_handle; __le64 timestamp; u8 maint_op_class; - u8 reserved[15]; + u8 maint_op_sub_class; + u8 reserved[14]; } __packed; struct cxl_event_media_hdr { @@ -44,19 +45,22 @@ struct cxl_event_generic { /* * General Media Event Record - * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43 + * CXL rev 3.1 Section 8.2.9.2.1.1; Table 8-45 */ #define CXL_EVENT_GEN_MED_COMP_ID_SIZE 0x10 struct cxl_event_gen_media { struct cxl_event_media_hdr media_hdr; u8 device[3]; u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; - u8 reserved[46]; + u8 cme_threshold_ev_flags; + u8 cme_count[3]; + u8 sub_type; + u8 reserved[41]; } __packed; /* * DRAM Event Record - DER - * CXL rev 3.0 section 8.2.9.2.1.2; Table 3-44 + * CXL rev 3.1 section 8.2.9.2.1.2; Table 8-46 */ #define CXL_EVENT_DER_CORRECTION_MASK_SIZE 0x20 struct cxl_event_dram { @@ -67,12 +71,17 @@ struct cxl_event_dram { u8 row[3]; u8 column[2]; u8 correction_mask[CXL_EVENT_DER_CORRECTION_MASK_SIZE]; - u8 reserved[0x17]; + u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; + u8 sub_channel; + u8 cme_threshold_ev_flags; + u8 cvme_count[3]; + u8 sub_type; + u8 reserved; } __packed; /* * Get Health Info Record - * CXL rev 3.0 section 8.2.9.8.3.1; Table 8-100 + * CXL rev 3.1 section 8.2.9.9.3.1; Table 8-133 */ struct cxl_get_health_info { u8 health_status; @@ -87,13 +96,16 @@ struct cxl_get_health_info { /* * Memory Module Event Record - * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45 + * CXL rev 3.1 section 8.2.9.2.1.3; Table 8-47 */ struct cxl_event_mem_module { struct cxl_event_record_hdr hdr; u8 event_type; struct cxl_get_health_info info; - u8 reserved[0x3d]; + u8 validity_flags[2]; + u8 component_id[CXL_EVENT_GEN_MED_COMP_ID_SIZE]; + u8 event_sub_type; + u8 reserved[0x2a]; } __packed; union cxl_event { diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h index a6f8b098c56f..3bd9f482f0c3 100644 --- a/include/drm/display/drm_dp.h +++ b/include/drm/display/drm_dp.h @@ -359,6 +359,7 @@ # define DP_DSC_BITS_PER_PIXEL_1_4 0x2 # define DP_DSC_BITS_PER_PIXEL_1_2 0x3 # define DP_DSC_BITS_PER_PIXEL_1_1 0x4 +# define DP_DSC_BITS_PER_PIXEL_MASK 0x7 #define DP_PSR_SUPPORT 0x070 /* XXX 1.2? */ # define DP_PSR_IS_SUPPORTED 1 diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h index f77fe1531cf8..9732f514566d 100644 --- a/include/drm/drm_print.h +++ b/include/drm/drm_print.h @@ -32,6 +32,7 @@ #include <linux/dynamic_debug.h> #include <drm/drm.h> +#include <drm/drm_device.h> struct debugfs_regset32; struct drm_device; diff --git a/include/dt-bindings/clock/qcom,qcs8300-camcc.h b/include/dt-bindings/clock/qcom,qcs8300-camcc.h new file mode 100644 index 000000000000..fc535c847859 --- /dev/null +++ b/include/dt-bindings/clock/qcom,qcs8300-camcc.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_QCS8300_CAM_CC_H +#define _DT_BINDINGS_CLK_QCOM_QCS8300_CAM_CC_H + +#include "qcom,sa8775p-camcc.h" + +/* QCS8300 introduces below new clocks compared to SA8775P */ + +/* CAM_CC clocks */ +#define CAM_CC_TITAN_TOP_ACCU_SHIFT_CLK 86 + +#endif diff --git a/include/dt-bindings/clock/qcom,qcs8300-gpucc.h b/include/dt-bindings/clock/qcom,qcs8300-gpucc.h new file mode 100644 index 000000000000..afa187467b4c --- /dev/null +++ b/include/dt-bindings/clock/qcom,qcs8300-gpucc.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DT_BINDINGS_CLK_QCOM_GPUCC_QCS8300_H +#define _DT_BINDINGS_CLK_QCOM_GPUCC_QCS8300_H + +#include "qcom,sa8775p-gpucc.h" + +/* QCS8300 introduces below new clocks compared to SA8775P */ + +/* GPU_CC clocks */ +#define GPU_CC_CX_ACCU_SHIFT_CLK 23 +#define GPU_CC_GX_ACCU_SHIFT_CLK 24 + +#endif diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a0a9007cc1e3..fa2a76cc2f73 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -861,12 +861,22 @@ static inline bool blk_mq_add_to_batch(struct request *req, void (*complete)(struct io_comp_batch *)) { /* - * blk_mq_end_request_batch() can't end request allocated from - * sched tags + * Check various conditions that exclude batch processing: + * 1) No batch container + * 2) Has scheduler data attached + * 3) Not a passthrough request and end_io set + * 4) Not a passthrough request and an ioerror */ - if (!iob || (req->rq_flags & RQF_SCHED_TAGS) || ioerror || - (req->end_io && !blk_rq_is_passthrough(req))) + if (!iob) return false; + if (req->rq_flags & RQF_SCHED_TAGS) + return false; + if (!blk_rq_is_passthrough(req)) { + if (req->end_io) + return false; + if (ioerror < 0) + return false; + } if (!iob->complete) iob->complete = complete; @@ -900,8 +910,22 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs); void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv); void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset); -void blk_mq_freeze_queue(struct request_queue *q); -void blk_mq_unfreeze_queue(struct request_queue *q); +void blk_mq_freeze_queue_nomemsave(struct request_queue *q); +void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q); +static inline unsigned int __must_check +blk_mq_freeze_queue(struct request_queue *q) +{ + unsigned int memflags = memalloc_noio_save(); + + blk_mq_freeze_queue_nomemsave(q); + return memflags; +} +static inline void +blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags) +{ + blk_mq_unfreeze_queue_nomemrestore(q); + memalloc_noio_restore(memflags); +} void blk_freeze_queue_start(struct request_queue *q); void blk_mq_freeze_queue_wait(struct request_queue *q); int blk_mq_freeze_queue_wait_timeout(struct request_queue *q, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 76f0a4e7c2e5..248416ecd01c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -561,7 +561,6 @@ struct request_queue { struct list_head flush_list; struct mutex sysfs_lock; - struct mutex sysfs_dir_lock; struct mutex limits_lock; /* @@ -605,8 +604,6 @@ struct request_queue { * Serializes all debugfs metadata operations using the above dentries. */ struct mutex debugfs_mutex; - - bool mq_sysfs_init_done; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index 2d7d86f0290d..c7f2c63b3bc3 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -504,20 +504,6 @@ struct ceph_mds_request_head_legacy { #define CEPH_MDS_REQUEST_HEAD_VERSION 3 -struct ceph_mds_request_head_old { - __le16 version; /* struct version */ - __le64 oldest_client_tid; - __le32 mdsmap_epoch; /* on client */ - __le32 flags; /* CEPH_MDS_FLAG_* */ - __u8 num_retry, num_fwd; /* count retry, fwd attempts */ - __le16 num_releases; /* # include cap/lease release records */ - __le32 op; /* mds op code */ - __le32 caller_uid, caller_gid; - __le64 ino; /* use this ino for openc, mkdir, mknod, - etc. (if replaying) */ - union ceph_mds_request_args_ext args; -} __attribute__ ((packed)); - struct ceph_mds_request_head { __le16 version; /* struct version */ __le64 oldest_client_tid; diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 1b20d2d8ef7c..17960a1e858d 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -71,9 +71,6 @@ enum { /* Cgroup is frozen. */ CGRP_FROZEN, - - /* Control group has to be killed. */ - CGRP_KILL, }; /* cgroup_root->flags */ @@ -461,6 +458,9 @@ struct cgroup { int nr_threaded_children; /* # of live threaded child cgroups */ + /* sequence number for cgroup.kill, serialized by css_set_lock. */ + unsigned int kill_seq; + struct kernfs_node *kn; /* cgroup kernfs entry */ struct cgroup_file procs_file; /* handle for "cgroup.procs" */ struct cgroup_file events_file; /* handle for "cgroup.events" */ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index b087de2f3e94..200fd3c5bc70 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -191,6 +191,25 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __v; \ }) +#ifdef __CHECKER__ +#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) +#else /* __CHECKER__ */ +#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);})) +#endif /* __CHECKER__ */ + +/* &a[0] degrades to a pointer: a different type from an array */ +#define __is_array(a) (!__same_type((a), &(a)[0])) +#define __must_be_array(a) __BUILD_BUG_ON_ZERO_MSG(!__is_array(a), \ + "must be array") + +#define __is_byte_array(a) (__is_array(a) && sizeof((a)[0]) == 1) +#define __must_be_byte_array(a) __BUILD_BUG_ON_ZERO_MSG(!__is_byte_array(a), \ + "must be byte array") + +/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */ +#define __must_be_cstr(p) \ + __BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)") + #endif /* __KERNEL__ */ /** @@ -231,19 +250,6 @@ static inline void *offset_to_ptr(const int *off) #define __ADDRESSABLE_ASM_STR(sym) __stringify(__ADDRESSABLE_ASM(sym)) -#ifdef __CHECKER__ -#define __BUILD_BUG_ON_ZERO_MSG(e, msg) (0) -#else /* __CHECKER__ */ -#define __BUILD_BUG_ON_ZERO_MSG(e, msg) ((int)sizeof(struct {_Static_assert(!(e), msg);})) -#endif /* __CHECKER__ */ - -/* &a[0] degrades to a pointer: a different type from an array */ -#define __must_be_array(a) __BUILD_BUG_ON_ZERO_MSG(__same_type((a), &(a)[0]), "must be array") - -/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */ -#define __must_be_cstr(p) \ - __BUILD_BUG_ON_ZERO_MSG(__annotated(p, nonstring), "must be cstr (NUL-terminated)") - /* * This returns a constant expression while determining if an argument is * a constant expression, most importantly without evaluating the argument. diff --git a/include/linux/cpu.h b/include/linux/cpu.h index bdcec1732445..6a0a8f1c7c90 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -77,6 +77,7 @@ extern ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_ghostwrite(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/dcache.h b/include/linux/dcache.h index bff956f7b2b9..4afb60365675 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -57,6 +57,7 @@ struct qstr { }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } +#define QSTR(n) (struct qstr)QSTR_INIT(n, strlen(n)) extern const struct qstr empty_name; extern const struct qstr slash_name; @@ -68,16 +69,24 @@ extern const struct qstr dotdot_name; * large memory footprint increase). */ #ifdef CONFIG_64BIT -# define DNAME_INLINE_LEN 40 /* 192 bytes */ +# define DNAME_INLINE_WORDS 5 /* 192 bytes */ #else # ifdef CONFIG_SMP -# define DNAME_INLINE_LEN 36 /* 128 bytes */ +# define DNAME_INLINE_WORDS 9 /* 128 bytes */ # else -# define DNAME_INLINE_LEN 44 /* 128 bytes */ +# define DNAME_INLINE_WORDS 11 /* 128 bytes */ # endif #endif +#define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long)) + +union shortname_store { + unsigned char string[DNAME_INLINE_LEN]; + unsigned long words[DNAME_INLINE_WORDS]; +}; + #define d_lock d_lockref.lock +#define d_iname d_shortname.string struct dentry { /* RCU lookup touched fields */ @@ -88,7 +97,7 @@ struct dentry { struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ - unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ + union shortname_store d_shortname; /* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */ /* Ref lookup also touches following */ @@ -136,7 +145,8 @@ enum d_real_type { }; struct dentry_operations { - int (*d_revalidate)(struct dentry *, unsigned int); + int (*d_revalidate)(struct inode *, const struct qstr *, + struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, @@ -150,6 +160,8 @@ struct dentry_operations { struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); + bool (*d_unalias_trylock)(const struct dentry *); + void (*d_unalias_unlock)(const struct dentry *); } ____cacheline_aligned; /* @@ -589,7 +601,7 @@ static inline struct inode *d_real_inode(const struct dentry *dentry) struct name_snapshot { struct qstr name; - unsigned char inline_name[DNAME_INLINE_LEN]; + union shortname_store inline_name; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); diff --git a/include/linux/device/faux.h b/include/linux/device/faux.h new file mode 100644 index 000000000000..9f43c0e46aa4 --- /dev/null +++ b/include/linux/device/faux.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Greg Kroah-Hartman <gregkh@linuxfoundation.org> + * Copyright (c) 2025 The Linux Foundation + * + * A "simple" faux bus that allows devices to be created and added + * automatically to it. This is to be used whenever you need to create a + * device that is not associated with any "real" system resources, and do + * not want to have to deal with a bus/driver binding logic. It is + * intended to be very simple, with only a create and a destroy function + * available. + */ +#ifndef _FAUX_DEVICE_H_ +#define _FAUX_DEVICE_H_ + +#include <linux/container_of.h> +#include <linux/device.h> + +/** + * struct faux_device - a "faux" device + * @dev: internal struct device of the object + * + * A simple faux device that can be created/destroyed. To be used when a + * driver only needs to have a device to "hang" something off. This can be + * used for downloading firmware or other basic tasks. Use this instead of + * a struct platform_device if the device has no resources assigned to + * it at all. + */ +struct faux_device { + struct device dev; +}; +#define to_faux_device(x) container_of_const((x), struct faux_device, dev) + +/** + * struct faux_device_ops - a set of callbacks for a struct faux_device + * @probe: called when a faux device is probed by the driver core + * before the device is fully bound to the internal faux bus + * code. If probe succeeds, return 0, otherwise return a + * negative error number to stop the probe sequence from + * succeeding. + * @remove: called when a faux device is removed from the system + * + * Both @probe and @remove are optional, if not needed, set to NULL. + */ +struct faux_device_ops { + int (*probe)(struct faux_device *faux_dev); + void (*remove)(struct faux_device *faux_dev); +}; + +struct faux_device *faux_device_create(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops); +struct faux_device *faux_device_create_with_groups(const char *name, + struct device *parent, + const struct faux_device_ops *faux_ops, + const struct attribute_group **groups); +void faux_device_destroy(struct faux_device *faux_dev); + +static inline void *faux_device_get_drvdata(const struct faux_device *faux_dev) +{ + return dev_get_drvdata(&faux_dev->dev); +} + +static inline void faux_device_set_drvdata(struct faux_device *faux_dev, void *data) +{ + dev_set_drvdata(&faux_dev->dev, data); +} + +#endif /* _FAUX_DEVICE_H_ */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 053c57e61869..7d63d1d75f22 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -114,21 +114,22 @@ typedef struct { #define EFI_MAX_MEMORY_TYPE 16 /* Attribute values: */ -#define EFI_MEMORY_UC ((u64)0x0000000000000001ULL) /* uncached */ -#define EFI_MEMORY_WC ((u64)0x0000000000000002ULL) /* write-coalescing */ -#define EFI_MEMORY_WT ((u64)0x0000000000000004ULL) /* write-through */ -#define EFI_MEMORY_WB ((u64)0x0000000000000008ULL) /* write-back */ -#define EFI_MEMORY_UCE ((u64)0x0000000000000010ULL) /* uncached, exported */ -#define EFI_MEMORY_WP ((u64)0x0000000000001000ULL) /* write-protect */ -#define EFI_MEMORY_RP ((u64)0x0000000000002000ULL) /* read-protect */ -#define EFI_MEMORY_XP ((u64)0x0000000000004000ULL) /* execute-protect */ -#define EFI_MEMORY_NV ((u64)0x0000000000008000ULL) /* non-volatile */ -#define EFI_MEMORY_MORE_RELIABLE \ - ((u64)0x0000000000010000ULL) /* higher reliability */ -#define EFI_MEMORY_RO ((u64)0x0000000000020000ULL) /* read-only */ -#define EFI_MEMORY_SP ((u64)0x0000000000040000ULL) /* soft reserved */ -#define EFI_MEMORY_CPU_CRYPTO ((u64)0x0000000000080000ULL) /* supports encryption */ -#define EFI_MEMORY_RUNTIME ((u64)0x8000000000000000ULL) /* range requires runtime mapping */ +#define EFI_MEMORY_UC BIT_ULL(0) /* uncached */ +#define EFI_MEMORY_WC BIT_ULL(1) /* write-coalescing */ +#define EFI_MEMORY_WT BIT_ULL(2) /* write-through */ +#define EFI_MEMORY_WB BIT_ULL(3) /* write-back */ +#define EFI_MEMORY_UCE BIT_ULL(4) /* uncached, exported */ +#define EFI_MEMORY_WP BIT_ULL(12) /* write-protect */ +#define EFI_MEMORY_RP BIT_ULL(13) /* read-protect */ +#define EFI_MEMORY_XP BIT_ULL(14) /* execute-protect */ +#define EFI_MEMORY_NV BIT_ULL(15) /* non-volatile */ +#define EFI_MEMORY_MORE_RELIABLE BIT_ULL(16) /* higher reliability */ +#define EFI_MEMORY_RO BIT_ULL(17) /* read-only */ +#define EFI_MEMORY_SP BIT_ULL(18) /* soft reserved */ +#define EFI_MEMORY_CPU_CRYPTO BIT_ULL(19) /* supports encryption */ +#define EFI_MEMORY_HOT_PLUGGABLE BIT_ULL(20) /* supports unplugging at runtime */ +#define EFI_MEMORY_RUNTIME BIT_ULL(63) /* range requires runtime mapping */ + #define EFI_MEMORY_DESCRIPTOR_VERSION 1 #define EFI_PAGE_SHIFT 12 diff --git a/include/linux/export.h b/include/linux/export.h index 2633df4d31e6..a8c23d945634 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -52,9 +52,24 @@ #else +#ifdef CONFIG_GENDWARFKSYMS +/* + * With CONFIG_GENDWARFKSYMS, ensure the compiler emits debugging + * information for all exported symbols, including those defined in + * different TUs, by adding a __gendwarfksyms_ptr_<symbol> pointer + * that's discarded during the final link. + */ +#define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; +#else +#define __GENDWARFKSYMS_EXPORT(sym) +#endif + #define __EXPORT_SYMBOL(sym, license, ns) \ extern typeof(sym) sym; \ __ADDRESSABLE(sym) \ + __GENDWARFKSYMS_EXPORT(sym) \ asm(__stringify(___EXPORT_SYMBOL(sym, license, ns))) #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index be3ad155ec9f..2c3b2f8a621f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -222,7 +222,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_FSNOTIFY_HSM(mode) 0 #endif - /* * Attribute flags. These should be or-ed together to figure out what * has been changed! @@ -791,6 +790,19 @@ struct inode { static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { + int testlen; + + /* + * TODO: patch it into a debug-only check if relevant macros show up. + * In the meantime, since we are suffering strlen even on production kernels + * to find the right length, do a fixup if the wrong value got passed. + */ + testlen = strlen(link); + if (testlen != linklen) { + WARN_ONCE(1, "bad length passed for symlink [%s] (got %d, expected %d)", + link, linklen, testlen); + linklen = testlen; + } inode->i_link = link; inode->i_linklen = linklen; inode->i_opflags |= IOP_CACHED_LINK; @@ -3140,6 +3152,12 @@ static inline void exe_file_allow_write_access(struct file *exe_file) allow_write_access(exe_file); } +static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode) +{ + file->f_mode &= ~FMODE_FSNOTIFY_MASK; + file->f_mode |= mode; +} + static inline bool inode_is_open_for_write(const struct inode *inode) { return atomic_read(&inode->i_writecount) > 0; diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index 772f822dc6b8..18855cb44b1c 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -192,7 +192,8 @@ struct fscrypt_operations { unsigned int *num_devs); }; -int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags); +int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags); static inline struct fscrypt_inode_info * fscrypt_get_inode_info(const struct inode *inode) @@ -711,8 +712,8 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir, return 0; } -static inline int fscrypt_d_revalidate(struct dentry *dentry, - unsigned int flags) +static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { return 1; } diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1a9ef8f6784d..6a33288bd6a1 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -129,7 +129,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask) #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS -void file_set_fsnotify_mode(struct file *file); +void file_set_fsnotify_mode_from_watchers(struct file *file); /* * fsnotify_file_area_perm - permission hook before access to file range @@ -213,7 +213,7 @@ static inline int fsnotify_open_perm(struct file *file) } #else -static inline void file_set_fsnotify_mode(struct file *file) +static inline void file_set_fsnotify_mode_from_watchers(struct file *file) { } diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h index c3b4b7ed7c16..84a5045f80f3 100644 --- a/include/linux/hrtimer_defs.h +++ b/include/linux/hrtimer_defs.h @@ -125,6 +125,7 @@ struct hrtimer_cpu_base { ktime_t softirq_expires_next; struct hrtimer *softirq_next_timer; struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + call_single_data_t csd; } ____cacheline_aligned; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index c31fd1dba3bd..2b2af24d2a43 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -244,6 +244,7 @@ enum i2c_driver_flags { * @id_table: List of I2C devices supported by this driver * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) + * @clients: List of detected clients we created (for i2c-core use only) * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. @@ -298,6 +299,7 @@ struct i2c_driver { /* Device detection callback for automatic device creation */ int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; + struct list_head clients; u32 flags; }; @@ -313,6 +315,8 @@ struct i2c_driver { * @dev: Driver model device node for the slave. * @init_irq: IRQ that was set at initialization * @irq: indicates the IRQ generated by this device (if any) + * @detected: member of an i2c_driver.clients list or i2c-core's + * userspace_devices list * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter * calls it to pass on slave events to the slave driver. * @devres_group_id: id of the devres group that will be created for resources @@ -332,8 +336,6 @@ struct i2c_client { #define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ #define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ #define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ -#define I2C_CLIENT_AUTO 0x100 /* client was auto-detected */ -#define I2C_CLIENT_USER 0x200 /* client was userspace-created */ #define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ @@ -345,6 +347,7 @@ struct i2c_client { struct device dev; /* the device structure */ int init_irq; /* irq set at initialization */ int irq; /* irq issued by device */ + struct list_head detected; #if IS_ENABLED(CONFIG_I2C_SLAVE) i2c_slave_cb_t slave_cb; /* callback for slave mode */ #endif @@ -751,6 +754,9 @@ struct i2c_adapter { char name[48]; struct completion dev_released; + struct mutex userspace_clients_lock; + struct list_head userspace_clients; + struct i2c_bus_recovery_info *bus_recovery_info; const struct i2c_adapter_quirks *quirks; diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h index a3ce553413de..abd0c8bd950b 100644 --- a/include/linux/io_uring/cmd.h +++ b/include/linux/io_uring/cmd.h @@ -19,8 +19,8 @@ struct io_uring_cmd { }; struct io_uring_cmd_data { - struct io_uring_sqe sqes[2]; void *op_data; + struct io_uring_sqe sqes[2]; }; static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe) diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h index 623d8e798a11..3def525a1da3 100644 --- a/include/linux/io_uring_types.h +++ b/include/linux/io_uring_types.h @@ -222,7 +222,8 @@ struct io_alloc_cache { void **entries; unsigned int nr_cached; unsigned int max_cached; - size_t elem_size; + unsigned int elem_size; + unsigned int init_clear; }; struct io_ring_ctx { diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index ed945f42e064..0ea8c9887429 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -537,7 +537,7 @@ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m) * * Return: jiffies value */ -#define secs_to_jiffies(_secs) ((_secs) * HZ) +#define secs_to_jiffies(_secs) (unsigned long)((_secs) * HZ) extern unsigned long __usecs_to_jiffies(const unsigned int u); #if !(USEC_PER_SEC % HZ) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3cb9a32a6330..f34f4cfaa513 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1615,7 +1615,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); -int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); void kvm_arch_create_vm_debugfs(struct kvm *kvm); diff --git a/include/linux/lockref.h b/include/linux/lockref.h index c39f119659ba..676721ee878d 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -37,12 +37,13 @@ struct lockref { /** * lockref_init - Initialize a lockref * @lockref: pointer to lockref structure - * @count: initial count + * + * Initializes @lockref->count to 1. */ -static inline void lockref_init(struct lockref *lockref, unsigned int count) +static inline void lockref_init(struct lockref *lockref) { spin_lock_init(&lockref->lock); - lockref->count = count; + lockref->count = 1; } void lockref_get(struct lockref *lockref); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5f1b2dc788e2..6b27db7f9496 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -1406,6 +1406,7 @@ enum tlb_flush_reason { TLB_LOCAL_SHOOTDOWN, TLB_LOCAL_MM_SHOOTDOWN, TLB_REMOTE_SEND_IPI, + TLB_REMOTE_WRONG_CPU, NR_TLB_FLUSH_REASONS, }; diff --git a/include/linux/module.h b/include/linux/module.h index 37eb5d88f6eb..30e5b19bafa9 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -306,7 +306,10 @@ extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); -#define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x)))) +#define symbol_get(x) ({ \ + static const char __notrim[] \ + __used __section(".no_trim_symbol") = __stringify(x); \ + (typeof(&x))(__symbol_get(__stringify(x))); }) /* modules using other modules: kdb wants to see this. */ struct module_use { @@ -430,7 +433,7 @@ struct module { /* Exported symbols */ const struct kernel_symbol *syms; - const s32 *crcs; + const u32 *crcs; unsigned int num_syms; #ifdef CONFIG_ARCH_USES_CFI_TRAPS @@ -448,7 +451,7 @@ struct module { /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; - const s32 *gpl_crcs; + const u32 *gpl_crcs; bool using_gplonly_symbols; #ifdef CONFIG_MODULE_SIG diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 8da4c61f97b9..ab550a89b9bf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1085,8 +1085,8 @@ struct netdev_net_notifier { * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Old-style ioctl entry point. This is used internally by the - * appletalk and ieee802154 subsystems but is no longer called by - * the device ioctl handler. + * ieee802154 subsystem but is no longer called by the device + * ioctl handler. * * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); * Used by the bonding driver for its device specific ioctls: @@ -2664,6 +2664,12 @@ struct net *dev_net(const struct net_device *dev) } static inline +struct net *dev_net_rcu(const struct net_device *dev) +{ + return read_pnet_rcu(&dev->nd_net); +} + +static inline void dev_net_set(struct net_device *dev, struct net *net) { write_pnet(&dev->nd_net, net); @@ -2904,9 +2910,9 @@ struct pcpu_sw_netstats { struct pcpu_dstats { u64_stats_t rx_packets; u64_stats_t rx_bytes; - u64_stats_t rx_drops; u64_stats_t tx_packets; u64_stats_t tx_bytes; + u64_stats_t rx_drops; u64_stats_t tx_drops; struct u64_stats_sync syncp; } __aligned(8 * sizeof(u64)); @@ -3269,6 +3275,8 @@ static inline struct net_device *first_net_device_rcu(struct net *net) } int netdev_boot_setup_check(struct net_device *dev); +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *hwaddr); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); @@ -4109,7 +4117,6 @@ void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 071d05d81d38..c86a11cfc4a3 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -278,7 +278,7 @@ struct netfs_io_request { #define NETFS_RREQ_PAUSE 11 /* Pause subrequest generation */ #define NETFS_RREQ_USE_IO_ITER 12 /* Use ->io_iter rather than ->i_pages */ #define NETFS_RREQ_ALL_QUEUED 13 /* All subreqs are now queued */ -#define NETFS_RREQ_NEED_RETRY 14 /* Need to try retrying */ +#define NETFS_RREQ_RETRYING 14 /* Set if we're in the retry path */ #define NETFS_RREQ_USE_PGPRIV2 31 /* [DEPRECATED] Use PG_private_2 to mark * write to cache on read */ const struct netfs_request_ops *netfs_ops; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 162b7c0c3555..9155a6ffc370 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1781,7 +1781,7 @@ struct nfs_rpc_ops { struct nfs_fattr *, struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); - int (*lookup) (struct inode *, struct dentry *, + int (*lookup) (struct inode *, struct dentry *, const struct qstr *, struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index de5deb1a0118..1a2594a38199 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3134,6 +3134,7 @@ #define PCI_DEVICE_ID_INTEL_HDA_LNL_P 0xa828 #define PCI_DEVICE_ID_INTEL_S21152BB 0xb152 #define PCI_DEVICE_ID_INTEL_HDA_BMG 0xe2f7 +#define PCI_DEVICE_ID_INTEL_HDA_PTL_H 0xe328 #define PCI_DEVICE_ID_INTEL_HDA_PTL 0xe428 #define PCI_DEVICE_ID_INTEL_HDA_CML_R 0xf0c8 #define PCI_DEVICE_ID_INTEL_HDA_RKL_S 0xf1c8 diff --git a/include/linux/pm.h b/include/linux/pm.h index 08c37b83fea8..78855d794342 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -384,12 +384,8 @@ const struct dev_pm_ops name = { \ #ifdef CONFIG_PM #define _EXPORT_DEV_PM_OPS(name, license, ns) _EXPORT_PM_OPS(name, license, ns) -#define EXPORT_PM_FN_GPL(name) EXPORT_SYMBOL_GPL(name) -#define EXPORT_PM_FN_NS_GPL(name, ns) EXPORT_SYMBOL_NS_GPL(name, "ns") #else #define _EXPORT_DEV_PM_OPS(name, license, ns) _DISCARD_PM_OPS(name, license, ns) -#define EXPORT_PM_FN_GPL(name) -#define EXPORT_PM_FN_NS_GPL(name, ns) #endif #ifdef CONFIG_PM_SLEEP @@ -684,6 +680,7 @@ struct dev_pm_info { bool no_pm_callbacks:1; /* Owned by the PM core */ bool async_in_progress:1; /* Owned by the PM core */ bool must_resume:1; /* Owned by the PM core */ + bool set_active:1; /* Owned by the PM core */ bool may_skip_resume:1; /* Set by subsystems */ #else bool should_wakeup:1; diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index 903ddfea8585..f3cad182d4ef 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -815,6 +815,15 @@ struct sev_data_snp_commit { #ifdef CONFIG_CRYPTO_DEV_SP_PSP /** + * sev_module_init - perform PSP SEV module initialization + * + * Returns: + * 0 if the PSP module is successfully initialized + * negative value if the PSP module initialization fails + */ +int sev_module_init(void); + +/** * sev_platform_init - perform SEV INIT command * * @args: struct sev_platform_init_args to pass in arguments diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 0f2aeb37bbb0..ca1db4b92c32 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -43,6 +43,7 @@ struct kernel_clone_args { void *fn_arg; struct cgroup *cgrp; struct css_set *cset; + unsigned int kill_seq; }; /* diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index bd9836690da6..2d6c30317792 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -54,6 +54,8 @@ struct sdw_slave; #define SDW_MAX_PORTS 15 #define SDW_VALID_PORT_RANGE(n) ((n) < SDW_MAX_PORTS && (n) >= 1) +#define SDW_MAX_LANES 8 + enum { SDW_PORT_DIRN_SINK = 0, SDW_PORT_DIRN_SOURCE, @@ -356,6 +358,7 @@ struct sdw_dpn_prop { * and masks are supported * @commit_register_supported: is PCP_Commit register supported * @scp_int1_mask: SCP_INT1_MASK desired settings + * @lane_maps: Lane mapping for the slave, only valid if lane_control_support is set * @clock_reg_supported: the Peripheral implements the clock base and scale * registers introduced with the SoundWire 1.2 specification. SDCA devices * do not need to set this boolean property as the registers are required. @@ -385,6 +388,7 @@ struct sdw_slave_prop { u32 sdca_interrupt_register_list; u8 commit_register_supported; u8 scp_int1_mask; + u8 lane_maps[SDW_MAX_LANES]; bool clock_reg_supported; bool use_domain_irq; }; @@ -450,6 +454,7 @@ struct sdw_master_prop { int sdw_master_read_prop(struct sdw_bus *bus); int sdw_slave_read_prop(struct sdw_slave *slave); +int sdw_slave_read_lane_mapping(struct sdw_slave *slave); /* * SDW Slave Structures and APIs @@ -850,77 +855,6 @@ struct sdw_master_ops { int dev_num); }; -/** - * struct sdw_bus - SoundWire bus - * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. - * @md: Master device - * @bus_lock_key: bus lock key associated to @bus_lock - * @bus_lock: bus lock - * @slaves: list of Slaves on this bus - * @msg_lock_key: message lock key associated to @msg_lock - * @msg_lock: message lock - * @m_rt_list: List of Master instance of all stream(s) running on Bus. This - * is used to compute and program bus bandwidth, clock, frame shape, - * transport and port parameters - * @defer_msg: Defer message - * @params: Current bus parameters - * @stream_refcount: number of streams currently using this bus - * @ops: Master callback ops - * @port_ops: Master port callback ops - * @prop: Master properties - * @vendor_specific_prop: pointer to non-standard properties - * @hw_sync_min_links: Number of links used by a stream above which - * hardware-based synchronization is required. This value is only - * meaningful if multi_link is set. If set to 1, hardware-based - * synchronization will be used even if a stream only uses a single - * SoundWire segment. - * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used. - * @link_id: Link id number, can be 0 to N, unique for each Controller - * @id: bus system-wide unique id - * @compute_params: points to Bus resource management implementation - * @assigned: Bitmap for Slave device numbers. - * Bit set implies used number, bit clear implies unused number. - * @clk_stop_timeout: Clock stop timeout computed - * @bank_switch_timeout: Bank switch timeout computed - * @domain: IRQ domain - * @irq_chip: IRQ chip - * @debugfs: Bus debugfs (optional) - * @multi_link: Store bus property that indicates if multi links - * are supported. This flag is populated by drivers after reading - * appropriate firmware (ACPI/DT). - */ -struct sdw_bus { - struct device *dev; - struct sdw_master_device *md; - struct lock_class_key bus_lock_key; - struct mutex bus_lock; - struct list_head slaves; - struct lock_class_key msg_lock_key; - struct mutex msg_lock; - struct list_head m_rt_list; - struct sdw_defer defer_msg; - struct sdw_bus_params params; - int stream_refcount; - const struct sdw_master_ops *ops; - const struct sdw_master_port_ops *port_ops; - struct sdw_master_prop prop; - void *vendor_specific_prop; - int hw_sync_min_links; - int controller_id; - unsigned int link_id; - int id; - int (*compute_params)(struct sdw_bus *bus); - DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); - unsigned int clk_stop_timeout; - u32 bank_switch_timeout; - struct irq_chip irq_chip; - struct irq_domain *domain; -#ifdef CONFIG_DEBUG_FS - struct dentry *debugfs; -#endif - bool multi_link; -}; - int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, struct fwnode_handle *fwnode); void sdw_bus_master_delete(struct sdw_bus *bus); @@ -1010,10 +944,83 @@ struct sdw_stream_runtime { struct list_head master_list; }; +/** + * struct sdw_bus - SoundWire bus + * @dev: Shortcut to &bus->md->dev to avoid changing the entire code. + * @md: Master device + * @bus_lock_key: bus lock key associated to @bus_lock + * @bus_lock: bus lock + * @slaves: list of Slaves on this bus + * @msg_lock_key: message lock key associated to @msg_lock + * @msg_lock: message lock + * @m_rt_list: List of Master instance of all stream(s) running on Bus. This + * is used to compute and program bus bandwidth, clock, frame shape, + * transport and port parameters + * @defer_msg: Defer message + * @params: Current bus parameters + * @stream_refcount: number of streams currently using this bus + * @ops: Master callback ops + * @port_ops: Master port callback ops + * @prop: Master properties + * @vendor_specific_prop: pointer to non-standard properties + * @hw_sync_min_links: Number of links used by a stream above which + * hardware-based synchronization is required. This value is only + * meaningful if multi_link is set. If set to 1, hardware-based + * synchronization will be used even if a stream only uses a single + * SoundWire segment. + * @controller_id: system-unique controller ID. If set to -1, the bus @id will be used. + * @link_id: Link id number, can be 0 to N, unique for each Controller + * @id: bus system-wide unique id + * @compute_params: points to Bus resource management implementation + * @assigned: Bitmap for Slave device numbers. + * Bit set implies used number, bit clear implies unused number. + * @clk_stop_timeout: Clock stop timeout computed + * @bank_switch_timeout: Bank switch timeout computed + * @domain: IRQ domain + * @irq_chip: IRQ chip + * @debugfs: Bus debugfs (optional) + * @multi_link: Store bus property that indicates if multi links + * are supported. This flag is populated by drivers after reading + * appropriate firmware (ACPI/DT). + * @lane_used_bandwidth: how much bandwidth in bits per second is used by each lane + */ +struct sdw_bus { + struct device *dev; + struct sdw_master_device *md; + struct lock_class_key bus_lock_key; + struct mutex bus_lock; + struct list_head slaves; + struct lock_class_key msg_lock_key; + struct mutex msg_lock; + struct list_head m_rt_list; + struct sdw_defer defer_msg; + struct sdw_bus_params params; + int stream_refcount; + const struct sdw_master_ops *ops; + const struct sdw_master_port_ops *port_ops; + struct sdw_master_prop prop; + void *vendor_specific_prop; + int hw_sync_min_links; + int controller_id; + unsigned int link_id; + int id; + int (*compute_params)(struct sdw_bus *bus, struct sdw_stream_runtime *stream); + DECLARE_BITMAP(assigned, SDW_MAX_DEVICES); + unsigned int clk_stop_timeout; + u32 bank_switch_timeout; + struct irq_chip irq_chip; + struct irq_domain *domain; +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs; +#endif + bool multi_link; + unsigned int lane_used_bandwidth[SDW_MAX_LANES]; +}; + struct sdw_stream_runtime *sdw_alloc_stream(const char *stream_name); void sdw_release_stream(struct sdw_stream_runtime *stream); -int sdw_compute_params(struct sdw_bus *bus); +int sdw_compute_params(struct sdw_bus *bus, struct sdw_stream_runtime *stream); int sdw_stream_add_master(struct sdw_bus *bus, struct sdw_stream_config *stream_config, @@ -1034,6 +1041,7 @@ int sdw_bus_exit_clk_stop(struct sdw_bus *bus); int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id); void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id); +bool is_clock_scaling_supported_by_slave(struct sdw_slave *slave); #if IS_ENABLED(CONFIG_SOUNDWIRE) @@ -1045,6 +1053,8 @@ int sdw_stream_add_slave(struct sdw_slave *slave, int sdw_stream_remove_slave(struct sdw_slave *slave, struct sdw_stream_runtime *stream); +int sdw_slave_get_scale_index(struct sdw_slave *slave, u8 *base); + /* messaging and data APIs */ int sdw_read(struct sdw_slave *slave, u32 addr); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value); diff --git a/include/linux/stat.h b/include/linux/stat.h index 9d8382e23a9c..be7496a6a0dd 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -50,11 +50,11 @@ struct kstat { struct timespec64 btime; /* File creation time */ u64 blocks; u64 mnt_id; + u64 change_cookie; + u64 subvol; u32 dio_mem_align; u32 dio_offset_align; u32 dio_read_offset_align; - u64 change_cookie; - u64 subvol; u32 atomic_write_unit_min; u32 atomic_write_unit_max; u32 atomic_write_segments_max; diff --git a/include/linux/string.h b/include/linux/string.h index 86d5d352068b..f8e21e80942f 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -414,7 +414,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * must be discoverable by the compiler. */ #define strtomem_pad(dest, src, pad) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ @@ -437,7 +438,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * must be discoverable by the compiler. */ #define strtomem(dest, src) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ \ BUILD_BUG_ON(!__builtin_constant_p(_dest_len) || \ @@ -456,7 +458,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * Note that sizes of @dest and @src must be known at compile-time. */ #define memtostr(dest, src) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ @@ -481,7 +484,8 @@ void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, * Note that sizes of @dest and @src must be known at compile-time. */ #define memtostr_pad(dest, src) do { \ - const size_t _dest_len = __builtin_object_size(dest, 1); \ + const size_t _dest_len = __must_be_byte_array(dest) + \ + ARRAY_SIZE(dest); \ const size_t _src_len = __builtin_object_size(src, 1); \ const size_t _src_chars = strnlen(src, _src_len); \ const size_t _copy_len = min(_dest_len - 1, _src_chars); \ diff --git a/include/linux/swap.h b/include/linux/swap.h index a5f475335aea..b13b72645db3 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -222,6 +222,7 @@ enum { }; #define SWAP_CLUSTER_MAX 32UL +#define SWAP_CLUSTER_MAX_SKIPPED (SWAP_CLUSTER_MAX << 10) #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index d9c767cf773d..9189354c568f 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -668,7 +668,7 @@ struct l2cap_conn { struct l2cap_chan *smp; struct list_head chan_l; - struct mutex chan_lock; + struct mutex lock; struct kref ref; struct list_head users; }; @@ -970,6 +970,7 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err); void l2cap_send_conn_req(struct l2cap_chan *chan); struct l2cap_conn *l2cap_conn_get(struct l2cap_conn *conn); +struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *conn); void l2cap_conn_put(struct l2cap_conn *conn); int l2cap_register_user(struct l2cap_conn *conn, struct l2cap_user *user); diff --git a/include/net/gro.h b/include/net/gro.h index b9b58c1f8d19..7b548f91754b 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -11,6 +11,9 @@ #include <net/udp.h> #include <net/hotdata.h> +/* This should be increased if a protocol with a bigger head is added. */ +#define GRO_MAX_HEAD (MAX_HEADER + 128) + struct napi_gro_cb { union { struct { diff --git a/include/net/ip.h b/include/net/ip.h index 9f5e33e371fc..ba7b43447775 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -471,9 +471,12 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { const struct rtable *rt = dst_rtable(dst); - struct net *net = dev_net(dst->dev); - unsigned int mtu; + unsigned int mtu, res; + struct net *net; + + rcu_read_lock(); + net = dev_net_rcu(dst->dev); if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) || ip_mtu_locked(dst) || !forwarding) { @@ -497,7 +500,11 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); - return mtu - lwtunnel_headroom(dst->lwtstate, mtu); + res = mtu - lwtunnel_headroom(dst->lwtstate, mtu); + + rcu_read_unlock(); + + return res; } static inline unsigned int ip_skb_dst_mtu(struct sock *sk, diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 2d6141f28b53..f7fe796e8429 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -198,10 +198,12 @@ struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto) if (netif_is_l3_slave(dev)) { struct net_device *master; + rcu_read_lock(); master = netdev_master_upper_dev_get_rcu(dev); if (master && master->l3mdev_ops->l3mdev_l3_out) skb = master->l3mdev_ops->l3mdev_l3_out(master, sk, skb, proto); + rcu_read_unlock(); } return skb; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 0f5eb9db0c62..f467a66abc6b 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -297,6 +297,7 @@ static inline int check_net(const struct net *net) } void net_drop_ns(void *); +void net_passive_dec(struct net *net); #else @@ -326,8 +327,18 @@ static inline int check_net(const struct net *net) } #define net_drop_ns NULL + +static inline void net_passive_dec(struct net *net) +{ + refcount_dec(&net->passive); +} #endif +static inline void net_passive_inc(struct net *net) +{ + refcount_inc(&net->passive); +} + /* Returns true if the netns initialization is completed successfully */ static inline bool net_initialized(const struct net *net) { @@ -398,7 +409,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet) #endif } -static inline struct net *read_pnet_rcu(possible_net_t *pnet) +static inline struct net *read_pnet_rcu(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS return rcu_dereference(pnet->net); diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index ed4cd114180a..7f405672b089 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -237,7 +237,6 @@ struct page_pool { struct { struct hlist_node list; u64 detach_time; - u32 napi_id; u32 id; } user; }; diff --git a/include/net/route.h b/include/net/route.h index f86775be3e29..c605fd5ec0c0 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -382,10 +382,15 @@ static inline int inet_iif(const struct sk_buff *skb) static inline int ip4_dst_hoplimit(const struct dst_entry *dst) { int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT); - struct net *net = dev_net(dst->dev); - if (hoplimit == 0) + if (hoplimit == 0) { + const struct net *net; + + rcu_read_lock(); + net = dev_net_rcu(dst->dev); hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); + rcu_read_unlock(); + } return hoplimit; } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d635c5b47eba..d48c657191cd 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -851,7 +851,7 @@ static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch, } static inline void _bstats_update(struct gnet_stats_basic_sync *bstats, - __u64 bytes, __u32 packets) + __u64 bytes, __u64 packets) { u64_stats_update_begin(&bstats->syncp); u64_stats_add(&bstats->bytes, bytes); diff --git a/include/net/tcp.h b/include/net/tcp.h index 9c044fb9ab26..2d08473a6dc0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -41,6 +41,7 @@ #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> +#include <net/xfrm.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -683,6 +684,19 @@ void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); +static inline void tcp_cleanup_skb(struct sk_buff *skb) +{ + skb_dst_drop(skb); + secpath_reset(skb); +} + +static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb) +{ + DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); + DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb)); + __skb_queue_tail(&sk->sk_receive_queue, skb); +} + /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 4b0677e48190..ed4b83696c77 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1268,9 +1268,19 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, if (xo) { x = xfrm_input_state(skb); - if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) - return (xo->flags & CRYPTO_DONE) && - (xo->status & CRYPTO_SUCCESS); + if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) { + bool check = (xo->flags & CRYPTO_DONE) && + (xo->status & CRYPTO_SUCCESS); + + /* The packets here are plain ones and secpath was + * needed to indicate that hardware already handled + * them and there is no need to do nothing in addition. + * + * Consume secpath which was set by drivers. + */ + secpath_reset(skb); + return check; + } } return __xfrm_check_nopolicy(net, skb, dir) || diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 6e699cadcb29..f880835f7695 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -99,7 +99,7 @@ EM(netfs_sreq_trace_limited, "LIMIT") \ EM(netfs_sreq_trace_need_clear, "N-CLR") \ EM(netfs_sreq_trace_partial_read, "PARTR") \ - EM(netfs_sreq_trace_need_retry, "NRTRY") \ + EM(netfs_sreq_trace_need_retry, "ND-RT") \ EM(netfs_sreq_trace_prepare, "PREP ") \ EM(netfs_sreq_trace_prep_failed, "PRPFL") \ EM(netfs_sreq_trace_progress, "PRGRS") \ @@ -108,7 +108,9 @@ EM(netfs_sreq_trace_short, "SHORT") \ EM(netfs_sreq_trace_split, "SPLIT") \ EM(netfs_sreq_trace_submit, "SUBMT") \ + EM(netfs_sreq_trace_superfluous, "SPRFL") \ EM(netfs_sreq_trace_terminated, "TERM ") \ + EM(netfs_sreq_trace_wait_for, "_WAIT") \ EM(netfs_sreq_trace_write, "WRITE") \ EM(netfs_sreq_trace_write_skip, "SKIP ") \ E_(netfs_sreq_trace_write_term, "WTERM") diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 2f119d18a061..cad50d91077e 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -219,6 +219,7 @@ EM(rxrpc_conn_get_conn_input, "GET inp-conn") \ EM(rxrpc_conn_get_idle, "GET idle ") \ EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \ + EM(rxrpc_conn_get_poke_secured, "GET secured ") \ EM(rxrpc_conn_get_poke_timer, "GET poke ") \ EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ EM(rxrpc_conn_new_client, "NEW client ") \ diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index efe5de6ce208..aaa4f3bc688b 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -411,13 +411,20 @@ struct drm_amdgpu_gem_userptr { /* GFX12 and later: */ #define AMDGPU_TILING_GFX12_SWIZZLE_MODE_SHIFT 0 #define AMDGPU_TILING_GFX12_SWIZZLE_MODE_MASK 0x7 -/* These are DCC recompression setting for memory management: */ +/* These are DCC recompression settings for memory management: */ #define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_SHIFT 3 #define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_MASK 0x3 /* 0:64B, 1:128B, 2:256B */ #define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_SHIFT 5 #define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_MASK 0x7 /* CB_COLOR0_INFO.NUMBER_TYPE */ #define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_SHIFT 8 #define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_MASK 0x3f /* [0:4]:CB_COLOR0_INFO.FORMAT, [5]:MM */ +/* When clearing the buffer or moving it from VRAM to GTT, don't compress and set DCC metadata + * to uncompressed. Set when parts of an allocation bypass DCC and read raw data. */ +#define AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE_SHIFT 14 +#define AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE_MASK 0x1 +/* bit gap */ +#define AMDGPU_TILING_GFX12_SCANOUT_SHIFT 63 +#define AMDGPU_TILING_GFX12_SCANOUT_MASK 0x1 /* Set/Get helpers for tiling flags. */ #define AMDGPU_TILING_SET(field, value) \ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index d1089b88efc7..9b18c4cfe56f 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -682,6 +682,7 @@ enum ethtool_link_ext_substate_module { * @ETH_SS_STATS_ETH_CTRL: names of IEEE 802.3 MAC Control statistics * @ETH_SS_STATS_RMON: names of RMON statistics * @ETH_SS_STATS_PHY: names of PHY(dev) statistics + * @ETH_SS_TS_FLAGS: hardware timestamping flags * * @ETH_SS_COUNT: number of defined string sets */ @@ -708,6 +709,7 @@ enum ethtool_stringset { ETH_SS_STATS_ETH_CTRL, ETH_SS_STATS_RMON, ETH_SS_STATS_PHY, + ETH_SS_TS_FLAGS, /* add new constants above here */ ETH_SS_COUNT diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index f1e99458e29e..5e0eb41d967e 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -220,6 +220,15 @@ * * 7.41 * - add FUSE_ALLOW_IDMAP + * 7.42 + * - Add FUSE_OVER_IO_URING and all other io-uring related flags and data + * structures: + * - struct fuse_uring_ent_in_out + * - struct fuse_uring_req_header + * - struct fuse_uring_cmd_req + * - FUSE_URING_IN_OUT_HEADER_SZ + * - FUSE_URING_OP_IN_OUT_SZ + * - enum fuse_uring_cmd */ #ifndef _LINUX_FUSE_H @@ -255,7 +264,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 41 +#define FUSE_KERNEL_MINOR_VERSION 42 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -425,6 +434,7 @@ struct fuse_file_lock { * FUSE_HAS_RESEND: kernel supports resending pending requests, and the high bit * of the request ID indicates resend requests * FUSE_ALLOW_IDMAP: allow creation of idmapped mounts + * FUSE_OVER_IO_URING: Indicate that client supports io-uring */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -471,6 +481,7 @@ struct fuse_file_lock { /* Obsolete alias for FUSE_DIRECT_IO_ALLOW_MMAP */ #define FUSE_DIRECT_IO_RELAX FUSE_DIRECT_IO_ALLOW_MMAP #define FUSE_ALLOW_IDMAP (1ULL << 40) +#define FUSE_OVER_IO_URING (1ULL << 41) /** * CUSE INIT request/reply flags @@ -1206,4 +1217,67 @@ struct fuse_supp_groups { uint32_t groups[]; }; +/** + * Size of the ring buffer header + */ +#define FUSE_URING_IN_OUT_HEADER_SZ 128 +#define FUSE_URING_OP_IN_OUT_SZ 128 + +/* Used as part of the fuse_uring_req_header */ +struct fuse_uring_ent_in_out { + uint64_t flags; + + /* + * commit ID to be used in a reply to a ring request (see also + * struct fuse_uring_cmd_req) + */ + uint64_t commit_id; + + /* size of user payload buffer */ + uint32_t payload_sz; + uint32_t padding; + + uint64_t reserved; +}; + +/** + * Header for all fuse-io-uring requests + */ +struct fuse_uring_req_header { + /* struct fuse_in_header / struct fuse_out_header */ + char in_out[FUSE_URING_IN_OUT_HEADER_SZ]; + + /* per op code header */ + char op_in[FUSE_URING_OP_IN_OUT_SZ]; + + struct fuse_uring_ent_in_out ring_ent_in_out; +}; + +/** + * sqe commands to the kernel + */ +enum fuse_uring_cmd { + FUSE_IO_URING_CMD_INVALID = 0, + + /* register the request buffer and fetch a fuse request */ + FUSE_IO_URING_CMD_REGISTER = 1, + + /* commit fuse request result and fetch next request */ + FUSE_IO_URING_CMD_COMMIT_AND_FETCH = 2, +}; + +/** + * In the 80B command area of the SQE. + */ +struct fuse_uring_cmd_req { + uint64_t flags; + + /* entry identifier for commits */ + uint64_t commit_id; + + /* queue the command is for (queue index) */ + uint16_t qid; + uint8_t padding[6]; +}; + #endif /* _LINUX_FUSE_H */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 934e20ef7f79..95762232e018 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 14 +#define TASKSTATS_VERSION 15 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ diff --git a/include/uapi/linux/thermal.h b/include/uapi/linux/thermal.h index 349718c271eb..46a2633d33aa 100644 --- a/include/uapi/linux/thermal.h +++ b/include/uapi/linux/thermal.h @@ -30,7 +30,6 @@ enum thermal_genl_attr { THERMAL_GENL_ATTR_TZ, THERMAL_GENL_ATTR_TZ_ID, THERMAL_GENL_ATTR_TZ_TEMP, - THERMAL_GENL_ATTR_TZ_PREV_TEMP, THERMAL_GENL_ATTR_TZ_TRIP, THERMAL_GENL_ATTR_TZ_TRIP_ID, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, @@ -54,6 +53,7 @@ enum thermal_genl_attr { THERMAL_GENL_ATTR_THRESHOLD, THERMAL_GENL_ATTR_THRESHOLD_TEMP, THERMAL_GENL_ATTR_THRESHOLD_DIRECTION, + THERMAL_GENL_ATTR_TZ_PREV_TEMP, __THERMAL_GENL_ATTR_MAX, }; #define THERMAL_GENL_ATTR_MAX (__THERMAL_GENL_ATTR_MAX - 1) diff --git a/include/uapi/linux/virtio_snd.h b/include/uapi/linux/virtio_snd.h index 5f4100c2cf04..a4cfb9f6561a 100644 --- a/include/uapi/linux/virtio_snd.h +++ b/include/uapi/linux/virtio_snd.h @@ -25,7 +25,7 @@ struct virtio_snd_config { __le32 streams; /* # of available channel maps */ __le32 chmaps; - /* # of available control elements */ + /* # of available control elements (if VIRTIO_SND_F_CTLS) */ __le32 controls; }; diff --git a/include/uapi/mtd/ubi-user.h b/include/uapi/mtd/ubi-user.h index e1571603175e..aa872a41ffb9 100644 --- a/include/uapi/mtd/ubi-user.h +++ b/include/uapi/mtd/ubi-user.h @@ -175,6 +175,8 @@ #define UBI_IOCRPEB _IOW(UBI_IOC_MAGIC, 4, __s32) /* Force scrubbing on the specified PEB */ #define UBI_IOCSPEB _IOW(UBI_IOC_MAGIC, 5, __s32) +/* Read detailed device erase counter information */ +#define UBI_IOCECNFO _IOWR(UBI_IOC_MAGIC, 6, struct ubi_ecinfo_req) /* ioctl commands of the UBI control character device */ @@ -413,6 +415,37 @@ struct ubi_rnvol_req { } __packed; /** + * struct ubi_ecinfo_req - a data structure used for requesting and receiving + * erase block counter information from a UBI device. + * + * @start: index of first physical erase block to read (in) + * @length: number of erase counters to read (in) + * @read_length: number of erase counters that was actually read (out) + * @padding: reserved for future, not used, has to be zeroed + * @erase_counters: array of erase counter values (out) + * + * This structure is used to retrieve erase counter information for a specified + * range of PEBs on a UBI device. + * Erase counters are read from @start and attempts to read @length number of + * erase counters. + * The retrieved values are stored in the @erase_counters array. It is the + * responsibility of the caller to allocate enough memory for storing @length + * elements in the @erase_counters array. + * If a block is bad or if the erase counter is unknown the corresponding value + * in the array will be set to -1. + * The @read_length field will indicate the number of erase counters actually + * read. Typically @read_length will be limited due to memory or the number of + * PEBs on the UBI device. + */ +struct ubi_ecinfo_req { + __s32 start; + __s32 length; + __s32 read_length; + __s8 padding[16]; + __s32 erase_counters[]; +} __packed; + +/** * struct ubi_leb_change_req - a data structure used in atomic LEB change * requests. * @lnum: logical eraseblock number to change diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h index 89672ad8c3bb..f151feb0ca8c 100644 --- a/include/ufs/ufs.h +++ b/include/ufs/ufs.h @@ -385,8 +385,8 @@ enum { /* Possible values for dExtendedUFSFeaturesSupport */ enum { - UFS_DEV_LOW_TEMP_NOTIF = BIT(4), - UFS_DEV_HIGH_TEMP_NOTIF = BIT(5), + UFS_DEV_HIGH_TEMP_NOTIF = BIT(4), + UFS_DEV_LOW_TEMP_NOTIF = BIT(5), UFS_DEV_EXT_TEMP_NOTIF = BIT(6), UFS_DEV_HPB_SUPPORT = BIT(7), UFS_DEV_WRITE_BOOSTER_SUP = BIT(8), diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 650ff238cd74..8bf31e6ca4e5 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -1309,7 +1309,6 @@ static inline void ufshcd_rmwl(struct ufs_hba *hba, u32 mask, u32 val, u32 reg) void ufshcd_enable_irq(struct ufs_hba *hba); void ufshcd_disable_irq(struct ufs_hba *hba); int ufshcd_alloc_host(struct device *, struct ufs_hba **); -void ufshcd_dealloc_host(struct ufs_hba *); int ufshcd_hba_enable(struct ufs_hba *hba); int ufshcd_init(struct ufs_hba *, void __iomem *, unsigned int); int ufshcd_link_recovery(struct ufs_hba *hba); diff --git a/init/Kconfig b/init/Kconfig index 4dbc059d2de5..d0d021b3fa3b 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1969,7 +1969,8 @@ config RUST bool "Rust support" depends on HAVE_RUST depends on RUST_IS_AVAILABLE - depends on !MODVERSIONS + select EXTENDED_MODVERSIONS if MODVERSIONS + depends on !MODVERSIONS || GENDWARFKSYMS depends on !GCC_PLUGIN_RANDSTRUCT depends on !RANDSTRUCT depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index f86ef92a6c46..f6867bad0d78 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -21,7 +21,7 @@ phys_addr_t phys_initrd_start __initdata; unsigned long phys_initrd_size __initdata; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_do_mounts_initrd_table[] = { +static const struct ctl_table kern_do_mounts_initrd_table[] = { { .procname = "real-root-dev", .data = &real_root_dev, diff --git a/io_uring/Makefile b/io_uring/Makefile index 53167bef37d7..d695b60dba4f 100644 --- a/io_uring/Makefile +++ b/io_uring/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_IO_URING) += io_uring.o opdef.o kbuf.o rsrc.o notif.o \ sync.o msg_ring.o advise.o openclose.o \ epoll.o statx.o timeout.o fdinfo.o \ cancel.o waitid.o register.o \ - truncate.o memmap.o + truncate.o memmap.o alloc_cache.o obj-$(CONFIG_IO_WQ) += io-wq.o obj-$(CONFIG_FUTEX) += futex.o obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o diff --git a/io_uring/alloc_cache.c b/io_uring/alloc_cache.c new file mode 100644 index 000000000000..58423888b736 --- /dev/null +++ b/io_uring/alloc_cache.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "alloc_cache.h" + +void io_alloc_cache_free(struct io_alloc_cache *cache, + void (*free)(const void *)) +{ + void *entry; + + if (!cache->entries) + return; + + while ((entry = io_alloc_cache_get(cache)) != NULL) + free(entry); + + kvfree(cache->entries); + cache->entries = NULL; +} + +/* returns false if the cache was initialized properly */ +bool io_alloc_cache_init(struct io_alloc_cache *cache, + unsigned max_nr, unsigned int size, + unsigned int init_bytes) +{ + cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL); + if (!cache->entries) + return true; + + cache->nr_cached = 0; + cache->max_cached = max_nr; + cache->elem_size = size; + cache->init_clear = init_bytes; + return false; +} + +void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp) +{ + void *obj; + + obj = kmalloc(cache->elem_size, gfp); + if (obj && cache->init_clear) + memset(obj, 0, cache->init_clear); + return obj; +} diff --git a/io_uring/alloc_cache.h b/io_uring/alloc_cache.h index a3a8cfec32ce..0dd17d8ba93a 100644 --- a/io_uring/alloc_cache.h +++ b/io_uring/alloc_cache.h @@ -1,11 +1,30 @@ #ifndef IOU_ALLOC_CACHE_H #define IOU_ALLOC_CACHE_H +#include <linux/io_uring_types.h> + /* * Don't allow the cache to grow beyond this size. */ #define IO_ALLOC_CACHE_MAX 128 +void io_alloc_cache_free(struct io_alloc_cache *cache, + void (*free)(const void *)); +bool io_alloc_cache_init(struct io_alloc_cache *cache, + unsigned max_nr, unsigned int size, + unsigned int init_bytes); + +void *io_cache_alloc_new(struct io_alloc_cache *cache, gfp_t gfp); + +static inline void io_alloc_cache_kasan(struct iovec **iov, int *nr) +{ + if (IS_ENABLED(CONFIG_KASAN)) { + kfree(*iov); + *iov = NULL; + *nr = 0; + } +} + static inline bool io_alloc_cache_put(struct io_alloc_cache *cache, void *entry) { @@ -23,52 +42,30 @@ static inline void *io_alloc_cache_get(struct io_alloc_cache *cache) if (cache->nr_cached) { void *entry = cache->entries[--cache->nr_cached]; + /* + * If KASAN is enabled, always clear the initial bytes that + * must be zeroed post alloc, in case any of them overlap + * with KASAN storage. + */ +#if defined(CONFIG_KASAN) kasan_mempool_unpoison_object(entry, cache->elem_size); + if (cache->init_clear) + memset(entry, 0, cache->init_clear); +#endif return entry; } return NULL; } -static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp, - void (*init_once)(void *obj)) +static inline void *io_cache_alloc(struct io_alloc_cache *cache, gfp_t gfp) { - if (unlikely(!cache->nr_cached)) { - void *obj = kmalloc(cache->elem_size, gfp); + void *obj; - if (obj && init_once) - init_once(obj); + obj = io_alloc_cache_get(cache); + if (obj) return obj; - } - return io_alloc_cache_get(cache); + return io_cache_alloc_new(cache, gfp); } -/* returns false if the cache was initialized properly */ -static inline bool io_alloc_cache_init(struct io_alloc_cache *cache, - unsigned max_nr, size_t size) -{ - cache->entries = kvmalloc_array(max_nr, sizeof(void *), GFP_KERNEL); - if (cache->entries) { - cache->nr_cached = 0; - cache->max_cached = max_nr; - cache->elem_size = size; - return false; - } - return true; -} - -static inline void io_alloc_cache_free(struct io_alloc_cache *cache, - void (*free)(const void *)) -{ - void *entry; - - if (!cache->entries) - return; - - while ((entry = io_alloc_cache_get(cache)) != NULL) - free(entry); - - kvfree(cache->entries); - cache->entries = NULL; -} #endif diff --git a/io_uring/filetable.c b/io_uring/filetable.c index a21660e3145a..dd8eeec97acf 100644 --- a/io_uring/filetable.c +++ b/io_uring/filetable.c @@ -68,7 +68,7 @@ static int io_install_fixed_file(struct io_ring_ctx *ctx, struct file *file, if (slot_index >= ctx->file_table.data.nr) return -EINVAL; - node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(IORING_RSRC_FILE); if (!node) return -ENOMEM; diff --git a/io_uring/futex.c b/io_uring/futex.c index 30139cc150f2..43e2143255f5 100644 --- a/io_uring/futex.c +++ b/io_uring/futex.c @@ -36,7 +36,7 @@ struct io_futex_data { bool io_futex_cache_init(struct io_ring_ctx *ctx) { return io_alloc_cache_init(&ctx->futex_cache, IO_FUTEX_ALLOC_CACHE_MAX, - sizeof(struct io_futex_data)); + sizeof(struct io_futex_data), 0); } void io_futex_cache_free(struct io_ring_ctx *ctx) @@ -320,7 +320,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) } io_ring_submit_lock(ctx, issue_flags); - ifd = io_cache_alloc(&ctx->futex_cache, GFP_NOWAIT, NULL); + ifd = io_cache_alloc(&ctx->futex_cache, GFP_NOWAIT); if (!ifd) { ret = -ENOMEM; goto done_unlock; @@ -338,7 +338,7 @@ int io_futex_wait(struct io_kiocb *req, unsigned int issue_flags) hlist_add_head(&req->hash_node, &ctx->futex_list); io_ring_submit_unlock(ctx, issue_flags); - futex_queue(&ifd->q, hb); + futex_queue(&ifd->q, hb, NULL); return IOU_ISSUE_SKIP_COMPLETE; } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 7bfbc7c22367..ceacf6230e34 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -157,7 +157,7 @@ static int __read_mostly sysctl_io_uring_disabled; static int __read_mostly sysctl_io_uring_group = -1; #ifdef CONFIG_SYSCTL -static struct ctl_table kernel_io_uring_disabled_table[] = { +static const struct ctl_table kernel_io_uring_disabled_table[] = { { .procname = "io_uring_disabled", .data = &sysctl_io_uring_disabled, @@ -315,16 +315,18 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_LIST_HEAD(&ctx->cq_overflow_list); INIT_LIST_HEAD(&ctx->io_buffers_cache); ret = io_alloc_cache_init(&ctx->apoll_cache, IO_POLL_ALLOC_CACHE_MAX, - sizeof(struct async_poll)); + sizeof(struct async_poll), 0); ret |= io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_async_msghdr)); + sizeof(struct io_async_msghdr), + offsetof(struct io_async_msghdr, clear)); ret |= io_alloc_cache_init(&ctx->rw_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_async_rw)); + sizeof(struct io_async_rw), + offsetof(struct io_async_rw, clear)); ret |= io_alloc_cache_init(&ctx->uring_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_uring_cmd_data)); + sizeof(struct io_uring_cmd_data), 0); spin_lock_init(&ctx->msg_lock); ret |= io_alloc_cache_init(&ctx->msg_cache, IO_ALLOC_CACHE_MAX, - sizeof(struct io_kiocb)); + sizeof(struct io_kiocb), 0); ret |= io_futex_cache_init(ctx); if (ret) goto free_ref; diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h index f65e3f3ede51..ab619e63ef39 100644 --- a/io_uring/io_uring.h +++ b/io_uring/io_uring.h @@ -226,21 +226,16 @@ static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags) } static inline void *io_uring_alloc_async_data(struct io_alloc_cache *cache, - struct io_kiocb *req, - void (*init_once)(void *obj)) + struct io_kiocb *req) { - req->async_data = io_cache_alloc(cache, GFP_KERNEL, init_once); - if (req->async_data) - req->flags |= REQ_F_ASYNC_DATA; - return req->async_data; -} + if (cache) { + req->async_data = io_cache_alloc(cache, GFP_KERNEL); + } else { + const struct io_issue_def *def = &io_issue_defs[req->opcode]; -static inline void *io_uring_alloc_async_data_nocache(struct io_kiocb *req) -{ - const struct io_issue_def *def = &io_issue_defs[req->opcode]; - - WARN_ON_ONCE(!def->async_size); - req->async_data = kmalloc(def->async_size, GFP_KERNEL); + WARN_ON_ONCE(!def->async_size); + req->async_data = kmalloc(def->async_size, GFP_KERNEL); + } if (req->async_data) req->flags |= REQ_F_ASYNC_DATA; return req->async_data; diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c index 04bf493eecae..8e72de7712ac 100644 --- a/io_uring/kbuf.c +++ b/io_uring/kbuf.c @@ -415,6 +415,13 @@ void io_destroy_buffers(struct io_ring_ctx *ctx) } } +static void io_destroy_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl) +{ + scoped_guard(mutex, &ctx->mmap_lock) + WARN_ON_ONCE(xa_erase(&ctx->io_bl_xa, bl->bgid) != bl); + io_put_bl(ctx, bl); +} + int io_remove_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_provide_buf *p = io_kiocb_to_cmd(req, struct io_provide_buf); @@ -636,12 +643,13 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg) /* if mapped buffer ring OR classic exists, don't allow */ if (bl->flags & IOBL_BUF_RING || !list_empty(&bl->buf_list)) return -EEXIST; - } else { - free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL); - if (!bl) - return -ENOMEM; + io_destroy_bl(ctx, bl); } + free_bl = bl = kzalloc(sizeof(*bl), GFP_KERNEL); + if (!bl) + return -ENOMEM; + mmap_offset = (unsigned long)reg.bgid << IORING_OFF_PBUF_SHIFT; ring_size = flex_array_size(br, bufs, reg.ring_entries); diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index bd3cd78d2dba..7e6f68e911f1 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -89,8 +89,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, struct io_tw_state *ts) static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, int res, u32 cflags, u64 user_data) { - req->tctx = READ_ONCE(ctx->submitter_task->io_uring); - if (!req->tctx) { + if (!READ_ONCE(ctx->submitter_task)) { kmem_cache_free(req_cachep, req); return -EOWNERDEAD; } @@ -98,6 +97,7 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req, io_req_set_res(req, res, cflags); percpu_ref_get(&ctx->refs); req->ctx = ctx; + req->tctx = NULL; req->io_task_work.func = io_msg_tw_complete; io_req_task_work_add_remote(req, ctx, IOU_F_TWQ_LAZY_WAKE); return 0; diff --git a/io_uring/net.c b/io_uring/net.c index 85f55fbc25c9..17852a6616ff 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -137,7 +137,6 @@ static void io_netmsg_iovec_free(struct io_async_msghdr *kmsg) static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_msghdr *hdr = req->async_data; - struct iovec *iov; /* can't recycle, ensure we free the iovec if we have one */ if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) { @@ -146,44 +145,30 @@ static void io_netmsg_recycle(struct io_kiocb *req, unsigned int issue_flags) } /* Let normal cleanup path reap it if we fail adding to the cache */ - iov = hdr->free_iov; + io_alloc_cache_kasan(&hdr->free_iov, &hdr->free_iov_nr); if (io_alloc_cache_put(&req->ctx->netmsg_cache, hdr)) { - if (iov) - kasan_mempool_poison_object(iov); req->async_data = NULL; req->flags &= ~REQ_F_ASYNC_DATA; } } -static void io_msg_async_data_init(void *obj) -{ - struct io_async_msghdr *hdr = (struct io_async_msghdr *)obj; - - hdr->free_iov = NULL; - hdr->free_iov_nr = 0; -} - static struct io_async_msghdr *io_msg_alloc_async(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct io_async_msghdr *hdr; - hdr = io_uring_alloc_async_data(&ctx->netmsg_cache, req, - io_msg_async_data_init); + hdr = io_uring_alloc_async_data(&ctx->netmsg_cache, req); if (!hdr) return NULL; /* If the async data was cached, we might have an iov cached inside. */ - if (hdr->free_iov) { - kasan_mempool_unpoison_object(hdr->free_iov, - hdr->free_iov_nr * sizeof(struct iovec)); + if (hdr->free_iov) req->flags |= REQ_F_NEED_CLEANUP; - } return hdr; } /* assign new iovec to kmsg, if we need to */ -static int io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg, +static void io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg, struct iovec *iov) { if (iov) { @@ -193,7 +178,6 @@ static int io_net_vec_assign(struct io_kiocb *req, struct io_async_msghdr *kmsg, kfree(kmsg->free_iov); kmsg->free_iov = iov; } - return 0; } static inline void io_mshot_prep_retry(struct io_kiocb *req, @@ -255,7 +239,8 @@ static int io_compat_msg_copy_hdr(struct io_kiocb *req, if (unlikely(ret < 0)) return ret; - return io_net_vec_assign(req, iomsg, iov); + io_net_vec_assign(req, iomsg, iov); + return 0; } #endif @@ -295,11 +280,12 @@ static int io_msg_copy_hdr(struct io_kiocb *req, struct io_async_msghdr *iomsg, ret = -EINVAL; goto ua_end; } else { + struct iovec __user *uiov = msg->msg_iov; + /* we only need the length for provided buffers */ - if (!access_ok(&msg->msg_iov[0].iov_len, sizeof(__kernel_size_t))) + if (!access_ok(&uiov->iov_len, sizeof(uiov->iov_len))) goto ua_end; - unsafe_get_user(iov->iov_len, &msg->msg_iov[0].iov_len, - ua_end); + unsafe_get_user(iov->iov_len, &uiov->iov_len, ua_end); sr->len = iov->iov_len; } ret = 0; @@ -314,7 +300,8 @@ ua_end: if (unlikely(ret < 0)) return ret; - return io_net_vec_assign(req, iomsg, iov); + io_net_vec_assign(req, iomsg, iov); + return 0; } static int io_sendmsg_copy_hdr(struct io_kiocb *req, @@ -579,6 +566,54 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) return IOU_OK; } +static int io_send_select_buffer(struct io_kiocb *req, unsigned int issue_flags, + struct io_async_msghdr *kmsg) +{ + struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); + + int ret; + struct buf_sel_arg arg = { + .iovs = &kmsg->fast_iov, + .max_len = min_not_zero(sr->len, INT_MAX), + .nr_iovs = 1, + }; + + if (kmsg->free_iov) { + arg.nr_iovs = kmsg->free_iov_nr; + arg.iovs = kmsg->free_iov; + arg.mode = KBUF_MODE_FREE; + } + + if (!(sr->flags & IORING_RECVSEND_BUNDLE)) + arg.nr_iovs = 1; + else + arg.mode |= KBUF_MODE_EXPAND; + + ret = io_buffers_select(req, &arg, issue_flags); + if (unlikely(ret < 0)) + return ret; + + if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) { + kmsg->free_iov_nr = ret; + kmsg->free_iov = arg.iovs; + req->flags |= REQ_F_NEED_CLEANUP; + } + sr->len = arg.out_len; + + if (ret == 1) { + sr->buf = arg.iovs[0].iov_base; + ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, + &kmsg->msg.msg_iter); + if (unlikely(ret)) + return ret; + } else { + iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE, + arg.iovs, ret, arg.out_len); + } + + return 0; +} + int io_send(struct io_kiocb *req, unsigned int issue_flags) { struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg); @@ -602,44 +637,9 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags) retry_bundle: if (io_do_buffer_select(req)) { - struct buf_sel_arg arg = { - .iovs = &kmsg->fast_iov, - .max_len = min_not_zero(sr->len, INT_MAX), - .nr_iovs = 1, - }; - - if (kmsg->free_iov) { - arg.nr_iovs = kmsg->free_iov_nr; - arg.iovs = kmsg->free_iov; - arg.mode = KBUF_MODE_FREE; - } - - if (!(sr->flags & IORING_RECVSEND_BUNDLE)) - arg.nr_iovs = 1; - else - arg.mode |= KBUF_MODE_EXPAND; - - ret = io_buffers_select(req, &arg, issue_flags); - if (unlikely(ret < 0)) + ret = io_send_select_buffer(req, issue_flags, kmsg); + if (ret) return ret; - - if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) { - kmsg->free_iov_nr = ret; - kmsg->free_iov = arg.iovs; - req->flags |= REQ_F_NEED_CLEANUP; - } - sr->len = arg.out_len; - - if (ret == 1) { - sr->buf = arg.iovs[0].iov_base; - ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len, - &kmsg->msg.msg_iter); - if (unlikely(ret)) - return ret; - } else { - iov_iter_init(&kmsg->msg.msg_iter, ITER_SOURCE, - arg.iovs, ret, arg.out_len); - } } /* @@ -1710,6 +1710,11 @@ int io_connect(struct io_kiocb *req, unsigned int issue_flags) int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + if (unlikely(req->flags & REQ_F_FAIL)) { + ret = -ECONNRESET; + goto out; + } + file_flags = force_nonblock ? O_NONBLOCK : 0; ret = __sys_connect_file(req->file, &io->addr, connect->addr_len, @@ -1813,11 +1818,8 @@ void io_netmsg_cache_free(const void *entry) { struct io_async_msghdr *kmsg = (struct io_async_msghdr *) entry; - if (kmsg->free_iov) { - kasan_mempool_unpoison_object(kmsg->free_iov, - kmsg->free_iov_nr * sizeof(struct iovec)); + if (kmsg->free_iov) io_netmsg_iovec_free(kmsg); - } kfree(kmsg); } #endif diff --git a/io_uring/net.h b/io_uring/net.h index 52bfee05f06a..b804c2b36e60 100644 --- a/io_uring/net.h +++ b/io_uring/net.h @@ -5,16 +5,20 @@ struct io_async_msghdr { #if defined(CONFIG_NET) - struct iovec fast_iov; - /* points to an allocated iov, if NULL we use fast_iov instead */ struct iovec *free_iov; + /* points to an allocated iov, if NULL we use fast_iov instead */ int free_iov_nr; - int namelen; - __kernel_size_t controllen; - __kernel_size_t payloadlen; - struct sockaddr __user *uaddr; - struct msghdr msg; - struct sockaddr_storage addr; + struct_group(clear, + int namelen; + struct iovec fast_iov; + __kernel_size_t controllen; + __kernel_size_t payloadlen; + struct sockaddr __user *uaddr; + struct msghdr msg; + struct sockaddr_storage addr; + ); +#else + struct_group(clear); #endif }; diff --git a/io_uring/poll.c b/io_uring/poll.c index cc01c40b43d3..bb1c0cd4f809 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -273,6 +273,8 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts) return IOU_POLL_REISSUE; } } + if (unlikely(req->cqe.res & EPOLLERR)) + req_set_fail(req); if (req->apoll_events & EPOLLONESHOT) return IOU_POLL_DONE; @@ -315,8 +317,10 @@ void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts) ret = io_poll_check_events(req, ts); if (ret == IOU_POLL_NO_ACTION) { + io_kbuf_recycle(req, 0); return; } else if (ret == IOU_POLL_REQUEUE) { + io_kbuf_recycle(req, 0); __io_poll_execute(req, 0); return; } @@ -650,7 +654,7 @@ static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req, kfree(apoll->double_poll); } else { if (!(issue_flags & IO_URING_F_UNLOCKED)) - apoll = io_cache_alloc(&ctx->apoll_cache, GFP_ATOMIC, NULL); + apoll = io_cache_alloc(&ctx->apoll_cache, GFP_ATOMIC); else apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (!apoll) diff --git a/io_uring/register.c b/io_uring/register.c index 05025047d1da..9a4d2fbce4ae 100644 --- a/io_uring/register.c +++ b/io_uring/register.c @@ -552,7 +552,7 @@ overflow: ctx->cqe_cached = ctx->cqe_sentinel = NULL; WRITE_ONCE(n.rings->sq_dropped, READ_ONCE(o.rings->sq_dropped)); - WRITE_ONCE(n.rings->sq_flags, READ_ONCE(o.rings->sq_flags)); + atomic_set(&n.rings->sq_flags, atomic_read(&o.rings->sq_flags)); WRITE_ONCE(n.rings->cq_flags, READ_ONCE(o.rings->cq_flags)); WRITE_ONCE(n.rings->cq_overflow, READ_ONCE(o.rings->cq_overflow)); @@ -853,6 +853,8 @@ struct file *io_uring_register_get_file(unsigned int fd, bool registered) return ERR_PTR(-EINVAL); fd = array_index_nospec(fd, IO_RINGFD_REG_MAX); file = tctx->registered_rings[fd]; + if (file) + get_file(file); } else { file = fget(fd); } @@ -919,7 +921,7 @@ SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode, trace_io_uring_register(ctx, opcode, ctx->file_table.data.nr, ctx->buf_table.nr, ret); mutex_unlock(&ctx->uring_lock); - if (!use_registered_ring) - fput(file); + + fput(file); return ret; } diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c index e32ac5853391..af39b69eb4fd 100644 --- a/io_uring/rsrc.c +++ b/io_uring/rsrc.c @@ -118,7 +118,7 @@ static void io_buffer_unmap(struct io_ring_ctx *ctx, struct io_rsrc_node *node) } } -struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type) +struct io_rsrc_node *io_rsrc_node_alloc(int type) { struct io_rsrc_node *node; @@ -203,7 +203,7 @@ static int __io_sqe_files_update(struct io_ring_ctx *ctx, err = -EBADF; break; } - node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(IORING_RSRC_FILE); if (!node) { err = -ENOMEM; fput(file); @@ -444,8 +444,6 @@ int io_files_update(struct io_kiocb *req, unsigned int issue_flags) void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node) { - lockdep_assert_held(&ctx->uring_lock); - if (node->tag) io_post_aux_cqe(ctx, node->tag, 0, 0); @@ -525,7 +523,7 @@ int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg, goto fail; } ret = -ENOMEM; - node = io_rsrc_node_alloc(ctx, IORING_RSRC_FILE); + node = io_rsrc_node_alloc(IORING_RSRC_FILE); if (!node) { fput(file); goto fail; @@ -730,7 +728,7 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx, if (!iov->iov_base) return NULL; - node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER); + node = io_rsrc_node_alloc(IORING_RSRC_BUFFER); if (!node) return ERR_PTR(-ENOMEM); node->buf = NULL; @@ -921,6 +919,16 @@ int io_import_fixed(int ddir, struct iov_iter *iter, return 0; } +/* Lock two rings at once. The rings must be different! */ +static void lock_two_rings(struct io_ring_ctx *ctx1, struct io_ring_ctx *ctx2) +{ + if (ctx1 > ctx2) + swap(ctx1, ctx2); + mutex_lock(&ctx1->uring_lock); + mutex_lock_nested(&ctx2->uring_lock, SINGLE_DEPTH_NESTING); +} + +/* Both rings are locked by the caller. */ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx, struct io_uring_clone_buffers *arg) { @@ -928,6 +936,9 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx int i, ret, off, nr; unsigned int nbufs; + lockdep_assert_held(&ctx->uring_lock); + lockdep_assert_held(&src_ctx->uring_lock); + /* * Accounting state is shared between the two rings; that only works if * both rings are accounted towards the same counters. @@ -942,7 +953,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx if (ctx->buf_table.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE)) return -EBUSY; - nbufs = READ_ONCE(src_ctx->buf_table.nr); + nbufs = src_ctx->buf_table.nr; if (!arg->nr) arg->nr = nbufs; else if (arg->nr > nbufs) @@ -966,27 +977,20 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx } } - /* - * Drop our own lock here. We'll setup the data we need and reference - * the source buffers, then re-grab, check, and assign at the end. - */ - mutex_unlock(&ctx->uring_lock); - - mutex_lock(&src_ctx->uring_lock); ret = -ENXIO; nbufs = src_ctx->buf_table.nr; if (!nbufs) - goto out_unlock; + goto out_free; ret = -EINVAL; if (!arg->nr) arg->nr = nbufs; else if (arg->nr > nbufs) - goto out_unlock; + goto out_free; ret = -EOVERFLOW; if (check_add_overflow(arg->nr, arg->src_off, &off)) - goto out_unlock; + goto out_free; if (off > nbufs) - goto out_unlock; + goto out_free; off = arg->dst_off; i = arg->src_off; @@ -998,10 +1002,10 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx if (!src_node) { dst_node = NULL; } else { - dst_node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER); + dst_node = io_rsrc_node_alloc(IORING_RSRC_BUFFER); if (!dst_node) { ret = -ENOMEM; - goto out_unlock; + goto out_free; } refcount_inc(&src_node->buf->refs); @@ -1011,10 +1015,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx i++; } - /* Have a ref on the bufs now, drop src lock and re-grab our own lock */ - mutex_unlock(&src_ctx->uring_lock); - mutex_lock(&ctx->uring_lock); - /* * If asked for replace, put the old table. data->nodes[] holds both * old and new nodes at this point. @@ -1023,24 +1023,17 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx io_rsrc_data_free(ctx, &ctx->buf_table); /* - * ctx->buf_table should be empty now - either the contents are being - * replaced and we just freed the table, or someone raced setting up - * a buffer table while the clone was happening. If not empty, fall - * through to failure handling. + * ctx->buf_table must be empty now - either the contents are being + * replaced and we just freed the table, or the contents are being + * copied to a ring that does not have buffers yet (checked at function + * entry). */ - if (!ctx->buf_table.nr) { - ctx->buf_table = data; - return 0; - } + WARN_ON_ONCE(ctx->buf_table.nr); + ctx->buf_table = data; + return 0; - mutex_unlock(&ctx->uring_lock); - mutex_lock(&src_ctx->uring_lock); - /* someone raced setting up buffers, dump ours */ - ret = -EBUSY; -out_unlock: +out_free: io_rsrc_data_free(ctx, &data); - mutex_unlock(&src_ctx->uring_lock); - mutex_lock(&ctx->uring_lock); return ret; } @@ -1054,6 +1047,7 @@ out_unlock: int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg) { struct io_uring_clone_buffers buf; + struct io_ring_ctx *src_ctx; bool registered_src; struct file *file; int ret; @@ -1071,8 +1065,18 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg) file = io_uring_register_get_file(buf.src_fd, registered_src); if (IS_ERR(file)) return PTR_ERR(file); - ret = io_clone_buffers(ctx, file->private_data, &buf); - if (!registered_src) - fput(file); + + src_ctx = file->private_data; + if (src_ctx != ctx) { + mutex_unlock(&ctx->uring_lock); + lock_two_rings(ctx, src_ctx); + } + + ret = io_clone_buffers(ctx, src_ctx, &buf); + + if (src_ctx != ctx) + mutex_unlock(&src_ctx->uring_lock); + + fput(file); return ret; } diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index c8b093584461..190f7ee45de9 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -2,6 +2,8 @@ #ifndef IOU_RSRC_H #define IOU_RSRC_H +#include <linux/lockdep.h> + #define IO_NODE_ALLOC_CACHE_MAX 32 #define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) @@ -43,7 +45,7 @@ struct io_imu_folio_data { unsigned int nr_folios; }; -struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx, int type); +struct io_rsrc_node *io_rsrc_node_alloc(int type); void io_free_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node); void io_rsrc_data_free(struct io_ring_ctx *ctx, struct io_rsrc_data *data); int io_rsrc_data_alloc(struct io_rsrc_data *data, unsigned nr); @@ -80,6 +82,7 @@ static inline struct io_rsrc_node *io_rsrc_node_lookup(struct io_rsrc_data *data static inline void io_put_rsrc_node(struct io_ring_ctx *ctx, struct io_rsrc_node *node) { + lockdep_assert_held(&ctx->uring_lock); if (node && !--node->refs) io_free_rsrc_node(ctx, node); } diff --git a/io_uring/rw.c b/io_uring/rw.c index a9a2733be842..7aa1e4c9f64a 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -146,28 +146,15 @@ static inline int io_import_iovec(int rw, struct io_kiocb *req, return 0; } -static void io_rw_iovec_free(struct io_async_rw *rw) -{ - if (rw->free_iovec) { - kfree(rw->free_iovec); - rw->free_iov_nr = 0; - rw->free_iovec = NULL; - } -} - static void io_rw_recycle(struct io_kiocb *req, unsigned int issue_flags) { struct io_async_rw *rw = req->async_data; - struct iovec *iov; - if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) { - io_rw_iovec_free(rw); + if (unlikely(issue_flags & IO_URING_F_UNLOCKED)) return; - } - iov = rw->free_iovec; + + io_alloc_cache_kasan(&rw->free_iovec, &rw->free_iov_nr); if (io_alloc_cache_put(&req->ctx->rw_cache, rw)) { - if (iov) - kasan_mempool_poison_object(iov); req->async_data = NULL; req->flags &= ~REQ_F_ASYNC_DATA; } @@ -208,27 +195,16 @@ static void io_req_rw_cleanup(struct io_kiocb *req, unsigned int issue_flags) } } -static void io_rw_async_data_init(void *obj) -{ - struct io_async_rw *rw = (struct io_async_rw *)obj; - - rw->free_iovec = NULL; - rw->bytes_done = 0; -} - static int io_rw_alloc_async(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; struct io_async_rw *rw; - rw = io_uring_alloc_async_data(&ctx->rw_cache, req, io_rw_async_data_init); + rw = io_uring_alloc_async_data(&ctx->rw_cache, req); if (!rw) return -ENOMEM; - if (rw->free_iovec) { - kasan_mempool_unpoison_object(rw->free_iovec, - rw->free_iov_nr * sizeof(struct iovec)); + if (rw->free_iovec) req->flags |= REQ_F_NEED_CLEANUP; - } rw->bytes_done = 0; return 0; } @@ -1323,10 +1299,7 @@ void io_rw_cache_free(const void *entry) { struct io_async_rw *rw = (struct io_async_rw *) entry; - if (rw->free_iovec) { - kasan_mempool_unpoison_object(rw->free_iovec, - rw->free_iov_nr * sizeof(struct iovec)); - io_rw_iovec_free(rw); - } + if (rw->free_iovec) + kfree(rw->free_iovec); kfree(rw); } diff --git a/io_uring/rw.h b/io_uring/rw.h index 2d7656bd268d..eaa59bd64870 100644 --- a/io_uring/rw.h +++ b/io_uring/rw.h @@ -9,19 +9,24 @@ struct io_meta_state { struct io_async_rw { size_t bytes_done; - struct iov_iter iter; - struct iov_iter_state iter_state; - struct iovec fast_iov; struct iovec *free_iovec; - int free_iov_nr; - /* wpq is for buffered io, while meta fields are used with direct io */ - union { - struct wait_page_queue wpq; - struct { - struct uio_meta meta; - struct io_meta_state meta_state; + struct_group(clear, + struct iov_iter iter; + struct iov_iter_state iter_state; + struct iovec fast_iov; + int free_iov_nr; + /* + * wpq is for buffered io, while meta fields are used with + * direct io + */ + union { + struct wait_page_queue wpq; + struct { + struct uio_meta meta; + struct io_meta_state meta_state; + }; }; - }; + ); }; int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe); diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 2bd7e0a317bb..48fc8cf70784 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -544,7 +544,7 @@ static int __io_timeout_prep(struct io_kiocb *req, if (WARN_ON_ONCE(req_has_async_data(req))) return -EFAULT; - data = io_uring_alloc_async_data_nocache(req); + data = io_uring_alloc_async_data(NULL, req); if (!data) return -ENOMEM; data->req = req; diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index fc94c465a985..e6701b7aa147 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -54,9 +54,6 @@ bool io_uring_try_cancel_uring_cmd(struct io_ring_ctx *ctx, continue; if (cmd->flags & IORING_URING_CMD_CANCELABLE) { - /* ->sqe isn't available if no async data */ - if (!req_has_async_data(req)) - cmd->sqe = NULL; file->f_op->uring_cmd(cmd, IO_URING_F_CANCEL | IO_URING_F_COMPLETE_DEFER); ret = true; @@ -168,32 +165,26 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, u64 res2, } EXPORT_SYMBOL_GPL(io_uring_cmd_done); -static void io_uring_cmd_init_once(void *obj) -{ - struct io_uring_cmd_data *data = obj; - - data->op_data = NULL; -} - static int io_uring_cmd_prep_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); struct io_uring_cmd_data *cache; - cache = io_uring_alloc_async_data(&req->ctx->uring_cache, req, - io_uring_cmd_init_once); + cache = io_uring_alloc_async_data(&req->ctx->uring_cache, req); if (!cache) return -ENOMEM; - - if (!(req->flags & REQ_F_FORCE_ASYNC)) { - /* defer memcpy until we need it */ - ioucmd->sqe = sqe; - return 0; - } - - memcpy(req->async_data, sqe, uring_sqe_size(req->ctx)); - ioucmd->sqe = req->async_data; + cache->op_data = NULL; + + /* + * Unconditionally cache the SQE for now - this is only needed for + * requests that go async, but prep handlers must ensure that any + * sqe data is stable beyond prep. Since uring_cmd is special in + * that it doesn't read in per-op data, play it safe and ensure that + * any SQE data is stable beyond prep. This can later get relaxed. + */ + memcpy(cache->sqes, sqe, uring_sqe_size(req->ctx)); + ioucmd->sqe = cache->sqes; return 0; } @@ -256,16 +247,8 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags) } ret = file->f_op->uring_cmd(ioucmd, issue_flags); - if (ret == -EAGAIN) { - struct io_uring_cmd_data *cache = req->async_data; - - if (ioucmd->sqe != (void *) cache) - memcpy(cache, ioucmd->sqe, uring_sqe_size(req->ctx)); - return -EAGAIN; - } else if (ret == -EIOCBQUEUED) { - return -EIOCBQUEUED; - } - + if (ret == -EAGAIN || ret == -EIOCBQUEUED) + return ret; if (ret < 0) req_set_fail(req); io_req_uring_cleanup(req, issue_flags); @@ -350,7 +333,7 @@ int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags) if (!prot || !prot->ioctl) return -EOPNOTSUPP; - switch (cmd->sqe->cmd_op) { + switch (cmd->cmd_op) { case SOCKET_URING_OP_SIOCINQ: ret = prot->ioctl(sk, SIOCINQ, &arg); if (ret) diff --git a/io_uring/waitid.c b/io_uring/waitid.c index 6778c0ee76c4..15a7daf3ff4f 100644 --- a/io_uring/waitid.c +++ b/io_uring/waitid.c @@ -118,7 +118,6 @@ static int io_waitid_finish(struct io_kiocb *req, int ret) static void io_waitid_complete(struct io_kiocb *req, int ret) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); - struct io_tw_state ts = {}; /* anyone completing better be holding a reference */ WARN_ON_ONCE(!