diff --git a/Makefile b/Makefile index 2e5d92ce2774..0bd4bee2128b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 6 -SUBLEVEL = 44 +SUBLEVEL = 45 EXTRAVERSION = NAME = Hurr durr I'ma ninja sloth diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c index 7147edbe56c6..1d230ac9d0eb 100644 --- a/arch/arm/kernel/perf_callchain.c +++ b/arch/arm/kernel/perf_callchain.c @@ -85,8 +85,7 @@ static bool callchain_trace(void *data, unsigned long pc) { struct perf_callchain_entry_ctx *entry = data; - perf_callchain_store(entry, pc); - return true; + return perf_callchain_store(entry, pc) == 0; } void diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 5effd8180cc4..e5993a365870 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -641,6 +641,7 @@ dwc_0: usb@8a00000 { interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>; phys = <&qusb_phy_0>, <&usb0_ssphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; @@ -683,6 +684,7 @@ dwc_1: usb@8c00000 { interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>; phys = <&qusb_phy_1>, <&usb1_ssphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 9c072ce19735..7fcc15b6946a 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -2159,7 +2159,8 @@ usb3_dwc3: usb@a800000 { interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&qusb2phy>, <&usb1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&qusb2phy>, <&usb3phy>; phy-names = "usb2-phy", "usb3-phy"; snps,has-lpm-erratum; snps,hird-threshold = /bits/ 8 <0x10>; @@ -2168,33 +2169,26 @@ usb3_dwc3: usb@a800000 { usb3phy: phy@c010000 { compatible = "qcom,msm8998-qmp-usb3-phy"; - reg = <0x0c010000 0x18c>; - status = "disabled"; - #address-cells = <1>; - #size-cells = <1>; - ranges; + reg = <0x0c010000 0x1000>; clocks = <&gcc GCC_USB3_PHY_AUX_CLK>, + <&gcc GCC_USB3_CLKREF_CLK>, <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, - <&gcc GCC_USB3_CLKREF_CLK>; - clock-names = "aux", "cfg_ahb", "ref"; + <&gcc GCC_USB3_PHY_PIPE_CLK>; + clock-names = "aux", + "ref", + "cfg_ahb", + "pipe"; + clock-output-names = "usb3_phy_pipe_clk_src"; + #clock-cells = <0>; + #phy-cells = <0>; resets = <&gcc GCC_USB3_PHY_BCR>, <&gcc GCC_USB3PHY_PHY_BCR>; - reset-names = "phy", "common"; + reset-names = "phy", + "phy_phy"; - usb1_ssphy: phy@c010200 { - reg = <0xc010200 0x128>, - <0xc010400 0x200>, - <0xc010c00 0x20c>, - <0xc010600 0x128>, - <0xc010800 0x200>; - #phy-cells = <0>; - #clock-cells = <0>; - clocks = <&gcc GCC_USB3_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; + status = "disabled"; }; qusb2phy: phy@c012000 { diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index f7c528ecb224..68b1c017a9fd 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -15,6 +15,7 @@ #include <dt-bindings/interconnect/qcom,osm-l3.h> #include <dt-bindings/interconnect/qcom,sc7180.h> #include <dt-bindings/interrupt-controller/arm-gic.h> +#include <dt-bindings/phy/phy-qcom-qmp.h> #include <dt-bindings/phy/phy-qcom-qusb2.h> #include <dt-bindings/power/qcom-rpmpd.h> #include <dt-bindings/reset/qcom,sdm845-aoss.h> @@ -2795,49 +2796,28 @@ usb_1_hsphy: phy@88e3000 { nvmem-cells = <&qusb2p_hstx_trim>; }; - usb_1_qmpphy: phy-wrapper@88e9000 { + usb_1_qmpphy: phy@88e8000 { compatible = "qcom,sc7180-qmp-usb3-dp-phy"; - reg = <0 0x088e9000 0 0x18c>, - <0 0x088e8000 0 0x3c>, - <0 0x088ea000 0 0x18c>; + reg = <0 0x088e8000 0 0x3000>; status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, - <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, <&gcc GCC_USB3_PRIM_CLKREF_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>, + <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>; + clock-names = "aux", + "ref", + "com_aux", + "usb3_pipe", + "cfg_ahb"; resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, <&gcc GCC_USB3_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - usb_1_ssphy: usb3-phy@88e9200 { - reg = <0 0x088e9200 0 0x128>, - <0 0x088e9400 0 0x200>, - <0 0x088e9c00 0 0x218>, - <0 0x088e9600 0 0x128>, - <0 0x088e9800 0 0x200>, - <0 0x088e9a00 0 0x18>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; - - dp_phy: dp-phy@88ea200 { - reg = <0 0x088ea200 0 0x200>, - <0 0x088ea400 0 0x200>, - <0 0x088eaa00 0 0x200>, - <0 0x088ea600 0 0x200>, - <0 0x088ea800 0 0x200>; - #clock-cells = <1>; - #phy-cells = <0>; - }; + #clock-cells = <1>; + #phy-cells = <1>; }; pmu@90b6300 { @@ -3001,7 +2981,8 @@ usb_1_dwc3: usb@a600000 { iommus = <&apps_smmu 0x540 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; maximum-speed = "super-speed"; }; @@ -3307,8 +3288,9 @@ mdss_dp: displayport-controller@ae90000 { "ctrl_link_iface", "stream_pixel"; assigned-clocks = <&dispcc DISP_CC_MDSS_DP_LINK_CLK_SRC>, <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK_SRC>; - assigned-clock-parents = <&dp_phy 0>, <&dp_phy 1>; - phys = <&dp_phy>; + assigned-clock-parents = <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; + phys = <&usb_1_qmpphy QMP_USB43DP_DP_PHY>; phy-names = "dp"; operating-points-v2 = <&dp_opp_table>; @@ -3365,8 +3347,8 @@ dispcc: clock-controller@af00000 { <&gcc GCC_DISP_GPLL0_CLK_SRC>, <&mdss_dsi0_phy 0>, <&mdss_dsi0_phy 1>, - <&dp_phy 0>, - <&dp_phy 1>; + <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; clock-names = "bi_tcxo", "gcc_disp_gpll0_clk_src", "dsi0_phy_pll_out_byteclk", diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi index b75de7caaa7e..149c7962f2cb 100644 --- a/arch/arm64/boot/dts/qcom/sc7280.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi @@ -18,6 +18,7 @@ #include <dt-bindings/interconnect/qcom,sc7280.h> #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/mailbox/qcom-ipcc.h> +#include <dt-bindings/phy/phy-qcom-qmp.h> #include <dt-bindings/power/qcom-rpmpd.h> #include <dt-bindings/reset/qcom,sdm845-aoss.h> #include <dt-bindings/reset/qcom,sdm845-pdc.h> @@ -858,7 +859,7 @@ gcc: clock-controller@100000 { <&rpmhcc RPMH_CXO_CLK_A>, <&sleep_clk>, <0>, <&pcie1_lane>, <0>, <0>, <0>, - <&usb_1_ssphy>; + <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>; clock-names = "bi_tcxo", "bi_tcxo_ao", "sleep_clk", "pcie_0_pipe_clk", "pcie_1_pipe_clk", "ufs_phy_rx_symbol_0_clk", "ufs_phy_rx_symbol_1_clk", @@ -3351,49 +3352,26 @@ usb_2_hsphy: phy@88e4000 { resets = <&gcc GCC_QUSB2PHY_SEC_BCR>; }; - usb_1_qmpphy: phy-wrapper@88e9000 { - compatible = "qcom,sc7280-qmp-usb3-dp-phy", - "qcom,sm8250-qmp-usb3-dp-phy"; - reg = <0 0x088e9000 0 0x200>, - <0 0x088e8000 0 0x40>, - <0 0x088ea000 0 0x200>; + usb_1_qmpphy: phy@88e8000 { + compatible = "qcom,sc7280-qmp-usb3-dp-phy"; + reg = <0 0x088e8000 0 0x3000>; status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, <&rpmhcc RPMH_CXO_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "ref_clk_src", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; + clock-names = "aux", + "ref", + "com_aux", + "usb3_pipe"; resets = <&gcc GCC_USB3_DP_PHY_PRIM_BCR>, <&gcc GCC_USB3_PHY_PRIM_BCR>; reset-names = "phy", "common"; - usb_1_ssphy: usb3-phy@88e9200 { - reg = <0 0x088e9200 0 0x200>, - <0 0x088e9400 0 0x200>, - <0 0x088e9c00 0 0x400>, - <0 0x088e9600 0 0x200>, - <0 0x088e9800 0 0x200>, - <0 0x088e9a00 0 0x100>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; - - dp_phy: dp-phy@88ea200 { - reg = <0 0x088ea200 0 0x200>, - <0 0x088ea400 0 0x200>, - <0 0x088eaa00 0 0x200>, - <0 0x088ea600 0 0x200>, - <0 0x088ea800 0 0x200>; - #phy-cells = <0>; - #clock-cells = <1>; - }; + #clock-cells = <1>; + #phy-cells = <1>; }; usb_2: usb@8cf8800 { @@ -3702,7 +3680,8 @@ usb_1_dwc3: usb@a600000 { iommus = <&apps_smmu 0xe0 0x0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; maximum-speed = "super-speed"; }; @@ -3807,8 +3786,8 @@ dispcc: clock-controller@af00000 { <&gcc GCC_DISP_GPLL0_CLK_SRC>, <&mdss_dsi_phy 0>, <&mdss_dsi_phy 1>, - <&dp_phy 0>, - <&dp_phy 1>, + <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>, <&mdss_edp_phy 0>, <&mdss_edp_phy 1>; clock-names = "bi_tcxo", @@ -4144,8 +4123,9 @@ mdss_dp: displayport-controller@ae90000 { "stream_pixel"; assigned-clocks = <&dispcc DISP_CC_MDSS_DP_LINK_CLK_SRC>, <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK_SRC>; - assigned-clock-parents = <&dp_phy 0>, <&dp_phy 1>; - phys = <&dp_phy>; + assigned-clock-parents = <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; + phys = <&usb_1_qmpphy QMP_USB43DP_DP_PHY>; phy-names = "dp"; operating-points-v2 = <&dp_opp_table>; diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 9d9b378c07e1..dcdc8a0cd181 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -18,6 +18,7 @@ #include <dt-bindings/interconnect/qcom,osm-l3.h> #include <dt-bindings/interconnect/qcom,sdm845.h> #include <dt-bindings/interrupt-controller/arm-gic.h> +#include <dt-bindings/phy/phy-qcom-qmp.h> #include <dt-bindings/phy/phy-qcom-qusb2.h> #include <dt-bindings/power/qcom-rpmpd.h> #include <dt-bindings/reset/qcom,sdm845-aoss.h> @@ -3983,80 +3984,54 @@ usb_2_hsphy: phy@88e3000 { nvmem-cells = <&qusb2s_hstx_trim>; }; - usb_1_qmpphy: phy@88e9000 { + usb_1_qmpphy: phy@88e8000 { compatible = "qcom,sdm845-qmp-usb3-dp-phy"; - reg = <0 0x088e9000 0 0x18c>, - <0 0x088e8000 0 0x38>, - <0 0x088ea000 0 0x40>; + reg = <0 0x088e8000 0 0x3000>; status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, - <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, <&gcc GCC_USB3_PRIM_CLKREF_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>, + <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>; + clock-names = "aux", + "ref", + "com_aux", + "usb3_pipe", + "cfg_ahb"; resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, <&gcc GCC_USB3_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - usb_1_ssphy: usb3-phy@88e9200 { - reg = <0 0x088e9200 0 0x128>, - <0 0x088e9400 0 0x200>, - <0 0x088e9c00 0 0x218>, - <0 0x088e9600 0 0x128>, - <0 0x088e9800 0 0x200>, - <0 0x088e9a00 0 0x100>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; - - dp_phy: dp-phy@88ea200 { - reg = <0 0x088ea200 0 0x200>, - <0 0x088ea400 0 0x200>, - <0 0x088eaa00 0 0x200>, - <0 0x088ea600 0 0x200>, - <0 0x088ea800 0 0x200>; - #clock-cells = <1>; - #phy-cells = <0>; - }; + #clock-cells = <1>; + #phy-cells = <1>; }; usb_2_qmpphy: phy@88eb000 { compatible = "qcom,sdm845-qmp-usb3-uni-phy"; - reg = <0 0x088eb000 0 0x18c>; - status = "disabled"; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x088eb000 0 0x1000>; clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>, <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, <&gcc GCC_USB3_SEC_CLKREF_CLK>, - <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>; - clock-names = "aux", "cfg_ahb", "ref", "com_aux"; + <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; + clock-names = "aux", + "cfg_ahb", + "ref", + "com_aux", + "pipe"; + clock-output-names = "usb3_uni_phy_pipe_clk_src"; + #clock-cells = <0>; + #phy-cells = <0>; - resets = <&gcc GCC_USB3PHY_PHY_SEC_BCR>, - <&gcc GCC_USB3_PHY_SEC_BCR>; - reset-names = "phy", "common"; + resets = <&gcc GCC_USB3_PHY_SEC_BCR>, + <&gcc GCC_USB3PHY_PHY_SEC_BCR>; + reset-names = "phy", + "phy_phy"; - usb_2_ssphy: phy@88eb200 { - reg = <0 0x088eb200 0 0x128>, - <0 0x088eb400 0 0x1fc>, - <0 0x088eb800 0 0x218>, - <0 0x088eb600 0 0x70>; - #clock-cells = <0>; - #phy-cells = <0>; - clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_uni_phy_pipe_clk_src"; - }; + status = "disabled"; }; usb_1: usb@a6f8800 { @@ -4105,7 +4080,8 @@ usb_1_dwc3: usb@a600000 { iommus = <&apps_smmu 0x740 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; }; }; @@ -4156,7 +4132,8 @@ usb_2_dwc3: usb@a800000 { iommus = <&apps_smmu 0x760 0>; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&usb_2_hsphy>, <&usb_2_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&usb_2_hsphy>, <&usb_2_qmpphy>; phy-names = "usb2-phy", "usb3-phy"; }; }; @@ -4573,8 +4550,9 @@ mdss_dp: displayport-controller@ae90000 { "ctrl_link_iface", "stream_pixel"; assigned-clocks = <&dispcc DISP_CC_MDSS_DP_LINK_CLK_SRC>, <&dispcc DISP_CC_MDSS_DP_PIXEL_CLK_SRC>; - assigned-clock-parents = <&dp_phy 0>, <&dp_phy 1>; - phys = <&dp_phy>; + assigned-clock-parents = <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; + phys = <&usb_1_qmpphy QMP_USB43DP_DP_PHY>; phy-names = "dp"; operating-points-v2 = <&dp_opp_table>; @@ -4912,8 +4890,8 @@ dispcc: clock-controller@af00000 { <&mdss_dsi0_phy 1>, <&mdss_dsi1_phy 0>, <&mdss_dsi1_phy 1>, - <&dp_phy 0>, - <&dp_phy 1>; + <&usb_1_qmpphy QMP_USB43DP_DP_LINK_CLK>, + <&usb_1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>; clock-names = "bi_tcxo", "gcc_disp_gpll0_clk_src", "gcc_disp_gpll0_div_clk_src", diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 6aafbb789991..4b9915915082 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -13,6 +13,7 @@ #include <linux/types.h> #include <asm/insn.h> +#define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE static __always_inline bool arch_static_branch(struct static_key * const key, diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c index faf88ec9c48e..f63ea915d6ad 100644 --- a/arch/arm64/kernel/jump_label.c +++ b/arch/arm64/kernel/jump_label.c @@ -7,11 +7,12 @@ */ #include <linux/kernel.h> #include <linux/jump_label.h> +#include <linux/smp.h> #include <asm/insn.h> #include <asm/patching.h> -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type) { void *addr = (void *)jump_entry_code(entry); u32 insn; @@ -25,4 +26,10 @@ void arch_jump_label_transform(struct jump_entry *entry, } aarch64_insn_patch_text_nosync(addr, insn); + return true; +} + +void arch_jump_label_transform_apply(void) +{ + kick_all_cpus_sync(); } diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi index c0be84a6e81f..cc7747c5f21f 100644 --- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi +++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi @@ -99,8 +99,8 @@ liointc1: interrupt-controller@1fe11440 { rtc0: rtc@1fe07800 { compatible = "loongson,ls2k1000-rtc"; reg = <0 0x1fe07800 0 0x78>; - interrupt-parent = <&liointc0>; - interrupts = <60 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&liointc1>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; }; uart0: serial@1fe00000 { @@ -108,7 +108,7 @@ uart0: serial@1fe00000 { reg = <0 0x1fe00000 0 0x8>; clock-frequency = <125000000>; interrupt-parent = <&liointc0>; - interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; no-loopback-test; }; @@ -117,7 +117,6 @@ pci@1a000000 { device_type = "pci"; #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <2>; reg = <0 0x1a000000 0 0x02000000>, <0xfe 0x00000000 0 0x20000000>; @@ -132,8 +131,8 @@ gmac@3,0 { "pciclass0c03"; reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_LOW>, - <13 IRQ_TYPE_LEVEL_LOW>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, + <13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&liointc0>; phy-mode = "rgmii-id"; @@ -156,8 +155,8 @@ gmac@3,1 { "loongson, pci-gmac"; reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_LOW>, - <15 IRQ_TYPE_LEVEL_LOW>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, + <15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&liointc0>; phy-mode = "rgmii-id"; @@ -179,7 +178,7 @@ ehci@4,1 { "pciclass0c03"; reg = <0x2100 0x0 0x0 0x0 0x0>; - interrupts = <18 IRQ_TYPE_LEVEL_LOW>; + interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; }; @@ -190,7 +189,7 @@ ohci@4,2 { "pciclass0c03"; reg = <0x2200 0x0 0x0 0x0 0x0>; - interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; }; @@ -201,97 +200,121 @@ sata@8,0 { "pciclass0106"; reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc0>; }; - pci_bridge@9,0 { + pcie@9,0 { compatible = "pci0014,7a19.0", "pci0014,7a19", "pciclass060400", "pciclass0604"; reg = <0x4800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@a,0 { + pcie@a,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x5000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@b,0 { + pcie@b,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x5800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <2 IRQ_TYPE_LEVEL_LOW>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@c,0 { + pcie@c,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x6000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@d,0 { + pcie@d,0 { compatible = "pci0014,7a19.0", "pci0014,7a19", "pciclass060400", "pciclass0604"; reg = <0x6800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <4 IRQ_TYPE_LEVEL_LOW>; + interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@e,0 { + pcie@e,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x7000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <5 IRQ_TYPE_LEVEL_LOW>; + interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c index 5348d842c745..e867fe465164 100644 --- a/arch/riscv/kernel/traps_misaligned.c +++ b/arch/riscv/kernel/traps_misaligned.c @@ -151,51 +151,19 @@ #define PRECISION_S 0 #define PRECISION_D 1 -#define DECLARE_UNPRIVILEGED_LOAD_FUNCTION(type, insn) \ -static inline type load_##type(const type *addr) \ -{ \ - type val; \ - asm (#insn " %0, %1" \ - : "=&r" (val) : "m" (*addr)); \ - return val; \ -} +static inline u8 load_u8(const u8 *addr) +{ + u8 val; -#define DECLARE_UNPRIVILEGED_STORE_FUNCTION(type, insn) \ -static inline void store_##type(type *addr, type val) \ -{ \ - asm volatile (#insn " %0, %1\n" \ - : : "r" (val), "m" (*addr)); \ -} + asm volatile("lbu %0, %1" : "=&r" (val) : "m" (*addr)); -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u8, lbu) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u16, lhu) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s8, lb) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s16, lh) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(s32, lw) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u8, sb) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u16, sh) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u32, sw) -#if defined(CONFIG_64BIT) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lwu) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u64, ld) -DECLARE_UNPRIVILEGED_STORE_FUNCTION(u64, sd) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, ld) -#else -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(u32, lw) -DECLARE_UNPRIVILEGED_LOAD_FUNCTION(ulong, lw) - -static inline u64 load_u64(const u64 *addr) -{ - return load_u32((u32 *)addr) - + ((u64)load_u32((u32 *)addr + 1) << 32); + return val; } -static inline void store_u64(u64 *addr, u64 val) +static inline void store_u8(u8 *addr, u8 val) { - store_u32((u32 *)addr, val); - store_u32((u32 *)addr + 1, val >> 32); + asm volatile ("sb %0, %1\n" : : "r" (val), "m" (*addr)); } -#endif static inline ulong get_insn(ulong mepc) { diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 90d4ba36d1d0..655b2b1bb529 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -61,26 +61,27 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) { + if (!user_mode(regs)) { + no_context(regs, addr); + return; + } + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return the userspace * (which will retry the fault, or kill us if we got oom-killed). */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } pagefault_out_of_memory(); return; } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) { /* Kernel mode? Handle exceptions or die */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } do_trap(regs, SIGBUS, BUS_ADRERR, addr); return; + } else if (fault & VM_FAULT_SIGSEGV) { + do_trap(regs, SIGSEGV, SEGV_MAPERR, addr); + return; } + BUG(); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 8adcb9419ad5..9b10e9655df8 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -217,8 +217,6 @@ static void __init setup_bootmem(void) */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - phys_ram_end = memblock_end_of_DRAM(); - /* * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. @@ -233,6 +231,16 @@ static void __init setup_bootmem(void) if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; + /* + * The size of the linear page mapping may restrict the amount of + * usable RAM. + */ + if (IS_ENABLED(CONFIG_64BIT)) { + max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE; + memblock_cap_memory_range(phys_ram_base, + max_mapped_addr - phys_ram_base); + } + /* * Reserve physical address space that would be mapped to virtual * addresses greater than (void *)(-PAGE_SIZE) because: @@ -249,6 +257,7 @@ static void __init setup_bootmem(void) memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr); } + phys_ram_end = memblock_end_of_DRAM(); min_low_pfn = PFN_UP(phys_ram_base); max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); @@ -1269,8 +1278,6 @@ static void __init create_linear_mapping_page_table(void) if (start <= __pa(PAGE_OFFSET) && __pa(PAGE_OFFSET) < end) start = __pa(PAGE_OFFSET); - if (end >= __pa(PAGE_OFFSET) + memory_limit) - end = __pa(PAGE_OFFSET) + memory_limit; create_linear_mapping_range(start, end, 0); } diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h new file mode 100644 index 000000000000..f0324c56f7af --- /dev/null +++ b/arch/x86/include/asm/posted_intr.