(atomic_read(&iw->refs) & IO_WAITID_REF_MASK)); @@ -131,7 +130,6 @@ static void io_waitid_complete(struct io_kiocb *req, int ret) if (ret < 0) req_set_fail(req); io_req_set_res(req, ret, 0); - io_req_task_complete(req, &ts); } static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) @@ -153,6 +151,7 @@ static bool __io_waitid_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) list_del_init(&iwa->wo.child_wait.entry); spin_unlock_irq(&iw->head->lock); io_waitid_complete(req, -ECANCELED); + io_req_queue_tw_complete(req, -ECANCELED); return true; } @@ -258,6 +257,7 @@ static void io_waitid_cb(struct io_kiocb *req, struct io_tw_state *ts) } io_waitid_complete(req, ret); + io_req_task_complete(req, ts); } static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, @@ -285,10 +285,16 @@ static int io_waitid_wait(struct wait_queue_entry *wait, unsigned mode, int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa; if (sqe->addr || sqe->buf_index || sqe->addr3 || sqe->waitid_flags) return -EINVAL; + iwa = io_uring_alloc_async_data(NULL, req); + if (!unlikely(iwa)) + return -ENOMEM; + iwa->req = req; + iw->which = READ_ONCE(sqe->len); iw->upid = READ_ONCE(sqe->fd); iw->options = READ_ONCE(sqe->file_index); @@ -299,16 +305,10 @@ int io_waitid_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) int io_waitid(struct io_kiocb *req, unsigned int issue_flags) { struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid); + struct io_waitid_async *iwa = req->async_data; struct io_ring_ctx *ctx = req->ctx; - struct io_waitid_async *iwa; int ret; - iwa = io_uring_alloc_async_data_nocache(req); - if (!iwa) - return -ENOMEM; - - iwa->req = req; - ret = kernel_waitid_prepare(&iwa->wo, iw->which, iw->upid, &iw->info, iw->options, NULL); if (ret) diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 54318e0b4557..15b17e86e198 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -73,7 +73,7 @@ int ipc_mni = IPCMNI; int ipc_mni_shift = IPCMNI_SHIFT; int ipc_min_cycle = RADIX_TREE_MAP_SIZE; -static struct ctl_table ipc_sysctls[] = { +static const struct ctl_table ipc_sysctls[] = { { .procname = "shmmax", .data = &init_ipc_ns.shm_ctlmax, diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index b70dc2ff22d8..0dd12e1c9f53 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -20,7 +20,7 @@ static int msg_max_limit_max = HARD_MSGMAX; static int msg_maxsize_limit_min = MIN_MSGSIZEMAX; static int msg_maxsize_limit_max = HARD_MSGSIZEMAX; -static struct ctl_table mq_sysctls[] = { +static const struct ctl_table mq_sysctls[] = { { .procname = "queues_max", .data = &init_ipc_ns.mq_queues_max, diff --git a/kernel/acct.c b/kernel/acct.c index 179848ad33e9..6520baa13669 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -76,7 +76,7 @@ static int acct_parm[3] = {4, 2, 30}; #define ACCT_TIMEOUT (acct_parm[2]) /* foo second timeout between checks */ #ifdef CONFIG_SYSCTL -static struct ctl_table kern_acct_table[] = { +static const struct ctl_table kern_acct_table[] = { { .procname = "acct", .data = &acct_parm, @@ -103,48 +103,50 @@ struct bsd_acct_struct { atomic_long_t count; struct rcu_head rcu; struct mutex lock; - int active; + bool active; + bool check_space; unsigned long needcheck; struct file *file; struct pid_namespace *ns; struct work_struct work; struct completion done; + acct_t ac; }; -static void do_acct_process(struct bsd_acct_struct *acct); +static void fill_ac(struct bsd_acct_struct *acct); +static void acct_write_process(struct bsd_acct_struct *acct); /* * Check the amount of free space and suspend/resume accordingly. */ -static int check_free_space(struct bsd_acct_struct *acct) +static bool check_free_space(struct bsd_acct_struct *acct) { struct kstatfs sbuf; - if (time_is_after_jiffies(acct->needcheck)) - goto out; + if (!acct->check_space) + return acct->active; /* May block */ if (vfs_statfs(&acct->file->f_path, &sbuf)) - goto out; + return acct->active; if (acct->active) { u64 suspend = sbuf.f_blocks * SUSPEND; do_div(suspend, 100); if (sbuf.f_bavail <= suspend) { - acct->active = 0; + acct->active = false; pr_info("Process accounting paused\n"); } } else { u64 resume = sbuf.f_blocks * RESUME; do_div(resume, 100); if (sbuf.f_bavail >= resume) { - acct->active = 1; + acct->active = true; pr_info("Process accounting resumed\n"); } } acct->needcheck = jiffies + ACCT_TIMEOUT*HZ; -out: return acct->active; } @@ -189,7 +191,11 @@ static void acct_pin_kill(struct fs_pin *pin) { struct bsd_acct_struct *acct = to_acct(pin); mutex_lock(&acct->lock); - do_acct_process(acct); + /* + * Fill the accounting struct with the exiting task's info + * before punting to the workqueue. + */ + fill_ac(acct); schedule_work(&acct->work); wait_for_completion(&acct->done); cmpxchg(&acct->ns->bacct, pin, NULL); @@ -202,6 +208,9 @@ static void close_work(struct work_struct *work) { struct bsd_acct_struct *acct = container_of(work, struct bsd_acct_struct, work); struct file *file = acct->file; + + /* We were fired by acct_pin_kill() which holds acct->lock. */ + acct_write_process(acct); if (file->f_op->flush) file->f_op->flush(file, NULL); __fput_sync(file); @@ -234,6 +243,20 @@ static int acct_on(struct filename *pathname) return -EACCES; } + /* Exclude kernel kernel internal filesystems. */ + if (file_inode(file)->i_sb->s_flags & (SB_NOUSER | SB_KERNMOUNT)) { + kfree(acct); + filp_close(file, NULL); + return -EINVAL; + } + + /* Exclude procfs and sysfs. */ + if (file_inode(file)->i_sb->s_iflags & SB_I_USERNS_VISIBLE) { + kfree(acct); + filp_close(file, NULL); + return -EINVAL; + } + if (!(file->f_mode & FMODE_CAN_WRITE)) { kfree(acct); filp_close(file, NULL); @@ -430,13 +453,27 @@ static u32 encode_float(u64 value) * do_exit() or when switching to a different output file. */ -static void fill_ac(acct_t *ac) +static void fill_ac(struct bsd_acct_struct *acct) { struct pacct_struct *pacct = ¤t->signal->pacct; + struct file *file = acct->file; + acct_t *ac = &acct->ac; u64 elapsed, run_time; time64_t btime; struct tty_struct *tty; + lockdep_assert_held(&acct->lock); + + if (time_is_after_jiffies(acct->needcheck)) { + acct->check_space = false; + + /* Don't fill in @ac if nothing will be written. */ + if (!acct->active) + return; + } else { + acct->check_space = true; + } + /* * Fill the accounting struct with the needed info as recorded * by the different kernel functions. @@ -484,64 +521,61 @@ static void fill_ac(acct_t *ac) ac->ac_majflt = encode_comp_t(pacct->ac_majflt); ac->ac_exitcode = pacct->ac_exitcode; spin_unlock_irq(¤t->sighand->siglock); -} -/* - * do_acct_process does all actual work. Caller holds the reference to file. - */ -static void do_acct_process(struct bsd_acct_struct *acct) -{ - acct_t ac; - unsigned long flim; - const struct cred *orig_cred; - struct file *file = acct->file; - /* - * Accounting records are not subject to resource limits. - */ - flim = rlimit(RLIMIT_FSIZE); - current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; - /* Perform file operations on behalf of whoever enabled accounting */ - orig_cred = override_creds(file->f_cred); - - /* - * First check to see if there is enough free_space to continue - * the process accounting system. - */ - if (!check_free_space(acct)) - goto out; - - fill_ac(&ac); /* we really need to bite the bullet and change layout */ - ac.ac_uid = from_kuid_munged(file->f_cred->user_ns, orig_cred->uid); - ac.ac_gid = from_kgid_munged(file->f_cred->user_ns, orig_cred->gid); + ac->ac_uid = from_kuid_munged(file->f_cred->user_ns, current_uid()); + ac->ac_gid = from_kgid_munged(file->f_cred->user_ns, current_gid()); #if ACCT_VERSION == 1 || ACCT_VERSION == 2 /* backward-compatible 16 bit fields */ - ac.ac_uid16 = ac.ac_uid; - ac.ac_gid16 = ac.ac_gid; + ac->ac_uid16 = ac->ac_uid; + ac->ac_gid16 = ac->ac_gid; #elif ACCT_VERSION == 3 { struct pid_namespace *ns = acct->ns; - ac.ac_pid = task_tgid_nr_ns(current, ns); + ac->ac_pid = task_tgid_nr_ns(current, ns); rcu_read_lock(); - ac.ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), - ns); + ac->ac_ppid = task_tgid_nr_ns(rcu_dereference(current->real_parent), ns); rcu_read_unlock(); } #endif +} + +static void acct_write_process(struct bsd_acct_struct *acct) +{ + struct file *file = acct->file; + const struct cred *cred; + acct_t *ac = &acct->ac; + + /* Perform file operations on behalf of whoever enabled accounting */ + cred = override_creds(file->f_cred); + /* - * Get freeze protection. If the fs is frozen, just skip the write - * as we could deadlock the system otherwise. + * First check to see if there is enough free_space to continue + * the process accounting system. Then get freeze protection. If + * the fs is frozen, just skip the write as we could deadlock + * the system otherwise. */ - if (file_start_write_trylock(file)) { + if (check_free_space(acct) && file_start_write_trylock(file)) { /* it's been opened O_APPEND, so position is irrelevant */ loff_t pos = 0; - __kernel_write(file, &ac, sizeof(acct_t), &pos); + __kernel_write(file, ac, sizeof(acct_t), &pos); file_end_write(file); } -out: + + revert_creds(cred); +} + +static void do_acct_process(struct bsd_acct_struct *acct) +{ + unsigned long flim; + + /* Accounting records are not subject to resource limits. */ + flim = rlimit(RLIMIT_FSIZE); + current->signal->rlim[RLIMIT_FSIZE].rlim_cur = RLIM_INFINITY; + fill_ac(acct); + acct_write_process(acct); current->signal->rlim[RLIMIT_FSIZE].rlim_cur = flim; - revert_creds(orig_cred); } /** diff --git a/kernel/audit.c b/kernel/audit.c index 13d0144efaa3..5f5bf85bcc90 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1221,7 +1221,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; struct audit_sig_info *sig_data; - struct lsm_context lsmctx; + struct lsm_context lsmctx = { NULL, 0, 0 }; err = audit_netlink_ok(skb, msg_type); if (err) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 548ec1c46b78..e1e42e918ba7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -6129,7 +6129,7 @@ static int bpf_unpriv_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table bpf_syscall_table[] = { +static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d9061bd55436..afc665b7b1fe 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4013,7 +4013,7 @@ static void __cgroup_kill(struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); - set_bit(CGRP_KILL, &cgrp->flags); + cgrp->kill_seq++; spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); @@ -4029,10 +4029,6 @@ static void __cgroup_kill(struct cgroup *cgrp) send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); - - spin_lock_irq(&css_set_lock); - clear_bit(CGRP_KILL, &cgrp->flags); - spin_unlock_irq(&css_set_lock); } static void cgroup_kill(struct cgroup *cgrp) @@ -6488,6 +6484,10 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); + if (kargs->cgrp) + kargs->kill_seq = kargs->cgrp->kill_seq; + else + kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { @@ -6668,6 +6668,7 @@ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { + unsigned int cgrp_kill_seq = 0; unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; @@ -6681,10 +6682,13 @@ void cgroup_post_fork(struct task_struct *child, /* init tasks are special, only link regular threads */ if (likely(child->pid)) { - if (kargs->cgrp) + if (kargs->cgrp) { cgrp_flags = kargs->cgrp->flags; - else + cgrp_kill_seq = kargs->cgrp->kill_seq; + } else { cgrp_flags = cset->dfl_cgrp->flags; + cgrp_kill_seq = cset->dfl_cgrp->kill_seq; + } WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; @@ -6719,7 +6723,7 @@ void cgroup_post_fork(struct task_struct *child, * child down right after we finished preparing it for * userspace. */ - kill = test_bit(CGRP_KILL, &cgrp_flags); + kill = kargs->kill_seq != cgrp_kill_seq; } spin_unlock_irq(&css_set_lock); diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 5877974ece92..aac91466279f 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -590,7 +590,6 @@ static void root_cgroup_cputime(struct cgroup_base_stat *bstat) cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; - cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; #ifdef CONFIG_SCHED_CORE bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index b238eb8c6573..eb63a021ac04 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -64,7 +64,7 @@ static int sysctl_delayacct(const struct ctl_table *table, int write, void *buff return err; } -static struct ctl_table kern_delayacct_table[] = { +static const struct ctl_table kern_delayacct_table[] = { { .procname = "task_delayacct", .data = NULL, diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index e421a5f2ec7d..2ca797cbe465 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -28,6 +28,7 @@ #include <linux/rcupdate_trace.h> #include <linux/workqueue.h> #include <linux/srcu.h> +#include <linux/oom.h> /* check_stable_address_space */ #include <linux/uprobes.h> @@ -1260,6 +1261,9 @@ register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) * returns NULL in find_active_uprobe_rcu(). */ mmap_write_lock(mm); + if (check_stable_address_space(mm)) + goto unlock; + vma = find_vma(mm, info->vaddr); if (!vma || !valid_vma(vma, is_register) || file_inode(vma->vm_file) != uprobe->inode) diff --git a/kernel/exit.c b/kernel/exit.c index 1dcddfe537ee..3485e5fc499e 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -85,7 +85,7 @@ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_exit_table[] = { +static const struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, diff --git a/kernel/fork.c b/kernel/fork.c index cba5ede2c639..735405a9c5f3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -760,7 +760,8 @@ loop_out: mt_set_in_rcu(vmi.mas.tree); ksm_fork(mm, oldmm); khugepaged_fork(mm, oldmm); - } else if (mpnt) { + } else { + /* * The entire maple tree has already been duplicated. If the * mmap duplication fails, mark the failure point with @@ -768,8 +769,18 @@ loop_out: * stop releasing VMAs that have not been duplicated after this * point. */ - mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); - mas_store(&vmi.mas, XA_ZERO_ENTRY); + if (mpnt) { + mas_set_range(&vmi.mas, mpnt->vm_start, mpnt->vm_end - 1); + mas_store(&vmi.mas, XA_ZERO_ENTRY); + /* Avoid OOM iterating a broken tree */ + set_bit(MMF_OOM_SKIP, &mm->flags); + } + /* + * The mm_struct is going to exit, but the locks will be dropped + * first. Set the mm_struct as unstable is advisable as it is + * not fully initialised. + */ + set_bit(MMF_UNSTABLE, &mm->flags); } out: mmap_write_unlock(mm); diff --git a/kernel/futex/core.c b/kernel/futex/core.c index ebdd76b4ecbb..3db8567f5a44 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -532,7 +532,8 @@ void futex_q_unlock(struct futex_hash_bucket *hb) futex_hb_waiters_dec(hb); } -void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) +void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task) { int prio; @@ -548,7 +549,7 @@ void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) plist_node_init(&q->list, prio); plist_add(&q->list, &hb->chain); - q->task = current; + q->task = task; } /** diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 99b32e728c4a..6b2f4c7eb720 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -285,13 +285,15 @@ static inline int futex_get_value_locked(u32 *dest, u32 __user *from) } extern void __futex_unqueue(struct futex_q *q); -extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb); +extern void __futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task); extern int futex_unqueue(struct futex_q *q); /** * futex_queue() - Enqueue the futex_q on the futex_hash_bucket * @q: The futex_q to enqueue * @hb: The destination hash bucket + * @task: Task queueing this futex * * The hb->lock must be held by the caller, and is released here. A call to * futex_queue() is typically paired with exactly one call to futex_unqueue(). The @@ -299,11 +301,14 @@ extern int futex_unqueue(struct futex_q *q); * or nothing if the unqueue is done as part of the wake process and the unqueue * state is implicit in the state of woken task (see futex_wait_requeue_pi() for * an example). + * + * Note that @task may be NULL, for async usage of futexes. */ -static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb) +static inline void futex_queue(struct futex_q *q, struct futex_hash_bucket *hb, + struct task_struct *task) __releases(&hb->lock) { - __futex_queue(q, hb); + __futex_queue(q, hb, task); spin_unlock(&hb->lock); } diff --git a/kernel/futex/pi.c b/kernel/futex/pi.c index daea650b16f5..7a941845f7ee 100644 --- a/kernel/futex/pi.c +++ b/kernel/futex/pi.c @@ -982,7 +982,7 @@ retry_private: /* * Only actually queue now that the atomic ops are done: */ - __futex_queue(&q, hb); + __futex_queue(&q, hb, current); if (trylock) { ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex); diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index eb86a7ade06a..25877d4f2f8f 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -349,7 +349,7 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, * access to the hash list and forcing another memory barrier. */ set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); - futex_queue(q, hb); + futex_queue(q, hb, current); /* Arm the timer */ if (timeout) @@ -460,7 +460,7 @@ retry: * next futex. Queue each futex at this moment so hb can * be unlocked. */ - futex_queue(q, hb); + futex_queue(q, hb, current); continue; } diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 7e1340da5aca..00529c81cc40 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -7,20 +7,13 @@ set -e sfile="$(readlink -f "$0")" outdir="$(pwd)" tarfile=$1 -cpio_dir=$outdir/${tarfile%/*}/.tmp_cpio_dir +tmpdir=$outdir/${tarfile%/*}/.tmp_dir dir_list=" include/ arch/$SRCARCH/include/ " -if ! command -v cpio >/dev/null; then - echo >&2 "***" - echo >&2 "*** 'cpio' could not be found." - echo >&2 "***" - exit 1 -fi - # Support incremental builds by skipping archive generation # if timestamps of files being archived are not changed. @@ -48,9 +41,9 @@ all_dirs="$all_dirs $dir_list" # check include/generated/autoconf.h explicitly. # # Ignore them for md5 calculation to avoid pointless regeneration. -headers_md5="$(find $all_dirs -name "*.h" | - grep -v "include/generated/utsversion.h" | - grep -v "include/generated/autoconf.h" | +headers_md5="$(find $all_dirs -name "*.h" -a \ + ! -path include/generated/utsversion.h -a \ + ! -path include/generated/autoconf.h | xargs ls -l | md5sum | cut -d ' ' -f1)" # Any changes to this script will also cause a rebuild of the archive. @@ -65,36 +58,43 @@ fi echo " GEN $tarfile" -rm -rf $cpio_dir -mkdir $cpio_dir +rm -rf "${tmpdir}" +mkdir "${tmpdir}" if [ "$building_out_of_srctree" ]; then ( cd $srctree for f in $dir_list do find "$f" -name "*.h"; - done | cpio --quiet -pd $cpio_dir + done | tar -c -f - -T - | tar -xf - -C "${tmpdir}" ) fi -# The second CPIO can complain if files already exist which can happen with out -# of tree builds having stale headers in srctree. Just silence CPIO for now. for f in $dir_list; do find "$f" -name "*.h"; -done | cpio --quiet -pdu $cpio_dir >/dev/null 2>&1 +done | tar -c -f - -T - | tar -xf - -C "${tmpdir}" + +# Always exclude include/generated/utsversion.h +# Otherwise, the contents of the tarball may vary depending on the build steps. +rm -f "${tmpdir}/include/generated/utsversion.h" # Remove comments except SDPX lines -find $cpio_dir -type f -print0 | - xargs -0 -P8 -n1 perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' +# Use a temporary file to store directory contents to prevent find/xargs from +# seeing temporary files created by perl. +find "${tmpdir}" -type f -print0 > "${tmpdir}.contents.txt" +xargs -0 -P8 -n1 \ + perl -pi -e 'BEGIN {undef $/;}; s/\/\*((?!SPDX).)*?\*\///smg;' \ + < "${tmpdir}.contents.txt" +rm -f "${tmpdir}.contents.txt" # Create archive and try to normalize metadata for reproducibility. tar "${KBUILD_BUILD_TIMESTAMP:+--mtime=$KBUILD_BUILD_TIMESTAMP}" \ --exclude=".__afs*" --exclude=".nfs*" \ --owner=0 --group=0 --sort=name --numeric-owner --mode=u=rw,go=r,a+X \ - -I $XZ -cf $tarfile -C $cpio_dir/ . > /dev/null + -I $XZ -cf $tarfile -C "${tmpdir}/" . > /dev/null echo $headers_md5 > kernel/kheaders.md5 echo "$this_file_md5" >> kernel/kheaders.md5 echo "$(md5sum $tarfile | cut -d ' ' -f1)" >> kernel/kheaders.md5 -rm -rf $cpio_dir +rm -rf "${tmpdir}" diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 953169893a95..04efa7a6e69b 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -274,7 +274,7 @@ static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int writ * and hung_task_check_interval_secs */ static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ); -static struct ctl_table hung_task_sysctls[] = { +static const struct ctl_table hung_task_sysctls[] = { #ifdef CONFIG_SMP { .procname = "hung_task_all_cpu_backtrace", diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 5432418c0fea..875f25ed6f71 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -31,10 +31,6 @@ config GENERIC_IRQ_EFFECTIVE_AFF_MASK config GENERIC_PENDING_IRQ bool -# Deduce delayed migration from top-level interrupt chip flags -config GENERIC_PENDING_IRQ_CHIPFLAGS - bool - # Support for generic irq migrating off cpu before the cpu is offline. config GENERIC_IRQ_MIGRATION bool diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index b424a5c6ae87..c0bdc1686154 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -925,7 +925,7 @@ static int kexec_limit_handler(const struct ctl_table *table, int write, return proc_dointvec(&tmp, write, buffer, lenp, ppos); } -static struct ctl_table kexec_core_sysctls[] = { +static const struct ctl_table kexec_core_sysctls[] = { { .procname = "kexec_load_disabled", .data = &kexec_load_disabled, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 030569210670..88aeac84e4c0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -946,7 +946,7 @@ static int proc_kprobes_optimization_handler(const struct ctl_table *table, return ret; } -static struct ctl_table kprobe_sysctls[] = { +static const struct ctl_table kprobe_sysctls[] = { { .procname = "kprobes-optimization", .data = &sysctl_kprobes_optimization, diff --git a/kernel/kthread.c b/kernel/kthread.c index 4005b13ebd7f..5dc5b0d7238e 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -859,7 +859,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) struct kthread *kthread = to_kthread(p); cpumask_var_t affinity; unsigned long flags; - int ret; + int ret = 0; if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) { WARN_ON(1); @@ -892,7 +892,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) out: free_cpumask_var(affinity); - return 0; + return ret; } /* diff --git a/kernel/latencytop.c b/kernel/latencytop.c index 77ee3ea8a573..d4281d1e13a6 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -77,7 +77,7 @@ static int sysctl_latencytop(const struct ctl_table *table, int write, void *buf return err; } -static struct ctl_table latencytop_sysctl[] = { +static const struct ctl_table latencytop_sysctl[] = { { .procname = "latencytop", .data = &latencytop_enabled, diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 29acd238dad7..4470680f0226 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -79,7 +79,7 @@ module_param(lock_stat, int, 0644); #endif #ifdef CONFIG_SYSCTL -static struct ctl_table kern_lockdep_table[] = { +static const struct ctl_table kern_lockdep_table[] = { #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index 74fe976e3b01..d7762ef5949a 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -169,6 +169,36 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +choice + prompt "Module versioning implementation" + depends on MODVERSIONS + help + Select the tool used to calculate symbol versions for modules. + + If unsure, select GENKSYMS. + +config GENKSYMS + bool "genksyms (from source code)" + help + Calculate symbol versions from pre-processed source code using + genksyms. + + If unsure, say Y. + +config GENDWARFKSYMS + bool "gendwarfksyms (from debugging information)" + depends on DEBUG_INFO + # Requires full debugging information, split DWARF not supported. + depends on !DEBUG_INFO_REDUCED && !DEBUG_INFO_SPLIT + # Requires ELF object files. + depends on !LTO + help + Calculate symbol versions from DWARF debugging information using + gendwarfksyms. Requires DEBUG_INFO to be enabled. + + If unsure, say N. +endchoice + config ASM_MODVERSIONS bool default HAVE_ASM_MODVERSIONS && MODVERSIONS @@ -177,6 +207,31 @@ config ASM_MODVERSIONS assembly. This can be enabled only when the target architecture supports it. +config EXTENDED_MODVERSIONS + bool "Extended Module Versioning Support" + depends on MODVERSIONS + help + This enables extended MODVERSIONs support, allowing long symbol + names to be versioned. + + The most likely reason you would enable this is to enable Rust + support. If unsure, say N. + +config BASIC_MODVERSIONS + bool "Basic Module Versioning Support" + depends on MODVERSIONS + default y + help + This enables basic MODVERSIONS support, allowing older tools or + kernels to potentially load modules. + + Disabling this may cause older `modprobe` or `kmod` to be unable + to read MODVERSIONS information from built modules. With this + disabled, older kernels may treat this module as unversioned. + + This is enabled by default when MODVERSIONS are enabled. + If unsure, say Y. + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help diff --git a/kernel/module/internal.h b/kernel/module/internal.h index b35c0ec54a89..d09b46ef032f 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -55,8 +55,8 @@ extern const struct kernel_symbol __start___ksymtab[]; extern const struct kernel_symbol __stop___ksymtab[]; extern const struct kernel_symbol __start___ksymtab_gpl[]; extern const struct kernel_symbol __stop___ksymtab_gpl[]; -extern const s32 __start___kcrctab[]; -extern const s32 __start___kcrctab_gpl[]; +extern const u32 __start___kcrctab[]; +extern const u32 __start___kcrctab_gpl[]; struct load_info { const char *name; @@ -86,6 +86,8 @@ struct load_info { unsigned int vers; unsigned int info; unsigned int pcpu; + unsigned int vers_ext_crc; + unsigned int vers_ext_name; } index; }; @@ -102,7 +104,7 @@ struct find_symbol_arg { /* Output */ struct module *owner; - const s32 *crc; + const u32 *crc; const struct kernel_symbol *sym; enum mod_license license; }; @@ -385,16 +387,25 @@ static inline void init_param_lock(struct module *mod) { } #ifdef CONFIG_MODVERSIONS int check_version(const struct load_info *info, - const char *symname, struct module *mod, const s32 *crc); + const char *symname, struct module *mod, const u32 *crc); void module_layout(struct module *mod, struct modversion_info *ver, struct kernel_param *kp, struct kernel_symbol *ks, struct tracepoint * const *tp); int check_modstruct_version(const struct load_info *info, struct module *mod); int same_magic(const char *amagic, const char *bmagic, bool has_crcs); +struct modversion_info_ext { + size_t remaining; + const u32 *crc; + const char *name; +}; +void modversion_ext_start(const struct load_info *info, struct modversion_info_ext *ver); +void modversion_ext_advance(struct modversion_info_ext *ver); +#define for_each_modversion_info_ext(ver, info) \ + for (modversion_ext_start(info, &ver); ver.remaining > 0; modversion_ext_advance(&ver)) #else /* !CONFIG_MODVERSIONS */ static inline int check_version(const struct load_info *info, const char *symname, struct module *mod, - const s32 *crc) + const u32 *crc) { return 1; } diff --git a/kernel/module/main.c b/kernel/module/main.c index 8808b6906d5a..1fb9ad289a6f 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -86,7 +86,7 @@ struct mod_tree_root mod_tree __cacheline_aligned = { struct symsearch { const struct kernel_symbol *start, *stop; - const s32 *crcs; + const u32 *crcs; enum mod_license license; }; @@ -2074,6 +2074,82 @@ static int elf_validity_cache_index_str(struct load_info *info) } /** + * elf_validity_cache_index_versions() - Validate and cache version indices + * @info: Load info to cache version indices in. + * Must have &load_info->sechdrs and &load_info->secstrings populated. + * @flags: Load flags, relevant to suppress version loading, see + * uapi/linux/module.h + * + * If we're ignoring modversions based on @flags, zero all version indices + * and return validity. Othewrise check: + * + * * If "__version_ext_crcs" is present, "__version_ext_names" is present + * * There is a name present for every crc + * + * Then populate: + * + * * &load_info->index.vers + * * &load_info->index.vers_ext_crc + * * &load_info->index.vers_ext_names + * + * if present. + * + * Return: %0 if valid, %-ENOEXEC on failure. + */ +static int elf_validity_cache_index_versions(struct load_info *info, int flags) +{ + unsigned int vers_ext_crc; + unsigned int vers_ext_name; + size_t crc_count; + size_t remaining_len; + size_t name_size; + char *name; + + /* If modversions were suppressed, pretend we didn't find any */ + if (flags & MODULE_INIT_IGNORE_MODVERSIONS) { + info->index.vers = 0; + info->index.vers_ext_crc = 0; + info->index.vers_ext_name = 0; + return 0; + } + + vers_ext_crc = find_sec(info, "__version_ext_crcs"); + vers_ext_name = find_sec(info, "__version_ext_names"); + + /* If we have one field, we must have the other */ + if (!!vers_ext_crc != !!vers_ext_name) { + pr_err("extended version crc+name presence does not match"); + return -ENOEXEC; + } + + /* + * If we have extended version information, we should have the same + * number of entries in every section. + */ + if (vers_ext_crc) { + crc_count = info->sechdrs[vers_ext_crc].sh_size / sizeof(u32); + name = (void *)info->hdr + + info->sechdrs[vers_ext_name].sh_offset; + remaining_len = info->sechdrs[vers_ext_name].sh_size; + + while (crc_count--) { + name_size = strnlen(name, remaining_len) + 1; + if (name_size > remaining_len) { + pr_err("more extended version crcs than names"); + return -ENOEXEC; + } + remaining_len -= name_size; + name += name_size; + } + } + + info->index.vers = find_sec(info, "__versions"); + info->index.vers_ext_crc = vers_ext_crc; + info->index.vers_ext_name = vers_ext_name; + return 0; +} + +/** * elf_validity_cache_index() - Resolve, validate, cache section indices * @info: Load info to read from and update. * &load_info->sechdrs and &load_info->secstrings must be populated. @@ -2087,9 +2163,7 @@ static int elf_validity_cache_index_str(struct load_info *info) * * elf_validity_cache_index_mod() * * elf_validity_cache_index_sym() * * elf_validity_cache_index_str() - * - * If versioning is not suppressed via flags, load the version index from - * a section called "__versions" with no validation. + * * elf_validity_cache_index_versions() * * If CONFIG_SMP is enabled, load the percpu section by name with no * validation. @@ -2112,11 +2186,9 @@ static int elf_validity_cache_index(struct load_info *info, int flags) err = elf_validity_cache_index_str(info); if (err < 0) return err; - - if (flags & MODULE_INIT_IGNORE_MODVERSIONS) - info->index.vers = 0; /* Pretend no __versions section! */ - else - info->index.vers = find_sec(info, "__versions"); + err = elf_validity_cache_index_versions(info, flags); + if (err < 0) + return err; info->index.pcpu = find_pcpusec(info); @@ -2327,6 +2399,10 @@ static int rewrite_section_headers(struct load_info *info, int flags) /* Track but don't keep modinfo and version sections. */ info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; + info->sechdrs[info->index.vers_ext_crc].sh_flags &= + ~(unsigned long)SHF_ALLOC; + info->sechdrs[info->index.vers_ext_name].sh_flags &= + ~(unsigned long)SHF_ALLOC; info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; return 0; diff --git a/kernel/module/version.c b/kernel/module/version.c index 53f43ac5a73e..3718a8868321 100644 --- a/kernel/module/version.c +++ b/kernel/module/version.c @@ -13,17 +13,34 @@ int check_version(const struct load_info *info, const char *symname, struct module *mod, - const s32 *crc) + const u32 *crc) { Elf_Shdr *sechdrs = info->sechdrs; unsigned int versindex = info->index.vers; unsigned int i, num_versions; struct modversion_info *versions; + struct modversion_info_ext version_ext; /* Exporting module didn't supply crcs? OK, we're already tainted. */ if (!crc) return 1; + /* If we have extended version info, rely on it */ + if (info->index.vers_ext_crc) { + for_each_modversion_info_ext(version_ext, info) { + if (strcmp(version_ext.name, symname) != 0) + continue; + if (*version_ext.crc == *crc) + return 1; + pr_debug("Found checksum %X vs module %X\n", + *crc, *version_ext.crc); + goto bad_version; + } + pr_warn_once("%s: no extended symbol version for %s\n", + info->name, symname); + return 1; + } + /* No versions at all? modprobe --force does this. */ if (versindex == 0) return try_to_force_load(mod, symname) == 0; @@ -87,6 +104,34 @@ int same_magic(const char *amagic, const char *bmagic, return strcmp(amagic, bmagic) == 0; } +void modversion_ext_start(const struct load_info *info, + struct modversion_info_ext *start) +{ + unsigned int crc_idx = info->index.vers_ext_crc; + unsigned int name_idx = info->index.vers_ext_name; + Elf_Shdr *sechdrs = info->sechdrs; + + /* + * Both of these fields are needed for this to be useful + * Any future fields should be initialized to NULL if absent. + */ + if (crc_idx == 0 || name_idx == 0) { + start->remaining = 0; + return; + } + + start->crc = (const u32 *)sechdrs[crc_idx].sh_addr; + start->name = (const char *)sechdrs[name_idx].sh_addr; + start->remaining = sechdrs[crc_idx].sh_size / sizeof(*start->crc); +} + +void modversion_ext_advance(struct modversion_info_ext *vers) +{ + vers->remaining--; + vers->crc++; + vers->name += strlen(vers->name) + 1; +} + /* * Generate the signature for all relevant module structures here. * If these change, we don't want to try to parse the module. diff --git a/kernel/panic.c b/kernel/panic.c index fbc59b3b64d0..d8635d5cecb2 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -84,7 +84,7 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); #ifdef CONFIG_SYSCTL -static struct ctl_table kern_panic_table[] = { +static const struct ctl_table kern_panic_table[] = { #ifdef CONFIG_SMP { .procname = "oops_all_cpu_backtrace", diff --git a/kernel/pid.c b/kernel/pid.c index 3a10a7b6fcf8..924084713be8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -695,7 +695,7 @@ static struct ctl_table_root pid_table_root = { .set_ownership = pid_table_root_set_ownership, }; -static struct ctl_table pid_table[] = { +static const struct ctl_table pid_table[] = { { .procname = "pid_max", .data = &init_pid_ns.pid_max, diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index f1ffa032fc32..8f6cfec87555 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -303,7 +303,7 @@ static int pid_ns_ctl_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table pid_ns_ctl_table[] = { +static const struct ctl_table pid_ns_ctl_table[] = { { .procname = "ns_last_pid", .maxlen = sizeof(int), diff --git a/kernel/pid_sysctl.h b/kernel/pid_sysctl.h index 18ecaef6be41..5d8f981de7c5 100644 --- a/kernel/pid_sysctl.h +++ b/kernel/pid_sysctl.h @@ -31,7 +31,7 @@ static int pid_mfd_noexec_dointvec_minmax(const struct ctl_table *table, return err; } -static struct ctl_table pid_ns_ctl_table_vm[] = { +static const struct ctl_table pid_ns_ctl_table_vm[] = { { .procname = "memfd_noexec", .data = &init_pid_ns.memfd_noexec_scope, diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 1f87aa01ba44..10a01af63a80 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -608,7 +608,11 @@ int hibernation_platform_enter(void) local_irq_disable(); system_state = SYSTEM_SUSPEND; - syscore_suspend(); + + error = syscore_suspend(); + if (error) + goto Enable_irqs; + if (pm_wakeup_pending()) { error = -EAGAIN; goto Power_up; @@ -620,6 +624,7 @@ int hibernation_platform_enter(void) Power_up: syscore_resume(); + Enable_irqs: system_state = SYSTEM_RUNNING; local_irq_enable(); diff --git a/kernel/printk/sysctl.c b/kernel/printk/sysctl.c index f5072dc85f7a..da77f3f5c1fe 100644 --- a/kernel/printk/sysctl.c +++ b/kernel/printk/sysctl.c @@ -20,7 +20,7 @@ static int proc_dointvec_minmax_sysadmin(const struct ctl_table *table, int writ return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } -static struct ctl_table printk_sysctls[] = { +static const struct ctl_table printk_sysctls[] = { { .procname = "printk", .data = &console_loglevel, diff --git a/kernel/reboot.c b/kernel/reboot.c index a701000bab34..b5a8569e5d81 100644 --- a/kernel/reboot.c +++ b/kernel/reboot.c @@ -1287,7 +1287,7 @@ static struct attribute *reboot_attrs[] = { }; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_reboot_table[] = { +static const struct ctl_table kern_reboot_table[] = { { .procname = "poweroff_cmd", .data = &poweroff_cmd, diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index db68a964e34e..2b331822c7e7 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -9,7 +9,7 @@ static struct autogroup autogroup_default; static atomic_t autogroup_seq_nr; #ifdef CONFIG_SYSCTL -static struct ctl_table sched_autogroup_sysctls[] = { +static const struct ctl_table sched_autogroup_sysctls[] = { { .procname = "sched_autogroup_enabled", .data = &sysctl_sched_autogroup_enabled, @@ -150,7 +150,7 @@ void sched_autogroup_exit_task(struct task_struct *p) * see this thread after that: we can no longer use signal->autogroup. * See the PF_EXITING check in task_wants_autogroup(). */ - sched_move_task(p); + sched_move_task(p, true); } static void @@ -182,7 +182,7 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag) * sched_autogroup_exit_task(). */ for_each_thread(p, t) - sched_move_task(t); + sched_move_task(t, true); unlock_task_sighand(p, &flags); autogroup_kref_put(prev); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9142a0394d46..9aecd914ac69 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1063,9 +1063,10 @@ void wake_up_q(struct wake_q_head *head) struct task_struct *task; task = container_of(node, struct task_struct, wake_q); - /* Task can safely be re-inserted now: */ node = node->next; - task->wake_q.next = NULL; + /* pairs with cmpxchg_relaxed() in __wake_q_add() */ + WRITE_ONCE(task->wake_q.next, NULL); + /* Task can safely be re-inserted now. */ /* * wake_up_process() executes a full barrier, which pairs with @@ -4654,7 +4655,7 @@ static int sysctl_schedstats(const struct ctl_table *table, int write, void *buf #endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_SYSCTL -static struct ctl_table sched_core_sysctls[] = { +static const struct ctl_table sched_core_sysctls[] = { #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", @@ -9050,7 +9051,7 @@ static void sched_change_group(struct task_struct *tsk, struct task_group *group * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect * its new group. */ -void sched_move_task(struct task_struct *tsk) +void sched_move_task(struct task_struct *tsk, bool for_autogroup) { int queued, running, queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; @@ -9079,7 +9080,8 @@ void sched_move_task(struct task_struct *tsk) put_prev_task(rq, tsk); sched_change_group(tsk, group); - scx_move_task(tsk); + if (!for_autogroup) + scx_cgroup_move_task(tsk); if (queued) enqueue_task(rq, tsk, queue_flags); @@ -9180,7 +9182,7 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; cgroup_taskset_for_each(task, css, tset) - sched_move_task(task); + sched_move_task(task, false); scx_cgroup_finish_attach(); } diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index a2a29e3fffca..1a19d69b91ed 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -666,7 +666,11 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy) } sg_policy->thread = thread; - kthread_bind_mask(thread, policy->related_cpus); + if (policy->dvfs_possible_from_any_cpu) + set_cpus_allowed_ptr(thread, policy->related_cpus); + else + kthread_bind_mask(thread, policy->related_cpus); + init_irq_work(&sg_policy->irq_work, sugov_irq_work); mutex_init(&sg_policy->work_lock); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 62192ac79c30..38e4537790af 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -26,7 +26,7 @@ static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */ static unsigned int sysctl_sched_dl_period_min = 100; /* 100 us */ #ifdef CONFIG_SYSCTL -static struct ctl_table sched_dl_sysctls[] = { +static const struct ctl_table sched_dl_sysctls[] = { { .procname = "sched_deadline_period_max_us", .data = &sysctl_sched_dl_period_max, diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index fd7e85220715..ef047add7f9e 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1262,6 +1262,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, if (task_has_dl_policy(p)) { P(dl.runtime); P(dl.deadline); + } else if (fair_policy(p->policy)) { + P(se.slice); } #ifdef CONFIG_SCHED_CLASS_EXT __PS("ext.enabled", task_on_scx(p)); diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 8857c0709bdd..5a81d9a1e31f 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -123,6 +123,19 @@ enum scx_ops_flags { SCX_OPS_SWITCH_PARTIAL = 1LLU << 3, /* + * A migration disabled task can only execute on its current CPU. By + * default, such tasks are automatically put on the CPU's local DSQ with + * the default slice on enqueue. If this ops flag is set, they also go + * through ops.enqueue(). + * + * A migration disabled task never invokes ops.select_cpu() as it can + * only select the current CPU. Also, p->cpus_ptr will only contain its + * current CPU while p->nr_cpus_allowed keeps tracking p->user_cpus_ptr + * and thus may disagree with cpumask_weight(p->cpus_ptr). + */ + SCX_OPS_ENQ_MIGRATION_DISABLED = 1LLU << 4, + + /* * CPU cgroup support flags */ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */ @@ -130,6 +143,7 @@ enum scx_ops_flags { SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE | SCX_OPS_ENQ_LAST | SCX_OPS_ENQ_EXITING | + SCX_OPS_ENQ_MIGRATION_DISABLED | SCX_OPS_SWITCH_PARTIAL | SCX_OPS_HAS_CGROUP_WEIGHT, }; @@ -416,7 +430,7 @@ struct sched_ext_ops { /** * @update_idle: Update the idle state of a CPU - * @cpu: CPU to udpate the idle state for + * @cpu: CPU to update the idle state for * @idle: whether entering or exiting the idle state * * This operation is called when @rq's CPU goes or leaves the idle @@ -882,6 +896,7 @@ static bool scx_warned_zero_slice; static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last); static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting); +static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_migration_disabled); static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt); static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled); @@ -1214,7 +1229,7 @@ static bool scx_kf_allowed_if_unlocked(void) /** * nldsq_next_task - Iterate to the next task in a non-local DSQ - * @dsq: user dsq being interated + * @dsq: user dsq being iterated * @cur: current position, %NULL to start iteration * @rev: walk backwards * @@ -2014,6 +2029,11 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, unlikely(p->flags & PF_EXITING)) goto local; + /* see %SCX_OPS_ENQ_MIGRATION_DISABLED */ + if (!static_branch_unlikely(&scx_ops_enq_migration_disabled) && + is_migration_disabled(p)) + goto local; + if (!SCX_HAS_OP(enqueue)) goto global; @@ -2078,7 +2098,7 @@ static void set_task_runnable(struct rq *rq, struct task_struct *p) /* * list_add_tail() must be used. scx_ops_bypass() depends on tasks being - * appened to the runnable_list. + * appended to the runnable_list. */ list_add_tail(&p->scx.runnable_node, &rq->scx.runnable_list); } @@ -2313,12 +2333,35 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags, * * - The BPF scheduler is bypassed while the rq is offline and we can always say * no to the BPF scheduler initiated migrations while offline. + * + * The caller must ensure that @p and @rq are on different CPUs. */ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { int cpu = cpu_of(rq); + SCHED_WARN_ON(task_cpu(p) == cpu); + + /* + * If @p has migration disabled, @p->cpus_ptr is updated to contain only + * the pinned CPU in migrate_disable_switch() while @p is being switched + * out. However, put_prev_task_scx() is called before @p->cpus_ptr is + * updated and thus another CPU may see @p on a DSQ inbetween leading to + * @p passing the below task_allowed_on_cpu() check while migration is + * disabled. + * + * Test the migration disabled state first as the race window is narrow + * and the BPF scheduler failing to check migration disabled state can + * easily be masked if task_allowed_on_cpu() is done first. + */ + if (unlikely(is_migration_disabled(p))) { + if (trigger_error) + scx_ops_error("SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d", + p->comm, p->pid, task_cpu(p), cpu); + return false; + } + /* * We don't require the BPF scheduler to avoid dispatching to offline * CPUs mostly for convenience but also because CPUs can go offline @@ -2327,14 +2370,11 @@ static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, */ if (!task_allowed_on_cpu(p, cpu)) { if (trigger_error) - scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]", - cpu_of(rq), p->comm, p->pid); + scx_ops_error("SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]", + cpu, p->comm, p->pid); return false; } - if (unlikely(is_migration_disabled(p))) - return false; - if (!scx_rq_online(rq)) return false; @@ -2437,7 +2477,8 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags, if (dst_dsq->id == SCX_DSQ_LOCAL) { dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); - if (!task_can_run_on_remote_rq(p, dst_rq, true)) { + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { dst_dsq = find_global_dsq(p); dst_rq = src_rq; } @@ -2480,7 +2521,7 @@ static struct rq *move_task_between_dsqs(struct task_struct *p, u64 enq_flags, /* * A poorly behaving BPF scheduler can live-lock the system by e.g. incessantly * banging on the same DSQ on a large NUMA system to the point where switching - * to the bypass mode can take a long time. Inject artifical delays while the + * to the bypass mode can take a long time. Inject artificial delays while the * bypass mode is switching to guarantee timely completion. */ static void scx_ops_breather(struct rq *rq) @@ -2575,6 +2616,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, { struct rq *src_rq = task_rq(p); struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq); +#ifdef CONFIG_SMP + struct rq *locked_rq = rq; +#endif /* * We're synchronized against dequeue through DISPATCHING. As @p can't @@ -2588,7 +2632,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } #ifdef CONFIG_SMP - if (unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { + if (src_rq != dst_rq && + unlikely(!task_can_run_on_remote_rq(p, dst_rq, true))) { dispatch_enqueue(find_global_dsq(p), p, enq_flags | SCX_ENQ_CLEAR_OPSS); return; @@ -2611,8 +2656,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE); /* switch to @src_rq lock */ - if (rq != src_rq) { - raw_spin_rq_unlock(rq); + if (locked_rq != src_rq) { + raw_spin_rq_unlock(locked_rq); + locked_rq = src_rq; raw_spin_rq_lock(src_rq); } @@ -2630,6 +2676,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } else { move_remote_task_to_local_dsq(p, enq_flags, src_rq, dst_rq); + /* task has been moved to dst_rq, which is now locked */ + locked_rq = dst_rq; } /* if the destination CPU is idle, wake it up */ @@ -2638,8 +2686,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq, } /* switch back to @rq lock */ - if (rq != dst_rq) { - raw_spin_rq_unlock(dst_rq); + if (locked_rq != rq) { + raw_spin_rq_unlock(locked_rq); raw_spin_rq_lock(rq); } #else /* CONFIG_SMP */ @@ -3144,7 +3192,7 @@ static struct task_struct *pick_task_scx(struct rq *rq) * * Unless overridden by ops.core_sched_before(), @p->scx.core_sched_at is used * to implement the default task ordering. The older the timestamp, the higher - * prority the task - the global FIFO ordering matching the default scheduling + * priority the task - the global FIFO ordering matching the default scheduling * behavior. * * When ops.core_sched_before() is enabled, @p->scx.core_sched_at is used to @@ -3851,7 +3899,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) curr->scx.slice = 0; touch_core_sched(rq, curr); } else if (SCX_HAS_OP(tick)) { - SCX_CALL_OP(SCX_KF_REST, tick, curr); + SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr); } if (!curr->scx.slice) @@ -3998,7 +4046,7 @@ static void scx_ops_disable_task(struct task_struct *p) WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); if (SCX_HAS_OP(disable)) - SCX_CALL_OP(SCX_KF_REST, disable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, disable, p); scx_set_task_state(p, SCX_TASK_READY); } @@ -4027,7 +4075,7 @@ static void scx_ops_exit_task(struct task_struct *p) } if (SCX_HAS_OP(exit_task)) - SCX_CALL_OP(SCX_KF_REST, exit_task, p, &args); + SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args); scx_set_task_state(p, SCX_TASK_NONE); } @@ -4323,25 +4371,12 @@ err: return ops_sanitize_err("cgroup_prep_move", ret); } -void scx_move_task(struct task_struct *p) +void scx_cgroup_move_task(struct task_struct *p) { if (!scx_cgroup_enabled) return; /* - * We're called from sched_move_task() which handles both cgroup and - * autogroup moves. Ignore the latter. - * - * Also ignore exiting tasks, because in the exit path tasks transition - * from the autogroup to the root group, so task_group_is_autogroup() - * alone isn't able to catch exiting autogroup tasks. This is safe for - * cgroup_move(), because cgroup migrations never happen for PF_EXITING - * tasks. - */ - if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING)) - return; - - /* * @p must have ops.cgroup_prep_move() called on it and thus * cgrp_moving_from set. */ @@ -4590,7 +4625,7 @@ static int scx_cgroup_init(void) cgroup_warned_missing_idle = false; /* - * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk + * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk * cgroups and init, all online cgroups are initialized. */ rcu_read_lock(); @@ -5059,6 +5094,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) static_branch_disable(&scx_has_op[i]); static_branch_disable(&scx_ops_enq_last); static_branch_disable(&scx_ops_enq_exiting); + static_branch_disable(&scx_ops_enq_migration_disabled); static_branch_disable(&scx_ops_cpu_preempt); static_branch_disable(&scx_builtin_idle_enabled); synchronize_rcu(); @@ -5277,9 +5313,10 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, scx_get_task_state(p), p->scx.flags & ~SCX_TASK_STATE_MASK, p->scx.dsq_flags, ops_state & SCX_OPSS_STATE_MASK, ops_state >> SCX_OPSS_QSEQ_SHIFT); - dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s dsq_vtime=%llu slice=%llu", - p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf, - p->scx.dsq_vtime, p->scx.slice); + dump_line(s, " sticky/holding_cpu=%d/%d dsq_id=%s", + p->scx.sticky_cpu, p->scx.holding_cpu, dsq_id_buf); + dump_line(s, " dsq_vtime=%llu slice=%llu weight=%u", + p->scx.dsq_vtime, p->scx.slice, p->scx.weight); dump_line(s, " cpus=%*pb", cpumask_pr_args(p->cpus_ptr)); if (SCX_HAS_OP(dump_task)) { @@ -5667,6 +5704,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) if (ops->flags & SCX_OPS_ENQ_EXITING) static_branch_enable(&scx_ops_enq_exiting); + if (ops->flags & SCX_OPS_ENQ_MIGRATION_DISABLED) + static_branch_enable(&scx_ops_enq_migration_disabled); if (scx_ops.cpu_acquire || scx_ops.cpu_release) static_branch_enable(&scx_ops_cpu_preempt); diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h index 4d022d17ac7d..1079b56b0f7a 100644 --- a/kernel/sched/ext.h +++ b/kernel/sched/ext.h @@ -73,7 +73,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {} int scx_tg_online(struct task_group *tg); void scx_tg_offline(struct task_group *tg); int scx_cgroup_can_attach(struct cgroup_taskset *tset); -void scx_move_task(struct task_struct *p); +void scx_cgroup_move_task(struct task_struct *p); void scx_cgroup_finish_attach(void); void scx_cgroup_cancel_attach(struct cgroup_taskset *tset); void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight); @@ -82,7 +82,7 @@ void scx_group_set_idle(struct task_group *tg, bool idle); static inline int scx_tg_online(struct task_group *tg) { return 0; } static inline void scx_tg_offline(struct task_group *tg) {} static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static inline void scx_move_task(struct task_struct *p) {} +static inline void scx_cgroup_move_task(struct task_struct *p) {} static inline void scx_cgroup_finish_attach(void) {} static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {} static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {} diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1e78caa21436..1c0ef435a7aa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -133,7 +133,7 @@ static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536; #endif #ifdef CONFIG_SYSCTL -static struct ctl_table sched_fair_sysctls[] = { +static const struct ctl_table sched_fair_sysctls[] = { #ifdef CONFIG_CFS_BANDWIDTH { .procname = "sched_cfs_bandwidth_slice_us", @@ -5385,6 +5385,15 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); static void set_delayed(struct sched_entity *se) { se->sched_delayed = 1; + + /* + * Delayed se of cfs_rq have no tasks queued on them. + * Do not adjust h_nr_runnable since dequeue_entities() + * will account it for blocked tasks. + */ + if (!entity_is_task(se)) + return; + for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -5397,6 +5406,16 @@ static void set_delayed(struct sched_entity *se) static void clear_delayed(struct sched_entity *se) { se->sched_delayed = 0; + + /* + * Delayed se of cfs_rq have no tasks queued on them. + * Do not adjust h_nr_runnable since a dequeue has + * already accounted for it or an enqueue of a task + * below it will account for it in enqueue_task_fair(). + */ + if (!entity_is_task(se)) + return; + for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index bd66a46b06ac..4b8e33c615b1 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -26,7 +26,7 @@ static int sched_rt_handler(const struct ctl_table *table, int write, void *buff size_t *lenp, loff_t *ppos); static int sched_rr_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -static struct ctl_table sched_rt_sysctls[] = { +static const struct ctl_table sched_rt_sysctls[] = { { .procname = "sched_rt_period_us", .data = &sysctl_sched_rt_period, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 38e0e323dda2..b93c8c3dc05a 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -572,7 +572,7 @@ extern void sched_online_group(struct task_group *tg, extern void sched_destroy_group(struct task_group *tg); extern void sched_release_group(struct task_group *tg); -extern void sched_move_task(struct task_struct *tsk); +extern void sched_move_task(struct task_struct *tsk, bool for_autogroup); #ifdef CONFIG_FAIR_GROUP_SCHED extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c index 149e2c8036d3..456d339be98f 100644 --- a/kernel/sched/syscalls.c +++ b/kernel/sched/syscalls.c @@ -1130,6 +1130,13 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) return 0; /* + * The special/sugov task isn't part of regular bandwidth/admission + * control so let userspace change affinities. + */ + if (dl_entity_is_special(&p->dl)) + return 0; + + /* * Since bandwidth control happens on root_domain basis, * if admission test is enabled, we only admit -deadline * tasks allowed to run on all the CPUs in the task's diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index da33ec9e94ab..c49aea8c1025 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -312,7 +312,7 @@ static int sched_energy_aware_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table sched_energy_aware_sysctls[] = { +static const struct ctl_table sched_energy_aware_sysctls[] = { { .procname = "sched_energy_aware", .data = &sysctl_sched_energy_aware, diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 385d48293a5f..7bbb408431eb 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -749,6 +749,15 @@ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, if (WARN_ON_ONCE(!fprog)) return false; + /* Our single exception to filtering. */ +#ifdef __NR_uretprobe +#ifdef SECCOMP_ARCH_COMPAT + if (sd->arch == SECCOMP_ARCH_NATIVE) +#endif + if (sd->nr == __NR_uretprobe) + return true; +#endif + for (pc = 0; pc < fprog->len; pc++) { struct sock_filter *insn = &fprog->filter[pc]; u16 code = insn->code; @@ -1023,6 +1032,9 @@ static inline void seccomp_log(unsigned long syscall, long signr, u32 action, */ static const int mode1_syscalls[] = { __NR_seccomp_read, __NR_seccomp_write, __NR_seccomp_exit, __NR_seccomp_sigreturn, +#ifdef __NR_uretprobe + __NR_uretprobe, +#endif -1, /* negative terminated */ }; @@ -2450,7 +2462,7 @@ static int seccomp_actions_logged_handler(const struct ctl_table *ro_table, int return ret; } -static struct ctl_table seccomp_sysctl_table[] = { +static const struct ctl_table seccomp_sysctl_table[] = { { .procname = "actions_avail", .data = (void *) &seccomp_actions_avail, diff --git a/kernel/signal.c b/kernel/signal.c index a2afd54303f0..875e97f6205a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4950,7 +4950,7 @@ static inline void siginfo_buildtime_checks(void) } #if defined(CONFIG_SYSCTL) -static struct ctl_table signal_debug_table[] = { +static const struct ctl_table signal_debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { .procname = "exception-trace", diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 0f4804f28c61..bb65321761b4 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -45,7 +45,7 @@ static int stack_erasing_sysctl(const struct ctl_table *table, int write, str_enabled_disabled(state)); return ret; } -static struct ctl_table stackleak_sysctls[] = { +static const struct ctl_table stackleak_sysctls[] = { { .procname = "stack_erasing", .data = NULL, diff --git a/kernel/sysctl-test.c b/kernel/sysctl-test.c index 3ac98bb7fb82..eb2842bd0557 100644 --- a/kernel/sysctl-test.c +++ b/kernel/sysctl-test.c @@ -374,7 +374,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( struct kunit *test) { unsigned char data = 0; - struct ctl_table table_foo[] = { + const struct ctl_table table_foo[] = { { .procname = "foo", .data = &data, @@ -386,7 +386,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( }, }; - struct ctl_table table_bar[] = { + const struct ctl_table table_bar[] = { { .procname = "bar", .data = &data, @@ -398,7 +398,7 @@ static void sysctl_test_register_sysctl_sz_invalid_extra_value( }, }; - struct ctl_table table_qux[] = { + const struct ctl_table table_qux[] = { { .procname = "qux", .data = &data, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 7ae7a4136855..cb57da499ebb 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1609,7 +1609,7 @@ int proc_do_static_key(const struct ctl_table *table, int write, return ret; } -static struct ctl_table kern_table[] = { +static const struct ctl_table kern_table[] = { { .procname = "panic", .data = &panic_timeout, @@ -2021,7 +2021,7 @@ static struct ctl_table kern_table[] = { #endif }; -static struct ctl_table vm_table[] = { +static const struct ctl_table vm_table[] = { { .procname = "overcommit_memory", .data = &sysctl_overcommit_memory, diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 7304d7cf47f2..2a7802ec480c 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -373,16 +373,18 @@ void clocksource_verify_percpu(struct clocksource *cs) cpumask_clear(&cpus_ahead); cpumask_clear(&cpus_behind); cpus_read_lock(); - preempt_disable(); + migrate_disable(); clocksource_verify_choose_cpus(); if (cpumask_empty(&cpus_chosen)) { - preempt_enable(); + migrate_enable(); cpus_read_unlock(); pr_warn("Not enough CPUs to check clocksource '%s'.\n", cs->name); return; } testcpu = smp_processor_id(); - pr_warn("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", cs->name, testcpu, cpumask_pr_args(&cpus_chosen)); + pr_info("Checking clocksource %s synchronization from CPU %d to CPUs %*pbl.\n", + cs->name, testcpu, cpumask_pr_args(&cpus_chosen)); + preempt_disable(); for_each_cpu(cpu, &cpus_chosen) { if (cpu == testcpu) continue; @@ -402,6 +404,7 @@ void clocksource_verify_percpu(struct clocksource *cs) cs_nsec_min = cs_nsec; } preempt_enable(); + migrate_enable(); cpus_read_unlock(); if (!cpumask_empty(&cpus_ahead)) pr_warn(" CPUs %*pbl ahead of CPU %d for clocksource %s.\n", diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index f6d8df94045c..deb1aa32814e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -58,6 +58,8 @@ #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) +static void retrigger_next_event(void *arg); + /* * The timer bases: * @@ -111,7 +113,8 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, - } + }, + .csd = CSD_INIT(retrigger_next_event, NULL) }; static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { @@ -124,6 +127,14 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { [CLOCK_TAI] = HRTIMER_BASE_TAI, }; +static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) +{ + if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) + return true; + else + return likely(base->online); +} + /* * Functions and macros which are different for UP/SMP systems are kept in a * single place @@ -145,11 +156,6 @@ static struct hrtimer_cpu_base migration_cpu_base = { #define migration_base migration_cpu_base.clock_base[0] -static inline bool is_migration_base(struct hrtimer_clock_base *base) -{ - return base == &migration_base; -} - /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are @@ -183,27 +189,54 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, } /* - * We do not migrate the timer when it is expiring before the next - * event on the target cpu. When high resolution is enabled, we cannot - * reprogram the target cpu hardware and we would cause it to fire - * late. To keep it simple, we handle the high resolution enabled and - * disabled case similar. + * Check if the elected target is suitable considering its next + * event and the hotplug state of the current CPU. + * + * If the elected target is remote and its next event is after the timer + * to queue, then a remote reprogram is necessary. However there is no + * guarantee the IPI handling the operation would arrive in time to meet + * the high resolution deadline. In this case the local CPU becomes a + * preferred target, unless it is offline. + * + * High and low resolution modes are handled the same way for simplicity. * * Called with cpu_base->lock of target cpu held. */ -static int -hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) +static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base, + struct hrtimer_cpu_base *new_cpu_base, + struct hrtimer_cpu_base *this_cpu_base) { ktime_t expires; + /* + * The local CPU clockevent can be reprogrammed. Also get_target_base() + * guarantees it is online. + */ + if (new_cpu_base == this_cpu_base) + return true; + + /* + * The offline local CPU can't be the default target if the + * next remote target event is after this timer. Keep the + * elected new base. An IPI will we issued to reprogram + * it as a last resort. + */ + if (!hrtimer_base_is_online(this_cpu_base)) + return true; + expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); - return expires < new_base->cpu_base->expires_next; + + return expires >= new_base->cpu_base->expires_next; } -static inline -struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, - int pinned) +static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { + if (!hrtimer_base_is_online(base)) { + int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER)); + + return &per_cpu(hrtimer_bases, cpu); + } + #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); @@ -254,8 +287,8 @@ again: raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); - if (new_cpu_base != this_cpu_base && - hrtimer_check_target(timer, new_base)) { + if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, + this_cpu_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; @@ -264,8 +297,7 @@ again: } WRITE_ONCE(timer->base, new_base); } else { - if (new_cpu_base != this_cpu_base && - hrtimer_check_target(timer, new_base)) { + if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { new_cpu_base = this_cpu_base; goto again; } @@ -275,11 +307,6 @@ again: #else /* CONFIG_SMP */ -static inline bool is_migration_base(struct hrtimer_clock_base *base) -{ - return false; -} - static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) @@ -716,8 +743,6 @@ static inline int hrtimer_is_hres_enabled(void) return hrtimer_hres_enabled; } -static void retrigger_next_event(void *arg); - /* * Switch to high resolution mode */ @@ -1205,6 +1230,7 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { + struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *new_base; bool force_local, first; @@ -1216,10 +1242,16 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ - force_local = base->cpu_base == this_cpu_ptr(&hrtimer_bases); + force_local = base->cpu_base == this_cpu_base; force_local &= base->cpu_base->next_timer == timer; /* + * Don't force local queuing if this enqueue happens on a unplugged + * CPU after hrtimer_cpu_dying() has been invoked. + */ + force_local &= this_cpu_base->online; + + /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. @@ -1248,8 +1280,27 @@ static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, } first = enqueue_hrtimer(timer, new_base, mode); - if (!force_local) - return first; + if (!force_local) { + /* + * If the current CPU base is online, then the timer is + * never queued on a remote CPU if it would be the first + * expiring timer there. + */ + if (hrtimer_base_is_online(this_cpu_base)) + return first; + + /* + * Timer was enqueued remote because the current base is + * already offline. If the timer is the first to expire, + * kick the remote CPU to reprogram the clock event. + */ + if (first) { + struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base; + + smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd); + } + return 0; + } /* * Timer was forced to stay on the current CPU to avoid @@ -1370,6 +1421,18 @@ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, } } +#ifdef CONFIG_SMP +static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) +{ + return base == &migration_base; +} +#else +static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) +{ + return false; +} +#endif + /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 40706cb36920..c8f776dc6ee0 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -301,7 +301,7 @@ static int timer_migration_handler(const struct ctl_table *table, int write, return ret; } -static struct ctl_table timer_sysctl[] = { +static const struct ctl_table timer_sysctl[] = { { .procname = "timer_migration", .data = &sysctl_timer_migration, diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 9cb9b6584ea1..2f6330831f08 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1675,6 +1675,9 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) } while (i < tmigr_hierarchy_levels); + /* Assert single root */ + WARN_ON_ONCE(!err && !group->parent && !list_is_singular(&tmigr_level_list[top])); + while (i > 0) { group = stack[--i]; @@ -1716,7 +1719,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) WARN_ON_ONCE(top == 0); lvllist = &tmigr_level_list[top]; - if (group->num_children == 1 && list_is_singular(lvllist)) { + + /* + * Newly created root level should have accounted the upcoming + * CPU's child group and pre-accounted the old root. + */ + if (group->num_children == 2 && list_is_singular(lvllist)) { /* * The target CPU must never do the prepare work, except * on early boot when the boot CPU is the target. Otherwise diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f79eb9386c7f..728ecda6e8d4 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -8780,7 +8780,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write, return 0; } -static struct ctl_table ftrace_sysctls[] = { +static const struct ctl_table ftrace_sysctls[] = { { .procname = "ftrace_enabled", .data = &ftrace_enabled, diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b8e0ae15ca5b..bb6089c2951e 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1672,7 +1672,8 @@ static void *rb_range_buffer(struct ring_buffer_per_cpu *cpu_buffer, int idx) * must be the same. */ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, - struct trace_buffer *buffer, int nr_pages) + struct trace_buffer *buffer, int nr_pages, + unsigned long *subbuf_mask) { int subbuf_size = PAGE_SIZE; struct buffer_data_page *subbuf; @@ -1680,6 +1681,9 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, unsigned long buffers_end; int i; + if (!subbuf_mask) + return false; + /* Check the meta magic and meta struct size */ if (meta->magic != RING_BUFFER_META_MAGIC || meta->struct_size != sizeof(*meta)) { @@ -1712,6 +1716,8 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, subbuf = rb_subbufs_from_meta(meta); + bitmap_clear(subbuf_mask, 0, meta->nr_subbufs); + /* Is the meta buffers and the subbufs themselves have correct data? */ for (i = 0; i < meta->nr_subbufs; i++) { if (meta->buffers[i] < 0 || @@ -1725,6 +1731,12 @@ static bool rb_meta_valid(struct ring_buffer_meta *meta, int cpu, return false; } + if (test_bit(meta->buffers[i], subbuf_mask)) { + pr_info("Ring buffer boot meta [%d] array has duplicates\n", cpu); + return false; + } + + set_bit(meta->buffers[i], subbuf_mask); subbuf = (void *)subbuf + subbuf_size; } @@ -1838,6 +1850,11 @@ static void rb_meta_validate_events(struct ring_buffer_per_cpu *cpu_buffer) cpu_buffer->cpu); goto invalid; } + + /* If the buffer has content, update pages_touched */ + if (ret) + local_inc(&cpu_buffer->pages_touched); + entries += ret; entry_bytes += local_read(&head_page->page->commit); local_set(&cpu_buffer->head_page->entries, ret); @@ -1889,17 +1906,22 @@ static void rb_meta_init_text_addr(struct ring_buffer_meta *meta) static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) { struct ring_buffer_meta *meta; + unsigned long *subbuf_mask; unsigned long delta; void *subbuf; int cpu; int i; + /* Create a mask to test the subbuf array */ + subbuf_mask = bitmap_alloc(nr_pages + 1, GFP_KERNEL); + /* If subbuf_mask fails to allocate, then rb_meta_valid() will return false */ + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { void *next_meta; meta = rb_range_meta(buffer, nr_pages, cpu); - if (rb_meta_valid(meta, cpu, buffer, nr_pages)) { + if (rb_meta_valid(meta, cpu, buffer, nr_pages, subbuf_mask)) { /* Make the mappings match the current address */ subbuf = rb_subbufs_from_meta(meta); delta = (unsigned long)subbuf - meta->first_buffer; @@ -1943,6 +1965,7 @@ static void rb_range_meta_init(struct trace_buffer *buffer, int nr_pages) subbuf += meta->subbuf_size; } } + bitmap_free(subbuf_mask); } static void *rbm_start(struct seq_file *m, loff_t *pos) @@ -7126,6 +7149,7 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, kfree(cpu_buffer->subbuf_ids); cpu_buffer->subbuf_ids = NULL; rb_free_meta_page(cpu_buffer); + atomic_dec(&cpu_buffer->resize_disabled); } unlock: diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1496a5ac33ae..0e6d517e74e0 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5977,8 +5977,6 @@ static int __tracing_resize_ring_buffer(struct trace_array *tr, ssize_t tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu_id) { - int ret; - guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { @@ -5987,11 +5985,7 @@ ssize_t tracing_resize_ring_buffer(struct trace_array *tr, return -EINVAL; } - ret = __tracing_resize_ring_buffer(tr, size, cpu_id); - if (ret < 0) - ret = -ENOMEM; - - return ret; + return __tracing_resize_ring_buffer(tr, size, cpu_id); } static void update_last_data(struct trace_array *tr) @@ -8285,6 +8279,10 @@ static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) struct trace_iterator *iter = &info->iter; int ret = 0; + /* Currently the boot mapped buffer is not supported for mmap */ + if (iter->tr->flags & TRACE_ARRAY_FL_BOOT) + return -ENODEV; + ret = get_snapshot_map(iter->tr); if (ret) return ret; diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index 17bcad8f79de..97325fbd6283 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -2899,7 +2899,7 @@ static int set_max_user_events_sysctl(const struct ctl_table *table, int write, return ret; } -static struct ctl_table user_event_sysctls[] = { +static const struct ctl_table user_event_sysctls[] = { { .procname = "user_events_max", .data = &max_user_events, diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 54d850997c0a..136c750b0b4d 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -198,7 +198,7 @@ int trace_graph_entry(struct ftrace_graph_ent *trace, * returning from the function. */ if (ftrace_graph_notrace_addr(trace->func)) { - *task_var |= TRACE_GRAPH_NOTRACE_BIT; + *task_var |= TRACE_GRAPH_NOTRACE; /* * Need to return 1 to have the return called * that will clear the NOTRACE bit. diff --git a/kernel/umh.c b/kernel/umh.c index be9234270777..b4da45a3a7cf 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -544,7 +544,7 @@ static int proc_cap_handler(const struct ctl_table *table, int write, return 0; } -static struct ctl_table usermodehelper_table[] = { +static const struct ctl_table usermodehelper_table[] = { { .procname = "bset", .data = &usermodehelper_bset, diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c index 7282f61a8650..bfbaaecb1dd4 100644 --- a/kernel/utsname_sysctl.c +++ b/kernel/utsname_sysctl.c @@ -75,7 +75,7 @@ static DEFINE_CTL_TABLE_POLL(hostname_poll); static DEFINE_CTL_TABLE_POLL(domainname_poll); // Note: update 'enum uts_proc' to match any changes to this table -static struct ctl_table uts_kern_table[] = { +static const struct ctl_table uts_kern_table[] = { { .procname = "arch", .data = init_uts_ns.name.machine, @@ -129,7 +129,7 @@ static struct ctl_table uts_kern_table[] = { */ void uts_proc_notify(enum uts_proc proc) { - struct ctl_table *table = &uts_kern_table[proc]; + const struct ctl_table *table = &uts_kern_table[proc]; proc_sys_poll_notify(table->poll); } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 177abb7d0d4e..b2da7de39d06 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -1094,7 +1094,7 @@ static int proc_watchdog_cpumask(const struct ctl_table *table, int write, static const int sixty = 60; -static struct ctl_table watchdog_sysctls[] = { +static const struct ctl_table watchdog_sysctls[] = { { .procname = "watchdog", .data = &watchdog_user_enabled, diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3c2c45313c88..97152f2250fe 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -3517,12 +3517,6 @@ repeat: } /* - * Put the reference grabbed by send_mayday(). @pool won't - * go away while we're still attached to it. - */ - put_pwq(pwq); - - /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ @@ -3532,6 +3526,12 @@ repeat: worker_detach_from_pool(rescuer); + /* + * Put the reference grabbed by send_mayday(). @pool might + * go away any time after it. + */ + put_pwq_unlocked(pwq); + raw_spin_lock_irq(&wq_mayday_lock); } diff --git a/lib/Kconfig b/lib/Kconfig index a78d22c6507f..dccb61b7d698 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -164,34 +164,9 @@ config CRC_T10DIF config ARCH_HAS_CRC_T10DIF bool -choice - prompt "CRC-T10DIF implementation" - depends on CRC_T10DIF - default CRC_T10DIF_IMPL_ARCH if ARCH_HAS_CRC_T10DIF - default CRC_T10DIF_IMPL_GENERIC if !ARCH_HAS_CRC_T10DIF - help - This option allows you to override the default choice of CRC-T10DIF - implementation. - -config CRC_T10DIF_IMPL_ARCH - bool "Architecture-optimized" if ARCH_HAS_CRC_T10DIF - help - Use the optimized implementation of CRC-T10DIF for the selected - architecture. It is recommended to keep this enabled, as it can - greatly improve CRC-T10DIF performance. - -config CRC_T10DIF_IMPL_GENERIC - bool "Generic implementation" - help - Use the generic table-based implementation of CRC-T10DIF. Selecting - this will reduce code size slightly but can greatly reduce CRC-T10DIF - performance. - -endchoice - config CRC_T10DIF_ARCH tristate - default CRC_T10DIF if CRC_T10DIF_IMPL_ARCH + default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS config CRC64_ROCKSOFT tristate "CRC calculation for the Rocksoft model CRC64" @@ -223,87 +198,9 @@ config CRC32 config ARCH_HAS_CRC32 bool -choice - prompt "CRC32 implementation" - depends on CRC32 - default CRC32_IMPL_ARCH_PLUS_SLICEBY8 if ARCH_HAS_CRC32 - default CRC32_IMPL_SLICEBY8 if !ARCH_HAS_CRC32 - help - This option allows you to override the default choice of CRC32 - implementation. Choose the default unless you know that you need one - of the others. - -config CRC32_IMPL_ARCH_PLUS_SLICEBY8 - bool "Arch-optimized, with fallback to slice-by-8" if ARCH_HAS_CRC32 - help - Use architecture-optimized implementation of CRC32. Fall back to - slice-by-8 in cases where the arch-optimized implementation cannot be - used, e.g. if the CPU lacks support for the needed instructions. - - This is the default when an arch-optimized implementation exists. - -config CRC32_IMPL_ARCH_PLUS_SLICEBY1 - bool "Arch-optimized, with fallback to slice-by-1" if ARCH_HAS_CRC32 - help - Use architecture-optimized implementation of CRC32, but fall back to - slice-by-1 instead of slice-by-8 in order to reduce the binary size. - -config CRC32_IMPL_SLICEBY8 - bool "Slice by 8 bytes" - help - Calculate checksum 8 bytes at a time with a clever slicing algorithm. - This is much slower than the architecture-optimized implementation of - CRC32 (if the selected arch has one), but it is portable and is the - fastest implementation when no arch-optimized implementation is - available. It uses an 8KiB lookup table. Most modern processors have - enough cache to hold this table without thrashing the cache. - -config CRC32_IMPL_SLICEBY4 - bool "Slice by 4 bytes" - help - Calculate checksum 4 bytes at a time with a clever slicing algorithm. - This is a bit slower than slice by 8, but has a smaller 4KiB lookup - table. - - Only choose this option if you know what you are doing. - -config CRC32_IMPL_SLICEBY1 - bool "Slice by 1 byte (Sarwate's algorithm)" - help - Calculate checksum a byte at a time using Sarwate's algorithm. This - is not particularly fast, but has a small 1KiB lookup table. - - Only choose this option if you know what you are doing. - -config CRC32_IMPL_BIT - bool "Classic Algorithm (one bit at a time)" - help - Calculate checksum one bit at a time. This is VERY slow, but has - no lookup table. This is provided as a debugging option. - - Only choose this option if you are debugging crc32. - -endchoice - config CRC32_ARCH tristate - default CRC32 if CRC32_IMPL_ARCH_PLUS_SLICEBY8 || CRC32_IMPL_ARCH_PLUS_SLICEBY1 - -config CRC32_SLICEBY8 - bool - default y if CRC32_IMPL_SLICEBY8 || CRC32_IMPL_ARCH_PLUS_SLICEBY8 - -config CRC32_SLICEBY4 - bool - default y if CRC32_IMPL_SLICEBY4 - -config CRC32_SARWATE - bool - default y if CRC32_IMPL_SLICEBY1 || CRC32_IMPL_ARCH_PLUS_SLICEBY1 - -config CRC32_BIT - bool - default y if CRC32_IMPL_BIT + default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS config CRC64 tristate "CRC64 functions" @@ -343,6 +240,17 @@ config CRC8 when they need to do cyclic redundancy check according CRC8 algorithm. Module will be called crc8. +config CRC_OPTIMIZATIONS + bool "Enable optimized CRC implementations" if EXPERT + default y + help + Disabling this option reduces code size slightly by disabling the + architecture-optimized implementations of any CRC variants that are + enabled. CRC checksumming performance may get much slower. + + Keep this enabled unless you're really trying to minimize the size of + the kernel. + config XXHASH tristate diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 775966cf6114..1af972a92d06 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2456,22 +2456,8 @@ config TEST_BITMAP config TEST_UUID tristate "Test functions located in the uuid module at runtime" -config XARRAY_KUNIT - tristate "KUnit test XArray code at runtime" if !KUNIT_ALL_TESTS - depends on KUNIT - default KUNIT_ALL_TESTS - help - Enable this option to test the Xarray code at boot. - - KUnit tests run during boot and output the results to the debug log - in TAP format (http://testanything.org/). Only useful for kernel devs - running the KUnit test harness, and not intended for inclusion into a - production build. - - For more information on KUnit and unit tests in general please refer - to the KUnit documentation in Documentation/dev-tools/kunit/. - - If unsure, say N. +config TEST_XARRAY + tristate "Test the XArray code at runtime" config TEST_MAPLE_TREE tristate "Test the Maple Tree code at runtime or module load" diff --git a/lib/Makefile b/lib/Makefile index f1c6e9d76a7c..d5cfc7afbbb8 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -94,6 +94,7 @@ GCOV_PROFILE_test_bitmap.o := n endif obj-$(CONFIG_TEST_UUID) += test_uuid.o +obj-$(CONFIG_TEST_XARRAY) += test_xarray.o obj-$(CONFIG_TEST_MAPLE_TREE) += test_maple_tree.o obj-$(CONFIG_TEST_PARMAN) += test_parman.o obj-$(CONFIG_TEST_KMOD) += test_kmod.o @@ -372,7 +373,6 @@ CFLAGS_bitfield_kunit.o := $(DISABLE_STRUCTLEAK_PLUGIN) obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o obj-$(CONFIG_CHECKSUM_KUNIT) += checksum_kunit.o obj-$(CONFIG_UTIL_MACROS_KUNIT) += util_macros_kunit.o -obj-$(CONFIG_XARRAY_KUNIT) += test_xarray.o obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o obj-$(CONFIG_HASHTABLE_KUNIT_TEST) += hashtable_test.o obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o diff --git a/lib/crc32.c b/lib/crc32.c index 47151624332e..ede6131f66fc 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -30,20 +30,6 @@ #include <linux/crc32poly.h> #include <linux/module.h> #include <linux/types.h> -#include <linux/sched.h> -#include "crc32defs.h" - -#if CRC_LE_BITS > 8 -# define tole(x) ((__force u32) cpu_to_le32(x)) -#else -# define tole(x) (x) -#endif - -#if CRC_BE_BITS > 8 -# define tobe(x) ((__force u32) cpu_to_be32(x)) -#else -# define tobe(x) (x) -#endif #include "crc32table.h" @@ -51,157 +37,20 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>"); MODULE_DESCRIPTION("Various CRC32 calculations"); MODULE_LICENSE("GPL"); -#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8 - -/* implements slicing-by-4 or slicing-by-8 algorithm */ -static inline u32 __pure -crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) -{ -# ifdef __LITTLE_ENDIAN -# define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8) -# define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \ - t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255]) -# define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \ - t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255]) -# else -# define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8) -# define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \ - t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255]) -# define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \ - t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255]) -# endif - const u32 *b; - size_t rem_len; -# ifdef CONFIG_X86 - size_t i; -# endif - const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3]; -# if CRC_LE_BITS != 32 - const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7]; -# endif - u32 q; - - /* Align it */ - if (unlikely((long)buf & 3 && len)) { - do { - DO_CRC(*buf++); - } while ((--len) && ((long)buf)&3); - } - -# if CRC_LE_BITS == 32 - rem_len = len & 3; - len = len >> 2; -# else - rem_len = len & 7; - len = len >> 3; -# endif - - b = (const u32 *)buf; -# ifdef CONFIG_X86 - --b; - for (i = 0; i < len; i++) { -# else - for (--b; len; --len) { -# endif - q = crc ^ *++b; /* use pre increment for speed */ -# if CRC_LE_BITS == 32 - crc = DO_CRC4; -# else - crc = DO_CRC8; - q = *++b; - crc ^= DO_CRC4; -# endif - } - len = rem_len; - /* And the last few bytes */ - if (len) { - u8 *p = (u8 *)(b + 1) - 1; -# ifdef CONFIG_X86 - for (i = 0; i < len; i++) - DO_CRC(*++p); /* use pre increment for speed */ -# else - do { - DO_CRC(*++p); /* use pre increment for speed */ - } while (--len); -# endif - } - return crc; -#undef DO_CRC -#undef DO_CRC4 -#undef DO_CRC8 -} -#endif - - -/** - * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II - * CRC32/CRC32C - * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for other - * uses, or the previous crc32/crc32c value if computing incrementally. - * @p: pointer to buffer over which CRC32/CRC32C is run - * @len: length of buffer @p - * @tab: little-endian Ethernet table - * @polynomial: CRC32/CRC32c LE polynomial - */ -static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p, - size_t len, const u32 (*tab)[256], - u32 polynomial) +u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len) { -#if CRC_LE_BITS == 1 - int i; - while (len--) { - crc ^= *p++; - for (i = 0; i < 8; i++) - crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); - } -# elif CRC_LE_BITS == 2 - while (len--) { - crc ^= *p++; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - crc = (crc >> 2) ^ tab[0][crc & 3]; - } -# elif CRC_LE_BITS == 4 - while (len--) { - crc ^= *p++; - crc = (crc >> 4) ^ tab[0][crc & 15]; - crc = (crc >> 4) ^ tab[0][crc & 15]; - } -# elif CRC_LE_BITS == 8 - /* aka Sarwate algorithm */ - while (len--) { - crc ^= *p++; - crc = (crc >> 8) ^ tab[0][crc & 255]; - } -# else - crc = (__force u32) __cpu_to_le32(crc); - crc = crc32_body(crc, p, len, tab); - crc = __le32_to_cpu((__force __le32)crc); -#endif + while (len--) + crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++]; return crc; } +EXPORT_SYMBOL(crc32_le_base); -#if CRC_LE_BITS == 1 -u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len) -{ - return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE); -} -u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len) -{ - return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE); -} -#else -u32 __pure crc32_le_base(u32 crc, const u8 *p, size_t len) -{ - return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE); -} u32 __pure crc32c_le_base(u32 crc, const u8 *p, size_t len) { - return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE); + while (len--) + crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++]; + return crc; } -#endif -EXPORT_SYMBOL(crc32_le_base); EXPORT_SYMBOL(crc32c_le_base); /* @@ -277,64 +126,10 @@ u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len) EXPORT_SYMBOL(crc32_le_shift); EXPORT_SYMBOL(__crc32c_le_shift); -/** - * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 - * @crc: seed value for computation. ~0 for Ethernet, sometimes 0 for - * other uses, or the previous crc32 value if computing incrementally. - * @p: pointer to buffer over which CRC32 is run - * @len: length of buffer @p - * @tab: big-endian Ethernet table - * @polynomial: CRC32 BE polynomial - */ -static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p, - size_t len, const u32 (*tab)[256], - u32 polynomial) -{ -#if CRC_BE_BITS == 1 - int i; - while (len--) { - crc ^= *p++ << 24; - for (i = 0; i < 8; i++) - crc = - (crc << 1) ^ ((crc & 0x80000000) ? polynomial : - 0); - } -# elif CRC_BE_BITS == 2 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - crc = (crc << 2) ^ tab[0][crc >> 30]; - } -# elif CRC_BE_BITS == 4 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 4) ^ tab[0][crc >> 28]; - crc = (crc << 4) ^ tab[0][crc >> 28]; - } -# elif CRC_BE_BITS == 8 - while (len--) { - crc ^= *p++ << 24; - crc = (crc << 8) ^ tab[0][crc >> 24]; - } -# else - crc = (__force u32) __cpu_to_be32(crc); - crc = crc32_body(crc, p, len, tab); - crc = __be32_to_cpu((__force __be32)crc); -# endif - return crc; -} - -#if CRC_BE_BITS == 1 -u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len) -{ - return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE); -} -#else u32 __pure crc32_be_base(u32 crc, const u8 *p, size_t len) { - return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE); + while (len--) + crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++]; + return crc; } -#endif EXPORT_SYMBOL(crc32_be_base); diff --git a/lib/crc32defs.h b/lib/crc32defs.h deleted file mode 100644 index 0c8fb5923e7e..000000000000 --- a/lib/crc32defs.h +++ /dev/null @@ -1,59 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* Try to choose an implementation variant via Kconfig */ -#ifdef CONFIG_CRC32_SLICEBY8 -# define CRC_LE_BITS 64 -# define CRC_BE_BITS 64 -#endif -#ifdef CONFIG_CRC32_SLICEBY4 -# define CRC_LE_BITS 32 -# define CRC_BE_BITS 32 -#endif -#ifdef CONFIG_CRC32_SARWATE -# define CRC_LE_BITS 8 -# define CRC_BE_BITS 8 -#endif -#ifdef CONFIG_CRC32_BIT -# define CRC_LE_BITS 1 -# define CRC_BE_BITS 1 -#endif - -/* - * How many bits at a time to use. Valid values are 1, 2, 4, 8, 32 and 64. - * For less performance-sensitive, use 4 or 8 to save table size. - * For larger systems choose same as CPU architecture as default. - * This works well on X86_64, SPARC64 systems. This may require some - * elaboration after experiments with other architectures. - */ -#ifndef CRC_LE_BITS -# ifdef CONFIG_64BIT -# define CRC_LE_BITS 64 -# else -# define CRC_LE_BITS 32 -# endif -#endif -#ifndef CRC_BE_BITS -# ifdef CONFIG_64BIT -# define CRC_BE_BITS 64 -# else -# define CRC_BE_BITS 32 -# endif -#endif - -/* - * Little-endian CRC computation. Used with serial bit streams sent - * lsbit-first. Be sure to use cpu_to_le32() to append the computed CRC. - */ -#if CRC_LE_BITS > 64 || CRC_LE_BITS < 1 || CRC_LE_BITS == 16 || \ - CRC_LE_BITS & CRC_LE_BITS-1 -# error "CRC_LE_BITS must be one of {1, 2, 4, 8, 32, 64}" -#endif - -/* - * Big-endian CRC computation. Used with serial bit streams sent - * msbit-first. Be sure to use cpu_to_be32() to append the computed CRC. - */ -#if CRC_BE_BITS > 64 || CRC_BE_BITS < 1 || CRC_BE_BITS == 16 || \ - CRC_BE_BITS & CRC_BE_BITS-1 -# error "CRC_BE_BITS must be one of {1, 2, 4, 8, 32, 64}" -#endif diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c index f755b997b967..6d03425b849e 100644 --- a/lib/gen_crc32table.c +++ b/lib/gen_crc32table.c @@ -2,30 +2,11 @@ #include <stdio.h> #include "../include/linux/crc32poly.h" #include "../include/generated/autoconf.h" -#include "crc32defs.h" #include <inttypes.h> -#define ENTRIES_PER_LINE 4 - -#if CRC_LE_BITS > 8 -# define LE_TABLE_ROWS (CRC_LE_BITS/8) -# define LE_TABLE_SIZE 256 -#else -# define LE_TABLE_ROWS 1 -# define LE_TABLE_SIZE (1 << CRC_LE_BITS) -#endif - -#if CRC_BE_BITS > 8 -# define BE_TABLE_ROWS (CRC_BE_BITS/8) -# define BE_TABLE_SIZE 256 -#else -# define BE_TABLE_ROWS 1 -# define BE_TABLE_SIZE (1 << CRC_BE_BITS) -#endif - -static uint32_t crc32table_le[LE_TABLE_ROWS][256]; -static uint32_t crc32table_be[BE_TABLE_ROWS][256]; -static uint32_t crc32ctable_le[LE_TABLE_ROWS][256]; +static uint32_t crc32table_le[256]; +static uint32_t crc32table_be[256]; +static uint32_t crc32ctable_le[256]; /** * crc32init_le() - allocate and initialize LE table data @@ -34,25 +15,17 @@ static uint32_t crc32ctable_le[LE_TABLE_ROWS][256]; * fact that crctable[i^j] = crctable[i] ^ crctable[j]. * */ -static void crc32init_le_generic(const uint32_t polynomial, - uint32_t (*tab)[256]) +static void crc32init_le_generic(const uint32_t polynomial, uint32_t tab[256]) { unsigned i, j; uint32_t crc = 1; - tab[0][0] = 0; + tab[0] = 0; - for (i = LE_TABLE_SIZE >> 1; i; i >>= 1) { + for (i = 128; i; i >>= 1) { crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0); - for (j = 0; j < LE_TABLE_SIZE; j += 2 * i) - tab[0][i + j] = crc ^ tab[0][j]; - } - for (i = 0; i < LE_TABLE_SIZE; i++) { - crc = tab[0][i]; - for (j = 1; j < LE_TABLE_ROWS; j++) { - crc = tab[0][crc & 0xff] ^ (crc >> 8); - tab[j][i] = crc; - } + for (j = 0; j < 256; j += 2 * i) + tab[i + j] = crc ^ tab[j]; } } @@ -74,34 +47,22 @@ static void crc32init_be(void) unsigned i, j; uint32_t crc = 0x80000000; - crc32table_be[0][0] = 0; + crc32table_be[0] = 0; - for (i = 1; i < BE_TABLE_SIZE; i <<= 1) { + for (i = 1; i < 256; i <<= 1) { crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0); for (j = 0; j < i; j++) - crc32table_be[0][i + j] = crc ^ crc32table_be[0][j]; - } - for (i = 0; i < BE_TABLE_SIZE; i++) { - crc = crc32table_be[0][i]; - for (j = 1; j < BE_TABLE_ROWS; j++) { - crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8); - crc32table_be[j][i] = crc; - } + crc32table_be[i + j] = crc ^ crc32table_be[j]; } } -static void output_table(uint32_t (*table)[256], int rows, int len, char *trans) +static void output_table(const uint32_t table[256]) { - int i, j; - - for (j = 0 ; j < rows; j++) { - printf("{"); - for (i = 0; i < len - 1; i++) { - if (i % ENTRIES_PER_LINE == 0) - printf("\n"); - printf("%s(0x%8.8xL), ", trans, table[j][i]); - } - printf("%s(0x%8.8xL)},\n", trans, table[j][len - 1]); + int i; + + for (i = 0; i < 256; i += 4) { + printf("\t0x%08x, 0x%08x, 0x%08x, 0x%08x,\n", + table[i], table[i + 1], table[i + 2], table[i + 3]); } } @@ -109,34 +70,20 @@ int main(int argc, char** argv) { printf("/* this file is generated - do not edit */\n\n"); - if (CRC_LE_BITS > 1) { - crc32init_le(); - printf("static const u32 ____cacheline_aligned " - "crc32table_le[%d][%d] = {", - LE_TABLE_ROWS, LE_TABLE_SIZE); - output_table(crc32table_le, LE_TABLE_ROWS, - LE_TABLE_SIZE, "tole"); - printf("};\n"); - } + crc32init_le(); + printf("static const u32 ____cacheline_aligned crc32table_le[256] = {\n"); + output_table(crc32table_le); + printf("};\n"); - if (CRC_BE_BITS > 1) { - crc32init_be(); - printf("static const u32 ____cacheline_aligned " - "crc32table_be[%d][%d] = {", - BE_TABLE_ROWS, BE_TABLE_SIZE); - output_table(crc32table_be, LE_TABLE_ROWS, - BE_TABLE_SIZE, "tobe"); - printf("};\n"); - } - if (CRC_LE_BITS > 1) { - crc32cinit_le(); - printf("static const u32 ____cacheline_aligned " - "crc32ctable_le[%d][%d] = {", - LE_TABLE_ROWS, LE_TABLE_SIZE); - output_table(crc32ctable_le, LE_TABLE_ROWS, - LE_TABLE_SIZE, "tole"); - printf("};\n"); - } + crc32init_be(); + printf("static const u32 ____cacheline_aligned crc32table_be[256] = {\n"); + output_table(crc32table_be); + printf("};\n"); + + crc32cinit_le(); + printf("static const u32 ____cacheline_aligned crc32ctable_le[256] = {\n"); + output_table(crc32ctable_le); + printf("};\n"); return 0; } diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 9ec806f989f2..65f550cb5081 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1428,6 +1428,8 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, struct iovec *iov = *iovp; ssize_t ret; + *iovp = NULL; + if (compat) ret = copy_compat_iovec_from_user(iov, uvec, 1); else @@ -1438,7 +1440,6 @@ static ssize_t __import_iovec_ubuf(int type, const struct iovec __user *uvec, ret = import_ubuf(type, iov->iov_base, iov->iov_len, i); if (unlikely(ret)) return ret; - *iovp = NULL; return i->count; } diff --git a/lib/stackinit_kunit.c b/lib/stackinit_kunit.c index c40818ec9c18..135322592faf 100644 --- a/lib/stackinit_kunit.c +++ b/lib/stackinit_kunit.c @@ -47,10 +47,12 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define DO_NOTHING_TYPE_SCALAR(var_type) var_type #define DO_NOTHING_TYPE_STRING(var_type) void #define DO_NOTHING_TYPE_STRUCT(var_type) void +#define DO_NOTHING_TYPE_UNION(var_type) void #define DO_NOTHING_RETURN_SCALAR(ptr) *(ptr) #define DO_NOTHING_RETURN_STRING(ptr) /**/ #define DO_NOTHING_RETURN_STRUCT(ptr) /**/ +#define DO_NOTHING_RETURN_UNION(ptr) /**/ #define DO_NOTHING_CALL_SCALAR(var, name) \ (var) = do_nothing_ ## name(&(var)) @@ -58,10 +60,13 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, do_nothing_ ## name(var) #define DO_NOTHING_CALL_STRUCT(var, name) \ do_nothing_ ## name(&(var)) +#define DO_NOTHING_CALL_UNION(var, name) \ + do_nothing_ ## name(&(var)) #define FETCH_ARG_SCALAR(var) &var #define FETCH_ARG_STRING(var) var #define FETCH_ARG_STRUCT(var) &var +#define FETCH_ARG_UNION(var) &var /* * On m68k, if the leaf function test variable is longer than 8 bytes, @@ -70,13 +75,16 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, */ #ifdef CONFIG_M68K #define FILL_SIZE_STRING 8 +#define FILL_SIZE_ARRAY 2 #else #define FILL_SIZE_STRING 16 +#define FILL_SIZE_ARRAY 8 #endif #define INIT_CLONE_SCALAR /**/ #define INIT_CLONE_STRING [FILL_SIZE_STRING] #define INIT_CLONE_STRUCT /**/ +#define INIT_CLONE_UNION /**/ #define ZERO_CLONE_SCALAR(zero) memset(&(zero), 0x00, sizeof(zero)) #define ZERO_CLONE_STRING(zero) memset(&(zero), 0x00, sizeof(zero)) @@ -92,6 +100,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, zero.three = 0; \ zero.four = 0; \ } while (0) +#define ZERO_CLONE_UNION(zero) ZERO_CLONE_STRUCT(zero) #define INIT_SCALAR_none(var_type) /**/ #define INIT_SCALAR_zero(var_type) = 0 @@ -101,6 +110,7 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define INIT_STRUCT_none(var_type) /**/ #define INIT_STRUCT_zero(var_type) = { } +#define INIT_STRUCT_old_zero(var_type) = { 0 } #define __static_partial { .two = 0, } @@ -146,6 +156,34 @@ static bool stackinit_range_contains(char *haystack_start, size_t haystack_size, #define INIT_STRUCT_assigned_copy(var_type) \ ; var = *(arg) +/* Union initialization is the same as structs. */ +#define INIT_UNION_none(var_type) INIT_STRUCT_none(var_type) +#define INIT_UNION_zero(var_type) INIT_STRUCT_zero(var_type) +#define INIT_UNION_old_zero(var_type) INIT_STRUCT_old_zero(var_type) + +#define INIT_UNION_static_partial(var_type) \ + INIT_STRUCT_static_partial(var_type) +#define INIT_UNION_static_all(var_type) \ + INIT_STRUCT_static_all(var_type) +#define INIT_UNION_dynamic_partial(var_type) \ + INIT_STRUCT_dynamic_partial(var_type) +#define INIT_UNION_dynamic_all(var_type) \ + INIT_STRUCT_dynamic_all(var_type) +#define INIT_UNION_runtime_partial(var_type) \ + INIT_STRUCT_runtime_partial(var_type) +#define INIT_UNION_runtime_all(var_type) \ + INIT_STRUCT_runtime_all(var_type) +#define INIT_UNION_assigned_static_partial(var_type) \ + INIT_STRUCT_assigned_static_partial(var_type) +#define INIT_UNION_assigned_static_all(var_type) \ + INIT_STRUCT_assigned_static_all(var_type) +#define INIT_UNION_assigned_dynamic_partial(var_type) \ + INIT_STRUCT_assigned_dynamic_partial(var_type) +#define INIT_UNION_assigned_dynamic_all(var_type) \ + INIT_STRUCT_assigned_dynamic_all(var_type) +#define INIT_UNION_assigned_copy(var_type) \ + INIT_STRUCT_assigned_copy(var_type) + /* * @name: unique string name for the test * @var_type: type to be tested for zeroing initialization @@ -294,6 +332,33 @@ struct test_user { unsigned long four; }; +/* No padding: all members are the same size. */ +union test_same_sizes { + unsigned long one; + unsigned long two; + unsigned long three; + unsigned long four; +}; + +/* Mismatched sizes, with one and two being small */ +union test_small_start { + char one:1; + char two; + short three; + unsigned long four; + struct big_struct { + unsigned long array[FILL_SIZE_ARRAY]; + } big; +}; + +/* Mismatched sizes, with three and four being small */ +union test_small_end { + short one; + unsigned long two; + char three:1; + char four; +}; + #define ALWAYS_PASS WANT_SUCCESS #define ALWAYS_FAIL XFAIL @@ -332,6 +397,11 @@ struct test_user { struct test_ ## name, STRUCT, init, \ xfail) +#define DEFINE_UNION_TEST(name, init, xfail) \ + DEFINE_TEST(name ## _ ## init, \ + union test_ ## name, STRUCT, init, \ + xfail) + #define DEFINE_STRUCT_TESTS(init, xfail) \ DEFINE_STRUCT_TEST(small_hole, init, xfail); \ DEFINE_STRUCT_TEST(big_hole, init, xfail); \ @@ -343,9 +413,22 @@ struct test_user { xfail); \ DEFINE_STRUCT_TESTS(base ## _ ## all, xfail) +#define DEFINE_UNION_INITIALIZER_TESTS(base, xfail) \ + DEFINE_UNION_TESTS(base ## _ ## partial, \ + xfail); \ + DEFINE_UNION_TESTS(base ## _ ## all, xfail) + +#define DEFINE_UNION_TESTS(init, xfail) \ + DEFINE_UNION_TEST(same_sizes, init, xfail); \ + DEFINE_UNION_TEST(small_start, init, xfail); \ + DEFINE_UNION_TEST(small_end, init, xfail); + /* These should be fully initialized all the time! */ DEFINE_SCALAR_TESTS(zero, ALWAYS_PASS); DEFINE_STRUCT_TESTS(zero, ALWAYS_PASS); +DEFINE_STRUCT_TESTS(old_zero, ALWAYS_PASS); +DEFINE_UNION_TESTS(zero, ALWAYS_PASS); +DEFINE_UNION_TESTS(old_zero, ALWAYS_PASS); /* Struct initializers: padding may be left uninitialized. */ DEFINE_STRUCT_INITIALIZER_TESTS(static, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(dynamic, STRONG_PASS); @@ -353,6 +436,12 @@ DEFINE_STRUCT_INITIALIZER_TESTS(runtime, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(assigned_static, STRONG_PASS); DEFINE_STRUCT_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS); DEFINE_STRUCT_TESTS(assigned_copy, ALWAYS_FAIL); +DEFINE_UNION_INITIALIZER_TESTS(static, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(dynamic, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(runtime, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(assigned_static, STRONG_PASS); +DEFINE_UNION_INITIALIZER_TESTS(assigned_dynamic, STRONG_PASS); +DEFINE_UNION_TESTS(assigned_copy, ALWAYS_FAIL); /* No initialization without compiler instrumentation. */ DEFINE_SCALAR_TESTS(none, STRONG_PASS); DEFINE_STRUCT_TESTS(none, BYREF_PASS); @@ -436,13 +525,23 @@ DEFINE_TEST_DRIVER(switch_2_none, uint64_t, SCALAR, ALWAYS_FAIL); KUNIT_CASE(test_trailing_hole_ ## init),\ KUNIT_CASE(test_packed_ ## init) \ +#define KUNIT_test_unions(init) \ + KUNIT_CASE(test_same_sizes_ ## init), \ + KUNIT_CASE(test_small_start_ ## init), \ + KUNIT_CASE(test_small_end_ ## init) \ + static struct kunit_case stackinit_test_cases[] = { /* These are explicitly initialized and should always pass. */ KUNIT_test_scalars(zero), KUNIT_test_structs(zero), + KUNIT_test_structs(old_zero), + KUNIT_test_unions(zero), + KUNIT_test_unions(old_zero), /* Padding here appears to be accidentally always initialized? */ KUNIT_test_structs(dynamic_partial), KUNIT_test_structs(assigned_dynamic_partial), + KUNIT_test_unions(dynamic_partial), + KUNIT_test_unions(assigned_dynamic_partial), /* Padding initialization depends on compiler behaviors. */ KUNIT_test_structs(static_partial), KUNIT_test_structs(static_all), @@ -452,8 +551,17 @@ static struct kunit_case stackinit_test_cases[] = { KUNIT_test_structs(assigned_static_partial), KUNIT_test_structs(assigned_static_all), KUNIT_test_structs(assigned_dynamic_all), + KUNIT_test_unions(static_partial), + KUNIT_test_unions(static_all), + KUNIT_test_unions(dynamic_all), + KUNIT_test_unions(runtime_partial), + KUNIT_test_unions(runtime_all), + KUNIT_test_unions(assigned_static_partial), + KUNIT_test_unions(assigned_static_all), + KUNIT_test_unions(assigned_dynamic_all), /* Everything fails this since it effectively performs a memcpy(). */ KUNIT_test_structs(assigned_copy), + KUNIT_test_unions(assigned_copy), /* STRUCTLEAK_BYREF_ALL should cover everything from here down. */ KUNIT_test_scalars(none), KUNIT_CASE(test_switch_1_none), diff --git a/lib/test_sysctl.c b/lib/test_sysctl.c index b6696fa1d426..4249e0cc8aaf 100644 --- a/lib/test_sysctl.c +++ b/lib/test_sysctl.c @@ -71,7 +71,7 @@ static struct test_sysctl_data test_data = { }; /* These are all under /proc/sys/debug/test_sysctl/ */ -static struct ctl_table test_table[] = { +static const struct ctl_table test_table[] = { { .procname = "int_0001", .data = &test_data.int_0001, @@ -177,7 +177,7 @@ static int test_sysctl_setup_node_tests(void) } /* Used to test that unregister actually removes the directory */ -static struct ctl_table test_table_unregister[] = { +static const struct ctl_table test_table_unregister[] = { { .procname = "unregister_error", .data = &test_data.int_0001, @@ -220,7 +220,7 @@ static int test_sysctl_run_register_mount_point(void) return 0; } -static struct ctl_table test_table_empty[] = { }; +static const struct ctl_table test_table_empty[] = { }; static int test_sysctl_run_register_empty(void) { diff --git a/lib/test_xarray.c b/lib/test_xarray.c index eab5971d0a48..0e865bab4a10 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -6,10 +6,11 @@ * Author: Matthew Wilcox <willy@infradead.org> */ -#include <kunit/test.h> - -#include <linux/module.h> #include <linux/xarray.h> +#include <linux/module.h> + +static unsigned int tests_run; +static unsigned int tests_passed; static const unsigned int order_limit = IS_ENABLED(CONFIG_XARRAY_MULTI) ? BITS_PER_LONG : 1; @@ -19,12 +20,15 @@ static const unsigned int order_limit = void xa_dump(const struct xarray *xa) { } # endif #undef XA_BUG_ON -#define XA_BUG_ON(xa, x) do { \ - if (x) { \ - KUNIT_FAIL(test, #x); \ - xa_dump(xa); \ - dump_stack(); \ - } \ +#define XA_BUG_ON(xa, x) do { \ + tests_run++; \ + if (x) { \ + printk("BUG at %s:%d\n", __func__, __LINE__); \ + xa_dump(xa); \ + dump_stack(); \ + } else { \ + tests_passed++; \ + } \ } while (0) #endif @@ -38,13 +42,13 @@ static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) return xa_store(xa, index, xa_mk_index(index), gfp); } -static void xa_insert_index(struct kunit *test, struct xarray *xa, unsigned long index) +static void xa_insert_index(struct xarray *xa, unsigned long index) { XA_BUG_ON(xa, xa_insert(xa, index, xa_mk_index(index), GFP_KERNEL) != 0); } -static void xa_alloc_index(struct kunit *test, struct xarray *xa, unsigned long index, gfp_t gfp) +static void xa_alloc_index(struct xarray *xa, unsigned long index, gfp_t gfp) { u32 id; @@ -53,7 +57,7 @@ static void xa_alloc_index(struct kunit *test, struct xarray *xa, unsigned long XA_BUG_ON(xa, id != index); } -static void xa_erase_index(struct kunit *test, struct xarray *xa, unsigned long index) +static void xa_erase_index(struct xarray *xa, unsigned long index) { XA_BUG_ON(xa, xa_erase(xa, index) != xa_mk_index(index)); XA_BUG_ON(xa, xa_load(xa, index) != NULL); @@ -79,15 +83,8 @@ static void *xa_store_order(struct xarray *xa, unsigned long index, return curr; } -static inline struct xarray *xa_param(struct kunit *test) +static noinline void check_xa_err(struct xarray *xa) { - return *(struct xarray **)test->param_value; -} - -static noinline void check_xa_err(struct kunit *test) -{ - struct xarray *xa = xa_param(test); - XA_BUG_ON(xa, xa_err(xa_store_index(xa, 0, GFP_NOWAIT)) != 0); XA_BUG_ON(xa, xa_err(xa_erase(xa, 0)) != 0); #ifndef __KERNEL__ @@ -102,10 +99,8 @@ static noinline void check_xa_err(struct kunit *test) // XA_BUG_ON(xa, xa_err(xa_store(xa, 0, xa_mk_internal(0), 0)) != -EINVAL); } -static noinline void check_xas_retry(struct kunit *test) +static noinline void check_xas_retry(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); void *entry; @@ -114,7 +109,7 @@ static noinline void check_xas_retry(struct kunit *test) rcu_read_lock(); XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_value(0)); - xa_erase_index(test, xa, 1); + xa_erase_index(xa, 1); XA_BUG_ON(xa, !xa_is_retry(xas_reload(&xas))); XA_BUG_ON(xa, xas_retry(&xas, NULL)); XA_BUG_ON(xa, xas_retry(&xas, xa_mk_value(0))); @@ -145,14 +140,12 @@ static noinline void check_xas_retry(struct kunit *test) } xas_unlock(&xas); - xa_erase_index(test, xa, 0); - xa_erase_index(test, xa, 1); + xa_erase_index(xa, 0); + xa_erase_index(xa, 1); } -static noinline void check_xa_load(struct kunit *test) +static noinline void check_xa_load(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned long i, j; for (i = 0; i < 1024; i++) { @@ -174,15 +167,13 @@ static noinline void check_xa_load(struct kunit *test) else XA_BUG_ON(xa, entry); } - xa_erase_index(test, xa, i); + xa_erase_index(xa, i); } XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_xa_mark_1(struct kunit *test, unsigned long index) +static noinline void check_xa_mark_1(struct xarray *xa, unsigned long index) { - struct xarray *xa = xa_param(test); - unsigned int order; unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 8 : 1; @@ -202,7 +193,7 @@ static noinline void check_xa_mark_1(struct kunit *test, unsigned long index) XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_1)); /* Storing NULL clears marks, and they can't be set again */ - xa_erase_index(test, xa, index); + xa_erase_index(xa, index); XA_BUG_ON(xa, !xa_empty(xa)); XA_BUG_ON(xa, xa_get_mark(xa, index, XA_MARK_0)); xa_set_mark(xa, index, XA_MARK_0); @@ -253,17 +244,15 @@ static noinline void check_xa_mark_1(struct kunit *test, unsigned long index) XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_0)); XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_1)); XA_BUG_ON(xa, xa_get_mark(xa, next, XA_MARK_2)); - xa_erase_index(test, xa, index); - xa_erase_index(test, xa, next); + xa_erase_index(xa, index); + xa_erase_index(xa, next); XA_BUG_ON(xa, !xa_empty(xa)); } XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_xa_mark_2(struct kunit *test) +static noinline void check_xa_mark_2(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); unsigned long index; unsigned int count = 0; @@ -300,11 +289,9 @@ static noinline void check_xa_mark_2(struct kunit *test) xa_destroy(xa); } -static noinline void check_xa_mark_3(struct kunit *test) +static noinline void check_xa_mark_3(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0x41); void *entry; int count = 0; @@ -323,21 +310,19 @@ static noinline void check_xa_mark_3(struct kunit *test) #endif } -static noinline void check_xa_mark(struct kunit *test) +static noinline void check_xa_mark(struct xarray *xa) { unsigned long index; for (index = 0; index < 16384; index += 4) - check_xa_mark_1(test, index); + check_xa_mark_1(xa, index); - check_xa_mark_2(test); - check_xa_mark_3(test); + check_xa_mark_2(xa); + check_xa_mark_3(xa); } -static noinline void check_xa_shrink(struct kunit *test) +static noinline void check_xa_shrink(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 1); struct xa_node *node; unsigned int order; @@ -362,7 +347,7 @@ static noinline void check_xa_shrink(struct kunit *test) XA_BUG_ON(xa, xas_load(&xas) != NULL); xas_unlock(&xas); XA_BUG_ON(xa, xa_load(xa, 0) != xa_mk_value(0)); - xa_erase_index(test, xa, 0); + xa_erase_index(xa, 0); XA_BUG_ON(xa, !xa_empty(xa)); for (order = 0; order < max_order; order++) { @@ -379,49 +364,45 @@ static noinline void check_xa_shrink(struct kunit *test) XA_BUG_ON(xa, xa_head(xa) == node); rcu_read_unlock(); XA_BUG_ON(xa, xa_load(xa, max + 1) != NULL); - xa_erase_index(test, xa, ULONG_MAX); + xa_erase_index(xa, ULONG_MAX); XA_BUG_ON(xa, xa->xa_head != node); - xa_erase_index(test, xa, 0); + xa_erase_index(xa, 0); } } -static noinline void check_insert(struct kunit *test) +static noinline void check_insert(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned long i; for (i = 0; i < 1024; i++) { - xa_insert_index(test, xa, i); + xa_insert_index(xa, i); XA_BUG_ON(xa, xa_load(xa, i - 1) != NULL); XA_BUG_ON(xa, xa_load(xa, i + 1) != NULL); - xa_erase_index(test, xa, i); + xa_erase_index(xa, i); } for (i = 10; i < BITS_PER_LONG; i++) { - xa_insert_index(test, xa, 1UL << i); + xa_insert_index(xa, 1UL << i); XA_BUG_ON(xa, xa_load(xa, (1UL << i) - 1) != NULL); XA_BUG_ON(xa, xa_load(xa, (1UL << i) + 1) != NULL); - xa_erase_index(test, xa, 1UL << i); + xa_erase_index(xa, 1UL << i); - xa_insert_index(test, xa, (1UL << i) - 1); + xa_insert_index(xa, (1UL << i) - 1); XA_BUG_ON(xa, xa_load(xa, (1UL << i) - 2) != NULL); XA_BUG_ON(xa, xa_load(xa, 1UL << i) != NULL); - xa_erase_index(test, xa, (1UL << i) - 1); + xa_erase_index(xa, (1UL << i) - 1); } - xa_insert_index(test, xa, ~0UL); + xa_insert_index(xa, ~0UL); XA_BUG_ON(xa, xa_load(xa, 0UL) != NULL); XA_BUG_ON(xa, xa_load(xa, ~1UL) != NULL); - xa_erase_index(test, xa, ~0UL); + xa_erase_index(xa, ~0UL); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_cmpxchg(struct kunit *test) +static noinline void check_cmpxchg(struct xarray *xa) { - struct xarray *xa = xa_param(test); - void *FIVE = xa_mk_value(5); void *SIX = xa_mk_value(6); void *LOTS = xa_mk_value(12345678); @@ -437,16 +418,14 @@ static noinline void check_cmpxchg(struct kunit *test) XA_BUG_ON(xa, xa_insert(xa, 5, FIVE, GFP_KERNEL) != -EBUSY); XA_BUG_ON(xa, xa_cmpxchg(xa, 5, FIVE, NULL, GFP_KERNEL) != FIVE); XA_BUG_ON(xa, xa_insert(xa, 5, FIVE, GFP_KERNEL) == -EBUSY); - xa_erase_index(test, xa, 12345678); - xa_erase_index(test, xa, 5); + xa_erase_index(xa, 12345678); + xa_erase_index(xa, 5); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_cmpxchg_order(struct kunit *test) +static noinline void check_cmpxchg_order(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI - struct xarray *xa = xa_param(test); - void *FIVE = xa_mk_value(5); unsigned int i, order = 3; @@ -497,10 +476,8 @@ static noinline void check_cmpxchg_order(struct kunit *test) #endif } -static noinline void check_reserve(struct kunit *test) +static noinline void check_reserve(struct xarray *xa) { - struct xarray *xa = xa_param(test); - void *entry; unsigned long index; int count; @@ -517,7 +494,7 @@ static noinline void check_reserve(struct kunit *test) XA_BUG_ON(xa, xa_reserve(xa, 12345678, GFP_KERNEL) != 0); XA_BUG_ON(xa, xa_store_index(xa, 12345678, GFP_NOWAIT) != NULL); xa_release(xa, 12345678); - xa_erase_index(test, xa, 12345678); + xa_erase_index(xa, 12345678); XA_BUG_ON(xa, !xa_empty(xa)); /* cmpxchg sees a reserved entry as ZERO */ @@ -525,7 +502,7 @@ static noinline void check_reserve(struct kunit *test) XA_BUG_ON(xa, xa_cmpxchg(xa, 12345678, XA_ZERO_ENTRY, xa_mk_value(12345678), GFP_NOWAIT) != NULL); xa_release(xa, 12345678); - xa_erase_index(test, xa, 12345678); + xa_erase_index(xa, 12345678); XA_BUG_ON(xa, !xa_empty(xa)); /* xa_insert treats it as busy */ @@ -565,10 +542,8 @@ static noinline void check_reserve(struct kunit *test) xa_destroy(xa); } -static noinline void check_xas_erase(struct kunit *test) +static noinline void check_xas_erase(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); void *entry; unsigned long i, j; @@ -606,11 +581,9 @@ static noinline void check_xas_erase(struct kunit *test) } #ifdef CONFIG_XARRAY_MULTI -static noinline void check_multi_store_1(struct kunit *test, unsigned long index, +static noinline void check_multi_store_1(struct xarray *xa, unsigned long index, unsigned int order) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, index); unsigned long min = index & ~((1UL << order) - 1); unsigned long max = min + (1UL << order); @@ -629,15 +602,13 @@ static noinline void check_multi_store_1(struct kunit *test, unsigned long index XA_BUG_ON(xa, xa_load(xa, max) != NULL); XA_BUG_ON(xa, xa_load(xa, min - 1) != NULL); - xa_erase_index(test, xa, min); + xa_erase_index(xa, min); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_multi_store_2(struct kunit *test, unsigned long index, +static noinline void check_multi_store_2(struct xarray *xa, unsigned long index, unsigned int order) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, index); xa_store_order(xa, index, order, xa_mk_value(0), GFP_KERNEL); @@ -649,11 +620,9 @@ static noinline void check_multi_store_2(struct kunit *test, unsigned long index XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_multi_store_3(struct kunit *test, unsigned long index, +static noinline void check_multi_store_3(struct xarray *xa, unsigned long index, unsigned int order) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); void *entry; int n = 0; @@ -678,11 +647,9 @@ static noinline void check_multi_store_3(struct kunit *test, unsigned long index } #endif -static noinline void check_multi_store(struct kunit *test) +static noinline void check_multi_store(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI - struct xarray *xa = xa_param(test); - unsigned long i, j, k; unsigned int max_order = (sizeof(long) == 4) ? 30 : 60; @@ -747,28 +714,26 @@ static noinline void check_multi_store(struct kunit *test) } for (i = 0; i < 20; i++) { - check_multi_store_1(test, 200, i); - check_multi_store_1(test, 0, i); - check_multi_store_1(test, (1UL << i) + 1, i); + check_multi_store_1(xa, 200, i); + check_multi_store_1(xa, 0, i); + check_multi_store_1(xa, (1UL << i) + 1, i); } - check_multi_store_2(test, 4095, 9); + check_multi_store_2(xa, 4095, 9); for (i = 1; i < 20; i++) { - check_multi_store_3(test, 0, i); - check_multi_store_3(test, 1UL << i, i); + check_multi_store_3(xa, 0, i); + check_multi_store_3(xa, 1UL << i, i); } #endif } #ifdef CONFIG_XARRAY_MULTI /* mimics page cache __filemap_add_folio() */ -static noinline void check_xa_multi_store_adv_add(struct kunit *test, +static noinline void check_xa_multi_store_adv_add(struct xarray *xa, unsigned long index, unsigned int order, void *p) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, index); unsigned int nrpages = 1UL << order; @@ -796,12 +761,10 @@ static noinline void check_xa_multi_store_adv_add(struct kunit *test, } /* mimics page_cache_delete() */ -static noinline void check_xa_multi_store_adv_del_entry(struct kunit *test, +static noinline void check_xa_multi_store_adv_del_entry(struct xarray *xa, unsigned long index, unsigned int order) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, index); xas_set_order(&xas, index, order); @@ -809,14 +772,12 @@ static noinline void check_xa_multi_store_adv_del_entry(struct kunit *test, xas_init_marks(&xas); } -static noinline void check_xa_multi_store_adv_delete(struct kunit *test, +static noinline void check_xa_multi_store_adv_delete(struct xarray *xa, unsigned long index, unsigned int order) { - struct xarray *xa = xa_param(test); - xa_lock_irq(xa); - check_xa_multi_store_adv_del_entry(test, index, order); + check_xa_multi_store_adv_del_entry(xa, index, order); xa_unlock_irq(xa); } @@ -853,12 +814,10 @@ static unsigned long some_val = 0xdeadbeef; static unsigned long some_val_2 = 0xdeaddead; /* mimics the page cache usage */ -static noinline void check_xa_multi_store_adv(struct kunit *test, +static noinline void check_xa_multi_store_adv(struct xarray *xa, unsigned long pos, unsigned int order) { - struct xarray *xa = xa_param(test); - unsigned int nrpages = 1UL << order; unsigned long index, base, next_index, next_next_index; unsigned int i; @@ -868,7 +827,7 @@ static noinline void check_xa_multi_store_adv(struct kunit *test, next_index = round_down(base + nrpages, nrpages); next_next_index = round_down(next_index + nrpages, nrpages); - check_xa_multi_store_adv_add(test, base, order, &some_val); + check_xa_multi_store_adv_add(xa, base, order, &some_val); for (i = 0; i < nrpages; i++) XA_BUG_ON(xa, test_get_entry(xa, base + i) != &some_val); @@ -876,20 +835,20 @@ static noinline void check_xa_multi_store_adv(struct kunit *test, XA_BUG_ON(xa, test_get_entry(xa, next_index) != NULL); /* Use order 0 for the next item */ - check_xa_multi_store_adv_add(test, next_index, 0, &some_val_2); + check_xa_multi_store_adv_add(xa, next_index, 0, &some_val_2); XA_BUG_ON(xa, test_get_entry(xa, next_index) != &some_val_2); /* Remove the next item */ - check_xa_multi_store_adv_delete(test, next_index, 0); + check_xa_multi_store_adv_delete(xa, next_index, 0); /* Now use order for a new pointer */ - check_xa_multi_store_adv_add(test, next_index, order, &some_val_2); + check_xa_multi_store_adv_add(xa, next_index, order, &some_val_2); for (i = 0; i < nrpages; i++) XA_BUG_ON(xa, test_get_entry(xa, next_index + i) != &some_val_2); - check_xa_multi_store_adv_delete(test, next_index, order); - check_xa_multi_store_adv_delete(test, base, order); + check_xa_multi_store_adv_delete(xa, next_index, order); + check_xa_multi_store_adv_delete(xa, base, order); XA_BUG_ON(xa, !xa_empty(xa)); /* starting fresh again */ @@ -897,7 +856,7 @@ static noinline void check_xa_multi_store_adv(struct kunit *test, /* let's test some holes now */ /* hole at base and next_next */ - check_xa_multi_store_adv_add(test, next_index, order, &some_val_2); + check_xa_multi_store_adv_add(xa, next_index, order, &some_val_2); for (i = 0; i < nrpages; i++) XA_BUG_ON(xa, test_get_entry(xa, base + i) != NULL); @@ -908,12 +867,12 @@ static noinline void check_xa_multi_store_adv(struct kunit *test, for (i = 0; i < nrpages; i++) XA_BUG_ON(xa, test_get_entry(xa, next_next_index + i) != NULL); - check_xa_multi_store_adv_delete(test, next_index, order); + check_xa_multi_store_adv_delete(xa, next_index, order); XA_BUG_ON(xa, !xa_empty(xa)); /* hole at base and next */ - check_xa_multi_store_adv_add(test, next_next_index, order, &some_val_2); + check_xa_multi_store_adv_add(xa, next_next_index, order, &some_val_2); for (i = 0; i < nrpages; i++) XA_BUG_ON(xa, test_get_entry(xa, base + i) != NULL); @@ -924,12 +883,12 @@ static noinline void check_xa_multi_store_adv(struct kunit *test, for (i = 0; i < nrpages; i++) XA_BUG_ON(xa, test_get_entry(xa, next_next_index + i) != &some_val_2); - check_xa_multi_store_adv_delete(test, next_next_index, order); + check_xa_multi_store_adv_delete(xa, next_next_index, order); XA_BUG_ON(xa, !xa_empty(xa)); } #endif -static noinline void check_multi_store_advanced(struct kunit *test) +static noinline void check_multi_store_advanced(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; @@ -941,59 +900,59 @@ static noinline void check_multi_store_advanced(struct kunit *test) */ for (pos = 7; pos < end; pos = (pos * pos) + 564) { for (i = 0; i < max_order; i++) { - check_xa_multi_store_adv(test, pos, i); - check_xa_multi_store_adv(test, pos + 157, i); + check_xa_multi_store_adv(xa, pos, i); + check_xa_multi_store_adv(xa, pos + 157, i); } } #endif } -static noinline void check_xa_alloc_1(struct kunit *test, struct xarray *xa, unsigned int base) +static noinline void check_xa_alloc_1(struct xarray *xa, unsigned int base) { int i; u32 id; XA_BUG_ON(xa, !xa_empty(xa)); /* An empty array should assign %base to the first alloc */ - xa_alloc_index(test, xa, base, GFP_KERNEL); + xa_alloc_index(xa, base, GFP_KERNEL); /* Erasing it should make the array empty again */ - xa_erase_index(test, xa, base); + xa_erase_index(xa, base); XA_BUG_ON(xa, !xa_empty(xa)); /* And it should assign %base again */ - xa_alloc_index(test, xa, base, GFP_KERNEL); + xa_alloc_index(xa, base, GFP_KERNEL); /* Allocating and then erasing a lot should not lose base */ for (i = base + 1; i < 2 * XA_CHUNK_SIZE; i++) - xa_alloc_index(test, xa, i, GFP_KERNEL); + xa_alloc_index(xa, i, GFP_KERNEL); for (i = base; i < 2 * XA_CHUNK_SIZE; i++) - xa_erase_index(test, xa, i); - xa_alloc_index(test, xa, base, GFP_KERNEL); + xa_erase_index(xa, i); + xa_alloc_index(xa, base, GFP_KERNEL); /* Destroying the array should do the same as erasing */ xa_destroy(xa); /* And it should assign %base again */ - xa_alloc_index(test, xa, base, GFP_KERNEL); + xa_alloc_index(xa, base, GFP_KERNEL); /* The next assigned ID should be base+1 */ - xa_alloc_index(test, xa, base + 1, GFP_KERNEL); - xa_erase_index(test, xa, base + 1); + xa_alloc_index(xa, base + 1, GFP_KERNEL); + xa_erase_index(xa, base + 1); /* Storing a value should mark it used */ xa_store_index(xa, base + 1, GFP_KERNEL); - xa_alloc_index(test, xa, base + 2, GFP_KERNEL); + xa_alloc_index(xa, base + 2, GFP_KERNEL); /* If we then erase base, it should be free */ - xa_erase_index(test, xa, base); - xa_alloc_index(test, xa, base, GFP_KERNEL); + xa_erase_index(xa, base); + xa_alloc_index(xa, base, GFP_KERNEL); - xa_erase_index(test, xa, base + 1); - xa_erase_index(test, xa, base + 2); + xa_erase_index(xa, base + 1); + xa_erase_index(xa, base + 2); for (i = 1; i < 5000; i++) { - xa_alloc_index(test, xa, base + i, GFP_KERNEL); + xa_alloc_index(xa, base + i, GFP_KERNEL); } xa_destroy(xa); @@ -1016,14 +975,14 @@ static noinline void check_xa_alloc_1(struct kunit *test, struct xarray *xa, uns XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(10), XA_LIMIT(10, 5), GFP_KERNEL) != -EBUSY); - XA_BUG_ON(xa, xa_store_index(xa, 3, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_store_index(xa, 3, GFP_KERNEL) != 0); XA_BUG_ON(xa, xa_alloc(xa, &id, xa_mk_index(10), XA_LIMIT(10, 5), GFP_KERNEL) != -EBUSY); - xa_erase_index(test, xa, 3); + xa_erase_index(xa, 3); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_xa_alloc_2(struct kunit *test, struct xarray *xa, unsigned int base) +static noinline void check_xa_alloc_2(struct xarray *xa, unsigned int base) { unsigned int i, id; unsigned long index; @@ -1059,7 +1018,7 @@ static noinline void check_xa_alloc_2(struct kunit *test, struct xarray *xa, uns XA_BUG_ON(xa, id != 5); xa_for_each(xa, index, entry) { - xa_erase_index(test, xa, index); + xa_erase_index(xa, index); } for (i = base; i < base + 9; i++) { @@ -1074,7 +1033,7 @@ static noinline void check_xa_alloc_2(struct kunit *test, struct xarray *xa, uns xa_destroy(xa); } -static noinline void check_xa_alloc_3(struct kunit *test, struct xarray *xa, unsigned int base) +static noinline void check_xa_alloc_3(struct xarray *xa, unsigned int base) { struct xa_limit limit = XA_LIMIT(1, 0x3fff); u32 next = 0; @@ -1090,8 +1049,8 @@ static noinline void check_xa_alloc_3(struct kunit *test, struct xarray *xa, uns XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, xa_mk_index(0x3ffd), limit, &next, GFP_KERNEL) != 0); XA_BUG_ON(xa, id != 0x3ffd); - xa_erase_index(test, xa, 0x3ffd); - xa_erase_index(test, xa, 1); + xa_erase_index(xa, 0x3ffd); + xa_erase_index(xa, 1); XA_BUG_ON(xa, !xa_empty(xa)); for (i = 0x3ffe; i < 0x4003; i++) { @@ -1106,8 +1065,8 @@ static noinline void check_xa_alloc_3(struct kunit *test, struct xarray *xa, uns /* Check wrap-around is handled correctly */ if (base != 0) - xa_erase_index(test, xa, base); - xa_erase_index(test, xa, base + 1); + xa_erase_index(xa, base); + xa_erase_index(xa, base + 1); next = UINT_MAX; XA_BUG_ON(xa, xa_alloc_cyclic(xa, &id, xa_mk_index(UINT_MAX), xa_limit_32b, &next, GFP_KERNEL) != 0); @@ -1120,7 +1079,7 @@ static noinline void check_xa_alloc_3(struct kunit *test, struct xarray *xa, uns XA_BUG_ON(xa, id != base + 1); xa_for_each(xa, index, entry) - xa_erase_index(test, xa, index); + xa_erase_index(xa, index); XA_BUG_ON(xa, !xa_empty(xa)); } @@ -1128,21 +1087,19 @@ static noinline void check_xa_alloc_3(struct kunit *test, struct xarray *xa, uns static DEFINE_XARRAY_ALLOC(xa0); static DEFINE_XARRAY_ALLOC1(xa1); -static noinline void check_xa_alloc(struct kunit *test) +static noinline void check_xa_alloc(void) { - check_xa_alloc_1(test, &xa0, 0); - check_xa_alloc_1(test, &xa1, 1); - check_xa_alloc_2(test, &xa0, 0); - check_xa_alloc_2(test, &xa1, 1); - check_xa_alloc_3(test, &xa0, 0); - check_xa_alloc_3(test, &xa1, 1); + check_xa_alloc_1(&xa0, 0); + check_xa_alloc_1(&xa1, 1); + check_xa_alloc_2(&xa0, 0); + check_xa_alloc_2(&xa1, 1); + check_xa_alloc_3(&xa0, 0); + check_xa_alloc_3(&xa1, 1); } -static noinline void __check_store_iter(struct kunit *test, unsigned long start, +static noinline void __check_store_iter(struct xarray *xa, unsigned long start, unsigned int order, unsigned int present) { - struct xarray *xa = xa_param(test); - XA_STATE_ORDER(xas, xa, start, order); void *entry; unsigned int count = 0; @@ -1166,54 +1123,50 @@ retry: XA_BUG_ON(xa, xa_load(xa, start) != xa_mk_index(start)); XA_BUG_ON(xa, xa_load(xa, start + (1UL << order) - 1) != xa_mk_index(start)); - xa_erase_index(test, xa, start); + xa_erase_index(xa, start); } -static noinline void check_store_iter(struct kunit *test) +static noinline void check_store_iter(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned int i, j; unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; for (i = 0; i < max_order; i++) { unsigned int min = 1 << i; unsigned int max = (2 << i) - 1; - __check_store_iter(test, 0, i, 0); + __check_store_iter(xa, 0, i, 0); XA_BUG_ON(xa, !xa_empty(xa)); - __check_store_iter(test, min, i, 0); + __check_store_iter(xa, min, i, 0); XA_BUG_ON(xa, !xa_empty(xa)); xa_store_index(xa, min, GFP_KERNEL); - __check_store_iter(test, min, i, 1); + __check_store_iter(xa, min, i, 1); XA_BUG_ON(xa, !xa_empty(xa)); xa_store_index(xa, max, GFP_KERNEL); - __check_store_iter(test, min, i, 1); + __check_store_iter(xa, min, i, 1); XA_BUG_ON(xa, !xa_empty(xa)); for (j = 0; j < min; j++) xa_store_index(xa, j, GFP_KERNEL); - __check_store_iter(test, 0, i, min); + __check_store_iter(xa, 0, i, min); XA_BUG_ON(xa, !xa_empty(xa)); for (j = 0; j < min; j++) xa_store_index(xa, min + j, GFP_KERNEL); - __check_store_iter(test, min, i, min); + __check_store_iter(xa, min, i, min); XA_BUG_ON(xa, !xa_empty(xa)); } #ifdef CONFIG_XARRAY_MULTI xa_store_index(xa, 63, GFP_KERNEL); xa_store_index(xa, 65, GFP_KERNEL); - __check_store_iter(test, 64, 2, 1); - xa_erase_index(test, xa, 63); + __check_store_iter(xa, 64, 2, 1); + xa_erase_index(xa, 63); #endif XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_multi_find_1(struct kunit *test, unsigned int order) +static noinline void check_multi_find_1(struct xarray *xa, unsigned order) { #ifdef CONFIG_XARRAY_MULTI - struct xarray *xa = xa_param(test); - unsigned long multi = 3 << order; unsigned long next = 4 << order; unsigned long index; @@ -1236,17 +1189,15 @@ static noinline void check_multi_find_1(struct kunit *test, unsigned int order) XA_BUG_ON(xa, xa_find_after(xa, &index, next, XA_PRESENT) != NULL); XA_BUG_ON(xa, index != next); - xa_erase_index(test, xa, multi); - xa_erase_index(test, xa, next); - xa_erase_index(test, xa, next + 1); + xa_erase_index(xa, multi); + xa_erase_index(xa, next); + xa_erase_index(xa, next + 1); XA_BUG_ON(xa, !xa_empty(xa)); #endif } -static noinline void check_multi_find_2(struct kunit *test) +static noinline void check_multi_find_2(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 10 : 1; unsigned int i, j; void *entry; @@ -1260,19 +1211,17 @@ static noinline void check_multi_find_2(struct kunit *test) GFP_KERNEL); rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { - xa_erase_index(test, xa, index); + xa_erase_index(xa, index); } rcu_read_unlock(); - xa_erase_index(test, xa, index - 1); + xa_erase_index(xa, index - 1); XA_BUG_ON(xa, !xa_empty(xa)); } } } -static noinline void check_multi_find_3(struct kunit *test) +static noinline void check_multi_find_3(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned int order; for (order = 5; order < order_limit; order++) { @@ -1281,14 +1230,12 @@ static noinline void check_multi_find_3(struct kunit *test) XA_BUG_ON(xa, !xa_empty(xa)); xa_store_order(xa, 0, order - 4, xa_mk_index(0), GFP_KERNEL); XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT)); - xa_erase_index(test, xa, 0); + xa_erase_index(xa, 0); } } -static noinline void check_find_1(struct kunit *test) +static noinline void check_find_1(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned long i, j, k; XA_BUG_ON(xa, !xa_empty(xa)); @@ -1325,20 +1272,18 @@ static noinline void check_find_1(struct kunit *test) else XA_BUG_ON(xa, entry != NULL); } - xa_erase_index(test, xa, j); + xa_erase_index(xa, j); XA_BUG_ON(xa, xa_get_mark(xa, j, XA_MARK_0)); XA_BUG_ON(xa, !xa_get_mark(xa, i, XA_MARK_0)); } - xa_erase_index(test, xa, i); + xa_erase_index(xa, i); XA_BUG_ON(xa, xa_get_mark(xa, i, XA_MARK_0)); } XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_find_2(struct kunit *test) +static noinline void check_find_2(struct xarray *xa) { - struct xarray *xa = xa_param(test); - void *entry; unsigned long i, j, index; @@ -1358,10 +1303,8 @@ static noinline void check_find_2(struct kunit *test) xa_destroy(xa); } -static noinline void check_find_3(struct kunit *test) +static noinline void check_find_3(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); unsigned long i, j, k; void *entry; @@ -1385,10 +1328,8 @@ static noinline void check_find_3(struct kunit *test) xa_destroy(xa); } -static noinline void check_find_4(struct kunit *test) +static noinline void check_find_4(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned long index = 0; void *entry; @@ -1400,22 +1341,22 @@ static noinline void check_find_4(struct kunit *test) entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT); XA_BUG_ON(xa, entry); - xa_erase_index(test, xa, ULONG_MAX); + xa_erase_index(xa, ULONG_MAX); } -static noinline void check_find(struct kunit *test) +static noinline void check_find(struct xarray *xa) { unsigned i; - check_find_1(test); - check_find_2(test); - check_find_3(test); - check_find_4(test); + check_find_1(xa); + check_find_2(xa); + check_find_3(xa); + check_find_4(xa); for (i = 2; i < 10; i++) - check_multi_find_1(test, i); - check_multi_find_2(test); - check_multi_find_3(test); + check_multi_find_1(xa, i); + check_multi_find_2(xa); + check_multi_find_3(xa); } /* See find_swap_entry() in mm/shmem.c */ @@ -1441,10 +1382,8 @@ static noinline unsigned long xa_find_entry(struct xarray *xa, void *item) return entry ? xas.xa_index : -1; } -static noinline void check_find_entry(struct kunit *test) +static noinline void check_find_entry(struct xarray *xa) { - struct xarray *xa = xa_param(test); - #ifdef CONFIG_XARRAY_MULTI unsigned int order; unsigned long offset, index; @@ -1471,17 +1410,15 @@ static noinline void check_find_entry(struct kunit *test) xa_store_index(xa, ULONG_MAX, GFP_KERNEL); XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1); XA_BUG_ON(xa, xa_find_entry(xa, xa_mk_index(ULONG_MAX)) != -1); - xa_erase_index(test, xa, ULONG_MAX); + xa_erase_index(xa, ULONG_MAX); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_pause(struct kunit *test) +static noinline void check_pause(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); void *entry; - unsigned int order; + int order; unsigned long index = 1; unsigned int count = 0; @@ -1513,7 +1450,7 @@ static noinline void check_pause(struct kunit *test) xa_destroy(xa); index = 0; - for (order = XA_CHUNK_SHIFT; order > 0; order--) { + for (order = order_limit - 1; order >= 0; order--) { XA_BUG_ON(xa, xa_store_order(xa, index, order, xa_mk_index(index), GFP_KERNEL)); index += 1UL << order; @@ -1525,33 +1462,32 @@ static noinline void check_pause(struct kunit *test) rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { XA_BUG_ON(xa, entry != xa_mk_index(index)); - index += 1UL << (XA_CHUNK_SHIFT - count); + index += 1UL << (order_limit - count - 1); count++; } rcu_read_unlock(); - XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + XA_BUG_ON(xa, count != order_limit); index = 0; count = 0; - xas_set(&xas, XA_CHUNK_SIZE / 2 + 1); + /* test unaligned index */ + xas_set(&xas, 1 % (1UL << (order_limit - 1))); rcu_read_lock(); xas_for_each(&xas, entry, ULONG_MAX) { XA_BUG_ON(xa, entry != xa_mk_index(index)); - index += 1UL << (XA_CHUNK_SHIFT - count); + index += 1UL << (order_limit - count - 1); count++; xas_pause(&xas); } rcu_read_unlock(); - XA_BUG_ON(xa, count != XA_CHUNK_SHIFT); + XA_BUG_ON(xa, count != order_limit); xa_destroy(xa); } -static noinline void check_move_tiny(struct kunit *test) +static noinline void check_move_tiny(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); XA_BUG_ON(xa, !xa_empty(xa)); @@ -1568,14 +1504,12 @@ static noinline void check_move_tiny(struct kunit *test) XA_BUG_ON(xa, xas_prev(&xas) != xa_mk_index(0)); XA_BUG_ON(xa, xas_prev(&xas) != NULL); rcu_read_unlock(); - xa_erase_index(test, xa, 0); + xa_erase_index(xa, 0); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_move_max(struct kunit *test) +static noinline void check_move_max(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); xa_store_index(xa, ULONG_MAX, GFP_KERNEL); @@ -1591,14 +1525,12 @@ static noinline void check_move_max(struct kunit *test) XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL); rcu_read_unlock(); - xa_erase_index(test, xa, ULONG_MAX); + xa_erase_index(xa, ULONG_MAX); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_move_small(struct kunit *test, unsigned long idx) +static noinline void check_move_small(struct xarray *xa, unsigned long idx) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); unsigned long i; @@ -1640,15 +1572,13 @@ static noinline void check_move_small(struct kunit *test, unsigned long idx) XA_BUG_ON(xa, xas.xa_index != ULONG_MAX); rcu_read_unlock(); - xa_erase_index(test, xa, 0); - xa_erase_index(test, xa, idx); + xa_erase_index(xa, 0); + xa_erase_index(xa, idx); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_move(struct kunit *test) +static noinline void check_move(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, (1 << 16) - 1); unsigned long i; @@ -1675,7 +1605,7 @@ static noinline void check_move(struct kunit *test) rcu_read_unlock(); for (i = (1 << 8); i < (1 << 15); i++) - xa_erase_index(test, xa, i); + xa_erase_index(xa, i); i = xas.xa_index; @@ -1706,17 +1636,17 @@ static noinline void check_move(struct kunit *test) xa_destroy(xa); - check_move_tiny(test); - check_move_max(test); + check_move_tiny(xa); + check_move_max(xa); for (i = 0; i < 16; i++) - check_move_small(test, 1UL << i); + check_move_small(xa, 1UL << i); for (i = 2; i < 16; i++) - check_move_small(test, (1UL << i) - 1); + check_move_small(xa, (1UL << i) - 1); } -static noinline void xa_store_many_order(struct kunit *test, struct xarray *xa, +static noinline void xa_store_many_order(struct xarray *xa, unsigned long index, unsigned order) { XA_STATE_ORDER(xas, xa, index, order); @@ -1739,34 +1669,30 @@ unlock: XA_BUG_ON(xa, xas_error(&xas)); } -static noinline void check_create_range_1(struct kunit *test, +static noinline void check_create_range_1(struct xarray *xa, unsigned long index, unsigned order) { - struct xarray *xa = xa_param(test); - unsigned long i; - xa_store_many_order(test, xa, index, order); + xa_store_many_order(xa, index, order); for (i = index; i < index + (1UL << order); i++) - xa_erase_index(test, xa, i); + xa_erase_index(xa, i); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_create_range_2(struct kunit *test, unsigned int order) +static noinline void check_create_range_2(struct xarray *xa, unsigned order) { - struct xarray *xa = xa_param(test); - unsigned long i; unsigned long nr = 1UL << order; for (i = 0; i < nr * nr; i += nr) - xa_store_many_order(test, xa, i, order); + xa_store_many_order(xa, i, order); for (i = 0; i < nr * nr; i++) - xa_erase_index(test, xa, i); + xa_erase_index(xa, i); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_create_range_3(struct kunit *test) +static noinline void check_create_range_3(void) { XA_STATE(xas, NULL, 0); xas_set_err(&xas, -EEXIST); @@ -1774,11 +1700,9 @@ static noinline void check_create_range_3(struct kunit *test) XA_BUG_ON(NULL, xas_error(&xas) != -EEXIST); } -static noinline void check_create_range_4(struct kunit *test, +static noinline void check_create_range_4(struct xarray *xa, unsigned long index, unsigned order) { - struct xarray *xa = xa_param(test); - XA_STATE_ORDER(xas, xa, index, order); unsigned long base = xas.xa_index; unsigned long i = 0; @@ -1804,15 +1728,13 @@ unlock: XA_BUG_ON(xa, xas_error(&xas)); for (i = base; i < base + (1UL << order); i++) - xa_erase_index(test, xa, i); + xa_erase_index(xa, i); XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_create_range_5(struct kunit *test, +static noinline void check_create_range_5(struct xarray *xa, unsigned long index, unsigned int order) { - struct xarray *xa = xa_param(test); - XA_STATE_ORDER(xas, xa, index, order); unsigned int i; @@ -1829,46 +1751,44 @@ static noinline void check_create_range_5(struct kunit *test, xa_destroy(xa); } -static noinline void check_create_range(struct kunit *test) +static noinline void check_create_range(struct xarray *xa) { unsigned int order; unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 12 : 1; for (order = 0; order < max_order; order++) { - check_create_range_1(test, 0, order); - check_create_range_1(test, 1U << order, order); - check_create_range_1(test, 2U << order, order); - check_create_range_1(test, 3U << order, order); - check_create_range_1(test, 1U << 24, order); + check_create_range_1(xa, 0, order); + check_create_range_1(xa, 1U << order, order); + check_create_range_1(xa, 2U << order, order); + check_create_range_1(xa, 3U << order, order); + check_create_range_1(xa, 1U << 24, order); if (order < 10) - check_create_range_2(test, order); - - check_create_range_4(test, 0, order); - check_create_range_4(test, 1U << order, order); - check_create_range_4(test, 2U << order, order); - check_create_range_4(test, 3U << order, order); - check_create_range_4(test, 1U << 24, order); - - check_create_range_4(test, 1, order); - check_create_range_4(test, (1U << order) + 1, order); - check_create_range_4(test, (2U << order) + 1, order); - check_create_range_4(test, (2U << order) - 1, order); - check_create_range_4(test, (3U << order) + 1, order); - check_create_range_4(test, (3U << order) - 1, order); - check_create_range_4(test, (1U << 24) + 1, order); - - check_create_range_5(test, 0, order); - check_create_range_5(test, (1U << order), order); + check_create_range_2(xa, order); + + check_create_range_4(xa, 0, order); + check_create_range_4(xa, 1U << order, order); + check_create_range_4(xa, 2U << order, order); + check_create_range_4(xa, 3U << order, order); + check_create_range_4(xa, 1U << 24, order); + + check_create_range_4(xa, 1, order); + check_create_range_4(xa, (1U << order) + 1, order); + check_create_range_4(xa, (2U << order) + 1, order); + check_create_range_4(xa, (2U << order) - 1, order); + check_create_range_4(xa, (3U << order) + 1, order); + check_create_range_4(xa, (3U << order) - 1, order); + check_create_range_4(xa, (1U << 24) + 1, order); + + check_create_range_5(xa, 0, order); + check_create_range_5(xa, (1U << order), order); } - check_create_range_3(test); + check_create_range_3(); } -static noinline void __check_store_range(struct kunit *test, unsigned long first, +static noinline void __check_store_range(struct xarray *xa, unsigned long first, unsigned long last) { - struct xarray *xa = xa_param(test); - #ifdef CONFIG_XARRAY_MULTI xa_store_range(xa, first, last, xa_mk_index(first), GFP_KERNEL); @@ -1883,28 +1803,26 @@ static noinline void __check_store_range(struct kunit *test, unsigned long first XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_store_range(struct kunit *test) +static noinline void check_store_range(struct xarray *xa) { unsigned long i, j; for (i = 0; i < 128; i++) { for (j = i; j < 128; j++) { - __check_store_range(test, i, j); - __check_store_range(test, 128 + i, 128 + j); - __check_store_range(test, 4095 + i, 4095 + j); - __check_store_range(test, 4096 + i, 4096 + j); - __check_store_range(test, 123456 + i, 123456 + j); - __check_store_range(test, (1 << 24) + i, (1 << 24) + j); + __check_store_range(xa, i, j); + __check_store_range(xa, 128 + i, 128 + j); + __check_store_range(xa, 4095 + i, 4095 + j); + __check_store_range(xa, 4096 + i, 4096 + j); + __check_store_range(xa, 123456 + i, 123456 + j); + __check_store_range(xa, (1 << 24) + i, (1 << 24) + j); } } } #ifdef CONFIG_XARRAY_MULTI -static void check_split_1(struct kunit *test, unsigned long index, +static void check_split_1(struct xarray *xa, unsigned long index, unsigned int order, unsigned int new_order) { - struct xarray *xa = xa_param(test); - XA_STATE_ORDER(xas, xa, index, new_order); unsigned int i, found; void *entry; @@ -1940,30 +1858,26 @@ static void check_split_1(struct kunit *test, unsigned long index, xa_destroy(xa); } -static noinline void check_split(struct kunit *test) +static noinline void check_split(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned int order, new_order; XA_BUG_ON(xa, !xa_empty(xa)); for (order = 1; order < 2 * XA_CHUNK_SHIFT; order++) { for (new_order = 0; new_order < order; new_order++) { - check_split_1(test, 0, order, new_order); - check_split_1(test, 1UL << order, order, new_order); - check_split_1(test, 3UL << order, order, new_order); + check_split_1(xa, 0, order, new_order); + check_split_1(xa, 1UL << order, order, new_order); + check_split_1(xa, 3UL << order, order, new_order); } } } #else -static void check_split(struct kunit *test) { } +static void check_split(struct xarray *xa) { } #endif -static void check_align_1(struct kunit *test, char *name) +static void check_align_1(struct xarray *xa, char *name) { - struct xarray *xa = xa_param(test); - int i; unsigned int id; unsigned long index; @@ -1983,10 +1897,8 @@ static void check_align_1(struct kunit *test, char *name) * We should always be able to store without allocating memory after * reserving a slot. */ -static void check_align_2(struct kunit *test, char *name) +static void check_align_2(struct xarray *xa, char *name) { - struct xarray *xa = xa_param(test); - int i; XA_BUG_ON(xa, !xa_empty(xa)); @@ -2005,15 +1917,15 @@ static void check_align_2(struct kunit *test, char *name) XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_align(struct kunit *test) +static noinline void check_align(struct xarray *xa) { char name[] = "Motorola 68000"; - check_align_1(test, name); - check_align_1(test, name + 1); - check_align_1(test, name + 2); - check_align_1(test, name + 3); - check_align_2(test, name); + check_align_1(xa, name); + check_align_1(xa, name + 1); + check_align_1(xa, name + 2); + check_align_1(xa, name + 3); + check_align_2(xa, name); } static LIST_HEAD(shadow_nodes); @@ -2029,7 +1941,7 @@ static void test_update_node(struct xa_node *node) } } -static noinline void shadow_remove(struct kunit *test, struct xarray *xa) +static noinline void shadow_remove(struct xarray *xa) { struct xa_node *node; @@ -2043,17 +1955,8 @@ static noinline void shadow_remove(struct kunit *test, struct xarray *xa) xa_unlock(xa); } -struct workingset_testcase { - struct xarray *xa; - unsigned long index; -}; - -static noinline void check_workingset(struct kunit *test) +static noinline void check_workingset(struct xarray *xa, unsigned long index) { - struct workingset_testcase tc = *(struct workingset_testcase *)test->param_value; - struct xarray *xa = tc.xa; - unsigned long index = tc.index; - XA_STATE(xas, xa, index); xas_set_update(&xas, test_update_node); @@ -2076,7 +1979,7 @@ static noinline void check_workingset(struct kunit *test) xas_unlock(&xas); XA_BUG_ON(xa, list_empty(&shadow_nodes)); - shadow_remove(test, xa); + shadow_remove(xa); XA_BUG_ON(xa, !list_empty(&shadow_nodes)); XA_BUG_ON(xa, !xa_empty(xa)); } @@ -2085,11 +1988,9 @@ static noinline void check_workingset(struct kunit *test) * Check that the pointer / value / sibling entries are accounted the * way we expect them to be. */ -static noinline void check_account(struct kunit *test) +static noinline void check_account(struct xarray *xa) { #ifdef CONFIG_XARRAY_MULTI - struct xarray *xa = xa_param(test); - unsigned int order; for (order = 1; order < 12; order++) { @@ -2116,10 +2017,8 @@ static noinline void check_account(struct kunit *test) #endif } -static noinline void check_get_order(struct kunit *test) +static noinline void check_get_order(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; unsigned int order; unsigned long i, j; @@ -2138,10 +2037,8 @@ static noinline void check_get_order(struct kunit *test) } } -static noinline void check_xas_get_order(struct kunit *test) +static noinline void check_xas_get_order(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); unsigned int max_order = IS_ENABLED(CONFIG_XARRAY_MULTI) ? 20 : 1; @@ -2173,10 +2070,8 @@ static noinline void check_xas_get_order(struct kunit *test) } } -static noinline void check_xas_conflict_get_order(struct kunit *test) +static noinline void check_xas_conflict_get_order(struct xarray *xa) { - struct xarray *xa = xa_param(test); - XA_STATE(xas, xa, 0); void *entry; @@ -2233,10 +2128,8 @@ static noinline void check_xas_conflict_get_order(struct kunit *test) } -static noinline void check_destroy(struct kunit *test) +static noinline void check_destroy(struct xarray *xa) { - struct xarray *xa = xa_param(test); - unsigned long index; XA_BUG_ON(xa, !xa_empty(xa)); @@ -2269,59 +2162,52 @@ static noinline void check_destroy(struct kunit *test) } static DEFINE_XARRAY(array); -static struct xarray *arrays[] = { &array }; -KUNIT_ARRAY_PARAM(array, arrays, NULL); - -static struct xarray *xa0s[] = { &xa0 }; -KUNIT_ARRAY_PARAM(xa0, xa0s, NULL); - -static struct workingset_testcase workingset_testcases[] = { - { &array, 0 }, - { &array, 64 }, - { &array, 4096 }, -}; -KUNIT_ARRAY_PARAM(workingset, workingset_testcases, NULL); - -static struct kunit_case xarray_cases[] = { - KUNIT_CASE_PARAM(check_xa_err, array_gen_params), - KUNIT_CASE_PARAM(check_xas_retry, array_gen_params), - KUNIT_CASE_PARAM(check_xa_load, array_gen_params), - KUNIT_CASE_PARAM(check_xa_mark, array_gen_params), - KUNIT_CASE_PARAM(check_xa_shrink, array_gen_params), - KUNIT_CASE_PARAM(check_xas_erase, array_gen_params), - KUNIT_CASE_PARAM(check_insert, array_gen_params), - KUNIT_CASE_PARAM(check_cmpxchg, array_gen_params), - KUNIT_CASE_PARAM(check_cmpxchg_order, array_gen_params), - KUNIT_CASE_PARAM(check_reserve, array_gen_params), - KUNIT_CASE_PARAM(check_reserve, xa0_gen_params), - KUNIT_CASE_PARAM(check_multi_store, array_gen_params), - KUNIT_CASE_PARAM(check_multi_store_advanced, array_gen_params), - KUNIT_CASE_PARAM(check_get_order, array_gen_params), - KUNIT_CASE_PARAM(check_xas_get_order, array_gen_params), - KUNIT_CASE_PARAM(check_xas_conflict_get_order, array_gen_params), - KUNIT_CASE(check_xa_alloc), - KUNIT_CASE_PARAM(check_find, array_gen_params), - KUNIT_CASE_PARAM(check_find_entry, array_gen_params), - KUNIT_CASE_PARAM(check_pause, array_gen_params), - KUNIT_CASE_PARAM(check_account, array_gen_params), - KUNIT_CASE_PARAM(check_destroy, array_gen_params), - KUNIT_CASE_PARAM(check_move, array_gen_params), - KUNIT_CASE_PARAM(check_create_range, array_gen_params), - KUNIT_CASE_PARAM(check_store_range, array_gen_params), - KUNIT_CASE_PARAM(check_store_iter, array_gen_params), - KUNIT_CASE_PARAM(check_align, xa0_gen_params), - KUNIT_CASE_PARAM(check_split, array_gen_params), - KUNIT_CASE_PARAM(check_workingset, workingset_gen_params), - {}, -}; - -static struct kunit_suite xarray_suite = { - .name = "xarray", - .test_cases = xarray_cases, -}; - -kunit_test_suite(xarray_suite); +static int xarray_checks(void) +{ + check_xa_err(&array); + check_xas_retry(&array); + check_xa_load(&array); + check_xa_mark(&array); + check_xa_shrink(&array); + check_xas_erase(&array); + check_insert(&array); + check_cmpxchg(&array); + check_cmpxchg_order(&array); + check_reserve(&array); + check_reserve(&xa0); + check_multi_store(&array); + check_multi_store_advanced(&array); + check_get_order(&array); + check_xas_get_order(&array); + check_xas_conflict_get_order(&array); + check_xa_alloc(); + check_find(&array); + check_find_entry(&array); + check_pause(&array); + check_account(&array); + check_destroy(&array); + check_move(&array); + check_create_range(&array); + check_store_range(&array); + check_store_iter(&array); + check_align(&xa0); + check_split(&array); + + check_workingset(&array, 0); + check_workingset(&array, 64); + check_workingset(&array, 4096); + + printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); + return (tests_run == tests_passed) ? 0 : -EINVAL; +} + +static void xarray_exit(void) +{ +} + +module_init(xarray_checks); +module_exit(xarray_exit); MODULE_AUTHOR("Matthew Wilcox <willy@infradead.org>"); MODULE_DESCRIPTION("XArray API test module"); MODULE_LICENSE("GPL"); diff --git a/mm/compaction.c b/mm/compaction.c index 73e80b2fb22e..12ed8425fa17 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2491,7 +2491,8 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, */ static enum compact_result compaction_suit_allocation_order(struct zone *zone, unsigned int order, - int highest_zoneidx, unsigned int alloc_flags) + int highest_zoneidx, unsigned int alloc_flags, + bool async) { unsigned long watermark; @@ -2500,6 +2501,23 @@ compaction_suit_allocation_order(struct zone *zone, unsigned int order, alloc_flags)) return COMPACT_SUCCESS; + /* + * For unmovable allocations (without ALLOC_CMA), check if there is enough + * free memory in the non-CMA pageblocks. Otherwise compaction could form + * the high-order page in CMA pageblocks, which would not help the + * allocation to succeed. However, limit the check to costly order async + * compaction (such as opportunistic THP attempts) because there is the + * possibility that compaction would migrate pages from non-CMA to CMA + * pageblock. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER && async && + !(alloc_flags & ALLOC_CMA)) { + watermark = low_wmark_pages(zone) + compact_gap(order); + if (!__zone_watermark_ok(zone, 0, watermark, highest_zoneidx, + 0, zone_page_state(zone, NR_FREE_PAGES))) + return COMPACT_SKIPPED; + } + if (!compaction_suitable(zone, order, highest_zoneidx)) return COMPACT_SKIPPED; @@ -2535,7 +2553,8 @@ compact_zone(struct compact_control *cc, struct capture_control *capc) if (!is_via_compact_memory(cc->order)) { ret = compaction_suit_allocation_order(cc->zone, cc->order, cc->highest_zoneidx, - cc->alloc_flags); + cc->alloc_flags, + cc->mode == MIGRATE_ASYNC); if (ret != COMPACT_CONTINUE) return ret; } @@ -3038,7 +3057,8 @@ static bool kcompactd_node_suitable(pg_data_t *pgdat) ret = compaction_suit_allocation_order(zone, pgdat->kcompactd_max_order, - highest_zoneidx, ALLOC_WMARK_MIN); + highest_zoneidx, ALLOC_WMARK_MIN, + false); if (ret == COMPACT_CONTINUE) return true; } @@ -3079,7 +3099,8 @@ static void kcompactd_do_work(pg_data_t *pgdat) continue; ret = compaction_suit_allocation_order(zone, - cc.order, zoneid, ALLOC_WMARK_MIN); + cc.order, zoneid, ALLOC_WMARK_MIN, + false); if (ret != COMPACT_CONTINUE) continue; @@ -3272,7 +3293,7 @@ static int proc_dointvec_minmax_warn_RT_change(const struct ctl_table *table, return ret; } -static struct ctl_table vm_compaction[] = { +static const struct ctl_table vm_compaction[] = { { .procname = "compact_memory", .data = &sysctl_compact_memory, @@ -2320,13 +2320,13 @@ static void pofs_unpin(struct pages_or_folios *pofs) /* * Returns the number of collected folios. Return value is always >= 0. */ -static unsigned long collect_longterm_unpinnable_folios( +static void collect_longterm_unpinnable_folios( struct list_head *movable_folio_list, struct pages_or_folios *pofs) { - unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; + unsigned long i; for (i = 0; i < pofs->nr_entries; i++) { struct folio *folio = pofs_get_folio(pofs, i); @@ -2338,8 +2338,6 @@ static unsigned long collect_longterm_unpinnable_folios( if (folio_is_longterm_pinnable(folio)) continue; - collected++; - if (folio_is_device_coherent(folio)) continue; @@ -2361,8 +2359,6 @@ static unsigned long collect_longterm_unpinnable_folios( NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } - - return collected; } /* @@ -2439,11 +2435,9 @@ static long check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs) { LIST_HEAD(movable_folio_list); - unsigned long collected; - collected = collect_longterm_unpinnable_folios(&movable_folio_list, - pofs); - if (!collected) + collect_longterm_unpinnable_folios(&movable_folio_list, pofs); + if (list_empty(&movable_folio_list)) return 0; return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 87761b042ed0..163190e89ea1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3145,7 +3145,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid) /* do node specific alloc */ if (nid != NUMA_NO_NODE) { - m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + m = memblock_alloc_exact_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!m) return 0; @@ -3309,7 +3309,7 @@ static void __init gather_bootmem_prealloc(void) .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, - .size = num_node_state(N_MEMORY), + .size = nr_node_ids, .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), @@ -4867,7 +4867,7 @@ out: return ret; } -static struct ctl_table hugetlb_table[] = { +static const struct ctl_table hugetlb_table[] = { { .procname = "nr_hugepages", .data = NULL, diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 57b7f591eee8..7735972add01 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -693,7 +693,7 @@ void hugetlb_vmemmap_optimize_folios(struct hstate *h, struct list_head *folio_l free_vmemmap_page_list(&vmemmap_pages); } -static struct ctl_table hugetlb_vmemmap_sysctls[] = { +static const struct ctl_table hugetlb_vmemmap_sysctls[] = { { .procname = "hugetlb_optimize_vmemmap", .data = &vmemmap_optimize_enabled, diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 3fe77a360f1c..8357e1a33699 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -370,6 +370,36 @@ static inline bool init_task_stack_addr(const void *addr) sizeof(init_thread_union.stack)); } +/* + * This function is invoked with report_lock (a raw_spinlock) held. A + * PREEMPT_RT kernel cannot call find_vm_area() as it will acquire a sleeping + * rt_spinlock. + * + * For !RT kernel, the PROVE_RAW_LOCK_NESTING config option will print a + * lockdep warning for this raw_spinlock -> spinlock dependency. This config + * option is enabled by default to ensure better test coverage to expose this + * kind of RT kernel problem. This lockdep splat, however, can be suppressed + * by using DEFINE_WAIT_OVERRIDE_MAP() if it serves a useful purpose and the + * invalid PREEMPT_RT case has been taken care of. + */ +static inline struct vm_struct *kasan_find_vm_area(void *addr) +{ + static DEFINE_WAIT_OVERRIDE_MAP(vmalloc_map, LD_WAIT_SLEEP); + struct vm_struct *va; + + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + return NULL; + + /* + * Suppress lockdep warning and fetch vmalloc area of the + * offending address. + */ + lock_map_acquire_try(&vmalloc_map); + va = find_vm_area(addr); + lock_map_release(&vmalloc_map); + return va; +} + static void print_address_description(void *addr, u8 tag, struct kasan_report_info *info) { @@ -399,7 +429,7 @@ static void print_address_description(void *addr, u8 tag, } if (is_vmalloc_addr(addr)) { - struct vm_struct *va = find_vm_area(addr); + struct vm_struct *va = kasan_find_vm_area(addr); if (va) { pr_err("The buggy address belongs to the virtual mapping at\n" @@ -409,6 +439,8 @@ static void print_address_description(void *addr, u8 tag, pr_err("\n"); page = vmalloc_to_page(addr); + } else { + pr_err("The buggy address %px belongs to a vmalloc virtual mapping\n", addr); } } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 67fc321db79b..102048821c22 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -21,6 +21,7 @@ #include <linux/log2.h> #include <linux/memblock.h> #include <linux/moduleparam.h> +#include <linux/nodemask.h> #include <linux/notifier.h> #include <linux/panic_notifier.h> #include <linux/random.h> @@ -1084,6 +1085,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) * properties (e.g. reside in DMAable memory). */ if ((flags & GFP_ZONEMASK) || + ((flags & __GFP_THISNODE) && num_online_nodes() > 1) || (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32))) { atomic_long_inc(&counters[KFENCE_COUNTER_SKIP_INCOMPAT]); return NULL; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 982bb5ef3233..c6ed68604136 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1689,7 +1689,7 @@ static void kmemleak_scan(void) unsigned long phys = object->pointer; if (PHYS_PFN(phys) < min_low_pfn || - PHYS_PFN(phys + object->size) >= max_low_pfn) + PHYS_PFN(phys + object->size) > max_low_pfn) __paint_it(object, KMEMLEAK_BLACK); } diff --git a/mm/madvise.c b/mm/madvise.c index 49f3a75046f6..08b207f8e61e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -933,7 +933,16 @@ static long madvise_dontneed_free(struct vm_area_struct *vma, */ end = vma->vm_end; } - VM_WARN_ON(start >= end); + /* + * If the memory region between start and end was + * originally backed by 4kB pages and then remapped to + * be backed by hugepages while mmap_lock was dropped, + * the adjustment for hugetlb vma above may have rounded + * end down to the start address. + */ + if (start == end) + return 0; + VM_WARN_ON(start > end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 46f8b372d212..4de6acb9b8ec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4166,6 +4166,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, memcg_memory_event(memcg, MEMCG_OOM); if (!mem_cgroup_out_of_memory(memcg, GFP_KERNEL, 0)) break; + cond_resched(); } memcg_wb_domain_size_changed(memcg); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index a7b8ccd29b6f..995a15eb67e2 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -124,7 +124,7 @@ const struct attribute_group memory_failure_attr_group = { .attrs = memory_failure_attr, }; -static struct ctl_table memory_failure_table[] = { +static const struct ctl_table memory_failure_table[] = { { .procname = "memory_failure_early_kill", .data = &sysctl_memory_failure_early_kill, diff --git a/mm/memory.c b/mm/memory.c index 539c0f7c6d54..b4d3d4893267 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1719,7 +1719,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, pmd_t pmdval; unsigned long start = addr; bool can_reclaim_pt = reclaim_pt_is_enabled(start, end, details); - bool direct_reclaim = false; + bool direct_reclaim = true; int nr; retry: @@ -1734,8 +1734,10 @@ retry: do { bool any_skipped = false; - if (need_resched()) + if (need_resched()) { + direct_reclaim = false; break; + } nr = do_zap_pte_range(tlb, vma, pte, addr, end, details, rss, &force_flush, &force_break, &any_skipped); @@ -1743,11 +1745,20 @@ retry: can_reclaim_pt = false; if (unlikely(force_break)) { addr += nr * PAGE_SIZE; + direct_reclaim = false; break; } } while (pte += nr, addr += PAGE_SIZE * nr, addr != end); - if (can_reclaim_pt && addr == end) + /* + * Fast path: try to hold the pmd lock and unmap the PTE page. + * + * If the pte lock was released midway (retry case), or if the attempt + * to hold the pmd lock failed, then we need to recheck all pte entries + * to ensure they are still none, thereby preventing the pte entries + * from being repopulated by another thread. + */ + if (can_reclaim_pt && direct_reclaim && addr == end) direct_reclaim = try_get_and_clear_pmd(mm, pmd, &pmdval); add_mm_rss_vec(mm, rss); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index 9cf26592ac93..5bd888223cc8 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -840,20 +840,15 @@ void migrate_device_finalize(unsigned long *src_pfns, dst = src; } + if (!folio_is_zone_device(dst)) + folio_add_lru(dst); remove_migration_ptes(src, dst, 0); folio_unlock(src); - - if (folio_is_zone_device(src)) - folio_put(src); - else - folio_putback_lru(src); + folio_put(src); if (dst != src) { folio_unlock(dst); - if (folio_is_zone_device(dst)) - folio_put(dst); - else - folio_putback_lru(dst); + folio_put(dst); } } } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 044ebab2c941..1cf121ad7085 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -705,7 +705,7 @@ static void queue_oom_reaper(struct task_struct *tsk) } #ifdef CONFIG_SYSCTL -static struct ctl_table vm_oom_kill_table[] = { +static const struct ctl_table vm_oom_kill_table[] = { { .procname = "panic_on_oom", .data = &sysctl_panic_on_oom, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4f5970723cf2..eb55ece39c56 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2298,7 +2298,7 @@ static int page_writeback_cpu_online(unsigned int cpu) /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; -static struct ctl_table vm_page_writeback_sysctls[] = { +static const struct ctl_table vm_page_writeback_sysctls[] = { { .procname = "dirty_background_ratio", .data = &dirty_background_ratio, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e469c7ef9a4..579789600a3c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6166,7 +6166,7 @@ out: return ret; } -static struct ctl_table page_alloc_sysctl_table[] = { +static const struct ctl_table page_alloc_sysctl_table[] = { { .procname = "min_free_kbytes", .data = &min_free_kbytes, diff --git a/mm/secretmem.c b/mm/secretmem.c index 399552814fd0..1b0a214ee558 100644 --- a/mm/secretmem.c +++ b/mm/secretmem.c @@ -195,14 +195,13 @@ static struct file *secretmem_file_create(unsigned long flags) struct file *file; struct inode *inode; const char *anon_name = "[secretmem]"; - const struct qstr qname = QSTR_INIT(anon_name, strlen(anon_name)); int err; inode = alloc_anon_inode(secretmem_mnt->mnt_sb); if (IS_ERR(inode)) return ERR_CAST(inode); - err = security_inode_init_security_anon(inode, &qname, NULL); + err = security_inode_init_security_anon(inode, &QSTR(anon_name), NULL); if (err) { file = ERR_PTR(err); goto err_free_inode; diff --git a/mm/swapfile.c b/mm/swapfile.c index 6e867c16ea93..ba19430dd4ea 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -794,7 +794,7 @@ static unsigned int alloc_swap_scan_cluster(struct swap_info_struct *si, if (!cluster_scan_range(si, ci, offset, nr_pages, &need_reclaim)) continue; if (need_reclaim) { - ret = cluster_reclaim_range(si, ci, start, end); + ret = cluster_reclaim_range(si, ci, offset, offset + nr_pages); /* * Reclaim drops ci->lock and cluster could be used * by another order. Not checking flag as off-list diff --git a/mm/vmscan.c b/mm/vmscan.c index 683ec56d4f60..c767d71c43d7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1086,7 +1086,7 @@ static unsigned int shrink_folio_list(struct list_head *folio_list, struct folio_batch free_folios; LIST_HEAD(ret_folios); LIST_HEAD(demote_folios); - unsigned int nr_reclaimed = 0; + unsigned int nr_reclaimed = 0, nr_demoted = 0; unsigned int pgactivate = 0; bool do_demote_pass; struct swap_iocb *plug = NULL; @@ -1550,8 +1550,9 @@ keep: /* 'folio_list' is always empty here */ /* Migrate folios selected for demotion */ - stat->nr_demoted = demote_folio_list(&demote_folios, pgdat); - nr_reclaimed += stat->nr_demoted; + nr_demoted = demote_folio_list(&demote_folios, pgdat); + nr_reclaimed += nr_demoted; + stat->nr_demoted += nr_demoted; /* Folios that could not be demoted are still in @demote_folios */ if (!list_empty(&demote_folios)) { /* Folios which weren't demoted go back on @folio_list */ @@ -1692,6 +1693,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, unsigned long nr_skipped[MAX_NR_ZONES] = { 0, }; unsigned long skipped = 0; unsigned long scan, total_scan, nr_pages; + unsigned long max_nr_skipped = 0; LIST_HEAD(folios_skipped); total_scan = 0; @@ -1706,9 +1708,12 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan, nr_pages = folio_nr_pages(folio); total_scan += nr_pages; - if (folio_zonenum(folio) > sc->reclaim_idx) { + /* Using max_nr_skipped to prevent hard LOCKUP*/ + if (max_nr_skipped < SWAP_CLUSTER_MAX_SKIPPED && + (folio_zonenum(folio) > sc->reclaim_idx)) { nr_skipped[folio_zonenum(folio)] += nr_pages; move_to = &folios_skipped; + max_nr_skipped++; goto move; } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 817626a351f8..6d0e47f7ae33 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -452,7 +452,7 @@ static DEFINE_PER_CPU(struct mapping_area, zs_map_area) = { .lock = INIT_LOCAL_LOCK(lock), }; -static inline bool is_first_zpdesc(struct zpdesc *zpdesc) +static inline bool __maybe_unused is_first_zpdesc(struct zpdesc *zpdesc) { return PagePrivate(zpdesc_page(zpdesc)); } diff --git a/mm/zswap.c b/mm/zswap.c index 6504174fbc6a..ac9d299e7d0c 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1445,9 +1445,9 @@ resched: * main API **********************************/ -static ssize_t zswap_store_page(struct page *page, - struct obj_cgroup *objcg, - struct zswap_pool *pool) +static bool zswap_store_page(struct page *page, + struct obj_cgroup *objcg, + struct zswap_pool *pool) { swp_entry_t page_swpentry = page_swap_entry(page); struct zswap_entry *entry, *old; @@ -1456,7 +1456,7 @@ static ssize_t zswap_store_page(struct page *page, entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page)); if (!entry) { zswap_reject_kmemcache_fail++; - return -EINVAL; + return false; } if (!zswap_compress(page, entry, pool)) @@ -1483,13 +1483,17 @@ static ssize_t zswap_store_page(struct page *page, /* * The entry is successfully compressed and stored in the tree, there is - * no further possibility of failure. Grab refs to the pool and objcg. - * These refs will be dropped by zswap_entry_free() when the entry is - * removed from the tree. + * no further possibility of failure. Grab refs to the pool and objcg, + * charge zswap memory, and increment zswap_stored_pages. + * The opposite actions will be performed by zswap_entry_free() + * when the entry is removed from the tree. */ zswap_pool_get(pool); - if (objcg) + if (objcg) { obj_cgroup_get(objcg); + obj_cgroup_charge_zswap(objcg, entry->length); + } + atomic_long_inc(&zswap_stored_pages); /* * We finish initializing the entry while it's already in xarray. @@ -1510,13 +1514,13 @@ static ssize_t zswap_store_page(struct page *page, zswap_lru_add(&zswap_list_lru, entry); } - return entry->length; + return true; store_failed: zpool_free(pool->zpool, entry->handle); compress_failed: zswap_entry_cache_free(entry); - return -EINVAL; + return false; } bool zswap_store(struct folio *folio) @@ -1526,7 +1530,6 @@ bool zswap_store(struct folio *folio) struct obj_cgroup *objcg = NULL; struct mem_cgroup *memcg = NULL; struct zswap_pool *pool; - size_t compressed_bytes = 0; bool ret = false; long index; @@ -1564,20 +1567,14 @@ bool zswap_store(struct folio *folio) for (index = 0; index < nr_pages; ++index) { struct page *page = folio_page(folio, index); - ssize_t bytes; - bytes = zswap_store_page(page, objcg, pool); - if (bytes < 0) + if (!zswap_store_page(page, objcg, pool)) goto put_pool; - compressed_bytes += bytes; } - if (objcg) { - obj_cgroup_charge_zswap(objcg, compressed_bytes); + if (objcg) count_objcg_events(objcg, ZSWPOUT, nr_pages); - } - atomic_long_add(nr_pages, &zswap_stored_pages); count_vm_events(ZSWPOUT, nr_pages); ret = true; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index aa6c714892ec..9f3b8b682adb 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -685,6 +685,15 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, break; } + if (ax25->ax25_dev) { + if (dev == ax25->ax25_dev->dev) { + rcu_read_unlock(); + break; + } + netdev_put(ax25->ax25_dev->dev, &ax25->dev_tracker); + ax25_dev_put(ax25->ax25_dev); + } + ax25->ax25_dev = ax25_dev_ax25dev(dev); if (!ax25->ax25_dev) { rcu_read_unlock(); @@ -692,6 +701,8 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, break; } ax25_fillin_cb(ax25, ax25->ax25_dev); + netdev_hold(dev, &ax25->dev_tracker, GFP_ATOMIC); + ax25_dev_hold(ax25->ax25_dev); rcu_read_unlock(); break; diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index ac11f1f08db0..d35479c465e2 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -113,8 +113,6 @@ static void batadv_v_hardif_neigh_init(struct batadv_hardif_neigh_node *hardif_neigh) { ewma_throughput_init(&hardif_neigh->bat_v.throughput); - INIT_WORK(&hardif_neigh->bat_v.metric_work, - batadv_v_elp_throughput_metric_update); } /** diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 1d704574e6bf..b065578b4436 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -18,6 +18,7 @@ #include <linux/if_ether.h> #include <linux/jiffies.h> #include <linux/kref.h> +#include <linux/list.h> #include <linux/minmax.h> #include <linux/netdevice.h> #include <linux/nl80211.h> @@ -26,6 +27,7 @@ #include <linux/rcupdate.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> @@ -42,6 +44,18 @@ #include "send.h" /** + * struct batadv_v_metric_queue_entry - list of hardif neighbors which require + * and metric update + */ +struct batadv_v_metric_queue_entry { + /** @hardif_neigh: hardif neighbor scheduled for metric update */ + struct batadv_hardif_neigh_node *hardif_neigh; + + /** @list: list node for metric_queue */ + struct list_head list; +}; + +/** * batadv_v_elp_start_timer() - restart timer for ELP periodic work * @hard_iface: the interface for which the timer has to be reset */ @@ -59,25 +73,36 @@ static void batadv_v_elp_start_timer(struct batadv_hard_iface *hard_iface) /** * batadv_v_elp_get_throughput() - get the throughput towards a neighbour * @neigh: the neighbour for which the throughput has to be obtained + * @pthroughput: calculated throughput towards the given neighbour in multiples + * of 100kpbs (a value of '1' equals 0.1Mbps, '10' equals 1Mbps, etc). * - * Return: The throughput towards the given neighbour in multiples of 100kpbs - * (a value of '1' equals 0.1Mbps, '10' equals 1Mbps, etc). + * Return: true when value behind @pthroughput was set */ -static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) +static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, + u32 *pthroughput) { struct batadv_hard_iface *hard_iface = neigh->if_incoming; + struct net_device *soft_iface = hard_iface->soft_iface; struct ethtool_link_ksettings link_settings; struct net_device *real_netdev; struct station_info sinfo; u32 throughput; int ret; + /* don't query throughput when no longer associated with any + * batman-adv interface + */ + if (!soft_iface) + return false; + /* if the user specified a customised value for this interface, then * return it directly */ throughput = atomic_read(&hard_iface->bat_v.throughput_override); - if (throughput != 0) - return throughput; + if (throughput != 0) { + *pthroughput = throughput; + return true; + } /* if this is a wireless device, then ask its throughput through * cfg80211 API @@ -104,27 +129,39 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) * possible to delete this neighbor. For now set * the throughput metric to 0. */ - return 0; + *pthroughput = 0; + return true; } if (ret) goto default_throughput; - if (sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT)) - return sinfo.expected_throughput / 100; + if (sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT)) { + *pthroughput = sinfo.expected_throughput / 100; + return true; + } /* try to estimate the expected throughput based on reported tx * rates */ - if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) - return cfg80211_calculate_bitrate(&sinfo.txrate) / 3; + if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) { + *pthroughput = cfg80211_calculate_bitrate(&sinfo.txrate) / 3; + return true; + } goto default_throughput; } + /* only use rtnl_trylock because the elp worker will be cancelled while + * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise + * wait forever when the elp work_item was started and it is then also + * trying to rtnl_lock + */ + if (!rtnl_trylock()) + return false; + /* if not a wifi interface, check if this device provides data via * ethtool (e.g. an Ethernet adapter) */ - rtnl_lock(); ret = __ethtool_get_link_ksettings(hard_iface->net_dev, &link_settings); rtnl_unlock(); if (ret == 0) { @@ -135,13 +172,15 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) hard_iface->bat_v.flags &= ~BATADV_FULL_DUPLEX; throughput = link_settings.base.speed; - if (throughput && throughput != SPEED_UNKNOWN) - return throughput * 10; + if (throughput && throughput != SPEED_UNKNOWN) { + *pthroughput = throughput * 10; + return true; + } } default_throughput: if (!(hard_iface->bat_v.flags & BATADV_WARNING_DEFAULT)) { - batadv_info(hard_iface->soft_iface, + batadv_info(soft_iface, "WiFi driver or ethtool info does not provide information about link speeds on interface %s, therefore defaulting to hardcoded throughput values of %u.%1u Mbps. Consider overriding the throughput manually or checking your driver.\n", hard_iface->net_dev->name, BATADV_THROUGHPUT_DEFAULT_VALUE / 10, @@ -150,31 +189,26 @@ default_throughput: } /* if none of the above cases apply, return the base_throughput */ - return BATADV_THROUGHPUT_DEFAULT_VALUE; + *pthroughput = BATADV_THROUGHPUT_DEFAULT_VALUE; + return true; } /** * batadv_v_elp_throughput_metric_update() - worker updating the throughput * metric of a single hop neighbour - * @work: the work queue item + * @neigh: the neighbour to probe */ -void batadv_v_elp_throughput_metric_update(struct work_struct *work) +static void +batadv_v_elp_throughput_metric_update(struct batadv_hardif_neigh_node *neigh) { - struct batadv_hardif_neigh_node_bat_v *neigh_bat_v; - struct batadv_hardif_neigh_node *neigh; - - neigh_bat_v = container_of(work, struct batadv_hardif_neigh_node_bat_v, - metric_work); - neigh = container_of(neigh_bat_v, struct batadv_hardif_neigh_node, - bat_v); + u32 throughput; + bool valid; - ewma_throughput_add(&neigh->bat_v.throughput, - batadv_v_elp_get_throughput(neigh)); + valid = batadv_v_elp_get_throughput(neigh, &throughput); + if (!valid) + return; - /* decrement refcounter to balance increment performed before scheduling - * this task - */ - batadv_hardif_neigh_put(neigh); + ewma_throughput_add(&neigh->bat_v.throughput, throughput); } /** @@ -248,14 +282,16 @@ batadv_v_elp_wifi_neigh_probe(struct batadv_hardif_neigh_node *neigh) */ static void batadv_v_elp_periodic_work(struct work_struct *work) { + struct batadv_v_metric_queue_entry *metric_entry; + struct batadv_v_metric_queue_entry *metric_safe; struct batadv_hardif_neigh_node *hardif_neigh; struct batadv_hard_iface *hard_iface; struct batadv_hard_iface_bat_v *bat_v; struct batadv_elp_packet *elp_packet; + struct list_head metric_queue; struct batadv_priv *bat_priv; struct sk_buff *skb; u32 elp_interval; - bool ret; bat_v = container_of(work, struct batadv_hard_iface_bat_v, elp_wq.work); hard_iface = container_of(bat_v, struct batadv_hard_iface, bat_v); @@ -291,6 +327,8 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) atomic_inc(&hard_iface->bat_v.elp_seqno); + INIT_LIST_HEAD(&metric_queue); + /* The throughput metric is updated on each sent packet. This way, if a * node is dead and no longer sends packets, batman-adv is still able to * react timely to its death. @@ -315,16 +353,28 @@ static void batadv_v_elp_periodic_work(struct work_struct *work) /* Reading the estimated throughput from cfg80211 is a task that * may sleep and that is not allowed in an rcu protected - * context. Therefore schedule a task for that. + * context. Therefore add it to metric_queue and process it + * outside rcu protected context. */ - ret = queue_work(batadv_event_workqueue, - &hardif_neigh->bat_v.metric_work); - - if (!ret) + metric_entry = kzalloc(sizeof(*metric_entry), GFP_ATOMIC); + if (!metric_entry) { batadv_hardif_neigh_put(hardif_neigh); + continue; + } + + metric_entry->hardif_neigh = hardif_neigh; + list_add(&metric_entry->list, &metric_queue); } rcu_read_unlock(); + list_for_each_entry_safe(metric_entry, metric_safe, &metric_queue, list) { + batadv_v_elp_throughput_metric_update(metric_entry->hardif_neigh); + + batadv_hardif_neigh_put(metric_entry->hardif_neigh); + list_del(&metric_entry->list); + kfree(metric_entry); + } + restart_timer: batadv_v_elp_start_timer(hard_iface); out: diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index 9e2740195fa2..c9cb0a307100 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -10,7 +10,6 @@ #include "main.h" #include <linux/skbuff.h> -#include <linux/workqueue.h> int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface); void batadv_v_elp_iface_disable(struct batadv_hard_iface *hard_iface); @@ -19,6 +18,5 @@ void batadv_v_elp_iface_activate(struct batadv_hard_iface *primary_iface, void batadv_v_elp_primary_iface_set(struct batadv_hard_iface *primary_iface); int batadv_v_elp_packet_recv(struct sk_buff *skb, struct batadv_hard_iface *if_incoming); -void batadv_v_elp_throughput_metric_update(struct work_struct *work); #endif /* _NET_BATMAN_ADV_BAT_V_ELP_H_ */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 3c0a14a582e4..d4b71d34310f 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -3937,23 +3937,21 @@ static void batadv_tt_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv, struct batadv_tvlv_tt_change *tt_change; struct batadv_tvlv_tt_data *tt_data; u16 num_entries, num_vlan; - size_t flex_size; + size_t tt_data_sz; if (tvlv_value_len < sizeof(*tt_data)) return; tt_data = tvlv_value; - tvlv_value_len -= sizeof(*tt_data); - num_vlan = ntohs(tt_data->num_vlan); - flex_size = flex_array_size(tt_data, vlan_data, num_vlan); - if (tvlv_value_len < flex_size) + tt_data_sz = struct_size(tt_data, vlan_data, num_vlan); + if (tvlv_value_len < tt_data_sz) return; tt_change = (struct batadv_tvlv_tt_change *)((void *)tt_data - + flex_size); - tvlv_value_len -= flex_size; + + tt_data_sz); + tvlv_value_len -= tt_data_sz; num_entries = batadv_tt_entries(tvlv_value_len); diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index f491bff8c51b..fe89f08533fe 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -596,9 +596,6 @@ struct batadv_hardif_neigh_node_bat_v { * neighbor */ unsigned long last_unicast_tx; - - /** @metric_work: work queue callback item for metric update */ - struct work_struct metric_work; }; /** diff --git a/net/bluetooth/hidp/Kconfig b/net/bluetooth/hidp/Kconfig index 6746be07e222..e08aae35351a 100644 --- a/net/bluetooth/hidp/Kconfig +++ b/net/bluetooth/hidp/Kconfig @@ -1,8 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config BT_HIDP tristate "HIDP protocol support" - depends on BT_BREDR && INPUT && HID_SUPPORT - select HID + depends on BT_BREDR && HID help HIDP (Human Interface Device Protocol) is a transport layer for HID reports. HIDP is required for the Bluetooth Human diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 27b4c4a2ba1f..fec11e576f31 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -119,7 +119,6 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, { struct l2cap_chan *c; - mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_scid(conn, cid); if (c) { /* Only lock if chan reference is not 0 */ @@ -127,7 +126,6 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, if (c) l2cap_chan_lock(c); } - mutex_unlock(&conn->chan_lock); return c; } @@ -140,7 +138,6 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, { struct l2cap_chan *c; - mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_dcid(conn, cid); if (c) { /* Only lock if chan reference is not 0 */ @@ -148,7 +145,6 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, if (c) l2cap_chan_lock(c); } - mutex_unlock(&conn->chan_lock); return c; } @@ -418,7 +414,7 @@ static void l2cap_chan_timeout(struct work_struct *work) if (!conn) return; - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); /* __set_chan_timer() calls l2cap_chan_hold(chan) while scheduling * this work. No need to call l2cap_chan_hold(chan) here again. */ @@ -439,7 +435,7 @@ static void l2cap_chan_timeout(struct work_struct *work) l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); } struct l2cap_chan *l2cap_chan_create(void) @@ -641,9 +637,9 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) { - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); __l2cap_chan_add(conn, chan); - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); } void l2cap_chan_del(struct l2cap_chan *chan, int err) @@ -731,9 +727,9 @@ void l2cap_chan_list(struct l2cap_conn *conn, l2cap_chan_func_t func, if (!conn) return; - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); __l2cap_chan_list(conn, func, data); - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); } EXPORT_SYMBOL_GPL(l2cap_chan_list); @@ -745,7 +741,7 @@ static void l2cap_conn_update_id_addr(struct work_struct *work) struct hci_conn *hcon = conn->hcon; struct l2cap_chan *chan; - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); list_for_each_entry(chan, &conn->chan_l, list) { l2cap_chan_lock(chan); @@ -754,7 +750,7 @@ static void l2cap_conn_update_id_addr(struct work_struct *work) l2cap_chan_unlock(chan); } - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); } static void l2cap_chan_le_connect_reject(struct l2cap_chan *chan) @@ -948,6 +944,16 @@ static u8 l2cap_get_ident(struct l2cap_conn *conn) return id; } +static void l2cap_send_acl(struct l2cap_conn *conn, struct sk_buff *skb, + u8 flags) +{ + /* Check if the hcon still valid before attempting to send */ + if (hci_conn_valid(conn->hcon->hdev, conn->hcon)) + hci_send_acl(conn->hchan, skb, flags); + else + kfree_skb(skb); +} + static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data) { @@ -970,7 +976,7 @@ static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, bt_cb(skb)->force_active = BT_POWER_FORCE_ACTIVE_ON; skb->priority = HCI_PRIO_MAX; - hci_send_acl(conn->hchan, skb, flags); + l2cap_send_acl(conn, skb, flags); } static void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) @@ -1497,8 +1503,6 @@ static void l2cap_conn_start(struct l2cap_conn *conn) BT_DBG("conn %p", conn); - mutex_lock(&conn->chan_lock); - list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { l2cap_chan_lock(chan); @@ -1567,8 +1571,6 @@ static void l2cap_conn_start(struct l2cap_conn *conn) l2cap_chan_unlock(chan); } - - mutex_unlock(&conn->chan_lock); } static void l2cap_le_conn_ready(struct l2cap_conn *conn) @@ -1614,7 +1616,7 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) if (hcon->type == ACL_LINK) l2cap_request_info(conn); - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); list_for_each_entry(chan, &conn->chan_l, list) { @@ -1632,7 +1634,7 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) l2cap_chan_unlock(chan); } - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); if (hcon->type == LE_LINK) l2cap_le_conn_ready(conn); @@ -1647,14 +1649,10 @@ static void l2cap_conn_unreliable(struct l2cap_conn *conn, int err) BT_DBG("conn %p", conn); - mutex_lock(&conn->chan_lock); - list_for_each_entry(chan, &conn->chan_l, list) { if (test_bit(FLAG_FORCE_RELIABLE, &chan->flags)) l2cap_chan_set_err(chan, err); } - - mutex_unlock(&conn->chan_lock); } static void l2cap_info_timeout(struct work_struct *work) @@ -1665,7 +1663,9 @@ static void l2cap_info_timeout(struct work_struct *work) conn->info_state |= L2CAP_INFO_FEAT_MASK_REQ_DONE; conn->info_ident = 0; + mutex_lock(&conn->lock); l2cap_conn_start(conn); + mutex_unlock(&conn->lock); } /* @@ -1757,6 +1757,8 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); + mutex_lock(&conn->lock); + kfree_skb(conn->rx_skb); skb_queue_purge(&conn->pending_rx); @@ -1775,8 +1777,6 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) /* Force the connection to be immediately dropped */ hcon->disc_timeout = 0; - mutex_lock(&conn->chan_lock); - /* Kill channels */ list_for_each_entry_safe(chan, l, &conn->chan_l, list) { l2cap_chan_hold(chan); @@ -1790,15 +1790,14 @@ static void l2cap_conn_del(struct hci_conn *hcon, int err) l2cap_chan_put(chan); } - mutex_unlock(&conn->chan_lock); - - hci_chan_del(conn->hchan); - if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) cancel_delayed_work_sync(&conn->info_timer); - hcon->l2cap_data = NULL; + hci_chan_del(conn->hchan); conn->hchan = NULL; + + hcon->l2cap_data = NULL; + mutex_unlock(&conn->lock); l2cap_conn_put(conn); } @@ -2916,8 +2915,6 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) BT_DBG("conn %p", conn); - mutex_lock(&conn->chan_lock); - list_for_each_entry(chan, &conn->chan_l, list) { if (chan->chan_type != L2CAP_CHAN_RAW) continue; @@ -2932,8 +2929,6 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) if (chan->ops->recv(chan, nskb)) kfree_skb(nskb); } - - mutex_unlock(&conn->chan_lock); } /* ---- L2CAP signalling commands ---- */ @@ -3952,7 +3947,6 @@ static void l2cap_connect(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, goto response; } - mutex_lock(&conn->chan_lock); l2cap_chan_lock(pchan); /* Check if the ACL is secure enough (if not SDP) */ @@ -4059,7 +4053,6 @@ response: } l2cap_chan_unlock(pchan); - mutex_unlock(&conn->chan_lock); l2cap_chan_put(pchan); } @@ -4098,27 +4091,19 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x result 0x%2.2x status 0x%2.2x", dcid, scid, result, status); - mutex_lock(&conn->chan_lock); - if (scid) { chan = __l2cap_get_chan_by_scid(conn, scid); - if (!chan) { - err = -EBADSLT; - goto unlock; - } + if (!chan) + return -EBADSLT; } else { chan = __l2cap_get_chan_by_ident(conn, cmd->ident); - if (!chan) { - err = -EBADSLT; - goto unlock; - } + if (!chan) + return -EBADSLT; } chan = l2cap_chan_hold_unless_zero(chan); - if (!chan) { - err = -EBADSLT; - goto unlock; - } + if (!chan) + return -EBADSLT; err = 0; @@ -4156,9 +4141,6 @@ static int l2cap_connect_create_rsp(struct l2cap_conn *conn, l2cap_chan_unlock(chan); l2cap_chan_put(chan); -unlock: - mutex_unlock(&conn->chan_lock); - return err; } @@ -4446,11 +4428,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, chan->ops->set_shutdown(chan); - l2cap_chan_unlock(chan); - mutex_lock(&conn->chan_lock); - l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNRESET); - mutex_unlock(&conn->chan_lock); chan->ops->close(chan); @@ -4487,11 +4465,7 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, return 0; } - l2cap_chan_unlock(chan); - mutex_lock(&conn->chan_lock); - l2cap_chan_lock(chan); l2cap_chan_del(chan, 0); - mutex_unlock(&conn->chan_lock); chan->ops->close(chan); @@ -4689,13 +4663,9 @@ static int l2cap_le_connect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x mtu %u mps %u credits %u result 0x%2.2x", dcid, mtu, mps, credits, result); - mutex_lock(&conn->chan_lock); - chan = __l2cap_get_chan_by_ident(conn, cmd->ident); - if (!chan) { - err = -EBADSLT; - goto unlock; - } + if (!chan) + return -EBADSLT; err = 0; @@ -4743,9 +4713,6 @@ static int l2cap_le_connect_rsp(struct l2cap_conn *conn, l2cap_chan_unlock(chan); -unlock: - mutex_unlock(&conn->chan_lock); - return err; } @@ -4857,7 +4824,6 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, goto response; } - mutex_lock(&conn->chan_lock); l2cap_chan_lock(pchan); if (!smp_sufficient_security(conn->hcon, pchan->sec_level, @@ -4923,7 +4889,6 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, response_unlock: l2cap_chan_unlock(pchan); - mutex_unlock(&conn->chan_lock); l2cap_chan_put(pchan); if (result == L2CAP_CR_PEND) @@ -5057,7 +5022,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, goto response; } - mutex_lock(&conn->chan_lock); l2cap_chan_lock(pchan); if (!smp_sufficient_security(conn->hcon, pchan->sec_level, @@ -5132,7 +5096,6 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, unlock: l2cap_chan_unlock(pchan); - mutex_unlock(&conn->chan_lock); l2cap_chan_put(pchan); response: @@ -5169,8 +5132,6 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, BT_DBG("mtu %u mps %u credits %u result 0x%4.4x", mtu, mps, credits, result); - mutex_lock(&conn->chan_lock); - cmd_len -= sizeof(*rsp); list_for_each_entry_safe(chan, tmp, &conn->chan_l, list) { @@ -5256,8 +5217,6 @@ static inline int l2cap_ecred_conn_rsp(struct l2cap_conn *conn, l2cap_chan_unlock(chan); } - mutex_unlock(&conn->chan_lock); - return err; } @@ -5370,8 +5329,6 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, if (cmd_len < sizeof(*rej)) return -EPROTO; - mutex_lock(&conn->chan_lock); - chan = __l2cap_get_chan_by_ident(conn, cmd->ident); if (!chan) goto done; @@ -5386,7 +5343,6 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, l2cap_chan_put(chan); done: - mutex_unlock(&conn->chan_lock); return 0; } @@ -6841,8 +6797,12 @@ static void process_pending_rx(struct work_struct *work) BT_DBG(""); + mutex_lock(&conn->lock); + while ((skb = skb_dequeue(&conn->pending_rx))) l2cap_recv_frame(conn, skb); + + mutex_unlock(&conn->lock); } static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) @@ -6881,7 +6841,7 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon) conn->local_fixed_chan |= L2CAP_FC_SMP_BREDR; mutex_init(&conn->ident_lock); - mutex_init(&conn->chan_lock); + mutex_init(&conn->lock); INIT_LIST_HEAD(&conn->chan_l); INIT_LIST_HEAD(&conn->users); @@ -7072,7 +7032,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, } } - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); l2cap_chan_lock(chan); if (cid && __l2cap_get_chan_by_dcid(conn, cid)) { @@ -7113,7 +7073,7 @@ int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid, chan_unlock: l2cap_chan_unlock(chan); - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); done: hci_dev_unlock(hdev); hci_dev_put(hdev); @@ -7325,7 +7285,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) BT_DBG("conn %p status 0x%2.2x encrypt %u", conn, status, encrypt); - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); list_for_each_entry(chan, &conn->chan_l, list) { l2cap_chan_lock(chan); @@ -7399,7 +7359,7 @@ static void l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) l2cap_chan_unlock(chan); } - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); } /* Append fragment into frame respecting the maximum len of rx_skb */ @@ -7466,19 +7426,45 @@ static void l2cap_recv_reset(struct l2cap_conn *conn) conn->rx_len = 0; } +struct l2cap_conn *l2cap_conn_hold_unless_zero(struct l2cap_conn *c) +{ + if (!c) + return NULL; + + BT_DBG("conn %p orig refcnt %u", c, kref_read(&c->ref)); + + if (!kref_get_unless_zero(&c->ref)) + return NULL; + + return c; +} + void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) { - struct l2cap_conn *conn = hcon->l2cap_data; + struct l2cap_conn *conn; int len; + /* Lock hdev to access l2cap_data to avoid race with l2cap_conn_del */ + hci_dev_lock(hcon->hdev); + + conn = hcon->l2cap_data; + if (!conn) conn = l2cap_conn_add(hcon); - if (!conn) - goto drop; + conn = l2cap_conn_hold_unless_zero(conn); + + hci_dev_unlock(hcon->hdev); + + if (!conn) { + kfree_skb(skb); + return; + } BT_DBG("conn %p len %u flags 0x%x", conn, skb->len, flags); + mutex_lock(&conn->lock); + switch (flags) { case ACL_START: case ACL_START_NO_FLUSH: @@ -7503,7 +7489,7 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) if (len == skb->len) { /* Complete frame received */ l2cap_recv_frame(conn, skb); - return; + goto unlock; } BT_DBG("Start: total len %d, frag len %u", len, skb->len); @@ -7567,6 +7553,9 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) drop: kfree_skb(skb); +unlock: + mutex_unlock(&conn->lock); + l2cap_conn_put(conn); } static struct hci_cb l2cap_cb = { diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 49f97d4138ea..acd11b268b98 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -710,12 +710,12 @@ static bool l2cap_valid_mtu(struct l2cap_chan *chan, u16 mtu) { switch (chan->scid) { case L2CAP_CID_ATT: - if (mtu < L2CAP_LE_MIN_MTU) + if (mtu && mtu < L2CAP_LE_MIN_MTU) return false; break; default: - if (mtu < L2CAP_DEFAULT_MIN_MTU) + if (mtu && mtu < L2CAP_DEFAULT_MIN_MTU) return false; } @@ -1326,9 +1326,10 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) /* prevent sk structure from being freed whilst unlocked */ sock_hold(sk); - chan = l2cap_pi(sk)->chan; /* prevent chan structure from being freed whilst unlocked */ - l2cap_chan_hold(chan); + chan = l2cap_chan_hold_unless_zero(l2cap_pi(sk)->chan); + if (!chan) + goto shutdown_already; BT_DBG("chan %p state %s", chan, state_to_string(chan->state)); @@ -1358,22 +1359,20 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) release_sock(sk); l2cap_chan_lock(chan); - conn = chan->conn; - if (conn) - /* prevent conn structure from being freed */ - l2cap_conn_get(conn); + /* prevent conn structure from being freed */ + conn = l2cap_conn_hold_unless_zero(chan->conn); l2cap_chan_unlock(chan); if (conn) /* mutex lock must be taken before l2cap_chan_lock() */ - mutex_lock(&conn->chan_lock); + mutex_lock(&conn->lock); l2cap_chan_lock(chan); l2cap_chan_close(chan, 0); l2cap_chan_unlock(chan); if (conn) { - mutex_unlock(&conn->chan_lock); + mutex_unlock(&conn->lock); l2cap_conn_put(conn); } diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 305dd72c844c..17226b2341d0 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -1132,7 +1132,7 @@ static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, todo_size = size; - while (todo_size) { + do { struct j1939_sk_buff_cb *skcb; segment_size = min_t(size_t, J1939_MAX_TP_PACKET_SIZE, @@ -1177,7 +1177,7 @@ static int j1939_sk_send_loop(struct j1939_priv *priv, struct sock *sk, todo_size -= segment_size; session->total_queued_size += segment_size; - } + } while (todo_size); switch (ret) { case 0: /* OK */ diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 95f7a7e65a73..9b72d118d756 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -382,8 +382,9 @@ sk_buff *j1939_session_skb_get_by_offset(struct j1939_session *session, skb_queue_walk(&session->skb_queue, do_skb) { do_skcb = j1939_skb_to_cb(do_skb); - if (offset_start >= do_skcb->offset && - offset_start < (do_skcb->offset + do_skb->len)) { + if ((offset_start >= do_skcb->offset && + offset_start < (do_skcb->offset + do_skb->len)) || + (offset_start == 0 && do_skcb->offset == 0 && do_skb->len == 0)) { skb = do_skb; } } diff --git a/net/core/dev.c b/net/core/dev.c index afa2282f2604..1b252e9459fd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1121,6 +1121,12 @@ out: return ret; } +static bool dev_addr_cmp(struct net_device *dev, unsigned short type, + const char *ha) +{ + return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); +} + /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace @@ -1129,7 +1135,7 @@ out: * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. - * The caller must hold RCU or RTNL. + * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * @@ -1141,14 +1147,39 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, struct net_device *dev; for_each_netdev_rcu(net, dev) - if (dev->type == type && - !memcmp(dev->dev_addr, ha, dev->addr_len)) + if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); +/** + * dev_getbyhwaddr() - find a device by its hardware address + * @net: the applicable net namespace + * @type: media type of device + * @ha: hardware address + * + * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold + * rtnl_lock. + * + * Context: rtnl_lock() must be held. + * Return: pointer to the net_device, or NULL if not found + */ +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *ha) +{ + struct net_device *dev; + + ASSERT_RTNL(); + for_each_netdev(net, dev) + if (dev_addr_cmp(dev, type, ha)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_getbyhwaddr); + struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; @@ -2070,6 +2101,42 @@ static void __move_netdevice_notifier_net(struct net *src_net, __register_netdevice_notifier_net(dst_net, nb, true); } +static void rtnl_net_dev_lock(struct net_device *dev) +{ + bool again; + + do { + struct net *net; + + again = false; + + /* netns might be being dismantled. */ + rcu_read_lock(); + net = dev_net_rcu(dev); + net_passive_inc(net); + rcu_read_unlock(); + + rtnl_net_lock(net); + +#ifdef CONFIG_NET_NS + /* dev might have been moved to another netns. */ + if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) { + rtnl_net_unlock(net); + net_passive_dec(net); + again = true; + } +#endif + } while (again); +} + +static void rtnl_net_dev_unlock(struct net_device *dev) +{ + struct net *net = dev_net(dev); + + rtnl_net_unlock(net); + net_passive_dec(net); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -2077,6 +2144,11 @@ int register_netdevice_notifier_dev_net(struct net_device *dev, struct net *net = dev_net(dev); int err; + /* rtnl_net_lock() assumes dev is not yet published by + * register_netdevice(). + */ + DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list)); + rtnl_net_lock(net); err = __register_netdevice_notifier_net(net, nb, false); if (!err) { @@ -2093,13 +2165,12 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); list_del(&nn->list); - err = __unregister_netdevice_notifier_net(net, nb); - rtnl_net_unlock(net); + err = __unregister_netdevice_notifier_net(dev_net(dev), nb); + rtnl_net_dev_unlock(dev); return err; } @@ -6708,7 +6779,7 @@ void napi_resume_irqs(unsigned int napi_id) static void __napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { - napi->napi_id = napi_id; + WRITE_ONCE(napi->napi_id, napi_id); hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); } @@ -6920,6 +6991,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } +/* Double check that napi_get_frags() allocates skbs with + * skb->head being backed by slab, not a page fragment. + * This is to make sure bug fixed in 3226b158e67c + * ("net: avoid 32 x truesize under-estimation for tiny skbs") + * does not accidentally come back. + */ +static void napi_get_frags_check(struct napi_struct *napi) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = napi_get_frags(napi); + WARN_ON_ONCE(skb && skb->head_frag); + napi_free_frags(napi); + local_bh_enable(); +} + void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), @@ -9924,6 +10012,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Program bound to different device"); return -EINVAL; } + if (bpf_prog_is_dev_bound(new_prog->aux) && mode == XDP_MODE_SKB) { + NL_SET_ERR_MSG(extack, "Can't attach device-bound programs in generic mode"); + return -EINVAL; + } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; @@ -10260,37 +10352,14 @@ static bool from_cleanup_net(void) #endif } -static void rtnl_drop_if_cleanup_net(void) -{ - if (from_cleanup_net()) - __rtnl_unlock(); -} - -static void rtnl_acquire_if_cleanup_net(void) -{ - if (from_cleanup_net()) - rtnl_lock(); -} - /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); -static LIST_HEAD(net_todo_list_for_cleanup_net); - -/* TODO: net_todo_list/net_todo_list_for_cleanup_net should probably - * be provided by callers, instead of being static, rtnl protected. - */ -static struct list_head *todo_list(void) -{ - return from_cleanup_net() ? &net_todo_list_for_cleanup_net : - &net_todo_list; -} - DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { - list_add_tail(&dev->todo_list, todo_list()); + list_add_tail(&dev->todo_list, &net_todo_list); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, @@ -11140,7 +11209,7 @@ void netdev_run_todo(void) #endif /* Snapshot list, allow later requests */ - list_replace_init(todo_list(), &list); + list_replace_init(&net_todo_list, &list); __rtnl_unlock(); @@ -11305,6 +11374,20 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, const struct net_device_ops *ops = dev->netdev_ops; const struct net_device_core_stats __percpu *p; + /* + * IPv{4,6} and udp tunnels share common stat helpers and use + * different stat type (NETDEV_PCPU_STAT_TSTATS vs + * NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent. + */ + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) != + offsetof(struct pcpu_dstats, rx_bytes)); + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) != + offsetof(struct pcpu_dstats, rx_packets)); + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) != + offsetof(struct pcpu_dstats, tx_bytes)); + BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) != + offsetof(struct pcpu_dstats, tx_packets)); + if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); ops->ndo_get_stats64(dev, storage); @@ -11785,11 +11868,9 @@ void unregister_netdevice_many_notify(struct list_head *head, WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); netdev_unlock(dev); } - - rtnl_drop_if_cleanup_net(); flush_all_backlogs(); + synchronize_net(); - rtnl_acquire_if_cleanup_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; @@ -11849,9 +11930,7 @@ void unregister_netdevice_many_notify(struct list_head *head, #endif } - rtnl_drop_if_cleanup_net(); synchronize_net(); - rtnl_acquire_if_cleanup_net(); list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); @@ -11889,11 +11968,9 @@ EXPORT_SYMBOL(unregister_netdevice_many); */ void unregister_netdev(struct net_device *dev) { - struct net *net = dev_net(dev); - - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); unregister_netdevice(dev); - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); } EXPORT_SYMBOL(unregister_netdev); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 6efd4cccc9dd..212f0a048cab 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1734,30 +1734,30 @@ static int __init init_net_drop_monitor(void) return -ENOSPC; } - rc = genl_register_family(&net_drop_monitor_family); - if (rc) { - pr_err("Could not create drop monitor netlink family\n"); - return rc; + for_each_possible_cpu(cpu) { + net_dm_cpu_data_init(cpu); + net_dm_hw_cpu_data_init(cpu); } - WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); + return rc; + } + + rc = genl_register_family(&net_drop_monitor_family); + if (rc) { + pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } + WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; - for_each_possible_cpu(cpu) { - net_dm_cpu_data_init(cpu); - net_dm_hw_cpu_data_init(cpu); - } - goto out; out_unreg: - genl_unregister_family(&net_drop_monitor_family); + WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } @@ -1766,19 +1766,18 @@ static void exit_net_drop_monitor(void) { int cpu; - BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); - /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } - - BUG_ON(genl_unregister_family(&net_drop_monitor_family)); } module_init(init_net_drop_monitor); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index e684ba3ebb38..94a7872ab231 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -37,8 +37,8 @@ static const struct fib_kuid_range fib_kuid_range_unset = { bool fib_rule_matchall(const struct fib_rule *rule) { - if (rule->iifindex || rule->oifindex || rule->mark || rule->tun_id || - rule->flags) + if (READ_ONCE(rule->iifindex) || READ_ONCE(rule->oifindex) || + rule->mark || rule->tun_id || rule->flags) return false; if (rule->suppress_ifgroup != -1 || rule->suppress_prefixlen != -1) return false; @@ -261,12 +261,14 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, struct flowi *fl, int flags, struct fib_lookup_arg *arg) { - int ret = 0; + int iifindex, oifindex, ret = 0; - if (rule->iifindex && (rule->iifindex != fl->flowi_iif)) + iifindex = READ_ONCE(rule->iifindex); + if (iifindex && (iifindex != fl->flowi_iif)) goto out; - if (rule->oifindex && (rule->oifindex != fl->flowi_oif)) + oifindex = READ_ONCE(rule->oifindex); + if (oifindex && (oifindex != fl->flowi_oif)) goto out; if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask) @@ -1041,14 +1043,14 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (rule->iifname[0]) { if (nla_put_string(skb, FRA_IIFNAME, rule->iifname)) goto nla_put_failure; - if (rule->iifindex == -1) + if (READ_ONCE(rule->iifindex) == -1) frh->flags |= FIB_RULE_IIF_DETACHED; } if (rule->oifname[0]) { if (nla_put_string(skb, FRA_OIFNAME, rule->oifname)) goto nla_put_failure; - if (rule->oifindex == -1) + if (READ_ONCE(rule->oifindex) == -1) frh->flags |= FIB_RULE_OIF_DETACHED; } @@ -1220,10 +1222,10 @@ static void attach_rules(struct list_head *rules, struct net_device *dev) list_for_each_entry(rule, rules, list) { if (rule->iifindex == -1 && strcmp(dev->name, rule->iifname) == 0) - rule->iifindex = dev->ifindex; + WRITE_ONCE(rule->iifindex, dev->ifindex); if (rule->oifindex == -1 && strcmp(dev->name, rule->oifname) == 0) - rule->oifindex = dev->ifindex; + WRITE_ONCE(rule->oifindex, dev->ifindex); } } @@ -1233,9 +1235,9 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) list_for_each_entry(rule, rules, list) { if (rule->iifindex == dev->ifindex) - rule->iifindex = -1; + WRITE_ONCE(rule->iifindex, -1); if (rule->oifindex == dev->ifindex) - rule->oifindex = -1; + WRITE_ONCE(rule->oifindex, -1); } } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 0e638a37aa09..9cd8de6bebb5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -853,23 +853,30 @@ __skb_flow_dissect_ports(const struct sk_buff *skb, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { - enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; - struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_ports_range *key_ports_range = NULL; + struct flow_dissector_key_ports *key_ports = NULL; + __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS; - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); - if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + if (!key_ports && !key_ports_range) return; - key_ports = skb_flow_dissector_target(flow_dissector, - dissector_ports, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); + ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); + + if (key_ports) + key_ports->ports = ports; + + if (key_ports_range) + key_ports_range->tp.ports = ports; } static void @@ -924,6 +931,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { + struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; @@ -968,20 +976,21 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE, - target_container); - - if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) { + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + key_ports_range->tp.src = flow_keys->sport; + key_ports_range->tp.dst = flow_keys->dport; + } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { @@ -1108,10 +1117,12 @@ bool __skb_flow_dissect(const struct net *net, FLOW_DISSECTOR_KEY_BASIC, target_container); + rcu_read_lock(); + if (skb) { if (!net) { if (skb->dev) - net = dev_net(skb->dev); + net = dev_net_rcu(skb->dev); else if (skb->sk) net = sock_net(skb->sk); } @@ -1122,7 +1133,6 @@ bool __skb_flow_dissect(const struct net *net, enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR; struct bpf_prog_array *run_array; - rcu_read_lock(); run_array = rcu_dereference(init_net.bpf.run_array[type]); if (!run_array) run_array = rcu_dereference(net->bpf.run_array[type]); @@ -1150,17 +1160,17 @@ bool __skb_flow_dissect(const struct net *net, prog = READ_ONCE(run_array->items[0].prog); result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff, hlen, flags); - if (result == BPF_FLOW_DISSECTOR_CONTINUE) - goto dissect_continue; - __skb_flow_bpf_to_target(&flow_keys, flow_dissector, - target_container); - rcu_read_unlock(); - return result == BPF_OK; + if (result != BPF_FLOW_DISSECTOR_CONTINUE) { + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, + target_container); + rcu_read_unlock(); + return result == BPF_OK; + } } -dissect_continue: - rcu_read_unlock(); } + rcu_read_unlock(); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); diff --git a/net/core/gro.c b/net/core/gro.c index d1f44084e978..78b320b63174 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -7,9 +7,6 @@ #define MAX_GRO_SKBS 8 -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) - static DEFINE_SPINLOCK(offload_lock); /** diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 89656d180bc6..bd0251bd74a1 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3447,10 +3447,12 @@ static const struct seq_operations neigh_stat_seq_ops = { static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid) { - struct net *net = dev_net(n->dev); struct sk_buff *skb; int err = -ENOBUFS; + struct net *net; + rcu_read_lock(); + net = dev_net_rcu(n->dev); skb = nlmsg_new(neigh_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) goto errout; @@ -3463,9 +3465,11 @@ static void __neigh_notify(struct neighbour *n, int type, int flags, goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); - return; + goto out; errout: rtnl_set_sk_err(net, RTNLGRP_NEIGH, err); +out: + rcu_read_unlock(); } void neigh_app_ns(struct neighbour *n) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cb39a12b2f82..4303f2a49262 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -464,7 +464,7 @@ static void net_complete_free(void) } -static void net_free(struct net *net) +void net_passive_dec(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); @@ -482,7 +482,7 @@ void net_drop_ns(void *p) struct net *net = (struct net *)p; if (net) - net_free(net); + net_passive_dec(net); } struct net *copy_net_ns(unsigned long flags, @@ -523,7 +523,7 @@ put_userns: key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); - net_free(net); + net_passive_dec(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); @@ -672,7 +672,7 @@ static void cleanup_net(struct work_struct *work) key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); - net_free(net); + net_passive_dec(net); } cleanup_net_task = NULL; } diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1906c62dee85..f5e908c9e7ad 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -1146,7 +1146,9 @@ void page_pool_disable_direct_recycling(struct page_pool *pool) WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state)); WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1); + mutex_lock(&page_pools_lock); WRITE_ONCE(pool->p.napi, NULL); + mutex_unlock(&page_pools_lock); } EXPORT_SYMBOL(page_pool_disable_direct_recycling); diff --git a/net/core/page_pool_priv.h b/net/core/page_pool_priv.h index 57439787b9c2..2fb06d5f6d55 100644 --- a/net/core/page_pool_priv.h +++ b/net/core/page_pool_priv.h @@ -7,6 +7,8 @@ #include "netmem_priv.h" +extern struct mutex page_pools_lock; + s32 page_pool_inflight(const struct page_pool *pool, bool strict); int page_pool_list(struct page_pool *pool); diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c index 48335766c1bf..6677e0c2e256 100644 --- a/net/core/page_pool_user.c +++ b/net/core/page_pool_user.c @@ -3,6 +3,7 @@ #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/xarray.h> +#include <net/busy_poll.h> #include <net/net_debug.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/helpers.h> @@ -14,10 +15,11 @@ #include "netdev-genl-gen.h" static DEFINE_XARRAY_FLAGS(page_pools, XA_FLAGS_ALLOC1); -/* Protects: page_pools, netdevice->page_pools, pool->slow.netdev, pool->user. +/* Protects: page_pools, netdevice->page_pools, pool->p.napi, pool->slow.netdev, + * pool->user. * Ordering: inside rtnl_lock */ -static DEFINE_MUTEX(page_pools_lock); +DEFINE_MUTEX(page_pools_lock); /* Page pools are only reachable from user space (via netlink) if they are * linked to a netdev at creation time. Following page pool "visibility" @@ -216,6 +218,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, { struct net_devmem_dmabuf_binding *binding = pool->mp_priv; size_t inflight, refsz; + unsigned int napi_id; void *hdr; hdr = genlmsg_iput(rsp, info); @@ -229,8 +232,10 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool, nla_put_u32(rsp, NETDEV_A_PAGE_POOL_IFINDEX, pool->slow.netdev->ifindex)) goto err_cancel; - if (pool->user.napi_id && - nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id)) + + napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0; + if (napi_id >= MIN_NAPI_ID && + nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id)) goto err_cancel; inflight = page_pool_inflight(pool, false); @@ -319,8 +324,6 @@ int page_pool_list(struct page_pool *pool) if (pool->slow.netdev) { hlist_add_head(&pool->user.list, &pool->slow.netdev->page_pools); - pool->user.napi_id = pool->p.napi ? pool->p.napi->napi_id : 0; - netdev_nl_page_pool_event(pool, NETDEV_CMD_PAGE_POOL_ADD_NTF); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1f4d4b5570ab..d1e559fce918 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3432,6 +3432,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, err = -ENODEV; rtnl_nets_unlock(&rtnl_nets); + rtnl_nets_destroy(&rtnl_nets); errout: return err; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a441613a1e6c..7b03b64fdcb2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/gro.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> @@ -95,7 +96,9 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif -#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) +#define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN) +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \ + GRO_MAX_HEAD_PAD)) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique @@ -220,67 +223,9 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) -#if PAGE_SIZE == SZ_4K - -#define NAPI_HAS_SMALL_PAGE_FRAG 1 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc) - -/* specialized page frag allocator using a single order 0 page - * and slicing it into 1K sized fragment. Constrained to systems - * with a very limited amount of 1K fragments fitting a single - * page - to avoid excessive truesize underestimation - */ - -struct page_frag_1k { - void *va; - u16 offset; - bool pfmemalloc; -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) -{ - struct page *page; - int offset; - - offset = nc->offset - SZ_1K; - if (likely(offset >= 0)) - goto use_frag; - - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - if (!page) - return NULL; - - nc->va = page_address(page); - nc->pfmemalloc = page_is_pfmemalloc(page); - offset = PAGE_SIZE - SZ_1K; - page_ref_add(page, offset / SZ_1K); - -use_frag: - nc->offset = offset; - return nc->va + offset; -} -#else - -/* the small page is actually unused in this build; add dummy helpers - * to please the compiler and avoid later preprocessor's conditionals - */ -#define NAPI_HAS_SMALL_PAGE_FRAG 0 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false - -struct page_frag_1k { -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) -{ - return NULL; -} - -#endif - struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; - struct page_frag_1k page_small; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; @@ -290,23 +235,6 @@ static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; -/* Double check that napi_get_frags() allocates skbs with - * skb->head being backed by slab, not a page fragment. - * This is to make sure bug fixed in 3226b158e67c - * ("net: avoid 32 x truesize under-estimation for tiny skbs") - * does not accidentally come back. - */ -void napi_get_frags_check(struct napi_struct *napi) -{ - struct sk_buff *skb; - - local_bh_disable(); - skb = napi_get_frags(napi); - WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag); - napi_free_frags(napi); - local_bh_enable(); -} - void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -736,7 +664,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ - if (len <= SKB_WITH_OVERHEAD(1024) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); @@ -813,10 +741,8 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. - * When the small frag allocator is available, prefer it over kmalloc - * for small fragments */ - if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, @@ -826,32 +752,16 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } + len = SKB_HEAD_ALIGN(len); + if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); - if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { - /* we are artificially inflating the allocation size, but - * that is not as bad as it may look like, as: - * - 'len' less than GRO_MAX_HEAD makes little sense - * - On most systems, larger 'len' values lead to fragment - * size above 512 bytes - * - kmalloc would use the kmalloc-1k slab for such values - * - Builds with smaller GRO_MAX_HEAD will very likely do - * little networking, as that implies no WiFi and no - * tunnels support, and 32 bits arches. - */ - len = SZ_1K; - data = page_frag_alloc_1k(&nc->page_small, gfp_mask); - pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); - } else { - len = SKB_HEAD_ALIGN(len); - - data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); - } + data = page_frag_alloc(&nc->page, len, gfp_mask); + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 3b0f59d9b4db..82a14f131d00 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -544,6 +544,9 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_stream_unix(sk)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; + if (sk_is_vsock(sk) && + (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 2bd77c94f9f1..d88e9080643b 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -462,6 +462,11 @@ const char ts_rx_filter_names[][ETH_GSTRING_LEN] = { }; static_assert(ARRAY_SIZE(ts_rx_filter_names) == __HWTSTAMP_FILTER_CNT); +const char ts_flags_names[][ETH_GSTRING_LEN] = { + [const_ilog2(HWTSTAMP_FLAG_BONDED_PHC_INDEX)] = "bonded-phc-index", +}; +static_assert(ARRAY_SIZE(ts_flags_names) == __HWTSTAMP_FLAG_CNT); + const char udp_tunnel_type_names[][ETH_GSTRING_LEN] = { [ETHTOOL_UDP_TUNNEL_TYPE_VXLAN] = "vxlan", [ETHTOOL_UDP_TUNNEL_TYPE_GENEVE] = "geneve", diff --git a/net/ethtool/common.h b/net/ethtool/common.h index 850eadde4bfc..58e9e7db06f9 100644 --- a/net/ethtool/common.h +++ b/net/ethtool/common.h @@ -13,6 +13,7 @@ ETHTOOL_LINK_MODE_ ## speed ## base ## type ## _ ## duplex ## _BIT #define __SOF_TIMESTAMPING_CNT (const_ilog2(SOF_TIMESTAMPING_LAST) + 1) +#define __HWTSTAMP_FLAG_CNT (const_ilog2(HWTSTAMP_FLAG_LAST) + 1) struct link_mode_info { int speed; @@ -38,6 +39,7 @@ extern const char wol_mode_names[][ETH_GSTRING_LEN]; extern const char sof_timestamping_names[][ETH_GSTRING_LEN]; extern const char ts_tx_type_names[][ETH_GSTRING_LEN]; extern const char ts_rx_filter_names[][ETH_GSTRING_LEN]; +extern const char ts_flags_names[][ETH_GSTRING_LEN]; extern const char udp_tunnel_type_names[][ETH_GSTRING_LEN]; int __ethtool_get_link(struct net_device *dev); diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 7bb94875a7ec..7609ce2b2c5e 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -993,12 +993,12 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, return rc; /* Nonzero ring with RSS only makes sense if NIC adds them together */ - if (cmd == ETHTOOL_SRXCLSRLINS && info.flow_type & FLOW_RSS && + if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS && !ops->cap_rss_rxnfc_adds && ethtool_get_flow_spec_ring(info.fs.ring_cookie)) return -EINVAL; - if (ops->get_rxfh) { + if (cmd == ETHTOOL_SRXFH && ops->get_rxfh) { struct ethtool_rxfh_param rxfh = {}; rc = ops->get_rxfh(dev, &rxfh); diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index 7cb106b590ab..58df9ad02ce8 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -107,6 +107,8 @@ rss_prepare_ctx(const struct rss_req_info *request, struct net_device *dev, u32 total_size, indir_bytes; u8 *rss_config; + data->no_key_fields = !dev->ethtool_ops->rxfh_per_ctx_key; + ctx = xa_load(&dev->ethtool->rss_ctx, request->rss_context); if (!ctx) return -ENOENT; @@ -153,7 +155,6 @@ rss_prepare_data(const struct ethnl_req_info *req_base, if (!ops->cap_rss_ctx_supported && !ops->create_rxfh_context) return -EOPNOTSUPP; - data->no_key_fields = !ops->rxfh_per_ctx_key; return rss_prepare_ctx(request, dev, data, info); } diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 818cf01f0911..6b76c05caba4 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -75,6 +75,11 @@ static const struct strset_info info_template[] = { .count = __HWTSTAMP_FILTER_CNT, .strings = ts_rx_filter_names, }, + [ETH_SS_TS_FLAGS] = { + .per_dev = false, + .count = __HWTSTAMP_FLAG_CNT, + .strings = ts_flags_names, + }, [ETH_SS_UDP_TUNNEL_TYPES] = { .per_dev = false, .count = __ETHTOOL_UDP_TUNNEL_TYPE_CNT, diff --git a/net/ethtool/tsconfig.c b/net/ethtool/tsconfig.c index 9188e088fb2f..2be356bdfe87 100644 --- a/net/ethtool/tsconfig.c +++ b/net/ethtool/tsconfig.c @@ -54,7 +54,7 @@ static int tsconfig_prepare_data(const struct ethnl_req_info *req_base, data->hwtst_config.tx_type = BIT(cfg.tx_type); data->hwtst_config.rx_filter = BIT(cfg.rx_filter); - data->hwtst_config.flags = BIT(cfg.flags); + data->hwtst_config.flags = cfg.flags; data->hwprov_desc.index = -1; hwprov = rtnl_dereference(dev->hwprov); @@ -91,10 +91,16 @@ static int tsconfig_reply_size(const struct ethnl_req_info *req_base, BUILD_BUG_ON(__HWTSTAMP_TX_CNT > 32); BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT > 32); + BUILD_BUG_ON(__HWTSTAMP_FLAG_CNT > 32); - if (data->hwtst_config.flags) - /* _TSCONFIG_HWTSTAMP_FLAGS */ - len += nla_total_size(sizeof(u32)); + if (data->hwtst_config.flags) { + ret = ethnl_bitset32_size(&data->hwtst_config.flags, + NULL, __HWTSTAMP_FLAG_CNT, + ts_flags_names, compact); + if (ret < 0) + return ret; + len += ret; /* _TSCONFIG_HWTSTAMP_FLAGS */ + } if (data->hwtst_config.tx_type) { ret = ethnl_bitset32_size(&data->hwtst_config.tx_type, @@ -130,8 +136,10 @@ static int tsconfig_fill_reply(struct sk_buff *skb, int ret; if (data->hwtst_config.flags) { - ret = nla_put_u32(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, - data->hwtst_config.flags); + ret = ethnl_put_bitset32(skb, ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS, + &data->hwtst_config.flags, NULL, + __HWTSTAMP_FLAG_CNT, + ts_flags_names, compact); if (ret < 0) return ret; } @@ -180,7 +188,7 @@ const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1] = [ETHTOOL_A_TSCONFIG_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_TSCONFIG_HWTSTAMP_PROVIDER] = NLA_POLICY_NESTED(ethnl_ts_hwtst_prov_policy), - [ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS] = { .type = NLA_U32 }, + [ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS] = { .type = NLA_NESTED }, [ETHTOOL_A_TSCONFIG_RX_FILTERS] = { .type = NLA_NESTED }, [ETHTOOL_A_TSCONFIG_TX_TYPES] = { .type = NLA_NESTED }, }; @@ -296,6 +304,7 @@ static int ethnl_set_tsconfig(struct ethnl_req_info *req_base, BUILD_BUG_ON(__HWTSTAMP_TX_CNT >= 32); BUILD_BUG_ON(__HWTSTAMP_FILTER_CNT >= 32); + BUILD_BUG_ON(__HWTSTAMP_FLAG_CNT > 32); if (!netif_device_present(dev)) return -ENODEV; @@ -377,9 +386,13 @@ static int ethnl_set_tsconfig(struct ethnl_req_info *req_base, } if (tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS]) { - ethnl_update_u32(&hwtst_config.flags, - tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS], - &config_mod); + ret = ethnl_update_bitset32(&hwtst_config.flags, + __HWTSTAMP_FLAG_CNT, + tb[ETHTOOL_A_TSCONFIG_HWTSTAMP_FLAGS], + ts_flags_names, info->extack, + &config_mod); + if (ret < 0) + goto err_free_hwprov; } ret = net_hwtstamp_validate(&hwtst_config); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index 87bb3a91598e..a4bacf198555 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -700,9 +700,12 @@ static int fill_frame_info(struct hsr_frame_info *frame, frame->is_vlan = true; if (frame->is_vlan) { - if (skb->mac_len < offsetofend(struct hsr_vlan_ethhdr, vlanhdr)) + /* Note: skb->mac_len might be wrong here. */ + if (!pskb_may_pull(skb, + skb_mac_offset(skb) + + offsetofend(struct hsr_vlan_ethhdr, vlanhdr))) return -EINVAL; - vlan_hdr = (struct hsr_vlan_ethhdr *)ethhdr; + vlan_hdr = (struct hsr_vlan_ethhdr *)skb_mac_header(skb); proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index cb9a7ed8abd3..814300eee39d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -659,10 +659,12 @@ static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb */ void arp_xmit(struct sk_buff *skb) { + rcu_read_lock(); /* Send it off, maybe filter it using firewalling first. */ NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, - dev_net(skb->dev), NULL, skb, NULL, skb->dev, + dev_net_rcu(skb->dev), NULL, skb, NULL, skb->dev, arp_xmit_finish); + rcu_read_unlock(); } EXPORT_SYMBOL(arp_xmit); @@ -1075,7 +1077,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c8b3cf5fba4c..55b8151759bc 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1371,10 +1371,11 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) __be32 addr = 0; unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; - struct net *net = dev_net(dev); + struct net *net; int master_idx; rcu_read_lock(); + net = dev_net_rcu(dev); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b0fbf804bbba..0e4076866c0a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -279,7 +279,7 @@ static void esp_output_done(void *data, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb->sk, skb, err); + xfrm_output_resume(skb_to_full_sk(skb), skb, err); } } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 094084b61bff..5482edb5aade 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -399,10 +399,10 @@ static void icmp_push_reply(struct sock *sk, static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) { - struct ipcm_cookie ipc; struct rtable *rt = skb_rtable(skb); - struct net *net = dev_net(rt->dst.dev); + struct net *net = dev_net_rcu(rt->dst.dev); bool apply_ratelimit = false; + struct ipcm_cookie ipc; struct flowi4 fl4; struct sock *sk; struct inet_sock *inet; @@ -608,12 +608,14 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, struct sock *sk; if (!rt) - goto out; + return; + + rcu_read_lock(); if (rt->dst.dev) - net = dev_net(rt->dst.dev); + net = dev_net_rcu(rt->dst.dev); else if (skb_in->dev) - net = dev_net(skb_in->dev); + net = dev_net_rcu(skb_in->dev); else goto out; @@ -785,7 +787,8 @@ out_unlock: icmp_xmit_unlock(sk); out_bh_enable: local_bh_enable(); -out:; +out: + rcu_read_unlock(); } EXPORT_SYMBOL(__icmp_send); @@ -834,7 +837,7 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info) * avoid additional coding at protocol handlers. */ if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) { - __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); return; } @@ -868,7 +871,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) struct net *net; u32 info = 0; - net = dev_net(skb_dst(skb)->dev); + net = dev_net_rcu(skb_dst(skb)->dev); /* * Incomplete header ? @@ -979,7 +982,7 @@ out_err: static enum skb_drop_reason icmp_redirect(struct sk_buff *skb) { if (skb->len < sizeof(struct iphdr)) { - __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(dev_net_rcu(skb->dev), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } @@ -1011,7 +1014,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) struct icmp_bxm icmp_param; struct net *net; - net = dev_net(skb_dst(skb)->dev); + net = dev_net_rcu(skb_dst(skb)->dev); /* should there be an ICMP stat for ignored echos? */ if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all)) return SKB_NOT_DROPPED_YET; @@ -1040,9 +1043,9 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) { + struct net *net = dev_net_rcu(skb->dev); struct icmp_ext_hdr *ext_hdr, _ext_hdr; struct icmp_ext_echo_iio *iio, _iio; - struct net *net = dev_net(skb->dev); struct inet6_dev *in6_dev; struct in_device *in_dev; struct net_device *dev; @@ -1181,7 +1184,7 @@ static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb) return SKB_NOT_DROPPED_YET; out_err: - __ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS); + __ICMP_INC_STATS(dev_net_rcu(skb_dst(skb)->dev), ICMP_MIB_INERRORS); return SKB_DROP_REASON_PKT_TOO_SMALL; } @@ -1198,7 +1201,7 @@ int icmp_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; struct rtable *rt = skb_rtable(skb); - struct net *net = dev_net(rt->dst.dev); + struct net *net = dev_net_rcu(rt->dst.dev); struct icmphdr *icmph; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { @@ -1371,9 +1374,9 @@ int icmp_err(struct sk_buff *skb, u32 info) struct iphdr *iph = (struct iphdr *)skb->data; int offset = iph->ihl<<2; struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset); + struct net *net = dev_net_rcu(skb->dev); int type = icmp_hdr(skb)->type; int code = icmp_hdr(skb)->code; - struct net *net = dev_net(skb->dev); /* * Use ping_err to handle all icmp errors except those diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index 03b6eee407a2..28d77d454d44 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -330,9 +330,6 @@ next_entry: list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { if (e < s_e) goto next_entry2; - if (filter->dev && - !mr_mfc_uses_dev(mrt, mfc, filter->dev)) - goto next_entry2; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 577b88a43293..753704f75b2c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -390,7 +390,13 @@ static inline int ip_rt_proc_init(void) static inline bool rt_is_expired(const struct rtable *rth) { - return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); + bool res; + + rcu_read_lock(); + res = rth->rt_genid != rt_genid_ipv4(dev_net_rcu(rth->dst.dev)); + rcu_read_unlock(); + + return res; } void rt_cache_flush(struct net *net) @@ -1002,9 +1008,9 @@ out: kfree_skb_reason(skb, reason); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; - struct net *net = dev_net(dst->dev); struct fib_result res; bool lock = false; + struct net *net; u32 old_mtu; if (ip_mtu_locked(dst)) @@ -1014,6 +1020,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (old_mtu < mtu) return; + rcu_read_lock(); + net = dev_net_rcu(dst->dev); if (mtu < net->ipv4.ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, net->ipv4.ip_rt_min_pmtu); @@ -1021,9 +1029,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - net->ipv4.ip_rt_mtu_expires / 2)) - return; + goto out; - rcu_read_lock(); if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; @@ -1037,14 +1044,14 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } - rcu_read_unlock(); - return; + goto out; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + net->ipv4.ip_rt_mtu_expires); } +out: rcu_read_unlock(); } @@ -1307,10 +1314,15 @@ static void set_class_tag(struct rtable *rt, u32 tag) static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { - struct net *net = dev_net(dst->dev); unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); - unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, - net->ipv4.ip_rt_min_advmss); + unsigned int advmss; + struct net *net; + + rcu_read_lock(); + net = dev_net_rcu(dst->dev); + advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, + net->ipv4.ip_rt_min_advmss); + rcu_read_unlock(); return min(advmss, IPV4_MAX_PMTU - header_size); } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 0f523cbfe329..32b28fc21b63 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -178,7 +178,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) if (!skb) return; - skb_dst_drop(skb); + tcp_cleanup_skb(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects @@ -195,7 +195,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eb82e01da911..0cbf81bf3d45 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -243,9 +243,15 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; - if (old_ratio != tcp_sk(sk)->scaling_ratio) - WRITE_ONCE(tcp_sk(sk)->window_clamp, - tcp_win_from_space(sk, sk->sk_rcvbuf)); + if (old_ratio != tcp_sk(sk)->scaling_ratio) { + struct tcp_sock *tp = tcp_sk(sk); + + val = tcp_win_from_space(sk, sk->sk_rcvbuf); + tcp_set_window_clamp(sk, val); + + if (tp->window_clamp < tp->rcvq_space.space) + tp->rcvq_space.space = tp->window_clamp; + } } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -4970,7 +4976,7 @@ static void tcp_ofo_queue(struct sock *sk) tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); else kfree_skb_partial(skb, fragstolen); @@ -5162,7 +5168,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); skb_set_owner_r(skb, sk); } return eaten; @@ -5245,7 +5251,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); return; } - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); reason = SKB_DROP_REASON_NOT_SPECIFIED; @@ -6226,7 +6232,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_header_len); eaten = tcp_queue_rcv(sk, skb, &fragstolen); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cc2b5194a18d..2632844d2c35 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2027,7 +2027,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, */ skb_condense(skb); - skb_dst_drop(skb); + tcp_cleanup_skb(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0e5b9a654254..bc95d2a5924f 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -265,11 +265,14 @@ static u16 tcp_select_window(struct sock *sk) u32 cur_win, new_win; /* Make the window 0 if we failed to queue the data because we - * are out of memory. The window is temporary, so we don't store - * it on the socket. + * are out of memory. */ - if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) + if (unlikely(inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOMEM)) { + tp->pred_flags = 0; + tp->rcv_wnd = 0; + tp->rcv_wup = tp->rcv_nxt; return 0; + } cur_win = tcp_receive_window(tp); new_win = __tcp_select_window(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c472c9a57cf6..a9bb9ce5438e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1141,9 +1141,9 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) { + if (hlen + min(datalen, cork->gso_size) > cork->fragsize) { kfree_skb(skb); - return -EINVAL; + return -EMSGSIZE; } if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5f3d0cc1555a..9e73944e3b53 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -315,7 +315,7 @@ static void esp_output_done(void *data, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb->sk, skb, err); + xfrm_output_resume(skb_to_full_sk(skb), skb, err); } } diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index a6984a29fdb9..4d14ab7f7e99 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -76,7 +76,7 @@ static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, { /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */ struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset); - struct net *net = dev_net(skb->dev); + struct net *net = dev_net_rcu(skb->dev); if (type == ICMPV6_PKT_TOOBIG) ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); @@ -473,7 +473,10 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (!skb->dev) return; - net = dev_net(skb->dev); + + rcu_read_lock(); + + net = dev_net_rcu(skb->dev); mark = IP6_REPLY_MARK(net, skb->mark); /* * Make sure we respect the rules @@ -496,7 +499,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, !(type == ICMPV6_PARAMPROB && code == ICMPV6_UNK_OPTION && (opt_unrec(skb, info)))) - return; + goto out; saddr = NULL; } @@ -526,7 +529,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) { net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); - return; + goto out; } /* @@ -535,7 +538,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, if (is_ineligible(skb)) { net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); - return; + goto out; } /* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */ @@ -582,7 +585,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, np = inet6_sk(sk); if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit)) - goto out; + goto out_unlock; tmp_hdr.icmp6_type = type; tmp_hdr.icmp6_code = code; @@ -600,7 +603,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, dst = icmpv6_route_lookup(net, skb, sk, &fl6); if (IS_ERR(dst)) - goto out; + goto out_unlock; ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); @@ -616,7 +619,6 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, goto out_dst_release; } - rcu_read_lock(); idev = __in6_dev_get(skb->dev); if (ip6_append_data(sk, icmpv6_getfrag, &msg, @@ -630,13 +632,15 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr, len + sizeof(struct icmp6hdr)); } - rcu_read_unlock(); + out_dst_release: dst_release(dst); -out: +out_unlock: icmpv6_xmit_unlock(sk); out_bh_enable: local_bh_enable(); +out: + rcu_read_unlock(); } EXPORT_SYMBOL(icmp6_send); @@ -679,8 +683,8 @@ int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type, skb_pull(skb2, nhs); skb_reset_network_header(skb2); - rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, - skb, 0); + rt = rt6_lookup(dev_net_rcu(skb->dev), &ipv6_hdr(skb2)->saddr, + NULL, 0, skb, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; @@ -717,7 +721,7 @@ EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach); static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); + struct net *net = dev_net_rcu(skb->dev); struct sock *sk; struct inet6_dev *idev; struct ipv6_pinfo *np; @@ -832,7 +836,7 @@ enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { struct inet6_skb_parm *opt = IP6CB(skb); - struct net *net = dev_net(skb->dev); + struct net *net = dev_net_rcu(skb->dev); const struct inet6_protocol *ipprot; enum skb_drop_reason reason; int inner_offset; @@ -889,7 +893,7 @@ out: static int icmpv6_rcv(struct sk_buff *skb) { enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; - struct net *net = dev_net(skb->dev); + struct net *net = dev_net_rcu(skb->dev); struct net_device *dev = icmp6_dev(skb); struct inet6_dev *idev = __in6_dev_get(dev); const struct in6_addr *saddr, *daddr; @@ -921,7 +925,7 @@ static int icmpv6_rcv(struct sk_buff *skb) skb_set_network_header(skb, nh); } - __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INMSGS); + __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INMSGS); saddr = &ipv6_hdr(skb)->saddr; daddr = &ipv6_hdr(skb)->daddr; @@ -939,7 +943,7 @@ static int icmpv6_rcv(struct sk_buff *skb) type = hdr->icmp6_type; - ICMP6MSGIN_INC_STATS(dev_net(dev), idev, type); + ICMP6MSGIN_INC_STATS(dev_net_rcu(dev), idev, type); switch (type) { case ICMPV6_ECHO_REQUEST: @@ -1034,9 +1038,9 @@ static int icmpv6_rcv(struct sk_buff *skb) csum_error: reason = SKB_DROP_REASON_ICMP_CSUM; - __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS); + __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_CSUMERRORS); discard_it: - __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS); + __ICMP6_INC_STATS(dev_net_rcu(dev), idev, ICMP6_MIB_INERRORS); drop_no_count: kfree_skb_reason(skb, reason); return 0; diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 28e5a89dc255..2c383c12a431 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -336,7 +336,7 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb, static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb), *cache_dst; + struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL; struct in6_addr orig_daddr; struct ioam6_lwt *ilwt; int err = -EINVAL; @@ -407,13 +407,15 @@ do_encap: cache_dst = ip6_route_output(net, NULL, &fl6); if (cache_dst->error) { err = cache_dst->error; - dst_release(cache_dst); goto drop; } - local_bh_disable(); - dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr); - local_bh_enable(); + /* cache only if we don't create a dst reference loop */ + if (dst->lwtstate != cache_dst->lwtstate) { + local_bh_disable(); + dst_cache_set_ip6(&ilwt->cache, cache_dst, &fl6.saddr); + local_bh_enable(); + } err = skb_cow_head(skb, LL_RESERVED_SPACE(cache_dst->dev)); if (unlikely(err)) @@ -426,8 +428,10 @@ do_encap: return dst_output(net, sk, skb); } out: + dst_release(cache_dst); return dst->lwtstate->orig_output(net, sk, skb); drop: + dst_release(cache_dst); kfree_skb(skb); return err; } diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 70c0e16c0ae6..39da6a7ce5f1 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -477,9 +477,7 @@ discard: static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_clear_delivery_time(skb); - rcu_read_lock(); ip6_protocol_deliver_rcu(net, skb, 0, false); - rcu_read_unlock(); return 0; } @@ -487,9 +485,15 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk int ip6_input(struct sk_buff *skb) { - return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, - dev_net(skb->dev), NULL, skb, skb->dev, NULL, - ip6_input_finish); + int res; + + rcu_read_lock(); + res = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, + dev_net_rcu(skb->dev), NULL, skb, skb->dev, NULL, + ip6_input_finish); + rcu_read_unlock(); + + return res; } EXPORT_SYMBOL_GPL(ip6_input); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 9dfdb40988b0..65831b4fee1f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1773,21 +1773,19 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) struct net_device *dev = idev->dev; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - struct net *net = dev_net(dev); const struct in6_addr *saddr; struct in6_addr addr_buf; struct mld2_report *pmr; struct sk_buff *skb; unsigned int size; struct sock *sk; - int err; + struct net *net; - sk = net->ipv6.igmp_sk; /* we assume size > sizeof(ra) here * Also try to not allocate high-order pages for big MTU */ size = min_t(int, mtu, PAGE_SIZE / 2) + hlen + tlen; - skb = sock_alloc_send_skb(sk, size, 1, &err); + skb = alloc_skb(size, GFP_KERNEL); if (!skb) return NULL; @@ -1795,6 +1793,12 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); + rcu_read_lock(); + + net = dev_net_rcu(dev); + sk = net->ipv6.igmp_sk; + skb_set_owner_w(skb, sk); + if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: * use unspecified address as the source address @@ -1806,6 +1810,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) ip6_mc_hdr(sk, skb, dev, saddr, &mld2_all_mcr, NEXTHDR_HOP, 0); + rcu_read_unlock(); + skb_put_data(skb, ra, sizeof(ra)); skb_set_transport_header(skb, skb_tail_pointer(skb) - skb->data); @@ -2165,21 +2171,21 @@ static void mld_send_cr(struct inet6_dev *idev) static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) { - struct net *net = dev_net(dev); - struct sock *sk = net->ipv6.igmp_sk; + const struct in6_addr *snd_addr, *saddr; + int err, len, payload_len, full_len; + struct in6_addr addr_buf; struct inet6_dev *idev; struct sk_buff *skb; struct mld_msg *hdr; - const struct in6_addr *snd_addr, *saddr; - struct in6_addr addr_buf; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - int err, len, payload_len, full_len; u8 ra[8] = { IPPROTO_ICMPV6, 0, IPV6_TLV_ROUTERALERT, 2, 0, 0, IPV6_TLV_PADN, 0 }; - struct flowi6 fl6; struct dst_entry *dst; + struct flowi6 fl6; + struct net *net; + struct sock *sk; if (type == ICMPV6_MGM_REDUCTION) snd_addr = &in6addr_linklocal_allrouters; @@ -2190,19 +2196,21 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) payload_len = len + sizeof(ra); full_len = sizeof(struct ipv6hdr) + payload_len; - rcu_read_lock(); - IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); - rcu_read_unlock(); + skb = alloc_skb(hlen + tlen + full_len, GFP_KERNEL); - skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); + rcu_read_lock(); + net = dev_net_rcu(dev); + idev = __in6_dev_get(dev); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); if (!skb) { - rcu_read_lock(); - IP6_INC_STATS(net, __in6_dev_get(dev), - IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); return; } + sk = net->ipv6.igmp_sk; + skb_set_owner_w(skb, sk); + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); @@ -2227,9 +2235,6 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) IPPROTO_ICMPV6, csum_partial(hdr, len, 0)); - rcu_read_lock(); - idev = __in6_dev_get(skb->dev); - icmpv6_flow_init(sk, &fl6, type, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->dev->ifindex); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index d044c67019de..8699d1a188dc 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -418,15 +418,11 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, { int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; - struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); - if (!skb) { - ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", - __func__); + if (!skb) return NULL; - } skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -437,7 +433,9 @@ static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, /* Manually assign socket ownership as we avoid calling * sock_alloc_send_pskb() to bypass wmem buffer limits */ - skb_set_owner_w(skb, sk); + rcu_read_lock(); + skb_set_owner_w(skb, dev_net_rcu(dev)->ipv6.ndisc_sk); + rcu_read_unlock(); return skb; } @@ -473,16 +471,20 @@ static void ip6_nd_hdr(struct sk_buff *skb, void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr) { + struct icmp6hdr *icmp6h = icmp6_hdr(skb); struct dst_entry *dst = skb_dst(skb); - struct net *net = dev_net(skb->dev); - struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; + struct net *net; + struct sock *sk; int err; - struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; + rcu_read_lock(); + + net = dev_net_rcu(skb->dev); + sk = net->ipv6.ndisc_sk; if (!dst) { struct flowi6 fl6; int oif = skb->dev->ifindex; @@ -490,6 +492,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { + rcu_read_unlock(); kfree_skb(skb); return; } @@ -504,7 +507,6 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, ip6_nd_hdr(skb, saddr, daddr, READ_ONCE(inet6_sk(sk)->hop_limit), skb->len); - rcu_read_lock(); idev = __in6_dev_get(dst->dev); IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); @@ -1694,7 +1696,7 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) bool ret; if (netif_is_l3_master(skb->dev)) { - dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); + dev = dev_get_by_index_rcu(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) return; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 78362822b907..ef2d23a1e3d5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -3196,13 +3196,18 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) { struct net_device *dev = dst->dev; unsigned int mtu = dst_mtu(dst); - struct net *net = dev_net(dev); + struct net *net; mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); + rcu_read_lock(); + + net = dev_net_rcu(dev); if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) mtu = net->ipv6.sysctl.ip6_rt_min_advmss; + rcu_read_unlock(); + /* * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 7ba22d2f2bfe..0ac4283acdf2 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -232,13 +232,15 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { err = dst->error; - dst_release(dst); goto drop; } - local_bh_disable(); - dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr); - local_bh_enable(); + /* cache only if we don't create a dst reference loop */ + if (orig_dst->lwtstate != dst->lwtstate) { + local_bh_disable(); + dst_cache_set_ip6(&rlwt->cache, dst, &fl6.saddr); + local_bh_enable(); + } err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) @@ -251,6 +253,7 @@ static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb) return dst_output(net, sk, skb); drop: + dst_release(dst); kfree_skb(skb); return err; } @@ -269,8 +272,10 @@ static int rpl_input(struct sk_buff *skb) local_bh_enable(); err = rpl_do_srh(skb, rlwt, dst); - if (unlikely(err)) + if (unlikely(err)) { + dst_release(dst); goto drop; + } if (!dst) { ip6_route_input(skb); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 4bf937bfc263..33833b2064c0 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -482,8 +482,10 @@ static int seg6_input_core(struct net *net, struct sock *sk, local_bh_enable(); err = seg6_do_srh(skb, dst); - if (unlikely(err)) + if (unlikely(err)) { + dst_release(dst); goto drop; + } if (!dst) { ip6_route_input(skb); @@ -571,13 +573,15 @@ static int seg6_output_core(struct net *net, struct sock *sk, dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { err = dst->error; - dst_release(dst); goto drop; } - local_bh_disable(); - dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); - local_bh_enable(); + /* cache only if we don't create a dst reference loop */ + if (orig_dst->lwtstate != dst->lwtstate) { + local_bh_disable(); + dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr); + local_bh_enable(); + } err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) @@ -593,6 +597,7 @@ static int seg6_output_core(struct net *net, struct sock *sk, return dst_output(net, sk, skb); drop: + dst_release(dst); kfree_skb(skb); return err; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6671daa67f4f..c6ea438b5c75 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1389,9 +1389,9 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, const int hlen = skb_network_header_len(skb) + sizeof(struct udphdr); - if (hlen + cork->gso_size > cork->fragsize) { + if (hlen + min(datalen, cork->gso_size) > cork->fragsize) { kfree_skb(skb); - return -EINVAL; + return -EMSGSIZE; } if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 5f7b1fdbffe6..b3d5d1f266ee 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -82,14 +82,14 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) toobig = skb->len > mtu && !skb_is_gso(skb); - if (toobig && xfrm6_local_dontfrag(skb->sk)) { + if (toobig && xfrm6_local_dontfrag(sk)) { xfrm6_local_rxpmtu(skb, mtu); kfree_skb(skb); return -EMSGSIZE; } else if (toobig && xfrm6_noneed_fragment(skb)) { skb->ignore_df = 1; goto skip_frag; - } else if (!skb->ignore_df && toobig && skb->sk) { + } else if (!skb->ignore_df && toobig && sk) { xfrm_local_error(skb, mtu); kfree_skb(skb); return -EMSGSIZE; diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 3999e0ba2c35..2dd81e6c26bd 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -418,9 +418,9 @@ void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP); subflow->mpc_drop = 1; mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); - } else { - subflow->mpc_drop = 0; } + } else if (ssk->sk_state == TCP_SYN_SENT) { + subflow->mpc_drop = 0; } } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 123f3f297284..fd2de185bc93 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -108,7 +108,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, mp_opt->suboptions |= OPTION_MPTCP_DSS; mp_opt->use_map = 1; mp_opt->mpc_map = 1; - mp_opt->use_ack = 0; mp_opt->data_len = get_unaligned_be16(ptr); ptr += 2; } @@ -157,11 +156,6 @@ static void mptcp_parse_option(const struct sk_buff *skb, pr_debug("DSS\n"); ptr++; - /* we must clear 'mpc_map' be able to detect MP_CAPABLE - * map vs DSS map in mptcp_incoming_options(), and reconstruct - * map info accordingly - */ - mp_opt->mpc_map = 0; flags = (*ptr++) & MPTCP_DSS_FLAG_MASK; mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0; mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0; @@ -369,8 +363,11 @@ void mptcp_get_options(const struct sk_buff *skb, const unsigned char *ptr; int length; - /* initialize option status */ - mp_opt->suboptions = 0; + /* Ensure that casting the whole status to u32 is efficient and safe */ + BUILD_BUG_ON(sizeof_field(struct mptcp_options_received, status) != sizeof(u32)); + BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct mptcp_options_received, status), + sizeof(u32))); + *(u32 *)&mp_opt->status = 0; length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 98ac73938bd8..572d160edca3 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -2020,7 +2020,8 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info) return -EINVAL; } if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && - (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | + MPTCP_PM_ADDR_FLAG_IMPLICIT))) { spin_unlock_bh(&pernet->lock); GENL_SET_ERR_MSG(info, "invalid addr flags"); return -EINVAL; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c44c89ecaca6..6bd819047470 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1767,8 +1767,10 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, * see mptcp_disconnect(). * Attempt it again outside the problematic scope. */ - if (!mptcp_disconnect(sk, 0)) + if (!mptcp_disconnect(sk, 0)) { + sk->sk_disconnects++; sk->sk_socket->state = SS_UNCONNECTED; + } } inet_clear_bit(DEFER_CONNECT, sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 0174a5aad279..f6a207958459 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -149,22 +149,24 @@ struct mptcp_options_received { u32 subflow_seq; u16 data_len; __sum16 csum; - u16 suboptions; + struct_group(status, + u16 suboptions; + u16 use_map:1, + dsn64:1, + data_fin:1, + use_ack:1, + ack64:1, + mpc_map:1, + reset_reason:4, + reset_transient:1, + echo:1, + backup:1, + deny_join_id0:1, + __unused:2; + ); + u8 join_id; u32 token; u32 nonce; - u16 use_map:1, - dsn64:1, - data_fin:1, - use_ack:1, - ack64:1, - mpc_map:1, - reset_reason:4, - reset_transient:1, - echo:1, - backup:1, - deny_join_id0:1, - __unused:2; - u8 join_id; u64 thmac; u8 hmac[MPTCPOPT_HMAC_LEN]; struct mptcp_addr_info addr; diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index bf276eaf9330..7891a537bddd 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1385,6 +1385,12 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) nd->state = ncsi_dev_state_probe_package; break; case ncsi_dev_state_probe_package: + if (ndp->package_probe_id >= 8) { + /* Last package probed, finishing */ + ndp->flags |= NCSI_DEV_PROBED; + break; + } + ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_SP; @@ -1501,13 +1507,8 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) if (ret) goto error; - /* Probe next package */ + /* Probe next package after receiving response */ ndp->package_probe_id++; - if (ndp->package_probe_id >= 8) { - /* Probe finished */ - ndp->flags |= NCSI_DEV_PROBED; - break; - } nd->state = ncsi_dev_state_probe_package; ndp->active_package = NULL; break; diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index 14bd66909ca4..4a8ce2949fae 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -1089,14 +1089,12 @@ static int ncsi_rsp_handler_netlink(struct ncsi_request *nr) static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr) { struct ncsi_dev_priv *ndp = nr->ndp; + struct sockaddr *saddr = &ndp->pending_mac; struct net_device *ndev = ndp->ndev.dev; struct ncsi_rsp_gmcma_pkt *rsp; - struct sockaddr saddr; - int ret = -1; int i; rsp = (struct ncsi_rsp_gmcma_pkt *)skb_network_header(nr->rsp); - saddr.sa_family = ndev->type; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netdev_info(ndev, "NCSI: Received %d provisioned MAC addresses\n", @@ -1108,20 +1106,20 @@ static int ncsi_rsp_handler_gmcma(struct ncsi_request *nr) rsp->addresses[i][4], rsp->addresses[i][5]); } + saddr->sa_family = ndev->type; for (i = 0; i < rsp->address_count; i++) { - memcpy(saddr.sa_data, &rsp->addresses[i], ETH_ALEN); - ret = ndev->netdev_ops->ndo_set_mac_address(ndev, &saddr); - if (ret < 0) { + if (!is_valid_ether_addr(rsp->addresses[i])) { netdev_warn(ndev, "NCSI: Unable to assign %pM to device\n", - saddr.sa_data); + rsp->addresses[i]); continue; } - netdev_warn(ndev, "NCSI: Set MAC address to %pM\n", saddr.sa_data); + memcpy(saddr->sa_data, rsp->addresses[i], ETH_ALEN); + netdev_warn(ndev, "NCSI: Will set MAC address to %pM\n", saddr->sa_data); break; } - ndp->gma_flag = ret == 0; - return ret; + ndp->gma_flag = 1; + return 0; } static struct ncsi_rsp_handler { diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 97c6eb8847a0..8cd4cf7ae211 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -381,10 +381,8 @@ static int nf_flow_offload_forward(struct nf_flowtable_ctx *ctx, flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset; - if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) { - flow_offload_teardown(flow); + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) return 0; - } iph = (struct iphdr *)(skb_network_header(skb) + ctx->offset); thoff = (iph->ihl * 4) + ctx->offset; @@ -662,10 +660,8 @@ static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx, flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset; - if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) { - flow_offload_teardown(flow); + if (unlikely(nf_flow_exceeds_mtu(skb, mtu))) return 0; - } ip6h = (struct ipv6hdr *)(skb_network_header(skb) + ctx->offset); thoff = sizeof(*ip6h) + ctx->offset; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 667459256e4c..a34de9c17cf1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5078,7 +5078,7 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { - u32 num_regs = 0, key_num_regs = 0; + u32 len = 0, num_regs; struct nlattr *attr; int rem, err, i; @@ -5092,12 +5092,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, } for (i = 0; i < desc->field_count; i++) - num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + len += round_up(desc->field_len[i], sizeof(u32)); - key_num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); - if (key_num_regs != num_regs) + if (len != desc->klen) return -EINVAL; + num_regs = DIV_ROUND_UP(desc->klen, sizeof(u32)); if (num_regs > NFT_REG32_COUNT) return -E2BIG; diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c index de175318a3a0..082ab66f120b 100644 --- a/net/nfc/nci/hci.c +++ b/net/nfc/nci/hci.c @@ -542,6 +542,8 @@ static u8 nci_hci_create_pipe(struct nci_dev *ndev, u8 dest_host, pr_debug("pipe created=%d\n", pipe); + if (pipe >= NCI_HCI_MAX_PIPES) + pipe = NCI_HCI_INVALID_PIPE; return pipe; } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 225f6048867f..5d548eda742d 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2101,6 +2101,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; + struct net *net_vport; int err; ovs_header = genlmsg_put(skb, portid, seq, &dp_vport_genl_family, @@ -2117,12 +2118,15 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, nla_put_u32(skb, OVS_VPORT_ATTR_IFINDEX, vport->dev->ifindex)) goto nla_put_failure; - if (!net_eq(net, dev_net(vport->dev))) { - int id = peernet2id_alloc(net, dev_net(vport->dev), gfp); + rcu_read_lock(); + net_vport = dev_net_rcu(vport->dev); + if (!net_eq(net, net_vport)) { + int id = peernet2id_alloc(net, net_vport, GFP_ATOMIC); if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) - goto nla_put_failure; + goto nla_put_failure_unlock; } + rcu_read_unlock(); ovs_vport_get_stats(vport, &vport_stats); if (nla_put_64bit(skb, OVS_VPORT_ATTR_STATS, @@ -2143,6 +2147,8 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, genlmsg_end(skb, ovs_header); return 0; +nla_put_failure_unlock: + rcu_read_unlock(); nla_put_failure: err = -EMSGSIZE; error: diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 72c65d938a15..a4a668b88a8f 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -701,11 +701,9 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct net_device *dev; ax25_address *source; ax25_uid_assoc *user; + int err = -EINVAL; int n; - if (!sock_flag(sk, SOCK_ZAPPED)) - return -EINVAL; - if (addr_len != sizeof(struct sockaddr_rose) && addr_len != sizeof(struct full_sockaddr_rose)) return -EINVAL; @@ -718,8 +716,15 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if ((unsigned int) addr->srose_ndigis > ROSE_MAX_DIGIS) return -EINVAL; - if ((dev = rose_dev_get(&addr->srose_addr)) == NULL) - return -EADDRNOTAVAIL; + lock_sock(sk); + + if (!sock_flag(sk, SOCK_ZAPPED)) + goto out_release; + + err = -EADDRNOTAVAIL; + dev = rose_dev_get(&addr->srose_addr); + if (!dev) + goto out_release; source = &addr->srose_call; @@ -730,7 +735,8 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } else { if (ax25_uid_policy && !capable(CAP_NET_BIND_SERVICE)) { dev_put(dev); - return -EACCES; + err = -EACCES; + goto out_release; } rose->source_call = *source; } @@ -753,8 +759,10 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) rose_insert_socket(sk); sock_reset_flag(sk, SOCK_ZAPPED); - - return 0; + err = 0; +out_release: + release_sock(sk); + return err; } static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index f06ddbed3fed..1525773e94aa 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -122,6 +122,10 @@ static void rose_heartbeat_expiry(struct timer_list *t) struct rose_sock *rose = rose_sk(sk); bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ/20); + goto out; + } switch (rose->state) { case ROSE_STATE_0: /* Magic here: If we listen() and a new link dies before it @@ -152,6 +156,7 @@ static void rose_heartbeat_expiry(struct timer_list *t) } rose_start_heartbeat(sk); +out: bh_unlock_sock(sk); sock_put(sk); } @@ -162,6 +167,10 @@ static void rose_timer_expiry(struct timer_list *t) struct sock *sk = &rose->sock; bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &rose->timer, jiffies + HZ/20); + goto out; + } switch (rose->state) { case ROSE_STATE_1: /* T1 */ case ROSE_STATE_4: /* T2 */ @@ -182,6 +191,7 @@ static void rose_timer_expiry(struct timer_list *t) } break; } +out: bh_unlock_sock(sk); sock_put(sk); } @@ -192,6 +202,10 @@ static void rose_idletimer_expiry(struct timer_list *t) struct sock *sk = &rose->sock; bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + sk_reset_timer(sk, &rose->idletimer, jiffies + HZ/20); + goto out; + } rose_clear_queues(sk); rose_write_internal(sk, ROSE_CLEAR_REQUEST); @@ -207,6 +221,7 @@ static void rose_idletimer_expiry(struct timer_list *t) sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } +out: bh_unlock_sock(sk); sock_put(sk); } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 718193df9d2e..5e740c486203 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -327,8 +327,8 @@ struct rxrpc_local { * packet with a maximum set of jumbo subpackets or a PING ACK padded * out to 64K with zeropages for PMTUD. */ - struct kvec kvec[RXRPC_MAX_NR_JUMBO > 3 + 16 ? - RXRPC_MAX_NR_JUMBO : 3 + 16]; + struct kvec kvec[1 + RXRPC_MAX_NR_JUMBO > 3 + 16 ? + 1 + RXRPC_MAX_NR_JUMBO : 3 + 16]; }; /* @@ -582,6 +582,7 @@ enum rxrpc_call_flag { RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */ RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */ + RXRPC_CALL_CONN_CHALLENGING, /* The connection is being challenged */ }; /* @@ -602,7 +603,6 @@ enum rxrpc_call_state { RXRPC_CALL_CLIENT_AWAIT_REPLY, /* - client awaiting reply */ RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */ - RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */ RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ @@ -874,8 +874,7 @@ struct rxrpc_txbuf { #define RXRPC_TXBUF_RESENT 0x100 /* Set if has been resent */ __be16 cksum; /* Checksum to go in header */ bool jumboable; /* Can be non-terminal jumbo subpacket */ - u8 nr_kvec; /* Amount of kvec[] used */ - struct kvec kvec[1]; + void *data; /* Data with preceding jumbo header */ }; static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 5a543c3f6fb0..c4c8b46a68c6 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -22,7 +22,6 @@ const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { [RXRPC_CALL_CLIENT_AWAIT_REPLY] = "ClAwtRpl", [RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl", [RXRPC_CALL_SERVER_PREALLOC] = "SvPrealc", - [RXRPC_CALL_SERVER_SECURING] = "SvSecure", [RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq", [RXRPC_CALL_SERVER_ACK_REQUEST] = "SvAckReq", [RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl", @@ -453,17 +452,16 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->cong_tstamp = skb->tstamp; __set_bit(RXRPC_CALL_EXPOSED, &call->flags); - rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING); + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST); spin_lock(&conn->state_lock); switch (conn->state) { case RXRPC_CONN_SERVICE_UNSECURED: case RXRPC_CONN_SERVICE_CHALLENGING: - rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING); + __set_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags); break; case RXRPC_CONN_SERVICE: - rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST); break; case RXRPC_CONN_ABORTED: diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 713e04394ceb..4d9c5e21ba78 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -228,10 +228,8 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn) */ static void rxrpc_call_is_secure(struct rxrpc_call *call) { - if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) { - rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST); + if (call && __test_and_clear_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags)) rxrpc_notify_socket(call); - } } /* @@ -272,6 +270,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, * we've already received the packet, put it on the * front of the queue. */ + sp->conn = rxrpc_get_connection(conn, rxrpc_conn_get_poke_secured); skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED; rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured); skb_queue_head(&conn->local->rx_queue, skb); @@ -437,14 +436,16 @@ void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events)) rxrpc_abort_calls(conn); - switch (skb->mark) { - case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: - if (conn->state != RXRPC_CONN_SERVICE) - break; + if (skb) { + switch (skb->mark) { + case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: + if (conn->state != RXRPC_CONN_SERVICE) + break; - for (loop = 0; loop < RXRPC_MAXCALLS; loop++) - rxrpc_call_is_secure(conn->channels[loop].call); - break; + for (loop = 0; loop < RXRPC_MAXCALLS; loop++) + rxrpc_call_is_secure(conn->channels[loop].call); + break; + } } /* Process delayed ACKs whose time has come. */ diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 7eba4d7d9a38..2f1fd1e2e7e4 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -67,6 +67,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, INIT_WORK(&conn->destructor, rxrpc_clean_up_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); + INIT_LIST_HEAD(&conn->attend_link); mutex_init(&conn->security_lock); mutex_init(&conn->tx_data_alloc_lock); skb_queue_head_init(&conn->rx_queue); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 4974b5accafa..9047ba13bd31 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -448,11 +448,19 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); bool last = sp->hdr.flags & RXRPC_LAST_PACKET; - skb_queue_tail(&call->recvmsg_queue, skb); + spin_lock_irq(&call->recvmsg_queue.lock); + + __skb_queue_tail(&call->recvmsg_queue, skb); rxrpc_input_update_ack_window(call, window, wtop); trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); if (last) + /* Change the state inside the lock so that recvmsg syncs + * correctly with it and using sendmsg() to send a reply + * doesn't race. + */ rxrpc_end_rx_phase(call, sp->hdr.serial); + + spin_unlock_irq(&call->recvmsg_queue.lock); } /* @@ -657,7 +665,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb rxrpc_propose_delay_ACK(call, sp->hdr.serial, rxrpc_propose_ack_input_data); } - if (notify) { + if (notify && !test_bit(RXRPC_CALL_CONN_CHALLENGING, &call->flags)) { trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial); rxrpc_notify_socket(call); } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 6f7a125d6e90..95905b85a8d7 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -428,13 +428,13 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) static size_t rxrpc_prepare_data_subpacket(struct rxrpc_call *call, struct rxrpc_send_data_req *req, struct rxrpc_txbuf *txb, + struct rxrpc_wire_header *whdr, rxrpc_serial_t serial, int subpkt) { - struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; - struct rxrpc_jumbo_header *jumbo = (void *)(whdr + 1) - sizeof(*jumbo); + struct rxrpc_jumbo_header *jumbo = txb->data - sizeof(*jumbo); enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct kvec *kv = &call->local->kvec[subpkt]; + struct kvec *kv = &call->local->kvec[1 + subpkt]; size_t len = txb->pkt_len; bool last; u8 flags; @@ -491,18 +491,15 @@ static size_t rxrpc_prepare_data_subpacket(struct rxrpc_call *call, } dont_set_request_ack: - /* The jumbo header overlays the wire header in the txbuf. */ + /* There's a jumbo header prepended to the data if we need it. */ if (subpkt < req->n - 1) flags |= RXRPC_JUMBO_PACKET; else flags &= ~RXRPC_JUMBO_PACKET; if (subpkt == 0) { whdr->flags = flags; - whdr->serial = htonl(txb->serial); whdr->cksum = txb->cksum; - whdr->serviceId = htons(conn->service_id); - kv->iov_base = whdr; - len += sizeof(*whdr); + kv->iov_base = txb->data; } else { jumbo->flags = flags; jumbo->pad = 0; @@ -535,7 +532,9 @@ static unsigned int rxrpc_prepare_txqueue(struct rxrpc_txqueue *tq, /* * Prepare a (jumbo) packet for transmission. */ -static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req *req) +static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, + struct rxrpc_send_data_req *req, + struct rxrpc_wire_header *whdr) { struct rxrpc_txqueue *tq = req->tq; rxrpc_serial_t serial; @@ -549,6 +548,18 @@ static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_se /* Each transmission of a Tx packet needs a new serial number */ serial = rxrpc_get_next_serials(call->conn, req->n); + whdr->epoch = htonl(call->conn->proto.epoch); + whdr->cid = htonl(call->cid); + whdr->callNumber = htonl(call->call_id); + whdr->seq = htonl(seq); + whdr->serial = htonl(serial); + whdr->type = RXRPC_PACKET_TYPE_DATA; + whdr->flags = 0; + whdr->userStatus = 0; + whdr->securityIndex = call->security_ix; + whdr->_rsvd = 0; + whdr->serviceId = htons(call->conn->service_id); + call->tx_last_serial = serial + req->n - 1; call->tx_last_sent = req->now; xmit_ts = rxrpc_prepare_txqueue(tq, req); @@ -576,7 +587,7 @@ static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_se if (i + 1 == req->n) /* Only sample the last subpacket in a jumbo. */ __set_bit(ix, &tq->rtt_samples); - len += rxrpc_prepare_data_subpacket(call, req, txb, serial, i); + len += rxrpc_prepare_data_subpacket(call, req, txb, whdr, serial, i); serial++; seq++; i++; @@ -618,6 +629,7 @@ static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_se } rxrpc_set_keepalive(call, req->now); + page_frag_free(whdr); return len; } @@ -626,25 +638,33 @@ static size_t rxrpc_prepare_data_packet(struct rxrpc_call *call, struct rxrpc_se */ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req *req) { + struct rxrpc_wire_header *whdr; struct rxrpc_connection *conn = call->conn; enum rxrpc_tx_point frag; struct rxrpc_txqueue *tq = req->tq; struct rxrpc_txbuf *txb; struct msghdr msg; rxrpc_seq_t seq = req->seq; - size_t len; + size_t len = sizeof(*whdr); bool new_call = test_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags); int ret, stat_ix; _enter("%x,%x-%x", tq->qbase, seq, seq + req->n - 1); + whdr = page_frag_alloc(&call->local->tx_alloc, sizeof(*whdr), GFP_NOFS); + if (!whdr) + return; /* Drop the packet if no memory. */ + + call->local->kvec[0].iov_base = whdr; + call->local->kvec[0].iov_len = sizeof(*whdr); + stat_ix = umin(req->n, ARRAY_SIZE(call->rxnet->stat_tx_jumbo)) - 1; atomic_inc(&call->rxnet->stat_tx_jumbo[stat_ix]); - len = rxrpc_prepare_data_packet(call, req); + len += rxrpc_prepare_data_packet(call, req, whdr); txb = tq->bufs[seq & RXRPC_TXQ_MASK]; - iov_iter_kvec(&msg.msg_iter, WRITE, call->local->kvec, req->n, len); + iov_iter_kvec(&msg.msg_iter, WRITE, call->local->kvec, 1 + req->n, len); msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; @@ -695,13 +715,13 @@ void rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_send_data_req if (ret == -EMSGSIZE) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_msgsize); - trace_rxrpc_tx_packet(call->debug_id, call->local->kvec[0].iov_base, frag); + trace_rxrpc_tx_packet(call->debug_id, whdr, frag); ret = 0; } else if (ret < 0) { rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); trace_rxrpc_tx_fail(call->debug_id, txb->serial, ret, frag); } else { - trace_rxrpc_tx_packet(call->debug_id, call->local->kvec[0].iov_base, frag); + trace_rxrpc_tx_packet(call->debug_id, whdr, frag); } rxrpc_tx_backoff(call, ret); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index d82e44a3901b..bc283da9ee40 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -169,6 +169,13 @@ void rxrpc_input_error(struct rxrpc_local *local, struct sk_buff *skb) goto out; } + if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP6 && + serr->ee.ee_type == ICMPV6_PKT_TOOBIG && + serr->ee.ee_code == 0)) { + rxrpc_adjust_mtu(peer, serr->ee.ee_info); + goto out; + } + rxrpc_store_error(peer, skb); out: rxrpc_put_peer(peer, rxrpc_peer_put_input_error); @@ -246,7 +253,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, bool use; int slot; - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); while (!list_empty(collector)) { peer = list_entry(collector->next, @@ -257,7 +264,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, continue; use = __rxrpc_use_local(peer->local, rxrpc_local_use_peer_keepalive); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); if (use) { keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; @@ -277,17 +284,17 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, */ slot += cursor; slot &= mask; - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); rxrpc_unuse_local(peer->local, rxrpc_local_unuse_peer_keepalive); } rxrpc_put_peer(peer, rxrpc_peer_put_keepalive); - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); } - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); } /* @@ -317,7 +324,7 @@ void rxrpc_peer_keepalive_worker(struct work_struct *work) * second; the bucket at cursor + 1 goes at now + 1s and so * on... */ - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); list_splice_init(&rxnet->peer_keepalive_new, &collector); stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive); @@ -329,7 +336,7 @@ void rxrpc_peer_keepalive_worker(struct work_struct *work) } base = now; - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); rxnet->peer_keepalive_base = base; rxnet->peer_keepalive_cursor = cursor; diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index e1c63129586b..0fcc87f0409f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -325,10 +325,10 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) hash_key = rxrpc_peer_hash_key(local, &peer->srx); rxrpc_init_peer(local, peer, hash_key); - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); } /* @@ -360,7 +360,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, return NULL; } - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); @@ -373,7 +373,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, &rxnet->peer_keepalive_new); } - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); if (peer) rxrpc_free_peer(candidate); @@ -423,10 +423,10 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) ASSERT(hlist_empty(&peer->error_targets)); - spin_lock(&rxnet->peer_hash_lock); + spin_lock_bh(&rxnet->peer_hash_lock); hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); - spin_unlock(&rxnet->peer_hash_lock); + spin_unlock_bh(&rxnet->peer_hash_lock); rxrpc_free_peer(peer); } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 62b09d23ec08..6cb37b0eb77f 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -257,8 +257,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; - struct rxkad_level1_hdr *hdr = (void *)(whdr + 1); + struct rxkad_level1_hdr *hdr = txb->data; struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -274,7 +273,7 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; if (pad) { - memset(txb->kvec[0].iov_base + txb->offset, 0, pad); + memset(txb->data + txb->offset, 0, pad); txb->pkt_len += pad; } @@ -300,8 +299,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; - struct rxkad_level2_hdr *rxkhdr = (void *)(whdr + 1); + struct rxkad_level2_hdr *rxkhdr = txb->data; struct rxrpc_crypt iv; struct scatterlist sg; size_t content, pad; @@ -319,7 +317,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, txb->pkt_len = round_up(content, RXKAD_ALIGN); pad = txb->pkt_len - content; if (pad) - memset(txb->kvec[0].iov_base + txb->offset, 0, pad); + memset(txb->data + txb->offset, 0, pad); /* encrypt from the session key */ token = call->conn->key->payload.data[0]; @@ -407,9 +405,8 @@ static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) /* Clear excess space in the packet */ if (txb->pkt_len < txb->alloc_size) { - struct rxrpc_wire_header *whdr = txb->kvec[0].iov_base; size_t gap = txb->alloc_size - txb->pkt_len; - void *p = whdr + 1; + void *p = txb->data; memset(p + txb->pkt_len, 0, gap); } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 0e8da909d4f2..84dc6c94f23b 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -419,7 +419,7 @@ reload: size_t copy = umin(txb->space, msg_data_left(msg)); _debug("add %zu", copy); - if (!copy_from_iter_full(txb->kvec[0].iov_base + txb->offset, + if (!copy_from_iter_full(txb->data + txb->offset, copy, &msg->msg_iter)) goto efault; _debug("added"); @@ -445,8 +445,6 @@ reload: ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; - - txb->kvec[0].iov_len += txb->len; rxrpc_queue_packet(rx, call, txb, notify_end_tx); txb = NULL; } @@ -707,7 +705,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) } else { switch (rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_AWAIT_CONN: - case RXRPC_CALL_SERVER_SECURING: + case RXRPC_CALL_SERVER_RECV_REQUEST: if (p.command == RXRPC_CMD_SEND_ABORT) break; fallthrough; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 131d9e55c8e9..c550991d48fa 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -19,17 +19,19 @@ atomic_t rxrpc_nr_txbuf; struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_size, size_t data_align, gfp_t gfp) { - struct rxrpc_wire_header *whdr; struct rxrpc_txbuf *txb; - size_t total, hoff; + size_t total, doff, jsize = sizeof(struct rxrpc_jumbo_header); void *buf; txb = kzalloc(sizeof(*txb), gfp); if (!txb) return NULL; - hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr); - total = hoff + sizeof(*whdr) + data_size; + /* We put a jumbo header in the buffer, but not a full wire header to + * avoid delayed-corruption problems with zerocopy. + */ + doff = round_up(jsize, data_align); + total = doff + data_size; data_align = umax(data_align, L1_CACHE_BYTES); mutex_lock(&call->conn->tx_data_alloc_lock); @@ -41,30 +43,15 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_ return NULL; } - whdr = buf + hoff; - refcount_set(&txb->ref, 1); txb->call_debug_id = call->debug_id; txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); txb->alloc_size = data_size; txb->space = data_size; - txb->offset = sizeof(*whdr); + txb->offset = 0; txb->flags = call->conn->out_clientflag; txb->seq = call->send_top + 1; - txb->nr_kvec = 1; - txb->kvec[0].iov_base = whdr; - txb->kvec[0].iov_len = sizeof(*whdr); - - whdr->epoch = htonl(call->conn->proto.epoch); - whdr->cid = htonl(call->cid); - whdr->callNumber = htonl(call->call_id); - whdr->seq = htonl(txb->seq); - whdr->type = RXRPC_PACKET_TYPE_DATA; - whdr->flags = 0; - whdr->userStatus = 0; - whdr->securityIndex = call->security_ix; - whdr->_rsvd = 0; - whdr->serviceId = htons(call->dest_srx.srx_service); + txb->data = buf + doff; trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, rxrpc_txbuf_alloc_data); @@ -90,14 +77,10 @@ void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) static void rxrpc_free_txbuf(struct rxrpc_txbuf *txb) { - int i; - trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, rxrpc_txbuf_free); - for (i = 0; i < txb->nr_kvec; i++) - if (txb->kvec[i].iov_base && - !is_zero_pfn(page_to_pfn(virt_to_page(txb->kvec[i].iov_base)))) - page_frag_free(txb->kvec[i].iov_base); + if (txb->data) + page_frag_free(txb->data); kfree(txb); atomic_dec(&rxrpc_nr_txbuf); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8e47e5355be6..4f648af8cfaa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -97,7 +97,7 @@ tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, err = xa_alloc_cyclic(&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, n, xa_limit_32b, &next, GFP_KERNEL); - if (err) + if (err < 0) goto err_xa_alloc; exts->miss_cookie_node = n; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index f80bc05d4c5a..516038a44163 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -91,6 +91,8 @@ ets_class_from_arg(struct Qdisc *sch, unsigned long arg) { struct ets_sched *q = qdisc_priv(sch); + if (arg == 0 || arg > q->nbands) + return NULL; return &q->classes[arg - 1]; } diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index b50b2c2cc09b..e6bfd39ff339 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -40,6 +40,9 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, { unsigned int prev_backlog; + if (unlikely(READ_ONCE(sch->limit) == 0)) + return qdisc_drop(skb, sch, to_free); + if (likely(sch->q.qlen < READ_ONCE(sch->limit))) return qdisc_enqueue_tail(skb, sch); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 71ec9986ed37..fdd79d3ccd8c 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -749,9 +749,9 @@ deliver: if (err != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(err)) qdisc_qstats_drop(sch); - qdisc_tree_reduce_backlog(sch, 1, pkt_len); sch->qstats.backlog -= pkt_len; sch->q.qlen--; + qdisc_tree_reduce_backlog(sch, 1, pkt_len); } goto tfifo_dequeue; } diff --git a/net/sctp/stream.c b/net/sctp/stream.c index c241cc552e8d..bfcff6d6a438 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -735,7 +735,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * value SHOULD be the smallest TSN not acknowledged by the * receiver of the request plus 2^31. */ - init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1U << 31); sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, init_tsn, GFP_ATOMIC); diff --git a/net/socket.c b/net/socket.c index 262a28b59c7f..28bae5a94234 100644 --- a/net/socket.c +++ b/net/socket.c @@ -479,6 +479,11 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) sock->file = file; file->private_data = sock; stream_open(SOCK_INODE(sock), file); + /* + * Disable permission and pre-content events, but enable legacy + * inotify events for legacy users. + */ + file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return file; } EXPORT_SYMBOL(sock_alloc_file); diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 7ce3721c06ca..eadc00410ebc 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -630,7 +630,7 @@ static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry) static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent, const char *name) { - struct qstr q = QSTR_INIT(name, strlen(name)); + struct qstr q = QSTR(name); struct dentry *dentry = d_hash_and_lookup(parent, &q); if (!dentry) { dentry = d_alloc(parent, &q); @@ -1190,8 +1190,7 @@ static const struct rpc_filelist files[] = { struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name) { - struct qstr dir = QSTR_INIT(dir_name, strlen(dir_name)); - return d_hash_and_lookup(sb->s_root, &dir); + return d_hash_and_lookup(sb->s_root, &QSTR(dir_name)); } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); @@ -1300,11 +1299,9 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) struct dentry *gssd_dentry; struct dentry *clnt_dentry = NULL; struct dentry *pipe_dentry = NULL; - struct qstr q = QSTR_INIT(files[RPCAUTH_gssd].name, - strlen(files[RPCAUTH_gssd].name)); /* We should never get this far if "gssd" doesn't exist */ - gssd_dentry = d_hash_and_lookup(root, &q); + gssd_dentry = d_hash_and_lookup(root, &QSTR(files[RPCAUTH_gssd].name)); if (!gssd_dentry) return ERR_PTR(-ENOENT); @@ -1314,9 +1311,8 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) goto out; } - q.name = gssd_dummy_clnt_dir[0].name; - q.len = strlen(gssd_dummy_clnt_dir[0].name); - clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); + clnt_dentry = d_hash_and_lookup(gssd_dentry, + &QSTR(gssd_dummy_clnt_dir[0].name)); if (!clnt_dentry) { __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index fa9d1b49599b..7e3db87ae433 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -337,7 +337,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_socket); void vsock_remove_sock(struct vsock_sock *vsk) { - vsock_remove_bound(vsk); + /* Transport reassignment must not remove the binding. */ + if (sock_flag(sk_vsock(vsk), SOCK_DEAD)) + vsock_remove_bound(vsk); + vsock_remove_connected(vsk); } EXPORT_SYMBOL_GPL(vsock_remove_sock); @@ -821,6 +824,13 @@ static void __vsock_release(struct sock *sk, int level) */ lock_sock_nested(sk, level); + /* Indicate to vsock_remove_sock() that the socket is being released and + * can be removed from the bound_table. Unlike transport reassignment + * case, where the socket must remain bound despite vsock_remove_sock() + * being called from the transport release() callback. + */ + sock_set_flag(sk, SOCK_DEAD); + if (vsk->transport) vsk->transport->release(vsk); else if (sock_type_connectible(sk->sk_type)) @@ -1179,6 +1189,9 @@ static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor) { struct vsock_sock *vsk = vsock_sk(sk); + if (WARN_ON_ONCE(!vsk->transport)) + return -ENODEV; + return vsk->transport->read_skb(vsk, read_actor); } @@ -1519,6 +1532,11 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr, if (err < 0) goto out; + /* sk_err might have been set as a result of an earlier + * (failed) connect attempt. + */ + sk->sk_err = 0; + /* Mark sock as connecting and set the error code to in * progress in case this is a non-blocking connect. */ diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index b58c3818f284..f0e48e6911fc 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -670,6 +670,13 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) }; int ret; + mutex_lock(&vsock->rx_lock); + vsock->rx_buf_nr = 0; + vsock->rx_buf_max_nr = 0; + mutex_unlock(&vsock->rx_lock); + + atomic_set(&vsock->queued_replies, 0); + ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, vqs_info, NULL); if (ret < 0) return ret; @@ -779,9 +786,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->vdev = vdev; - vsock->rx_buf_nr = 0; - vsock->rx_buf_max_nr = 0; - atomic_set(&vsock->queued_replies, 0); mutex_init(&vsock->tx_lock); mutex_init(&vsock->rx_lock); diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index f201d9eca1df..07b96d56f3a5 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -87,7 +87,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, lock_sock(sk); vsk = vsock_sk(sk); - if (!vsk->transport) { + if (WARN_ON_ONCE(!vsk->transport)) { copied = -ENODEV; goto out; } diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index 98f1e2b67c76..c397eb99d867 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -506,7 +506,7 @@ xmit: skb_dst_set(skb, dst); skb->dev = tdev; - err = dst_output(xi->net, skb->sk, skb); + err = dst_output(xi->net, skb_to_full_sk(skb), skb); if (net_xmit_eval(err) == 0) { dev_sw_netstats_tx_add(dev, 1, length); } else { diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index b5025cf6136e..f7abd42c077d 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -802,7 +802,7 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) !skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) { skb->protocol = htons(ETH_P_IP); - if (skb->sk) + if (skb->sk && sk_fullsock(skb->sk)) xfrm_local_error(skb, mtu); else icmp_send(skb, ICMP_DEST_UNREACH, @@ -838,6 +838,7 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) { int mtu, ret = 0; struct dst_entry *dst = skb_dst(skb); + struct sock *sk = skb_to_full_sk(skb); if (skb->ignore_df) goto out; @@ -852,9 +853,9 @@ static int xfrm6_tunnel_check_size(struct sk_buff *skb) skb->dev = dst->dev; skb->protocol = htons(ETH_P_IPV6); - if (xfrm6_local_dontfrag(skb->sk)) + if (xfrm6_local_dontfrag(sk)) ipv6_stub->xfrm6_local_rxpmtu(skb, mtu); - else if (skb->sk) + else if (sk) xfrm_local_error(skb, mtu); else icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9e510021ee91..6551e588fe52 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2964,7 +2964,7 @@ static void xfrm_policy_queue_process(struct timer_list *t) skb_dst_drop(skb); skb_dst_set(skb, dst); - dst_output(net, skb->sk, skb); + dst_output(net, skb_to_full_sk(skb), skb); } out: diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index e500aebbad22..dbdf8a39dffe 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -714,10 +714,12 @@ static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff oseq += skb_shinfo(skb)->gso_segs; } - if (unlikely(xo->seq.low < replay_esn->oseq)) { - XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; - xo->seq.hi = oseq_hi; - replay_esn->oseq_hi = oseq_hi; + if (unlikely(oseq < replay_esn->oseq)) { + replay_esn->oseq_hi = ++oseq_hi; + if (xo->seq.low < replay_esn->oseq) { + XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi; + xo->seq.hi = oseq_hi; + } if (replay_esn->oseq_hi == 0) { replay_esn->oseq--; replay_esn->oseq_hi--; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 34067cb8a479..ad2202fa82f3 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -34,6 +34,8 @@ #define xfrm_state_deref_prot(table, net) \ rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) +#define xfrm_state_deref_check(table, net) \ + rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) static void xfrm_state_gc_task(struct work_struct *work); @@ -62,6 +64,8 @@ static inline unsigned int xfrm_dst_hash(struct net *net, u32 reqid, unsigned short family) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask); } @@ -70,6 +74,8 @@ static inline unsigned int xfrm_src_hash(struct net *net, const xfrm_address_t *saddr, unsigned short family) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } @@ -77,11 +83,15 @@ static inline unsigned int xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } static unsigned int xfrm_seq_hash(struct net *net, u32 seq) { + lockdep_assert_held(&net->xfrm.xfrm_state_lock); + return __xfrm_seq_hash(seq, net->xfrm.state_hmask); } @@ -1108,16 +1118,38 @@ xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, x->props.family = tmpl->encap_family; } -static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark, +struct xfrm_hash_state_ptrs { + const struct hlist_head *bydst; + const struct hlist_head *bysrc; + const struct hlist_head *byspi; + unsigned int hmask; +}; + +static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs) +{ + unsigned int sequence; + + do { + sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); + + ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net); + ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net); + ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net); + ptrs->hmask = net->xfrm.state_hmask; + } while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)); +} + +static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs, + u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, struct xfrm_dev_offload *xdo) { - unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); + unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { + hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { #ifdef CONFIG_XFRM_OFFLOAD if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) @@ -1151,15 +1183,16 @@ static struct xfrm_state *__xfrm_state_lookup_all(struct net *net, u32 mark, return NULL; } -static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, +static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs, + u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { - unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); + unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_byspi + h, byspi) { + hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || @@ -1181,11 +1214,11 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, __be32 spi, u8 proto, unsigned short family) { + struct xfrm_hash_state_ptrs state_ptrs; struct hlist_head *state_cache_input; struct xfrm_state *x = NULL; - int cpu = get_cpu(); - state_cache_input = per_cpu_ptr(net->xfrm.state_cache_input, cpu); + state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input); rcu_read_lock(); hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) { @@ -1202,7 +1235,9 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, goto out; } - x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); + xfrm_hash_ptrs_get(net, &state_ptrs); + + x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); if (x && x->km.state == XFRM_STATE_VALID) { spin_lock_bh(&net->xfrm.xfrm_state_lock); @@ -1217,20 +1252,20 @@ struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, out: rcu_read_unlock(); - put_cpu(); return x; } EXPORT_SYMBOL(xfrm_input_state_lookup); -static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, +static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs, + u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { - unsigned int h = xfrm_src_hash(net, daddr, saddr, family); + unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask); struct xfrm_state *x; - hlist_for_each_entry_rcu(x, net->xfrm.state_bysrc + h, bysrc) { + hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || @@ -1250,14 +1285,17 @@ static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, static inline struct xfrm_state * __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) { + struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xs_net(x); u32 mark = x->mark.v & x->mark.m; + xfrm_hash_ptrs_get(net, &state_ptrs); + if (use_spi) - return __xfrm_state_lookup(net, mark, &x->id.daddr, + return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr, x->id.spi, x->id.proto, family); else - return __xfrm_state_lookup_byaddr(net, mark, + return __xfrm_state_lookup_byaddr(&state_ptrs, mark, &x->id.daddr, &x->props.saddr, x->id.proto, family); @@ -1331,6 +1369,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; + struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xp_net(pol); unsigned int h, h_wildcard; struct xfrm_state *x, *x0, *to_put; @@ -1395,8 +1434,10 @@ cached: else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */ WARN_ON(1); - h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); - hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h, bydst) { + xfrm_hash_ptrs_get(net, &state_ptrs); + + h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask); + hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) @@ -1429,8 +1470,9 @@ cached: if (best || acquire_in_progress) goto found; - h_wildcard = xfrm_dst_hash(net, daddr, &saddr_wildcard, tmpl->reqid, encap_family); - hlist_for_each_entry_rcu(x, net->xfrm.state_bydst + h_wildcard, bydst) { + h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid, + encap_family, state_ptrs.hmask); + hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) @@ -1468,7 +1510,7 @@ found: if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && - (x0 = __xfrm_state_lookup_all(net, mark, daddr, + (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr, tmpl->id.spi, tmpl->id.proto, encap_family, &pol->xdo)) != NULL) { @@ -2253,10 +2295,13 @@ struct xfrm_state * xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { + struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; rcu_read_lock(); - x = __xfrm_state_lookup(net, mark, daddr, spi, proto, family); + xfrm_hash_ptrs_get(net, &state_ptrs); + + x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); rcu_read_unlock(); return x; } @@ -2267,10 +2312,14 @@ xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { + struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); - x = __xfrm_state_lookup_byaddr(net, mark, daddr, saddr, proto, family); + + xfrm_hash_ptrs_get(net, &state_ptrs); + + x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } diff --git a/rust/Makefile b/rust/Makefile index 71a05a3c895a..ea3849eb78f6 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -144,7 +144,7 @@ rusttestlib-kernel: private rustc_target_flags = --extern ffi \ --extern bindings --extern uapi rusttestlib-kernel: $(src)/kernel/lib.rs \ rusttestlib-bindings rusttestlib-uapi rusttestlib-build_error \ - $(obj)/libmacros.so $(obj)/bindings.o FORCE + $(obj)/$(libmacros_name) $(obj)/bindings.o FORCE +$(call if_changed,rustc_test_library) rusttestlib-bindings: private rustc_target_flags = --extern ffi @@ -240,6 +240,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ -fzero-call-used-regs=% -fno-stack-clash-protection \ -fno-inline-functions-called-once -fsanitize=bounds-strict \ -fstrict-flex-arrays=% -fmin-function-alignment=% \ + -fzero-init-padding-bits=% \ --param=% --param asan-% # Derived from `scripts/Makefile.clang`. @@ -331,10 +332,11 @@ $(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_extra = ; $(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers/helpers.c FORCE $(call if_changed_dep,bindgen) +rust_exports = $(NM) -p --defined-only $(1) | awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ && $$3!~/__odr_asan/ { printf $(2),$$3 }' + quiet_cmd_exports = EXPORTS $@ cmd_exports = \ - $(NM) -p --defined-only $< \ - | awk '$$2~/(T|R|D|B)/ && $$3!~/__cfi/ {printf "EXPORT_SYMBOL_RUST_GPL(%s);\n",$$3}' > $@ + $(call rust_exports,$<,"EXPORT_SYMBOL_RUST_GPL(%s);\n") > $@ $(obj)/exports_core_generated.h: $(obj)/core.o FORCE $(call if_changed,exports) @@ -403,11 +405,36 @@ ifneq ($(or $(CONFIG_ARM64),$(and $(CONFIG_RISCV),$(CONFIG_64BIT))),) __ashlti3 __lshrti3 endif +ifdef CONFIG_MODVERSIONS +cmd_gendwarfksyms = $(if $(skip_gendwarfksyms),, \ + $(call rust_exports,$@,"%s\n") | \ + scripts/gendwarfksyms/gendwarfksyms \ + $(if $(KBUILD_GENDWARFKSYMS_STABLE), --stable) \ + $(if $(KBUILD_SYMTYPES), --symtypes $(@:.o=.symtypes),) \ + $@ >> $(dot-target).cmd) +endif + define rule_rustc_library $(call cmd_and_fixdep,rustc_library) $(call cmd,gen_objtooldep) + $(call cmd,gendwarfksyms) endef +define rule_rust_cc_library + $(call if_changed_rule,cc_o_c) + $(call cmd,force_checksrc) + $(call cmd,gendwarfksyms) +endef + +# helpers.o uses the same export mechanism as Rust libraries, so ensure symbol +# versions are calculated for the helpers too. +$(obj)/helpers/helpers.o: $(src)/helpers/helpers.c $(recordmcount_source) FORCE + +$(call if_changed_rule,rust_cc_library) + +# Disable symbol versioning for exports.o to avoid conflicts with the actual +# symbol versions generated from Rust objects. +$(obj)/exports.o: private skip_gendwarfksyms = 1 + $(obj)/core.o: private skip_clippy = 1 $(obj)/core.o: private skip_flags = -Wunreachable_pub $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym)) @@ -419,13 +446,16 @@ ifneq ($(or $(CONFIG_X86_64),$(CONFIG_X86_32)),) $(obj)/core.o: scripts/target.json endif +$(obj)/compiler_builtins.o: private skip_gendwarfksyms = 1 $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*' $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE +$(call if_changed_rule,rustc_library) +$(obj)/build_error.o: private skip_gendwarfksyms = 1 $(obj)/build_error.o: $(src)/build_error.rs $(obj)/compiler_builtins.o FORCE +$(call if_changed_rule,rustc_library) +$(obj)/ffi.o: private skip_gendwarfksyms = 1 $(obj)/ffi.o: $(src)/ffi.rs $(obj)/compiler_builtins.o FORCE +$(call if_changed_rule,rustc_library) @@ -437,6 +467,7 @@ $(obj)/bindings.o: $(src)/bindings/lib.rs \ +$(call if_changed_rule,rustc_library) $(obj)/uapi.o: private rustc_target_flags = --extern ffi +$(obj)/uapi.o: private skip_gendwarfksyms = 1 $(obj)/uapi.o: $(src)/uapi/lib.rs \ $(obj)/ffi.o \ $(obj)/uapi/uapi_generated.rs FORCE diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 55354e4dec14..f46cf3bb7069 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -11,6 +11,7 @@ #include <linux/blk_types.h> #include <linux/blkdev.h> #include <linux/cred.h> +#include <linux/device/faux.h> #include <linux/errname.h> #include <linux/ethtool.h> #include <linux/file.h> diff --git a/rust/kernel/faux.rs b/rust/kernel/faux.rs new file mode 100644 index 000000000000..5acc0c02d451 --- /dev/null +++ b/rust/kernel/faux.rs @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only + +//! Abstractions for the faux bus. +//! +//! This module provides bindings for working with faux devices in kernel modules. +//! +//! C header: [`include/linux/device/faux.h`] + +use crate::{bindings, device, error::code::*, prelude::*}; +use core::ptr::{addr_of_mut, null, null_mut, NonNull}; + +/// The registration of a faux device. +/// +/// This type represents the registration of a [`struct faux_device`]. When an instance of this type +/// is dropped, its respective faux device will be unregistered from the system. +/// +/// # Invariants +/// +/// `self.0` always holds a valid pointer to an initialized and registered [`struct faux_device`]. +/// +/// [`struct faux_device`]: srctree/include/linux/device/faux.h +#[repr(transparent)] +pub struct Registration(NonNull<bindings::faux_device>); + +impl Registration { + /// Create and register a new faux device with the given name. + pub fn new(name: &CStr) -> Result<Self> { + // SAFETY: + // - `name` is copied by this function into its own storage + // - `faux_ops` is safe to leave NULL according to the C API + let dev = unsafe { bindings::faux_device_create(name.as_char_ptr(), null_mut(), null()) }; + + // The above function will return either a valid device, or NULL on failure + // INVARIANT: The device will remain registered until faux_device_destroy() is called, which + // happens in our Drop implementation. + Ok(Self(NonNull::new(dev).ok_or(ENODEV)?)) + } + + fn as_raw(&self) -> *mut bindings::faux_device { + self.0.as_ptr() + } +} + +impl AsRef<device::Device> for Registration { + fn as_ref(&self) -> &device::Device { + // SAFETY: The underlying `device` in `faux_device` is guaranteed by the C API to be + // a valid initialized `device`. + unsafe { device::Device::as_ref(addr_of_mut!((*self.as_raw()).dev)) } + } +} + +impl Drop for Registration { + fn drop(&mut self) { + // SAFETY: `self.0` is a valid registered faux_device via our type invariants. + unsafe { bindings::faux_device_destroy(self.as_raw()) } + } +} + +// SAFETY: The faux device API is thread-safe as guaranteed by the device core, as long as +// faux_device_destroy() is guaranteed to only be called once - which is guaranteed by our type not +// having Copy/Clone. +unsafe impl Send for Registration {} + +// SAFETY: The faux device API is thread-safe as guaranteed by the device core, as long as +// faux_device_destroy() is guaranteed to only be called once - which is guaranteed by our type not +// having Copy/Clone. +unsafe impl Sync for Registration {} diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs index 3f9236c1c9d5..7fd1ea8265a5 100644 --- a/rust/kernel/init.rs +++ b/rust/kernel/init.rs @@ -870,7 +870,7 @@ pub unsafe trait PinInit<T: ?Sized, E = Infallible>: Sized { /// use kernel::{types::Opaque, init::pin_init_from_closure}; /// #[repr(C)] /// struct RawFoo([u8; 16]); - /// extern { + /// extern "C" { /// fn init_foo(_: *mut RawFoo); /// } /// diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index 496ed32b0911..398242f92a96 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -46,6 +46,7 @@ pub mod device_id; pub mod devres; pub mod driver; pub mod error; +pub mod faux; #[cfg(CONFIG_RUST_FW_LOADER_ABSTRACTIONS)] pub mod firmware; pub mod fs; diff --git a/rust/kernel/rbtree.rs b/rust/kernel/rbtree.rs index ee2731dad72d..0d1e75810664 100644 --- a/rust/kernel/rbtree.rs +++ b/rust/kernel/rbtree.rs @@ -1149,7 +1149,7 @@ pub struct VacantEntry<'a, K, V> { /// # Invariants /// - `parent` may be null if the new node becomes the root. /// - `child_field_of_parent` is a valid pointer to the left-child or right-child of `parent`. If `parent` is -/// null, it is a pointer to the root of the [`RBTree`]. +/// null, it is a pointer to the root of the [`RBTree`]. struct RawVacantEntry<'a, K, V> { rbtree: *mut RBTree<K, V>, /// The node that will become the parent of the new node if we insert one. diff --git a/samples/check-exec/inc.c b/samples/check-exec/inc.c index 94b87569d2a2..7f6ef06a2f06 100644 --- a/samples/check-exec/inc.c +++ b/samples/check-exec/inc.c @@ -21,8 +21,15 @@ #include <stdlib.h> #include <string.h> #include <sys/prctl.h> +#include <sys/syscall.h> #include <unistd.h> +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + /* Returns 1 on error, 0 otherwise. */ static int interpret_buffer(char *buffer, size_t buffer_size) { @@ -78,8 +85,8 @@ static int interpret_stream(FILE *script, char *const script_name, * script execution. We must use the script file descriptor instead of * the script path name to avoid race conditions. */ - err = execveat(fileno(script), "", script_argv, envp, - AT_EMPTY_PATH | AT_EXECVE_CHECK); + err = sys_execveat(fileno(script), "", script_argv, envp, + AT_EMPTY_PATH | AT_EXECVE_CHECK); if (err && restrict_stream) { perror("ERROR: Script execution check"); return 1; diff --git a/samples/hid/Makefile b/samples/hid/Makefile index 8ea59e9631a3..db5a077c77fc 100644 --- a/samples/hid/Makefile +++ b/samples/hid/Makefile @@ -40,16 +40,17 @@ BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-generic endif endif -TPROGS_CFLAGS += -Wall -O2 -TPROGS_CFLAGS += -Wmissing-prototypes -TPROGS_CFLAGS += -Wstrict-prototypes +COMMON_CFLAGS += -Wall -O2 +COMMON_CFLAGS += -Wmissing-prototypes +COMMON_CFLAGS += -Wstrict-prototypes +TPROGS_CFLAGS += $(COMMON_CFLAGS) TPROGS_CFLAGS += -I$(objtree)/usr/include TPROGS_CFLAGS += -I$(LIBBPF_INCLUDE) TPROGS_CFLAGS += -I$(srctree)/tools/include ifdef SYSROOT -TPROGS_CFLAGS += --sysroot=$(SYSROOT) +COMMON_CFLAGS += --sysroot=$(SYSROOT) TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib endif @@ -112,7 +113,7 @@ clean: $(LIBBPF): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT) # Fix up variables inherited from Kbuild that tools/ build system won't like - $(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \ + $(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(COMMON_CFLAGS)" \ LDFLAGS=$(TPROGS_LDFLAGS) srctree=$(HID_SAMPLES_PATH)/../../ \ O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \ $@ install_headers @@ -163,7 +164,7 @@ $(obj)/hid_surface_dial.o: $(obj)/hid_surface_dial.skel.h VMLINUX_BTF_PATHS ?= $(abspath $(if $(O),$(O)/vmlinux)) \ $(abspath $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)) \ - $(abspath ./vmlinux) + $(abspath $(objtree)/vmlinux) VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS)))) $(obj)/vmlinux.h: $(VMLINUX_BTF) $(BPFTOOL) diff --git a/samples/rust/Kconfig b/samples/rust/Kconfig index 918dbead2c0b..3b6eae84b297 100644 --- a/samples/rust/Kconfig +++ b/samples/rust/Kconfig @@ -61,6 +61,16 @@ config SAMPLE_RUST_DRIVER_PLATFORM If unsure, say N. +config SAMPLE_RUST_DRIVER_FAUX + tristate "Faux Driver" + help + This option builds the Rust Faux driver sample. + + To compile this as a module, choose M here: + the module will be called rust_driver_faux. + + If unsure, say N. + config SAMPLE_RUST_HOSTPROGS bool "Host programs" help diff --git a/samples/rust/Makefile b/samples/rust/Makefile index 5a8ab0df0567..0dbc6d90f1ef 100644 --- a/samples/rust/Makefile +++ b/samples/rust/Makefile @@ -6,6 +6,7 @@ obj-$(CONFIG_SAMPLE_RUST_MISC_DEVICE) += rust_misc_device.o obj-$(CONFIG_SAMPLE_RUST_PRINT) += rust_print.o obj-$(CONFIG_SAMPLE_RUST_DRIVER_PCI) += rust_driver_pci.o obj-$(CONFIG_SAMPLE_RUST_DRIVER_PLATFORM) += rust_driver_platform.o +obj-$(CONFIG_SAMPLE_RUST_DRIVER_FAUX) += rust_driver_faux.o rust_print-y := rust_print_main.o rust_print_events.o diff --git a/samples/rust/rust_driver_faux.rs b/samples/rust/rust_driver_faux.rs new file mode 100644 index 000000000000..048c6cb98b29 --- /dev/null +++ b/samples/rust/rust_driver_faux.rs @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only + +//! Rust faux device sample. + +use kernel::{c_str, faux, prelude::*, Module}; + +module! { + type: SampleModule, + name: "rust_faux_driver", + author: "Lyude Paul", + description: "Rust faux device sample", + license: "GPL", +} + +struct SampleModule { + _reg: faux::Registration, +} + +impl Module for SampleModule { + fn init(_module: &'static ThisModule) -> Result<Self> { + pr_info!("Initialising Rust Faux Device Sample\n"); + + let reg = faux::Registration::new(c_str!("rust-faux-sample-device"))?; + + dev_info!(reg.as_ref(), "Hello from faux device!\n"); + + Ok(Self { _reg: reg }) + } +} diff --git a/scripts/Makefile b/scripts/Makefile index 546e8175e1c4..46f860529df5 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -53,7 +53,8 @@ hostprogs += unifdef gen_packed_field_checks targets += module.lds subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins -subdir-$(CONFIG_MODVERSIONS) += genksyms +subdir-$(CONFIG_GENKSYMS) += genksyms +subdir-$(CONFIG_GENDWARFKSYMS) += gendwarfksyms subdir-$(CONFIG_SECURITY_SELINUX) += selinux subdir-$(CONFIG_SECURITY_IPE) += ipe diff --git a/scripts/Makefile.build b/scripts/Makefile.build index c16e4cf54d77..993708d11874 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -107,13 +107,24 @@ cmd_cpp_i_c = $(CPP) $(c_flags) -o $@ $< $(obj)/%.i: $(obj)/%.c FORCE $(call if_changed_dep,cpp_i_c) +getexportsymbols = $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/$(1)/p' + +gendwarfksyms = $(objtree)/scripts/gendwarfksyms/gendwarfksyms \ + $(if $(KBUILD_SYMTYPES), --symtypes $(@:.o=.symtypes)) \ + $(if $(KBUILD_GENDWARFKSYMS_STABLE), --stable) + genksyms = $(objtree)/scripts/genksyms/genksyms \ $(if $(KBUILD_SYMTYPES), -T $(@:.o=.symtypes)) \ $(if $(KBUILD_PRESERVE), -p) \ $(addprefix -r , $(wildcard $(@:.o=.symref))) # These mirror gensymtypes_S and co below, keep them in synch. +ifdef CONFIG_GENDWARFKSYMS +cmd_gensymtypes_c = $(if $(skip_gendwarfksyms),, \ + $(call getexportsymbols,\1) | $(gendwarfksyms) $@) +else cmd_gensymtypes_c = $(CPP) -D__GENKSYMS__ $(c_flags) $< | $(genksyms) +endif # CONFIG_GENDWARFKSYMS # LLVM assembly # Generate .ll files from .c @@ -183,7 +194,9 @@ endif # CONFIG_FTRACE_MCOUNT_USE_RECORDMCOUNT is-standard-object = $(if $(filter-out y%, $(OBJECT_FILES_NON_STANDARD_$(target-stem).o)$(OBJECT_FILES_NON_STANDARD)n),$(is-kernel-object)) +ifdef CONFIG_OBJTOOL $(obj)/%.o: private objtool-enabled = $(if $(is-standard-object),$(if $(delay-objtool),$(is-single-obj-m),y)) +endif ifneq ($(findstring 1, $(KBUILD_EXTRA_WARN)),) cmd_warn_shared_object = $(if $(word 2, $(modname-multi)),$(warning $(kbuild-file): $*.o is added to multiple modules: $(modname-multi))) @@ -286,14 +299,26 @@ $(obj)/%.rs: $(obj)/%.rs.S FORCE # This is convoluted. The .S file must first be preprocessed to run guards and # expand names, then the resulting exports must be constructed into plain # EXPORT_SYMBOL(symbol); to build our dummy C file, and that gets preprocessed -# to make the genksyms input. +# to make the genksyms input or compiled into an object for gendwarfksyms. # # These mirror gensymtypes_c and co above, keep them in synch. -cmd_gensymtypes_S = \ - { echo "\#include <linux/kernel.h>" ; \ - echo "\#include <asm/asm-prototypes.h>" ; \ - $(NM) $@ | sed -n 's/.* __export_symbol_\(.*\)/EXPORT_SYMBOL(\1);/p' ; } | \ - $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms) +getasmexports = \ + { echo "\#include <linux/kernel.h>" ; \ + echo "\#include <linux/string.h>" ; \ + echo "\#include <asm/asm-prototypes.h>" ; \ + $(call getexportsymbols,EXPORT_SYMBOL(\1);) ; } + +ifdef CONFIG_GENDWARFKSYMS +cmd_gensymtypes_S = \ + $(getasmexports) | \ + $(CC) $(c_flags) -c -o $(@:.o=.gendwarfksyms.o) -xc -; \ + $(call getexportsymbols,\1) | \ + $(gendwarfksyms) $(@:.o=.gendwarfksyms.o) +else +cmd_gensymtypes_S = \ + $(getasmexports) | \ + $(CPP) -D__GENKSYMS__ $(c_flags) -xc - | $(genksyms) +endif # CONFIG_GENDWARFKSYMS quiet_cmd_cpp_s_S = CPP $(quiet_modtag) $@ cmd_cpp_s_S = $(CPP) $(a_flags) -o $@ $< diff --git a/scripts/Makefile.defconf b/scripts/Makefile.defconf index 226ea3df3b4b..a44307f08e9d 100644 --- a/scripts/Makefile.defconf +++ b/scripts/Makefile.defconf @@ -1,6 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # Configuration heplers +cmd_merge_fragments = \ + $(srctree)/scripts/kconfig/merge_config.sh \ + $4 -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$2 \ + $(foreach config,$3,$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + # Creates 'merged defconfigs' # --------------------------------------------------------------------------- # Usage: @@ -8,9 +13,7 @@ # # Input config fragments without '.config' suffix define merge_into_defconfig - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ - -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \ - $(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + $(call cmd,merge_fragments,$1,$2) +$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig endef @@ -22,8 +25,6 @@ endef # # Input config fragments without '.config' suffix define merge_into_defconfig_override - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh \ - -Q -m -O $(objtree) $(srctree)/arch/$(SRCARCH)/configs/$(1) \ - $(foreach config,$(2),$(srctree)/arch/$(SRCARCH)/configs/$(config).config) + $(call cmd,merge_fragments,$1,$2,-Q) +$(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig endef diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 1d13cecc7cc7..dc081cf46d21 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -31,6 +31,11 @@ KBUILD_CFLAGS-$(CONFIG_CC_NO_ARRAY_BOUNDS) += -Wno-array-bounds ifdef CONFIG_CC_IS_CLANG # The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable. KBUILD_CFLAGS += -Wno-gnu + +# Clang checks for overflow/truncation with '%p', while GCC does not: +# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219 +KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf) +KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf) else # gcc inanely warns about local variables called 'main' @@ -77,6 +82,9 @@ KBUILD_CFLAGS += $(call cc-option,-Werror=designated-init) # Warn if there is an enum types mismatch KBUILD_CFLAGS += $(call cc-option,-Wenum-conversion) +# Explicitly clear padding bits during variable initialization +KBUILD_CFLAGS += $(call cc-option,-fzero-init-padding-bits=all) + KBUILD_CFLAGS += -Wextra KBUILD_CFLAGS += -Wunused @@ -102,11 +110,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, packed-not-aligned) KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow) ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation) -else -# Clang checks for overflow/truncation with '%p', while GCC does not: -# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111219 -KBUILD_CFLAGS += $(call cc-disable-warning, format-overflow-non-kprintf) -KBUILD_CFLAGS += $(call cc-disable-warning, format-truncation-non-kprintf) endif KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) @@ -130,7 +133,6 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += -Wno-tautological-constant-out-of-range-compare KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) KBUILD_CFLAGS += -Wno-enum-compare-conditional -KBUILD_CFLAGS += -Wno-enum-enum-conversion endif endif @@ -154,6 +156,10 @@ KBUILD_CFLAGS += -Wno-missing-field-initializers KBUILD_CFLAGS += -Wno-type-limits KBUILD_CFLAGS += -Wno-shift-negative-value +ifdef CONFIG_CC_IS_CLANG +KBUILD_CFLAGS += -Wno-enum-enum-conversion +endif + ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += -Wno-maybe-uninitialized endif diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 7395200538da..cad20f0e66ee 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -287,6 +287,8 @@ delay-objtool := $(or $(CONFIG_LTO_CLANG),$(CONFIG_X86_KERNEL_IBT)) cmd_objtool = $(if $(objtool-enabled), ; $(objtool) $(objtool-args) $@) cmd_gen_objtooldep = $(if $(objtool-enabled), { echo ; echo '$@: $$(wildcard $(objtool))' ; } >> $(dot-target).cmd) +objtool-enabled := y + endif # CONFIG_OBJTOOL # Useful for describing the dependency of composite objects @@ -302,11 +304,11 @@ endef # =========================================================================== # These are shared by some Makefile.* files. -objtool-enabled := y - ifdef CONFIG_LTO_CLANG -# objtool cannot process LLVM IR. Make $(LD) covert LLVM IR to ELF here. -cmd_ld_single = $(if $(objtool-enabled), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@) +# Run $(LD) here to convert LLVM IR to ELF in the following cases: +# - when this object needs objtool processing, as objtool cannot process LLVM IR +# - when this is a single-object module, as modpost cannot process LLVM IR +cmd_ld_single = $(if $(objtool-enabled)$(is-single-obj-m), ; $(LD) $(ld_flags) -r -o $(tmp-target) $@; mv $(tmp-target) $@) endif quiet_cmd_cc_o_c = CC $(quiet_modtag) $@ @@ -374,6 +376,9 @@ quiet_cmd_ar = AR $@ quiet_cmd_objcopy = OBJCOPY $@ cmd_objcopy = $(OBJCOPY) $(OBJCOPYFLAGS) $(OBJCOPYFLAGS_$(@F)) $< $@ +quiet_cmd_strip_relocs = RSTRIP $@ +cmd_strip_relocs = $(OBJCOPY) --remove-section='.rel*' $@ + # Gzip # --------------------------------------------------------------------------- diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index f97c9926ed31..1628198f3e83 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -105,7 +105,7 @@ else sig-key := $(CONFIG_MODULE_SIG_KEY) endif quiet_cmd_sign = SIGN $@ - cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \ + cmd_sign = $(objtree)/scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" $(objtree)/certs/signing_key.x509 $@ \ $(if $(KBUILD_EXTMOD),|| true) ifeq ($(sign-only),) diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index ab0e94ea6249..d7d45067d08b 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -43,6 +43,8 @@ MODPOST = $(objtree)/scripts/mod/modpost modpost-args = \ $(if $(CONFIG_MODULES),-M) \ $(if $(CONFIG_MODVERSIONS),-m) \ + $(if $(CONFIG_BASIC_MODVERSIONS),-b) \ + $(if $(CONFIG_EXTENDED_MODVERSIONS),-x) \ $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ $(if $(KBUILD_MODPOST_WARN),-w) \ diff --git a/scripts/gdb/linux/cpus.py b/scripts/gdb/linux/cpus.py index 2f11c4f9c345..13eb8b3901b8 100644 --- a/scripts/gdb/linux/cpus.py +++ b/scripts/gdb/linux/cpus.py @@ -167,7 +167,7 @@ def get_current_task(cpu): var_ptr = gdb.parse_and_eval("&pcpu_hot.current_task") return per_cpu(var_ptr, cpu).dereference() elif utils.is_target_arch("aarch64"): - current_task_addr = gdb.parse_and_eval("$SP_EL0") + current_task_addr = gdb.parse_and_eval("(unsigned long)$SP_EL0") if (current_task_addr >> 63) != 0: current_task = current_task_addr.cast(task_ptr_type) return current_task.dereference() diff --git a/scripts/gendwarfksyms/.gitignore b/scripts/gendwarfksyms/.gitignore new file mode 100644 index 000000000000..0927f8d3cd96 --- /dev/null +++ b/scripts/gendwarfksyms/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +/gendwarfksyms diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile new file mode 100644 index 000000000000..6334c7d3c4d5 --- /dev/null +++ b/scripts/gendwarfksyms/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +hostprogs-always-y += gendwarfksyms + +gendwarfksyms-objs += gendwarfksyms.o +gendwarfksyms-objs += cache.o +gendwarfksyms-objs += die.o +gendwarfksyms-objs += dwarf.o +gendwarfksyms-objs += kabi.o +gendwarfksyms-objs += symbols.o +gendwarfksyms-objs += types.o + +HOSTLDLIBS_gendwarfksyms := -ldw -lelf -lz diff --git a/scripts/gendwarfksyms/cache.c b/scripts/gendwarfksyms/cache.c new file mode 100644 index 000000000000..c9c19b86a686 --- /dev/null +++ b/scripts/gendwarfksyms/cache.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +struct cache_item { + unsigned long key; + int value; + struct hlist_node hash; +}; + +void cache_set(struct cache *cache, unsigned long key, int value) +{ + struct cache_item *ci; + + ci = xmalloc(sizeof(struct cache_item)); + ci->key = key; + ci->value = value; + hash_add(cache->cache, &ci->hash, hash_32(key)); +} + +int cache_get(struct cache *cache, unsigned long key) +{ + struct cache_item *ci; + + hash_for_each_possible(cache->cache, ci, hash, hash_32(key)) { + if (ci->key == key) + return ci->value; + } + + return -1; +} + +void cache_init(struct cache *cache) +{ + hash_init(cache->cache); +} + +void cache_free(struct cache *cache) +{ + struct hlist_node *tmp; + struct cache_item *ci; + + hash_for_each_safe(cache->cache, ci, tmp, hash) { + free(ci); + } + + hash_init(cache->cache); +} diff --git a/scripts/gendwarfksyms/die.c b/scripts/gendwarfksyms/die.c new file mode 100644 index 000000000000..66bd4c9bc952 --- /dev/null +++ b/scripts/gendwarfksyms/die.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <string.h> +#include "gendwarfksyms.h" + +#define DIE_HASH_BITS 15 + +/* {die->addr, state} -> struct die * */ +static HASHTABLE_DEFINE(die_map, 1 << DIE_HASH_BITS); + +static unsigned int map_hits; +static unsigned int map_misses; + +static inline unsigned int die_hash(uintptr_t addr, enum die_state state) +{ + return hash_32(addr_hash(addr) ^ (unsigned int)state); +} + +static void init_die(struct die *cd) +{ + cd->state = DIE_INCOMPLETE; + cd->mapped = false; + cd->fqn = NULL; + cd->tag = -1; + cd->addr = 0; + INIT_LIST_HEAD(&cd->fragments); +} + +static struct die *create_die(Dwarf_Die *die, enum die_state state) +{ + struct die *cd; + + cd = xmalloc(sizeof(struct die)); + init_die(cd); + cd->addr = (uintptr_t)die->addr; + + hash_add(die_map, &cd->hash, die_hash(cd->addr, state)); + return cd; +} + +int __die_map_get(uintptr_t addr, enum die_state state, struct die **res) +{ + struct die *cd; + + hash_for_each_possible(die_map, cd, hash, die_hash(addr, state)) { + if (cd->addr == addr && cd->state == state) { + *res = cd; + return 0; + } + } + + return -1; +} + +struct die *die_map_get(Dwarf_Die *die, enum die_state state) +{ + struct die *cd; + + if (__die_map_get((uintptr_t)die->addr, state, &cd) == 0) { + map_hits++; + return cd; + } + + map_misses++; + return create_die(die, state); +} + +static void reset_die(struct die *cd) +{ + struct die_fragment *tmp; + struct die_fragment *df; + + list_for_each_entry_safe(df, tmp, &cd->fragments, list) { + if (df->type == FRAGMENT_STRING) + free(df->data.str); + free(df); + } + + if (cd->fqn && *cd->fqn) + free(cd->fqn); + init_die(cd); +} + +void die_map_for_each(die_map_callback_t func, void *arg) +{ + struct hlist_node *tmp; + struct die *cd; + + hash_for_each_safe(die_map, cd, tmp, hash) { + func(cd, arg); + } +} + +void die_map_free(void) +{ + struct hlist_node *tmp; + unsigned int stats[DIE_LAST + 1]; + struct die *cd; + int i; + + memset(stats, 0, sizeof(stats)); + + hash_for_each_safe(die_map, cd, tmp, hash) { + stats[cd->state]++; + reset_die(cd); + free(cd); + } + hash_init(die_map); + + if (map_hits + map_misses > 0) + debug("hits %u, misses %u (hit rate %.02f%%)", map_hits, + map_misses, + (100.0f * map_hits) / (map_hits + map_misses)); + + for (i = 0; i <= DIE_LAST; i++) + debug("%s: %u entries", die_state_name(i), stats[i]); +} + +static struct die_fragment *append_item(struct die *cd) +{ + struct die_fragment *df; + + df = xmalloc(sizeof(struct die_fragment)); + df->type = FRAGMENT_EMPTY; + list_add_tail(&df->list, &cd->fragments); + return df; +} + +void die_map_add_string(struct die *cd, const char *str) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.str = xstrdup(str); + df->type = FRAGMENT_STRING; +} + +void die_map_add_linebreak(struct die *cd, int linebreak) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.linebreak = linebreak; + df->type = FRAGMENT_LINEBREAK; +} + +void die_map_add_die(struct die *cd, struct die *child) +{ + struct die_fragment *df; + + if (!cd) + return; + + df = append_item(cd); + df->data.addr = child->addr; + df->type = FRAGMENT_DIE; +} diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c new file mode 100644 index 000000000000..534d9aa7c114 --- /dev/null +++ b/scripts/gendwarfksyms/dwarf.c @@ -0,0 +1,1159 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <assert.h> +#include <inttypes.h> +#include <stdarg.h> +#include "gendwarfksyms.h" + +/* See get_union_kabi_status */ +#define KABI_PREFIX "__kabi_" +#define KABI_PREFIX_LEN (sizeof(KABI_PREFIX) - 1) +#define KABI_RESERVED_PREFIX "reserved" +#define KABI_RESERVED_PREFIX_LEN (sizeof(KABI_RESERVED_PREFIX) - 1) +#define KABI_RENAMED_PREFIX "renamed" +#define KABI_RENAMED_PREFIX_LEN (sizeof(KABI_RENAMED_PREFIX) - 1) +#define KABI_IGNORED_PREFIX "ignored" +#define KABI_IGNORED_PREFIX_LEN (sizeof(KABI_IGNORED_PREFIX) - 1) + +static inline bool is_kabi_prefix(const char *name) +{ + return name && !strncmp(name, KABI_PREFIX, KABI_PREFIX_LEN); +} + +enum kabi_status { + /* >0 to stop DIE processing */ + KABI_NORMAL = 1, + KABI_RESERVED, + KABI_IGNORED, +}; + +static bool do_linebreak; +static int indentation_level; + +/* Line breaks and indentation for pretty-printing */ +static void process_linebreak(struct die *cache, int n) +{ + indentation_level += n; + do_linebreak = true; + die_map_add_linebreak(cache, n); +} + +#define DEFINE_GET_ATTR(attr, type) \ + static bool get_##attr##_attr(Dwarf_Die *die, unsigned int id, \ + type *value) \ + { \ + Dwarf_Attribute da; \ + return dwarf_attr(die, id, &da) && \ + !dwarf_form##attr(&da, value); \ + } + +DEFINE_GET_ATTR(flag, bool) +DEFINE_GET_ATTR(udata, Dwarf_Word) + +static bool get_ref_die_attr(Dwarf_Die *die, unsigned int id, Dwarf_Die *value) +{ + Dwarf_Attribute da; + + /* dwarf_formref_die returns a pointer instead of an error value. */ + return dwarf_attr(die, id, &da) && dwarf_formref_die(&da, value); +} + +#define DEFINE_GET_STRING_ATTR(attr) \ + static const char *get_##attr##_attr(Dwarf_Die *die) \ + { \ + Dwarf_Attribute da; \ + if (dwarf_attr(die, DW_AT_##attr, &da)) \ + return dwarf_formstring(&da); \ + return NULL; \ + } + +DEFINE_GET_STRING_ATTR(name) +DEFINE_GET_STRING_ATTR(linkage_name) + +static const char *get_symbol_name(Dwarf_Die *die) +{ + const char *name; + + /* rustc uses DW_AT_linkage_name for exported symbols */ + name = get_linkage_name_attr(die); + if (!name) + name = get_name_attr(die); + + return name; +} + +static bool match_export_symbol(struct state *state, Dwarf_Die *die) +{ + Dwarf_Die *source = die; + Dwarf_Die origin; + + /* If the DIE has an abstract origin, use it for type information. */ + if (get_ref_die_attr(die, DW_AT_abstract_origin, &origin)) + source = &origin; + + state->sym = symbol_get(get_symbol_name(die)); + + /* Look up using the origin name if there are no matches. */ + if (!state->sym && source != die) + state->sym = symbol_get(get_symbol_name(source)); + + state->die = *source; + return !!state->sym; +} + +/* DW_AT_decl_file -> struct srcfile */ +static struct cache srcfile_cache; + +static bool is_definition_private(Dwarf_Die *die) +{ + Dwarf_Word filenum; + Dwarf_Files *files; + Dwarf_Die cudie; + const char *s; + int res; + + /* + * Definitions in .c files cannot change the public ABI, + * so consider them private. + */ + if (!get_udata_attr(die, DW_AT_decl_file, &filenum)) + return false; + + res = cache_get(&srcfile_cache, filenum); + if (res >= 0) + return !!res; + + if (!dwarf_cu_die(die->cu, &cudie, NULL, NULL, NULL, NULL, NULL, NULL)) + error("dwarf_cu_die failed: '%s'", dwarf_errmsg(-1)); + + if (dwarf_getsrcfiles(&cudie, &files, NULL)) + error("dwarf_getsrcfiles failed: '%s'", dwarf_errmsg(-1)); + + s = dwarf_filesrc(files, filenum, NULL, NULL); + if (!s) + error("dwarf_filesrc failed: '%s'", dwarf_errmsg(-1)); + + s = strrchr(s, '.'); + res = s && !strcmp(s, ".c"); + cache_set(&srcfile_cache, filenum, res); + + return !!res; +} + +static bool is_kabi_definition(struct die *cache, Dwarf_Die *die) +{ + bool value; + + if (get_flag_attr(die, DW_AT_declaration, &value) && value) + return false; + + if (kabi_is_declonly(cache->fqn)) + return false; + + return !is_definition_private(die); +} + +/* + * Type string processing + */ +static void process(struct die *cache, const char *s) +{ + s = s ?: "<null>"; + + if (dump_dies && do_linebreak) { + fputs("\n", stderr); + for (int i = 0; i < indentation_level; i++) + fputs(" ", stderr); + do_linebreak = false; + } + if (dump_dies) + fputs(s, stderr); + + if (cache) + die_debug_r("cache %p string '%s'", cache, s); + die_map_add_string(cache, s); +} + +#define MAX_FMT_BUFFER_SIZE 128 + +static void process_fmt(struct die *cache, const char *fmt, ...) +{ + char buf[MAX_FMT_BUFFER_SIZE]; + va_list args; + + va_start(args, fmt); + + if (checkp(vsnprintf(buf, sizeof(buf), fmt, args)) >= sizeof(buf)) + error("vsnprintf overflow: increase MAX_FMT_BUFFER_SIZE"); + + process(cache, buf); + va_end(args); +} + +#define MAX_FQN_SIZE 64 + +/* Get a fully qualified name from DWARF scopes */ +static char *get_fqn(Dwarf_Die *die) +{ + const char *list[MAX_FQN_SIZE]; + Dwarf_Die *scopes = NULL; + bool has_name = false; + char *fqn = NULL; + char *p; + int count = 0; + int len = 0; + int res; + int i; + + res = checkp(dwarf_getscopes_die(die, &scopes)); + if (!res) { + list[count] = get_name_attr(die); + + if (!list[count]) + return NULL; + + len += strlen(list[count]); + count++; + + goto done; + } + + for (i = res - 1; i >= 0 && count < MAX_FQN_SIZE; i--) { + if (dwarf_tag(&scopes[i]) == DW_TAG_compile_unit) + continue; + + list[count] = get_name_attr(&scopes[i]); + + if (list[count]) { + has_name = true; + } else { + list[count] = "<anonymous>"; + has_name = false; + } + + len += strlen(list[count]); + count++; + + if (i > 0) { + list[count++] = "::"; + len += 2; + } + } + + free(scopes); + + if (count == MAX_FQN_SIZE) + warn("increase MAX_FQN_SIZE: reached the maximum"); + + /* Consider the DIE unnamed if the last scope doesn't have a name */ + if (!has_name) + return NULL; +done: + fqn = xmalloc(len + 1); + *fqn = '\0'; + + p = fqn; + for (i = 0; i < count; i++) + p = stpcpy(p, list[i]); + + return fqn; +} + +static void update_fqn(struct die *cache, Dwarf_Die *die) +{ + if (!cache->fqn) + cache->fqn = get_fqn(die) ?: ""; +} + +static void process_fqn(struct die *cache, Dwarf_Die *die) +{ + update_fqn(cache, die); + if (*cache->fqn) + process(cache, " "); + process(cache, cache->fqn); +} + +#define DEFINE_PROCESS_UDATA_ATTRIBUTE(attribute) \ + static void process_##attribute##_attr(struct die *cache, \ + Dwarf_Die *die) \ + { \ + Dwarf_Word value; \ + if (get_udata_attr(die, DW_AT_##attribute, &value)) \ + process_fmt(cache, " " #attribute "(%" PRIu64 ")", \ + value); \ + } + +DEFINE_PROCESS_UDATA_ATTRIBUTE(accessibility) +DEFINE_PROCESS_UDATA_ATTRIBUTE(alignment) +DEFINE_PROCESS_UDATA_ATTRIBUTE(bit_size) +DEFINE_PROCESS_UDATA_ATTRIBUTE(byte_size) +DEFINE_PROCESS_UDATA_ATTRIBUTE(encoding) +DEFINE_PROCESS_UDATA_ATTRIBUTE(data_bit_offset) +DEFINE_PROCESS_UDATA_ATTRIBUTE(data_member_location) +DEFINE_PROCESS_UDATA_ATTRIBUTE(discr_value) + +/* Match functions -- die_match_callback_t */ +#define DEFINE_MATCH(type) \ + static bool match_##type##_type(Dwarf_Die *die) \ + { \ + return dwarf_tag(die) == DW_TAG_##type##_type; \ + } + +DEFINE_MATCH(enumerator) +DEFINE_MATCH(formal_parameter) +DEFINE_MATCH(member) +DEFINE_MATCH(subrange) + +bool match_all(Dwarf_Die *die) +{ + return true; +} + +int process_die_container(struct state *state, struct die *cache, + Dwarf_Die *die, die_callback_t func, + die_match_callback_t match) +{ + Dwarf_Die current; + int res; + + /* Track the first item in lists. */ + if (state) + state->first_list_item = true; + + res = checkp(dwarf_child(die, ¤t)); + while (!res) { + if (match(¤t)) { + /* <0 = error, 0 = continue, >0 = stop */ + res = checkp(func(state, cache, ¤t)); + if (res) + goto out; + } + + res = checkp(dwarf_siblingof(¤t, ¤t)); + } + + res = 0; +out: + if (state) + state->first_list_item = false; + + return res; +} + +static int process_type(struct state *state, struct die *parent, + Dwarf_Die *die); + +static void process_type_attr(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Die type; + + if (get_ref_die_attr(die, DW_AT_type, &type)) { + check(process_type(state, cache, &type)); + return; + } + + /* Compilers can omit DW_AT_type -- print out 'void' to clarify */ + process(cache, "base_type void"); +} + +static void process_list_comma(struct state *state, struct die *cache) +{ + if (state->first_list_item) { + state->first_list_item = false; + } else { + process(cache, " ,"); + process_linebreak(cache, 0); + } +} + +/* Comma-separated with DW_AT_type */ +static void __process_list_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + const char *name = get_name_attr(die); + + if (stable) { + if (is_kabi_prefix(name)) + name = NULL; + state->kabi.orig_name = NULL; + } + + process_list_comma(state, cache); + process(cache, type); + process_type_attr(state, cache, die); + + if (stable && state->kabi.orig_name) + name = state->kabi.orig_name; + if (name) { + process(cache, " "); + process(cache, name); + } + + process_accessibility_attr(cache, die); + process_bit_size_attr(cache, die); + process_data_bit_offset_attr(cache, die); + process_data_member_location_attr(cache, die); +} + +#define DEFINE_PROCESS_LIST_TYPE(type) \ + static void process_##type##_type(struct state *state, \ + struct die *cache, Dwarf_Die *die) \ + { \ + __process_list_type(state, cache, die, #type " "); \ + } + +DEFINE_PROCESS_LIST_TYPE(formal_parameter) +DEFINE_PROCESS_LIST_TYPE(member) + +/* Container types with DW_AT_type */ +static void __process_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + process(cache, type); + process_fqn(cache, die); + process(cache, " {"); + process_linebreak(cache, 1); + process_type_attr(state, cache, die); + process_linebreak(cache, -1); + process(cache, "}"); + process_byte_size_attr(cache, die); + process_alignment_attr(cache, die); +} + +#define DEFINE_PROCESS_TYPE(type) \ + static void process_##type##_type(struct state *state, \ + struct die *cache, Dwarf_Die *die) \ + { \ + __process_type(state, cache, die, #type "_type"); \ + } + +DEFINE_PROCESS_TYPE(atomic) +DEFINE_PROCESS_TYPE(const) +DEFINE_PROCESS_TYPE(immutable) +DEFINE_PROCESS_TYPE(packed) +DEFINE_PROCESS_TYPE(pointer) +DEFINE_PROCESS_TYPE(reference) +DEFINE_PROCESS_TYPE(restrict) +DEFINE_PROCESS_TYPE(rvalue_reference) +DEFINE_PROCESS_TYPE(shared) +DEFINE_PROCESS_TYPE(template_type_parameter) +DEFINE_PROCESS_TYPE(volatile) +DEFINE_PROCESS_TYPE(typedef) + +static void process_subrange_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Word count = 0; + + if (get_udata_attr(die, DW_AT_count, &count)) + process_fmt(cache, "[%" PRIu64 "]", count); + else if (get_udata_attr(die, DW_AT_upper_bound, &count)) + process_fmt(cache, "[%" PRIu64 "]", count + 1); + else + process(cache, "[]"); +} + +static void process_array_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "array_type"); + /* Array size */ + check(process_die_container(state, cache, die, process_type, + match_subrange_type)); + process(cache, " {"); + process_linebreak(cache, 1); + process_type_attr(state, cache, die); + process_linebreak(cache, -1); + process(cache, "}"); +} + +static void __process_subroutine_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type) +{ + process(cache, type); + process(cache, " ("); + process_linebreak(cache, 1); + /* Parameters */ + check(process_die_container(state, cache, die, process_type, + match_formal_parameter_type)); + process_linebreak(cache, -1); + process(cache, ")"); + process_linebreak(cache, 0); + /* Return type */ + process(cache, "-> "); + process_type_attr(state, cache, die); +} + +static void process_subroutine_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_subroutine_type(state, cache, die, "subroutine_type"); +} + +static void process_variant_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process_list_comma(state, cache); + process(cache, "variant {"); + process_linebreak(cache, 1); + check(process_die_container(state, cache, die, process_type, + match_member_type)); + process_linebreak(cache, -1); + process(cache, "}"); + process_discr_value_attr(cache, die); +} + +static void process_variant_part_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process_list_comma(state, cache); + process(cache, "variant_part {"); + process_linebreak(cache, 1); + check(process_die_container(state, cache, die, process_type, + match_all)); + process_linebreak(cache, -1); + process(cache, "}"); +} + +static int get_kabi_status(Dwarf_Die *die, const char **suffix) +{ + const char *name = get_name_attr(die); + + if (suffix) + *suffix = NULL; + + if (is_kabi_prefix(name)) { + name += KABI_PREFIX_LEN; + + if (!strncmp(name, KABI_RESERVED_PREFIX, + KABI_RESERVED_PREFIX_LEN)) + return KABI_RESERVED; + if (!strncmp(name, KABI_IGNORED_PREFIX, + KABI_IGNORED_PREFIX_LEN)) + return KABI_IGNORED; + + if (!strncmp(name, KABI_RENAMED_PREFIX, + KABI_RENAMED_PREFIX_LEN)) { + if (suffix) { + name += KABI_RENAMED_PREFIX_LEN; + *suffix = name; + } + return KABI_RESERVED; + } + } + + return KABI_NORMAL; +} + +static int check_struct_member_kabi_status(struct state *state, + struct die *__unused, Dwarf_Die *die) +{ + int res; + + assert(dwarf_tag(die) == DW_TAG_member_type); + + /* + * If the union member is a struct, expect the __kabi field to + * be the first member of the structure, i.e..: + * + * union { + * type new_member; + * struct { + * type __kabi_field; + * } + * }; + */ + res = get_kabi_status(die, &state->kabi.orig_name); + + if (res == KABI_RESERVED && + !get_ref_die_attr(die, DW_AT_type, &state->kabi.placeholder)) + error("structure member missing a type?"); + + return res; +} + +static int check_union_member_kabi_status(struct state *state, + struct die *__unused, Dwarf_Die *die) +{ + Dwarf_Die type; + int res; + + assert(dwarf_tag(die) == DW_TAG_member_type); + + if (!get_ref_die_attr(die, DW_AT_type, &type)) + error("union member missing a type?"); + + /* + * We expect a union with two members. Check if either of them + * has a __kabi name prefix, i.e.: + * + * union { + * ... + * type memberN; // <- type, N = {0,1} + * ... + * }; + * + * The member can also be a structure type, in which case we'll + * check the first structure member. + * + * In any case, stop processing after we've seen two members. + */ + res = get_kabi_status(die, &state->kabi.orig_name); + + if (res == KABI_RESERVED) + state->kabi.placeholder = type; + if (res != KABI_NORMAL) + return res; + + if (dwarf_tag(&type) == DW_TAG_structure_type) + res = checkp(process_die_container( + state, NULL, &type, check_struct_member_kabi_status, + match_member_type)); + + if (res <= KABI_NORMAL && ++state->kabi.members < 2) + return 0; /* Continue */ + + return res; +} + +static int get_union_kabi_status(Dwarf_Die *die, Dwarf_Die *placeholder, + const char **orig_name) +{ + struct state state; + int res; + + if (!stable) + return KABI_NORMAL; + + /* + * To maintain a stable kABI, distributions may choose to reserve + * space in structs for later use by adding placeholder members, + * for example: + * + * struct s { + * u32 a; + * // an 8-byte placeholder for future use + * u64 __kabi_reserved_0; + * }; + * + * When the reserved member is taken into use, the type change + * would normally cause the symbol version to change as well, but + * if the replacement uses the following convention, gendwarfksyms + * continues to use the placeholder type for versioning instead, + * thus maintaining the same symbol version: + * + * struct s { + * u32 a; + * union { + * // placeholder replaced with a new member `b` + * struct t b; + * struct { + * // the placeholder type that is still + * // used for versioning + * u64 __kabi_reserved_0; + * }; + * }; + * }; + * + * I.e., as long as the replaced member is in a union, and the + * placeholder has a __kabi_reserved name prefix, we'll continue + * to use the placeholder type (here u64) for version calculation + * instead of the union type. + * + * It's also possible to ignore new members from versioning if + * they've been added to alignment holes, for example, by + * including them in a union with another member that uses the + * __kabi_ignored name prefix: + * + * struct s { + * u32 a; + * // an alignment hole is used to add `n` + * union { + * u32 n; + * // hide the entire union member from versioning + * u8 __kabi_ignored_0; + * }; + * u64 b; + * }; + * + * Note that the user of this feature is responsible for ensuring + * that the structure actually remains ABI compatible. + */ + memset(&state.kabi, 0, sizeof(struct kabi_state)); + + res = checkp(process_die_container(&state, NULL, die, + check_union_member_kabi_status, + match_member_type)); + + if (res == KABI_RESERVED) { + if (placeholder) + *placeholder = state.kabi.placeholder; + if (orig_name) + *orig_name = state.kabi.orig_name; + } + + return res; +} + +static bool is_kabi_ignored(Dwarf_Die *die) +{ + Dwarf_Die type; + + if (!stable) + return false; + + if (!get_ref_die_attr(die, DW_AT_type, &type)) + error("member missing a type?"); + + return dwarf_tag(&type) == DW_TAG_union_type && + checkp(get_union_kabi_status(&type, NULL, NULL)) == KABI_IGNORED; +} + +static int ___process_structure_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + switch (dwarf_tag(die)) { + case DW_TAG_member: + if (is_kabi_ignored(die)) + return 0; + return check(process_type(state, cache, die)); + case DW_TAG_variant_part: + return check(process_type(state, cache, die)); + case DW_TAG_class_type: + case DW_TAG_enumeration_type: + case DW_TAG_structure_type: + case DW_TAG_template_type_parameter: + case DW_TAG_union_type: + case DW_TAG_subprogram: + /* Skip non-member types, including member functions */ + return 0; + default: + error("unexpected structure_type child: %x", dwarf_tag(die)); + } +} + +static void __process_structure_type(struct state *state, struct die *cache, + Dwarf_Die *die, const char *type, + die_callback_t process_func, + die_match_callback_t match_func) +{ + bool expand; + + process(cache, type); + process_fqn(cache, die); + process(cache, " {"); + process_linebreak(cache, 1); + + expand = state->expand.expand && is_kabi_definition(cache, die); + + if (expand) { + state->expand.current_fqn = cache->fqn; + check(process_die_container(state, cache, die, process_func, + match_func)); + } + + process_linebreak(cache, -1); + process(cache, "}"); + + if (expand) { + process_byte_size_attr(cache, die); + process_alignment_attr(cache, die); + } +} + +#define DEFINE_PROCESS_STRUCTURE_TYPE(structure) \ + static void process_##structure##_type( \ + struct state *state, struct die *cache, Dwarf_Die *die) \ + { \ + __process_structure_type(state, cache, die, \ + #structure "_type", \ + ___process_structure_type, \ + match_all); \ + } + +DEFINE_PROCESS_STRUCTURE_TYPE(class) +DEFINE_PROCESS_STRUCTURE_TYPE(structure) + +static void process_union_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + Dwarf_Die placeholder; + + int res = checkp(get_union_kabi_status(die, &placeholder, + &state->kabi.orig_name)); + + if (res == KABI_RESERVED) + check(process_type(state, cache, &placeholder)); + if (res > KABI_NORMAL) + return; + + __process_structure_type(state, cache, die, "union_type", + ___process_structure_type, match_all); +} + +static void process_enumerator_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + bool overridden = false; + Dwarf_Word value; + + if (stable) { + /* Get the fqn before we process anything */ + update_fqn(cache, die); + + if (kabi_is_enumerator_ignored(state->expand.current_fqn, + cache->fqn)) + return; + + overridden = kabi_get_enumerator_value( + state->expand.current_fqn, cache->fqn, &value); + } + + process_list_comma(state, cache); + process(cache, "enumerator"); + process_fqn(cache, die); + + if (overridden || get_udata_attr(die, DW_AT_const_value, &value)) { + process(cache, " = "); + process_fmt(cache, "%" PRIu64, value); + } +} + +static void process_enumeration_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_structure_type(state, cache, die, "enumeration_type", + process_type, match_enumerator_type); +} + +static void process_base_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "base_type"); + process_fqn(cache, die); + process_byte_size_attr(cache, die); + process_encoding_attr(cache, die); + process_alignment_attr(cache, die); +} + +static void process_unspecified_type(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + /* + * These can be emitted for stand-alone assembly code, which means we + * might run into them in vmlinux.o. + */ + process(cache, "unspecified_type"); +} + +static void process_cached(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + struct die_fragment *df; + Dwarf_Die child; + + list_for_each_entry(df, &cache->fragments, list) { + switch (df->type) { + case FRAGMENT_STRING: + die_debug_b("cache %p STRING '%s'", cache, + df->data.str); + process(NULL, df->data.str); + break; + case FRAGMENT_LINEBREAK: + process_linebreak(NULL, df->data.linebreak); + break; + case FRAGMENT_DIE: + if (!dwarf_die_addr_die(dwarf_cu_getdwarf(die->cu), + (void *)df->data.addr, &child)) + error("dwarf_die_addr_die failed"); + die_debug_b("cache %p DIE addr %" PRIxPTR " tag %x", + cache, df->data.addr, dwarf_tag(&child)); + check(process_type(state, NULL, &child)); + break; + default: + error("empty die_fragment"); + } + } +} + +static void state_init(struct state *state) +{ + state->expand.expand = true; + state->expand.current_fqn = NULL; + cache_init(&state->expansion_cache); +} + +static void expansion_state_restore(struct expansion_state *state, + struct expansion_state *saved) +{ + state->expand = saved->expand; + state->current_fqn = saved->current_fqn; +} + +static void expansion_state_save(struct expansion_state *state, + struct expansion_state *saved) +{ + expansion_state_restore(saved, state); +} + +static bool is_expanded_type(int tag) +{ + return tag == DW_TAG_class_type || tag == DW_TAG_structure_type || + tag == DW_TAG_union_type || tag == DW_TAG_enumeration_type; +} + +#define PROCESS_TYPE(type) \ + case DW_TAG_##type##_type: \ + process_##type##_type(state, cache, die); \ + break; + +static int process_type(struct state *state, struct die *parent, Dwarf_Die *die) +{ + enum die_state want_state = DIE_COMPLETE; + struct die *cache; + struct expansion_state saved; + int tag = dwarf_tag(die); + + expansion_state_save(&state->expand, &saved); + + /* + * Structures and enumeration types are expanded only once per + * exported symbol. This is sufficient for detecting ABI changes + * within the structure. + */ + if (is_expanded_type(tag)) { + if (cache_was_expanded(&state->expansion_cache, die->addr)) + state->expand.expand = false; + + if (state->expand.expand) + cache_mark_expanded(&state->expansion_cache, die->addr); + else + want_state = DIE_UNEXPANDED; + } + + /* + * If we have want_state already cached, use it instead of walking + * through DWARF. + */ + cache = die_map_get(die, want_state); + + if (cache->state == want_state) { + die_debug_g("cached addr %p tag %x -- %s", die->addr, tag, + die_state_name(cache->state)); + + process_cached(state, cache, die); + die_map_add_die(parent, cache); + + expansion_state_restore(&state->expand, &saved); + return 0; + } + + die_debug_g("addr %p tag %x -- %s -> %s", die->addr, tag, + die_state_name(cache->state), die_state_name(want_state)); + + switch (tag) { + /* Type modifiers */ + PROCESS_TYPE(atomic) + PROCESS_TYPE(const) + PROCESS_TYPE(immutable) + PROCESS_TYPE(packed) + PROCESS_TYPE(pointer) + PROCESS_TYPE(reference) + PROCESS_TYPE(restrict) + PROCESS_TYPE(rvalue_reference) + PROCESS_TYPE(shared) + PROCESS_TYPE(volatile) + /* Container types */ + PROCESS_TYPE(class) + PROCESS_TYPE(structure) + PROCESS_TYPE(union) + PROCESS_TYPE(enumeration) + /* Subtypes */ + PROCESS_TYPE(enumerator) + PROCESS_TYPE(formal_parameter) + PROCESS_TYPE(member) + PROCESS_TYPE(subrange) + PROCESS_TYPE(template_type_parameter) + PROCESS_TYPE(variant) + PROCESS_TYPE(variant_part) + /* Other types */ + PROCESS_TYPE(array) + PROCESS_TYPE(base) + PROCESS_TYPE(subroutine) + PROCESS_TYPE(typedef) + PROCESS_TYPE(unspecified) + default: + error("unexpected type: %x", tag); + } + + die_debug_r("parent %p cache %p die addr %p tag %x", parent, cache, + die->addr, tag); + + /* Update cache state and append to the parent (if any) */ + cache->tag = tag; + cache->state = want_state; + die_map_add_die(parent, cache); + + expansion_state_restore(&state->expand, &saved); + return 0; +} + +/* + * Exported symbol processing + */ +static struct die *get_symbol_cache(struct state *state, Dwarf_Die *die) +{ + struct die *cache; + + cache = die_map_get(die, DIE_SYMBOL); + + if (cache->state != DIE_INCOMPLETE) + return NULL; /* We already processed a symbol for this DIE */ + + cache->tag = dwarf_tag(die); + return cache; +} + +static void process_symbol(struct state *state, Dwarf_Die *die, + die_callback_t process_func) +{ + struct die *cache; + + symbol_set_die(state->sym, die); + + cache = get_symbol_cache(state, die); + if (!cache) + return; + + debug("%s", state->sym->name); + check(process_func(state, cache, die)); + cache->state = DIE_SYMBOL; + if (dump_dies) + fputs("\n", stderr); +} + +static int __process_subprogram(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + __process_subroutine_type(state, cache, die, "subprogram"); + return 0; +} + +static void process_subprogram(struct state *state, Dwarf_Die *die) +{ + process_symbol(state, die, __process_subprogram); +} + +static int __process_variable(struct state *state, struct die *cache, + Dwarf_Die *die) +{ + process(cache, "variable "); + process_type_attr(state, cache, die); + return 0; +} + +static void process_variable(struct state *state, Dwarf_Die *die) +{ + process_symbol(state, die, __process_variable); +} + +static void save_symbol_ptr(struct state *state) +{ + Dwarf_Die ptr_type; + Dwarf_Die type; + + if (!get_ref_die_attr(&state->die, DW_AT_type, &ptr_type) || + dwarf_tag(&ptr_type) != DW_TAG_pointer_type) + error("%s must be a pointer type!", + get_symbol_name(&state->die)); + + if (!get_ref_die_attr(&ptr_type, DW_AT_type, &type)) + error("%s pointer missing a type attribute?", + get_symbol_name(&state->die)); + + /* + * Save the symbol pointer DIE in case the actual symbol is + * missing from the DWARF. Clang, for example, intentionally + * omits external symbols from the debugging information. + */ + if (dwarf_tag(&type) == DW_TAG_subroutine_type) + symbol_set_ptr(state->sym, &type); + else + symbol_set_ptr(state->sym, &ptr_type); +} + +static int process_exported_symbols(struct state *unused, struct die *cache, + Dwarf_Die *die) +{ + int tag = dwarf_tag(die); + + switch (tag) { + /* Possible containers of exported symbols */ + case DW_TAG_namespace: + case DW_TAG_class_type: + case DW_TAG_structure_type: + return check(process_die_container( + NULL, cache, die, process_exported_symbols, match_all)); + + /* Possible exported symbols */ + case DW_TAG_subprogram: + case DW_TAG_variable: { + struct state state; + + if (!match_export_symbol(&state, die)) + return 0; + + state_init(&state); + + if (is_symbol_ptr(get_symbol_name(&state.die))) + save_symbol_ptr(&state); + else if (tag == DW_TAG_subprogram) + process_subprogram(&state, &state.die); + else + process_variable(&state, &state.die); + + cache_free(&state.expansion_cache); + return 0; + } + default: + return 0; + } +} + +static void process_symbol_ptr(struct symbol *sym, void *arg) +{ + struct state state; + Dwarf *dwarf = arg; + + if (sym->state != SYMBOL_UNPROCESSED || !sym->ptr_die_addr) + return; + + debug("%s", sym->name); + state_init(&state); + state.sym = sym; + + if (!dwarf_die_addr_die(dwarf, (void *)sym->ptr_die_addr, &state.die)) + error("dwarf_die_addr_die failed for symbol ptr: '%s'", + sym->name); + + if (dwarf_tag(&state.die) == DW_TAG_subroutine_type) + process_subprogram(&state, &state.die); + else + process_variable(&state, &state.die); + + cache_free(&state.expansion_cache); +} + +void process_cu(Dwarf_Die *cudie) +{ + check(process_die_container(NULL, NULL, cudie, process_exported_symbols, + match_all)); + + symbol_for_each(process_symbol_ptr, dwarf_cu_getdwarf(cudie->cu)); + + cache_free(&srcfile_cache); +} diff --git a/scripts/gendwarfksyms/examples/kabi.h b/scripts/gendwarfksyms/examples/kabi.h new file mode 100644 index 000000000000..97a5669b083d --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Google LLC + * + * Example macros for maintaining kABI stability. + * + * This file is based on android_kabi.h, which has the following notice: + * + * Heavily influenced by rh_kabi.h which came from the RHEL/CENTOS kernel + * and was: + * Copyright (c) 2014 Don Zickus + * Copyright (c) 2015-2018 Jiri Benc + * Copyright (c) 2015 Sabrina Dubroca, Hannes Frederic Sowa + * Copyright (c) 2016-2018 Prarit Bhargava + * Copyright (c) 2017 Paolo Abeni, Larry Woodman + */ + +#ifndef __KABI_H__ +#define __KABI_H__ + +/* Kernel macros for userspace testing. */ +#ifndef __aligned +#define __aligned(x) __attribute__((__aligned__(x))) +#endif +#ifndef __used +#define __used __attribute__((__used__)) +#endif +#ifndef __section +#define __section(section) __attribute__((__section__(section))) +#endif +#ifndef __PASTE +#define ___PASTE(a, b) a##b +#define __PASTE(a, b) ___PASTE(a, b) +#endif +#ifndef __stringify +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) +#endif + +#define __KABI_RULE(hint, target, value) \ + static const char __PASTE(__gendwarfksyms_rule_, \ + __COUNTER__)[] __used __aligned(1) \ + __section(".discard.gendwarfksyms.kabi_rules") = \ + "1\0" #hint "\0" #target "\0" #value + +#define __KABI_NORMAL_SIZE_ALIGN(_orig, _new) \ + union { \ + _Static_assert( \ + sizeof(struct { _new; }) <= sizeof(struct { _orig; }), \ + __FILE__ ":" __stringify(__LINE__) ": " __stringify( \ + _new) " is larger than " __stringify(_orig)); \ + _Static_assert( \ + __alignof__(struct { _new; }) <= \ + __alignof__(struct { _orig; }), \ + __FILE__ ":" __stringify(__LINE__) ": " __stringify( \ + _orig) " is not aligned the same as " __stringify(_new)); \ + } + +#define __KABI_REPLACE(_orig, _new) \ + union { \ + _new; \ + struct { \ + _orig; \ + }; \ + __KABI_NORMAL_SIZE_ALIGN(_orig, _new); \ + } + +/* + * KABI_DECLONLY(fqn) + * Treat the struct/union/enum fqn as a declaration, i.e. even if + * a definition is available, don't expand the contents. + */ +#define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, ) + +/* + * KABI_ENUMERATOR_IGNORE(fqn, field) + * When expanding enum fqn, skip the provided field. This makes it + * possible to hide added enum fields from versioning. + */ +#define KABI_ENUMERATOR_IGNORE(fqn, field) \ + __KABI_RULE(enumerator_ignore, fqn field, ) + +/* + * KABI_ENUMERATOR_VALUE(fqn, field, value) + * When expanding enum fqn, use the provided value for the + * specified field. This makes it possible to override enumerator + * values when calculating versions. + */ +#define KABI_ENUMERATOR_VALUE(fqn, field, value) \ + __KABI_RULE(enumerator_value, fqn field, value) + +/* + * KABI_RESERVE + * Reserve some "padding" in a structure for use by LTS backports. + * This is normally placed at the end of a structure. + * number: the "number" of the padding variable in the structure. Start with + * 1 and go up. + */ +#define KABI_RESERVE(n) unsigned long __kabi_reserved##n + +/* + * KABI_RESERVE_ARRAY + * Same as _BACKPORT_RESERVE but allocates an array with the specified + * size in bytes. + */ +#define KABI_RESERVE_ARRAY(n, s) \ + unsigned char __aligned(8) __kabi_reserved##n[s] + +/* + * KABI_IGNORE + * Add a new field that's ignored in versioning. + */ +#define KABI_IGNORE(n, _new) \ + union { \ + _new; \ + unsigned char __kabi_ignored##n; \ + } + +/* + * KABI_REPLACE + * Replace a field with a compatible new field. + */ +#define KABI_REPLACE(_oldtype, _oldname, _new) \ + __KABI_REPLACE(_oldtype __kabi_renamed##_oldname, struct { _new; }) + +/* + * KABI_USE(number, _new) + * Use a previous padding entry that was defined with KABI_RESERVE + * number: the previous "number" of the padding variable + * _new: the variable to use now instead of the padding variable + */ +#define KABI_USE(number, _new) __KABI_REPLACE(KABI_RESERVE(number), _new) + +/* + * KABI_USE2(number, _new1, _new2) + * Use a previous padding entry that was defined with KABI_RESERVE for + * two new variables that fit into 64 bits. This is good for when you do not + * want to "burn" a 64bit padding variable for a smaller variable size if not + * needed. + */ +#define KABI_USE2(number, _new1, _new2) \ + __KABI_REPLACE( \ + KABI_RESERVE(number), struct { \ + _new1; \ + _new2; \ + }) +/* + * KABI_USE_ARRAY(number, bytes, _new) + * Use a previous padding entry that was defined with KABI_RESERVE_ARRAY + * number: the previous "number" of the padding variable + * bytes: the size in bytes reserved for the array + * _new: the variable to use now instead of the padding variable + */ +#define KABI_USE_ARRAY(number, bytes, _new) \ + __KABI_REPLACE(KABI_RESERVE_ARRAY(number, bytes), _new) + +#endif /* __KABI_H__ */ diff --git a/scripts/gendwarfksyms/examples/kabi_ex.c b/scripts/gendwarfksyms/examples/kabi_ex.c new file mode 100644 index 000000000000..0b7ffd830541 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * kabi_ex.c + * + * Copyright (C) 2024 Google LLC + * + * Examples for kABI stability features with --stable. See kabi_ex.h + * for details. + */ + +#include "kabi_ex.h" + +struct s e0; +enum e e1; + +struct ex0a ex0a; +struct ex0b ex0b; +struct ex0c ex0c; + +struct ex1a ex1a; +struct ex1b ex1b; +struct ex1c ex1c; + +struct ex2a ex2a; +struct ex2b ex2b; +struct ex2c ex2c; + +struct ex3a ex3a; +struct ex3b ex3b; +struct ex3c ex3c; diff --git a/scripts/gendwarfksyms/examples/kabi_ex.h b/scripts/gendwarfksyms/examples/kabi_ex.h new file mode 100644 index 000000000000..1736e0f65208 --- /dev/null +++ b/scripts/gendwarfksyms/examples/kabi_ex.h @@ -0,0 +1,263 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * kabi_ex.h + * + * Copyright (C) 2024 Google LLC + * + * Examples for kABI stability features with --stable. + */ + +/* + * The comments below each example contain the expected gendwarfksyms + * output, which can be verified using LLVM's FileCheck tool: + * + * https://llvm.org/docs/CommandGuide/FileCheck.html + * + * Usage: + * + * $ gcc -g -c examples/kabi_ex.c -o examples/kabi_ex.o + * + * $ nm examples/kabi_ex.o | awk '{ print $NF }' | \ + * ./gendwarfksyms --stable --dump-dies \ + * examples/kabi_ex.o 2>&1 >/dev/null | \ + * FileCheck examples/kabi_ex.h --check-prefix=STABLE + */ + +#ifndef __KABI_EX_H__ +#define __KABI_EX_H__ + +#include "kabi.h" + +/* + * Example: kABI rules + */ + +struct s { + int a; +}; + +KABI_DECLONLY(s); + +/* + * STABLE: variable structure_type s { + * STABLE-NEXT: } + */ + +enum e { + A, + B, + C, + D, +}; + +KABI_ENUMERATOR_IGNORE(e, B); +KABI_ENUMERATOR_IGNORE(e, C); +KABI_ENUMERATOR_VALUE(e, D, 123456789); + +/* + * STABLE: variable enumeration_type e { + * STABLE-NEXT: enumerator A = 0 , + * STABLE-NEXT: enumerator D = 123456789 + * STABLE-NEXT: } byte_size(4) +*/ + +/* + * Example: Reserved fields + */ +struct ex0a { + int a; + KABI_RESERVE(0); + KABI_RESERVE(1); +}; + +/* + * STABLE: variable structure_type ex0a { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +struct ex0b { + int a; + KABI_RESERVE(0); + KABI_USE2(1, int b, int c); +}; + +/* + * STABLE: variable structure_type ex0b { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +struct ex0c { + int a; + KABI_USE(0, void *p); + KABI_USE2(1, int b, int c); +}; + +/* + * STABLE: variable structure_type ex0c { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16) + * STABLE-NEXT: } byte_size(24) + */ + +/* + * Example: A reserved array + */ + +struct ex1a { + unsigned int a; + KABI_RESERVE_ARRAY(0, 64); +}; + +/* + * STABLE: variable structure_type ex1a { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +struct ex1b { + unsigned int a; + KABI_USE_ARRAY( + 0, 64, struct { + void *p; + KABI_RESERVE_ARRAY(1, 56); + }); +}; + +/* + * STABLE: variable structure_type ex1b { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +struct ex1c { + unsigned int a; + KABI_USE_ARRAY(0, 64, void *p[8]); +}; + +/* + * STABLE: variable structure_type ex1c { + * STABLE-NEXT: member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) , + * STABLE-NEXT: member array_type[64] { + * STABLE-NEXT: base_type unsigned char byte_size(1) encoding(8) + * STABLE-NEXT: } data_member_location(8) + * STABLE-NEXT: } byte_size(72) + */ + +/* + * Example: An ignored field added to an alignment hole + */ + +struct ex2a { + int a; + unsigned long b; + int c; + unsigned long d; +}; + +/* + * STABLE: variable structure_type ex2a { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + +struct ex2b { + int a; + KABI_IGNORE(0, unsigned int n); + unsigned long b; + int c; + unsigned long d; +}; + +_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2b), "ex2a size doesn't match ex2b"); + +/* + * STABLE: variable structure_type ex2b { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + +struct ex2c { + int a; + KABI_IGNORE(0, unsigned int n); + unsigned long b; + int c; + KABI_IGNORE(1, unsigned int m); + unsigned long d; +}; + +_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2c), "ex2a size doesn't match ex2c"); + +/* + * STABLE: variable structure_type ex2c { + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) a data_member_location(0) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8) + * STABLE-NEXT: member base_type int byte_size(4) encoding(5) c data_member_location(16) , + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24) + * STABLE-NEXT: } byte_size(32) + */ + + +/* + * Example: A replaced field + */ + +struct ex3a { + unsigned long a; + unsigned long unused; +}; + +/* + * STABLE: variable structure_type ex3a { + * STABLE-NEXT: member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +struct ex3b { + unsigned long a; + KABI_REPLACE(unsigned long, unused, unsigned long renamed); +}; + +_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3b), "ex3a size doesn't match ex3b"); + +/* + * STABLE: variable structure_type ex3b { + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +struct ex3c { + unsigned long a; + KABI_REPLACE(unsigned long, unused, long replaced); +}; + +_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3c), "ex3a size doesn't match ex3c"); + +/* + * STABLE: variable structure_type ex3c { + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0) + * STABLE-NEXT: member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8) + * STABLE-NEXT: } byte_size(16) + */ + +#endif /* __KABI_EX_H__ */ diff --git a/scripts/gendwarfksyms/examples/symbolptr.c b/scripts/gendwarfksyms/examples/symbolptr.c new file mode 100644 index 000000000000..88bc1bd60da8 --- /dev/null +++ b/scripts/gendwarfksyms/examples/symbolptr.