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_POSTED_INTR_H +#define _X86_POSTED_INTR_H + +#define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 + +#define PID_TABLE_ENTRY_VALID 1 + +/* Posted-Interrupt Descriptor */ +struct pi_desc { + u32 pir[8]; /* Posted interrupt requested */ + union { + struct { + /* bit 256 - Outstanding Notification */ + u16 on : 1, + /* bit 257 - Suppress Notification */ + sn : 1, + /* bit 271:258 - Reserved */ + rsvd_1 : 14; + /* bit 279:272 - Notification Vector */ + u8 nv; + /* bit 287:280 - Reserved */ + u8 rsvd_2; + /* bit 319:288 - Notification Destination */ + u32 ndst; + }; + u64 control; + }; + u32 rsvd[6]; +} __aligned(64); + +static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) +{ + return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +{ + return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); +} + +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); +} + +static inline void pi_set_sn(struct pi_desc *pi_desc) +{ + set_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline void pi_set_on(struct pi_desc *pi_desc) +{ + set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline void pi_clear_on(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_on(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_sn(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +#endif /* _X86_POSTED_INTR_H */ diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 80e3fe184d17..a99ffc3f3a3f 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -26,6 +26,10 @@ kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ vmx/hyperv.o vmx/nested.o vmx/posted_intr.o kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o +ifdef CONFIG_HYPERV +kvm-intel-y += vmx/vmx_onhyperv.o +endif + kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ svm/sev.o svm/hyperv.o diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 313b8bb5b8a7..de13dc14fe1d 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,111 +13,6 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_ENABLE_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ {EVMCS1_OFFSET(name), clean_field} @@ -608,40 +503,6 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } -#if IS_ENABLED(CONFIG_HYPERV) -DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -/* - * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption - * is: in case a feature has corresponding fields in eVMCS described and it was - * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a - * feature which has no corresponding eVMCS field, this likely means that KVM - * needs to be updated. - */ -#define evmcs_check_vmcs_conf(field, ctrl) \ - do { \ - typeof(vmcs_conf->field) unsupported; \ - \ - unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ - if (unsupported) { \ - pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ - (u64)unsupported); \ - vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ - } \ - } \ - while (0) - -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) -{ - evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); - evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); - evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); - evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); - evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); - evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); -} -#endif - int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 9623fe1651c4..9401dbfaea7c 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -14,12 +14,113 @@ #include "vmcs.h" #include "vmcs12.h" -struct vmcs_config; - -#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) - #define KVM_EVMCS_VERSION 1 +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_ENABLE_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) + struct evmcs_field { u16 offset; u16 clean_field; @@ -65,114 +166,6 @@ static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, return vmcs12_read_any((void *)evmcs, field, offset); } -#if IS_ENABLED(CONFIG_HYPERV) - -DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -static __always_inline bool kvm_is_using_evmcs(void) -{ - return static_branch_unlikely(&__kvm_is_using_evmcs); -} - -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) -{ - int offset = evmcs_field_offset(field, clean_field); - - WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); - return offset; -} - -static __always_inline void evmcs_write64(unsigned long field, u64 value) -{ - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u64 *)((char *)current_evmcs + offset) = value; - - current_evmcs->hv_clean_fields &= ~clean_field; -} - -static __always_inline void evmcs_write32(unsigned long field, u32 value) -{ - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u32 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; -} - -static __always_inline void evmcs_write16(unsigned long field, u16 value) -{ - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u16 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; -} - -static __always_inline u64 evmcs_read64(unsigned long field) -{ - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u64 *)((char *)current_evmcs + offset); -} - -static __always_inline u32 evmcs_read32(unsigned long field) -{ - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u32 *)((char *)current_evmcs + offset); -} - -static __always_inline u16 evmcs_read16(unsigned long field) -{ - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u16 *)((char *)current_evmcs + offset); -} - -static inline void evmcs_load(u64 phys_addr) -{ - struct hv_vp_assist_page *vp_ap = - hv_get_vp_assist_page(smp_processor_id()); - - if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) - vp_ap->nested_control.features.directhypercall = 1; - vp_ap->current_nested_vmcs = phys_addr; - vp_ap->enlighten_vmentry = 1; -} - -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); -#else /* !IS_ENABLED(CONFIG_HYPERV) */ -static __always_inline bool kvm_is_using_evmcs(void) { return false; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static __always_inline void evmcs_write32(unsigned long field, u32 value) {} -static __always_inline void evmcs_write16(unsigned long field, u16 value) {} -static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } -static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } -static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } -static inline void evmcs_load(u64 phys_addr) {} -#endif /* IS_ENABLED(CONFIG_HYPERV) */ - #define EVMPTR_INVALID (-1ULL) #define EVMPTR_MAP_PENDING (-2ULL) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d1b4a85def0a..0ad66b9207e8 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -12,6 +12,7 @@ #include "mmu.h" #include "nested.h" #include "pmu.h" +#include "posted_intr.h" #include "sgx.h" #include "trace.h" #include "vmx.h" @@ -3830,8 +3831,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) if (!pi_test_and_clear_on(vmx->nested.pi_desc)) return 0; - max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256); - if (max_irr != 256) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0) { vapic_page = vmx->nested.virtual_apic_map.hva; if (!vapic_page) goto mmio_needed; @@ -3964,8 +3965,40 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection) { - return nested_vmx_preemption_timer_pending(vcpu) || - to_vmx(vcpu)->nested.mtf_pending; + struct vcpu_vmx *vmx = to_vmx(vcpu); + void *vapic = vmx->nested.virtual_apic_map.hva; + int max_irr, vppr; + + if (nested_vmx_preemption_timer_pending(vcpu) || + vmx->nested.mtf_pending) + return true; + + /* + * Virtual Interrupt Delivery doesn't require manual injection. Either + * the interrupt is already in GUEST_RVI and will be recognized by CPU + * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move + * the interrupt from the PIR to RVI prior to entering the guest. + */ + if (for_injection) + return false; + + if (!nested_cpu_has_vid(get_vmcs12(vcpu)) || + __vmx_interrupt_blocked(vcpu)) + return false; + + if (!vapic) + return false; + + vppr = *((u32 *)(vapic + APIC_PROCPRI)); + + if (vmx->nested.pi_pending && vmx->nested.pi_desc && + pi_test_on(vmx->nested.pi_desc)) { + max_irr = pi_find_highest_vector(vmx->nested.pi_desc); + if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0)) + return true; + } + + return false; } /* diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 26992076552e..1715d2ab07be 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,97 +2,8 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#define POSTED_INTR_ON 0 -#define POSTED_INTR_SN 1 - -#define PID_TABLE_ENTRY_VALID 1 - -/* Posted-Interrupt Descriptor */ -struct pi_desc { - u32 pir[8]; /* Posted interrupt requested */ - union { - struct { - /* bit 256 - Outstanding Notification */ - u16 on : 1, - /* bit 257 - Suppress Notification */ - sn : 1, - /* bit 271:258 - Reserved */ - rsvd_1 : 14; - /* bit 279:272 - Notification Vector */ - u8 nv; - /* bit 287:280 - Reserved */ - u8 rsvd_2; - /* bit 319:288 - Notification Destination */ - u32 ndst; - }; - u64 control; - }; - u32 rsvd[6]; -} __aligned(64); - -static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) -{ - return test_and_set_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) -{ - return test_and_clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc) -{ - return test_and_clear_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) -{ - return test_and_set_bit(vector, (unsigned long *)pi_desc->pir); -} - -static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) -{ - return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS); -} - -static inline void pi_set_sn(struct pi_desc *pi_desc) -{ - set_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_set_on(struct pi_desc *pi_desc) -{ - set_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_clear_on(struct pi_desc *pi_desc) -{ - clear_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline void pi_clear_sn(struct pi_desc *pi_desc) -{ - clear_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_on(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_ON, - (unsigned long *)&pi_desc->control); -} - -static inline bool pi_test_sn(struct pi_desc *pi_desc) -{ - return test_bit(POSTED_INTR_SN, - (unsigned long *)&pi_desc->control); -} +#include <linux/find.h> +#include <asm/posted_intr.h> void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu); @@ -103,4 +14,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void vmx_pi_start_assignment(struct kvm *kvm); +static inline int pi_find_highest_vector(struct pi_desc *pi_desc) +{ + int vec; + + vec = find_last_bit((unsigned long *)pi_desc->pir, 256); + return vec < 256 ? vec : -1; +} + #endif /* __KVM_X86_VMX_POSTED_INTR_H */ diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index f5f652a546bf..2e0106d9d371 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -66,6 +66,8 @@ #include "vmx.h" #include "x86.h" #include "smm.h" +#include "vmx_onhyperv.h" +#include "posted_intr.