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + * + * Example for symbol pointers. When compiled with Clang, gendwarfkyms + * uses a symbol pointer for `f`. + * + * $ clang -g -c examples/symbolptr.c -o examples/symbolptr.o + * $ echo -e "f\ng\np" | ./gendwarfksyms -d examples/symbolptr.o + */ + +/* Kernel macros for userspace testing. */ +#ifndef __used +#define __used __attribute__((__used__)) +#endif +#ifndef __section +#define __section(section) __attribute__((__section__(section))) +#endif + +#define __GENDWARFKSYMS_EXPORT(sym) \ + static typeof(sym) *__gendwarfksyms_ptr_##sym __used \ + __section(".discard.gendwarfksyms") = &sym; + +extern void f(unsigned int arg); +void g(int *arg); +void g(int *arg) {} + +struct s; +extern struct s *p; + +__GENDWARFKSYMS_EXPORT(f); +__GENDWARFKSYMS_EXPORT(g); +__GENDWARFKSYMS_EXPORT(p); diff --git a/scripts/gendwarfksyms/gendwarfksyms.c b/scripts/gendwarfksyms/gendwarfksyms.c new file mode 100644 index 000000000000..08ae61eb327e --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include <fcntl.h> +#include <getopt.h> +#include <errno.h> +#include <stdarg.h> +#include <string.h> +#include <unistd.h> +#include "gendwarfksyms.h" + +/* + * Options + */ + +/* Print debugging information to stderr */ +int debug; +/* Dump DIE contents */ +int dump_dies; +/* Print debugging information about die_map changes */ +int dump_die_map; +/* Print out type strings (i.e. type_map) */ +int dump_types; +/* Print out expanded type strings used for symbol versions */ +int dump_versions; +/* Support kABI stability features */ +int stable; +/* Write a symtypes file */ +int symtypes; +static const char *symtypes_file; + +static void usage(void) +{ + fputs("Usage: gendwarfksyms [options] elf-object-file ... < symbol-list\n\n" + "Options:\n" + " -d, --debug Print debugging information\n" + " --dump-dies Dump DWARF DIE contents\n" + " --dump-die-map Print debugging information about die_map changes\n" + " --dump-types Dump type strings\n" + " --dump-versions Dump expanded type strings used for symbol versions\n" + " -s, --stable Support kABI stability features\n" + " -T, --symtypes file Write a symtypes file\n" + " -h, --help Print this message\n" + "\n", + stderr); +} + +static int process_module(Dwfl_Module *mod, void **userdata, const char *name, + Dwarf_Addr base, void *arg) +{ + Dwarf_Addr dwbias; + Dwarf_Die cudie; + Dwarf_CU *cu = NULL; + Dwarf *dbg; + FILE *symfile = arg; + int res; + + debug("%s", name); + dbg = dwfl_module_getdwarf(mod, &dwbias); + + /* + * Look for exported symbols in each CU, follow the DIE tree, and add + * the entries to die_map. + */ + do { + res = dwarf_get_units(dbg, cu, &cu, NULL, NULL, &cudie, NULL); + if (res < 0) + error("dwarf_get_units failed: no debugging information?"); + if (res == 1) + break; /* No more units */ + + process_cu(&cudie); + } while (cu); + + /* + * Use die_map to expand type strings, write them to `symfile`, and + * calculate symbol versions. + */ + generate_symtypes_and_versions(symfile); + die_map_free(); + + return DWARF_CB_OK; +} + +static const Dwfl_Callbacks callbacks = { + .section_address = dwfl_offline_section_address, + .find_debuginfo = dwfl_standard_find_debuginfo, +}; + +int main(int argc, char **argv) +{ + FILE *symfile = NULL; + unsigned int n; + int opt; + + static const struct option opts[] = { + { "debug", 0, NULL, 'd' }, + { "dump-dies", 0, &dump_dies, 1 }, + { "dump-die-map", 0, &dump_die_map, 1 }, + { "dump-types", 0, &dump_types, 1 }, + { "dump-versions", 0, &dump_versions, 1 }, + { "stable", 0, NULL, 's' }, + { "symtypes", 1, NULL, 'T' }, + { "help", 0, NULL, 'h' }, + { 0, 0, NULL, 0 } + }; + + while ((opt = getopt_long(argc, argv, "dsT:h", opts, NULL)) != EOF) { + switch (opt) { + case 0: + break; + case 'd': + debug = 1; + break; + case 's': + stable = 1; + break; + case 'T': + symtypes = 1; + symtypes_file = optarg; + break; + case 'h': + usage(); + return 0; + default: + usage(); + return 1; + } + } + + if (dump_die_map) + dump_dies = 1; + + if (optind >= argc) { + usage(); + error("no input files?"); + } + + symbol_read_exports(stdin); + + if (symtypes_file) { + symfile = fopen(symtypes_file, "w"); + if (!symfile) + error("fopen failed for '%s': %s", symtypes_file, + strerror(errno)); + } + + for (n = optind; n < argc; n++) { + Dwfl *dwfl; + int fd; + + fd = open(argv[n], O_RDONLY); + if (fd == -1) + error("open failed for '%s': %s", argv[n], + strerror(errno)); + + symbol_read_symtab(fd); + kabi_read_rules(fd); + + dwfl = dwfl_begin(&callbacks); + if (!dwfl) + error("dwfl_begin failed for '%s': %s", argv[n], + dwarf_errmsg(-1)); + + if (!dwfl_report_offline(dwfl, argv[n], argv[n], fd)) + error("dwfl_report_offline failed for '%s': %s", + argv[n], dwarf_errmsg(-1)); + + dwfl_report_end(dwfl, NULL, NULL); + + if (dwfl_getmodules(dwfl, &process_module, symfile, 0)) + error("dwfl_getmodules failed for '%s'", argv[n]); + + dwfl_end(dwfl); + kabi_free(); + } + + if (symfile) + check(fclose(symfile)); + + symbol_print_versions(); + symbol_free(); + + return 0; +} diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h new file mode 100644 index 000000000000..197a1a8123c6 --- /dev/null +++ b/scripts/gendwarfksyms/gendwarfksyms.h @@ -0,0 +1,296 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Google LLC + */ + +#include <dwarf.h> +#include <elfutils/libdw.h> +#include <elfutils/libdwfl.h> +#include <stdlib.h> +#include <stdio.h> + +#include <hash.h> +#include <hashtable.h> +#include <xalloc.h> + +#ifndef __GENDWARFKSYMS_H +#define __GENDWARFKSYMS_H + +/* + * Options -- in gendwarfksyms.c + */ +extern int debug; +extern int dump_dies; +extern int dump_die_map; +extern int dump_types; +extern int dump_versions; +extern int stable; +extern int symtypes; + +/* + * Output helpers + */ +#define __PREFIX "gendwarfksyms: " +#define __println(prefix, format, ...) \ + fprintf(stderr, prefix __PREFIX "%s: " format "\n", __func__, \ + ##__VA_ARGS__) + +#define debug(format, ...) \ + do { \ + if (debug) \ + __println("", format, ##__VA_ARGS__); \ + } while (0) + +#define warn(format, ...) __println("warning: ", format, ##__VA_ARGS__) +#define error(format, ...) \ + do { \ + __println("error: ", format, ##__VA_ARGS__); \ + exit(1); \ + } while (0) + +#define __die_debug(color, format, ...) \ + do { \ + if (dump_dies && dump_die_map) \ + fprintf(stderr, \ + "\033[" #color "m<" format ">\033[39m", \ + __VA_ARGS__); \ + } while (0) + +#define die_debug_r(format, ...) __die_debug(91, format, __VA_ARGS__) +#define die_debug_g(format, ...) __die_debug(92, format, __VA_ARGS__) +#define die_debug_b(format, ...) __die_debug(94, format, __VA_ARGS__) + +/* + * Error handling helpers + */ +#define __check(expr, test) \ + ({ \ + int __res = expr; \ + if (test) \ + error("`%s` failed: %d", #expr, __res); \ + __res; \ + }) + +/* Error == non-zero values */ +#define check(expr) __check(expr, __res) +/* Error == negative values */ +#define checkp(expr) __check(expr, __res < 0) + +/* Consistent aliases (DW_TAG_<type>_type) for DWARF tags */ +#define DW_TAG_enumerator_type DW_TAG_enumerator +#define DW_TAG_formal_parameter_type DW_TAG_formal_parameter +#define DW_TAG_member_type DW_TAG_member +#define DW_TAG_template_type_parameter_type DW_TAG_template_type_parameter +#define DW_TAG_typedef_type DW_TAG_typedef +#define DW_TAG_variant_part_type DW_TAG_variant_part +#define DW_TAG_variant_type DW_TAG_variant + +/* + * symbols.c + */ + +/* See symbols.c:is_symbol_ptr */ +#define SYMBOL_PTR_PREFIX "__gendwarfksyms_ptr_" +#define SYMBOL_PTR_PREFIX_LEN (sizeof(SYMBOL_PTR_PREFIX) - 1) + +static inline unsigned int addr_hash(uintptr_t addr) +{ + return hash_ptr((const void *)addr); +} + +enum symbol_state { + SYMBOL_UNPROCESSED, + SYMBOL_MAPPED, + SYMBOL_PROCESSED +}; + +struct symbol_addr { + uint32_t section; + Elf64_Addr address; +}; + +struct symbol { + const char *name; + struct symbol_addr addr; + struct hlist_node addr_hash; + struct hlist_node name_hash; + enum symbol_state state; + uintptr_t die_addr; + uintptr_t ptr_die_addr; + unsigned long crc; +}; + +typedef void (*symbol_callback_t)(struct symbol *, void *arg); + +bool is_symbol_ptr(const char *name); +void symbol_read_exports(FILE *file); +void symbol_read_symtab(int fd); +struct symbol *symbol_get(const char *name); +void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr); +void symbol_set_die(struct symbol *sym, Dwarf_Die *die); +void symbol_set_crc(struct symbol *sym, unsigned long crc); +void symbol_for_each(symbol_callback_t func, void *arg); +void symbol_print_versions(void); +void symbol_free(void); + +/* + * die.c + */ + +enum die_state { + DIE_INCOMPLETE, + DIE_UNEXPANDED, + DIE_COMPLETE, + DIE_SYMBOL, + DIE_LAST = DIE_SYMBOL +}; + +enum die_fragment_type { + FRAGMENT_EMPTY, + FRAGMENT_STRING, + FRAGMENT_LINEBREAK, + FRAGMENT_DIE +}; + +struct die_fragment { + enum die_fragment_type type; + union { + char *str; + int linebreak; + uintptr_t addr; + } data; + struct list_head list; +}; + +#define CASE_CONST_TO_STR(name) \ + case name: \ + return #name; + +static inline const char *die_state_name(enum die_state state) +{ + switch (state) { + CASE_CONST_TO_STR(DIE_INCOMPLETE) + CASE_CONST_TO_STR(DIE_UNEXPANDED) + CASE_CONST_TO_STR(DIE_COMPLETE) + CASE_CONST_TO_STR(DIE_SYMBOL) + } + + error("unexpected die_state: %d", state); +} + +struct die { + enum die_state state; + bool mapped; + char *fqn; + int tag; + uintptr_t addr; + struct list_head fragments; + struct hlist_node hash; +}; + +typedef void (*die_map_callback_t)(struct die *, void *arg); + +int __die_map_get(uintptr_t addr, enum die_state state, struct die **res); +struct die *die_map_get(Dwarf_Die *die, enum die_state state); +void die_map_add_string(struct die *pd, const char *str); +void die_map_add_linebreak(struct die *pd, int linebreak); +void die_map_for_each(die_map_callback_t func, void *arg); +void die_map_add_die(struct die *pd, struct die *child); +void die_map_free(void); + +/* + * cache.c + */ + +#define CACHE_HASH_BITS 10 + +/* A cache for addresses we've already seen. */ +struct cache { + HASHTABLE_DECLARE(cache, 1 << CACHE_HASH_BITS); +}; + +void cache_set(struct cache *cache, unsigned long key, int value); +int cache_get(struct cache *cache, unsigned long key); +void cache_init(struct cache *cache); +void cache_free(struct cache *cache); + +static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr) +{ + cache_set(cache, addr, 1); +} + +static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr) +{ + return cache_get(cache, addr) == 1; +} + +static inline void cache_mark_expanded(struct cache *cache, void *addr) +{ + __cache_mark_expanded(cache, (uintptr_t)addr); +} + +static inline bool cache_was_expanded(struct cache *cache, void *addr) +{ + return __cache_was_expanded(cache, (uintptr_t)addr); +} + +/* + * dwarf.c + */ + +struct expansion_state { + bool expand; + const char *current_fqn; +}; + +struct kabi_state { + int members; + Dwarf_Die placeholder; + const char *orig_name; +}; + +struct state { + struct symbol *sym; + Dwarf_Die die; + + /* List expansion */ + bool first_list_item; + + /* Structure expansion */ + struct expansion_state expand; + struct cache expansion_cache; + + /* Reserved or ignored members */ + struct kabi_state kabi; +}; + +typedef int (*die_callback_t)(struct state *state, struct die *cache, + Dwarf_Die *die); +typedef bool (*die_match_callback_t)(Dwarf_Die *die); +bool match_all(Dwarf_Die *die); + +int process_die_container(struct state *state, struct die *cache, + Dwarf_Die *die, die_callback_t func, + die_match_callback_t match); + +void process_cu(Dwarf_Die *cudie); + +/* + * types.c + */ + +void generate_symtypes_and_versions(FILE *file); + +/* + * kabi.c + */ + +bool kabi_is_enumerator_ignored(const char *fqn, const char *field); +bool kabi_get_enumerator_value(const char *fqn, const char *field, + unsigned long *value); +bool kabi_is_declonly(const char *fqn); + +void kabi_read_rules(int fd); +void kabi_free(void); + +#endif /* __GENDWARFKSYMS_H */ diff --git a/scripts/gendwarfksyms/kabi.c b/scripts/gendwarfksyms/kabi.c new file mode 100644 index 000000000000..66f01fcd1607 --- /dev/null +++ b/scripts/gendwarfksyms/kabi.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> + +#include "gendwarfksyms.h" + +#define KABI_RULE_SECTION ".discard.gendwarfksyms.kabi_rules" +#define KABI_RULE_VERSION "1" + +/* + * The rule section consists of four null-terminated strings per + * entry: + * + * 1. version + * Entry format version. Must match KABI_RULE_VERSION. + * + * 2. type + * Type of the kABI rule. Must be one of the tags defined below. + * + * 3. target + * Rule-dependent target, typically the fully qualified name of + * the target DIE. + * + * 4. value + * Rule-dependent value. + */ +#define KABI_RULE_MIN_ENTRY_SIZE \ + (/* version\0 */ 2 + /* type\0 */ 2 + /* target\0" */ 1 + \ + /* value\0 */ 1) +#define KABI_RULE_EMPTY_VALUE "" + +/* + * Rule: declonly + * - For the struct/enum/union in the target field, treat it as a + * declaration only even if a definition is available. + */ +#define KABI_RULE_TAG_DECLONLY "declonly" + +/* + * Rule: enumerator_ignore + * - For the enum_field in the target field, ignore the enumerator. + */ +#define KABI_RULE_TAG_ENUMERATOR_IGNORE "enumerator_ignore" + +/* + * Rule: enumerator_value + * - For the fqn_field in the target field, set the value to the + * unsigned integer in the value field. + */ +#define KABI_RULE_TAG_ENUMERATOR_VALUE "enumerator_value" + +enum kabi_rule_type { + KABI_RULE_TYPE_UNKNOWN, + KABI_RULE_TYPE_DECLONLY, + KABI_RULE_TYPE_ENUMERATOR_IGNORE, + KABI_RULE_TYPE_ENUMERATOR_VALUE, +}; + +#define RULE_HASH_BITS 7 + +struct rule { + enum kabi_rule_type type; + const char *target; + const char *value; + struct hlist_node hash; +}; + +/* { type, target } -> struct rule */ +static HASHTABLE_DEFINE(rules, 1 << RULE_HASH_BITS); + +static inline unsigned int rule_values_hash(enum kabi_rule_type type, + const char *target) +{ + return hash_32(type) ^ hash_str(target); +} + +static inline unsigned int rule_hash(const struct rule *rule) +{ + return rule_values_hash(rule->type, rule->target); +} + +static inline const char *get_rule_field(const char **pos, ssize_t *left) +{ + const char *start = *pos; + size_t len; + + if (*left <= 0) + error("unexpected end of kABI rules"); + + len = strnlen(start, *left) + 1; + *pos += len; + *left -= len; + + return start; +} + +void kabi_read_rules(int fd) +{ + GElf_Shdr shdr_mem; + GElf_Shdr *shdr; + Elf_Data *rule_data = NULL; + Elf_Scn *scn; + Elf *elf; + size_t shstrndx; + const char *rule_str; + ssize_t left; + int i; + + const struct { + enum kabi_rule_type type; + const char *tag; + } rule_types[] = { + { + .type = KABI_RULE_TYPE_DECLONLY, + .tag = KABI_RULE_TAG_DECLONLY, + }, + { + .type = KABI_RULE_TYPE_ENUMERATOR_IGNORE, + .tag = KABI_RULE_TAG_ENUMERATOR_IGNORE, + }, + { + .type = KABI_RULE_TYPE_ENUMERATOR_VALUE, + .tag = KABI_RULE_TAG_ENUMERATOR_VALUE, + }, + }; + + if (!stable) + return; + + if (elf_version(EV_CURRENT) != EV_CURRENT) + error("elf_version failed: %s", elf_errmsg(-1)); + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) + error("elf_begin failed: %s", elf_errmsg(-1)); + + if (elf_getshdrstrndx(elf, &shstrndx) < 0) + error("elf_getshdrstrndx failed: %s", elf_errmsg(-1)); + + scn = elf_nextscn(elf, NULL); + + while (scn) { + const char *sname; + + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + sname = elf_strptr(elf, shstrndx, shdr->sh_name); + if (!sname) + error("elf_strptr failed: %s", elf_errmsg(-1)); + + if (!strcmp(sname, KABI_RULE_SECTION)) { + rule_data = elf_getdata(scn, NULL); + if (!rule_data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + break; + } + + scn = elf_nextscn(elf, scn); + } + + if (!rule_data) { + debug("kABI rules not found"); + check(elf_end(elf)); + return; + } + + rule_str = rule_data->d_buf; + left = shdr->sh_size; + + if (left < KABI_RULE_MIN_ENTRY_SIZE) + error("kABI rule section too small: %zd bytes", left); + + if (rule_str[left - 1] != '\0') + error("kABI rules are not null-terminated"); + + while (left > KABI_RULE_MIN_ENTRY_SIZE) { + enum kabi_rule_type type = KABI_RULE_TYPE_UNKNOWN; + const char *field; + struct rule *rule; + + /* version */ + field = get_rule_field(&rule_str, &left); + + if (strcmp(field, KABI_RULE_VERSION)) + error("unsupported kABI rule version: '%s'", field); + + /* type */ + field = get_rule_field(&rule_str, &left); + + for (i = 0; i < ARRAY_SIZE(rule_types); i++) { + if (!strcmp(field, rule_types[i].tag)) { + type = rule_types[i].type; + break; + } + } + + if (type == KABI_RULE_TYPE_UNKNOWN) + error("unsupported kABI rule type: '%s'", field); + + rule = xmalloc(sizeof(struct rule)); + + rule->type = type; + rule->target = xstrdup(get_rule_field(&rule_str, &left)); + rule->value = xstrdup(get_rule_field(&rule_str, &left)); + + hash_add(rules, &rule->hash, rule_hash(rule)); + + debug("kABI rule: type: '%s', target: '%s', value: '%s'", field, + rule->target, rule->value); + } + + if (left > 0) + warn("unexpected data at the end of the kABI rules section"); + + check(elf_end(elf)); +} + +bool kabi_is_declonly(const char *fqn) +{ + struct rule *rule; + + if (!stable) + return false; + if (!fqn || !*fqn) + return false; + + hash_for_each_possible(rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_DECLONLY, fqn)) { + if (rule->type == KABI_RULE_TYPE_DECLONLY && + !strcmp(fqn, rule->target)) + return true; + } + + return false; +} + +static char *get_enumerator_target(const char *fqn, const char *field) +{ + char *target = NULL; + + if (asprintf(&target, "%s %s", fqn, field) < 0) + error("asprintf failed for '%s %s'", fqn, field); + + return target; +} + +static unsigned long get_ulong_value(const char *value) +{ + unsigned long result = 0; + char *endptr = NULL; + + errno = 0; + result = strtoul(value, &endptr, 10); + + if (errno || *endptr) + error("invalid unsigned value '%s'", value); + + return result; +} + +bool kabi_is_enumerator_ignored(const char *fqn, const char *field) +{ + bool match = false; + struct rule *rule; + char *target; + + if (!stable) + return false; + if (!fqn || !*fqn || !field || !*field) + return false; + + target = get_enumerator_target(fqn, field); + + hash_for_each_possible( + rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_IGNORE, target)) { + if (rule->type == KABI_RULE_TYPE_ENUMERATOR_IGNORE && + !strcmp(target, rule->target)) { + match = true; + break; + } + } + + free(target); + return match; +} + +bool kabi_get_enumerator_value(const char *fqn, const char *field, + unsigned long *value) +{ + bool match = false; + struct rule *rule; + char *target; + + if (!stable) + return false; + if (!fqn || !*fqn || !field || !*field) + return false; + + target = get_enumerator_target(fqn, field); + + hash_for_each_possible(rules, rule, hash, + rule_values_hash(KABI_RULE_TYPE_ENUMERATOR_VALUE, + target)) { + if (rule->type == KABI_RULE_TYPE_ENUMERATOR_VALUE && + !strcmp(target, rule->target)) { + *value = get_ulong_value(rule->value); + match = true; + break; + } + } + + free(target); + return match; +} + +void kabi_free(void) +{ + struct hlist_node *tmp; + struct rule *rule; + + hash_for_each_safe(rules, rule, tmp, hash) { + free((void *)rule->target); + free((void *)rule->value); + free(rule); + } + + hash_init(rules); +} diff --git a/scripts/gendwarfksyms/symbols.c b/scripts/gendwarfksyms/symbols.c new file mode 100644 index 000000000000..327f87389c34 --- /dev/null +++ b/scripts/gendwarfksyms/symbols.c @@ -0,0 +1,341 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#include "gendwarfksyms.h" + +#define SYMBOL_HASH_BITS 12 + +/* struct symbol_addr -> struct symbol */ +static HASHTABLE_DEFINE(symbol_addrs, 1 << SYMBOL_HASH_BITS); +/* name -> struct symbol */ +static HASHTABLE_DEFINE(symbol_names, 1 << SYMBOL_HASH_BITS); + +static inline unsigned int symbol_addr_hash(const struct symbol_addr *addr) +{ + return hash_32(addr->section ^ addr_hash(addr->address)); +} + +static unsigned int __for_each_addr(struct symbol *sym, symbol_callback_t func, + void *data) +{ + struct hlist_node *tmp; + struct symbol *match = NULL; + unsigned int processed = 0; + + hash_for_each_possible_safe(symbol_addrs, match, tmp, addr_hash, + symbol_addr_hash(&sym->addr)) { + if (match == sym) + continue; /* Already processed */ + + if (match->addr.section == sym->addr.section && + match->addr.address == sym->addr.address) { + func(match, data); + ++processed; + } + } + + return processed; +} + +/* + * For symbols without debugging information (e.g. symbols defined in other + * TUs), we also match __gendwarfksyms_ptr_<symbol_name> symbols, which the + * kernel uses to ensure type information is present in the TU that exports + * the symbol. A __gendwarfksyms_ptr pointer must have the same type as the + * exported symbol, e.g.: + * + * typeof(symname) *__gendwarf_ptr_symname = &symname; + */ +bool is_symbol_ptr(const char *name) +{ + return name && !strncmp(name, SYMBOL_PTR_PREFIX, SYMBOL_PTR_PREFIX_LEN); +} + +static unsigned int for_each(const char *name, symbol_callback_t func, + void *data) +{ + struct hlist_node *tmp; + struct symbol *match; + + if (!name || !*name) + return 0; + if (is_symbol_ptr(name)) + name += SYMBOL_PTR_PREFIX_LEN; + + hash_for_each_possible_safe(symbol_names, match, tmp, name_hash, + hash_str(name)) { + if (strcmp(match->name, name)) + continue; + + /* Call func for the match, and all address matches */ + if (func) + func(match, data); + + if (match->addr.section != SHN_UNDEF) + return __for_each_addr(match, func, data) + 1; + + return 1; + } + + return 0; +} + +static void set_crc(struct symbol *sym, void *data) +{ + unsigned long *crc = data; + + if (sym->state == SYMBOL_PROCESSED && sym->crc != *crc) + warn("overriding version for symbol %s (crc %lx vs. %lx)", + sym->name, sym->crc, *crc); + + sym->state = SYMBOL_PROCESSED; + sym->crc = *crc; +} + +void symbol_set_crc(struct symbol *sym, unsigned long crc) +{ + if (for_each(sym->name, set_crc, &crc) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static void set_ptr(struct symbol *sym, void *data) +{ + sym->ptr_die_addr = (uintptr_t)((Dwarf_Die *)data)->addr; +} + +void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr) +{ + if (for_each(sym->name, set_ptr, ptr) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static void set_die(struct symbol *sym, void *data) +{ + sym->die_addr = (uintptr_t)((Dwarf_Die *)data)->addr; + sym->state = SYMBOL_MAPPED; +} + +void symbol_set_die(struct symbol *sym, Dwarf_Die *die) +{ + if (for_each(sym->name, set_die, die) == 0) + error("no matching symbols: '%s'", sym->name); +} + +static bool is_exported(const char *name) +{ + return for_each(name, NULL, NULL) > 0; +} + +void symbol_read_exports(FILE *file) +{ + struct symbol *sym; + char *line = NULL; + char *name = NULL; + size_t size = 0; + int nsym = 0; + + while (getline(&line, &size, file) > 0) { + if (sscanf(line, "%ms\n", &name) != 1) + error("malformed input line: %s", line); + + if (is_exported(name)) { + /* Ignore duplicates */ + free(name); + continue; + } + + sym = xcalloc(1, sizeof(struct symbol)); + sym->name = name; + sym->addr.section = SHN_UNDEF; + sym->state = SYMBOL_UNPROCESSED; + + hash_add(symbol_names, &sym->name_hash, hash_str(sym->name)); + ++nsym; + + debug("%s", sym->name); + } + + free(line); + debug("%d exported symbols", nsym); +} + +static void get_symbol(struct symbol *sym, void *arg) +{ + struct symbol **res = arg; + + if (sym->state == SYMBOL_UNPROCESSED) + *res = sym; +} + +struct symbol *symbol_get(const char *name) +{ + struct symbol *sym = NULL; + + for_each(name, get_symbol, &sym); + return sym; +} + +void symbol_for_each(symbol_callback_t func, void *arg) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + func(sym, arg); + } +} + +typedef void (*elf_symbol_callback_t)(const char *name, GElf_Sym *sym, + Elf32_Word xndx, void *arg); + +static void elf_for_each_global(int fd, elf_symbol_callback_t func, void *arg) +{ + size_t sym_size; + GElf_Shdr shdr_mem; + GElf_Shdr *shdr; + Elf_Data *xndx_data = NULL; + Elf_Scn *scn; + Elf *elf; + + if (elf_version(EV_CURRENT) != EV_CURRENT) + error("elf_version failed: %s", elf_errmsg(-1)); + + elf = elf_begin(fd, ELF_C_READ_MMAP, NULL); + if (!elf) + error("elf_begin failed: %s", elf_errmsg(-1)); + + scn = elf_nextscn(elf, NULL); + + while (scn) { + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + if (shdr->sh_type == SHT_SYMTAB_SHNDX) { + xndx_data = elf_getdata(scn, NULL); + if (!xndx_data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + break; + } + + scn = elf_nextscn(elf, scn); + } + + sym_size = gelf_fsize(elf, ELF_T_SYM, 1, EV_CURRENT); + scn = elf_nextscn(elf, NULL); + + while (scn) { + shdr = gelf_getshdr(scn, &shdr_mem); + if (!shdr) + error("gelf_getshdr failed: %s", elf_errmsg(-1)); + + if (shdr->sh_type == SHT_SYMTAB) { + unsigned int nsyms; + unsigned int n; + Elf_Data *data = elf_getdata(scn, NULL); + + if (!data) + error("elf_getdata failed: %s", elf_errmsg(-1)); + + if (shdr->sh_entsize != sym_size) + error("expected sh_entsize (%lu) to be %zu", + shdr->sh_entsize, sym_size); + + nsyms = shdr->sh_size / shdr->sh_entsize; + + for (n = 1; n < nsyms; ++n) { + const char *name = NULL; + Elf32_Word xndx = 0; + GElf_Sym sym_mem; + GElf_Sym *sym; + + sym = gelf_getsymshndx(data, xndx_data, n, + &sym_mem, &xndx); + if (!sym) + error("gelf_getsymshndx failed: %s", + elf_errmsg(-1)); + + if (GELF_ST_BIND(sym->st_info) == STB_LOCAL) + continue; + + if (sym->st_shndx != SHN_XINDEX) + xndx = sym->st_shndx; + + name = elf_strptr(elf, shdr->sh_link, + sym->st_name); + if (!name) + error("elf_strptr failed: %s", + elf_errmsg(-1)); + + /* Skip empty symbol names */ + if (*name) + func(name, sym, xndx, arg); + } + } + + scn = elf_nextscn(elf, scn); + } + + check(elf_end(elf)); +} + +static void set_symbol_addr(struct symbol *sym, void *arg) +{ + struct symbol_addr *addr = arg; + + if (sym->addr.section == SHN_UNDEF) { + sym->addr = *addr; + hash_add(symbol_addrs, &sym->addr_hash, + symbol_addr_hash(&sym->addr)); + + debug("%s -> { %u, %lx }", sym->name, sym->addr.section, + sym->addr.address); + } else if (sym->addr.section != addr->section || + sym->addr.address != addr->address) { + warn("multiple addresses for symbol %s?", sym->name); + } +} + +static void elf_set_symbol_addr(const char *name, GElf_Sym *sym, + Elf32_Word xndx, void *arg) +{ + struct symbol_addr addr = { .section = xndx, .address = sym->st_value }; + + /* Set addresses for exported symbols */ + if (addr.section != SHN_UNDEF) + for_each(name, set_symbol_addr, &addr); +} + +void symbol_read_symtab(int fd) +{ + elf_for_each_global(fd, elf_set_symbol_addr, NULL); +} + +void symbol_print_versions(void) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + if (sym->state != SYMBOL_PROCESSED) + warn("no information for symbol %s", sym->name); + + printf("#SYMVER %s 0x%08lx\n", sym->name, sym->crc); + } +} + +void symbol_free(void) +{ + struct hlist_node *tmp; + struct symbol *sym; + + hash_for_each_safe(symbol_names, sym, tmp, name_hash) { + free((void *)sym->name); + free(sym); + } + + hash_init(symbol_addrs); + hash_init(symbol_names); +} diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c new file mode 100644 index 000000000000..6c03265f4d10 --- /dev/null +++ b/scripts/gendwarfksyms/types.c @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Google LLC + */ + +#define _GNU_SOURCE +#include <inttypes.h> +#include <stdio.h> +#include <zlib.h> + +#include "gendwarfksyms.h" + +static struct cache expansion_cache; + +/* + * A simple linked list of shared or owned strings to avoid copying strings + * around when not necessary. + */ +struct type_list_entry { + const char *str; + void *owned; + struct list_head list; +}; + +static void type_list_free(struct list_head *list) +{ + struct type_list_entry *entry; + struct type_list_entry *tmp; + + list_for_each_entry_safe(entry, tmp, list, list) { + if (entry->owned) + free(entry->owned); + free(entry); + } + + INIT_LIST_HEAD(list); +} + +static int type_list_append(struct list_head *list, const char *s, void *owned) +{ + struct type_list_entry *entry; + + if (!s) + return 0; + + entry = xmalloc(sizeof(struct type_list_entry)); + entry->str = s; + entry->owned = owned; + list_add_tail(&entry->list, list); + + return strlen(entry->str); +} + +static void type_list_write(struct list_head *list, FILE *file) +{ + struct type_list_entry *entry; + + list_for_each_entry(entry, list, list) { + if (entry->str) + checkp(fputs(entry->str, file)); + } +} + +/* + * An expanded type string in symtypes format. + */ +struct type_expansion { + char *name; + size_t len; + struct list_head expanded; + struct hlist_node hash; +}; + +static void type_expansion_init(struct type_expansion *type) +{ + type->name = NULL; + type->len = 0; + INIT_LIST_HEAD(&type->expanded); +} + +static inline void type_expansion_free(struct type_expansion *type) +{ + free(type->name); + type->name = NULL; + type->len = 0; + type_list_free(&type->expanded); +} + +static void type_expansion_append(struct type_expansion *type, const char *s, + void *owned) +{ + type->len += type_list_append(&type->expanded, s, owned); +} + +/* + * type_map -- the longest expansions for each type. + * + * const char *name -> struct type_expansion * + */ +#define TYPE_HASH_BITS 12 +static HASHTABLE_DEFINE(type_map, 1 << TYPE_HASH_BITS); + +static int type_map_get(const char *name, struct type_expansion **res) +{ + struct type_expansion *e; + + hash_for_each_possible(type_map, e, hash, hash_str(name)) { + if (!strcmp(name, e->name)) { + *res = e; + return 0; + } + } + + return -1; +} + +static void type_map_add(const char *name, struct type_expansion *type) +{ + struct type_expansion *e; + + if (type_map_get(name, &e)) { + e = xmalloc(sizeof(struct type_expansion)); + type_expansion_init(e); + e->name = xstrdup(name); + + hash_add(type_map, &e->hash, hash_str(e->name)); + + if (dump_types) + debug("adding %s", e->name); + } else { + /* Use the longest available expansion */ + if (type->len <= e->len) + return; + + type_list_free(&e->expanded); + + if (dump_types) + debug("replacing %s", e->name); + } + + /* Take ownership of type->expanded */ + list_replace_init(&type->expanded, &e->expanded); + e->len = type->len; + + if (dump_types) { + checkp(fputs(e->name, stderr)); + checkp(fputs(" ", stderr)); + type_list_write(&e->expanded, stderr); + checkp(fputs("\n", stderr)); + } +} + +static void type_map_write(FILE *file) +{ + struct type_expansion *e; + struct hlist_node *tmp; + + if (!file) + return; + + hash_for_each_safe(type_map, e, tmp, hash) { + checkp(fputs(e->name, file)); + checkp(fputs(" ", file)); + type_list_write(&e->expanded, file); + checkp(fputs("\n", file)); + } +} + +static void type_map_free(void) +{ + struct type_expansion *e; + struct hlist_node *tmp; + + hash_for_each_safe(type_map, e, tmp, hash) { + type_expansion_free(e); + free(e); + } + + hash_init(type_map); +} + +/* + * CRC for a type, with an optional fully expanded type string for + * debugging. + */ +struct version { + struct type_expansion type; + unsigned long crc; +}; + +static void version_init(struct version *version) +{ + version->crc = crc32(0, NULL, 0); + type_expansion_init(&version->type); +} + +static void version_free(struct version *version) +{ + type_expansion_free(&version->type); +} + +static void version_add(struct version *version, const char *s) +{ + version->crc = crc32(version->crc, (void *)s, strlen(s)); + if (dump_versions) + type_expansion_append(&version->type, s, NULL); +} + +/* + * Type reference format: <prefix>#<name>, where prefix: + * s -> structure + * u -> union + * e -> enum + * t -> typedef + * + * Names with spaces are additionally wrapped in single quotes. + */ +static inline bool is_type_prefix(const char *s) +{ + return (s[0] == 's' || s[0] == 'u' || s[0] == 'e' || s[0] == 't') && + s[1] == '#'; +} + +static char get_type_prefix(int tag) +{ + switch (tag) { + case DW_TAG_class_type: + case DW_TAG_structure_type: + return 's'; + case DW_TAG_union_type: + return 'u'; + case DW_TAG_enumeration_type: + return 'e'; + case DW_TAG_typedef_type: + return 't'; + default: + return 0; + } +} + +static char *get_type_name(struct die *cache) +{ + const char *quote; + char prefix; + char *name; + + if (cache->state == DIE_INCOMPLETE) { + warn("found incomplete cache entry: %p", cache); + return NULL; + } + if (cache->state == DIE_SYMBOL) + return NULL; + if (!cache->fqn || !*cache->fqn) + return NULL; + + prefix = get_type_prefix(cache->tag); + if (!prefix) + return NULL; + + /* Wrap names with spaces in single quotes */ + quote = strstr(cache->fqn, " ") ? "'" : ""; + + /* <prefix>#<type_name>\0 */ + if (asprintf(&name, "%c#%s%s%s", prefix, quote, cache->fqn, quote) < 0) + error("asprintf failed for '%s'", cache->fqn); + + return name; +} + +static void __calculate_version(struct version *version, struct list_head *list) +{ + struct type_list_entry *entry; + struct type_expansion *e; + + /* Calculate a CRC over an expanded type string */ + list_for_each_entry(entry, list, list) { + if (is_type_prefix(entry->str)) { + check(type_map_get(entry->str, &e)); + + /* + * It's sufficient to expand each type reference just + * once to detect changes. + */ + if (cache_was_expanded(&expansion_cache, e)) { + version_add(version, entry->str); + } else { + cache_mark_expanded(&expansion_cache, e); + __calculate_version(version, &e->expanded); + } + } else { + version_add(version, entry->str); + } + } +} + +static void calculate_version(struct version *version, struct list_head *list) +{ + version_init(version); + __calculate_version(version, list); + cache_free(&expansion_cache); +} + +static void __type_expand(struct die *cache, struct type_expansion *type, + bool recursive); + +static void type_expand_child(struct die *cache, struct type_expansion *type, + bool recursive) +{ + struct type_expansion child; + char *name; + + name = get_type_name(cache); + if (!name) { + __type_expand(cache, type, recursive); + return; + } + + if (recursive && !__cache_was_expanded(&expansion_cache, cache->addr)) { + __cache_mark_expanded(&expansion_cache, cache->addr); + type_expansion_init(&child); + __type_expand(cache, &child, true); + type_map_add(name, &child); + type_expansion_free(&child); + } + + type_expansion_append(type, name, name); +} + +static void __type_expand(struct die *cache, struct type_expansion *type, + bool recursive) +{ + struct die_fragment *df; + struct die *child; + + list_for_each_entry(df, &cache->fragments, list) { + switch (df->type) { + case FRAGMENT_STRING: + type_expansion_append(type, df->data.str, NULL); + break; + case FRAGMENT_DIE: + /* Use a complete die_map expansion if available */ + if (__die_map_get(df->data.addr, DIE_COMPLETE, + &child) && + __die_map_get(df->data.addr, DIE_UNEXPANDED, + &child)) + error("unknown child: %" PRIxPTR, + df->data.addr); + + type_expand_child(child, type, recursive); + break; + case FRAGMENT_LINEBREAK: + /* + * Keep whitespace in the symtypes format, but avoid + * repeated spaces. + */ + if (list_is_last(&df->list, &cache->fragments) || + list_next_entry(df, list)->type != + FRAGMENT_LINEBREAK) + type_expansion_append(type, " ", NULL); + break; + default: + error("empty die_fragment in %p", cache); + } + } +} + +static void type_expand(struct die *cache, struct type_expansion *type, + bool recursive) +{ + type_expansion_init(type); + __type_expand(cache, type, recursive); + cache_free(&expansion_cache); +} + +static void expand_type(struct die *cache, void *arg) +{ + struct type_expansion type; + char *name; + + if (cache->mapped) + return; + + cache->mapped = true; + + /* + * Skip unexpanded die_map entries if there's a complete + * expansion available for this DIE. + */ + if (cache->state == DIE_UNEXPANDED && + !__die_map_get(cache->addr, DIE_COMPLETE, &cache)) { + if (cache->mapped) + return; + + cache->mapped = true; + } + + name = get_type_name(cache); + if (!name) + return; + + debug("%s", name); + type_expand(cache, &type, true); + type_map_add(name, &type); + + type_expansion_free(&type); + free(name); +} + +static void expand_symbol(struct symbol *sym, void *arg) +{ + struct type_expansion type; + struct version version; + struct die *cache; + + /* + * No need to expand again unless we want a symtypes file entry + * for the symbol. Note that this means `sym` has the same address + * as another symbol that was already processed. + */ + if (!symtypes && sym->state == SYMBOL_PROCESSED) + return; + + if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache)) + return; /* We'll warn about missing CRCs later. */ + + type_expand(cache, &type, false); + + /* If the symbol already has a version, don't calculate it again. */ + if (sym->state != SYMBOL_PROCESSED) { + calculate_version(&version, &type.expanded); + symbol_set_crc(sym, version.crc); + debug("%s = %lx", sym->name, version.crc); + + if (dump_versions) { + checkp(fputs(sym->name, stderr)); + checkp(fputs(" ", stderr)); + type_list_write(&version.type.expanded, stderr); + checkp(fputs("\n", stderr)); + } + + version_free(&version); + } + + /* These aren't needed in type_map unless we want a symtypes file. */ + if (symtypes) + type_map_add(sym->name, &type); + + type_expansion_free(&type); +} + +void generate_symtypes_and_versions(FILE *file) +{ + cache_init(&expansion_cache); + + /* + * die_map processing: + * + * 1. die_map contains all types referenced in exported symbol + * signatures, but can contain duplicates just like the original + * DWARF, and some references may not be fully expanded depending + * on how far we processed the DIE tree for that specific symbol. + * + * For each die_map entry, find the longest available expansion, + * and add it to type_map. + */ + die_map_for_each(expand_type, NULL); + + /* + * 2. For each exported symbol, expand the die_map type, and use + * type_map expansions to calculate a symbol version from the + * fully expanded type string. + */ + symbol_for_each(expand_symbol, NULL); + + /* + * 3. If a symtypes file is requested, write type_map contents to + * the file. + */ + type_map_write(file); + type_map_free(); +} diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 0d00ac3723b5..4fd6b6ab3e32 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -165,6 +165,18 @@ impl KernelConfig { let option = "CONFIG_".to_owned() + option; self.0.contains_key(&option) } + + /// Is the rustc version at least `major.minor.patch`? + fn rustc_version_atleast(&self, major: u32, minor: u32, patch: u32) -> bool { + let check_version = 100000 * major + 100 * minor + patch; + let actual_version = self + .0 + .get("CONFIG_RUSTC_VERSION") + .unwrap() + .parse::<u32>() + .unwrap(); + check_version <= actual_version + } } fn main() { @@ -182,6 +194,9 @@ fn main() { } } else if cfg.has("X86_64") { ts.push("arch", "x86_64"); + if cfg.rustc_version_atleast(1, 86, 0) { + ts.push("rustc-abi", "x86-softfloat"); + } ts.push( "data-layout", "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128", @@ -215,6 +230,9 @@ fn main() { panic!("32-bit x86 only works under UML"); } ts.push("arch", "x86"); + if cfg.rustc_version_atleast(1, 86, 0) { + ts.push("rustc-abi", "x86-softfloat"); + } ts.push( "data-layout", "e-m:e-p:32:32-p270:32:32-p271:32:32-p272:64:64-i128:128-f64:32:64-f80:32-n8:16:32-S128", diff --git a/scripts/genksyms/Makefile b/scripts/genksyms/Makefile index 312edccda736..4350311fb7b3 100644 --- a/scripts/genksyms/Makefile +++ b/scripts/genksyms/Makefile @@ -4,24 +4,6 @@ hostprogs-always-y += genksyms genksyms-objs := genksyms.o parse.tab.o lex.lex.o -# FIXME: fix the ambiguous grammar in parse.y and delete this hack -# -# Suppress shift/reduce, reduce/reduce conflicts warnings -# unless W=1 is specified. -# -# Just in case, run "$(YACC) --version" without suppressing stderr -# so that 'bison: not found' will be displayed if it is missing. -ifeq ($(findstring 1,$(KBUILD_EXTRA_WARN)),) - -quiet_cmd_bison_no_warn = $(quiet_cmd_bison) - cmd_bison_no_warn = $(YACC) --version >/dev/null; \ - $(cmd_bison) 2>/dev/null - -$(obj)/pars%.tab.c $(obj)/pars%.tab.h: $(src)/pars%.y FORCE - $(call if_changed,bison_no_warn) - -endif - # -I needed for generated C source to include headers in source tree HOSTCFLAGS_parse.tab.o := -I $(src) HOSTCFLAGS_lex.lex.o := -I $(src) diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c index 07f9b8cfb233..8b0d7ac73dbb 100644 --- a/scripts/genksyms/genksyms.c +++ b/scripts/genksyms/genksyms.c @@ -12,18 +12,19 @@ #include <stdio.h> #include <string.h> +#include <stdint.h> #include <stdlib.h> #include <unistd.h> #include <assert.h> #include <stdarg.h> #include <getopt.h> +#include <hashtable.h> + #include "genksyms.h" /*----------------------------------------------------------------------*/ -#define HASH_BUCKETS 4096 - -static struct symbol *symtab[HASH_BUCKETS]; +static HASHTABLE_DEFINE(symbol_hashtable, 1U << 12); static FILE *debugfile; int cur_line = 1; @@ -60,7 +61,7 @@ static void print_type_name(enum symbol_type type, const char *name); /*----------------------------------------------------------------------*/ -static const unsigned int crctab32[] = { +static const uint32_t crctab32[] = { 0x00000000U, 0x77073096U, 0xee0e612cU, 0x990951baU, 0x076dc419U, 0x706af48fU, 0xe963a535U, 0x9e6495a3U, 0x0edb8832U, 0x79dcb8a4U, 0xe0d5e91eU, 0x97d2d988U, 0x09b64c2bU, 0x7eb17cbdU, 0xe7b82d07U, @@ -115,19 +116,19 @@ static const unsigned int crctab32[] = { 0x2d02ef8dU }; -static unsigned long partial_crc32_one(unsigned char c, unsigned long crc) +static uint32_t partial_crc32_one(uint8_t c, uint32_t crc) { return crctab32[(crc ^ c) & 0xff] ^ (crc >> 8); } -static unsigned long partial_crc32(const char *s, unsigned long crc) +static uint32_t partial_crc32(const char *s, uint32_t crc) { while (*s) crc = partial_crc32_one(*s++, crc); return crc; } -static unsigned long crc32(const char *s) +static uint32_t crc32(const char *s) { return partial_crc32(s, 0xffffffff) ^ 0xffffffff; } @@ -151,14 +152,14 @@ static enum symbol_type map_to_ns(enum symbol_type t) struct symbol *find_symbol(const char *name, enum symbol_type ns, int exact) { - unsigned long h = crc32(name) % HASH_BUCKETS; struct symbol *sym; - for (sym = symtab[h]; sym; sym = sym->hash_next) + hash_for_each_possible(symbol_hashtable, sym, hnode, crc32(name)) { if (map_to_ns(sym->type) == map_to_ns(ns) && strcmp(name, sym->name) == 0 && sym->is_declared) break; + } if (exact && sym && sym->type != ns) return NULL; @@ -224,64 +225,56 @@ static struct symbol *__add_symbol(const char *name, enum symbol_type type, return NULL; } - h = crc32(name) % HASH_BUCKETS; - for (sym = symtab[h]; sym; sym = sym->hash_next) { - if (map_to_ns(sym->type) == map_to_ns(type) && - strcmp(name, sym->name) == 0) { - if (is_reference) - /* fall through */ ; - else if (sym->type == type && - equal_list(sym->defn, defn)) { - if (!sym->is_declared && sym->is_override) { - print_location(); - print_type_name(type, name); - fprintf(stderr, " modversion is " - "unchanged\n"); - } - sym->is_declared = 1; - return sym; - } else if (!sym->is_declared) { - if (sym->is_override && flag_preserve) { - print_location(); - fprintf(stderr, "ignoring "); - print_type_name(type, name); - fprintf(stderr, " modversion change\n"); - sym->is_declared = 1; - return sym; - } else { - status = is_unknown_symbol(sym) ? - STATUS_DEFINED : STATUS_MODIFIED; - } - } else { - error_with_pos("redefinition of %s", name); - return sym; + h = crc32(name); + hash_for_each_possible(symbol_hashtable, sym, hnode, h) { + if (map_to_ns(sym->type) != map_to_ns(type) || + strcmp(name, sym->name)) + continue; + + if (is_reference) { + break; + } else if (sym->type == type && equal_list(sym->defn, defn)) { + if (!sym->is_declared && sym->is_override) { + print_location(); + print_type_name(type, name); + fprintf(stderr, " modversion is unchanged\n"); } + sym->is_declared = 1; + } else if (sym->is_declared) { + error_with_pos("redefinition of %s", name); + } else if (sym->is_override && flag_preserve) { + print_location(); + fprintf(stderr, "ignoring "); + print_type_name(type, name); + fprintf(stderr, " modversion change\n"); + sym->is_declared = 1; + } else { + status = is_unknown_symbol(sym) ? + STATUS_DEFINED : STATUS_MODIFIED; break; } + free_list(defn, NULL); + return sym; } if (sym) { - struct symbol **psym; + hash_del(&sym->hnode); - for (psym = &symtab[h]; *psym; psym = &(*psym)->hash_next) { - if (*psym == sym) { - *psym = sym->hash_next; - break; - } - } + free_list(sym->defn, NULL); + free(sym->name); + free(sym); --nsyms; } sym = xmalloc(sizeof(*sym)); - sym->name = name; + sym->name = xstrdup(name); sym->type = type; sym->defn = defn; sym->expansion_trail = NULL; sym->visited = NULL; sym->is_extern = is_extern; - sym->hash_next = symtab[h]; - symtab[h] = sym; + hash_add(symbol_hashtable, &sym->hnode, h); sym->is_declared = !is_reference; sym->status = status; @@ -480,7 +473,7 @@ static void read_reference(FILE *f) defn = def; def = read_node(f); } - subsym = add_reference_symbol(xstrdup(sym->string), sym->tag, + subsym = add_reference_symbol(sym->string, sym->tag, defn, is_extern); subsym->is_override = is_override; free_node(sym); @@ -525,7 +518,7 @@ static void print_list(FILE * f, struct string_list *list) } } -static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc) +static uint32_t expand_and_crc_sym(struct symbol *sym, uint32_t crc) { struct string_list *list = sym->defn; struct string_list **e, **b; @@ -632,7 +625,7 @@ static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc) void export_symbol(const char *name) { struct symbol *sym; - unsigned long crc; + uint32_t crc; int has_changed = 0; sym = find_symbol(name, SYM_NORMAL, 0); @@ -680,7 +673,7 @@ void export_symbol(const char *name) if (flag_dump_defs) fputs(">\n", debugfile); - printf("#SYMVER %s 0x%08lx\n", name, crc); + printf("#SYMVER %s 0x%08lx\n", name, (unsigned long)crc); } /*----------------------------------------------------------------------*/ @@ -832,9 +825,9 @@ int main(int argc, char **argv) } if (flag_debug) { - fprintf(debugfile, "Hash table occupancy %d/%d = %g\n", - nsyms, HASH_BUCKETS, - (double)nsyms / (double)HASH_BUCKETS); + fprintf(debugfile, "Hash table occupancy %d/%zd = %g\n", + nsyms, HASH_SIZE(symbol_hashtable), + (double)nsyms / HASH_SIZE(symbol_hashtable)); } if (dumpfile) diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h index 21ed2ec2d98c..0c355075f0e6 100644 --- a/scripts/genksyms/genksyms.h +++ b/scripts/genksyms/genksyms.h @@ -12,8 +12,11 @@ #ifndef MODUTILS_GENKSYMS_H #define MODUTILS_GENKSYMS_H 1 +#include <stdbool.h> #include <stdio.h> +#include <list_types.h> + enum symbol_type { SYM_NORMAL, SYM_TYPEDEF, SYM_ENUM, SYM_STRUCT, SYM_UNION, SYM_ENUM_CONST @@ -31,8 +34,8 @@ struct string_list { }; struct symbol { - struct symbol *hash_next; - const char *name; + struct hlist_node hnode; + char *name; enum symbol_type type; struct string_list *defn; struct symbol *expansion_trail; @@ -64,6 +67,8 @@ struct string_list *copy_list_range(struct string_list *start, int yylex(void); int yyparse(void); +extern bool dont_want_type_specifier; + void error_with_pos(const char *, ...) __attribute__ ((format(printf, 1, 2))); /*----------------------------------------------------------------------*/ diff --git a/scripts/genksyms/lex.l b/scripts/genksyms/lex.l index a4d7495eaf75..22aeb57649d9 100644 --- a/scripts/genksyms/lex.l +++ b/scripts/genksyms/lex.l @@ -12,6 +12,7 @@ %{ #include <limits.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include <ctype.h> @@ -50,6 +51,7 @@ MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>) %% +u?int(8|16|32|64)x(1|2|4|8|16)_t return BUILTIN_INT_KEYW; /* Keep track of our location in the original source files. */ ^#[ \t]+{INT}[ \t]+\"[^\"\n]+\".*\n return FILENAME; @@ -113,6 +115,12 @@ MC_TOKEN ([~%^&*+=|<>/-]=)|(&&)|("||")|(->)|(<<)|(>>) /* The second stage lexer. Here we incorporate knowledge of the state of the parser to tailor the tokens that are returned. */ +/* + * The lexer cannot distinguish whether a typedef'ed string is a TYPE or an + * IDENT. We need a hint from the parser to handle this accurately. + */ +bool dont_want_type_specifier; + int yylex(void) { @@ -207,7 +215,7 @@ repeat: goto repeat; } } - if (!suppress_type_lookup) + if (!suppress_type_lookup && !dont_want_type_specifier) { if (find_symbol(yytext, SYM_TYPEDEF, 1)) token = TYPE; @@ -431,7 +439,12 @@ fini: if (suppress_type_lookup > 0) --suppress_type_lookup; - if (dont_want_brace_phrase > 0) + + /* + * __attribute__() can be placed immediately after the 'struct' keyword. + * e.g.) struct __attribute__((__packed__)) foo { ... }; + */ + if (token != ATTRIBUTE_PHRASE && dont_want_brace_phrase > 0) --dont_want_brace_phrase; yylval = &next_node->next; diff --git a/scripts/genksyms/parse.y b/scripts/genksyms/parse.y index 8e9b5e69e8f0..ee600a804fa1 100644 --- a/scripts/genksyms/parse.y +++ b/scripts/genksyms/parse.y @@ -12,6 +12,7 @@ %{ #include <assert.h> +#include <stdbool.h> #include <stdlib.h> #include <string.h> #include "genksyms.h" @@ -148,32 +149,45 @@ simple_declaration: current_name = NULL; } $$ = $3; + dont_want_type_specifier = false; } ; init_declarator_list_opt: - /* empty */ { $$ = NULL; } - | init_declarator_list + /* empty */ { $$ = NULL; } + | init_declarator_list { free_list(decl_spec, NULL); $$ = $1; } ; init_declarator_list: init_declarator { struct string_list *decl = *$1; *$1 = NULL; + + /* avoid sharing among multiple init_declarators */ + if (decl_spec) + decl_spec = copy_list_range(decl_spec, NULL); + add_symbol(current_name, is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; $$ = $1; + dont_want_type_specifier = true; } - | init_declarator_list ',' init_declarator - { struct string_list *decl = *$3; - *$3 = NULL; + | init_declarator_list ',' attribute_opt init_declarator + { struct string_list *decl = *$4; + *$4 = NULL; free_list(*$2, NULL); *$2 = decl_spec; + + /* avoid sharing among multiple init_declarators */ + if (decl_spec) + decl_spec = copy_list_range(decl_spec, NULL); + add_symbol(current_name, is_typedef ? SYM_TYPEDEF : SYM_NORMAL, decl, is_extern); current_name = NULL; - $$ = $3; + $$ = $4; + dont_want_type_specifier = true; } ; @@ -189,8 +203,9 @@ decl_specifier_seq_opt: ; decl_specifier_seq: - decl_specifier { decl_spec = *$1; } + attribute_opt decl_specifier { decl_spec = *$2; } | decl_specifier_seq decl_specifier { decl_spec = *$2; } + | decl_specifier_seq ATTRIBUTE_PHRASE { decl_spec = *$2; } ; decl_specifier: @@ -200,7 +215,8 @@ decl_specifier: remove_node($1); $$ = $1; } - | type_specifier + | type_specifier { dont_want_type_specifier = true; $$ = $1; } + | type_qualifier ; storage_class_specifier: @@ -213,24 +229,23 @@ storage_class_specifier: type_specifier: simple_type_specifier - | cvar_qualifier | TYPEOF_KEYW '(' parameter_declaration ')' | TYPEOF_PHRASE /* References to s/u/e's defined elsewhere. Rearrange things so that it is easier to expand the definition fully later. */ - | STRUCT_KEYW IDENT - { remove_node($1); (*$2)->tag = SYM_STRUCT; $$ = $2; } - | UNION_KEYW IDENT - { remove_node($1); (*$2)->tag = SYM_UNION; $$ = $2; } + | STRUCT_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_STRUCT; $$ = $3; } + | UNION_KEYW attribute_opt IDENT + { remove_node($1); (*$3)->tag = SYM_UNION; $$ = $3; } | ENUM_KEYW IDENT { remove_node($1); (*$2)->tag = SYM_ENUM; $$ = $2; } /* Full definitions of an s/u/e. Record it. */ - | STRUCT_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_STRUCT); $$ = $3; } - | UNION_KEYW IDENT class_body - { record_compound($1, $2, $3, SYM_UNION); $$ = $3; } + | STRUCT_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_STRUCT); $$ = $4; } + | UNION_KEYW attribute_opt IDENT class_body + { record_compound($1, $3, $4, SYM_UNION); $$ = $4; } | ENUM_KEYW IDENT enum_body { record_compound($1, $2, $3, SYM_ENUM); $$ = $3; } /* @@ -239,8 +254,8 @@ type_specifier: | ENUM_KEYW enum_body { add_symbol(NULL, SYM_ENUM, NULL, 0); $$ = $2; } /* Anonymous s/u definitions. Nothing needs doing. */ - | STRUCT_KEYW class_body { $$ = $2; } - | UNION_KEYW class_body { $$ = $2; } + | STRUCT_KEYW attribute_opt class_body { $$ = $3; } + | UNION_KEYW attribute_opt class_body { $$ = $3; } ; simple_type_specifier: @@ -260,22 +275,24 @@ simple_type_specifier: ; ptr_operator: - '*' cvar_qualifier_seq_opt + '*' type_qualifier_seq_opt { $$ = $2 ? $2 : $1; } ; -cvar_qualifier_seq_opt: +type_qualifier_seq_opt: /* empty */ { $$ = NULL; } - | cvar_qualifier_seq + | type_qualifier_seq ; -cvar_qualifier_seq: - cvar_qualifier - | cvar_qualifier_seq cvar_qualifier { $$ = $2; } +type_qualifier_seq: + type_qualifier + | ATTRIBUTE_PHRASE + | type_qualifier_seq type_qualifier { $$ = $2; } + | type_qualifier_seq ATTRIBUTE_PHRASE { $$ = $2; } ; -cvar_qualifier: - CONST_KEYW | VOLATILE_KEYW | ATTRIBUTE_PHRASE +type_qualifier: + CONST_KEYW | VOLATILE_KEYW | RESTRICT_KEYW { /* restrict has no effect in prototypes so ignore it */ remove_node($1); @@ -297,15 +314,7 @@ direct_declarator: current_name = (*$1)->string; $$ = $1; } - } - | TYPE - { if (current_name != NULL) { - error_with_pos("unexpected second declaration name"); - YYERROR; - } else { - current_name = (*$1)->string; - $$ = $1; - } + dont_want_type_specifier = false; } | direct_declarator '(' parameter_declaration_clause ')' { $$ = $4; } @@ -325,16 +334,19 @@ nested_declarator: ; direct_nested_declarator: - IDENT - | TYPE - | direct_nested_declarator '(' parameter_declaration_clause ')' + direct_nested_declarator1 + | direct_nested_declarator1 '(' parameter_declaration_clause ')' { $$ = $4; } - | direct_nested_declarator '(' error ')' + ; + +direct_nested_declarator1: + IDENT { $$ = $1; dont_want_type_specifier = false; } + | direct_nested_declarator1 '(' error ')' { $$ = $4; } - | direct_nested_declarator BRACKET_PHRASE + | direct_nested_declarator1 BRACKET_PHRASE { $$ = $2; } - | '(' nested_declarator ')' - { $$ = $3; } + | '(' attribute_opt nested_declarator ')' + { $$ = $4; } | '(' error ')' { $$ = $3; } ; @@ -352,45 +364,57 @@ parameter_declaration_list_opt: parameter_declaration_list: parameter_declaration + { $$ = $1; dont_want_type_specifier = false; } | parameter_declaration_list ',' parameter_declaration - { $$ = $3; } + { $$ = $3; dont_want_type_specifier = false; } ; parameter_declaration: - decl_specifier_seq m_abstract_declarator + decl_specifier_seq abstract_declarator_opt { $$ = $2 ? $2 : $1; } ; -m_abstract_declarator: - ptr_operator m_abstract_declarator +abstract_declarator_opt: + /* empty */ { $$ = NULL; } + | abstract_declarator + ; + +abstract_declarator: + ptr_operator + | ptr_operator abstract_declarator { $$ = $2 ? $2 : $1; } - | direct_m_abstract_declarator + | direct_abstract_declarator attribute_opt + { $$ = $2; dont_want_type_specifier = false; } ; -direct_m_abstract_declarator: - /* empty */ { $$ = NULL; } - | IDENT +direct_abstract_declarator: + direct_abstract_declarator1 + | direct_abstract_declarator1 open_paren parameter_declaration_clause ')' + { $$ = $4; } + | open_paren parameter_declaration_clause ')' + { $$ = $3; } + ; + +direct_abstract_declarator1: + IDENT { /* For version 2 checksums, we don't want to remember private parameter names. */ remove_node($1); $$ = $1; } - /* This wasn't really a typedef name but an identifier that - shadows one. */ - | TYPE - { remove_node($1); - $$ = $1; - } - | direct_m_abstract_declarator '(' parameter_declaration_clause ')' - { $$ = $4; } - | direct_m_abstract_declarator '(' error ')' + | direct_abstract_declarator1 open_paren error ')' { $$ = $4; } - | direct_m_abstract_declarator BRACKET_PHRASE + | direct_abstract_declarator1 BRACKET_PHRASE { $$ = $2; } - | '(' m_abstract_declarator ')' - { $$ = $3; } - | '(' error ')' + | open_paren attribute_opt abstract_declarator ')' + { $$ = $4; } + | open_paren error ')' { $$ = $3; } + | BRACKET_PHRASE + ; + +open_paren: + '(' { $$ = $1; dont_want_type_specifier = false; } ; function_definition: @@ -430,9 +454,9 @@ member_specification: member_declaration: decl_specifier_seq_opt member_declarator_list_opt ';' - { $$ = $3; } + { $$ = $3; dont_want_type_specifier = false; } | error ';' - { $$ = $2; } + { $$ = $2; dont_want_type_specifier = false; } ; member_declarator_list_opt: @@ -442,7 +466,9 @@ member_declarator_list_opt: member_declarator_list: member_declarator - | member_declarator_list ',' member_declarator { $$ = $3; } + { $$ = $1; dont_want_type_specifier = true; } + | member_declarator_list ',' member_declarator + { $$ = $3; dont_want_type_specifier = true; } ; member_declarator: @@ -457,7 +483,7 @@ member_bitfield_declarator: attribute_opt: /* empty */ { $$ = NULL; } - | attribute_opt ATTRIBUTE_PHRASE + | attribute_opt ATTRIBUTE_PHRASE { $$ = $2; } ; enum_body: @@ -472,12 +498,12 @@ enumerator_list: enumerator: IDENT { - const char *name = strdup((*$1)->string); + const char *name = (*$1)->string; add_symbol(name, SYM_ENUM_CONST, NULL, 0); } | IDENT '=' EXPRESSION_PHRASE { - const char *name = strdup((*$1)->string); + const char *name = (*$1)->string; struct string_list *expr = copy_list_range(*$3, *$2); add_symbol(name, SYM_ENUM_CONST, expr, 0); } diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index a0a0be38cbdc..fb50bd4f4103 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -105,9 +105,11 @@ configfiles = $(wildcard $(srctree)/kernel/configs/$(1) $(srctree)/arch/$(SRCARC all-config-fragments = $(call configfiles,*.config) config-fragments = $(call configfiles,$@) +cmd_merge_fragments = $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments) + %.config: $(obj)/conf $(if $(config-fragments),, $(error $@ fragment does not exists on this architecture)) - $(Q)$(CONFIG_SHELL) $(srctree)/scripts/kconfig/merge_config.sh -m $(KCONFIG_CONFIG) $(config-fragments) + $(call cmd,merge_fragments) $(Q)$(MAKE) -f $(srctree)/Makefile olddefconfig PHONY += tinyconfig diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index 4286d5e7f95d..3b55e7a4131d 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -360,10 +360,12 @@ int conf_read_simple(const char *name, int def) *p = '\0'; - in = zconf_fopen(env); + name = env; + + in = zconf_fopen(name); if (in) { conf_message("using defaults found in %s", - env); + name); goto load; } diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index 6c92ef1e16ef..eaa465b0ccf9 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -1464,8 +1464,8 @@ void ConfigMainWindow::loadConfig(void) { QString str; - str = QFileDialog::getOpenFileName(this, "", configname); - if (str.isNull()) + str = QFileDialog::getOpenFileName(this, QString(), configname); + if (str.isEmpty()) return; if (conf_read(str.toLocal8Bit().constData())) @@ -1491,8 +1491,8 @@ void ConfigMainWindow::saveConfigAs(void) { QString str; - str = QFileDialog::getSaveFileName(this, "", configname); - if (str.isNull()) + str = QFileDialog::getSaveFileName(this, QString(), configname); + if (str.isEmpty()) return; if (conf_write(str.toLocal8Bit().constData())) { diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 89b84bf8e21f..7beb59dec5a0 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -388,6 +388,7 @@ static void sym_warn_unmet_dep(const struct symbol *sym) " Selected by [m]:\n"); fputs(str_get(&gs), stderr); + str_free(&gs); sym_warnings++; } diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 7ea59dc4926b..c35d22607978 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -33,6 +33,10 @@ static bool module_enabled; static bool modversions; /* Is CONFIG_MODULE_SRCVERSION_ALL set? */ static bool all_versions; +/* Is CONFIG_BASIC_MODVERSIONS set? */ +static bool basic_modversions; +/* Is CONFIG_EXTENDED_MODVERSIONS set? */ +static bool extended_modversions; /* If we are modposting external module set to 1 */ static bool external_module; /* Only warn about unresolved symbols */ @@ -186,8 +190,8 @@ static struct module *new_module(const char *name, size_t namelen) /* * Set mod->is_gpl_compatible to true by default. If MODULE_LICENSE() - * is missing, do not check the use for EXPORT_SYMBOL_GPL() becasue - * modpost will exit wiht error anyway. + * is missing, do not check the use for EXPORT_SYMBOL_GPL() because + * modpost will exit with an error anyway. */ mod->is_gpl_compatible = true; @@ -503,6 +507,9 @@ static int parse_elf(struct elf_info *info, const char *filename) info->modinfo_len = sechdrs[i].sh_size; } else if (!strcmp(secname, ".export_symbol")) { info->export_symbol_secndx = i; + } else if (!strcmp(secname, ".no_trim_symbol")) { + info->no_trim_symbol = (void *)hdr + sechdrs[i].sh_offset; + info->no_trim_symbol_len = sechdrs[i].sh_size; } if (sechdrs[i].sh_type == SHT_SYMTAB) { @@ -1562,6 +1569,14 @@ static void read_symbols(const char *modname) /* strip trailing .o */ mod = new_module(modname, strlen(modname) - strlen(".o")); + /* save .no_trim_symbol section for later use */ + if (info.no_trim_symbol_len) { + mod->no_trim_symbol = xmalloc(info.no_trim_symbol_len); + memcpy(mod->no_trim_symbol, info.no_trim_symbol, + info.no_trim_symbol_len); + mod->no_trim_symbol_len = info.no_trim_symbol_len; + } + if (!mod->is_vmlinux) { license = get_modinfo(&info, "license"); if (!license) @@ -1724,6 +1739,28 @@ static void handle_white_list_exports(const char *white_list) free(buf); } +/* + * Keep symbols recorded in the .no_trim_symbol section. This is necessary to + * prevent CONFIG_TRIM_UNUSED_KSYMS from dropping EXPORT_SYMBOL because + * symbol_get() relies on the symbol being present in the ksymtab for lookups. + */ +static void keep_no_trim_symbols(struct module *mod) +{ + unsigned long size = mod->no_trim_symbol_len; + + for (char *s = mod->no_trim_symbol; s; s = next_string(s , &size)) { + struct symbol *sym; + + /* + * If find_symbol() returns NULL, this symbol is not provided + * by any module, and symbol_get() will fail. + */ + sym = find_symbol(s); + if (sym) + sym->used = true; + } +} + static void check_modname_len(struct module *mod) { const char *mod_name; @@ -1806,13 +1843,56 @@ static void add_exported_symbols(struct buffer *buf, struct module *mod) } /** + * Record CRCs for unresolved symbols, supporting long names + */ +static void add_extended_versions(struct buffer *b, struct module *mod) +{ + struct symbol *s; + + if (!extended_modversions) + return; + + buf_printf(b, "\n"); + buf_printf(b, "static const u32 ____version_ext_crcs[]\n"); + buf_printf(b, "__used __section(\"__version_ext_crcs\") = {\n"); + list_for_each_entry(s, &mod->unresolved_symbols, list) { + if (!s->module) + continue; + if (!s->crc_valid) { + warn("\"%s\" [%s.ko] has no CRC!\n", + s->name, mod->name); + continue; + } + buf_printf(b, "\t0x%08x,\n", s->crc); + } + buf_printf(b, "};\n"); + + buf_printf(b, "static const char ____version_ext_names[]\n"); + buf_printf(b, "__used __section(\"__version_ext_names\") =\n"); + list_for_each_entry(s, &mod->unresolved_symbols, list) { + if (!s->module) + continue; + if (!s->crc_valid) + /* + * We already warned on this when producing the crc + * table. + * We need to skip its name too, as the indexes in + * both tables need to align. + */ + continue; + buf_printf(b, "\t\"%s\\0\"\n", s->name); + } + buf_printf(b, ";\n"); +} + +/** * Record CRCs for unresolved symbols **/ static void add_versions(struct buffer *b, struct module *mod) { struct symbol *s; - if (!modversions) + if (!basic_modversions) return; buf_printf(b, "\n"); @@ -1828,11 +1908,16 @@ static void add_versions(struct buffer *b, struct module *mod) continue; } if (strlen(s->name) >= MODULE_NAME_LEN) { - error("too long symbol \"%s\" [%s.ko]\n", - s->name, mod->name); - break; + if (extended_modversions) { + /* this symbol will only be in the extended info */ + continue; + } else { + error("too long symbol \"%s\" [%s.ko]\n", + s->name, mod->name); + break; + } } - buf_printf(b, "\t{ %#8x, \"%s\" },\n", + buf_printf(b, "\t{ 0x%08x, \"%s\" },\n", s->crc, s->name); } @@ -1961,6 +2046,7 @@ static void write_mod_c_file(struct module *mod) add_header(&buf, mod); add_exported_symbols(&buf, mod); add_versions(&buf, mod); + add_extended_versions(&buf, mod); add_depends(&buf, mod); buf_printf(&buf, "\n"); @@ -2126,7 +2212,7 @@ int main(int argc, char **argv) LIST_HEAD(dump_lists); struct dump_list *dl, *dl2; - while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:")) != -1) { + while ((opt = getopt(argc, argv, "ei:MmnT:to:au:WwENd:xb")) != -1) { switch (opt) { case 'e': external_module = true; @@ -2175,6 +2261,12 @@ int main(int argc, char **argv) case 'd': missing_namespace_deps = optarg; break; + case 'b': + basic_modversions = true; + break; + case 'x': + extended_modversions = true; + break; default: exit(1); } @@ -2195,6 +2287,8 @@ int main(int argc, char **argv) read_symbols_from_files(files_source); list_for_each_entry(mod, &modules, list) { + keep_no_trim_symbols(mod); + if (mod->dump_file || mod->is_vmlinux) continue; diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h index ffd0a52a606e..59366f456b76 100644 --- a/scripts/mod/modpost.h +++ b/scripts/mod/modpost.h @@ -111,6 +111,8 @@ struct module_alias { * * @dump_file: path to the .symvers file if loaded from a file * @aliases: list head for module_aliases + * @no_trim_symbol: .no_trim_symbol section data + * @no_trim_symbol_len: length of the .no_trim_symbol section */ struct module { struct list_head list; @@ -128,6 +130,8 @@ struct module { // Actual imported namespaces struct list_head imported_namespaces; struct list_head aliases; + char *no_trim_symbol; + unsigned int no_trim_symbol_len; char name[]; }; @@ -141,6 +145,8 @@ struct elf_info { char *strtab; char *modinfo; unsigned int modinfo_len; + char *no_trim_symbol; + unsigned int no_trim_symbol_len; /* support for 32bit section numbers */ diff --git a/scripts/module.lds.S b/scripts/module.lds.S index c2f80f9141d4..450f1088d5fd 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -16,6 +16,7 @@ SECTIONS { *(.discard) *(.discard.*) *(.export_symbol) + *(.no_trim_symbol) } __ksymtab 0 : ALIGN(8) { *(SORT(___ksymtab+*)) } diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index dca706617adc..0cf3a55b05e1 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -22,7 +22,6 @@ license=(GPL-2.0-only) makedepends=( bc bison - cpio flex gettext kmod diff --git a/scripts/package/builddeb b/scripts/package/builddeb index ad7aba0f268e..3627ca227e5a 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -5,10 +5,12 @@ # # Simple script to generate a deb package for a Linux kernel. All the # complexity of what to do with a kernel after it is installed or removed -# is left to other scripts and packages: they can install scripts in the -# /etc/kernel/{pre,post}{inst,rm}.d/ directories (or an alternative location -# specified in KDEB_HOOKDIR) that will be called on package install and -# removal. +# is left to other scripts and packages. Scripts can be placed into the +# preinst, postinst, prerm and postrm directories in /etc/kernel or +# /usr/share/kernel. A different list of search directories can be given +# via KDEB_HOOKDIR. Scripts in directories earlier in the list will +# override scripts of the same name in later directories. The script will +# be called on package installation and removal. set -eu @@ -74,10 +76,8 @@ install_maint_scripts () { # kernel packages, as well as kernel packages built using make-kpkg. # make-kpkg sets $INITRD to indicate whether an initramfs is wanted, and # so do we; recent versions of dracut and initramfs-tools will obey this. - debhookdir=${KDEB_HOOKDIR:-/etc/kernel} + debhookdir=${KDEB_HOOKDIR:-/etc/kernel /usr/share/kernel} for script in postinst postrm preinst prerm; do - mkdir -p "${pdir}${debhookdir}/${script}.d" - mkdir -p "${pdir}/DEBIAN" cat <<-EOF > "${pdir}/DEBIAN/${script}" #!/bin/sh @@ -90,7 +90,15 @@ install_maint_scripts () { # Tell initramfs builder whether it's wanted export INITRD=$(if_enabled_echo CONFIG_BLK_DEV_INITRD Yes No) - test -d ${debhookdir}/${script}.d && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" ${debhookdir}/${script}.d + # run-parts will error out if one of its directory arguments does not + # exist, so filter the list of hook directories accordingly. + hookdirs= + for dir in ${debhookdir}; do + test -d "\$dir/${script}.d" || continue + hookdirs="\$hookdirs \$dir/${script}.d" + done + hookdirs="\${hookdirs# }" + test -n "\$hookdirs" && run-parts --arg="${KERNELRELEASE}" --arg="/${installed_image_path}" \$hookdirs exit 0 EOF chmod 755 "${pdir}/DEBIAN/${script}" diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build index d3c5b104c063..2966473b4660 100755 --- a/scripts/package/install-extmod-build +++ b/scripts/package/install-extmod-build @@ -49,17 +49,10 @@ mkdir -p "${destdir}" # This caters to host programs that participate in Kbuild. objtool and # resolve_btfids are out of scope. if [ "${CC}" != "${HOSTCC}" ]; then - echo "Rebuilding host programs with ${CC}..." - - # This leverages external module building. - # - Clear sub_make_done to allow the top-level Makefile to redo sub-make. - # - Filter out --no-print-directory to print "Entering directory" logs - # when Make changes the working directory. - unset sub_make_done - MAKEFLAGS=$(echo "${MAKEFLAGS}" | sed s/--no-print-directory//) - - cat <<-'EOF' > "${destdir}/Kbuild" - subdir-y := scripts + cat "${destdir}/scripts/Makefile" - <<-'EOF' > "${destdir}/scripts/Kbuild" + subdir-y += basic + hostprogs-always-y += mod/modpost + mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o) EOF # HOSTCXX is not overridden. The C++ compiler is used to build: @@ -67,20 +60,12 @@ if [ "${CC}" != "${HOSTCC}" ]; then # - GCC plugins, which will not work on the installed system even after # being rebuilt. # - # Use the single-target build to avoid the modpost invocation, which - # would overwrite Module.symvers. - "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ - - cat <<-'EOF' > "${destdir}/scripts/Kbuild" - subdir-y := basic - hostprogs-always-y := mod/modpost - mod/modpost-objs := $(addprefix mod/, modpost.o file2alias.o sumversion.o symsearch.o) - EOF - - # Run once again to rebuild scripts/basic/ and scripts/mod/modpost. - "${MAKE}" HOSTCC="${CC}" KBUILD_OUTPUT=. KBUILD_EXTMOD="${destdir}" scripts/ + # Clear VPATH and srcroot because the source files reside in the output + # directory. + # shellcheck disable=SC2016 # $(MAKE) and $(build) will be expanded by Make + "${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"${destdir}"/scripts - rm -f "${destdir}/Kbuild" "${destdir}/scripts/Kbuild" + rm -f "${destdir}/scripts/Kbuild" fi find "${destdir}" \( -name '.*.cmd' -o -name '*.o' \) -delete diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index b038a1380b8a..b6dd98ca860b 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -205,7 +205,7 @@ Priority: optional Maintainer: $maintainer Rules-Requires-Root: no Build-Depends: debhelper-compat (= 12) -Build-Depends-Arch: bc, bison, cpio, flex, +Build-Depends-Arch: bc, bison, flex, gcc-${host_gnu} <!pkg.${sourcename}.nokernelheaders>, kmod, libelf-dev:native, libssl-dev:native, libssl-dev <!pkg.${sourcename}.nokernelheaders>, diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 1edc12862a7d..9b6c2f157f83 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -2038,7 +2038,7 @@ static int apparmor_dointvec(const struct ctl_table *table, int write, return proc_dointvec(table, write, buffer, lenp, ppos); } -static struct ctl_table apparmor_sysctl_table[] = { +static const struct ctl_table apparmor_sysctl_table[] = { #ifdef CONFIG_USER_NS { .procname = "unprivileged_userns_apparmor_policy", diff --git a/security/keys/sysctl.c b/security/keys/sysctl.c index 91f000eef3ad..cde08c478f32 100644 --- a/security/keys/sysctl.c +++ b/security/keys/sysctl.c @@ -9,7 +9,7 @@ #include <linux/sysctl.h> #include "internal.h" -static struct ctl_table key_sysctls[] = { +static const struct ctl_table key_sysctls[] = { { .procname = "maxkeys", .data = &key_quota_maxkeys, diff --git a/security/tomoyo/common.c b/security/tomoyo/common.c index d9fa69632147..0f78898bce09 100644 --- a/security/tomoyo/common.c +++ b/security/tomoyo/common.c @@ -1981,6 +1981,114 @@ static int tomoyo_truncate(char *str) } /** + * tomoyo_numscan - sscanf() which stores the length of a decimal integer value. + * + * @str: String to scan. + * @head: Leading string that must start with. + * @width: Pointer to "int" for storing length of a decimal integer value after @head. + * @tail: Optional character that must match after a decimal integer value. + * + * Returns whether @str starts with @head and a decimal value follows @head. + */ +static bool tomoyo_numscan(const char *str, const char *head, int *width, const char tail) +{ + const char *cp; + const int n = strlen(head); + + if (!strncmp(str, head, n)) { + cp = str + n; + while (*cp && *cp >= '0' && *cp <= '9') + cp++; + if (*cp == tail || !tail) { + *width = cp - (str + n); + return *width != 0; + } + } + *width = 0; + return 0; +} + +/** + * tomoyo_patternize_path - Make patterns for file path. Used by learning mode. + * + * @buffer: Destination buffer. + * @len: Size of @buffer. + * @entry: Original line. + * + * Returns nothing. + */ +static void tomoyo_patternize_path(char *buffer, const int len, char *entry) +{ + int width; + char *cp = entry; + + /* Nothing to do if this line is not for "file" related entry. */ + if (strncmp(entry, "file ", 5)) + goto flush; + /* + * Nothing to do if there is no colon in this line, for this rewriting + * applies to only filesystems where numeric values in the path are volatile. + */ + cp = strchr(entry + 5, ':'); + if (!cp) { + cp = entry; + goto flush; + } + /* Flush e.g. "file ioctl" part. */ + while (*cp != ' ') + cp--; + *cp++ = '\0'; + tomoyo_addprintf(buffer, len, "%s ", entry); + /* e.g. file ioctl pipe:[$INO] $CMD */ + if (tomoyo_numscan(cp, "pipe:[", &width, ']')) { + cp += width + 7; + tomoyo_addprintf(buffer, len, "pipe:[\\$]"); + goto flush; + } + /* e.g. file ioctl socket:[$INO] $CMD */ + if (tomoyo_numscan(cp, "socket:[", &width, ']')) { + cp += width + 9; + tomoyo_addprintf(buffer, len, "socket:[\\$]"); + goto flush; + } + if (!strncmp(cp, "proc:/self", 10)) { + /* e.g. file read proc:/self/task/$TID/fdinfo/$FD */ + cp += 10; + tomoyo_addprintf(buffer, len, "proc:/self"); + } else if (tomoyo_numscan(cp, "proc:/", &width, 0)) { + /* e.g. file read proc:/$PID/task/$TID/fdinfo/$FD */ + /* + * Don't patternize $PID part if $PID == 1, for several + * programs access only files in /proc/1/ directory. + */ + cp += width + 6; + if (width == 1 && *(cp - 1) == '1') + tomoyo_addprintf(buffer, len, "proc:/1"); + else + tomoyo_addprintf(buffer, len, "proc:/\\$"); + } else { + goto flush; + } + /* Patternize $TID part if "/task/" follows. */ + if (tomoyo_numscan(cp, "/task/", &width, 0)) { + cp += width + 6; + tomoyo_addprintf(buffer, len, "/task/\\$"); + } + /* Patternize $FD part if "/fd/" or "/fdinfo/" follows. */ + if (tomoyo_numscan(cp, "/fd/", &width, 0)) { + cp += width + 4; + tomoyo_addprintf(buffer, len, "/fd/\\$"); + } else if (tomoyo_numscan(cp, "/fdinfo/", &width, 0)) { + cp += width + 8; + tomoyo_addprintf(buffer, len, "/fdinfo/\\$"); + } +flush: + /* Flush remaining part if any. */ + if (*cp) + tomoyo_addprintf(buffer, len, "%s", cp); +} + +/** * tomoyo_add_entry - Add an ACL to current thread's domain. Used by learning mode. * * @domain: Pointer to "struct tomoyo_domain_info". @@ -2003,7 +2111,8 @@ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) if (!cp) return; *cp++ = '\0'; - len = strlen(cp) + 1; + /* Reserve some space for potentially using patterns. */ + len = strlen(cp) + 16; /* strstr() will return NULL if ordering is wrong. */ if (*cp == 'f') { argv0 = strstr(header, " argv[]={ \""); @@ -2020,40 +2129,10 @@ static void tomoyo_add_entry(struct tomoyo_domain_info *domain, char *header) if (symlink) len += tomoyo_truncate(symlink + 1) + 1; } - buffer = kmalloc(len, GFP_NOFS); + buffer = kmalloc(len, GFP_NOFS | __GFP_ZERO); if (!buffer) return; - snprintf(buffer, len - 1, "%s", cp); - if (*cp == 'f' && strchr(buffer, ':')) { - /* Automatically replace 2 or more digits with \$ pattern. */ - char *cp2; - - /* e.g. file read proc:/$PID/stat */ - cp = strstr(buffer, " proc:/"); - if (cp && simple_strtoul(cp + 7, &cp2, 10) >= 10 && *cp2 == '/') { - *(cp + 7) = '\\'; - *(cp + 8) = '$'; - memmove(cp + 9, cp2, strlen(cp2) + 1); - goto ok; - } - /* e.g. file ioctl pipe:[$INO] $CMD */ - cp = strstr(buffer, " pipe:["); - if (cp && simple_strtoul(cp + 7, &cp2, 10) >= 10 && *cp2 == ']') { - *(cp + 7) = '\\'; - *(cp + 8) = '$'; - memmove(cp + 9, cp2, strlen(cp2) + 1); - goto ok; - } - /* e.g. file ioctl socket:[$INO] $CMD */ - cp = strstr(buffer, " socket:["); - if (cp && simple_strtoul(cp + 9, &cp2, 10) >= 10 && *cp2 == ']') { - *(cp + 9) = '\\'; - *(cp + 10) = '$'; - memmove(cp + 11, cp2, strlen(cp2) + 1); - goto ok; - } - } -ok: + tomoyo_patternize_path(buffer, len, cp); if (realpath) tomoyo_addprintf(buffer, len, " exec.%s", realpath); if (argv0) diff --git a/security/tomoyo/domain.c b/security/tomoyo/domain.c index 3a7b0874cf44..5f9ccab26e9a 100644 --- a/security/tomoyo/domain.c +++ b/security/tomoyo/domain.c @@ -920,7 +920,7 @@ bool tomoyo_dump_page(struct linux_binprm *bprm, unsigned long pos, #ifdef CONFIG_MMU /* * This is called at execve() time in order to dig around - * in the argv/environment of the new proceess + * in the argv/environment of the new process * (represented by bprm). */ mmap_read_lock(bprm->mm); diff --git a/security/tomoyo/securityfs_if.c b/security/tomoyo/securityfs_if.c index a2705798476f..7e69747b2f77 100644 --- a/security/tomoyo/securityfs_if.c +++ b/security/tomoyo/securityfs_if.c @@ -229,11 +229,11 @@ static void __init tomoyo_create_entry(const char *name, const umode_t mode, } /** - * tomoyo_initerface_init - Initialize /sys/kernel/security/tomoyo/ interface. + * tomoyo_interface_init - Initialize /sys/kernel/security/tomoyo/ interface. * * Returns 0. */ -static int __init tomoyo_initerface_init(void) +static int __init tomoyo_interface_init(void) { struct tomoyo_domain_info *domain; struct dentry *tomoyo_dir; @@ -270,4 +270,4 @@ static int __init tomoyo_initerface_init(void) return 0; } -fs_initcall(tomoyo_initerface_init); +fs_initcall(tomoyo_interface_init); diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c index 04a92c3d65d4..d6ebcd9db80a 100644 --- a/security/tomoyo/tomoyo.c +++ b/security/tomoyo/tomoyo.c @@ -549,10 +549,7 @@ static const struct lsm_id tomoyo_lsmid = { .id = LSM_ID_TOMOYO, }; -/* - * tomoyo_security_ops is a "struct security_operations" which is used for - * registering TOMOYO. - */ +/* tomoyo_hooks is used for registering TOMOYO. */ static struct security_hook_list tomoyo_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, tomoyo_cred_prepare), LSM_HOOK_INIT(bprm_committed_creds, tomoyo_bprm_committed_creds), diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c index 1a2d02fee09b..1971710620c1 100644 --- a/security/yama/yama_lsm.c +++ b/security/yama/yama_lsm.c @@ -452,7 +452,7 @@ static int yama_dointvec_minmax(const struct ctl_table *table, int write, static int max_scope = YAMA_SCOPE_NO_ATTACH; -static struct ctl_table yama_sysctl_table[] = { +static const struct ctl_table yama_sysctl_table[] = { { .procname = "ptrace_scope", .data = &ptrace_scope, diff --git a/sound/core/hrtimer.c b/sound/core/hrtimer.c index 147c1fea4708..e9c60dce59fb 100644 --- a/sound/core/hrtimer.c +++ b/sound/core/hrtimer.c @@ -66,9 +66,8 @@ static int snd_hrtimer_open(struct snd_timer *t) stime = kzalloc(sizeof(*stime), GFP_KERNEL); if (!stime) return -ENOMEM; - hrtimer_init(&stime->hrt, CLOCK_MONOTONIC, HRTIMER_MODE_REL); stime->timer = t; - stime->hrt.function = snd_hrtimer_callback; + hrtimer_setup(&stime->hrt, snd_hrtimer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_REL); t->private_data = stime; return 0; } diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 8a3384342e8d..6c2b6a62d9d2 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3245,7 +3245,7 @@ static int snd_pcm_xfern_frames_ioctl(struct snd_pcm_substream *substream, if (copy_from_user(&xfern, _xfern, sizeof(xfern))) return -EFAULT; - bufs = memdup_user(xfern.bufs, sizeof(void *) * runtime->channels); + bufs = memdup_array_user(xfern.bufs, runtime->channels, sizeof(void *)); if (IS_ERR(bufs)) return PTR_ERR(bufs); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 073b56dc2225..cb66ec42a3f8 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -678,12 +678,18 @@ static int snd_seq_deliver_single_event(struct snd_seq_client *client, dest_port->time_real); #if IS_ENABLED(CONFIG_SND_SEQ_UMP) - if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) { - if (snd_seq_ev_is_ump(event)) { + if (snd_seq_ev_is_ump(event)) { + if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) { result = snd_seq_deliver_from_ump(client, dest, dest_port, event, atomic, hop); goto __skip; - } else if (snd_seq_client_is_ump(dest)) { + } else if (dest->type == USER_CLIENT && + !snd_seq_client_is_ump(dest)) { + result = 0; // drop the event + goto __skip; + } + } else if (snd_seq_client_is_ump(dest)) { + if (!(dest->filter & SNDRV_SEQ_FILTER_NO_CONVERT)) { result = snd_seq_deliver_to_ump(client, dest, dest_port, event, atomic, hop); goto __skip; diff --git a/sound/drivers/dummy.c b/sound/drivers/dummy.c index 8f5df9b3aaaa..c1a3efb633c5 100644 --- a/sound/drivers/dummy.c +++ b/sound/drivers/dummy.c @@ -457,8 +457,7 @@ static int dummy_hrtimer_create(struct snd_pcm_substream *substream) if (!dpcm) return -ENOMEM; substream->runtime->private_data = dpcm; - hrtimer_init(&dpcm->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); - dpcm->timer.function = dummy_hrtimer_callback; + hrtimer_setup(&dpcm->timer, dummy_hrtimer_callback, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); dpcm->substream = substream; atomic_set(&dpcm->running, 0); return 0; diff --git a/sound/drivers/pcsp/pcsp.c b/sound/drivers/pcsp/pcsp.c index 78c9b1c7590f..e8482c2290c3 100644 --- a/sound/drivers/pcsp/pcsp.c +++ b/sound/drivers/pcsp/pcsp.c @@ -103,8 +103,7 @@ static int snd_card_pcsp_probe(int devnum, struct device *dev) if (devnum != 0) return -EINVAL; - hrtimer_init(&pcsp_chip.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - pcsp_chip.timer.function = pcsp_do_timer; + hrtimer_setup(&pcsp_chip.timer, pcsp_do_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); err = snd_devm_card_new(dev, index, id, THIS_MODULE, 0, &card); if (err < 0) diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c index f564ec7af194..ce3ae2cba660 100644 --- a/sound/hda/intel-dsp-config.c +++ b/sound/hda/intel-dsp-config.c @@ -539,6 +539,11 @@ static const struct config_entry config_table[] = { .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, .device = PCI_DEVICE_ID_INTEL_HDA_PTL, }, + { + .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC_OR_SOUNDWIRE, + .device = PCI_DEVICE_ID_INTEL_HDA_PTL_H, + }, + #endif }; diff --git a/sound/pci/hda/hda_auto_parser.c b/sound/pci/hda/hda_auto_parser.c index 84393f4f429d..8923813ce424 100644 --- a/sound/pci/hda/hda_auto_parser.c +++ b/sound/pci/hda/hda_auto_parser.c @@ -80,7 +80,11 @@ static int compare_input_type(const void *ap, const void *bp) /* In case one has boost and the other one has not, pick the one with boost first. */ - return (int)(b->has_boost_on_pin - a->has_boost_on_pin); + if (a->has_boost_on_pin != b->has_boost_on_pin) + return (int)(b->has_boost_on_pin - a->has_boost_on_pin); + + /* Keep the original order */ + return a->order - b->order; } /* Reorder the surround channels @@ -400,6 +404,8 @@ int snd_hda_parse_pin_defcfg(struct hda_codec *codec, reorder_outputs(cfg->speaker_outs, cfg->speaker_pins); /* sort inputs in the order of AUTO_PIN_* type */ + for (i = 0; i < cfg->num_inputs; i++) + cfg->inputs[i].order = i; sort(cfg->inputs, cfg->num_inputs, sizeof(cfg->inputs[0]), compare_input_type, NULL); diff --git a/sound/pci/hda/hda_auto_parser.h b/sound/pci/hda/hda_auto_parser.h index 579b11beac71..87af3d8c02f7 100644 --- a/sound/pci/hda/hda_auto_parser.h +++ b/sound/pci/hda/hda_auto_parser.h @@ -37,6 +37,7 @@ struct auto_pin_cfg_item { unsigned int is_headset_mic:1; unsigned int is_headphone_mic:1; /* Mic-only in headphone jack */ unsigned int has_boost_on_pin:1; + int order; }; struct auto_pin_cfg; diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 14763c0f31ad..46a220404999 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -2470,7 +2470,9 @@ int snd_hda_create_dig_out_ctls(struct hda_codec *codec, break; id = kctl->id; id.index = spdif_index; - snd_ctl_rename_id(codec->card, &kctl->id, &id); + err = snd_ctl_rename_id(codec->card, &kctl->id, &id); + if (err < 0) + return err; } bus->primary_dig_out_type = HDA_PCM_TYPE_HDMI; } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 7d7f9aac50a9..67540e037309 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2496,6 +2496,8 @@ static const struct pci_device_id azx_ids[] = { { PCI_DEVICE_DATA(INTEL, HDA_ARL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE) }, /* Panther Lake */ { PCI_DEVICE_DATA(INTEL, HDA_PTL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_LNL) }, + /* Panther Lake-H */ + { PCI_DEVICE_DATA(INTEL, HDA_PTL_H, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_LNL) }, /* Apollolake (Broxton-P) */ { PCI_DEVICE_DATA(INTEL, HDA_APL, AZX_DRIVER_SKL | AZX_DCAPS_INTEL_BROXTON) }, /* Gemini-Lake */ diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 4985e72b9094..34874039ad45 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -1090,6 +1090,7 @@ static const struct hda_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO), + SND_PCI_QUIRK(0x103c, 0x8231, "HP ProBook 450 G4", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), diff --git a/sound/pci/hda/patch_cs8409-tables.c b/sound/pci/hda/patch_cs8409-tables.c index 759f48038273..09240138e087 100644 --- a/sound/pci/hda/patch_cs8409-tables.c +++ b/sound/pci/hda/patch_cs8409-tables.c @@ -121,7 +121,7 @@ static const struct cs8409_i2c_param cs42l42_init_reg_seq[] = { { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3f }, - { CS42L42_HP_CTL, 0x03 }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_MIC_DET_CTL1, 0xB6 }, { CS42L42_TIPSENSE_CTL, 0xC2 }, { CS42L42_HS_CLAMP_DISABLE, 0x01 }, @@ -131,7 +131,7 @@ static const struct cs8409_i2c_param cs42l42_init_reg_seq[] = { { CS42L42_RSENSE_CTL3, 0x00 }, { CS42L42_TSENSE_CTL, 0x80 }, { CS42L42_HS_BIAS_CTL, 0xC0 }, - { CS42L42_PWR_CTL1, 0x02 }, + { CS42L42_PWR_CTL1, 0x02, 10000 }, { CS42L42_ADC_OVFL_INT_MASK, 0xff }, { CS42L42_MIXER_INT_MASK, 0xff }, { CS42L42_SRC_INT_MASK, 0xff }, @@ -315,7 +315,7 @@ static const struct cs8409_i2c_param dolphin_c0_init_reg_seq[] = { { CS42L42_ASP_TX_SZ_EN, 0x01 }, { CS42L42_PWR_CTL1, 0x0A }, { CS42L42_PWR_CTL2, 0x84 }, - { CS42L42_HP_CTL, 0x03 }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3f }, @@ -328,7 +328,7 @@ static const struct cs8409_i2c_param dolphin_c0_init_reg_seq[] = { { CS42L42_RSENSE_CTL3, 0x00 }, { CS42L42_TSENSE_CTL, 0x80 }, { CS42L42_HS_BIAS_CTL, 0xC0 }, - { CS42L42_PWR_CTL1, 0x02 }, + { CS42L42_PWR_CTL1, 0x02, 10000 }, { CS42L42_ADC_OVFL_INT_MASK, 0xff }, { CS42L42_MIXER_INT_MASK, 0xff }, { CS42L42_SRC_INT_MASK, 0xff }, @@ -371,7 +371,7 @@ static const struct cs8409_i2c_param dolphin_c1_init_reg_seq[] = { { CS42L42_ASP_TX_SZ_EN, 0x00 }, { CS42L42_PWR_CTL1, 0x0E }, { CS42L42_PWR_CTL2, 0x84 }, - { CS42L42_HP_CTL, 0x01 }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3f }, @@ -384,7 +384,7 @@ static const struct cs8409_i2c_param dolphin_c1_init_reg_seq[] = { { CS42L42_RSENSE_CTL3, 0x00 }, { CS42L42_TSENSE_CTL, 0x80 }, { CS42L42_HS_BIAS_CTL, 0xC0 }, - { CS42L42_PWR_CTL1, 0x06 }, + { CS42L42_PWR_CTL1, 0x06, 10000 }, { CS42L42_ADC_OVFL_INT_MASK, 0xff }, { CS42L42_MIXER_INT_MASK, 0xff }, { CS42L42_SRC_INT_MASK, 0xff }, diff --git a/sound/pci/hda/patch_cs8409.c b/sound/pci/hda/patch_cs8409.c index 614327218634..e50006757a2c 100644 --- a/sound/pci/hda/patch_cs8409.c +++ b/sound/pci/hda/patch_cs8409.c @@ -346,6 +346,11 @@ static int cs8409_i2c_bulk_write(struct sub_codec *scodec, const struct cs8409_i if (cs8409_i2c_wait_complete(codec) < 0) goto error; + /* Certain use cases may require a delay + * after a write operation before proceeding. + */ + if (seq[i].delay) + fsleep(seq[i].delay); } mutex_unlock(&spec->i2c_mux); @@ -876,7 +881,7 @@ static void cs42l42_resume(struct sub_codec *cs42l42) { CS42L42_DET_INT_STATUS2, 0x00 }, { CS42L42_TSRS_PLUG_STATUS, 0x00 }, }; - int fsv_old, fsv_new; + unsigned int fsv; /* Bring CS42L42 out of Reset */ spec->gpio_data = snd_hda_codec_read(codec, CS8409_PIN_AFG, 0, AC_VERB_GET_GPIO_DATA, 0); @@ -888,18 +893,19 @@ static void cs42l42_resume(struct sub_codec *cs42l42) /* Initialize CS42L42 companion codec */ cs8409_i2c_bulk_write(cs42l42, cs42l42->init_seq, cs42l42->init_seq_num); - msleep(CS42L42_INIT_TIMEOUT_MS); /* Clear interrupts, by reading interrupt status registers */ cs8409_i2c_bulk_read(cs42l42, irq_regs, ARRAY_SIZE(irq_regs)); - fsv_old = cs8409_i2c_read(cs42l42, CS42L42_HP_CTL); - if (cs42l42->full_scale_vol == CS42L42_FULL_SCALE_VOL_0DB) - fsv_new = fsv_old & ~CS42L42_FULL_SCALE_VOL_MASK; - else - fsv_new = fsv_old & CS42L42_FULL_SCALE_VOL_MASK; - if (fsv_new != fsv_old) - cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv_new); + fsv = cs8409_i2c_read(cs42l42, CS42L42_HP_CTL); + if (cs42l42->full_scale_vol) { + // Set the full scale volume bit + fsv |= CS42L42_FULL_SCALE_VOL_MASK; + cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv); + } + // Unmute analog channels A and B + fsv = (fsv & ~CS42L42_ANA_MUTE_AB); + cs8409_i2c_write(cs42l42, CS42L42_HP_CTL, fsv); /* we have to explicitly allow unsol event handling even during the * resume phase so that the jack event is processed properly @@ -920,7 +926,7 @@ static void cs42l42_suspend(struct sub_codec *cs42l42) { CS42L42_MIXER_CHA_VOL, 0x3F }, { CS42L42_MIXER_ADC_VOL, 0x3F }, { CS42L42_MIXER_CHB_VOL, 0x3F }, - { CS42L42_HP_CTL, 0x0F }, + { CS42L42_HP_CTL, 0x0D }, { CS42L42_ASP_RX_DAI0_EN, 0x00 }, { CS42L42_ASP_CLK_CFG, 0x00 }, { CS42L42_PWR_CTL1, 0xFE }, diff --git a/sound/pci/hda/patch_cs8409.h b/sound/pci/hda/patch_cs8409.h index 5e48115caf09..e4bd2e12110b 100644 --- a/sound/pci/hda/patch_cs8409.h +++ b/sound/pci/hda/patch_cs8409.h @@ -229,10 +229,10 @@ enum cs8409_coefficient_index_registers { #define CS42L42_I2C_SLEEP_US (2000) #define CS42L42_PDN_TIMEOUT_US (250000) #define CS42L42_PDN_SLEEP_US (2000) -#define CS42L42_INIT_TIMEOUT_MS (45) +#define CS42L42_ANA_MUTE_AB (0x0C) #define CS42L42_FULL_SCALE_VOL_MASK (2) -#define CS42L42_FULL_SCALE_VOL_0DB (1) -#define CS42L42_FULL_SCALE_VOL_MINUS6DB (0) +#define CS42L42_FULL_SCALE_VOL_0DB (0) +#define CS42L42_FULL_SCALE_VOL_MINUS6DB (1) /* Dell BULLSEYE / WARLOCK / CYBORG Specific Definitions */ @@ -290,6 +290,7 @@ enum { struct cs8409_i2c_param { unsigned int addr; unsigned int value; + unsigned int delay; }; struct cs8409_cir_param { diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index d3c9ed963588..224616fbec4f 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3788,6 +3788,7 @@ static void alc225_init(struct hda_codec *codec) AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE); msleep(75); + alc_update_coef_idx(codec, 0x4a, 3 << 10, 0); alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x4); /* Hight power */ } } @@ -7497,6 +7498,16 @@ static void alc287_fixup_lenovo_thinkpad_with_alc1318(struct hda_codec *codec, spec->gen.pcm_playback_hook = alc287_alc1318_playback_pcm_hook; } +/* + * Clear COEF 0x0d (PCBEEP passthrough) bit 0x40 where BIOS sets it wrongly + * at PM resume + */ +static void alc283_fixup_dell_hp_resume(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action == HDA_FIXUP_ACT_INIT) + alc_write_coef_idx(codec, 0xd, 0x2800); +} enum { ALC269_FIXUP_GPIO2, @@ -7799,6 +7810,7 @@ enum { ALC269_FIXUP_VAIO_VJFH52_MIC_NO_PRESENCE, ALC233_FIXUP_MEDION_MTL_SPK, ALC294_FIXUP_BASS_SPEAKER_15, + ALC283_FIXUP_DELL_HP_RESUME, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -10143,6 +10155,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc294_fixup_bass_speaker_15, }, + [ALC283_FIXUP_DELL_HP_RESUME] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc283_fixup_dell_hp_resume, + }, }; static const struct hda_quirk alc269_fixup_tbl[] = { @@ -10203,6 +10219,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x05f4, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x05f5, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x05f6, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1028, 0x0604, "Dell Venue 11 Pro 7130", ALC283_FIXUP_DELL_HP_RESUME), SND_PCI_QUIRK(0x1028, 0x0615, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x0616, "Dell Vostro 5470", ALC290_FIXUP_SUBWOOFER_HSJACK), SND_PCI_QUIRK(0x1028, 0x062c, "Dell Latitude E5550", ALC292_FIXUP_DELL_E7X), @@ -10918,7 +10935,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN), HDA_CODEC_QUIRK(0x17aa, 0x386e, "Legion Y9000X 2022 IAH7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x386e, "Yoga Pro 7 14ARP8", ALC285_FIXUP_SPEAKER2_TO_DAC1), - HDA_CODEC_QUIRK(0x17aa, 0x386f, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), + HDA_CODEC_QUIRK(0x17aa, 0x38a8, "Legion Pro 7 16ARX8H", ALC287_FIXUP_TAS2781_I2C), /* this must match before PCI SSID 17aa:386f below */ SND_PCI_QUIRK(0x17aa, 0x386f, "Legion Pro 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C), SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2), @@ -11029,6 +11046,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1d72, 0x1945, "Redmi G", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC), SND_PCI_QUIRK(0x1f66, 0x0105, "Ayaneo Portable Game Player", ALC287_FIXUP_CS35L41_I2C_2), + SND_PCI_QUIRK(0x2014, 0x800a, "Positivo ARN50", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13), SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO), diff --git a/sound/pci/hda/tas2781_hda_spi.c b/sound/pci/hda/tas2781_hda_spi.c index a42fa990e7b9..04db80af53c0 100644 --- a/sound/pci/hda/tas2781_hda_spi.c +++ b/sound/pci/hda/tas2781_hda_spi.c @@ -912,7 +912,7 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) struct tasdevice_priv *tas_priv = context; struct tas2781_hda *tas_hda = dev_get_drvdata(tas_priv->dev); struct hda_codec *codec = tas_priv->codec; - int i, j, ret; + int i, j, ret, val; pm_runtime_get_sync(tas_priv->dev); guard(mutex)(&tas_priv->codec_lock); @@ -981,13 +981,16 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) /* Perform AMP reset before firmware download. */ tas_priv->rcabin.profile_cfg_id = TAS2781_PRE_POST_RESET_CFG; - tasdevice_spi_tuning_switch(tas_priv, 0); tas2781_spi_reset(tas_priv); tas_priv->rcabin.profile_cfg_id = 0; - tasdevice_spi_tuning_switch(tas_priv, 1); tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK; - ret = tasdevice_spi_prmg_load(tas_priv, 0); + ret = tasdevice_spi_dev_read(tas_priv, TAS2781_REG_CLK_CONFIG, &val); + if (ret < 0) + goto out; + + if (val == TAS2781_REG_CLK_CONFIG_RESET) + ret = tasdevice_spi_prmg_load(tas_priv, 0); if (ret < 0) { dev_err(tas_priv->dev, "FW download failed = %d\n", ret); goto out; @@ -1001,7 +1004,6 @@ static void tasdev_fw_ready(const struct firmware *fmw, void *context) * If calibrated data occurs error, dsp will still works with default * calibrated data inside algo. */ - tas_priv->save_calibration(tas_priv); out: if (fmw) @@ -1160,7 +1162,8 @@ static int tas2781_runtime_suspend(struct device *dev) guard(mutex)(&tas_hda->priv->codec_lock); - tasdevice_spi_tuning_switch(tas_hda->priv, 1); + if (tas_hda->priv->playback_started) + tasdevice_spi_tuning_switch(tas_hda->priv, 1); tas_hda->priv->cur_book = -1; tas_hda->priv->cur_conf = -1; @@ -1174,7 +1177,8 @@ static int tas2781_runtime_resume(struct device *dev) guard(mutex)(&tas_hda->priv->codec_lock); - tasdevice_spi_tuning_switch(tas_hda->priv, 0); + if (tas_hda->priv->playback_started) + tasdevice_spi_tuning_switch(tas_hda->priv, 0); return 0; } @@ -1189,12 +1193,9 @@ static int tas2781_system_suspend(struct device *dev) return ret; /* Shutdown chip before system suspend */ - tasdevice_spi_tuning_switch(tas_hda->priv, 1); - tas2781_spi_reset(tas_hda->priv); - /* - * Reset GPIO may be shared, so cannot reset here. - * However beyond this point, amps may be powered down. - */ + if (tas_hda->priv->playback_started) + tasdevice_spi_tuning_switch(tas_hda->priv, 1); + return 0; } diff --git a/sound/pci/hda/tas2781_spi_fwlib.c b/sound/pci/hda/tas2781_spi_fwlib.c index 0e2acbc3c900..131d9a77d140 100644 --- a/sound/pci/hda/tas2781_spi_fwlib.c +++ b/sound/pci/hda/tas2781_spi_fwlib.c @@ -2,7 +2,7 @@ // // TAS2781 HDA SPI driver // -// Copyright 2024 Texas Instruments, Inc. +// Copyright 2024-2025 Texas Instruments, Inc. // // Author: Baojun Xu <baojun.xu@ti.com> @@ -771,19 +771,19 @@ static int tasdevice_process_block(void *context, unsigned char *data, switch (subblk_typ) { case TASDEVICE_CMD_SING_W: subblk_offset = tasdevice_single_byte_wr(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; case TASDEVICE_CMD_BURST: subblk_offset = tasdevice_burst_wr(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; case TASDEVICE_CMD_DELAY: subblk_offset = tasdevice_delay(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; case TASDEVICE_CMD_FIELD_W: subblk_offset = tasdevice_field_wr(tas_priv, - dev_idx & 0x4f, data, sublocksize); + dev_idx & 0x3f, data, sublocksize); break; default: subblk_offset = 2; diff --git a/sound/sh/sh_dac_audio.c b/sound/sh/sh_dac_audio.c index 3f5422145c5e..84a4b17a0cc2 100644 --- a/sound/sh/sh_dac_audio.c +++ b/sound/sh/sh_dac_audio.c @@ -312,8 +312,7 @@ static int snd_sh_dac_create(struct snd_card *card, chip->card = card; - hrtimer_init(&chip->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - chip->hrtimer.function = sh_dac_audio_timer; + hrtimer_setup(&chip->hrtimer, sh_dac_audio_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); dac_audio_reset(chip); chip->rate = 8000; diff --git a/sound/soc/amd/acp/acp-i2s.c b/sound/soc/amd/acp/acp-i2s.c index 1f59ee248771..89e99ed4275a 100644 --- a/sound/soc/amd/acp/acp-i2s.c +++ b/sound/soc/amd/acp/acp-i2s.c @@ -181,6 +181,7 @@ static int acp_i2s_set_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask, u32 rx_mas break; default: dev_err(dev, "Unknown chip revision %d\n", chip->acp_rev); + spin_unlock_irq(&adata->acp_lock); return -EINVAL; } } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index ecf57a6cb7c3..b16587d8f97a 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -307,6 +307,34 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83L3"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83N6"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83Q2"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "83Q3"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_PRODUCT_NAME, "UM5302TA"), } diff --git a/sound/soc/codecs/arizona.c b/sound/soc/codecs/arizona.c index 402b9a2ff024..68cdb1027d0c 100644 --- a/sound/soc/codecs/arizona.c +++ b/sound/soc/codecs/arizona.c @@ -967,7 +967,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, case ARIZONA_OUT3L_ENA_SHIFT: case ARIZONA_OUT3R_ENA_SHIFT: priv->out_up_pending++; - priv->out_up_delay += 17; + priv->out_up_delay += 17000; break; case ARIZONA_OUT4L_ENA_SHIFT: case ARIZONA_OUT4R_ENA_SHIFT: @@ -977,7 +977,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, case WM8997: break; default: - priv->out_up_delay += 10; + priv->out_up_delay += 10000; break; } break; @@ -999,7 +999,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, if (!priv->out_up_pending && priv->out_up_delay) { dev_dbg(component->dev, "Power up delay: %d\n", priv->out_up_delay); - msleep(priv->out_up_delay); + fsleep(priv->out_up_delay); priv->out_up_delay = 0; } break; @@ -1017,7 +1017,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, case ARIZONA_OUT3L_ENA_SHIFT: case ARIZONA_OUT3R_ENA_SHIFT: priv->out_down_pending++; - priv->out_down_delay++; + priv->out_down_delay += 1000; break; case ARIZONA_OUT4L_ENA_SHIFT: case ARIZONA_OUT4R_ENA_SHIFT: @@ -1028,10 +1028,10 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, break; case WM8998: case WM1814: - priv->out_down_delay += 5; + priv->out_down_delay += 5000; break; default: - priv->out_down_delay++; + priv->out_down_delay += 1000; break; } break; @@ -1053,7 +1053,7 @@ int arizona_out_ev(struct snd_soc_dapm_widget *w, if (!priv->out_down_pending && priv->out_down_delay) { dev_dbg(component->dev, "Power down delay: %d\n", priv->out_down_delay); - msleep(priv->out_down_delay); + fsleep(priv->out_down_delay); priv->out_down_delay = 0; } break; diff --git a/sound/soc/codecs/cs35l41.c b/sound/soc/codecs/cs35l41.c index 07a5cab35fe1..ff4134bee858 100644 --- a/sound/soc/codecs/cs35l41.c +++ b/sound/soc/codecs/cs35l41.c @@ -1148,21 +1148,31 @@ err_dsp: return ret; } +#ifdef CONFIG_ACPI static int cs35l41_acpi_get_name(struct cs35l41_private *cs35l41) { - acpi_handle handle = ACPI_HANDLE(cs35l41->dev); + struct acpi_device *adev = ACPI_COMPANION(cs35l41->dev); + acpi_handle handle = acpi_device_handle(adev); + const char *hid; const char *sub; - /* If there is no ACPI_HANDLE, there is no ACPI for this system, return 0 */ - if (!handle) + /* If there is no acpi_device, there is no ACPI for this system, return 0 */ + if (!adev) return 0; sub = acpi_get_subsystem_id(handle); if (IS_ERR(sub)) { - /* If bad ACPI, return 0 and fallback to legacy firmware path, otherwise fail */ - if (PTR_ERR(sub) == -ENODATA) - return 0; - else + /* If no _SUB, fallback to _HID, otherwise fail */ + if (PTR_ERR(sub) == -ENODATA) { + hid = acpi_device_hid(adev); + /* If dummy hid, return 0 and fallback to legacy firmware path */ + if (!strcmp(hid, "device")) + return 0; + sub = kstrdup(hid, GFP_KERNEL); + if (!sub) + sub = ERR_PTR(-ENOMEM); + + } else return PTR_ERR(sub); } @@ -1171,6 +1181,12 @@ static int cs35l41_acpi_get_name(struct cs35l41_private *cs35l41) return 0; } +#else +static int cs35l41_acpi_get_name(struct cs35l41_private *cs35l41) +{ + return 0; +} +#endif /* CONFIG_ACPI */ int cs35l41_probe(struct cs35l41_private *cs35l41, const struct cs35l41_hw_cfg *hw_cfg) { diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index ca4cc954efa8..eb97ac73ec06 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -2203,6 +2203,8 @@ static int da7213_i2c_probe(struct i2c_client *i2c) return ret; } + mutex_init(&da7213->ctrl_lock); + pm_runtime_set_autosuspend_delay(&i2c->dev, 100); pm_runtime_use_autosuspend(&i2c->dev); pm_runtime_set_active(&i2c->dev); diff --git a/sound/soc/codecs/es8316.c b/sound/soc/codecs/es8316.c index f508df01145b..e7bd561a8f40 100644 --- a/sound/soc/codecs/es8316.c +++ b/sound/soc/codecs/es8316.c @@ -101,7 +101,7 @@ static const struct snd_kcontrol_new es8316_snd_controls[] = { SOC_DOUBLE_R_TLV("DAC Playback Volume", ES8316_DAC_VOLL, ES8316_DAC_VOLR, 0, 0xc0, 1, dac_vol_tlv), SOC_SINGLE("DAC Soft Ramp Switch", ES8316_DAC_SET1, 4, 1, 1), - SOC_SINGLE("DAC Soft Ramp Rate", ES8316_DAC_SET1, 2, 4, 0), + SOC_SINGLE("DAC Soft Ramp Rate", ES8316_DAC_SET1, 2, 3, 0), SOC_SINGLE("DAC Notch Filter Switch", ES8316_DAC_SET2, 6, 1, 0), SOC_SINGLE("DAC Double Fs Switch", ES8316_DAC_SET2, 7, 1, 0), SOC_SINGLE("DAC Stereo Enhancement", ES8316_DAC_SET3, 0, 7, 0), diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c index b06eead7e0f6..066d92b54312 100644 --- a/sound/soc/codecs/es8326.c +++ b/sound/soc/codecs/es8326.c @@ -911,7 +911,7 @@ static void es8326_jack_detect_handler(struct work_struct *work) regmap_write(es8326->regmap, ES8326_INT_SOURCE, (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON)); regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x1f); - regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x08); + regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x0d); queue_delayed_work(system_wq, &es8326->jack_detect_work, msecs_to_jiffies(400)); es8326->hp = 1; @@ -1023,7 +1023,7 @@ static void es8326_init(struct snd_soc_component *component) struct es8326_priv *es8326 = snd_soc_component_get_drvdata(component); regmap_write(es8326->regmap, ES8326_RESET, 0x1f); - regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E); + regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x3E); regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0); usleep_range(10000, 15000); regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xd9); diff --git a/sound/soc/codecs/madera.c b/sound/soc/codecs/madera.c index a840a2eb92b9..af109761f359 100644 --- a/sound/soc/codecs/madera.c +++ b/sound/soc/codecs/madera.c @@ -2323,10 +2323,10 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case CS42L92: case CS47L92: case CS47L93: - out_up_delay = 6; + out_up_delay = 6000; break; default: - out_up_delay = 17; + out_up_delay = 17000; break; } @@ -2357,7 +2357,7 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case MADERA_OUT3R_ENA_SHIFT: priv->out_up_pending--; if (!priv->out_up_pending) { - msleep(priv->out_up_delay); + fsleep(priv->out_up_delay); priv->out_up_delay = 0; } break; @@ -2376,7 +2376,7 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case MADERA_OUT3L_ENA_SHIFT: case MADERA_OUT3R_ENA_SHIFT: priv->out_down_pending++; - priv->out_down_delay++; + priv->out_down_delay += 1000; break; default: break; @@ -2393,7 +2393,7 @@ int madera_out_ev(struct snd_soc_dapm_widget *w, case MADERA_OUT3R_ENA_SHIFT: priv->out_down_pending--; if (!priv->out_down_pending) { - msleep(priv->out_down_delay); + fsleep(priv->out_down_delay); priv->out_down_delay = 0; } break; diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c index 2b3c0f9e178c..9cb74962161a 100644 --- a/sound/soc/codecs/rt5514.c +++ b/sound/soc/codecs/rt5514.c @@ -1091,8 +1091,7 @@ static int rt5514_set_bias_level(struct snd_soc_component *component, static int rt5514_probe(struct snd_soc_component *component) { struct rt5514_priv *rt5514 = snd_soc_component_get_drvdata(component); - struct platform_device *pdev = container_of(component->dev, - struct platform_device, dev); + struct platform_device *pdev = to_platform_device(component->dev); rt5514->mclk = devm_clk_get_optional(component->dev, "mclk"); if (IS_ERR(rt5514->mclk)) diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c index a730ab6ad4e3..90c5b2e74d12 100644 --- a/sound/soc/codecs/tas2781-i2c.c +++ b/sound/soc/codecs/tas2781-i2c.c @@ -2,7 +2,7 @@ // // ALSA SoC Texas Instruments TAS2563/TAS2781 Audio Smart Amplifier // -// Copyright (C) 2022 - 2024 Texas Instruments Incorporated +// Copyright (C) 2022 - 2025 Texas Instruments Incorporated // https://www.ti.com // // The TAS2563/TAS2781 driver implements a flexible and configurable @@ -1260,8 +1260,6 @@ static int tasdevice_create_cali_ctrls(struct tasdevice_priv *priv) (cali_data->cali_dat_sz_per_dev + 1) + 1 + 15 + 1; priv->cali_data.total_sz = priv->ndev * (cali_data->cali_dat_sz_per_dev + 1); - priv->cali_data.data = devm_kzalloc(priv->dev, - ext_cali_data->max, GFP_KERNEL); cali_ctrls[i].name = cali_name; cali_ctrls[i].iface = SNDRV_CTL_ELEM_IFACE_MIXER; cali_ctrls[i].info = snd_soc_bytes_info_ext; diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c index 502196253d42..64eee0d2347d 100644 --- a/sound/soc/codecs/wm5110.c +++ b/sound/soc/codecs/wm5110.c @@ -302,7 +302,7 @@ static int wm5110_hp_pre_enable(struct snd_soc_dapm_widget *w) } else { wseq = wm5110_no_dre_left_enable; nregs = ARRAY_SIZE(wm5110_no_dre_left_enable); - priv->out_up_delay += 10; + priv->out_up_delay += 10000; } break; case ARIZONA_OUT1R_ENA_SHIFT: @@ -312,7 +312,7 @@ static int wm5110_hp_pre_enable(struct snd_soc_dapm_widget *w) } else { wseq = wm5110_no_dre_right_enable; nregs = ARRAY_SIZE(wm5110_no_dre_right_enable); - priv->out_up_delay += 10; + priv->out_up_delay += 10000; } break; default: @@ -338,7 +338,7 @@ static int wm5110_hp_pre_disable(struct snd_soc_dapm_widget *w) snd_soc_component_update_bits(component, ARIZONA_SPARE_TRIGGERS, ARIZONA_WS_TRG1, 0); - priv->out_down_delay += 27; + priv->out_down_delay += 27000; } break; case ARIZONA_OUT1R_ENA_SHIFT: @@ -350,7 +350,7 @@ static int wm5110_hp_pre_disable(struct snd_soc_dapm_widget *w) snd_soc_component_update_bits(component, ARIZONA_SPARE_TRIGGERS, ARIZONA_WS_TRG2, 0); - priv->out_down_delay += 27; + priv->out_down_delay += 27000; } break; default: diff --git a/sound/soc/fsl/Kconfig b/sound/soc/fsl/Kconfig index e5fbf5305ea2..c4cf3cff58de 100644 --- a/sound/soc/fsl/Kconfig +++ b/sound/soc/fsl/Kconfig @@ -6,6 +6,7 @@ comment "Common SoC Audio options for Freescale CPUs:" config SND_SOC_FSL_ASRC tristate "Asynchronous Sample Rate Converter (ASRC) module support" depends on HAS_DMA + select DMA_SHARED_BUFFER select REGMAP_MMIO select SND_SOC_GENERIC_DMAENGINE_PCM select SND_COMPRESS_ACCEL diff --git a/sound/soc/fsl/fsl_asrc_m2m.c b/sound/soc/fsl/fsl_asrc_m2m.c index 4906843e2a8f..f46881f71e43 100644 --- a/sound/soc/fsl/fsl_asrc_m2m.c +++ b/sound/soc/fsl/fsl_asrc_m2m.c @@ -183,7 +183,7 @@ static int asrc_dmaconfig(struct fsl_asrc_pair *pair, } /* main function of converter */ -static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_task_runtime *task) +static int asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_task_runtime *task) { struct fsl_asrc *asrc = pair->asrc; struct device *dev = &asrc->pdev->dev; @@ -193,7 +193,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas unsigned int out_dma_len; unsigned int width; u32 fifo_addr; - int ret; + int ret = 0; /* set ratio mod */ if (asrc->m2m_set_ratio_mod) { @@ -215,6 +215,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas in_buf_len > ASRC_M2M_BUFFER_SIZE || in_buf_len % (width * pair->channels / 8)) { dev_err(dev, "out buffer size is error: [%d]\n", in_buf_len); + ret = -EINVAL; goto end; } @@ -245,6 +246,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas } } else if (out_dma_len > ASRC_M2M_BUFFER_SIZE) { dev_err(dev, "cap buffer size error\n"); + ret = -EINVAL; goto end; } @@ -263,12 +265,14 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas if (!wait_for_completion_interruptible_timeout(&pair->complete[IN], 10 * HZ)) { dev_err(dev, "out DMA task timeout\n"); + ret = -ETIMEDOUT; goto end; } if (out_dma_len > 0) { if (!wait_for_completion_interruptible_timeout(&pair->complete[OUT], 10 * HZ)) { dev_err(dev, "cap DMA task timeout\n"); + ret = -ETIMEDOUT; goto end; } } @@ -278,7 +282,7 @@ static void asrc_m2m_device_run(struct fsl_asrc_pair *pair, struct snd_compr_tas /* update payload length for capture */ task->output_size = out_dma_len; end: - return; + return ret; } static int fsl_asrc_m2m_comp_open(struct snd_compr_stream *stream) @@ -525,9 +529,7 @@ static int fsl_asrc_m2m_comp_task_start(struct snd_compr_stream *stream, struct snd_compr_runtime *runtime = stream->runtime; struct fsl_asrc_pair *pair = runtime->private_data; - asrc_m2m_device_run(pair, task); - - return 0; + return asrc_m2m_device_run(pair, task); } static int fsl_asrc_m2m_comp_task_stop(struct snd_compr_stream *stream, @@ -633,7 +635,7 @@ int fsl_asrc_m2m_suspend(struct fsl_asrc *asrc) for (i = 0; i < PAIR_CTX_NUM; i++) { pair = asrc->pair[i]; - if (!pair) + if (!pair || !pair->dma_buffer[IN].area || !pair->dma_buffer[OUT].area) continue; if (!completion_done(&pair->complete[IN])) { if (pair->dma_chan[IN]) diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 1075598a6647..fa4136683392 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -183,6 +183,8 @@ static int micfil_set_quality(struct fsl_micfil *micfil) case QUALITY_VLOW2: qsel = MICFIL_QSEL_VLOW2_QUALITY; break; + default: + return -EINVAL; } return regmap_update_bits(micfil->regmap, REG_MICFIL_CTRL2, diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c index 231400661c90..50ecc5f51100 100644 --- a/sound/soc/fsl/imx-audmix.c +++ b/sound/soc/fsl/imx-audmix.c @@ -23,7 +23,6 @@ struct imx_audmix { struct snd_soc_card card; struct platform_device *audmix_pdev; struct platform_device *out_pdev; - struct clk *cpu_mclk; int num_dai; struct snd_soc_dai_link *dai; int num_dai_conf; @@ -32,34 +31,11 @@ struct imx_audmix { struct snd_soc_dapm_route *dapm_routes; }; -static const u32 imx_audmix_rates[] = { - 8000, 12000, 16000, 24000, 32000, 48000, 64000, 96000, -}; - -static const struct snd_pcm_hw_constraint_list imx_audmix_rate_constraints = { - .count = ARRAY_SIZE(imx_audmix_rates), - .list = imx_audmix_rates, -}; - static int imx_audmix_fe_startup(struct snd_pcm_substream *substream) { - struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream); - struct imx_audmix *priv = snd_soc_card_get_drvdata(rtd->card); struct snd_pcm_runtime *runtime = substream->runtime; - struct device *dev = rtd->card->dev; - unsigned long clk_rate = clk_get_rate(priv->cpu_mclk); int ret; - if (clk_rate % 24576000 == 0) { - ret = snd_pcm_hw_constraint_list(runtime, 0, - SNDRV_PCM_HW_PARAM_RATE, - &imx_audmix_rate_constraints); - if (ret < 0) - return ret; - } else { - dev_warn(dev, "mclk may be not supported %lu\n", clk_rate); - } - ret = snd_pcm_hw_constraint_minmax(runtime, SNDRV_PCM_HW_PARAM_CHANNELS, 1, 8); if (ret < 0) @@ -323,13 +299,6 @@ static int imx_audmix_probe(struct platform_device *pdev) } put_device(&cpu_pdev->dev); - priv->cpu_mclk = devm_clk_get(&cpu_pdev->dev, "mclk1"); - if (IS_ERR(priv->cpu_mclk)) { - ret = PTR_ERR(priv->cpu_mclk); - dev_err(&cpu_pdev->dev, "failed to get DAI mclk1: %d\n", ret); - return ret; - } - priv->audmix_pdev = audmix_pdev; priv->out_pdev = cpu_pdev; diff --git a/sound/soc/generic/audio-graph-card2.c b/sound/soc/generic/audio-graph-card2.c index c36b1a2ac949..ee94b256b770 100644 --- a/sound/soc/generic/audio-graph-card2.c +++ b/sound/soc/generic/audio-graph-card2.c @@ -648,23 +648,23 @@ multi_err: static int graph_parse_node_single(struct simple_util_priv *priv, enum graph_type gtype, - struct device_node *port, + struct device_node *ep, struct link_info *li, int is_cpu) { - struct device_node *ep __free(device_node) = of_graph_get_next_port_endpoint(port, NULL); - return __graph_parse_node(priv, gtype, ep, li, is_cpu, 0); } static int graph_parse_node(struct simple_util_priv *priv, enum graph_type gtype, - struct device_node *port, + struct device_node *ep, struct link_info *li, int is_cpu) { + struct device_node *port __free(device_node) = ep_to_port(ep); + if (graph_lnk_is_multi(port)) return graph_parse_node_multi(priv, gtype, port, li, is_cpu); else - return graph_parse_node_single(priv, gtype, port, li, is_cpu); + return graph_parse_node_single(priv, gtype, ep, li, is_cpu); } static void graph_parse_daifmt(struct device_node *node, unsigned int *daifmt) @@ -722,14 +722,15 @@ static unsigned int graph_parse_bitframe(struct device_node *ep) static void graph_link_init(struct simple_util_priv *priv, struct device_node *lnk, - struct device_node *port_cpu, - struct device_node *port_codec, + struct device_node *ep_cpu, + struct device_node *ep_codec, struct link_info *li, int is_cpu_node) { struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); - struct device_node *ep_cpu, *ep_codec; + struct device_node *port_cpu = ep_to_port(ep_cpu); + struct device_node *port_codec = ep_to_port(ep_codec); struct device_node *multi_cpu_port = NULL, *multi_codec_port = NULL; struct snd_soc_dai_link_component *dlc; unsigned int daifmt = 0; @@ -739,25 +740,23 @@ static void graph_link_init(struct simple_util_priv *priv, int multi_cpu_port_idx = 1, multi_codec_port_idx = 1; int i; - of_node_get(port_cpu); if (graph_lnk_is_multi(port_cpu)) { multi_cpu_port = port_cpu; ep_cpu = graph_get_next_multi_ep(&multi_cpu_port, multi_cpu_port_idx++); of_node_put(port_cpu); port_cpu = ep_to_port(ep_cpu); } else { - ep_cpu = of_graph_get_next_port_endpoint(port_cpu, NULL); + of_node_get(ep_cpu); } struct device_node *ports_cpu __free(device_node) = port_to_ports(port_cpu); - of_node_get(port_codec); if (graph_lnk_is_multi(port_codec)) { multi_codec_port = port_codec; ep_codec = graph_get_next_multi_ep(&multi_codec_port, multi_codec_port_idx++); of_node_put(port_codec); port_codec = ep_to_port(ep_codec); } else { - ep_codec = of_graph_get_next_port_endpoint(port_codec, NULL); + of_node_get(ep_codec); } struct device_node *ports_codec __free(device_node) = port_to_ports(port_codec); @@ -833,7 +832,7 @@ int audio_graph2_link_normal(struct simple_util_priv *priv, { struct device_node *cpu_port = lnk; struct device_node *cpu_ep __free(device_node) = of_graph_get_next_port_endpoint(cpu_port, NULL); - struct device_node *codec_port __free(device_node) = of_graph_get_remote_port(cpu_ep); + struct device_node *codec_ep __free(device_node) = of_graph_get_remote_endpoint(cpu_ep); int ret; /* @@ -841,18 +840,18 @@ int audio_graph2_link_normal(struct simple_util_priv *priv, * see * __graph_parse_node() :: DAI Naming */ - ret = graph_parse_node(priv, GRAPH_NORMAL, codec_port, li, 0); + ret = graph_parse_node(priv, GRAPH_NORMAL, codec_ep, li, 0); if (ret < 0) return ret; /* * call CPU, and set DAI Name */ - ret = graph_parse_node(priv, GRAPH_NORMAL, cpu_port, li, 1); + ret = graph_parse_node(priv, GRAPH_NORMAL, cpu_ep, li, 1); if (ret < 0) return ret; - graph_link_init(priv, lnk, cpu_port, codec_port, li, 1); + graph_link_init(priv, lnk, cpu_ep, codec_ep, li, 1); return ret; } @@ -864,15 +863,15 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv, { struct device_node *ep __free(device_node) = of_graph_get_next_port_endpoint(lnk, NULL); struct device_node *rep __free(device_node) = of_graph_get_remote_endpoint(ep); - struct device_node *cpu_port = NULL; - struct device_node *codec_port = NULL; + struct device_node *cpu_ep = NULL; + struct device_node *codec_ep = NULL; struct snd_soc_dai_link *dai_link = simple_priv_to_link(priv, li->link); struct simple_dai_props *dai_props = simple_priv_to_props(priv, li->link); int is_cpu = graph_util_is_ports0(lnk); int ret; if (is_cpu) { - cpu_port = of_graph_get_remote_port(ep); /* rport */ + cpu_ep = rep; /* * dpcm { @@ -901,12 +900,12 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv, dai_link->dynamic = 1; dai_link->dpcm_merged_format = 1; - ret = graph_parse_node(priv, GRAPH_DPCM, cpu_port, li, 1); + ret = graph_parse_node(priv, GRAPH_DPCM, cpu_ep, li, 1); if (ret) - goto err; + return ret; } else { - codec_port = of_graph_get_remote_port(ep); /* rport */ + codec_ep = rep; /* * dpcm { @@ -937,18 +936,15 @@ int audio_graph2_link_dpcm(struct simple_util_priv *priv, dai_link->no_pcm = 1; dai_link->be_hw_params_fixup = simple_util_be_hw_params_fixup; - ret = graph_parse_node(priv, GRAPH_DPCM, codec_port, li, 0); + ret = graph_parse_node(priv, GRAPH_DPCM, codec_ep, li, 0); if (ret < 0) - goto err; + return ret; } graph_parse_convert(ep, dai_props); /* at node of <dpcm> */ graph_parse_convert(rep, dai_props); /* at node of <CPU/Codec> */ - graph_link_init(priv, lnk, cpu_port, codec_port, li, is_cpu); -err: - of_node_put(cpu_port); - of_node_put(codec_port); + graph_link_init(priv, lnk, cpu_ep, codec_ep, li, is_cpu); return ret; } @@ -1013,26 +1009,26 @@ int audio_graph2_link_c2c(struct simple_util_priv *priv, struct device_node *ep0 __free(device_node) = of_graph_get_next_port_endpoint(port0, NULL); struct device_node *ep1 __free(device_node) = of_graph_get_next_port_endpoint(port1, NULL); - struct device_node *codec0_port __free(device_node) = of_graph_get_remote_port(ep0); - struct device_node *codec1_port __free(device_node) = of_graph_get_remote_port(ep1); + struct device_node *codec0_ep __free(device_node) = of_graph_get_remote_endpoint(ep0); + struct device_node *codec1_ep __free(device_node) = of_graph_get_remote_endpoint(ep1); /* * call Codec first. * see * __graph_parse_node() :: DAI Naming */ - ret = graph_parse_node(priv, GRAPH_C2C, codec1_port, li, 0); + ret = graph_parse_node(priv, GRAPH_C2C, codec1_ep, li, 0); if (ret < 0) return ret; /* * call CPU, and set DAI Name */ - ret = graph_parse_node(priv, GRAPH_C2C, codec0_port, li, 1); + ret = graph_parse_node(priv, GRAPH_C2C, codec0_ep, li, 1); if (ret < 0) return ret; - graph_link_init(priv, lnk, codec0_port, codec1_port, li, 1); + graph_link_init(priv, lnk, codec0_ep, codec1_ep, li, 1); return ret; } diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index dd414634b4ac..c2445c5ccd84 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -1092,6 +1092,7 @@ int graph_util_parse_dai(struct device *dev, struct device_node *ep, args.np = ep; dai = snd_soc_get_dai_via_args(&args); if (dai) { + dlc->of_node = node; dlc->dai_name = snd_soc_dai_name_get(dai); dlc->dai_args = snd_soc_copy_dai_args(dev, &args); if (!dlc->dai_args) diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 9caa4407c1ca..6446cda0f857 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -1132,7 +1132,22 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = { BYT_RT5640_SSP0_AIF2 | BYT_RT5640_MCLK_EN), }, - { /* Vexia Edu Atla 10 tablet */ + { + /* Vexia Edu Atla 10 tablet 5V version */ + .matches = { + /* Having all 3 of these not set is somewhat unique */ + DMI_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."), + DMI_MATCH(DMI_PRODUCT_NAME, "To be filled by O.E.M."), + DMI_MATCH(DMI_BOARD_NAME, "To be filled by O.E.M."), + /* Above strings are too generic, also match on BIOS date */ + DMI_MATCH(DMI_BIOS_DATE, "05/14/2015"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | + BYT_RT5640_JD_NOT_INV | + BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, + { /* Vexia Edu Atla 10 tablet 9V version */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"), DMI_MATCH(DMI_BOARD_NAME, "Aptio CRB"), diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c index b0d35fda7b17..203b07d4d833 100644 --- a/sound/soc/intel/boards/sof_sdw.c +++ b/sound/soc/intel/boards/sof_sdw.c @@ -13,6 +13,7 @@ #include <linux/soundwire/sdw.h> #include <linux/soundwire/sdw_type.h> #include <linux/soundwire/sdw_intel.h> +#include <sound/core.h> #include <sound/soc-acpi.h> #include "sof_sdw_common.h" #include "../../codecs/rt711.h" @@ -748,9 +749,36 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = { }, .driver_data = (void *)(SOC_SDW_PCH_DMIC), }, + { + .callback = sof_sdw_quirk_cb, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Google"), + DMI_MATCH(DMI_PRODUCT_NAME, "Fatcat"), + }, + .driver_data = (void *)(SOC_SDW_PCH_DMIC | + SOF_BT_OFFLOAD_SSP(2) | + SOF_SSP_BT_OFFLOAD_PRESENT), + }, + {} +}; + +static const struct snd_pci_quirk sof_sdw_ssid_quirk_table[] = { + SND_PCI_QUIRK(0x1043, 0x1e13, "ASUS Zenbook S14", SOC_SDW_CODEC_MIC), {} }; +static void sof_sdw_check_ssid_quirk(const struct snd_soc_acpi_mach *mach) +{ + const struct snd_pci_quirk *quirk_entry; + + quirk_entry = snd_pci_quirk_lookup_id(mach->mach_params.subsystem_vendor, + mach->mach_params.subsystem_device, + sof_sdw_ssid_quirk_table); + + if (quirk_entry) + sof_sdw_quirk = quirk_entry->value; +} + static struct snd_soc_dai_link_component platform_component[] = { { /* name might be overridden during probe */ @@ -1278,6 +1306,13 @@ static int mc_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(card, ctx); + if (mach->mach_params.subsystem_id_set) { + snd_soc_card_set_pci_ssid(card, + mach->mach_params.subsystem_vendor, + mach->mach_params.subsystem_device); + sof_sdw_check_ssid_quirk(mach); + } + dmi_check_system(sof_sdw_quirk_table); if (quirk_override != -1) { @@ -1293,12 +1328,6 @@ static int mc_probe(struct platform_device *pdev) for (i = 0; i < ctx->codec_info_list_count; i++) codec_info_list[i].amp_num = 0; - if (mach->mach_params.subsystem_id_set) { - snd_soc_card_set_pci_ssid(card, - mach->mach_params.subsystem_vendor, - mach->mach_params.subsystem_device); - } - ret = sof_card_dai_links_create(card); if (ret < 0) return ret; diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c index 770e2194a283..9e611e3667ad 100644 --- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c @@ -330,7 +330,7 @@ static const struct snd_soc_acpi_adr_device rt1316_3_single_adr[] = { static const struct snd_soc_acpi_adr_device rt1318_1_single_adr[] = { { - .adr = 0x000130025D131801, + .adr = 0x000130025D131801ull, .num_endpoints = 1, .endpoints = &single_endpoint, .name_prefix = "rt1318-1" diff --git a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c index 9eb4a43e3e7a..dd7993b76dee 100644 --- a/sound/soc/intel/common/soc-acpi-intel-ptl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-ptl-match.c @@ -251,7 +251,7 @@ static const struct snd_soc_acpi_link_adr ptl_rvp[] = { {} }; -static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_vb_l2_rt1320_l13[] = { +static const struct snd_soc_acpi_link_adr ptl_sdw_rt713_vb_l2_rt1320_l13[] = { { .mask = BIT(2), .num_adr = ARRAY_SIZE(rt713_vb_2_adr), @@ -270,7 +270,7 @@ static const struct snd_soc_acpi_link_adr lnl_sdw_rt713_vb_l2_rt1320_l13[] = { {} }; -static const struct snd_soc_acpi_link_adr lnl_sdw_rt712_vb_l2_rt1320_l1[] = { +static const struct snd_soc_acpi_link_adr ptl_sdw_rt712_vb_l2_rt1320_l1[] = { { .mask = BIT(2), .num_adr = ARRAY_SIZE(rt712_vb_2_group1_adr), @@ -337,17 +337,17 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_ptl_sdw_machines[] = { }, { .link_mask = BIT(1) | BIT(2), - .links = lnl_sdw_rt712_vb_l2_rt1320_l1, + .links = ptl_sdw_rt712_vb_l2_rt1320_l1, .drv_name = "sof_sdw", .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, - .sof_tplg_filename = "sof-lnl-rt712-l2-rt1320-l1.tplg" + .sof_tplg_filename = "sof-ptl-rt712-l2-rt1320-l1.tplg" }, { .link_mask = BIT(1) | BIT(2) | BIT(3), - .links = lnl_sdw_rt713_vb_l2_rt1320_l13, + .links = ptl_sdw_rt713_vb_l2_rt1320_l13, .drv_name = "sof_sdw", .machine_check = snd_soc_acpi_intel_sdca_is_device_rt712_vb, - .sof_tplg_filename = "sof-lnl-rt713-l2-rt1320-l13.tplg" + .sof_tplg_filename = "sof-ptl-rt713-l2-rt1320-l13.tplg" }, {}, }; diff --git a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c index 6f8c06413665..b77aafb0bfb6 100644 --- a/sound/soc/intel/common/soc-acpi-intel-tgl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-tgl-match.c @@ -658,25 +658,25 @@ static const struct snd_soc_acpi_endpoint cs35l56_7_fb_endpoints[] = { static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_1_4_fb_adr[] = { { - .adr = 0x00003301fa355601, + .adr = 0x00003301fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_l_fb_endpoints), .endpoints = cs35l56_l_fb_endpoints, .name_prefix = "AMP1" }, { - .adr = 0x00003201fa355601, + .adr = 0x00003201fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_2_fb_endpoints), .endpoints = cs35l56_2_fb_endpoints, .name_prefix = "AMP2" }, { - .adr = 0x00003101fa355601, + .adr = 0x00003101fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_4_fb_endpoints), .endpoints = cs35l56_4_fb_endpoints, .name_prefix = "AMP3" }, { - .adr = 0x00003001fa355601, + .adr = 0x00003001fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_6_fb_endpoints), .endpoints = cs35l56_6_fb_endpoints, .name_prefix = "AMP4" @@ -685,25 +685,25 @@ static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_1_4_fb_adr[] = { static const struct snd_soc_acpi_adr_device cs35l56_sdw_eight_5_8_fb_adr[] = { { - .adr = 0x00013701fa355601, + .adr = 0x00013701fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_r_fb_endpoints), .endpoints = cs35l56_r_fb_endpoints, .name_prefix = "AMP8" }, { - .adr = 0x00013601fa355601, + .adr = 0x00013601fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_3_fb_endpoints), .endpoints = cs35l56_3_fb_endpoints, .name_prefix = "AMP7" }, { - .adr = 0x00013501fa355601, + .adr = 0x00013501fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_5_fb_endpoints), .endpoints = cs35l56_5_fb_endpoints, .name_prefix = "AMP6" }, { - .adr = 0x00013401fa355601, + .adr = 0x00013401fa355601ull, .num_endpoints = ARRAY_SIZE(cs35l56_7_fb_endpoints), .endpoints = cs35l56_7_fb_endpoints, .name_prefix = "AMP5" diff --git a/sound/soc/renesas/Kconfig b/sound/soc/renesas/Kconfig index 426632996a0a..cb01fb36355f 100644 --- a/sound/soc/renesas/Kconfig +++ b/sound/soc/renesas/Kconfig @@ -67,7 +67,7 @@ config SND_SH7760_AC97 config SND_SIU_MIGOR tristate "SIU sound support on Migo-R" - depends on SH_MIGOR && I2C + depends on SH_MIGOR && I2C && DMADEVICES select SND_SOC_SH4_SIU select SND_SOC_WM8978 help diff --git a/sound/soc/renesas/rcar/core.c b/sound/soc/renesas/rcar/core.c index d3709fd0409e..f3f0c3f0bb9f 100644 --- a/sound/soc/renesas/rcar/core.c +++ b/sound/soc/renesas/rcar/core.c @@ -1770,20 +1770,6 @@ int rsnd_kctrl_accept_anytime(struct rsnd_dai_stream *io) return 1; } -int rsnd_kctrl_accept_runtime(struct rsnd_dai_stream *io) -{ - struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); - struct rsnd_priv *priv = rsnd_io_to_priv(io); - struct device *dev = rsnd_priv_to_dev(priv); - - if (!runtime) { - dev_warn(dev, "Can't update kctrl when idle\n"); - return 0; - } - - return 1; -} - struct rsnd_kctrl_cfg *rsnd_kctrl_init_m(struct rsnd_kctrl_cfg_m *cfg) { cfg->cfg.val = cfg->val; diff --git a/sound/soc/renesas/rcar/rsnd.h b/sound/soc/renesas/rcar/rsnd.h index a5f54b65313c..04c70690f7a2 100644 --- a/sound/soc/renesas/rcar/rsnd.h +++ b/sound/soc/renesas/rcar/rsnd.h @@ -742,7 +742,6 @@ struct rsnd_kctrl_cfg_s { #define rsnd_kctrl_vals(x) ((x).val) /* = (x).cfg.val[0] */ int rsnd_kctrl_accept_anytime(struct rsnd_dai_stream *io); -int rsnd_kctrl_accept_runtime(struct rsnd_dai_stream *io); struct rsnd_kctrl_cfg *rsnd_kctrl_init_m(struct rsnd_kctrl_cfg_m *cfg); struct rsnd_kctrl_cfg *rsnd_kctrl_init_s(struct rsnd_kctrl_cfg_s *cfg); int rsnd_kctrl_new(struct rsnd_mod *mod, diff --git a/sound/soc/renesas/rcar/src.c b/sound/soc/renesas/rcar/src.c index e7f86db0d94c..7d73b183bda6 100644 --- a/sound/soc/renesas/rcar/src.c +++ b/sound/soc/renesas/rcar/src.c @@ -35,6 +35,7 @@ struct rsnd_src { struct rsnd_mod *dma; struct rsnd_kctrl_cfg_s sen; /* sync convert enable */ struct rsnd_kctrl_cfg_s sync; /* sync convert */ + u32 current_sync_rate; int irq; }; @@ -100,7 +101,7 @@ static u32 rsnd_src_convert_rate(struct rsnd_dai_stream *io, if (!rsnd_src_sync_is_enabled(mod)) return rsnd_io_converted_rate(io); - convert_rate = src->sync.val; + convert_rate = src->current_sync_rate; if (!convert_rate) convert_rate = rsnd_io_converted_rate(io); @@ -201,13 +202,73 @@ static const u32 chan222222[] = { static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, struct rsnd_mod *mod) { + struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); struct rsnd_priv *priv = rsnd_mod_to_priv(mod); - struct device *dev = rsnd_priv_to_dev(priv); + struct rsnd_src *src = rsnd_mod_to_src(mod); + u32 fin, fout, new_rate; + int inc, cnt, rate; + u64 base, val; + + if (!runtime) + return; + + if (!rsnd_src_sync_is_enabled(mod)) + return; + + fin = rsnd_src_get_in_rate(priv, io); + fout = rsnd_src_get_out_rate(priv, io); + + new_rate = src->sync.val; + + if (!new_rate) + new_rate = fout; + + /* Do nothing if no diff */ + if (new_rate == src->current_sync_rate) + return; + + /* + * SRCm_IFSVR::INTIFS can change within 1% + * see + * SRCm_IFSVR::INTIFS Note + */ + inc = fout / 100; + cnt = abs(new_rate - fout) / inc; + if (fout > new_rate) + inc *= -1; + + /* + * After start running SRC, we can update only SRC_IFSVR + * for Synchronous Mode + */ + base = (u64)0x0400000 * fin; + rate = fout; + for (int i = 0; i < cnt; i++) { + val = base; + rate += inc; + do_div(val, rate); + + rsnd_mod_write(mod, SRC_IFSVR, val); + } + val = base; + do_div(val, new_rate); + + rsnd_mod_write(mod, SRC_IFSVR, val); + + /* update current_sync_rate */ + src->current_sync_rate = new_rate; +} + +static void rsnd_src_init_convert_rate(struct rsnd_dai_stream *io, + struct rsnd_mod *mod) +{ struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); + struct rsnd_priv *priv = rsnd_mod_to_priv(mod); + struct device *dev = rsnd_priv_to_dev(priv); int is_play = rsnd_io_is_play(io); int use_src = 0; u32 fin, fout; - u32 ifscr, fsrate, adinr; + u32 ifscr, adinr; u32 cr, route; u32 i_busif, o_busif, tmp; const u32 *bsdsr_table; @@ -245,26 +306,15 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, adinr = rsnd_get_adinr_bit(mod, io) | chan; /* - * SRC_IFSCR / SRC_IFSVR - */ - ifscr = 0; - fsrate = 0; - if (use_src) { - u64 n; - - ifscr = 1; - n = (u64)0x0400000 * fin; - do_div(n, fout); - fsrate = n; - } - - /* + * SRC_IFSCR * SRC_SRCCR / SRC_ROUTE_MODE0 */ + ifscr = 0; cr = 0x00011110; route = 0x0; if (use_src) { route = 0x1; + ifscr = 0x1; if (rsnd_src_sync_is_enabled(mod)) { cr |= 0x1; @@ -335,7 +385,6 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, rsnd_mod_write(mod, SRC_SRCIR, 1); /* initialize */ rsnd_mod_write(mod, SRC_ADINR, adinr); rsnd_mod_write(mod, SRC_IFSCR, ifscr); - rsnd_mod_write(mod, SRC_IFSVR, fsrate); rsnd_mod_write(mod, SRC_SRCCR, cr); rsnd_mod_write(mod, SRC_BSDSR, bsdsr_table[idx]); rsnd_mod_write(mod, SRC_BSISR, bsisr_table[idx]); @@ -348,6 +397,9 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, rsnd_adg_set_src_timesel_gen2(mod, io, fin, fout); + /* update SRC_IFSVR */ + rsnd_src_set_convert_rate(io, mod); + return; convert_rate_err: @@ -467,7 +519,8 @@ static int rsnd_src_init(struct rsnd_mod *mod, int ret; /* reset sync convert_rate */ - src->sync.val = 0; + src->sync.val = + src->current_sync_rate = 0; ret = rsnd_mod_power_on(mod); if (ret < 0) @@ -475,7 +528,7 @@ static int rsnd_src_init(struct rsnd_mod *mod, rsnd_src_activation(mod); - rsnd_src_set_convert_rate(io, mod); + rsnd_src_init_convert_rate(io, mod); rsnd_src_status_clear(mod); @@ -493,7 +546,8 @@ static int rsnd_src_quit(struct rsnd_mod *mod, rsnd_mod_power_off(mod); /* reset sync convert_rate */ - src->sync.val = 0; + src->sync.val = + src->current_sync_rate = 0; return 0; } @@ -531,6 +585,22 @@ static irqreturn_t rsnd_src_interrupt(int irq, void *data) return IRQ_HANDLED; } +static int rsnd_src_kctrl_accept_runtime(struct rsnd_dai_stream *io) +{ + struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io); + + if (!runtime) { + struct rsnd_priv *priv = rsnd_io_to_priv(io); + struct device *dev = rsnd_priv_to_dev(priv); + + dev_warn(dev, "\"SRC Out Rate\" can use during running\n"); + + return 0; + } + + return 1; +} + static int rsnd_src_probe_(struct rsnd_mod *mod, struct rsnd_dai_stream *io, struct rsnd_priv *priv) @@ -585,7 +655,7 @@ static int rsnd_src_pcm_new(struct rsnd_mod *mod, "SRC Out Rate Switch" : "SRC In Rate Switch", rsnd_kctrl_accept_anytime, - rsnd_src_set_convert_rate, + rsnd_src_init_convert_rate, &src->sen, 1); if (ret < 0) return ret; @@ -594,7 +664,7 @@ static int rsnd_src_pcm_new(struct rsnd_mod *mod, rsnd_io_is_play(io) ? "SRC Out Rate" : "SRC In Rate", - rsnd_kctrl_accept_runtime, + rsnd_src_kctrl_accept_runtime, rsnd_src_set_convert_rate, &src->sync, 192000); diff --git a/sound/soc/renesas/rcar/ssi.c b/sound/soc/renesas/rcar/ssi.c index b3d4e8ae07ef..0c6424a1fcac 100644 --- a/sound/soc/renesas/rcar/ssi.c +++ b/sound/soc/renesas/rcar/ssi.c @@ -336,7 +336,8 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, return 0; rate_err: - dev_err(dev, "unsupported clock rate\n"); + dev_err(dev, "unsupported clock rate (%d)\n", rate); + return ret; } diff --git a/sound/soc/rockchip/rockchip_i2s_tdm.c b/sound/soc/rockchip/rockchip_i2s_tdm.c index bd0dc586e24a..78ab88843f86 100644 --- a/sound/soc/rockchip/rockchip_i2s_tdm.c +++ b/sound/soc/rockchip/rockchip_i2s_tdm.c @@ -22,7 +22,6 @@ #define DRV_NAME "rockchip-i2s-tdm" -#define DEFAULT_MCLK_FS 256 #define CH_GRP_MAX 4 /* The max channel 8 / 2 */ #define MULTIPLEX_CH_MAX 10 @@ -70,6 +69,8 @@ struct rk_i2s_tdm_dev { bool has_playback; bool has_capture; struct snd_soc_dai_driver *dai; + unsigned int mclk_rx_freq; + unsigned int mclk_tx_freq; }; static int to_ch_num(unsigned int val) @@ -450,11 +451,11 @@ static int rockchip_i2s_tdm_set_fmt(struct snd_soc_dai *cpu_dai, break; case SND_SOC_DAIFMT_DSP_A: val = I2S_TXCR_TFS_TDM_PCM; - tdm_val = TDM_SHIFT_CTRL(0); + tdm_val = TDM_SHIFT_CTRL(2); break; case SND_SOC_DAIFMT_DSP_B: val = I2S_TXCR_TFS_TDM_PCM; - tdm_val = TDM_SHIFT_CTRL(2); + tdm_val = TDM_SHIFT_CTRL(4); break; default: ret = -EINVAL; @@ -617,6 +618,27 @@ static int rockchip_i2s_trcm_mode(struct snd_pcm_substream *substream, return 0; } +static int rockchip_i2s_tdm_set_sysclk(struct snd_soc_dai *cpu_dai, int stream, + unsigned int freq, int dir) +{ + struct rk_i2s_tdm_dev *i2s_tdm = to_info(cpu_dai); + + if (i2s_tdm->clk_trcm) { + i2s_tdm->mclk_tx_freq = freq; + i2s_tdm->mclk_rx_freq = freq; + } else { + if (stream == SNDRV_PCM_STREAM_PLAYBACK) + i2s_tdm->mclk_tx_freq = freq; + else + i2s_tdm->mclk_rx_freq = freq; + } + + dev_dbg(i2s_tdm->dev, "The target mclk_%s freq is: %d\n", + stream ? "rx" : "tx", freq); + + return 0; +} + static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) @@ -631,15 +653,19 @@ static int rockchip_i2s_tdm_hw_params(struct snd_pcm_substream *substream, if (i2s_tdm->clk_trcm == TRCM_TX) { mclk = i2s_tdm->mclk_tx; + mclk_rate = i2s_tdm->mclk_tx_freq; } else if (i2s_tdm->clk_trcm == TRCM_RX) { mclk = i2s_tdm->mclk_rx; + mclk_rate = i2s_tdm->mclk_rx_freq; } else if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { mclk = i2s_tdm->mclk_tx; + mclk_rate = i2s_tdm->mclk_tx_freq; } else { mclk = i2s_tdm->mclk_rx; + mclk_rate = i2s_tdm->mclk_rx_freq; } - err = clk_set_rate(mclk, DEFAULT_MCLK_FS * params_rate(params)); + err = clk_set_rate(mclk, mclk_rate); if (err) return err; @@ -799,6 +825,7 @@ static const struct snd_soc_dai_ops rockchip_i2s_tdm_dai_ops = { .hw_params = rockchip_i2s_tdm_hw_params, .set_bclk_ratio = rockchip_i2s_tdm_set_bclk_ratio, .set_fmt = rockchip_i2s_tdm_set_fmt, + .set_sysclk = rockchip_i2s_tdm_set_sysclk, .set_tdm_slot = rockchip_dai_tdm_slot, .trigger = rockchip_i2s_tdm_trigger, }; diff --git a/sound/soc/sof/amd/acp-ipc.c b/sound/soc/sof/amd/acp-ipc.c index 5f371d9263f3..22d4b807e1bb 100644 --- a/sound/soc/sof/amd/acp-ipc.c +++ b/sound/soc/sof/amd/acp-ipc.c @@ -165,8 +165,9 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context) int dsp_msg, dsp_ack; unsigned int status; - if (sdev->first_boot && sdev->fw_state != SOF_FW_BOOT_COMPLETE) { + if (unlikely(sdev->first_boot && sdev->fw_state != SOF_FW_BOOT_COMPLETE)) { acp_mailbox_read(sdev, sdev->dsp_box.offset, &status, sizeof(status)); + if ((status & SOF_IPC_PANIC_MAGIC_MASK) == SOF_IPC_PANIC_MAGIC) { snd_sof_dsp_panic(sdev, sdev->dsp_box.offset + sizeof(status), true); @@ -188,13 +189,21 @@ irqreturn_t acp_sof_ipc_irq_thread(int irq, void *context) dsp_ack = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_SCRATCH_REG_0 + dsp_ack_write); if (dsp_ack) { - spin_lock_irq(&sdev->ipc_lock); - /* handle immediate reply from DSP core */ - acp_dsp_ipc_get_reply(sdev); - snd_sof_ipc_reply(sdev, 0); - /* set the done bit */ - acp_dsp_ipc_dsp_done(sdev); - spin_unlock_irq(&sdev->ipc_lock); + if (likely(sdev->fw_state == SOF_FW_BOOT_COMPLETE)) { + spin_lock_irq(&sdev->ipc_lock); + + /* handle immediate reply from DSP core */ + acp_dsp_ipc_get_reply(sdev); + snd_sof_ipc_reply(sdev, 0); + /* set the done bit */ + acp_dsp_ipc_dsp_done(sdev); + + spin_unlock_irq(&sdev->ipc_lock); + } else { + dev_dbg_ratelimited(sdev->dev, "IPC reply before FW_BOOT_COMPLETE: %#x\n", + dsp_ack); + } + ipc_irq = true; } diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c index 33648ff8b833..9e13c96528be 100644 --- a/sound/soc/sof/amd/acp.c +++ b/sound/soc/sof/amd/acp.c @@ -27,6 +27,7 @@ MODULE_PARM_DESC(enable_fw_debug, "Enable Firmware debug"); static struct acp_quirk_entry quirk_valve_galileo = { .signed_fw_image = true, .skip_iram_dram_size_mod = true, + .post_fw_run_delay = true, }; const struct dmi_system_id acp_sof_quirk_table[] = { diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h index 800594440f73..2a19d82d6200 100644 --- a/sound/soc/sof/amd/acp.h +++ b/sound/soc/sof/amd/acp.h @@ -220,6 +220,7 @@ struct sof_amd_acp_desc { struct acp_quirk_entry { bool signed_fw_image; bool skip_iram_dram_size_mod; + bool post_fw_run_delay; }; /* Common device data struct for ACP devices */ diff --git a/sound/soc/sof/amd/pci-vangogh.c b/sound/soc/sof/amd/pci-vangogh.c index 53f64d6bc91b..28f2d4050a67 100644 --- a/sound/soc/sof/amd/pci-vangogh.c +++ b/sound/soc/sof/amd/pci-vangogh.c @@ -13,11 +13,9 @@ #include <linux/module.h> #include <linux/pci.h> -#include <linux/platform_device.h> #include <sound/sof.h> #include <sound/soc-acpi.h> -#include "../ops.h" #include "../sof-pci-dev.h" #include "../../amd/mach-config.h" #include "acp.h" diff --git a/sound/soc/sof/amd/vangogh.c b/sound/soc/sof/amd/vangogh.c index 8e2672106ac6..6ed5f9aaa414 100644 --- a/sound/soc/sof/amd/vangogh.c +++ b/sound/soc/sof/amd/vangogh.c @@ -11,13 +11,10 @@ * Hardware interface for Audio DSP on Vangogh platform */ -#include <linux/platform_device.h> +#include <linux/delay.h> #include <linux/module.h> -#include "../ops.h" -#include "../sof-audio.h" #include "acp.h" -#include "acp-dsp-offset.h" #define I2S_HS_INSTANCE 0 #define I2S_BT_INSTANCE 1 @@ -136,6 +133,20 @@ static struct snd_soc_dai_driver vangogh_sof_dai[] = { }, }; +static int sof_vangogh_post_fw_run_delay(struct snd_sof_dev *sdev) +{ + /* + * Resuming from suspend in some cases my cause the DSP firmware + * to enter an unrecoverable faulty state. Delaying a bit any host + * to DSP transmission right after firmware boot completion seems + * to resolve the issue. + */ + if (!sdev->first_boot) + usleep_range(100, 150); + + return 0; +} + /* Vangogh ops */ struct snd_sof_dsp_ops sof_vangogh_ops; EXPORT_SYMBOL_NS(sof_vangogh_ops, "SND_SOC_SOF_AMD_COMMON"); @@ -157,6 +168,9 @@ int sof_vangogh_ops_init(struct snd_sof_dev *sdev) if (quirks->signed_fw_image) sof_vangogh_ops.load_firmware = acp_sof_load_signed_firmware; + + if (quirks->post_fw_run_delay) + sof_vangogh_ops.post_fw_run = sof_vangogh_post_fw_run_delay; } return 0; diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c index 0b85b29d1067..1e7bf00d7c46 100644 --- a/sound/soc/sof/imx/imx8.c +++ b/sound/soc/sof/imx/imx8.c @@ -175,8 +175,7 @@ static int imx8_run(struct snd_sof_dev *sdev) static int imx8_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct device_node *np = pdev->dev.of_node; struct device_node *res_node; struct resource *mmio; @@ -607,10 +606,31 @@ static struct snd_sof_of_mach sof_imx8_machs[] = { .drv_name = "asoc-audio-graph-card2", }, { + .compatible = "fsl,imx8qxp-mek-wcpu", + .sof_tplg_filename = "sof-imx8-wm8962.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + { .compatible = "fsl,imx8qm-mek", .sof_tplg_filename = "sof-imx8-wm8960.tplg", .drv_name = "asoc-audio-graph-card2", }, + { + .compatible = "fsl,imx8qm-mek-revd", + .sof_tplg_filename = "sof-imx8-wm8962.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + { + .compatible = "fsl,imx8qxp-mek-bb", + .sof_tplg_filename = "sof-imx8-cs42888.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + { + .compatible = "fsl,imx8qm-mek-bb", + .sof_tplg_filename = "sof-imx8-cs42888.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + {} }; diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c index ff42743efa79..3cabdebac558 100644 --- a/sound/soc/sof/imx/imx8m.c +++ b/sound/soc/sof/imx/imx8m.c @@ -144,8 +144,7 @@ static int imx8m_reset(struct snd_sof_dev *sdev) static int imx8m_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct device_node *np = pdev->dev.of_node; struct device_node *res_node; struct resource *mmio; @@ -295,6 +294,17 @@ static struct snd_soc_dai_driver imx8m_dai[] = { }, }, { + .name = "sai2", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, +{ .name = "sai3", .playback = { .channels_min = 1, @@ -306,6 +316,39 @@ static struct snd_soc_dai_driver imx8m_dai[] = { }, }, { + .name = "sai5", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, +{ + .name = "sai6", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, +{ + .name = "sai7", + .playback = { + .channels_min = 1, + .channels_max = 32, + }, + .capture = { + .channels_min = 1, + .channels_max = 32, + }, +}, +{ .name = "micfil", .capture = { .channels_min = 1, @@ -472,6 +515,11 @@ static const struct snd_sof_dsp_ops sof_imx8m_ops = { static struct snd_sof_of_mach sof_imx8mp_machs[] = { { + .compatible = "fsl,imx8mp-evk-revb4", + .sof_tplg_filename = "sof-imx8mp-wm8962.tplg", + .drv_name = "asoc-audio-graph-card2", + }, + { .compatible = "fsl,imx8mp-evk", .sof_tplg_filename = "sof-imx8mp-wm8960.tplg", .drv_name = "asoc-audio-graph-card2", diff --git a/sound/soc/sof/imx/imx8ulp.c b/sound/soc/sof/imx/imx8ulp.c index 6965791ab6ef..0704da27e69d 100644 --- a/sound/soc/sof/imx/imx8ulp.c +++ b/sound/soc/sof/imx/imx8ulp.c @@ -155,8 +155,7 @@ static int imx8ulp_reset(struct snd_sof_dev *sdev) static int imx8ulp_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct device_node *np = pdev->dev.of_node; struct device_node *res_node; struct resource *mmio; diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c index 5282c0071534..e1f0e38c2407 100644 --- a/sound/soc/sof/intel/bdw.c +++ b/sound/soc/sof/intel/bdw.c @@ -410,8 +410,7 @@ static int bdw_probe(struct snd_sof_dev *sdev) { struct snd_sof_pdata *pdata = sdev->pdata; const struct sof_dev_desc *desc = pdata->desc; - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); const struct sof_intel_dsp_desc *chip; struct resource *mmio; u32 base, size; diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c index 536d4c89d2f0..cae7dc0036c6 100644 --- a/sound/soc/sof/intel/byt.c +++ b/sound/soc/sof/intel/byt.c @@ -109,8 +109,7 @@ static int byt_acpi_probe(struct snd_sof_dev *sdev) { struct snd_sof_pdata *pdata = sdev->pdata; const struct sof_dev_desc *desc = pdata->desc; - struct platform_device *pdev = - container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); const struct sof_intel_dsp_desc *chip; struct resource *mmio; u32 base, size; diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c index 568f3dfe822f..2f9925830d1d 100644 --- a/sound/soc/sof/intel/hda-codec.c +++ b/sound/soc/sof/intel/hda-codec.c @@ -454,6 +454,7 @@ int hda_codec_i915_exit(struct snd_sof_dev *sdev) } EXPORT_SYMBOL_NS_GPL(hda_codec_i915_exit, "SND_SOC_SOF_HDA_AUDIO_CODEC_I915"); +MODULE_SOFTDEP("pre: snd-hda-codec-hdmi"); #endif MODULE_LICENSE("Dual BSD/GPL"); diff --git a/sound/soc/sof/intel/pci-ptl.c b/sound/soc/sof/intel/pci-ptl.c index 0aacdfac9fb4..c4fb6a2441b7 100644 --- a/sound/soc/sof/intel/pci-ptl.c +++ b/sound/soc/sof/intel/pci-ptl.c @@ -50,6 +50,7 @@ static const struct sof_dev_desc ptl_desc = { /* PCI IDs */ static const struct pci_device_id sof_pci_ids[] = { { PCI_DEVICE_DATA(INTEL, HDA_PTL, &ptl_desc) }, /* PTL */ + { PCI_DEVICE_DATA(INTEL, HDA_PTL_H, &ptl_desc) }, /* PTL-H */ { 0, } }; MODULE_DEVICE_TABLE(pci, sof_pci_ids); diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c index c04c62478827..6d5cda813e48 100644 --- a/sound/soc/sof/ipc4-topology.c +++ b/sound/soc/sof/ipc4-topology.c @@ -765,10 +765,16 @@ static int sof_ipc4_widget_setup_comp_dai(struct snd_sof_widget *swidget) } list_for_each_entry(w, &sdev->widget_list, list) { - if (w->widget->sname && + struct snd_sof_dai *alh_dai; + + if (!WIDGET_IS_DAI(w->id) || !w->widget->sname || strcmp(w->widget->sname, swidget->widget->sname)) continue; + alh_dai = w->private; + if (alh_dai->type != SOF_DAI_INTEL_ALH) + continue; + blob->alh_cfg.device_count++; } @@ -2061,11 +2067,13 @@ sof_ipc4_prepare_copier_module(struct snd_sof_widget *swidget, list_for_each_entry(w, &sdev->widget_list, list) { u32 node_type; - if (w->widget->sname && + if (!WIDGET_IS_DAI(w->id) || !w->widget->sname || strcmp(w->widget->sname, swidget->widget->sname)) continue; dai = w->private; + if (dai->type != SOF_DAI_INTEL_ALH) + continue; alh_copier = (struct sof_ipc4_copier *)dai->private; alh_data = &alh_copier->data; node_type = SOF_IPC4_GET_NODE_TYPE(alh_data->gtw_cfg.node_id); diff --git a/sound/soc/sof/mediatek/mt8186/mt8186.c b/sound/soc/sof/mediatek/mt8186/mt8186.c index 9955dfa520ae..31437fdd4e92 100644 --- a/sound/soc/sof/mediatek/mt8186/mt8186.c +++ b/sound/soc/sof/mediatek/mt8186/mt8186.c @@ -238,7 +238,7 @@ static int mt8186_run(struct snd_sof_dev *sdev) static int mt8186_dsp_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct adsp_priv *priv; int ret; diff --git a/sound/soc/sof/mediatek/mt8195/mt8195.c b/sound/soc/sof/mediatek/mt8195/mt8195.c index 6032b566c679..371563d7ce79 100644 --- a/sound/soc/sof/mediatek/mt8195/mt8195.c +++ b/sound/soc/sof/mediatek/mt8195/mt8195.c @@ -228,7 +228,7 @@ static int mt8195_run(struct snd_sof_dev *sdev) static int mt8195_dsp_probe(struct snd_sof_dev *sdev) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct adsp_priv *priv; int ret; @@ -341,7 +341,7 @@ static int mt8195_dsp_shutdown(struct snd_sof_dev *sdev) static void mt8195_dsp_remove(struct snd_sof_dev *sdev) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); struct adsp_priv *priv = sdev->pdata->hw_pdata; platform_device_unregister(priv->ipc_dev); @@ -351,7 +351,7 @@ static void mt8195_dsp_remove(struct snd_sof_dev *sdev) static int mt8195_dsp_suspend(struct snd_sof_dev *sdev, u32 target_state) { - struct platform_device *pdev = container_of(sdev->dev, struct platform_device, dev); + struct platform_device *pdev = to_platform_device(sdev->dev); int ret; u32 reset_sw, dbg_pc; diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c index 35a7462d8b69..c5c6353f18ce 100644 --- a/sound/soc/sof/pcm.c +++ b/sound/soc/sof/pcm.c @@ -511,6 +511,8 @@ static int sof_pcm_close(struct snd_soc_component *component, */ } + spcm->stream[substream->stream].substream = NULL; + return 0; } diff --git a/sound/soc/sof/stream-ipc.c b/sound/soc/sof/stream-ipc.c index 794c7bbccbaf..8262443ac89a 100644 --- a/sound/soc/sof/stream-ipc.c +++ b/sound/soc/sof/stream-ipc.c @@ -43,7 +43,7 @@ int sof_ipc_msg_data(struct snd_sof_dev *sdev, return -ESTRPIPE; posn_offset = stream->posn_offset; - } else { + } else if (sps->cstream) { struct sof_compr_stream *sstream = sps->cstream->runtime->private_data; @@ -51,6 +51,10 @@ int sof_ipc_msg_data(struct snd_sof_dev *sdev, return -ESTRPIPE; posn_offset = sstream->posn_offset; + + } else { + dev_err(sdev->dev, "%s: No stream opened\n", __func__); + return -EINVAL; } snd_sof_dsp_mailbox_read(sdev, posn_offset, p, sz); diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 7968d6a2f592..a97efb7b131e 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2343,6 +2343,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */ QUIRK_FLAG_CTL_MSG_DELAY_1M), + DEVICE_FLG(0x2fc6, 0xf0b7, /* iBasso DC07 Pro */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */ diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 100ad3dc091a..3feac0482fe9 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -196,22 +196,22 @@ static int get_family_id(int sd) static void print_delayacct(struct taskstats *t) { - printf("\n\nCPU %15s%15s%15s%15s%15s%15s\n" - " %15llu%15llu%15llu%15llu%15.3fms%13.6fms\n" - "IO %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "SWAP %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "RECLAIM %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "THRASHING%12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "COMPACT %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "WPCOPY %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "IRQ %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n", + printf("\n\nCPU %15s%15s%15s%15s%15s%15s%15s\n" + " %15llu%15llu%15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IO %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "SWAP %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "RECLAIM %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "THRASHING%12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "COMPACT %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "WPCOPY %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IRQ %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n", "count", "real total", "virtual total", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->cpu_count, diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index bcac7ebfb51f..d7e5e8902af8 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -24,8 +24,8 @@ #include <signal.h> #include <inttypes.h> #include <sys/types.h> -#include <sys/errno.h> -#include <sys/fcntl.h> +#include <errno.h> +#include <fcntl.h> #include <sys/mount.h> #include <sys/statfs.h> #include <sys/mman.h> diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index e16cef160bc2..ce32cb35007d 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -95,7 +95,7 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off, ynl_attr_for_each_payload(start, data_len, attr) { astart_off = (char *)attr - (char *)start; - aend_off = astart_off + ynl_attr_data_len(attr); + aend_off = (char *)ynl_attr_data_end(attr) - (char *)start; if (aend_off <= off) continue; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 753dbc4f8198..be18a0489303 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -227,6 +227,7 @@ static bool is_rust_noreturn(const struct symbol *func) str_ends_with(func->name, "_4core9panicking18panic_bounds_check") || str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || + strstr(func->name, "_4core9panicking13assert_failed") || strstr(func->name, "_4core9panicking11panic_const24panic_const_") || (strstr(func->name, "_4core5slice5index24slice_") && str_ends_with(func->name, "_fail")); @@ -1975,6 +1976,14 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, reloc_addend(reloc) == pfunc->offset) break; + /* + * Clang sometimes leaves dangling unused jump table entries + * which point to the end of the function. Ignore them. + */ + if (reloc->sym->sec == pfunc->sec && + reloc_addend(reloc) == pfunc->offset + pfunc->len) + goto next; + dest_insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!dest_insn) break; @@ -1992,6 +2001,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; alt->next = insn->alts; insn->alts = alt; +next: prev_offset = reloc_offset(reloc); } @@ -2264,7 +2274,7 @@ static int read_annotate(struct objtool_file *file, if (sec->sh.sh_entsize != 8) { static bool warned = false; - if (!warned) { + if (!warned && opts.verbose) { WARN("%s: dodgy linker, sh_entsize != 8", sec->name); warned = true; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index d7c7d29291fb..d466447ae928 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2107,8 +2107,12 @@ static int trace__read_syscall_info(struct trace *trace, int id) return PTR_ERR(sc->tp_format); } + /* + * The tracepoint format contains __syscall_nr field, so it's one more + * than the actual number of syscall arguments. + */ if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? - RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields)) + RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields - 1)) return -ENOMEM; sc->args = sc->tp_format->format.fields; diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh index 5a3b8a5a9b5c..8d1e6bbeac90 100755 --- a/tools/perf/tests/shell/trace_btf_enum.sh +++ b/tools/perf/tests/shell/trace_btf_enum.sh @@ -26,8 +26,12 @@ check_vmlinux() { trace_landlock() { echo "Tracing syscall ${syscall}" - # test flight just to see if landlock_add_rule and libbpf are available - $TESTPROG + # test flight just to see if landlock_add_rule is available + if ! perf trace $TESTPROG 2>&1 | grep -q landlock + then + echo "No landlock system call found, skipping to non-syscall tracing." + return + fi if perf trace -e $syscall $TESTPROG 2>&1 | \ grep -q -E ".*landlock_add_rule\(ruleset_fd: 11, rule_type: (LANDLOCK_RULE_PATH_BENEATH|LANDLOCK_RULE_NET_PORT), rule_attr: 0x[a-f0-9]+, flags: 45\) = -1.*" diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0d2ea22bd9e4..31bb326b07a6 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2100,6 +2100,57 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, return 0; } +const char * const perf_disassembler__strs[] = { + [PERF_DISASM_UNKNOWN] = "unknown", + [PERF_DISASM_LLVM] = "llvm", + [PERF_DISASM_CAPSTONE] = "capstone", + [PERF_DISASM_OBJDUMP] = "objdump", +}; + + +static void annotation_options__add_disassembler(struct annotation_options *options, + enum perf_disassembler dis) +{ + for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers); i++) { + if (options->disassemblers[i] == dis) { + /* Disassembler is already present then don't add again. */ + return; + } + if (options->disassemblers[i] == PERF_DISASM_UNKNOWN) { + /* Found a free slot. */ + options->disassemblers[i] = dis; + return; + } + } + pr_err("Failed to add disassembler %d\n", dis); +} + +static int annotation_options__add_disassemblers_str(struct annotation_options *options, + const char *str) +{ + while (str && *str != '\0') { + const char *comma = strchr(str, ','); + int len = comma ? comma - str : (int)strlen(str); + bool match = false; + + for (u8 i = 0; i < ARRAY_SIZE(perf_disassembler__strs); i++) { + const char *dis_str = perf_disassembler__strs[i]; + + if (len == (int)strlen(dis_str) && !strncmp(str, dis_str, len)) { + annotation_options__add_disassembler(options, i); + match = true; + break; + } + } + if (!match) { + pr_err("Invalid disassembler '%.*s'\n", len, str); + return -1; + } + str = comma ? comma + 1 : NULL; + } + return 0; +} + static int annotation__config(const char *var, const char *value, void *data) { struct annotation_options *opt = data; @@ -2115,11 +2166,10 @@ static int annotation__config(const char *var, const char *value, void *data) else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL) opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL; } else if (!strcmp(var, "annotate.disassemblers")) { - opt->disassemblers_str = strdup(value); - if (!opt->disassemblers_str) { - pr_err("Not enough memory for annotate.disassemblers\n"); - return -1; - } + int err = annotation_options__add_disassemblers_str(opt, value); + + if (err) + return err; } else if (!strcmp(var, "annotate.hide_src_code")) { opt->hide_src_code = perf_config_bool("hide_src_code", value); } else if (!strcmp(var, "annotate.jump_arrows")) { @@ -2185,9 +2235,25 @@ void annotation_options__exit(void) zfree(&annotate_opts.objdump_path); } +static void annotation_options__default_init_disassemblers(struct annotation_options *options) +{ + if (options->disassemblers[0] != PERF_DISASM_UNKNOWN) { + /* Already initialized. */ + return; + } +#ifdef HAVE_LIBLLVM_SUPPORT + annotation_options__add_disassembler(options, PERF_DISASM_LLVM); +#endif +#ifdef HAVE_LIBCAPSTONE_SUPPORT + annotation_options__add_disassembler(options, PERF_DISASM_CAPSTONE); +#endif + annotation_options__add_disassembler(options, PERF_DISASM_OBJDUMP); +} + void annotation_config__init(void) { perf_config(annotation__config, &annotate_opts); + annotation_options__default_init_disassemblers(&annotate_opts); } static unsigned int parse_percent_type(char *str1, char *str2) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 0ba5846dad4d..98db1b88daf4 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -34,8 +34,13 @@ struct annotated_data_type; #define ANNOTATION__BR_CNTR_WIDTH 30 #define ANNOTATION_DUMMY_LEN 256 -// llvm, capstone, objdump -#define MAX_DISASSEMBLERS 3 +enum perf_disassembler { + PERF_DISASM_UNKNOWN = 0, + PERF_DISASM_LLVM, + PERF_DISASM_CAPSTONE, + PERF_DISASM_OBJDUMP, +}; +#define MAX_DISASSEMBLERS (PERF_DISASM_OBJDUMP + 1) struct annotation_options { bool hide_src_code, @@ -52,14 +57,12 @@ struct annotation_options { annotate_src, full_addr; u8 offset_level; - u8 nr_disassemblers; + u8 disassemblers[MAX_DISASSEMBLERS]; int min_pcnt; int max_lines; int context; char *objdump_path; char *disassembler_style; - const char *disassemblers_str; - const char *disassemblers[MAX_DISASSEMBLERS]; const char *prefix; const char *prefix_strip; unsigned int percent_type; @@ -134,6 +137,8 @@ struct disasm_line { struct annotation_line al; }; +extern const char * const perf_disassembler__strs[]; + void annotation_line__add(struct annotation_line *al, struct list_head *head); static inline double annotation_data__percent(struct annotation_data *data, diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 4a62ed593e84..e4352881e3fa 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -431,9 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) { bool augmented, do_output = false; - int zero = 0, size, aug_size, index, - value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); + int zero = 0, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */ + s64 aug_size, size; unsigned int nr, *beauty_map; struct beauty_payload_enter *payload; void *arg, *payload_offset; @@ -484,14 +484,11 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } else if (size > 0 && size <= value_size) { /* struct */ if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg)) augmented = true; - } else if (size < 0 && size >= -6) { /* buffer */ + } else if ((int)size < 0 && size >= -6) { /* buffer */ index = -(size + 1); barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick. index &= 7; // Satisfy the bounds checking with the verifier in some kernels. - aug_size = args->args[index]; - - if (aug_size > TRACE_AUG_MAX_BUF) - aug_size = TRACE_AUG_MAX_BUF; + aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index]; if (aug_size > 0) { if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg)) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 27094211edd8..5c329ad614e9 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -293,7 +293,7 @@ struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data) die = cpu__get_die_id(cpu); /* There is no die_id on legacy system. */ - if (die == -1) + if (die < 0) die = 0; /* @@ -322,7 +322,7 @@ struct aggr_cpu_id aggr_cpu_id__cluster(struct perf_cpu cpu, void *data) struct aggr_cpu_id id; /* There is no cluster_id on legacy system. */ - if (cluster == -1) + if (cluster < 0) cluster = 0; id = aggr_cpu_id__die(cpu, data); diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index b7de4d9fd004..50c5c206b70e 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -2216,56 +2216,6 @@ out_free_command: return err; } -static int annotation_options__init_disassemblers(struct annotation_options *options) -{ - char *disassembler; - - if (options->disassemblers_str == NULL) { - const char *default_disassemblers_str = -#ifdef HAVE_LIBLLVM_SUPPORT - "llvm," -#endif -#ifdef HAVE_LIBCAPSTONE_SUPPORT - "capstone," -#endif - "objdump"; - - options->disassemblers_str = strdup(default_disassemblers_str); - if (!options->disassemblers_str) - goto out_enomem; - } - - disassembler = strdup(options->disassemblers_str); - if (disassembler == NULL) - goto out_enomem; - - while (1) { - char *comma = strchr(disassembler, ','); - - if (comma != NULL) - *comma = '\0'; - - options->disassemblers[options->nr_disassemblers++] = strim(disassembler); - - if (comma == NULL) - break; - - disassembler = comma + 1; - - if (options->nr_disassemblers >= MAX_DISASSEMBLERS) { - pr_debug("annotate.disassemblers can have at most %d entries, ignoring \"%s\"\n", - MAX_DISASSEMBLERS, disassembler); - break; - } - } - - return 0; - -out_enomem: - pr_err("Not enough memory for annotate.disassemblers\n"); - return -1; -} - int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *options = args->options; @@ -2274,7 +2224,6 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) char symfs_filename[PATH_MAX]; bool delete_extract = false; struct kcore_extract kce; - const char *disassembler; bool decomp = false; int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename)); @@ -2334,28 +2283,26 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) } } - err = annotation_options__init_disassemblers(options); - if (err) - goto out_remove_tmp; - err = -1; + for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers) && err != 0; i++) { + enum perf_disassembler dis = options->disassemblers[i]; - for (int i = 0; i < options->nr_disassemblers && err != 0; ++i) { - disassembler = options->disassemblers[i]; - - if (!strcmp(disassembler, "llvm")) + switch (dis) { + case PERF_DISASM_LLVM: err = symbol__disassemble_llvm(symfs_filename, sym, args); - else if (!strcmp(disassembler, "capstone")) + break; + case PERF_DISASM_CAPSTONE: err = symbol__disassemble_capstone(symfs_filename, sym, args); - else if (!strcmp(disassembler, "objdump")) + break; + case PERF_DISASM_OBJDUMP: err = symbol__disassemble_objdump(symfs_filename, sym, args); - else - pr_debug("Unknown disassembler %s, skipping...\n", disassembler); - } - - if (err == 0) { - pr_debug("Disassembled with %s\nannotate.disassemblers=%s\n", - disassembler, options->disassemblers_str); + break; + case PERF_DISASM_UNKNOWN: /* End of disassemblers. */ + default: + goto out_remove_tmp; + } + if (err == 0) + pr_debug("Disassembled with %s\n", perf_disassembler__strs[dis]); } out_remove_tmp: if (decomp) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a7f7ed01421c..99bf905ade81 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -136,7 +136,7 @@ displays the statistics gathered since it was forked. The system configuration dump (if --quiet is not used) is followed by statistics. The first row of the statistics labels the content of each column (below). The second row of statistics is the system summary line. The system summary line has a '-' in the columns for the Package, Core, and CPU. The contents of the system summary line depends on the type of column. Columns that count items (eg. IRQ) show the sum across all CPUs in the system. Columns that show a percentage show the average across all CPUs in the system. Columns that dump raw MSR values simply show 0 in the summary. After the system summary row, each row describes a specific Package/Core/CPU. Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system. .SH COLUMN DESCRIPTIONS .PP -\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to collect the counters on all cpus. +\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to snapshot the procfs/sysfs and collect the counters on all cpus. .PP \fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected. This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug". On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU. .PP @@ -190,7 +190,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. .PP -\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). Disabled by default. Enable with --enable SysWatt. +\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). .PP \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. .PP @@ -516,14 +516,40 @@ that they count at TSC rate, which is true on all processors tested to date. Volume 3B: System Programming Guide" https://www.intel.com/products/processor/manuals/ +.SH RUN THE LATEST VERSION +If turbostat complains that it doesn't recognize your processor, +please try the latest version. + +The latest version of turbostat does not require the latest version of the Linux kernel. +However, some features, such as perf(1) counters, do require kernel support. + +The latest turbostat release is available in the upstream Linux Kernel source tree. +eg. "git pull https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git" +and run make in tools/power/x86/turbostat/. + +n.b. "make install" will update your system manually, but a distro update may subsequently downgrade your turbostat to an older version. +For this reason, manually installing to /usr/local/bin may be what you want. + +Note that turbostat/Makefile has a "make snapshot" target, which will create a tar file +that can build without a local kernel source tree. + +If the upstream version isn't new enough, the development tree can be found here: +"git pull https://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat" + +If the development tree doesn't work, please contact the author via chat, +or via email with the word "turbostat" on the Subject line. + .SH FILES .ta .nf +/sys/bus/event_source/devices/ /dev/cpu/*/msr +/sys/class/intel_pmt/ +/sys/devices/system/cpu/ .fi .SH "SEE ALSO" -msr(4), vmstat(8) +perf(1), msr(4), vmstat(8) .PP .SH AUTHOR .nf diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 58a487c225a7..8d5011a0bf60 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3,7 +3,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel and AMD processors. * - * Copyright (c) 2024 Intel Corporation. + * Copyright (c) 2025 Intel Corporation. * Len Brown <len.brown@intel.com> */ @@ -95,6 +95,8 @@ #define INTEL_ECORE_TYPE 0x20 #define INTEL_PCORE_TYPE 0x40 +#define ROUND_UP_TO_PAGE_SIZE(n) (((n) + 0x1000UL-1UL) & ~(0x1000UL-1UL)) + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE }; @@ -202,6 +204,8 @@ struct msr_counter bic[] = { { 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "SysWatt", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "Sys_J", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "NMI", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%c1e", NULL, 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -266,14 +270,16 @@ struct msr_counter bic[] = { #define BIC_Diec6 (1ULL << 58) #define BIC_SysWatt (1ULL << 59) #define BIC_Sys_J (1ULL << 60) +#define BIC_NMI (1ULL << 61) +#define BIC_CPU_c1e (1ULL << 62) -#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) -#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) +#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die) +#define BIC_THERMAL_PWR (BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__ | BIC_SysWatt) #define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ) -#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) -#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) +#define BIC_IDLE (BIC_Busy | BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) +#define BIC_OTHER (BIC_IRQ | BIC_NMI | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_SysWatt | BIC_Sys_J) +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; @@ -326,6 +332,7 @@ unsigned int rapl_joules; unsigned int summary_only; unsigned int list_header_only; unsigned int dump_only; +unsigned int force_load; unsigned int has_aperf; unsigned int has_aperf_access; unsigned int has_epb; @@ -353,7 +360,7 @@ unsigned long long cpuidle_cur_sys_lpi_us; unsigned int tj_max; unsigned int tj_max_override; double rapl_power_units, rapl_time_units; -double rapl_dram_energy_units, rapl_energy_units; +double rapl_dram_energy_units, rapl_energy_units, rapl_psys_energy_units; double rapl_joule_counter_range; unsigned int crystal_hz; unsigned long long tsc_hz; @@ -365,6 +372,9 @@ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int first_counter_read = 1; + +static struct timeval procsysfs_tv_begin; + int ignore_stdin; bool no_msr; bool no_perf; @@ -419,6 +429,7 @@ struct platform_features { bool has_per_core_rapl; /* Indicates cores energy collection is per-core, not per-package. AMD specific for now */ bool has_rapl_divisor; /* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */ bool has_fixed_rapl_unit; /* Fixed Energy Unit used for DRAM RAPL Domain */ + bool has_fixed_rapl_psys_unit; /* Fixed Energy Unit used for PSYS RAPL Domain */ int rapl_quirk_tdp; /* Hardcoded TDP value when cannot be retrieved from hardware */ int tcc_offset_bits; /* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */ bool enable_tsc_tweak; /* Use CPU Base freq instead of TSC freq for aperf/mperf counter */ @@ -819,6 +830,7 @@ static const struct platform_features spr_features = { .has_msr_core_c1_res = 1, .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, + .has_fixed_rapl_psys_unit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; @@ -1024,6 +1036,7 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_ARROWLAKE_U, &adl_features }, { INTEL_ARROWLAKE, &adl_features }, { INTEL_LUNARLAKE_M, &lnl_features }, + { INTEL_PANTHERLAKE_L, &lnl_features }, { INTEL_ATOM_SILVERMONT, &slv_features }, { INTEL_ATOM_SILVERMONT_D, &slvd_features }, { INTEL_ATOM_AIRMONT, &amt_features }, @@ -1036,6 +1049,7 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_ATOM_GRACEMONT, &adl_features }, { INTEL_ATOM_CRESTMONT_X, &srf_features }, { INTEL_ATOM_CRESTMONT, &grr_features }, + { INTEL_ATOM_DARKMONT_X, &srf_features }, { INTEL_XEON_PHI_KNL, &knl_features }, { INTEL_XEON_PHI_KNM, &knl_features }, /* @@ -1054,9 +1068,10 @@ void probe_platform_features(unsigned int family, unsigned int model) { int i; - platform = &default_features; if (authentic_amd || hygon_genuine) { + /* fallback to default features on unsupported models */ + force_load++; if (max_extended_level >= 0x80000007) { unsigned int eax, ebx, ecx, edx; @@ -1065,11 +1080,11 @@ void probe_platform_features(unsigned int family, unsigned int model) if ((edx & (1 << 14)) && family >= 0x17) platform = &amd_features_with_rapl; } - return; + goto end; } if (!genuine_intel) - return; + goto end; for (i = 0; turbostat_pdata[i].features; i++) { if (VFM_FAMILY(turbostat_pdata[i].vfm) == family && VFM_MODEL(turbostat_pdata[i].vfm) == model) { @@ -1077,6 +1092,19 @@ void probe_platform_features(unsigned int family, unsigned int model) return; } } + +end: + if (force_load && !platform) { + fprintf(outf, "Forced to run on unsupported platform!\n"); + platform = &default_features; + } + + if (platform) + return; + + fprintf(stderr, "Unsupported platform detected.\n" + "\tSee RUN THE LATEST VERSION on turbostat(8)\n"); + exit(1); } /* Model specific support End */ @@ -1094,8 +1122,8 @@ int backwards_count; char *progname; #define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */ -cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset; -size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size; +cpu_set_t *cpu_present_set, *cpu_possible_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset; +size_t cpu_present_setsize, cpu_possible_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size; #define MAX_ADDED_THREAD_COUNTERS 24 #define MAX_ADDED_CORE_COUNTERS 8 #define MAX_ADDED_PACKAGE_COUNTERS 16 @@ -1271,7 +1299,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr = MSR_PLATFORM_ENERGY_STATUS, .msr_mask = 0x00000000FFFFFFFF, .msr_shift = 0, - .platform_rapl_msr_scale = &rapl_energy_units, + .platform_rapl_msr_scale = &rapl_psys_energy_units, .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM, .bic = BIC_SysWatt | BIC_Sys_J, .compat_scale = 1.0, @@ -1510,6 +1538,17 @@ static struct msr_counter_arch_info msr_counter_arch_infos[] = { #define PMT_COUNTER_MTL_DC6_LSB 0 #define PMT_COUNTER_MTL_DC6_MSB 63 #define PMT_MTL_DC6_GUID 0x1a067102 +#define PMT_MTL_DC6_SEQ 0 + +#define PMT_COUNTER_CWF_MC1E_OFFSET_BASE 20936 +#define PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT 24 +#define PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE 12 +#define PMT_COUNTER_CWF_CPUS_PER_MODULE 4 +#define PMT_COUNTER_CWF_MC1E_LSB 0 +#define PMT_COUNTER_CWF_MC1E_MSB 63 +#define PMT_CWF_MC1E_GUID 0x14421519 + +unsigned long long tcore_clock_freq_hz = 800000000; #define PMT_COUNTER_NAME_SIZE_BYTES 16 #define PMT_COUNTER_TYPE_NAME_SIZE_BYTES 32 @@ -1533,6 +1572,7 @@ struct pmt_mmio { enum pmt_datatype { PMT_TYPE_RAW, PMT_TYPE_XTAL_TIME, + PMT_TYPE_TCORE_CLOCK, }; struct pmt_domain_info { @@ -1562,6 +1602,93 @@ struct pmt_counter { struct pmt_domain_info *domains; }; +/* + * PMT telemetry directory iterator. + * Used to iterate telemetry files in sysfs in correct order. + */ +struct pmt_diriter_t { + DIR *dir; + struct dirent **namelist; + unsigned int num_names; + unsigned int current_name_idx; +}; + +int pmt_telemdir_filter(const struct dirent *e) +{ + unsigned int dummy; + + return sscanf(e->d_name, "telem%u", &dummy); +} + +int pmt_telemdir_sort(const struct dirent **a, const struct dirent **b) +{ + unsigned int aidx = 0, bidx = 0; + + sscanf((*a)->d_name, "telem%u", &aidx); + sscanf((*b)->d_name, "telem%u", &bidx); + + return aidx >= bidx; +} + +const struct dirent *pmt_diriter_next(struct pmt_diriter_t *iter) +{ + const struct dirent *ret = NULL; + + if (!iter->dir) + return NULL; + + if (iter->current_name_idx >= iter->num_names) + return NULL; + + ret = iter->namelist[iter->current_name_idx]; + ++iter->current_name_idx; + + return ret; +} + +const struct dirent *pmt_diriter_begin(struct pmt_diriter_t *iter, const char *pmt_root_path) +{ + int num_names = iter->num_names; + + if (!iter->dir) { + iter->dir = opendir(pmt_root_path); + if (iter->dir == NULL) + return NULL; + + num_names = scandir(pmt_root_path, &iter->namelist, pmt_telemdir_filter, pmt_telemdir_sort); + if (num_names == -1) + return NULL; + } + + iter->current_name_idx = 0; + iter->num_names = num_names; + + return pmt_diriter_next(iter); +} + +void pmt_diriter_init(struct pmt_diriter_t *iter) +{ + memset(iter, 0, sizeof(*iter)); +} + +void pmt_diriter_remove(struct pmt_diriter_t *iter) +{ + if (iter->namelist) { + for (unsigned int i = 0; i < iter->num_names; i++) { + free(iter->namelist[i]); + iter->namelist[i] = NULL; + } + } + + free(iter->namelist); + iter->namelist = NULL; + iter->num_names = 0; + iter->current_name_idx = 0; + + closedir(iter->dir); + iter->dir = NULL; +} + unsigned int pmt_counter_get_width(const struct pmt_counter *p) { return (p->msb - p->lsb) + 1; @@ -1611,6 +1738,7 @@ struct thread_data { unsigned long long c1; unsigned long long instr_count; unsigned long long irq_count; + unsigned long long nmi_count; unsigned int smi_count; unsigned int cpu_id; unsigned int apic_id; @@ -1917,6 +2045,7 @@ struct timeval tv_even, tv_odd, tv_delta; int *irq_column_2_cpu; /* /proc/interrupts column numbers */ int *irqs_per_cpu; /* indexed by cpu_num */ +int *nmi_per_cpu; /* indexed by cpu_num */ void setup_all_buffers(bool startup); @@ -1944,6 +2073,8 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk { int retval, pkg_no, core_no, thread_no, node_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -1959,14 +2090,12 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk c = GET_CORE(core_base, core_no, node_no, pkg_no); p = GET_PKG(pkg_base, pkg_no); - retval = func(t, c, p); - if (retval) - return retval; + retval |= func(t, c, p); } } } } - return 0; + return retval; } int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p) @@ -2085,13 +2214,17 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) int probe_msr(int cpu, off_t offset) { ssize_t retval; - unsigned long long dummy; + unsigned long long value; assert(!no_msr); - retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset); + retval = pread(get_msr_fd(cpu), &value, sizeof(value), offset); - if (retval != sizeof(dummy)) + /* + * Expect MSRs to accumulate some non-zero value since the system was powered on. + * Treat zero as a read failure. + */ + if (retval != sizeof(value) || value == 0) return 1; return 0; @@ -2135,41 +2268,54 @@ void help(void) "when COMMAND completes.\n" "If no COMMAND is specified, turbostat wakes every 5-seconds\n" "to print statistics, until interrupted.\n" - " -a, --add add a counter\n" + " -a, --add counter\n" + " add a counter\n" " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" " eg. --add perf/cstate_pkg/c2-residency,package,delta,percent,perfPC2\n" " eg. --add pmt,name=XTAL,type=raw,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102\n" - " -c, --cpu cpu-set limit output to summary plus cpu-set:\n" + " -c, --cpu cpu-set\n" + " limit output to summary plus cpu-set:\n" " {core | package | j,k,l..m,n-p }\n" - " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n" + " -d, --debug\n" + " displays usec, Time_Of_Day_Seconds and more debugging\n" " debug messages are printed to stderr\n" - " -D, --Dump displays the raw counter values\n" - " -e, --enable [all | column]\n" + " -D, --Dump\n" + " displays the raw counter values\n" + " -e, --enable [all | column]\n" " shows all or the specified disabled column\n" - " -H, --hide [column|column,column,...]\n" + " -f, --force\n" + " force load turbostat with minimum default features on unsupported platforms.\n" + " -H, --hide [column | column,column,...]\n" " hide the specified column(s)\n" " -i, --interval sec.subsec\n" - " Override default 5-second measurement interval\n" - " -J, --Joules displays energy in Joules instead of Watts\n" - " -l, --list list column headers only\n" - " -M, --no-msr Disable all uses of the MSR driver\n" - " -P, --no-perf Disable all uses of the perf API\n" + " override default 5-second measurement interval\n" + " -J, --Joules\n" + " displays energy in Joules instead of Watts\n" + " -l, --list\n" + " list column headers only\n" + " -M, --no-msr\n" + " disable all uses of the MSR driver\n" + " -P, --no-perf\n" + " disable all uses of the perf API\n" " -n, --num_iterations num\n" " number of the measurement iterations\n" " -N, --header_iterations num\n" " print header every num iterations\n" " -o, --out file\n" " create or truncate \"file\" for all output\n" - " -q, --quiet skip decoding system configuration header\n" - " -s, --show [column|column,column,...]\n" + " -q, --quiet\n" + " skip decoding system configuration header\n" + " -s, --show [column | column,column,...]