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 912b0c469742..6be1627d888e 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -7,10 +7,10 @@ #include <asm/kvm.h> #include <asm/intel_pt.h> #include <asm/perf_event.h> +#include <asm/posted_intr.h> #include "capabilities.h" #include "../kvm_cache_regs.h" -#include "posted_intr.h" #include "vmcs.h" #include "vmx_ops.h" #include "../cpuid.h" diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.c b/arch/x86/kvm/vmx/vmx_onhyperv.c new file mode 100644 index 000000000000..b9a8b91166d0 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "capabilities.h" +#include "vmx_onhyperv.h" + +DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h new file mode 100644 index 000000000000..11541d272dbd --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ +#define __ARCH_X86_KVM_VMX_ONHYPERV_H__ + +#include <asm/hyperv-tlfs.h> + +#include <linux/jump_label.h> + +#include "capabilities.h" +#include "hyperv.h" +#include "vmcs12.h" + +#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) + +#if IS_ENABLED(CONFIG_HYPERV) + +DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +static __always_inline bool kvm_is_using_evmcs(void) +{ + return static_branch_unlikely(&__kvm_is_using_evmcs); +} + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); + return offset; +} + +static __always_inline void evmcs_write64(unsigned long field, u64 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u64 *)((char *)current_evmcs + offset) = value; + + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write32(unsigned long field, u32 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u32 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write16(unsigned long field, u16 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u16 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline u64 evmcs_read64(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u64 *)((char *)current_evmcs + offset); +} + +static __always_inline u32 evmcs_read32(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u32 *)((char *)current_evmcs + offset); +} + +static __always_inline u16 evmcs_read16(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u16 *)((char *)current_evmcs + offset); +} + +static inline void evmcs_load(u64 phys_addr) +{ + struct hv_vp_assist_page *vp_ap = + hv_get_vp_assist_page(smp_processor_id()); + + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) + vp_ap->nested_control.features.directhypercall = 1; + vp_ap->current_nested_vmcs = phys_addr; + vp_ap->enlighten_vmentry = 1; +} + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); +#else /* !IS_ENABLED(CONFIG_HYPERV) */ +static __always_inline bool kvm_is_using_evmcs(void) { return false; } +static __always_inline void evmcs_write64(unsigned long field, u64 value) {} +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } +static inline void evmcs_load(u64 phys_addr) {} +#endif /* IS_ENABLED(CONFIG_HYPERV) */ + +#endif /* __ARCH_X86_KVM_VMX_ONHYPERV_H__ */ diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 6a0c6e81f7f3..8060e5fc6dbd 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -6,7 +6,7 @@ #include <asm/vmx.h> -#include "hyperv.h" +#include "vmx_onhyperv.h" #include "vmcs.h" #include "../x86.h" diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 3da3c266a66f..a936219aebb8 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -2845,6 +2845,9 @@ static int btintel_setup_combined(struct hci_dev *hdev) btintel_set_dsm_reset_method(hdev, &ver_tlv); err = btintel_bootloader_setup_tlv(hdev, &ver_tlv); + if (err) + goto exit_error; + btintel_register_devcoredump_support(hdev); break; default: diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index 84d7033e5efe..ef51dfb39baa 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -40,10 +40,14 @@ struct qcom_cpufreq_match_data { const char **genpd_names; }; +struct qcom_cpufreq_drv_cpu { + int opp_token; +}; + struct qcom_cpufreq_drv { - int *opp_tokens; u32 versions; const struct qcom_cpufreq_match_data *data; + struct qcom_cpufreq_drv_cpu cpus[]; }; static struct platform_device *cpufreq_dt_pdev, *cpufreq_pdev; @@ -243,42 +247,39 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) return -ENOENT; } - drv = kzalloc(sizeof(*drv), GFP_KERNEL); - if (!drv) + drv = devm_kzalloc(&pdev->dev, struct_size(drv, cpus, num_possible_cpus()), + GFP_KERNEL); + if (!drv) { + of_node_put(np); return -ENOMEM; + } match = pdev->dev.platform_data; drv->data = match->data; if (!drv->data) { - ret = -ENODEV; - goto free_drv; + of_node_put(np); + return -ENODEV; } if (drv->data->get_version) { speedbin_nvmem = of_nvmem_cell_get(np, NULL); if (IS_ERR(speedbin_nvmem)) { - ret = dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), - "Could not get nvmem cell\n"); - goto free_drv; + of_node_put(np); + return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), + "Could not get nvmem cell\n"); } ret = drv->data->get_version(cpu_dev, speedbin_nvmem, &pvs_name, drv); if (ret) { + of_node_put(np); nvmem_cell_put(speedbin_nvmem); - goto free_drv; + return ret; } nvmem_cell_put(speedbin_nvmem); } of_node_put(np); - drv->opp_tokens = kcalloc(num_possible_cpus(), sizeof(*drv->opp_tokens), - GFP_KERNEL); - if (!drv->opp_tokens) { - ret = -ENOMEM; - goto free_drv; - } - for_each_possible_cpu(cpu) { struct dev_pm_opp_config config = { .supported_hw = NULL, @@ -304,9 +305,9 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) } if (config.supported_hw || config.genpd_names) { - drv->opp_tokens[cpu] = dev_pm_opp_set_config(cpu_dev, &config); - if (drv->opp_tokens[cpu] < 0) { - ret = drv->opp_tokens[cpu]; + drv->cpus[cpu].opp_token = dev_pm_opp_set_config(cpu_dev, &config); + if (drv->cpus[cpu].opp_token < 0) { + ret = drv->cpus[cpu].opp_token; dev_err(cpu_dev, "Failed to set OPP config\n"); goto free_opp; } @@ -325,11 +326,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) free_opp: for_each_possible_cpu(cpu) - dev_pm_opp_clear_config(drv->opp_tokens[cpu]); - kfree(drv->opp_tokens); -free_drv: - kfree(drv); - + dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); return ret; } @@ -341,10 +338,7 @@ static void qcom_cpufreq_remove(struct platform_device *pdev) platform_device_unregister(cpufreq_dt_pdev); for_each_possible_cpu(cpu) - dev_pm_opp_clear_config(drv->opp_tokens[cpu]); - - kfree(drv->opp_tokens); - kfree(drv); + dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); } static struct platform_driver qcom_cpufreq_driver = { diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index 793f1a7ad5e3..53fdfd32a7e7 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -3,6 +3,7 @@ // Copyright (c) 2013-2014 Freescale Semiconductor, Inc // Copyright (c) 2017 Sysam, Angelo Dureghello <angelo@xxxxxxxx> +#include <linux/clk.h> #include <linux/dmapool.h> #include <linux/module.h> #include <linux/slab.h> @@ -74,18 +75,10 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan) flags = fsl_edma_drvflags(fsl_chan); val = edma_readl_chreg(fsl_chan, ch_sbr); - /* Remote/local swapped wrongly on iMX8 QM Audio edma */ - if (flags & FSL_EDMA_DRV_QUIRK_SWAPPED) { - if (!fsl_chan->is_rxchan) - val |= EDMA_V3_CH_SBR_RD; - else - val |= EDMA_V3_CH_SBR_WR; - } else { - if (fsl_chan->is_rxchan) - val |= EDMA_V3_CH_SBR_RD; - else - val |= EDMA_V3_CH_SBR_WR; - } + if (fsl_chan->is_rxchan) + val |= EDMA_V3_CH_SBR_RD; + else + val |= EDMA_V3_CH_SBR_WR; if (fsl_chan->is_remote) val &= ~(EDMA_V3_CH_SBR_RD | EDMA_V3_CH_SBR_WR); @@ -97,8 +90,8 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan) * ch_mux: With the exception of 0, attempts to write a value * already in use will be forced to 0. */ - if (!edma_readl_chreg(fsl_chan, ch_mux)) - edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux); + if (!edma_readl(fsl_chan->edma, fsl_chan->mux_addr)) + edma_writel(fsl_chan->edma, fsl_chan->srcid, fsl_chan->mux_addr); } val = edma_readl_chreg(fsl_chan, ch_csr); @@ -134,7 +127,7 @@ static void fsl_edma3_disable_request(struct fsl_edma_chan *fsl_chan) flags = fsl_edma_drvflags(fsl_chan); if (flags & FSL_EDMA_DRV_HAS_CHMUX) - edma_writel_chreg(fsl_chan, 0, ch_mux); + edma_writel(fsl_chan->edma, 0, fsl_chan->mux_addr); val &= ~EDMA_V3_CH_CSR_ERQ; edma_writel_chreg(fsl_chan, val, ch_csr); @@ -754,6 +747,8 @@ struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(struct dma_chan *chan, fsl_desc->iscyclic = false; fsl_chan->is_sw = true; + if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_MEM_REMOTE) + fsl_chan->is_remote = true; /* To match with copy_align and max_seg_size so 1 tcd is enough */ fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[0].vtcd, dma_src, dma_dst, @@ -802,6 +797,9 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan) { struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan); + if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK) + clk_prepare_enable(fsl_chan->clk); + fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev, sizeof(struct fsl_edma_hw_tcd), 32, 0); @@ -829,6 +827,9 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan) fsl_chan->tcd_pool = NULL; fsl_chan->is_sw = false; fsl_chan->srcid = 0; + fsl_chan->is_remote = false; + if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK) + clk_disable_unprepare(fsl_chan->clk); } void fsl_edma_cleanup_vchan(struct dma_device *dmadev) diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index 92fe53faa53b..6028389de408 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -146,6 +146,7 @@ struct fsl_edma_chan { enum dma_data_direction dma_dir; char chan_name[32]; struct fsl_edma_hw_tcd __iomem *tcd; + void __iomem *mux_addr; u32 real_count; struct work_struct issue_worker; struct platform_device *pdev; @@ -177,8 +178,7 @@ struct fsl_edma_desc { #define FSL_EDMA_DRV_HAS_PD BIT(5) #define FSL_EDMA_DRV_HAS_CHCLK BIT(6) #define FSL_EDMA_DRV_HAS_CHMUX BIT(7) -/* imx8 QM audio edma remote local swapped */ -#define FSL_EDMA_DRV_QUIRK_SWAPPED BIT(8) +#define FSL_EDMA_DRV_MEM_REMOTE BIT(8) /* control and status register is in tcd address space, edma3 reg layout */ #define FSL_EDMA_DRV_SPLIT_REG BIT(9) #define FSL_EDMA_DRV_BUS_8BYTE BIT(10) @@ -207,6 +207,8 @@ struct fsl_edma_drvdata { u32 chreg_off; u32 chreg_space_sz; u32 flags; + u32 mux_off; /* channel mux register offset */ + u32 mux_skip; /* how much skip for each channel */ int (*setup_irq)(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma); }; diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 42a338cbe614..8a0ae9054899 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -340,16 +340,19 @@ static struct fsl_edma_drvdata imx7ulp_data = { }; static struct fsl_edma_drvdata imx8qm_data = { - .flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3, + .flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE, .chreg_space_sz = 0x10000, .chreg_off = 0x10000, .setup_irq = fsl_edma3_irq_init, }; -static struct fsl_edma_drvdata imx8qm_audio_data = { - .flags = FSL_EDMA_DRV_QUIRK_SWAPPED | FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3, +static struct fsl_edma_drvdata imx8ulp_data = { + .flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_CHCLK | FSL_EDMA_DRV_HAS_DMACLK | + FSL_EDMA_DRV_EDMA3, .chreg_space_sz = 0x10000, .chreg_off = 0x10000, + .mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux), + .mux_skip = 0x10000, .setup_irq = fsl_edma3_irq_init, }; @@ -364,6 +367,8 @@ static struct fsl_edma_drvdata imx93_data4 = { .flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4, .chreg_space_sz = 0x8000, .chreg_off = 0x10000, + .mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux), + .mux_skip = 0x8000, .setup_irq = fsl_edma3_irq_init, }; @@ -372,7 +377,7 @@ static const struct of_device_id fsl_edma_dt_ids[] = { { .compatible = "fsl,ls1028a-edma", .data = &ls1028a_data}, { .compatible = "fsl,imx7ulp-edma", .data = &imx7ulp_data}, { .compatible = "fsl,imx8qm-edma", .data = &imx8qm_data}, - { .compatible = "fsl,imx8qm-adma", .data = &imx8qm_audio_data}, + { .compatible = "fsl,imx8ulp-edma", .data = &imx8ulp_data}, { .compatible = "fsl,imx93-edma3", .data = &imx93_data3}, { .compatible = "fsl,imx93-edma4", .data = &imx93_data4}, { /* sentinel */ } @@ -427,6 +432,7 @@ static int fsl_edma_probe(struct platform_device *pdev) struct fsl_edma_engine *fsl_edma; const struct fsl_edma_drvdata *drvdata = NULL; u32 chan_mask[2] = {0, 0}; + char clk_name[36]; struct edma_regs *regs; int chans; int ret, i; @@ -540,12 +546,23 @@ static int fsl_edma_probe(struct platform_device *pdev) offsetof(struct fsl_edma3_ch_reg, tcd) : 0; fsl_chan->tcd = fsl_edma->membase + i * drvdata->chreg_space_sz + drvdata->chreg_off + len; + fsl_chan->mux_addr = fsl_edma->membase + drvdata->mux_off + i * drvdata->mux_skip; + if (drvdata->flags & FSL_EDMA_DRV_HAS_CHCLK) { + snprintf(clk_name, sizeof(clk_name), "ch%02d", i); + fsl_chan->clk = devm_clk_get_enabled(&pdev->dev, + (const char *)clk_name); + + if (IS_ERR(fsl_chan->clk)) + return PTR_ERR(fsl_chan->clk); + } fsl_chan->pdev = pdev; vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev); edma_write_tcdreg(fsl_chan, 0, csr); fsl_edma_chan_mux(fsl_chan, 0, false); + if (fsl_chan->edma->drvdata->flags & FSL_EDMA_DRV_HAS_CHCLK) + clk_disable_unprepare(fsl_chan->clk); } ret = fsl_edma->drvdata->setup_irq(pdev, fsl_edma); diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index b59e3041fd62..f0e9f250669e 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -229,6 +229,7 @@ config QCOM_SCM_DOWNLOAD_MODE_DEFAULT config SYSFB bool select BOOT_VESA_SUPPORT + select SCREEN_INFO config SYSFB_SIMPLEFB bool "Mark VGA/VBE/EFI FB as generic system framebuffer" diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 3c197db42c9d..defd7a36cb08 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -77,6 +77,8 @@ static __init int sysfb_init(void) bool compatible; int ret = 0; + screen_info_apply_fixups(); + mutex_lock(&disable_lock); if (disabled) goto unlock_mutex; diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index d0255ea98348..247e7d675e2b 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -1556,7 +1556,7 @@ static void skl_wrpll_params_populate(struct skl_wrpll_params *params, } static int -skl_ddi_calculate_wrpll(int clock /* in Hz */, +skl_ddi_calculate_wrpll(int clock, int ref_clock, struct skl_wrpll_params *wrpll_params) { @@ -1581,7 +1581,7 @@ skl_ddi_calculate_wrpll(int clock /* in Hz */, }; unsigned int dco, d, i; unsigned int p0, p1, p2; - u64 afe_clock = clock * 5; /* AFE Clock is 5x Pixel clock */ + u64 afe_clock = (u64)clock * 1000 * 5; /* AFE Clock is 5x Pixel clock, in Hz */ for (d = 0; d < ARRAY_SIZE(dividers); d++) { for (dco = 0; dco < ARRAY_SIZE(dco_central_freq); dco++) { @@ -1713,7 +1713,7 @@ static int skl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state) ctrl1 |= DPLL_CTRL1_HDMI_MODE(0); - ret = skl_ddi_calculate_wrpll(crtc_state->port_clock * 1000, + ret = skl_ddi_calculate_wrpll(crtc_state->port_clock, i915->display.dpll.ref_clks.nssc, &wrpll_params); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h index 8023c85c7fa0..74059384892a 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h @@ -249,7 +249,7 @@ #define HDCP2_STREAM_STATUS(dev_priv, trans, port) \ (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_STREAM_STATUS(trans) : \ - PIPE_HDCP2_STREAM_STATUS(pipe)) + PIPE_HDCP2_STREAM_STATUS(port)) #define _PORTA_HDCP2_AUTH_STREAM 0x66F00 #define _PORTB_HDCP2_AUTH_STREAM 0x66F04 diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 3f90403d86cb..0808b54d3c51 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -2781,26 +2781,6 @@ oa_configure_all_contexts(struct i915_perf_stream *stream, return 0; } -static int -gen12_configure_all_contexts(struct i915_perf_stream *stream, - const struct i915_oa_config *oa_config, - struct i915_active *active) -{ - struct flex regs[] = { - { - GEN8_R_PWR_CLK_STATE(RENDER_RING_BASE), - CTX_R_PWR_CLK_STATE, - }, - }; - - if (stream->engine->class != RENDER_CLASS) - return 0; - - return oa_configure_all_contexts(stream, - regs, ARRAY_SIZE(regs), - active); -} - static int lrc_configure_all_contexts(struct i915_perf_stream *stream, const struct i915_oa_config *oa_config, @@ -2907,7 +2887,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, { struct drm_i915_private *i915 = stream->perf->i915; struct intel_uncore *uncore = stream->uncore; - struct i915_oa_config *oa_config = stream->oa_config; bool periodic = stream->periodic; u32 period_exponent = stream->period_exponent; u32 sqcnt1; @@ -2951,15 +2930,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream, intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1); - /* - * Update all contexts prior writing the mux configurations as we need - * to make sure all slices/subslices are ON before writing to NOA - * registers. - */ - ret = gen12_configure_all_contexts(stream, oa_config, active); - if (ret) - return ret; - /* * For Gen12, performance counters are context * saved/restored. Only enable it for the context that @@ -3014,9 +2984,6 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream) _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING)); } - /* Reset all contexts' slices/subslices configurations. */ - gen12_configure_all_contexts(stream, NULL, NULL); - /* disable the context save/restore or OAR counters */ if (stream->ctx) gen12_configure_oar_context(stream, NULL); diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 1b2ff0c40fc1..6c599a9f49ee 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -64,7 +64,8 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, * to the caller, instead of a normal nouveau_bo ttm reference. */ ret = drm_gem_object_init(dev, &nvbo->bo.base, size); if (ret) { - nouveau_bo_ref(NULL, &nvbo); + drm_gem_object_release(&nvbo->bo.base); + kfree(nvbo); obj = ERR_PTR(-ENOMEM); goto unlock; } diff --git a/drivers/gpu/drm/virtio/virtgpu_submit.c b/drivers/gpu/drm/virtio/virtgpu_submit.c index 5c514946bbad..d530c058f53e 100644 --- a/drivers/gpu/drm/virtio/virtgpu_submit.c +++ b/drivers/gpu/drm/virtio/virtgpu_submit.c @@ -48,7 +48,7 @@ struct virtio_gpu_submit { static int virtio_gpu_do_fence_wait(struct virtio_gpu_submit *submit, struct dma_fence *in_fence) { - u32 context = submit->fence_ctx + submit->ring_idx; + u64 context = submit->fence_ctx + submit->ring_idx; if (dma_fence_match_context(in_fence, context)) return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c index 5efc6a766f64..588d50ababf6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c @@ -32,7 +32,6 @@ #define VMW_FENCE_WRAP (1 << 31) struct vmw_fence_manager { - int num_fence_objects; struct vmw_private *dev_priv; spinlock_t lock; struct list_head fence_list; @@ -124,13 +123,13 @@ static void vmw_fence_obj_destroy(struct dma_fence *f) { struct vmw_fence_obj *fence = container_of(f, struct vmw_fence_obj, base); - struct vmw_fence_manager *fman = fman_from_fence(fence); - spin_lock(&fman->lock); - list_del_init(&fence->head); - --fman->num_fence_objects; - spin_unlock(&fman->lock); + if (!list_empty(&fence->head)) { + spin_lock(&fman->lock); + list_del_init(&fence->head); + spin_unlock(&fman->lock); + } fence->destroy(fence); } @@ -257,7 +256,6 @@ static const struct dma_fence_ops vmw_fence_ops = { .release = vmw_fence_obj_destroy, }; - /* * Execute signal actions on fences recently signaled. * This is done from a workqueue so we don't have to execute @@ -355,7 +353,6 @@ static int vmw_fence_obj_init(struct vmw_fence_manager *fman, goto out_unlock; } list_add_tail(&fence->head, &fman->fence_list); - ++fman->num_fence_objects; out_unlock: spin_unlock(&fman->lock); @@ -403,7 +400,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, u32 passed_seqno) { u32 goal_seqno; - struct vmw_fence_obj *fence; + struct vmw_fence_obj *fence, *next_fence; if (likely(!fman->seqno_valid)) return false; @@ -413,7 +410,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman, return false; fman->seqno_valid = false; - list_for_each_entry(fence, &fman->fence_list, head) { + list_for_each_entry_safe(fence, next_fence, &fman->fence_list, head) { if (!list_empty(&fence->seq_passed_actions)) { fman->seqno_valid = true; vmw_fence_goal_write(fman->dev_priv, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c index c45b4724e414..e20f64b67b26 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c @@ -92,7 +92,7 @@ static int vmw_overlay_send_put(struct vmw_private *dev_priv, { struct vmw_escape_video_flush *flush; size_t fifo_size; - bool have_so = (dev_priv->active_display_unit == vmw_du_screen_object); + bool have_so = (dev_priv->active_display_unit != vmw_du_legacy); int i, num_items; SVGAGuestPtr ptr; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 4ccab07faff0..cb03c589ab22 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -868,6 +868,32 @@ vmw_stdu_connector_mode_valid(struct drm_connector *connector, return MODE_OK; } +/* + * Trigger a modeset if the X,Y position of the Screen Target changes. + * This is needed when multi-mon is cycled. The original Screen Target will have + * the same mode but its relative X,Y position in the topology will change. + */ +static int vmw_stdu_connector_atomic_check(struct drm_connector *conn, + struct drm_atomic_state *state) +{ + struct drm_connector_state *conn_state; + struct vmw_screen_target_display_unit *du; + struct drm_crtc_state *new_crtc_state; + + conn_state = drm_atomic_get_connector_state(state, conn); + du = vmw_connector_to_stdu(conn); + + if (!conn_state->crtc) + return 0; + + new_crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); + if (du->base.gui_x != du->base.set_gui_x || + du->base.gui_y != du->base.set_gui_y) + new_crtc_state->mode_changed = true; + + return 0; +} + static const struct drm_connector_funcs vmw_stdu_connector_funcs = { .dpms = vmw_du_connector_dpms, .detect = vmw_du_connector_detect, @@ -882,7 +908,8 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = { static const struct drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = { .get_modes = vmw_connector_get_modes, - .mode_valid = vmw_stdu_connector_mode_valid + .mode_valid = vmw_stdu_connector_mode_valid, + .atomic_check = vmw_stdu_connector_atomic_check, }; diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index bdb578e0899f..4b59687ff5d8 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -288,12 +288,22 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) mp2_ops->start(privdata, info); cl_data->sensor_sts[i] = amd_sfh_wait_for_response (privdata, cl_data->sensor_idx[i], SENSOR_ENABLED); + + if (cl_data->sensor_sts[i] == SENSOR_ENABLED) + cl_data->is_any_sensor_enabled = true; + } + + if (!cl_data->is_any_sensor_enabled || + (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) { + dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", + cl_data->is_any_sensor_enabled); + rc = -EOPNOTSUPP; + goto cleanup; } for (i = 0; i < cl_data->num_hid_devices; i++) { cl_data->cur_hid_dev = i; if (cl_data->sensor_sts[i] == SENSOR_ENABLED) { - cl_data->is_any_sensor_enabled = true; rc = amdtp_hid_probe(i, cl_data); if (rc) goto cleanup; @@ -305,12 +315,6 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) cl_data->sensor_sts[i]); } - if (!cl_data->is_any_sensor_enabled || - (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) { - dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", cl_data->is_any_sensor_enabled); - rc = -EOPNOTSUPP; - goto cleanup; - } schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP)); return 0; diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 002cbaa16bd1..d2fe14ce423e 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -714,13 +714,12 @@ static int wacom_intuos_get_tool_type(int tool_id) case 0x8e2: /* IntuosHT2 pen */ case 0x022: case 0x200: /* Pro Pen 3 */ - case 0x04200: /* Pro Pen 3 */ case 0x10842: /* MobileStudio Pro Pro Pen slim */ case 0x14802: /* Intuos4/5 13HD/24HD Classic Pen */ case 0x16802: /* Cintiq 13HD Pro Pen */ case 0x18802: /* DTH2242 Pen */ case 0x10802: /* Intuos4/5 13HD/24HD General Pen */ - case 0x80842: /* Intuos Pro and Cintiq Pro 3D Pen */ + case 0x8842: /* Intuos Pro and Cintiq Pro 3D Pen */ tool_type = BTN_TOOL_PEN; break; diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 4f5829b726a7..72fd2fe8f6fe 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -194,11 +194,24 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) spin_unlock(&trig->leddev_list_lock); led_cdev->trigger = trig; + /* + * Some activate() calls use led_trigger_event() to initialize + * the brightness of the LED for which the trigger is being set. + * Ensure the led_cdev is visible on trig->led_cdevs for this. + */ + synchronize_rcu(); + + /* + * If "set brightness to 0" is pending in workqueue, + * we don't want that to be reordered after ->activate() + */ + flush_work(&led_cdev->set_brightness_work); + + ret = 0; if (trig->activate) ret = trig->activate(led_cdev); else - ret = 0; - + led_set_brightness(led_cdev, trig->brightness); if (ret) goto err_activate; @@ -269,19 +282,6 @@ void led_trigger_set_default(struct led_classdev *led_cdev) } EXPORT_SYMBOL_GPL(led_trigger_set_default); -void led_trigger_rename_static(const char *name, struct led_trigger *trig) -{ - /* new name must be on a temporary string to prevent races */ - BUG_ON(name == trig->name); - - down_write(&triggers_list_lock); - /* this assumes that trig->name was originaly allocated to - * non constant storage */ - strcpy((char *)trig->name, name); - up_write(&triggers_list_lock); -} -EXPORT_SYMBOL_GPL(led_trigger_rename_static); - /* LED Trigger Interface */ int led_trigger_register(struct led_trigger *trig) @@ -386,6 +386,8 @@ void led_trigger_event(struct led_trigger *trig, if (!trig) return; + trig->brightness = brightness; + rcu_read_lock(); list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) led_set_brightness(led_cdev, brightness); diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c index b4688d1d9d2b..1d213c999d40 100644 --- a/drivers/leds/trigger/ledtrig-timer.c +++ b/drivers/leds/trigger/ledtrig-timer.c @@ -110,11 +110,6 @@ static int timer_trig_activate(struct led_classdev *led_cdev) led_cdev->flags &= ~LED_INIT_DEFAULT_TRIGGER; } - /* - * If "set brightness to 0" is pending in workqueue, we don't - * want that to be reordered after blink_set() - */ - flush_work(&led_cdev->set_brightness_work); led_blink_set(led_cdev, &led_cdev->blink_delay_on, &led_cdev->blink_delay_off); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 24c914015973..49b1fa965116 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) if (rx_ring->vsi->type == ICE_VSI_PF) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - rx_ring->xdp_prog = NULL; + WRITE_ONCE(rx_ring->xdp_prog, NULL); if (rx_ring->xsk_pool) { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index f53566cb6bfb..67511153081a 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx) static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx) { ice_clean_tx_ring(vsi->tx_rings[q_idx]); - if (ice_is_xdp_ena_vsi(vsi)) { - synchronize_rcu(); + if (ice_is_xdp_ena_vsi(vsi)) ice_clean_tx_ring(vsi->xdp_rings[q_idx]); - } ice_clean_rx_ring(vsi->rx_rings[q_idx]); } @@ -180,11 +178,12 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) usleep_range(1000, 2000); } + synchronize_net(); + netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); + ice_qvec_dis_irq(vsi, rx_ring, q_vector); ice_qvec_toggle_napi(vsi, q_vector, false); - netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); - ice_fill_txq_meta(vsi, tx_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); if (err) @@ -199,10 +198,8 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } - err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); - if (err) - return err; + ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false); ice_qp_clean_rings(vsi, q_idx); ice_qp_reset_stats(vsi, q_idx); @@ -1068,6 +1065,10 @@ bool ice_xmit_zc(struct ice_tx_ring *xdp_ring) ice_clean_xdp_irq_zc(xdp_ring); + if (!netif_carrier_ok(xdp_ring->vsi->netdev) || + !netif_running(xdp_ring->vsi->netdev)) + return true; + budget = ICE_DESC_UNUSED(xdp_ring); budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring)); @@ -1111,7 +1112,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, struct ice_vsi *vsi = np->vsi; struct ice_tx_ring *ring; - if (test_bit(ICE_VSI_DOWN, vsi->state)) + if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev)) return -ENETDOWN; if (!ice_is_xdp_ena_vsi(vsi)) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index e83700ad7e62..d80bbcdeb93e 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6208,21 +6208,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - switch (qopt->cmd) { - case TAPRIO_CMD_REPLACE: - break; - case TAPRIO_CMD_DESTROY: - return igc_tsn_clear_schedule(adapter); - case TAPRIO_CMD_STATS: - igc_taprio_stats(adapter->netdev, &qopt->stats); - return 0; - case TAPRIO_CMD_QUEUE_STATS: - igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); - return 0; - default: - return -EOPNOTSUPP; - } - if (qopt->base_time < 0) return -ERANGE; @@ -6331,7 +6316,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, if (hw->mac.type != igc_i225) return -EOPNOTSUPP; - err = igc_save_qbv_schedule(adapter, qopt); + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + err = igc_save_qbv_schedule(adapter, qopt); + break; + case TAPRIO_CMD_DESTROY: + err = igc_tsn_clear_schedule(adapter); + break; + case TAPRIO_CMD_STATS: + igc_taprio_stats(adapter->netdev, &qopt->stats); + return 0; + case TAPRIO_CMD_QUEUE_STATS: + igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); + return 0; + default: + return -EOPNOTSUPP; + } + if (err) return err; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 05f4aa11b95c..34051c9abd97 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -953,13 +953,13 @@ static void mvpp2_bm_pool_update_fc(struct mvpp2_port *port, static void mvpp2_bm_pool_update_priv_fc(struct mvpp2 *priv, bool en) { struct mvpp2_port *port; - int i; + int i, j; for (i = 0; i < priv->port_count; i++) { port = priv->port_list[i]; if (port->priv->percpu_pools) { - for (i = 0; i < port->nrxqs; i++) - mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[i], + for (j = 0; j < port->nrxqs; j++) + mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[j], port->tx_fc & en); } else { mvpp2_bm_pool_update_fc(port, port->pool_long, port->tx_fc & en); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index fadfa8b50beb..8c4e3ecef590 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -920,6 +920,7 @@ mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv, mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh); mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); err_mod_hdr: + *attr = *old_attr; kfree(old_attr); err_attr: kvfree(spec); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index ce29e3172120..de83567aae79 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -50,9 +50,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev) MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap)) caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD; - if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) || - MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)) + if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) && + ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) || + MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))) caps |= MLX5_IPSEC_CAP_PRIO; if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 38263d5c98b3..50db127e6371 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1223,7 +1223,12 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext); + if (err) { + netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err); + goto out; + } + mlx5_toggle_port_link(mdev); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c index 3a9cdf79403a..6b17346aa4ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c @@ -206,6 +206,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev) static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded) { struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset; + struct devlink *devlink = priv_to_devlink(dev); /* if this is the driver that initiated the fw reset, devlink completed the reload */ if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) { @@ -217,9 +218,11 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n"); else mlx5_load_one(dev, true); - devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0, + devl_lock(devlink); + devlink_remote_reload_actions_performed(devlink, 0, BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE)); + devl_unlock(devlink); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c index 612e666ec263..e2230c8f1815 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c @@ -48,6 +48,7 @@ static struct mlx5_irq * irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc) { struct irq_affinity_desc auto_desc = {}; + struct mlx5_irq *irq; u32 irq_index; int err; @@ -64,9 +65,12 @@ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_de else cpu_get(pool, cpumask_first(&af_desc->mask)); } - return mlx5_irq_alloc(pool, irq_index, - cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc, - NULL); + irq = mlx5_irq_alloc(pool, irq_index, + cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc, + NULL); + if (IS_ERR(irq)) + xa_erase(&pool->irqs, irq_index); + return irq; } /* Looking for the IRQ with the smallest refcount that fits req_mask. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index dfc2ba6f780a..18cf756bad8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1512,7 +1512,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev, goto unlock; for (i = 0; i < ldev->ports; i++) { - if (ldev->pf[MLX5_LAG_P1].netdev == slave) { + if (ldev->pf[i].netdev == slave) { port = i; break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 2237b3d01e0e..11f11248feb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2130,7 +2130,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) /* Panic tear down fw command will stop the PCI bus communication * with the HCA, so the health poll is no longer needed. */ - mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_fast_teardown_hca(dev); @@ -2165,6 +2164,7 @@ static void shutdown(struct pci_dev *pdev) mlx5_core_info(dev, "Shutdown was called\n"); set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); + mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c index 30218f37d528..2028acbe85ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c @@ -90,6 +90,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev) struct mlx5_core_dev *mdev = sf_dev->mdev; set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state); + mlx5_drain_health_wq(mdev); mlx5_unload_one(mdev, false); } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d759f3373b17..8a732edac15a 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4256,7 +4256,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, if (unlikely(!rtl_tx_slots_avail(tp))) { if (net_ratelimit()) netdev_err(dev, "BUG! Tx Ring full when queue awake!\n"); - goto err_stop_0; + netif_stop_queue(dev); + return NETDEV_TX_BUSY; } opts[1] = rtl8169_tx_vlan_tag(skb); @@ -4312,11 +4313,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, dev_kfree_skb_any(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; - -err_stop_0: - netif_stop_queue(dev); - dev->stats.tx_dropped++; - return NETDEV_TX_BUSY; } static unsigned int rtl_last_frag_len(struct sk_buff *skb) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 3297aff969c8..11e08cb8d3c3 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1826,9 +1826,9 @@ static void axienet_dma_err_handler(struct work_struct *work) ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN)); axienet_set_mac_address(ndev, NULL); axienet_set_multicast_list(ndev); - axienet_setoptions(ndev, lp->options); napi_enable(&lp->napi_rx); napi_enable(&lp->napi_tx); + axienet_setoptions(ndev, lp->options); } /** diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 029c82f88ee3..9a0432145645 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1293,6 +1293,8 @@ static int ksz9131_config_init(struct phy_device *phydev) const struct device *dev_walker; int ret; + phydev->mdix_ctrl = ETH_TP_MDI_AUTO; + dev_walker = &phydev->mdio.dev; do { of_node = dev_walker->of_node; @@ -1342,28 +1344,30 @@ static int ksz9131_config_init(struct phy_device *phydev) #define MII_KSZ9131_AUTO_MDIX 0x1C #define MII_KSZ9131_AUTO_MDI_SET BIT(7) #define MII_KSZ9131_AUTO_MDIX_SWAP_OFF BIT(6) +#define MII_KSZ9131_DIG_AXAN_STS 0x14 +#define MII_KSZ9131_DIG_AXAN_STS_LINK_DET BIT(14) +#define MII_KSZ9131_DIG_AXAN_STS_A_SELECT BIT(12) static int ksz9131_mdix_update(struct phy_device *phydev) { int ret; - ret = phy_read(phydev, MII_KSZ9131_AUTO_MDIX); - if (ret < 0) - return ret; - - if (ret & MII_KSZ9131_AUTO_MDIX_SWAP_OFF) { - if (ret & MII_KSZ9131_AUTO_MDI_SET) - phydev->mdix_ctrl = ETH_TP_MDI; - else - phydev->mdix_ctrl = ETH_TP_MDI_X; + if (phydev->mdix_ctrl != ETH_TP_MDI_AUTO) { + phydev->mdix = phydev->mdix_ctrl; } else { - phydev->mdix_ctrl = ETH_TP_MDI_AUTO; - } + ret = phy_read(phydev, MII_KSZ9131_DIG_AXAN_STS); + if (ret < 0) + return ret; - if (ret & MII_KSZ9131_AUTO_MDI_SET) - phydev->mdix = ETH_TP_MDI; - else - phydev->mdix = ETH_TP_MDI_X; + if (ret & MII_KSZ9131_DIG_AXAN_STS_LINK_DET) { + if (ret & MII_KSZ9131_DIG_AXAN_STS_A_SELECT) + phydev->mdix = ETH_TP_MDI; + else + phydev->mdix = ETH_TP_MDI_X; + } else { + phydev->mdix = ETH_TP_MDI_INVALID; + } + } return 0; } diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 337899c69738..2604d9663a5b 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -1083,6 +1083,13 @@ static struct phy_driver realtek_drvs[] = { .handle_interrupt = genphy_handle_interrupt_no_ack, .suspend = genphy_suspend, .resume = genphy_resume, + }, { + PHY_ID_MATCH_EXACT(0x001cc960), + .name = "RTL8366S Gigabit Ethernet", + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, }; diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 0a662e42ed96..cb7d2f798fb4 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -179,6 +179,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) struct usbnet *dev = netdev_priv(netdev); __le16 res; int rc = 0; + int err; if (phy_id) { netdev_dbg(netdev, "Only internal phy supported\n"); @@ -189,11 +190,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc) if (loc == MII_BMSR) { u8 value; - sr_read_reg(dev, SR_NSR, &value); + err = sr_read_reg(dev, SR_NSR, &value); + if (err < 0) + return err; + if (value & NSR_LINKST) rc = 1; } - sr_share_read_word(dev, 1, loc, &res); + err = sr_share_read_word(dev, 1, loc, &res); + if (err < 0) + return err; + if (rc == 1) res = le16_to_cpu(res) | BMSR_LSTATUS; else diff --git a/drivers/pci/search.c b/drivers/pci/search.c index b4c138a6ec02..53840634fbfc 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -363,6 +363,37 @@ struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from) } EXPORT_SYMBOL(pci_get_class); +/** + * pci_get_base_class - searching for a PCI device by matching against the base class code only + * @class: search for a PCI device with this base class code + * @from: Previous PCI device found in search, or %NULL for new search. + * + * Iterates through the list of known PCI devices. If a PCI device is found + * with a matching base class code, the reference count to the device is + * incremented. See pci_match_one_device() to figure out how does this works. + * A new search is initiated by passing %NULL as the @from argument. + * Otherwise if @from is not %NULL, searches continue from next device on the + * global list. The reference count for @from is always decremented if it is + * not %NULL. + * + * Returns: + * A pointer to a matched PCI device, %NULL Otherwise. + */ +struct pci_dev *pci_get_base_class(unsigned int class, struct pci_dev *from) +{ + struct pci_device_id id = { + .vendor = PCI_ANY_ID, + .device = PCI_ANY_ID, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .class_mask = 0xFF0000, + .class = class << 16, + }; + + return pci_get_dev_by_id(&id, from); +} +EXPORT_SYMBOL(pci_get_base_class); + /** * pci_dev_present - Returns 1 if device matching the device list is present, 0 if not. * @ids: A pointer to a null terminated list of struct pci_device_id structures diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c index 5cf770a1bc31..4f6eade52202 100644 --- a/drivers/perf/fsl_imx9_ddr_perf.c +++ b/drivers/perf/fsl_imx9_ddr_perf.c @@ -476,12 +476,12 @@ static int ddr_perf_event_add(struct perf_event *event, int flags) hwc->idx = counter; hwc->state |= PERF_HES_STOPPED; - if (flags & PERF_EF_START) - ddr_perf_event_start(event, flags); - /* read trans, write trans, read beat */ ddr_perf_monitor_config(pmu, cfg, cfg1, cfg2); + if (flags & PERF_EF_START) + ddr_perf_event_start(event, flags); + return 0; } diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index ae16ecb15f2d..901da688ea3f 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -355,7 +355,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) * but not in the user access mode as we want to use the other counters * that support sampling/filtering. */ - if (hwc->flags & PERF_EVENT_FLAG_LEGACY) { + if ((hwc->flags & PERF_EVENT_FLAG_LEGACY) && (event->attr.type == PERF_TYPE_HARDWARE)) { if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES) { cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH; cmask = 1; diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 475a6dd72db6..809fabef3b44 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -805,9 +805,11 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, if (ret == -ENOPROTOOPT) { dev_dbg(ec_dev->dev, "GET_NEXT_EVENT returned invalid version error.\n"); + mutex_lock(&ec_dev->lock); ret = cros_ec_get_host_command_version_mask(ec_dev, EC_CMD_GET_NEXT_EVENT, &ver_mask); + mutex_unlock(&ec_dev->lock); if (ret < 0 || ver_mask == 0) /* * Do not change the MKBP supported version if we can't diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c index 3acc9288b310..3b1030fc4fbf 100644 --- a/drivers/thermal/broadcom/bcm2835_thermal.c +++ b/drivers/thermal/broadcom/bcm2835_thermal.c @@ -185,7 +185,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev) return err; } - data->clk = devm_clk_get(&pdev->dev, NULL); + data->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(data->clk)) { err = PTR_ERR(data->clk); if (err != -EPROBE_DEFER) @@ -193,10 +193,6 @@ static int bcm2835_thermal_probe(struct platform_device *pdev) return err; } - err = clk_prepare_enable(data->clk); - if (err) - return err; - rate = clk_get_rate(data->clk); if ((rate < 1920000) || (rate > 5000000)) dev_warn(&pdev->dev, @@ -211,7 +207,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Failed to register the thermal device: %d\n", err); - goto err_clk; + return err; } /* @@ -236,7 +232,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev) dev_err(&pdev->dev, "Not able to read trip_temp: %d\n", err); - goto err_tz; + return err; } /* set bandgap reference voltage and enable voltage regulator */ @@ -269,32 +265,23 @@ static int bcm2835_thermal_probe(struct platform_device *pdev) */ err = thermal_add_hwmon_sysfs(tz); if (err) - goto err_tz; + return err; bcm2835_thermal_debugfs(pdev); return 0; -err_tz: - devm_thermal_of_zone_unregister(&pdev->dev, tz); -err_clk: - clk_disable_unprepare(data->clk); - - return err; } -static int bcm2835_thermal_remove(struct platform_device *pdev) +static void bcm2835_thermal_remove(struct platform_device *pdev) { struct bcm2835_thermal_data *data = platform_get_drvdata(pdev); debugfs_remove_recursive(data->debugfsdir); - clk_disable_unprepare(data->clk); - - return 0; } static struct platform_driver bcm2835_thermal_driver = { .probe = bcm2835_thermal_probe, - .remove = bcm2835_thermal_remove, + .remove_new = bcm2835_thermal_remove, .driver = { .name = "bcm2835_thermal", .of_match_table = bcm2835_thermal_of_match_table, diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index