\n" " show only the specified column(s)\n" " -S, --Summary\n" " limits output to 1-line system summary per interval\n" " -T, --TCC temperature\n" " sets the Thermal Control Circuit temperature in\n" " degrees Celsius\n" - " -h, --help print this help message\n" - " -v, --version print version information\n" "\n" "For more help, run \"man turbostat\"\n"); + " -h, --help\n" + " print this help message\n" + " -v, --version\n" + " print version information\n\nFor more help, run \"man turbostat\"\n"); } /* @@ -2289,6 +2435,12 @@ void print_header(char *delim) else outp += sprintf(outp, "%sIRQ", (printed++ ? delim : "")); } + if (DO_BIC(BIC_NMI)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s NMI", (printed++ ? delim : "")); + else + outp += sprintf(outp, "%sNMI", (printed++ ? delim : "")); + } if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "%sSMI", (printed++ ? delim : "")); @@ -2335,6 +2487,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2409,6 +2562,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2540,6 +2694,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2575,6 +2730,8 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p if (DO_BIC(BIC_IRQ)) outp += sprintf(outp, "IRQ: %lld\n", t->irq_count); + if (DO_BIC(BIC_NMI)) + outp += sprintf(outp, "IRQ: %lld\n", t->nmi_count); if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "SMI: %d\n", t->smi_count); @@ -2794,6 +2951,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count); } + /* NMI */ + if (DO_BIC(BIC_NMI)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->nmi_count); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->nmi_count); + } + /* SMI */ if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count); @@ -2848,7 +3013,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = t->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2860,8 +3025,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -2928,7 +3098,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = c->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2940,8 +3110,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -3126,7 +3301,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = p->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -3138,8 +3313,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -3409,6 +3589,9 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d if (DO_BIC(BIC_IRQ)) old->irq_count = new->irq_count - old->irq_count; + if (DO_BIC(BIC_NMI)) + old->nmi_count = new->nmi_count - old->nmi_count; + if (DO_BIC(BIC_SMI)) old->smi_count = new->smi_count - old->smi_count; @@ -3447,12 +3630,10 @@ int delta_cpu(struct thread_data *t, struct core_data *c, /* always calculate thread delta */ retval = delta_thread(t, t2, c2); /* c2 is core delta */ - if (retval) - return retval; /* calculate package delta only for 1st core in package */ if (is_cpu_first_core_in_package(t, c, p)) - retval = delta_package(p, p2); + retval |= delta_package(p, p2); return retval; } @@ -3489,6 +3670,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data t->instr_count = 0; t->irq_count = 0; + t->nmi_count = 0; t->smi_count = 0; c->c3 = 0; @@ -3580,7 +3762,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) /* remember first tv_begin */ if (average.threads.tv_begin.tv_sec == 0) - average.threads.tv_begin = t->tv_begin; + average.threads.tv_begin = procsysfs_tv_begin; /* remember last tv_end */ average.threads.tv_end = t->tv_end; @@ -3593,6 +3775,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.threads.instr_count += t->instr_count; average.threads.irq_count += t->irq_count; + average.threads.nmi_count += t->nmi_count; average.threads.smi_count += t->smi_count; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { @@ -3734,6 +3917,9 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data if (average.threads.irq_count > 9999999) sums_need_wide_columns = 1; + if (average.threads.nmi_count > 9999999) + sums_need_wide_columns = 1; + average.cores.c3 /= topo.allowed_cores; average.cores.c6 /= topo.allowed_cores; @@ -4546,7 +4732,8 @@ unsigned long pmt_gen_value_mask(unsigned int lsb, unsigned int msb) unsigned long pmt_read_counter(struct pmt_counter *ppmt, unsigned int domain_id) { - assert(domain_id < ppmt->num_domains); + if (domain_id >= ppmt->num_domains) + return 0; const unsigned long *pmmio = ppmt->domains[domain_id].pcounter; const unsigned long value = pmmio ? *pmmio : 0; @@ -4590,6 +4777,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (DO_BIC(BIC_IRQ)) t->irq_count = irqs_per_cpu[cpu]; + if (DO_BIC(BIC_NMI)) + t->nmi_count = nmi_per_cpu[cpu]; get_cstate_counters(cpu, t, c, p); @@ -5335,6 +5524,7 @@ void free_all_buffers(void) free(irq_column_2_cpu); free(irqs_per_cpu); + free(nmi_per_cpu); for (i = 0; i <= topo.max_cpu_num; ++i) { if (cpus[i].put_ids) @@ -5566,6 +5756,8 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, { int retval, pkg_no, node_no, core_no, thread_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -5587,14 +5779,12 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, p = GET_PKG(pkg_base, pkg_no); p2 = GET_PKG(pkg_base2, pkg_no); - retval = func(t, c, p, t2, c2, p2); - if (retval) - return retval; + retval |= func(t, c, p, t2, c2, p2); } } } } - return 0; + return retval; } /* @@ -5791,31 +5981,37 @@ int snapshot_proc_interrupts(void) irq_column_2_cpu[column] = cpu_number; irqs_per_cpu[cpu_number] = 0; + nmi_per_cpu[cpu_number] = 0; } /* read /proc/interrupt count lines and sum up irqs per cpu */ while (1) { int column; char buf[64]; + int this_row_is_nmi = 0; - retval = fscanf(fp, " %s:", buf); /* flush irq# "N:" */ + retval = fscanf(fp, " %s:", buf); /* irq# "N:" */ if (retval != 1) break; + if (strncmp(buf, "NMI", strlen("NMI")) == 0) + this_row_is_nmi = 1; + /* read the count per cpu */ for (column = 0; column < topo.num_cpus; ++column) { int cpu_number, irq_count; retval = fscanf(fp, " %d", &irq_count); + if (retval != 1) break; cpu_number = irq_column_2_cpu[column]; irqs_per_cpu[cpu_number] += irq_count; - + if (this_row_is_nmi) + nmi_per_cpu[cpu_number] += irq_count; } - while (getc(fp) != '\n') ; /* flush interrupt description */ } @@ -5912,7 +6108,9 @@ int snapshot_sys_lpi_us(void) */ int snapshot_proc_sysfs_files(void) { - if (DO_BIC(BIC_IRQ)) + gettimeofday(&procsysfs_tv_begin, (struct timezone *)NULL); + + if (DO_BIC(BIC_IRQ) || DO_BIC(BIC_NMI)) if (snapshot_proc_interrupts()) return 1; @@ -7043,6 +7241,11 @@ void rapl_probe_intel(void) else rapl_dram_energy_units = rapl_energy_units; + if (platform->has_fixed_rapl_psys_unit) + rapl_psys_energy_units = 1.0; + else + rapl_psys_energy_units = rapl_energy_units; + time_unit = msr >> 16 & 0xF; if (time_unit == 0) time_unit = 0xA; @@ -8233,6 +8436,7 @@ void process_cpuid() aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1; BIC_PRESENT(BIC_IRQ); + BIC_PRESENT(BIC_NMI); BIC_PRESENT(BIC_TSC_MHz); } @@ -8292,6 +8496,33 @@ int dir_filter(const struct dirent *dirp) return 0; } +char *possible_file = "/sys/devices/system/cpu/possible"; +char possible_buf[1024]; + +int initialize_cpu_possible_set(void) +{ + FILE *fp; + + fp = fopen(possible_file, "r"); + if (!fp) { + warn("open %s", possible_file); + return -1; + } + if (fread(possible_buf, sizeof(char), 1024, fp) == 0) { + warn("read %s", possible_file); + goto err; + } + if (parse_cpu_str(possible_buf, cpu_possible_set, cpu_possible_setsize)) { + warnx("%s: cpu str malformat %s\n", possible_file, cpu_effective_str); + goto err; + } + return 0; + +err: + fclose(fp); + return -1; +} + void topology_probe(bool startup) { int i; @@ -8324,6 +8555,16 @@ void topology_probe(bool startup) for_all_proc_cpus(mark_cpu_present); /* + * Allocate and initialize cpu_possible_set + */ + cpu_possible_set = CPU_ALLOC((topo.max_cpu_num + 1)); + if (cpu_possible_set == NULL) + err(3, "CPU_ALLOC"); + cpu_possible_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); + CPU_ZERO_S(cpu_possible_setsize, cpu_possible_set); + initialize_cpu_possible_set(); + + /* * Allocate and initialize cpu_effective_set */ cpu_effective_set = CPU_ALLOC((topo.max_cpu_num + 1)); @@ -8583,7 +8824,11 @@ void allocate_irq_buffers(void) irqs_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int)); if (irqs_per_cpu == NULL) - err(-1, "calloc %d", topo.max_cpu_num + 1); + err(-1, "calloc %d IRQ", topo.max_cpu_num + 1); + + nmi_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int)); + if (nmi_per_cpu == NULL) + err(-1, "calloc %d NMI", topo.max_cpu_num + 1); } int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p) @@ -8854,49 +9099,36 @@ int parse_telem_info_file(int fd_dir, const char *info_filename, const char *for struct pmt_mmio *pmt_mmio_open(unsigned int target_guid) { - DIR *dirp; - struct dirent *entry; + struct pmt_diriter_t pmt_iter; + const struct dirent *entry; struct stat st; - unsigned int telem_idx; int fd_telem_dir, fd_pmt; unsigned long guid, size, offset; size_t mmap_size; void *mmio; - struct pmt_mmio *ret = NULL; + struct pmt_mmio *head = NULL, *last = NULL; + struct pmt_mmio *new_pmt = NULL; if (stat(SYSFS_TELEM_PATH, &st) == -1) return NULL; - dirp = opendir(SYSFS_TELEM_PATH); - if (dirp == NULL) + pmt_diriter_init(&pmt_iter); + entry = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); + if (!entry) { + pmt_diriter_remove(&pmt_iter); return NULL; + } - for (;;) { - entry = readdir(dirp); - - if (entry == NULL) - break; - - if (strcmp(entry->d_name, ".") == 0) - continue; - - if (strcmp(entry->d_name, "..") == 0) - continue; - - if (sscanf(entry->d_name, "telem%u", &telem_idx) != 1) - continue; - - if (fstatat(dirfd(dirp), entry->d_name, &st, 0) == -1) { + for ( ; entry != NULL; entry = pmt_diriter_next(&pmt_iter)) { + if (fstatat(dirfd(pmt_iter.dir), entry->d_name, &st, 0) == -1) break; - } if (!S_ISDIR(st.st_mode)) continue; - fd_telem_dir = openat(dirfd(dirp), entry->d_name, O_RDONLY); - if (fd_telem_dir == -1) { + fd_telem_dir = openat(dirfd(pmt_iter.dir), entry->d_name, O_RDONLY); + if (fd_telem_dir == -1) break; - } if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) { close(fd_telem_dir); @@ -8924,38 +9156,54 @@ struct pmt_mmio *pmt_mmio_open(unsigned int target_guid) if (fd_pmt == -1) goto loop_cleanup_and_break; - mmap_size = (size + 0x1000UL) & (~0x1000UL); + mmap_size = ROUND_UP_TO_PAGE_SIZE(size); mmio = mmap(0, mmap_size, PROT_READ, MAP_SHARED, fd_pmt, 0); if (mmio != MAP_FAILED) { - if (debug) fprintf(stderr, "%s: 0x%lx mmaped at: %p\n", __func__, guid, mmio); - ret = calloc(1, sizeof(*ret)); + new_pmt = calloc(1, sizeof(*new_pmt)); - if (!ret) { + if (!new_pmt) { fprintf(stderr, "%s: Failed to allocate pmt_mmio\n", __func__); exit(1); } - ret->guid = guid; - ret->mmio_base = mmio; - ret->pmt_offset = offset; - ret->size = size; + /* + * Create linked list of mmaped regions, + * but preserve the ordering from sysfs. + * Ordering is important for the user to + * use the seq=%u parameter when adding a counter. + */ + new_pmt->guid = guid; + new_pmt->mmio_base = mmio; + new_pmt->pmt_offset = offset; + new_pmt->size = size; + new_pmt->next = pmt_mmios; + + if (last) + last->next = new_pmt; + else + head = new_pmt; - ret->next = pmt_mmios; - pmt_mmios = ret; + last = new_pmt; } loop_cleanup_and_break: close(fd_pmt); close(fd_telem_dir); - break; } - closedir(dirp); + pmt_diriter_remove(&pmt_iter); - return ret; + /* + * If we found something, stick just + * created linked list to the front. + */ + if (head) + pmt_mmios = head; + + return head; } struct pmt_mmio *pmt_mmio_find(unsigned int guid) @@ -8992,7 +9240,7 @@ void *pmt_get_counter_pointer(struct pmt_mmio *pmmio, unsigned long counter_offs return ret; } -struct pmt_mmio *pmt_add_guid(unsigned int guid) +struct pmt_mmio *pmt_add_guid(unsigned int guid, unsigned int seq) { struct pmt_mmio *ret; @@ -9000,6 +9248,11 @@ struct pmt_mmio *pmt_add_guid(unsigned int guid) if (!ret) ret = pmt_mmio_open(guid); + while (ret && seq) { + ret = ret->next; + --seq; + } + return ret; } @@ -9046,7 +9299,7 @@ void pmt_counter_add_domain(struct pmt_counter *pcounter, unsigned long *pmmio, pcounter->domains[domain_id].pcounter = pmmio; } -int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, +int pmt_add_counter(unsigned int guid, unsigned int seq, const char *name, enum pmt_datatype type, unsigned int lsb, unsigned int msb, unsigned int offset, enum counter_scope scope, enum counter_format format, unsigned int domain_id, enum pmt_open_mode mode) { @@ -9066,10 +9319,10 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, exit(1); } - mmio = pmt_add_guid(guid); + mmio = pmt_add_guid(guid, seq); if (!mmio) { if (mode != PMT_OPEN_TRY) { - fprintf(stderr, "%s: failed to map PMT MMIO for guid %x\n", __func__, guid); + fprintf(stderr, "%s: failed to map PMT MMIO for guid %x, seq %u\n", __func__, guid, seq); exit(1); } @@ -9124,10 +9377,68 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, void pmt_init(void) { + int cpu_num; + unsigned long seq, offset, mod_num; + if (BIC_IS_ENABLED(BIC_Diec6)) { - pmt_add_counter(PMT_MTL_DC6_GUID, "Die%c6", PMT_TYPE_XTAL_TIME, PMT_COUNTER_MTL_DC6_LSB, - PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, SCOPE_PACKAGE, FORMAT_DELTA, - 0, PMT_OPEN_TRY); + pmt_add_counter(PMT_MTL_DC6_GUID, PMT_MTL_DC6_SEQ, "Die%c6", PMT_TYPE_XTAL_TIME, + PMT_COUNTER_MTL_DC6_LSB, PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, + SCOPE_PACKAGE, FORMAT_DELTA, 0, PMT_OPEN_TRY); + } + + if (BIC_IS_ENABLED(BIC_CPU_c1e)) { + seq = 0; + offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE; + mod_num = 0; /* Relative module number for current PMT file. */ + + /* Open the counter for each CPU. */ + for (cpu_num = 0; cpu_num < topo.max_cpu_num;) { + + if (cpu_is_not_allowed(cpu_num)) + goto next_loop_iter; + + /* + * Set the scope to CPU, even though CWF report the counter per module. + * CPUs inside the same module will read from the same location, instead of reporting zeros. + * + * CWF with newer firmware might require a PMT_TYPE_XTAL_TIME intead of PMT_TYPE_TCORE_CLOCK. + */ + pmt_add_counter(PMT_CWF_MC1E_GUID, seq, "CPU%c1e", PMT_TYPE_TCORE_CLOCK, + PMT_COUNTER_CWF_MC1E_LSB, PMT_COUNTER_CWF_MC1E_MSB, offset, SCOPE_CPU, + FORMAT_DELTA, cpu_num, PMT_OPEN_TRY); + + /* + * Rather complex logic for each time we go to the next loop iteration, + * so keep it as a label. + */ +next_loop_iter: + /* + * Advance the cpu number and check if we should also advance offset to + * the next counter inside the PMT file. + * + * On Clearwater Forest platform, the counter is reported per module, + * so open the same counter for all of the CPUs inside the module. + * That way, reported table show the correct value for all of the CPUs inside the module, + * instead of zeros. + */ + ++cpu_num; + if (cpu_num % PMT_COUNTER_CWF_CPUS_PER_MODULE == 0) { + offset += PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT; + ++mod_num; + } + + /* + * There are PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE in each PMT file. + * + * If that number is reached, seq must be incremented to advance to the next file in a sequence. + * Offset inside that file and a module counter has to be reset. + */ + if (mod_num == PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE) { + ++seq; + offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE; + mod_num = 0; + } + } } } @@ -9163,6 +9474,18 @@ void turbostat_init() } } +void affinitize_child(void) +{ + /* Prefer cpu_possible_set, if available */ + if (sched_setaffinity(0, cpu_possible_setsize, cpu_possible_set)) { + warn("sched_setaffinity cpu_possible_set"); + + /* Otherwise, allow child to run on same cpu set as turbostat */ + if (sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set)) + warn("sched_setaffinity cpu_allowed_set"); + } +} + int fork_it(char **argv) { pid_t child_pid; @@ -9178,6 +9501,7 @@ int fork_it(char **argv) child_pid = fork(); if (!child_pid) { /* child */ + affinitize_child(); execvp(argv[0], argv); err(errno, "exec %s", argv[0]); } else { @@ -9204,10 +9528,9 @@ int fork_it(char **argv) timersub(&tv_odd, &tv_even, &tv_delta); if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS)) fprintf(outf, "%s: Counter reset detected\n", progname); - else { - compute_average(EVEN_COUNTERS); - format_all_counters(EVEN_COUNTERS); - } + + compute_average(EVEN_COUNTERS); + format_all_counters(EVEN_COUNTERS); fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec / 1000000.0); @@ -9236,7 +9559,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2024.11.30 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2025.02.02 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -9561,7 +9884,7 @@ next: } if ((msr_num == 0) && (path == NULL) && (perf_device[0] == '\0' || perf_event[0] == '\0')) { - fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event ) required\n"); + fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event) required\n"); fail++; } @@ -9599,15 +9922,100 @@ bool starts_with(const char *str, const char *prefix) return strncmp(prefix, str, strlen(prefix)) == 0; } +int pmt_parse_from_path(const char *target_path, unsigned int *out_guid, unsigned int *out_seq) +{ + struct pmt_diriter_t pmt_iter; + const struct dirent *dirname; + struct stat stat, target_stat; + int fd_telem_dir = -1; + int fd_target_dir; + unsigned int seq = 0; + unsigned long guid, target_guid; + int ret = -1; + + fd_target_dir = open(target_path, O_RDONLY | O_DIRECTORY); + if (fd_target_dir == -1) { + return -1; + } + + if (fstat(fd_target_dir, &target_stat) == -1) { + fprintf(stderr, "%s: Failed to stat the target: %s", __func__, strerror(errno)); + exit(1); + } + + if (parse_telem_info_file(fd_target_dir, "guid", "%lx", &target_guid)) { + fprintf(stderr, "%s: Failed to parse the target guid file: %s", __func__, strerror(errno)); + exit(1); + } + + close(fd_target_dir); + + pmt_diriter_init(&pmt_iter); + + for (dirname = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); dirname != NULL; + dirname = pmt_diriter_next(&pmt_iter)) { + + fd_telem_dir = openat(dirfd(pmt_iter.dir), dirname->d_name, O_RDONLY | O_DIRECTORY); + if (fd_telem_dir == -1) + continue; + + if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) { + fprintf(stderr, "%s: Failed to parse the guid file: %s", __func__, strerror(errno)); + continue; + } + + if (fstat(fd_telem_dir, &stat) == -1) { + fprintf(stderr, "%s: Failed to stat %s directory: %s", __func__, + dirname->d_name, strerror(errno)); + continue; + } + + /* + * If reached the same directory as target, exit the loop. + * Seq has the correct value now. + */ + if (stat.st_dev == target_stat.st_dev && stat.st_ino == target_stat.st_ino) { + ret = 0; + break; + } + + /* + * If reached directory with the same guid, + * but it's not the target directory yet, + * increment seq and continue the search. + */ + if (guid == target_guid) + ++seq; + + close(fd_telem_dir); + fd_telem_dir = -1; + } + + pmt_diriter_remove(&pmt_iter); + + if (fd_telem_dir != -1) + close(fd_telem_dir); + + if (!ret) { + *out_guid = target_guid; + *out_seq = seq; + } + + return ret; +} + void parse_add_command_pmt(char *add_command) { char *name = NULL; char *type_name = NULL; char *format_name = NULL; + char *direct_path = NULL; + static const char direct_path_prefix[] = "path="; unsigned int offset; unsigned int lsb; unsigned int msb; unsigned int guid; + unsigned int seq = 0; /* By default, pick first file in a sequence with a given GUID. */ unsigned int domain_id; enum counter_scope scope = 0; enum pmt_datatype type = PMT_TYPE_RAW; @@ -9687,6 +10095,13 @@ void parse_add_command_pmt(char *add_command) goto next; } + if (sscanf(add_command, "seq=%x", &seq) == 1) + goto next; + + if (strncmp(add_command, direct_path_prefix, strlen(direct_path_prefix)) == 0) { + direct_path = add_command + strlen(direct_path_prefix); + goto next; + } next: add_command = strchr(add_command, ','); if (add_command) { @@ -9737,6 +10152,11 @@ next: has_type = true; } + if (strcmp("tcore_clock", type_name) == 0) { + type = PMT_TYPE_TCORE_CLOCK; + has_type = true; + } + if (!has_type) { printf("%s: invalid %s: %s\n", __func__, "type", type_name); exit(1); @@ -9758,8 +10178,24 @@ next: exit(1); } + if (direct_path && has_guid) { + printf("%s: path and guid+seq parameters are mutually exclusive\n" + "notice: passed guid=0x%x and path=%s\n", __func__, guid, direct_path); + exit(1); + } + + if (direct_path) { + if (pmt_parse_from_path(direct_path, &guid, &seq)) { + printf("%s: failed to parse PMT file from %s\n", __func__, direct_path); + exit(1); + } + + /* GUID was just infered from the direct path. */ + has_guid = true; + } + if (!has_guid) { - printf("%s: missing %s\n", __func__, "guid"); + printf("%s: missing %s\n", __func__, "guid or path"); exit(1); } @@ -9773,7 +10209,7 @@ next: exit(1); } - pmt_add_counter(guid, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED); + pmt_add_counter(guid, seq, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED); } void parse_add_command(char *add_command) @@ -9921,6 +10357,7 @@ void cmdline(int argc, char **argv) { "Dump", no_argument, 0, 'D' }, { "debug", no_argument, 0, 'd' }, /* internal, not documented */ { "enable", required_argument, 0, 'e' }, + { "force", no_argument, 0, 'f' }, { "interval", required_argument, 0, 'i' }, { "IPC", no_argument, 0, 'I' }, { "num_iterations", required_argument, 0, 'n' }, @@ -9981,6 +10418,9 @@ void cmdline(int argc, char **argv) /* --enable specified counter */ bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST); break; + case 'f': + force_load++; + break; case 'd': debug++; ENABLE_BIC(BIC_DISABLED_BY_DEFAULT); diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index f3e15e9efa76..7849405614b1 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -270,8 +270,16 @@ void bpf_obj_drop_impl(void *kptr, void *meta) __ksym; #define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL)) #define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL) -void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; -void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; +int bpf_list_push_front_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_front(head, node) bpf_list_push_front_impl(head, node, NULL, 0) + +int bpf_list_push_back_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_back(head, node) bpf_list_push_back_impl(head, node, NULL, 0) + struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ksym; struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym; struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, @@ -404,6 +412,17 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) return (const struct cpumask *)mask; } +/* + * Return true if task @p cannot migrate to a different CPU, false + * otherwise. + */ +static inline bool is_migration_disabled(const struct task_struct *p) +{ + if (bpf_core_field_exists(p->migration_disabled)) + return p->migration_disabled; + return false; +} + /* rcu */ void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; @@ -421,7 +440,7 @@ void bpf_rcu_read_unlock(void) __ksym; */ static inline s64 time_delta(u64 after, u64 before) { - return (s64)(after - before) > 0 ? : 0; + return (s64)(after - before) > 0 ? (s64)(after - before) : 0; } /** diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 347c1e7b37bd..8d731bd63988 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -401,6 +401,10 @@ struct cxl_test_gen_media gen_media = { .channel = 1, .rank = 30, }, + .component_id = { 0x3, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .cme_threshold_ev_flags = 3, + .cme_count = { 33, 0, 0 }, + .sub_type = 0x2, }, }; @@ -429,6 +433,11 @@ struct cxl_test_dram dram = { .bank_group = 5, .bank = 2, .column = {0xDE, 0xAD}, + .component_id = { 0x1, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .sub_channel = 8, + .cme_threshold_ev_flags = 2, + .cvme_count = { 14, 0, 0 }, + .sub_type = 0x5, }, }; @@ -456,7 +465,10 @@ struct cxl_test_mem_module mem_module = { .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, - } + }, + /* .validity_flags = <set below> */ + .component_id = { 0x2, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .event_sub_type = 0x3, }, }; @@ -478,13 +490,18 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds, static void cxl_mock_add_event_logs(struct mock_event_store *mes) { - put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, + put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK | + CXL_GMER_VALID_COMPONENT | CXL_GMER_VALID_COMPONENT_ID_FORMAT, &gen_media.rec.media_hdr.validity_flags); put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | - CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, + CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN | CXL_DER_VALID_SUB_CHANNEL | + CXL_DER_VALID_COMPONENT | CXL_DER_VALID_COMPONENT_ID_FORMAT, &dram.rec.media_hdr.validity_flags); + put_unaligned_le16(CXL_MMER_VALID_COMPONENT | CXL_MMER_VALID_COMPONENT_ID_FORMAT, + &mem_module.rec.validity_flags); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); mes_add_event(mes, CXL_EVENT_TYPE_INFO, (struct cxl_event_record_raw *)&gen_media); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 450c7566c33f..af2594e4f35d 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -228,16 +228,16 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL"); -int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +int __wrap_cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - if (ops && ops->is_mock_dev(dev)) + if (ops && ops->is_mock_dev(cxlds->dev)) rc = 0; else - rc = cxl_dvsec_rr_decode(dev, port, info); + rc = cxl_dvsec_rr_decode(cxlds, info); put_cxl_mock_ops(index); return rc; diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c index 3729fbfd3084..80b153d3ddec 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c @@ -542,8 +542,12 @@ static void detach_program(struct bpf_flow *skel, int prog_fd) static int set_port_drop(int pf, bool multi_port) { + char dst_port[16]; + + snprintf(dst_port, sizeof(dst_port), "%d", CFG_PORT_INNER); + SYS(fail, "tc qdisc add dev lo ingress"); - SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s", + SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s %s %s", "dev lo", "parent FFFF:", "protocol", pf == PF_INET6 ? "ipv6" : "ip", @@ -551,6 +555,7 @@ static int set_port_drop(int pf, bool multi_port) "flower", "ip_proto udp", "src_port", multi_port ? "8-10" : "9", + "dst_port", dst_port, "action drop"); return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index f8953455db29..1e3e4392dcca 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -111,31 +111,35 @@ out: static void test_sockmap_vsock_delete_on_close(void) { - int err, c, p, map; - const int zero = 0; - - err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); - if (!ASSERT_OK(err, "create_pair(AF_VSOCK)")) - return; + int map, c, p, err, zero = 0; map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); - if (!ASSERT_GE(map, 0, "bpf_map_create")) { - close(c); - goto out; - } + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; - err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); - close(c); - if (!ASSERT_OK(err, "bpf_map_update")) - goto out; + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; + + if (xbpf_map_update_elem(map, &zero, &c, BPF_NOEXIST)) + goto close_socks; + + xclose(c); + xclose(p); + + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; - err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); ASSERT_OK(err, "after close(), bpf_map_update"); -out: - close(p); - close(map); +close_socks: + xclose(c); + xclose(p); +close_map: + xclose(map); } static void test_skmsg_helpers(enum bpf_map_type map_type) @@ -1010,6 +1014,34 @@ destroy: test_sockmap_pass_prog__destroy(skel); } +static void test_sockmap_vsock_unconnected(void) +{ + struct sockaddr_storage addr; + int map, s, zero = 0; + socklen_t alen; + + map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), + sizeof(int), 1, NULL); + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; + + s = xsocket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) + goto close_map; + + /* Fail connect(), but trigger transport assignment. */ + init_addr_loopback(AF_VSOCK, &addr, &alen); + if (!ASSERT_ERR(connect(s, sockaddr(&addr), alen), "connect")) + goto close_sock; + + ASSERT_ERR(bpf_map_update_elem(map, &zero, &s, BPF_ANY), "map_update"); + +close_sock: + xclose(s); +close_map: + xclose(map); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1074,4 +1106,6 @@ void test_sockmap_basic(void) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH); if (test__start_subtest("sockmap skb_verdict vsock poll")) test_sockmap_skb_verdict_vsock_poll(); + if (test__start_subtest("sockmap vsock unconnected")) + test_sockmap_vsock_unconnected(); } diff --git a/tools/testing/selftests/bpf/progs/find_vma.c b/tools/testing/selftests/bpf/progs/find_vma.c index 38034fb82530..02b82774469c 100644 --- a/tools/testing/selftests/bpf/progs/find_vma.c +++ b/tools/testing/selftests/bpf/progs/find_vma.c @@ -25,7 +25,7 @@ static long check_vma(struct task_struct *task, struct vm_area_struct *vma, { if (vma->vm_file) bpf_probe_read_kernel_str(d_iname, DNAME_INLINE_LEN - 1, - vma->vm_file->f_path.dentry->d_iname); + vma->vm_file->f_path.dentry->d_shortname.string); /* check for VM_EXEC */ if (vma->vm_flags & VM_EXEC) diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh index 3f45512fb512..7406c24be1ac 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # Test the special cpuset v1 hotplug case where a cpuset become empty of diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index ca8a7edff3dd..319aaa004c40 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -252,6 +252,7 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True): try: # this targets queue 4, which doesn't exist ntuple2 = ethtool_create(cfg, "-N", flow) + defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}") except CmdExitFailure: pass else: @@ -259,7 +260,13 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True): # change the table to target queues 0 and 2 ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 1 0") # ntuple rule therefore targets queues 1 and 3 - ntuple2 = ethtool_create(cfg, "-N", flow) + try: + ntuple2 = ethtool_create(cfg, "-N", flow) + except CmdExitFailure: + ksft_pr("Driver does not support rss + queue offset") + return + + defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}") # should replace existing filter ksft_eq(ntuple, ntuple2) _send_traffic_check(cfg, port, ctx_ref, { 'target': (1, 3), diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 384cfa3d38a6..92c2f0376c08 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -142,7 +142,7 @@ function pre_ethtool { } function check_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 local -n expected=$2 local last=$3 @@ -212,7 +212,7 @@ function check_tables { } function print_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 read -a have < $path tree $NSIM_DEV_DFS/ @@ -641,7 +641,7 @@ for port in 0 1; do NSIM_NETDEV=`get_netdev_name old_netdevs` ip link set dev $NSIM_NETDEV up - echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error msg="1 - create VxLANs v6" exp0=( 0 0 0 0 ) @@ -663,7 +663,7 @@ for port in 0 1; do new_geneve gnv0 20000 msg="2 - destroy GENEVE" - echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error exp1=( `mke 20000 2` 0 0 0 ) del_dev gnv0 @@ -764,7 +764,7 @@ for port in 0 1; do msg="create VxLANs v4" new_vxlan vxlan0 10000 $NSIM_NETDEV - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes down" @@ -775,7 +775,7 @@ for port in 0 1; do fi check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes up again" @@ -789,7 +789,7 @@ for port in 0 1; do del_dev vxlan0 check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="destroy NIC" @@ -896,7 +896,7 @@ msg="vacate VxLAN in overflow table" exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) del_dev vxlan2 -echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset +echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="tunnels destroyed 2" diff --git a/tools/testing/selftests/exec/check-exec.c b/tools/testing/selftests/exec/check-exec.c index 4d3f4525e1e1..55bce47e56b7 100644 --- a/tools/testing/selftests/exec/check-exec.c +++ b/tools/testing/selftests/exec/check-exec.c @@ -22,6 +22,7 @@ #include <sys/prctl.h> #include <sys/socket.h> #include <sys/stat.h> +#include <sys/syscall.h> #include <sys/sysmacros.h> #include <unistd.h> @@ -31,6 +32,12 @@ #include "../kselftest_harness.h" +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + static void drop_privileges(struct __test_metadata *const _metadata) { const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED; @@ -219,8 +226,8 @@ static void test_exec_fd(struct __test_metadata *_metadata, const int fd, * test framework as an error. With AT_EXECVE_CHECK, we only check a * potential successful execution. */ - access_ret = - execveat(fd, "", argv, NULL, AT_EMPTY_PATH | AT_EXECVE_CHECK); + access_ret = sys_execveat(fd, "", argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); access_errno = errno; if (err_code) { EXPECT_EQ(-1, access_ret); diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index 8eb6aa606a0d..46d289611ce8 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -383,6 +383,10 @@ static void test_statmount_mnt_point(void) return; } + if (!(sm->mask & STATMOUNT_MNT_POINT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_POINT in mask\n"); + return; + } if (strcmp(sm->str + sm->mnt_point, "/") != 0) { ksft_test_result_fail("unexpected mount point: '%s' != '/'\n", sm->str + sm->mnt_point); @@ -408,6 +412,10 @@ static void test_statmount_mnt_root(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_MNT_ROOT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_ROOT in mask\n"); + return; + } mnt_root = sm->str + sm->mnt_root; last_root = strrchr(mnt_root, '/'); if (last_root) @@ -437,6 +445,10 @@ static void test_statmount_fs_type(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_FS_TYPE)) { + ksft_test_result_fail("missing STATMOUNT_FS_TYPE in mask\n"); + return; + } fs_type = sm->str + sm->fs_type; for (s = known_fs; s != NULL; s++) { if (strcmp(fs_type, *s) == 0) @@ -464,6 +476,11 @@ static void test_statmount_mnt_opts(void) return; } + if (!(sm->mask & STATMOUNT_MNT_BASIC)) { + ksft_test_result_fail("missing STATMOUNT_MNT_BASIC in mask\n"); + return; + } + while (getline(&line, &len, f_mountinfo) != -1) { int i; char *p, *p2; @@ -514,7 +531,10 @@ static void test_statmount_mnt_opts(void) if (p2) *p2 = '\0'; - statmount_opts = sm->str + sm->mnt_opts; + if (sm->mask & STATMOUNT_MNT_OPTS) + statmount_opts = sm->str + sm->mnt_opts; + else + statmount_opts = ""; if (strcmp(statmount_opts, p) != 0) ksft_test_result_fail( "unexpected mount options: '%s' != '%s'\n", diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 6fb66a687f17..bbc29ed9c60a 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -46,12 +46,6 @@ remove_chip() { rmdir $CONFIGFS_DIR/$CHIP || fail "Unable to remove the chip" } -configfs_cleanup() { - for CHIP in `ls $CONFIGFS_DIR/`; do - remove_chip $CHIP - done -} - create_chip() { local CHIP=$1 @@ -105,6 +99,13 @@ disable_chip() { echo 0 > $CONFIGFS_DIR/$CHIP/live || fail "Unable to disable the chip" } +configfs_cleanup() { + for CHIP in `ls $CONFIGFS_DIR/`; do + disable_chip $CHIP + remove_chip $CHIP + done +} + configfs_chip_name() { local CHIP=$1 local BANK=$2 @@ -181,6 +182,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/bank/chip_name` || fail "chip_name doesn't work" +disable_chip chip remove_chip chip echo "1.2. chip_name returns 'none' if the chip is still pending" @@ -195,6 +197,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/dev_name` || fail "dev_name doesn't work" +disable_chip chip remove_chip chip echo "2. Creating and configuring simulated chips" @@ -204,6 +207,7 @@ create_chip chip create_bank chip bank enable_chip chip test "`get_chip_num_lines chip bank`" = "1" || fail "default number of lines is not 1" +disable_chip chip remove_chip chip echo "2.2. Number of lines can be specified" @@ -212,6 +216,7 @@ create_bank chip bank set_num_lines chip bank 16 enable_chip chip test "`get_chip_num_lines chip bank`" = "16" || fail "number of lines is not 16" +disable_chip chip remove_chip chip echo "2.3. Label can be set" @@ -220,6 +225,7 @@ create_bank chip bank set_label chip bank foobar enable_chip chip test "`get_chip_label chip bank`" = "foobar" || fail "label is incorrect" +disable_chip chip remove_chip chip echo "2.4. Label can be left empty" @@ -227,6 +233,7 @@ create_chip chip create_bank chip bank enable_chip chip test -z "`cat $CONFIGFS_DIR/chip/bank/label`" || fail "label is not empty" +disable_chip chip remove_chip chip echo "2.5. Line names can be configured" @@ -238,6 +245,7 @@ set_line_name chip bank 2 bar enable_chip chip test "`get_line_name chip bank 0`" = "foo" || fail "line name is incorrect" test "`get_line_name chip bank 2`" = "bar" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.6. Line config can remain unused if offset is greater than number of lines" @@ -248,6 +256,7 @@ set_line_name chip bank 5 foobar enable_chip chip test "`get_line_name chip bank 0`" = "" || fail "line name is incorrect" test "`get_line_name chip bank 1`" = "" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.7. Line configfs directory names are sanitized" @@ -267,6 +276,7 @@ for CHIP in $CHIPS; do enable_chip $CHIP done for CHIP in $CHIPS; do + disable_chip $CHIP remove_chip $CHIP done @@ -278,6 +288,7 @@ echo foobar > $CONFIGFS_DIR/chip/bank/label 2> /dev/null && \ fail "Setting label of a live chip should fail" echo 8 > $CONFIGFS_DIR/chip/bank/num_lines 2> /dev/null && \ fail "Setting number of lines of a live chip should fail" +disable_chip chip remove_chip chip echo "2.10. Can't create line items when chip is live" @@ -285,6 +296,7 @@ create_chip chip create_bank chip bank enable_chip chip mkdir $CONFIGFS_DIR/chip/bank/line0 2> /dev/null && fail "Creating line item should fail" +disable_chip chip remove_chip chip echo "2.11. Probe errors are propagated to user-space" @@ -316,6 +328,7 @@ mkdir -p $CONFIGFS_DIR/chip/bank/line4/hog enable_chip chip $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 4 2> /dev/null && \ fail "Setting the value of a hogged line shouldn't succeed" +disable_chip chip remove_chip chip echo "3. Controlling simulated chips" @@ -331,6 +344,7 @@ test "$?" = "1" || fail "pull set incorrectly" sysfs_set_pull chip bank 0 pull-down $BASE_DIR/gpio-mockup-cdev /dev/`configfs_chip_name chip bank` 1 test "$?" = "0" || fail "pull set incorrectly" +disable_chip chip remove_chip chip echo "3.2. Pull can be read from sysfs" @@ -344,6 +358,7 @@ SYSFS_PATH=/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull test `cat $SYSFS_PATH` = "pull-down" || fail "reading the pull failed" sysfs_set_pull chip bank 0 pull-up test `cat $SYSFS_PATH` = "pull-up" || fail "reading the pull failed" +disable_chip chip remove_chip chip echo "3.3. Incorrect input in sysfs is rejected" @@ -355,6 +370,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull" echo foobar > $SYSFS_PATH 2> /dev/null && fail "invalid input not detected" +disable_chip chip remove_chip chip echo "3.4. Can't write to value" @@ -365,6 +381,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" echo 1 > $SYSFS_PATH 2> /dev/null && fail "writing to 'value' succeeded unexpectedly" +disable_chip chip remove_chip chip echo "4. Simulated GPIO chips are functional" @@ -382,6 +399,7 @@ $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 0 & sleep 0.1 # FIXME Any better way? test `cat $SYSFS_PATH` = "1" || fail "incorrect value read from sysfs" kill $! +disable_chip chip remove_chip chip echo "4.2. Bias settings work correctly" @@ -394,6 +412,7 @@ CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" +disable_chip chip remove_chip chip echo "GPIO $MODULE test PASS" diff --git a/tools/testing/selftests/kvm/s390/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c index e32dd59703a0..85cc8c18d6e7 100644 --- a/tools/testing/selftests/kvm/s390/cmma_test.c +++ b/tools/testing/selftests/kvm/s390/cmma_test.c @@ -444,7 +444,7 @@ static void assert_no_pages_cmma_dirty(struct kvm_vm *vm) ); } -static void test_get_inital_dirty(void) +static void test_get_initial_dirty(void) { struct kvm_vm *vm = create_vm_two_memslots(); struct kvm_vcpu *vcpu; @@ -651,7 +651,7 @@ struct testdef { } testlist[] = { { "migration mode and dirty tracking", test_migration_mode }, { "GET_CMMA_BITS: basic calls", test_get_cmma_basic }, - { "GET_CMMA_BITS: all pages are dirty initally", test_get_inital_dirty }, + { "GET_CMMA_BITS: all pages are dirty initially", test_get_initial_dirty }, { "GET_CMMA_BITS: holes are skipped", test_get_skip_holes }, }; diff --git a/tools/testing/selftests/kvm/s390/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c index 135ee22856cf..d265b34c54be 100644 --- a/tools/testing/selftests/kvm/s390/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c @@ -88,10 +88,6 @@ asm("test_skey_asm:\n" " ahi %r0,1\n" " st %r1,0(%r5,%r6)\n" - " iske %r1,%r6\n" - " ahi %r0,1\n" - " diag 0,0,0x44\n" - " sske %r1,%r6\n" " xgr %r1,%r1\n" " iske %r1,%r6\n" @@ -459,10 +455,14 @@ TEST_F(uc_kvm, uc_no_user_region) }; ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION, ®ion)); - ASSERT_EQ(EINVAL, errno); + ASSERT_TRUE(errno == EEXIST || errno == EINVAL) + TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION", + strerror(errno), errno); ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION2, ®ion2)); - ASSERT_EQ(EINVAL, errno); + ASSERT_TRUE(errno == EEXIST || errno == EINVAL) + TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION2", + strerror(errno), errno); } TEST_F(uc_kvm, uc_map_unmap) @@ -596,7 +596,9 @@ TEST_F(uc_kvm, uc_skey) ASSERT_EQ(true, uc_handle_exit(self)); ASSERT_EQ(1, sync_regs->gprs[0]); - /* ISKE */ + /* SSKE + ISKE */ + sync_regs->gprs[1] = skeyvalue; + run->kvm_dirty_regs |= KVM_SYNC_GPRS; ASSERT_EQ(0, uc_run_once(self)); /* @@ -608,21 +610,11 @@ TEST_F(uc_kvm, uc_skey) TEST_ASSERT_EQ(0, sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)); TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason); TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode); - TEST_REQUIRE(sie_block->ipa != 0xb229); + TEST_REQUIRE(sie_block->ipa != 0xb22b); - /* ISKE contd. */ + /* SSKE + ISKE contd. */ ASSERT_EQ(false, uc_handle_exit(self)); ASSERT_EQ(2, sync_regs->gprs[0]); - /* assert initial skey (ACC = 0, R & C = 1) */ - ASSERT_EQ(0x06, sync_regs->gprs[1]); - uc_assert_diag44(self); - - /* SSKE + ISKE */ - sync_regs->gprs[1] = skeyvalue; - run->kvm_dirty_regs |= KVM_SYNC_GPRS; - ASSERT_EQ(0, uc_run_once(self)); - ASSERT_EQ(false, uc_handle_exit(self)); - ASSERT_EQ(3, sync_regs->gprs[0]); ASSERT_EQ(skeyvalue, sync_regs->gprs[1]); uc_assert_diag44(self); @@ -631,7 +623,7 @@ TEST_F(uc_kvm, uc_skey) run->kvm_dirty_regs |= KVM_SYNC_GPRS; ASSERT_EQ(0, uc_run_once(self)); ASSERT_EQ(false, uc_handle_exit(self)); - ASSERT_EQ(4, sync_regs->gprs[0]); + ASSERT_EQ(3, sync_regs->gprs[0]); /* assert R reset but rest of skey unchanged */ ASSERT_EQ(skeyvalue & 0xfa, sync_regs->gprs[1]); ASSERT_EQ(0, sync_regs->gprs[1] & 0x04); diff --git a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c index 4f5881d4ef66..4e920705681a 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c @@ -41,13 +41,19 @@ static bool smt_possible(void) return res; } -static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, - bool evmcs_expected) +static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) { + const bool has_irqchip = !vcpu || vcpu->vm->has_irqchip; + const struct kvm_cpuid2 *hv_cpuid_entries; int i; int nent_expected = 10; u32 test_val; + if (vcpu) + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); + else + hv_cpuid_entries = kvm_get_supported_hv_cpuid(); + TEST_ASSERT(hv_cpuid_entries->nent == nent_expected, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" " (returned %d)", @@ -80,12 +86,19 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, entry->eax, evmcs_expected ); break; + case 0x40000003: + TEST_ASSERT(has_irqchip || !(entry->edx & BIT(19)), + "\"Direct\" Synthetic Timers should require in-kernel APIC"); + break; case 0x40000004: test_val = entry->eax & (1UL << 18); TEST_ASSERT(!!test_val == !smt_possible(), "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); + + TEST_ASSERT(has_irqchip || !(entry->eax & BIT(10)), + "Cluster IPI (i.e. SEND_IPI) should require in-kernel APIC"); break; case 0x4000000A: TEST_ASSERT(entry->eax & (1UL << 19), @@ -109,9 +122,16 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, * entry->edx); */ } + + /* + * Note, the CPUID array returned by the system-scoped helper is a one- + * time allocation, i.e. must not be freed. + */ + if (vcpu) + free((void *)hv_cpuid_entries); } -void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +static void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; @@ -129,19 +149,20 @@ void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) int main(int argc, char *argv[]) { struct kvm_vm *vm; - const struct kvm_cpuid2 *hv_cpuid_entries; struct kvm_vcpu *vcpu; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); - vm = vm_create_with_one_vcpu(&vcpu, guest_code); + /* Test the vCPU ioctl without an in-kernel local APIC. */ + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); + test_hv_cpuid(vcpu, false); + kvm_vm_free(vm); /* Test vCPU ioctl version */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); test_hv_cpuid_e2big(vm, vcpu); - - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, false); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, false); if (!kvm_cpu_has(X86_FEATURE_VMX) || !kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { @@ -149,9 +170,7 @@ int main(int argc, char *argv[]) goto do_sys; } vcpu_enable_evmcs(vcpu); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, true); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, true); do_sys: /* Test system ioctl version */ @@ -161,9 +180,7 @@ do_sys: } test_hv_cpuid_e2big(vm, NULL); - - hv_cpuid_entries = kvm_get_supported_hv_cpuid(); - test_hv_cpuid(hv_cpuid_entries, kvm_cpu_has(X86_FEATURE_VMX)); + test_hv_cpuid(NULL, kvm_cpu_has(X86_FEATURE_VMX)); out: kvm_vm_free(vm); diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 2af86bd796ba..aa6f2c1cbec7 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -59,6 +59,12 @@ int open_tree(int dfd, const char *filename, unsigned int flags) } #endif +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + #ifndef RENAME_EXCHANGE #define RENAME_EXCHANGE (1 << 1) #endif @@ -2024,8 +2030,8 @@ static void test_check_exec(struct __test_metadata *const _metadata, int ret; char *const argv[] = { (char *)path, NULL }; - ret = execveat(AT_FDCWD, path, argv, NULL, - AT_EMPTY_PATH | AT_EXECVE_CHECK); + ret = sys_execveat(AT_FDCWD, path, argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); if (err) { EXPECT_EQ(-1, ret); EXPECT_EQ(errno, err); diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index e5d06fb40233..15601402dee6 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -306,7 +306,8 @@ function check_result { result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \ grep -e 'livepatch:' -e 'test_klp' | \ grep -v '\(tainting\|taints\) kernel' | \ - sed 's/^\[[ 0-9.]*\] //') + sed 's/^\[[ 0-9.]*\] //' | \ + sed 's/^\[[ ]*[CT][0-9]*\] //') if [[ "$expect" == "$result" ]] ; then echo "ok" diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 333c468c2699..da7e26668103 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -220,7 +220,7 @@ run_test() { if test_selected ${CATEGORY}; then # On memory constrainted systems some tests can fail to allocate hugepages. # perform some cleanup before the test for a higher success rate. - if [ ${CATEGORY} == "thp" ] | [ ${CATEGORY} == "hugetlb" ]; then + if [ ${CATEGORY} == "thp" -o ${CATEGORY} == "hugetlb" ]; then echo 3 > /proc/sys/vm/drop_caches sleep 2 echo 1 > /proc/sys/vm/compact_memory diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py index d10f420e4ef6..fd0d959914e4 100755 --- a/tools/testing/selftests/net/bpf_offload.py +++ b/tools/testing/selftests/net/bpf_offload.py @@ -215,12 +215,14 @@ def bpftool_map_list_wait(expected=0, n_retry=20, ns=""): raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None, - fail=True, include_stderr=False): + fail=True, include_stderr=False, dev_bind=None): args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name) if prog_type is not None: args += " type " + prog_type if dev is not None: args += " dev " + dev + elif dev_bind is not None: + args += " xdpmeta_dev " + dev_bind if len(maps): args += " map " + " map ".join(maps) @@ -980,6 +982,16 @@ try: rm("/sys/fs/bpf/offload") sim.wait_for_flush() + bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/devbound", + dev_bind=sim['ifname']) + devbound = bpf_pinned("/sys/fs/bpf/devbound") + start_test("Test dev-bound program in generic mode...") + ret, _, err = sim.set_xdp(devbound, "generic", fail=False, include_stderr=True) + fail(ret == 0, "devbound program in generic mode allowed") + check_extack(err, "Can't attach device-bound programs in generic mode.", args) + rm("/sys/fs/bpf/devbound") + sim.wait_for_flush() + start_test("Test XDP load failure...") sim.dfs["dev/bpf_bind_verifier_accept"] = 0 ret, _, err = bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/offload", diff --git a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh index 3885a2a91f7d..baed5e380dae 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh @@ -20,6 +20,7 @@ ALL_TESTS=" test_port_range_ipv4_tcp test_port_range_ipv6_udp test_port_range_ipv6_tcp + test_port_range_ipv4_udp_drop " NUM_NETIFS=4 @@ -194,6 +195,51 @@ test_port_range_ipv6_tcp() __test_port_range $proto $ip_proto $sip $dip $mode "$name" } +test_port_range_ipv4_udp_drop() +{ + local proto=ipv4 + local ip_proto=udp + local sip=192.0.2.1 + local dip=192.0.2.2 + local mode="-4" + local name="IPv4 UDP Drop" + local dmac=$(mac_get $h2) + local smac=$(mac_get $h1) + local sport_min=2000 + local sport_max=3000 + local sport_mid=$((sport_min + (sport_max - sport_min) / 2)) + local dport=5000 + + RET=0 + + tc filter add dev $swp1 ingress protocol $proto handle 101 pref 1 \ + flower src_ip $sip dst_ip $dip ip_proto $ip_proto \ + src_port $sport_min-$sport_max \ + dst_port $dport \ + action drop + + # Test ports outside range - should pass + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_min - 1)),dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_max + 1)),dp=$dport" + + # Test ports inside range - should be dropped + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_mid,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_max,dp=$dport" + + tc_check_packets "dev $swp1 ingress" 101 3 + check_err $? "Filter did not drop the expected number of packets" + + tc filter del dev $swp1 ingress protocol $proto pref 1 handle 101 flower + + log_test "Port range matching - $name" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index 18b9443454a9..bc6b6762baf3 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../../ diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 8e3fc05a5397..c76525fe2b84 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 414addef9a45..d240d02fa443 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1302,7 +1302,7 @@ again: return ret; if (cfg_truncate > 0) { - xdisconnect(fd); + shutdown(fd, SHUT_WR); } else if (--cfg_repeat > 0) { xdisconnect(fd); diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile index 2f1508abc826..3fd1da2ec07d 100644 --- a/tools/testing/selftests/net/openvswitch/Makefile +++ b/tools/testing/selftests/net/openvswitch/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := openvswitch.sh diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index e15c43b7359b..ef8b25a606d8 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -39,11 +39,13 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then # xfail tests that are known flaky with dbg config, not fixable. # still run them for coverage (and expect 100% pass without dbg). declare -ar xfail_list=( + "tcp_eor_no-coalesce-retrans.pkt" "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_slow_start_slow-start-after-win-update.pkt" "tcp_timestamping.*.pkt" "tcp_user_timeout_user-timeout-probe.pkt" "tcp_zerocopy_epoll_.*.pkt" - "tcp_tcp_info_tcp-info-*-limited.pkt" + "tcp_tcp_info_tcp-info-.*-limited.pkt" ) readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 3f2fca02fec5..36ff28af4b19 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -103,6 +103,19 @@ struct testcase testcases_v4[] = { .r_num_mss = 1, }, { + /* datalen <= MSS < gso_len: will fall back to no GSO */ + .tlen = CONST_MSS_V4, + .gso_len = CONST_MSS_V4 + 1, + .r_num_mss = 0, + .r_len_last = CONST_MSS_V4, + }, + { + /* MSS < datalen < gso_len: fail */ + .tlen = CONST_MSS_V4 + 1, + .gso_len = CONST_MSS_V4 + 2, + .tfail = true, + }, + { /* send a single MSS + 1B */ .tlen = CONST_MSS_V4 + 1, .gso_len = CONST_MSS_V4, @@ -206,6 +219,19 @@ struct testcase testcases_v6[] = { .r_num_mss = 1, }, { + /* datalen <= MSS < gso_len: will fall back to no GSO */ + .tlen = CONST_MSS_V6, + .gso_len = CONST_MSS_V6 + 1, + .r_num_mss = 0, + .r_len_last = CONST_MSS_V6, + }, + { + /* MSS < datalen < gso_len: fail */ + .tlen = CONST_MSS_V6 + 1, + .gso_len = CONST_MSS_V6 + 2, + .tfail = true + }, + { /* send a single MSS + 1B */ .tlen = CONST_MSS_V6 + 1, .gso_len = CONST_MSS_V6, diff --git a/tools/testing/selftests/riscv/vector/.gitignore b/tools/testing/selftests/riscv/vector/.gitignore index 9ae7964491d5..7d9c87cd0649 100644 --- a/tools/testing/selftests/riscv/vector/.gitignore +++ b/tools/testing/selftests/riscv/vector/.gitignore @@ -1,3 +1,4 @@ vstate_exec_nolibc vstate_prctl -v_initval_nolibc +v_initval +v_exec_initval_nolibc diff --git a/tools/testing/selftests/riscv/vector/Makefile b/tools/testing/selftests/riscv/vector/Makefile index bfff0ff4f3be..6f7497f4e7b3 100644 --- a/tools/testing/selftests/riscv/vector/Makefile +++ b/tools/testing/selftests/riscv/vector/Makefile @@ -2,18 +2,27 @@ # Copyright (C) 2021 ARM Limited # Originally tools/testing/arm64/abi/Makefile -TEST_GEN_PROGS := vstate_prctl v_initval_nolibc -TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc +TEST_GEN_PROGS := v_initval vstate_prctl +TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc v_exec_initval_nolibc include ../../lib.mk -$(OUTPUT)/vstate_prctl: vstate_prctl.c ../hwprobe/sys_hwprobe.S +$(OUTPUT)/sys_hwprobe.o: ../hwprobe/sys_hwprobe.S + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/v_helpers.o: v_helpers.c + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/vstate_prctl: vstate_prctl.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ $(OUTPUT)/vstate_exec_nolibc: vstate_exec_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc -$(OUTPUT)/v_initval_nolibc: v_initval_nolibc.c +$(OUTPUT)/v_initval: v_initval.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ + +$(OUTPUT)/v_exec_initval_nolibc: v_exec_initval_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc diff --git a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c new file mode 100644 index 000000000000..35c0812e32de --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Get values of vector registers as soon as the program starts to test if + * is properly cleaning the values before starting a new program. Vector + * registers are caller saved, so no function calls may happen before reading + * the values. To further ensure consistency, this file is compiled without + * libc and without auto-vectorization. + * + * To be "clean" all values must be either all ones or all zeroes. + */ + +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) + +int main(int argc, char **argv) +{ + char prev_value = 0, value; + unsigned long vl; + int first = 1; + + if (argc > 2 && strcmp(argv[2], "x")) + asm volatile ( + // 0 | zimm[10:0] | rs1 | 1 1 1 | rd |1010111| vsetvli + // vsetvli t4, x0, e8, m1, d1 + ".4byte 0b00000000000000000111111011010111\n\t" + "mv %[vl], t4\n\t" + : [vl] "=r" (vl) : : "t4" + ); + else + asm volatile ( + ".option push\n\t" + ".option arch, +v\n\t" + "vsetvli %[vl], x0, e8, m1, ta, ma\n\t" + ".option pop\n\t" + : [vl] "=r" (vl) + ); + +#define CHECK_VECTOR_REGISTER(register) ({ \ + for (int i = 0; i < vl; i++) { \ + asm volatile ( \ + ".option push\n\t" \ + ".option arch, +v\n\t" \ + "vmv.x.s %0, " __stringify(register) "\n\t" \ + "vsrl.vi " __stringify(register) ", " __stringify(register) ", 8\n\t" \ + ".option pop\n\t" \ + : "=r" (value)); \ + if (first) { \ + first = 0; \ + } else if (value != prev_value || !(value == 0x00 || value == 0xff)) { \ + printf("Register " __stringify(register) \ + " values not clean! value: %u\n", value); \ + exit(-1); \ + } \ + prev_value = value; \ + } \ +}) + + CHECK_VECTOR_REGISTER(v0); + CHECK_VECTOR_REGISTER(v1); + CHECK_VECTOR_REGISTER(v2); + CHECK_VECTOR_REGISTER(v3); + CHECK_VECTOR_REGISTER(v4); + CHECK_VECTOR_REGISTER(v5); + CHECK_VECTOR_REGISTER(v6); + CHECK_VECTOR_REGISTER(v7); + CHECK_VECTOR_REGISTER(v8); + CHECK_VECTOR_REGISTER(v9); + CHECK_VECTOR_REGISTER(v10); + CHECK_VECTOR_REGISTER(v11); + CHECK_VECTOR_REGISTER(v12); + CHECK_VECTOR_REGISTER(v13); + CHECK_VECTOR_REGISTER(v14); + CHECK_VECTOR_REGISTER(v15); + CHECK_VECTOR_REGISTER(v16); + CHECK_VECTOR_REGISTER(v17); + CHECK_VECTOR_REGISTER(v18); + CHECK_VECTOR_REGISTER(v19); + CHECK_VECTOR_REGISTER(v20); + CHECK_VECTOR_REGISTER(v21); + CHECK_VECTOR_REGISTER(v22); + CHECK_VECTOR_REGISTER(v23); + CHECK_VECTOR_REGISTER(v24); + CHECK_VECTOR_REGISTER(v25); + CHECK_VECTOR_REGISTER(v26); + CHECK_VECTOR_REGISTER(v27); + CHECK_VECTOR_REGISTER(v28); + CHECK_VECTOR_REGISTER(v29); + CHECK_VECTOR_REGISTER(v30); + CHECK_VECTOR_REGISTER(v31); + +#undef CHECK_VECTOR_REGISTER + + return 0; +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.c b/tools/testing/selftests/riscv/vector/v_helpers.c new file mode 100644 index 000000000000..01a8799dcb78 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../hwprobe/hwprobe.h" +#include <asm/vendor/thead.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/wait.h> + +bool is_xtheadvector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR; +} + +bool is_vector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_EXT_ZVE32X; +} + +int launch_test(char *next_program, int test_inherit, int xtheadvector) +{ + char *exec_argv[4], *exec_envp[1]; + int rc, pid, status; + + pid = fork(); + if (pid < 0) { + printf("fork failed %d", pid); + return -1; + } + + if (!pid) { + exec_argv[0] = next_program; + exec_argv[1] = test_inherit != 0 ? "x" : NULL; + exec_argv[2] = xtheadvector != 0 ? "x" : NULL; + exec_argv[3] = NULL; + exec_envp[0] = NULL; + /* launch the program again to check inherit */ + rc = execve(next_program, exec_argv, exec_envp); + if (rc) { + perror("execve"); + printf("child execve failed %d\n", rc); + exit(-1); + } + } + + rc = waitpid(-1, &status, 0); + if (rc < 0) { + printf("waitpid failed\n"); + return -3; + } + + if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || + WIFSIGNALED(status)) { + printf("child exited abnormally\n"); + return -4; + } + + return WEXITSTATUS(status); +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.h b/tools/testing/selftests/riscv/vector/v_helpers.h new file mode 100644 index 000000000000..763cddfe26da --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include <stdbool.h> + +bool is_xtheadvector_supported(void); + +bool is_vector_supported(void); + +int launch_test(char *next_program, int test_inherit, int xtheadvector); diff --git a/tools/testing/selftests/riscv/vector/v_initval.c b/tools/testing/selftests/riscv/vector/v_initval.c new file mode 100644 index 000000000000..be9e1d18ad29 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_initval.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest_harness.h" +#include "v_helpers.h" + +#define NEXT_PROGRAM "./v_exec_initval_nolibc" + +TEST(v_initval) +{ + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + ASSERT_EQ(0, launch_test(NEXT_PROGRAM, 0, xtheadvector)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c deleted file mode 100644 index 6174ffe016dc..000000000000 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include "../../kselftest.h" -#define MAX_VSIZE (8192 * 32) - -void dump(char *ptr, int size) -{ - int i = 0; - - for (i = 0; i < size; i++) { - if (i != 0) { - if (i % 16 == 0) - printf("\n"); - else if (i % 8 == 0) - printf(" "); - } - printf("%02x ", ptr[i]); - } - printf("\n"); -} - -int main(void) -{ - int i; - unsigned long vl; - char *datap, *tmp; - - ksft_set_plan(1); - - datap = malloc(MAX_VSIZE); - if (!datap) { - ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); - exit(-1); - } - - tmp = datap; - asm volatile ( - ".option push\n\t" - ".option arch, +v\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%2)\n\t" - "add %1, %2, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl), "=r" (tmp) : "r" (datap) : "memory"); - - ksft_print_msg("vl = %lu\n", vl); - - if (datap[0] != 0x00 && datap[0] != 0xff) { - ksft_test_result_fail("v-regesters are not properly initialized\n"); - dump(datap, vl * 4); - exit(-1); - } - - for (i = 1; i < vl * 4; i++) { - if (datap[i] != datap[0]) { - ksft_test_result_fail("detect stale values on v-regesters\n"); - dump(datap, vl * 4); - exit(-2); - } - } - - free(datap); - - ksft_test_result_pass("tests for v_initval_nolibc pass\n"); - ksft_exit_pass(); - return 0; -} diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 1f9969bed235..7b7d6f21acb4 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -6,13 +6,16 @@ int main(int argc, char **argv) { - int rc, pid, status, test_inherit = 0; + int rc, pid, status, test_inherit = 0, xtheadvector = 0; long ctrl, ctrl_c; char *exec_argv[2], *exec_envp[2]; - if (argc > 1) + if (argc > 1 && strcmp(argv[1], "x")) test_inherit = 1; + if (argc > 2 && strcmp(argv[2], "x")) + xtheadvector = 1; + ctrl = my_syscall1(__NR_prctl, PR_RISCV_V_GET_CONTROL); if (ctrl < 0) { puts("PR_RISCV_V_GET_CONTROL is not supported\n"); @@ -53,11 +56,14 @@ int main(int argc, char **argv) puts("child's vstate_ctrl not equal to parent's\n"); exit(-1); } - asm volatile (".option push\n\t" - ".option arch, +v\n\t" - "vsetvli x0, x0, e32, m8, ta, ma\n\t" - ".option pop\n\t" - ); + if (xtheadvector) + asm volatile (".4byte 0x00007ed7"); + else + asm volatile (".option push\n\t" + ".option arch, +v\n\t" + "vsetvli x0, x0, e32, m8, ta, ma\n\t" + ".option pop\n\t" + ); exit(ctrl); } } diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 40b3bffcbb40..62fbb17a0556 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -3,181 +3,244 @@ #include <unistd.h> #include <errno.h> #include <sys/wait.h> +#include <sys/types.h> +#include <stdlib.h> -#include "../hwprobe/hwprobe.h" -#include "../../kselftest.h" +#include "../../kselftest_harness.h" +#include "v_helpers.h" #define NEXT_PROGRAM "./vstate_exec_nolibc" -static int launch_test(int test_inherit) -{ - char *exec_argv[3], *exec_envp[1]; - int rc, pid, status; - - pid = fork(); - if (pid < 0) { - ksft_test_result_fail("fork failed %d", pid); - return -1; - } - if (!pid) { - exec_argv[0] = NEXT_PROGRAM; - exec_argv[1] = test_inherit != 0 ? "x" : NULL; - exec_argv[2] = NULL; - exec_envp[0] = NULL; - /* launch the program again to check inherit */ - rc = execve(NEXT_PROGRAM, exec_argv, exec_envp); - if (rc) { - perror("execve"); - ksft_test_result_fail("child execve failed %d\n", rc); - exit(-1); - } - } - - rc = waitpid(-1, &status, 0); - if (rc < 0) { - ksft_test_result_fail("waitpid failed\n"); - return -3; - } - - if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || - WIFSIGNALED(status)) { - ksft_test_result_fail("child exited abnormally\n"); - return -4; - } - - return WEXITSTATUS(status); -} - -int test_and_compare_child(long provided, long expected, int inherit) +int test_and_compare_child(long provided, long expected, int inherit, int xtheadvector) { int rc; rc = prctl(PR_RISCV_V_SET_CONTROL, provided); if (rc != 0) { - ksft_test_result_fail("prctl with provided arg %lx failed with code %d\n", - provided, rc); + printf("prctl with provided arg %lx failed with code %d\n", + provided, rc); return -1; } - rc = launch_test(inherit); + rc = launch_test(NEXT_PROGRAM, inherit, xtheadvector); if (rc != expected) { - ksft_test_result_fail("Test failed, check %d != %ld\n", rc, - expected); + printf("Test failed, check %d != %ld\n", rc, expected); return -2; } return 0; } -#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 -#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 +#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 +#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 -int main(void) +TEST(get_control_no_v) { - struct riscv_hwprobe pair; - long flag, expected; long rc; - ksft_set_plan(1); + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); - pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; - rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); - if (rc < 0) { - ksft_test_result_fail("hwprobe() failed with %ld\n", rc); - return -1; - } + rc = prctl(PR_RISCV_V_GET_CONTROL); + EXPECT_EQ(-1, rc) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); +} - if (pair.key != RISCV_HWPROBE_KEY_IMA_EXT_0) { - ksft_test_result_fail("hwprobe cannot probe RISCV_HWPROBE_KEY_IMA_EXT_0\n"); - return -2; - } +TEST(set_control_no_v) +{ + long rc; - if (!(pair.value & RISCV_HWPROBE_EXT_ZVE32X)) { - rc = prctl(PR_RISCV_V_GET_CONTROL); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("GET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -3; - } - - rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("SET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -4; - } - - ksft_test_result_skip("Vector not supported\n"); - return 0; - } + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); + + rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); + EXPECT_EQ(-1, rc) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); +} + +TEST(vstate_on_current) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_ON; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != 0) { - ksft_test_result_fail("Enabling V for current should always success\n"); - return -5; - } + EXPECT_EQ(0, rc) TH_LOG("Enabling V for current should always succeed"); +} + +TEST(vstate_off_eperm) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_OFF; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != -1 || errno != EPERM) { - ksft_test_result_fail("Disabling current's V alive must fail with EPERM(%d)\n", - errno); - return -5; + EXPECT_EQ(EPERM, errno) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); + EXPECT_EQ(-1, rc) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); +} + +TEST(vstate_on_no_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); } /* Turn on next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0)) - return -6; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0, xtheadvector)); +} + +TEST(vstate_off_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 0)) - return -7; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 1, xtheadvector)); +} + +TEST(vstate_on_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + /* Turn on next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_on_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn on next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; - if (test_and_compare_child(flag, expected, 0)) - return -8; - if (test_and_compare_child(flag, expected, 1)) - return -9; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +TEST(vstate_off_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + /* Turn off next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_off_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; - if (test_and_compare_child(flag, expected, 0)) - return -10; - if (test_and_compare_child(flag, expected, 1)) - return -11; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_1) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); - /* arguments should fail with EINVAL */ rc = prctl(PR_RISCV_V_SET_CONTROL, 0xff0); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_2) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); rc = prctl(PR_RISCV_V_SET_CONTROL, 0x3); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } +/* arguments should fail with EINVAL */ +TEST(inval_set_control_3) +{ + int rc; - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); - ksft_test_result_pass("tests for riscv_v_vstate_ctrl pass\n"); - ksft_exit_pass(); - return 0; + rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); } + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/sched_ext/create_dsq.c b/tools/testing/selftests/sched_ext/create_dsq.c index fa946d9146d4..d67431f57ac6 100644 --- a/tools/testing/selftests/sched_ext/create_dsq.c +++ b/tools/testing/selftests/sched_ext/create_dsq.c @@ -14,11 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct create_dsq *skel; - skel = create_dsq__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = create_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(create_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c index e65d22f23f3b..b6d13496b24e 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_bogus_dsq_fail *skel; - skel = ddsp_bogus_dsq_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_bogus_dsq_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_bogus_dsq_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c index abafee587cd6..af9ce4ee8baa 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_vtimelocal_fail *skel; - skel = ddsp_vtimelocal_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_vtimelocal_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_vtimelocal_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index fbda6bf54671..c02b2aa6fc64 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,7 +43,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - if (p->nr_cpus_allowed == nr_cpus) + if (p->nr_cpus_allowed == nr_cpus && !is_migration_disabled(p)) target = bpf_get_prandom_u32() % nr_cpus; else target = scx_bpf_task_cpu(p); diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 0ff27e57fe43..e1f2ce4abfe6 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -15,6 +15,7 @@ static enum scx_test_status setup(void **ctx) skel = dsp_local_on__open(); SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); skel->rodata->nr_cpus = libbpf_num_possible_cpus(); SCX_FAIL_IF(dsp_local_on__load(skel), "Failed to load skel"); diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c index 73e679953e27..d3387ae03679 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_last_no_enq_fails *skel; - skel = enq_last_no_enq_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_last_no_enq_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_last_no_enq_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c index dd1350e5f002..a80e3a3b3698 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_select_cpu_fails *skel; - skel = enq_select_cpu_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_select_cpu_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_select_cpu_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index 31bcd06e21cd..9451782689de 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -23,6 +23,7 @@ static enum scx_test_status run(void *ctx) char buf[16]; skel = exit__open(); + SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; exit__load(skel); link = bpf_map__attach_struct_ops(skel->maps.exit_ops); diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index 87bf220b1bce..1c9ceb661c43 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -49,8 +49,10 @@ static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined) SCX_ASSERT(is_cpu_online()); - skel = hotplug__open_and_load(); - SCX_ASSERT(skel); + skel = hotplug__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(hotplug__load(skel), "Failed to load skel"); /* Testing the offline -> online path, so go offline before starting */ if (onlining) diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index 97d45f1e5597..eddf9e0e26e7 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -15,22 +15,6 @@ #define SCHED_EXT 7 -static struct init_enable_count * -open_load_prog(bool global) -{ - struct init_enable_count *skel; - - skel = init_enable_count__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); - - if (!global) - skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; - - SCX_BUG_ON(init_enable_count__load(skel), "Failed to load skel"); - - return skel; -} - static enum scx_test_status run_test(bool global) { struct init_enable_count *skel; @@ -40,7 +24,14 @@ static enum scx_test_status run_test(bool global) struct sched_param param = {}; pid_t pids[num_pre_forks]; - skel = open_load_prog(global); + skel = init_enable_count__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + + if (!global) + skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; + + SCX_FAIL_IF(init_enable_count__load(skel), "Failed to load skel"); /* * Fork a bunch of children before we attach the scheduler so that we @@ -159,7 +150,7 @@ static enum scx_test_status run(void *ctx) struct scx_test init_enable_count = { .name = "init_enable_count", - .description = "Verify we do the correct amount of counting of init, " + .description = "Verify we correctly count the occurrences of init, " "enable, etc callbacks.", .run = run, }; diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c index f38fc973c380..c6be50a9941d 100644 --- a/tools/testing/selftests/sched_ext/maximal.c +++ b/tools/testing/selftests/sched_ext/maximal.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct maximal *skel; - skel = maximal__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/maybe_null.c b/tools/testing/selftests/sched_ext/maybe_null.c index 31cfafb0cf65..aacf0c58ca4f 100644 --- a/tools/testing/selftests/sched_ext/maybe_null.c +++ b/tools/testing/selftests/sched_ext/maybe_null.c @@ -43,7 +43,7 @@ static enum scx_test_status run(void *ctx) struct scx_test maybe_null = { .name = "maybe_null", - .description = "Verify if PTR_MAYBE_NULL work for .dispatch", + .description = "Verify if PTR_MAYBE_NULL works for .dispatch", .run = run, }; REGISTER_SCX_TEST(&maybe_null) diff --git a/tools/testing/selftests/sched_ext/minimal.c b/tools/testing/selftests/sched_ext/minimal.c index 6c5db8ebbf8a..89f7261757ff 100644 --- a/tools/testing/selftests/sched_ext/minimal.c +++ b/tools/testing/selftests/sched_ext/minimal.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct minimal *skel; - skel = minimal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = minimal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(minimal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c index 3cd57ef8daaa..05974820ca69 100644 --- a/tools/testing/selftests/sched_ext/prog_run.c +++ b/tools/testing/selftests/sched_ext/prog_run.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct prog_run *skel; - skel = prog_run__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = prog_run__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(prog_run__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c index 5cfba2d6e056..308211d80436 100644 --- a/tools/testing/selftests/sched_ext/reload_loop.c +++ b/tools/testing/selftests/sched_ext/reload_loop.c @@ -18,11 +18,10 @@ bool force_exit = false; static enum scx_test_status setup(void **ctx) { - skel = maximal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); return SCX_TEST_PASS; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c index a53a40c2d2f0..5b6e045e1109 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl *skel; - skel = select_cpu_dfl__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c index 1d85bf4bf3a3..9b5d232efb7f 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl_nodispatch *skel; - skel = select_cpu_dfl_nodispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl_nodispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl_nodispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c index 0309ca8785b3..80283dbc41b7 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch *skel; - skel = select_cpu_dispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c index 47eb6ed7627d..5e72ebbc90a5 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_bad_dsq *skel; - skel = select_cpu_dispatch_bad_dsq__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_bad_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_bad_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c index 48ff028a3c46..aa85949478bc 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_dbl_dsp *skel; - skel = select_cpu_dispatch_dbl_dsp__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_dbl_dsp__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_dbl_dsp__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.c index b4629c2364f5..1e9b5c9bfff1 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_vtime *skel; - skel = select_cpu_vtime__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_vtime__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_vtime__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 8c3a73461475..14ba51b52095 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -47,6 +47,7 @@ #include <linux/kcmp.h> #include <sys/resource.h> #include <sys/capability.h> +#include <linux/perf_event.h> #include <unistd.h> #include <sys/syscall.h> @@ -68,6 +69,10 @@ # define PR_SET_PTRACER 0x59616d61 #endif +#ifndef noinline +#define noinline __attribute__((noinline)) +#endif + #ifndef PR_SET_NO_NEW_PRIVS #define PR_SET_NO_NEW_PRIVS 38 #define PR_GET_NO_NEW_PRIVS 39 @@ -4888,6 +4893,200 @@ TEST(tsync_vs_dead_thread_leader) EXPECT_EQ(0, status); } +noinline int probed(void) +{ + return 1; +} + +static int parse_uint_from_file(const char *file, const char *fmt) +{ + int err = -1, ret; + FILE *f; + + f = fopen(file, "re"); + if (f) { + err = fscanf(f, fmt, &ret); + fclose(f); + } + return err == 1 ? ret : err; +} + +static int determine_uprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_uprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static ssize_t get_uprobe_offset(const void *addr) +{ + size_t start, base, end; + bool found = false; + char buf[256]; + FILE *f; + + f = fopen("/proc/self/maps", "r"); + if (!f) + return -1; + + while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) { + if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) { + found = true; + break; + } + } + fclose(f); + return found ? (uintptr_t)addr - start + base : -1; +} + +FIXTURE(URETPROBE) { + int fd; +}; + +FIXTURE_VARIANT(URETPROBE) { + /* + * All of the URETPROBE behaviors can be tested with either + * uretprobe attached or not + */ + bool attach; +}; + +FIXTURE_VARIANT_ADD(URETPROBE, attached) { + .attach = true, +}; + +FIXTURE_VARIANT_ADD(URETPROBE, not_attached) { + .attach = false, +}; + +FIXTURE_SETUP(URETPROBE) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; + ssize_t offset; + int type, bit; + +#ifndef __NR_uretprobe + SKIP(return, "__NR_uretprobe syscall not defined"); +#endif + + if (!variant->attach) + return; + + memset(&attr, 0, attr_sz); + + type = determine_uprobe_perf_type(); + ASSERT_GE(type, 0); + bit = determine_uprobe_retprobe_bit(); + ASSERT_GE(bit, 0); + offset = get_uprobe_offset(probed); + ASSERT_GE(offset, 0); + + attr.config |= 1 << bit; + attr.size = attr_sz; + attr.type = type; + attr.config1 = ptr_to_u64("/proc/self/exe"); + attr.config2 = offset; + + self->fd = syscall(__NR_perf_event_open, &attr, + getpid() /* pid */, -1 /* cpu */, -1 /* group_fd */, + PERF_FLAG_FD_CLOEXEC); +} + +FIXTURE_TEARDOWN(URETPROBE) +{ + /* we could call close(self->fd), but we'd need extra filter for + * that and since we are calling _exit right away.. + */ +} + +static int run_probed_with_filter(struct sock_fprog *prog) +{ + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) || + seccomp(SECCOMP_SET_MODE_FILTER, 0, prog)) { + return -1; + } + + probed(); + return 0; +} + +TEST_F(URETPROBE, uretprobe_default_allow) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_default_block) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), +#ifdef __NR_uretprobe + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 0, 1), +#endif + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_default_block_with_uretprobe_syscall) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), +#ifdef __NR_uretprobe + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 2, 0), +#endif + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + /* * TODO: * - expand NNP testing diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index d3dd65b05b5f..9044ac054167 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -94,5 +94,37 @@ "$TC qdisc del dev $DUMMY ingress", "$IP addr del 10.10.10.10/24 dev $DUMMY" ] - } + }, + { + "id": "a4b9", + "name": "Test class qlen notification", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: netem", + "$TC qdisc add dev $DUMMY parent 2: handle 3: drr", + "$TC filter add dev $DUMMY parent 3: basic action drop", + "$TC class add dev $DUMMY parent 3: classid 3:1 drr", + "$TC class del dev $DUMMY classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC qdisc ls dev $DUMMY", + "matchPattern": "drr 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json index ae3d286a32b2..6f20d033670d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json @@ -313,6 +313,29 @@ "matchPattern": "qdisc bfifo 1: root", "matchCount": "0", "teardown": [ + ] + }, + { + "id": "d774", + "name": "Check pfifo_head_drop qdisc enqueue behaviour when limit == 0", + "category": [ + "qdisc", + "pfifo_head_drop" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: pfifo_head_drop limit 0", + "$IP link set dev $DUMMY up || true" + ], + "cmdUnderTest": "ping -c2 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "dropped 2", + "matchCount": "1", + "teardown": [ ] } ] diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0ea4f6813930..4d4a76532dc9 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -237,7 +237,7 @@ static uint64_t set_metadata(uint64_t src, unsigned long lam) * both pointers should point to the same address. * * @return: - * 0: value on the pointer with metadate and value on original are same + * 0: value on the pointer with metadata and value on original are same * 1: not same. */ static int handle_lam_test(void *src, unsigned int lam) diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 7058dc614c25..de25892f865f 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -96,41 +96,57 @@ void vsock_wait_remote_close(int fd) close(epollfd); } -/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ -int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ +int vsock_bind(unsigned int cid, unsigned int port, int type) { - struct sockaddr_vm sa_client = { - .svm_family = AF_VSOCK, - .svm_cid = VMADDR_CID_ANY, - .svm_port = bind_port, - }; - struct sockaddr_vm sa_server = { + struct sockaddr_vm sa = { .svm_family = AF_VSOCK, .svm_cid = cid, .svm_port = port, }; + int fd; - int client_fd, ret; - - client_fd = socket(AF_VSOCK, type, 0); - if (client_fd < 0) { + fd = socket(AF_VSOCK, type, 0); + if (fd < 0) { perror("socket"); exit(EXIT_FAILURE); } - if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) { + if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) { perror("bind"); exit(EXIT_FAILURE); } + return fd; +} + +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port) +{ + struct sockaddr_vm sa = { + .svm_family = AF_VSOCK, + .svm_cid = cid, + .svm_port = port, + }; + int ret; + timeout_begin(TIMEOUT); do { - ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server)); + ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa)); timeout_check("connect"); } while (ret < 0 && errno == EINTR); timeout_end(); - if (ret < 0) { + return ret; +} + +/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ +int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +{ + int client_fd; + + client_fd = vsock_bind(VMADDR_CID_ANY, bind_port, type); + + if (vsock_connect_fd(client_fd, cid, port)) { perror("connect"); exit(EXIT_FAILURE); } @@ -141,17 +157,6 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po /* Connect to <cid, port> and return the file descriptor. */ int vsock_connect(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; - int ret; int fd; control_expectln("LISTENING"); @@ -162,20 +167,14 @@ int vsock_connect(unsigned int cid, unsigned int port, int type) exit(EXIT_FAILURE); } - timeout_begin(TIMEOUT); - do { - ret = connect(fd, &addr.sa, sizeof(addr.svm)); - timeout_check("connect"); - } while (ret < 0 && errno == EINTR); - timeout_end(); - - if (ret < 0) { + if (vsock_connect_fd(fd, cid, port)) { int old_errno = errno; close(fd); fd = -1; errno = old_errno; } + return fd; } @@ -192,28 +191,9 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port) /* Listen on <cid, port> and return the file descriptor. */ static int vsock_listen(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; int fd; - fd = socket(AF_VSOCK, type, 0); - if (fd < 0) { - perror("socket"); - exit(EXIT_FAILURE); - } - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(cid, port, type); if (listen(fd, 1) < 0) { perror("listen"); diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index e62f46b2b92a..d1f765ce3eee 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -39,10 +39,12 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); unsigned int parse_port(const char *str); +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port); int vsock_connect(unsigned int cid, unsigned int port, int type); int vsock_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_bind(unsigned int cid, unsigned int port, int type); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); int vsock_seqpacket_connect(unsigned int cid, unsigned int port); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 1eebbc0d5f61..d0f6d253ac72 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -113,24 +113,9 @@ static void test_stream_bind_only_client(const struct test_opts *opts) static void test_stream_bind_only_server(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = opts->peer_port, - .svm_cid = VMADDR_CID_ANY, - }, - }; int fd; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(VMADDR_CID_ANY, opts->peer_port, SOCK_STREAM); /* Notify the client that the server is ready */ control_writeln("BIND"); @@ -1708,6 +1693,137 @@ static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts) close(fd); } +#define MAX_PORT_RETRIES 24 /* net/vmw_vsock/af_vsock.c */ + +/* Test attempts to trigger a transport release for an unbound socket. This can + * lead to a reference count mishandling. + */ +static void test_stream_transport_uaf_client(const struct test_opts *opts) +{ + int sockets[MAX_PORT_RETRIES]; + struct sockaddr_vm addr; + int fd, i, alen; + + fd = vsock_bind(VMADDR_CID_ANY, VMADDR_PORT_ANY, SOCK_STREAM); + + alen = sizeof(addr); + if (getsockname(fd, (struct sockaddr *)&addr, &alen)) { + perror("getsockname"); + exit(EXIT_FAILURE); + } + + for (i = 0; i < MAX_PORT_RETRIES; ++i) + sockets[i] = vsock_bind(VMADDR_CID_ANY, ++addr.svm_port, + SOCK_STREAM); + + close(fd); + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, addr.svm_cid, addr.svm_port)) { + perror("Unexpected connect() #1 success"); + exit(EXIT_FAILURE); + } + + /* Vulnerable system may crash now. */ + if (!vsock_connect_fd(fd, VMADDR_CID_HOST, VMADDR_PORT_ANY)) { + perror("Unexpected connect() #2 success"); + exit(EXIT_FAILURE); + } + + close(fd); + while (i--) + close(sockets[i]); + + control_writeln("DONE"); +} + +static void test_stream_transport_uaf_server(const struct test_opts *opts) +{ + control_expectln("DONE"); +} + +static void test_stream_connect_retry_client(const struct test_opts *opts) +{ + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + fprintf(stderr, "Unexpected connect() #1 success\n"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTEN"); + control_expectln("LISTENING"); + + if (vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + perror("connect() #2"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_connect_retry_server(const struct test_opts *opts) +{ + int fd; + + control_expectln("LISTEN"); + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + +static void test_stream_linger_client(const struct test_opts *opts) +{ + struct linger optval = { + .l_onoff = 1, + .l_linger = 1 + }; + int fd; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (setsockopt(fd, SOL_SOCKET, SO_LINGER, &optval, sizeof(optval))) { + perror("setsockopt(SO_LINGER)"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_linger_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -1853,6 +1969,21 @@ static struct test_case test_cases[] = { .run_client = test_stream_msgzcopy_leak_zcskb_client, .run_server = test_stream_msgzcopy_leak_zcskb_server, }, + { + .name = "SOCK_STREAM transport release use-after-free", + .run_client = test_stream_transport_uaf_client, + .run_server = test_stream_transport_uaf_server, + }, + { + .name = "SOCK_STREAM retry failed connect()", + .run_client = test_stream_connect_retry_client, + .run_server = test_stream_connect_retry_server, + }, + { + .name = "SOCK_STREAM SO_LINGER null-ptr-deref", + .run_client = test_stream_linger_client, + .run_server = test_stream_linger_server, + }, {}, }; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index faf10671eed2..ba0327e2d0d3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1071,15 +1071,6 @@ out_err: } /* - * Called after the VM is otherwise initialized, but just before adding it to - * the vm_list. - */ -int __weak kvm_arch_post_init_vm(struct kvm *kvm) -{ - return 0; -} - -/* * Called just after removing the VM from the vm_list, but before doing any * other destruction. */ @@ -1199,10 +1190,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) if (r) goto out_err_no_debugfs; - r = kvm_arch_post_init_vm(kvm); - if (r) - goto out_err; - mutex_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); mutex_unlock(&kvm_lock); @@ -1212,8 +1199,6 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) return kvm; -out_err: - kvm_destroy_vm_debugfs(kvm); out_err_no_debugfs: kvm_coalesced_mmio_free(kvm); out_no_coalesced_mmio: @@ -1971,7 +1956,15 @@ static int kvm_set_memory_region(struct kvm *kvm, return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) return -EINVAL; - if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) + + /* + * The size of userspace-defined memory regions is restricted in order + * to play nice with dirty bitmap operations, which are indexed with an + * "unsigned int". KVM's internal memory regions don't support dirty + * logging, and so are exempt. + */ + if (id < KVM_USER_MEM_SLOTS && + (mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) return -EINVAL; slots = __kvm_memslots(kvm, as_id); |