b694d7669d32..1eb755a94940 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -11,6 +11,10 @@ config APERTURE_HELPERS Support tracking and hand-over of aperture ownership. Required by graphics drivers for firmware-provided framebuffers. +config SCREEN_INFO + bool + default n + config STI_CORE bool depends on PARISC diff --git a/drivers/video/Makefile b/drivers/video/Makefile index 6bbc03950899..6bbf87c1b579 100644 --- a/drivers/video/Makefile +++ b/drivers/video/Makefile @@ -1,12 +1,16 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_APERTURE_HELPERS) += aperture.o +obj-$(CONFIG_SCREEN_INFO) += screen_info.o obj-$(CONFIG_STI_CORE) += sticore.o obj-$(CONFIG_VGASTATE) += vgastate.o obj-$(CONFIG_VIDEO_CMDLINE) += cmdline.o obj-$(CONFIG_VIDEO_NOMODESET) += nomodeset.o obj-$(CONFIG_HDMI) += hdmi.o +screen_info-y := screen_info_generic.o +screen_info-$(CONFIG_PCI) += screen_info_pci.o + obj-$(CONFIG_VT) += console/ obj-$(CONFIG_FB_STI) += console/ obj-$(CONFIG_LOGO) += logo/ diff --git a/drivers/video/fbdev/vesafb.c b/drivers/video/fbdev/vesafb.c index c0edceea0a79..a21581b40256 100644 --- a/drivers/video/fbdev/vesafb.c +++ b/drivers/video/fbdev/vesafb.c @@ -243,6 +243,7 @@ static int vesafb_setup(char *options) static int vesafb_probe(struct platform_device *dev) { + struct screen_info *si = &screen_info; struct fb_info *info; struct vesafb_par *par; int i, err; @@ -255,17 +256,17 @@ static int vesafb_probe(struct platform_device *dev) fb_get_options("vesafb", &option); vesafb_setup(option); - if (screen_info.orig_video_isVGA != VIDEO_TYPE_VLFB) + if (si->orig_video_isVGA != VIDEO_TYPE_VLFB) return -ENODEV; - vga_compat = (screen_info.capabilities & 2) ? 0 : 1; - vesafb_fix.smem_start = screen_info.lfb_base; - vesafb_defined.bits_per_pixel = screen_info.lfb_depth; + vga_compat = !__screen_info_vbe_mode_nonvga(si); + vesafb_fix.smem_start = si->lfb_base; + vesafb_defined.bits_per_pixel = si->lfb_depth; if (15 == vesafb_defined.bits_per_pixel) vesafb_defined.bits_per_pixel = 16; - vesafb_defined.xres = screen_info.lfb_width; - vesafb_defined.yres = screen_info.lfb_height; - vesafb_fix.line_length = screen_info.lfb_linelength; + vesafb_defined.xres = si->lfb_width; + vesafb_defined.yres = si->lfb_height; + vesafb_fix.line_length = si->lfb_linelength; vesafb_fix.visual = (vesafb_defined.bits_per_pixel == 8) ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; @@ -277,7 +278,7 @@ static int vesafb_probe(struct platform_device *dev) /* size_total -- all video memory we have. Used for mtrr * entries, resource allocation and bounds * checking. */ - size_total = screen_info.lfb_size * 65536; + size_total = si->lfb_size * 65536; if (vram_total) size_total = vram_total * 1024 * 1024; if (size_total < size_vmode) @@ -297,7 +298,7 @@ static int vesafb_probe(struct platform_device *dev) vesafb_fix.smem_len = size_remap; #ifndef __i386__ - screen_info.vesapm_seg = 0; + si->vesapm_seg = 0; #endif if (!request_mem_region(vesafb_fix.smem_start, size_total, "vesafb")) { @@ -317,23 +318,26 @@ static int vesafb_probe(struct platform_device *dev) par = info->par; info->pseudo_palette = par->pseudo_palette; - par->base = screen_info.lfb_base; + par->base = si->lfb_base; par->size = size_total; printk(KERN_INFO "vesafb: mode is %dx%dx%d, linelength=%d, pages=%d\n", - vesafb_defined.xres, vesafb_defined.yres, vesafb_defined.bits_per_pixel, vesafb_fix.line_length, screen_info.pages); + vesafb_defined.xres, vesafb_defined.yres, vesafb_defined.bits_per_pixel, + vesafb_fix.line_length, si->pages); - if (screen_info.vesapm_seg) { + if (si->vesapm_seg) { printk(KERN_INFO "vesafb: protected mode interface info at %04x:%04x\n", - screen_info.vesapm_seg,screen_info.vesapm_off); + si->vesapm_seg, si->vesapm_off); } - if (screen_info.vesapm_seg < 0xc000) + if (si->vesapm_seg < 0xc000) ypan = pmi_setpal = 0; /* not available or some DOS TSR ... */ if (ypan || pmi_setpal) { + unsigned long pmi_phys; unsigned short *pmi_base; - pmi_base = (unsigned short*)phys_to_virt(((unsigned long)screen_info.vesapm_seg << 4) + screen_info.vesapm_off); + pmi_phys = ((unsigned long)si->vesapm_seg << 4) + si->vesapm_off; + pmi_base = (unsigned short *)phys_to_virt(pmi_phys); pmi_start = (void*)((char*)pmi_base + pmi_base[1]); pmi_pal = (void*)((char*)pmi_base + pmi_base[2]); printk(KERN_INFO "vesafb: pmi: set display start = %p, set palette = %p\n",pmi_start,pmi_pal); @@ -377,14 +381,14 @@ static int vesafb_probe(struct platform_device *dev) vesafb_defined.left_margin = (vesafb_defined.xres / 8) & 0xf8; vesafb_defined.hsync_len = (vesafb_defined.xres / 8) & 0xf8; - vesafb_defined.red.offset = screen_info.red_pos; - vesafb_defined.red.length = screen_info.red_size; - vesafb_defined.green.offset = screen_info.green_pos; - vesafb_defined.green.length = screen_info.green_size; - vesafb_defined.blue.offset = screen_info.blue_pos; - vesafb_defined.blue.length = screen_info.blue_size; - vesafb_defined.transp.offset = screen_info.rsvd_pos; - vesafb_defined.transp.length = screen_info.rsvd_size; + vesafb_defined.red.offset = si->red_pos; + vesafb_defined.red.length = si->red_size; + vesafb_defined.green.offset = si->green_pos; + vesafb_defined.green.length = si->green_size; + vesafb_defined.blue.offset = si->blue_pos; + vesafb_defined.blue.length = si->blue_size; + vesafb_defined.transp.offset = si->rsvd_pos; + vesafb_defined.transp.length = si->rsvd_size; if (vesafb_defined.bits_per_pixel <= 8) { depth = vesafb_defined.green.length; @@ -399,14 +403,14 @@ static int vesafb_probe(struct platform_device *dev) (vesafb_defined.bits_per_pixel > 8) ? "Truecolor" : (vga_compat || pmi_setpal) ? "Pseudocolor" : "Static Pseudocolor", - screen_info.rsvd_size, - screen_info.red_size, - screen_info.green_size, - screen_info.blue_size, - screen_info.rsvd_pos, - screen_info.red_pos, - screen_info.green_pos, - screen_info.blue_pos); + si->rsvd_size, + si->red_size, + si->green_size, + si->blue_size, + si->rsvd_pos, + si->red_pos, + si->green_pos, + si->blue_pos); vesafb_fix.ypanstep = ypan ? 1 : 0; vesafb_fix.ywrapstep = (ypan>1) ? 1 : 0; diff --git a/drivers/video/screen_info_generic.c b/drivers/video/screen_info_generic.c new file mode 100644 index 000000000000..64117c6367ab --- /dev/null +++ b/drivers/video/screen_info_generic.c @@ -0,0 +1,146 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/export.h> +#include <linux/ioport.h> +#include <linux/screen_info.h> +#include <linux/string.h> + +static void resource_init_named(struct resource *r, + resource_size_t start, resource_size_t size, + const char *name, unsigned int flags) +{ + memset(r, 0, sizeof(*r)); + + r->start = start; + r->end = start + size - 1; + r->name = name; + r->flags = flags; +} + +static void resource_init_io_named(struct resource *r, + resource_size_t start, resource_size_t size, + const char *name) +{ + resource_init_named(r, start, size, name, IORESOURCE_IO); +} + +static void resource_init_mem_named(struct resource *r, + resource_size_t start, resource_size_t size, + const char *name) +{ + resource_init_named(r, start, size, name, IORESOURCE_MEM); +} + +static inline bool __screen_info_has_ega_gfx(unsigned int mode) +{ + switch (mode) { + case 0x0d: /* 320x200-4 */ + case 0x0e: /* 640x200-4 */ + case 0x0f: /* 640x350-1 */ + case 0x10: /* 640x350-4 */ + return true; + default: + return false; + } +} + +static inline bool __screen_info_has_vga_gfx(unsigned int mode) +{ + switch (mode) { + case 0x10: /* 640x480-1 */ + case 0x12: /* 640x480-4 */ + case 0x13: /* 320-200-8 */ + case 0x6a: /* 800x600-4 (VESA) */ + return true; + default: + return __screen_info_has_ega_gfx(mode); + } +} + +/** + * screen_info_resources() - Get resources from screen_info structure + * @si: the screen_info + * @r: pointer to an array of resource structures + * @num: number of elements in @r: + * + * Returns: + * The number of resources stored in @r on success, or a negative errno code otherwise. + * + * A call to screen_info_resources() returns the resources consumed by the + * screen_info's device or framebuffer. The result is stored in the caller-supplied + * array @r with up to @num elements. The function returns the number of + * initialized elements. + */ +ssize_t screen_info_resources(const struct screen_info *si, struct resource *r, size_t num) +{ + struct resource *pos = r; + unsigned int type = screen_info_video_type(si); + u64 base, size; + + switch (type) { + case VIDEO_TYPE_MDA: + if (num > 0) + resource_init_io_named(pos++, 0x3b0, 12, "mda"); + if (num > 1) + resource_init_io_named(pos++, 0x3bf, 0x01, "mda"); + if (num > 2) + resource_init_mem_named(pos++, 0xb0000, 0x2000, "mda"); + break; + case VIDEO_TYPE_CGA: + if (num > 0) + resource_init_io_named(pos++, 0x3d4, 0x02, "cga"); + if (num > 1) + resource_init_mem_named(pos++, 0xb8000, 0x2000, "cga"); + break; + case VIDEO_TYPE_EGAM: + if (num > 0) + resource_init_io_named(pos++, 0x3bf, 0x10, "ega"); + if (num > 1) + resource_init_mem_named(pos++, 0xb0000, 0x8000, "ega"); + break; + case VIDEO_TYPE_EGAC: + if (num > 0) + resource_init_io_named(pos++, 0x3c0, 0x20, "ega"); + if (num > 1) { + if (__screen_info_has_ega_gfx(si->orig_video_mode)) + resource_init_mem_named(pos++, 0xa0000, 0x10000, "ega"); + else + resource_init_mem_named(pos++, 0xb8000, 0x8000, "ega"); + } + break; + case VIDEO_TYPE_VGAC: + if (num > 0) + resource_init_io_named(pos++, 0x3c0, 0x20, "vga+"); + if (num > 1) { + if (__screen_info_has_vga_gfx(si->orig_video_mode)) + resource_init_mem_named(pos++, 0xa0000, 0x10000, "vga+"); + else + resource_init_mem_named(pos++, 0xb8000, 0x8000, "vga+"); + } + break; + case VIDEO_TYPE_VLFB: + case VIDEO_TYPE_EFI: + base = __screen_info_lfb_base(si); + if (!base) + break; + size = __screen_info_lfb_size(si, type); + if (!size) + break; + if (num > 0) + resource_init_mem_named(pos++, base, size, "lfb"); + break; + case VIDEO_TYPE_PICA_S3: + case VIDEO_TYPE_MIPS_G364: + case VIDEO_TYPE_SGI: + case VIDEO_TYPE_TGAC: + case VIDEO_TYPE_SUN: + case VIDEO_TYPE_SUNPCI: + case VIDEO_TYPE_PMAC: + default: + /* not supported */ + return -EINVAL; + } + + return pos - r; +} +EXPORT_SYMBOL(screen_info_resources); diff --git a/drivers/video/screen_info_pci.c b/drivers/video/screen_info_pci.c new file mode 100644 index 000000000000..6c5833517141 --- /dev/null +++ b/drivers/video/screen_info_pci.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/pci.h> +#include <linux/printk.h> +#include <linux/screen_info.h> +#include <linux/string.h> + +static struct pci_dev *screen_info_lfb_pdev; +static size_t screen_info_lfb_bar; +static resource_size_t screen_info_lfb_offset; +static struct resource screen_info_lfb_res = DEFINE_RES_MEM(0, 0); + +static bool __screen_info_relocation_is_valid(const struct screen_info *si, struct resource *pr) +{ + u64 size = __screen_info_lfb_size(si, screen_info_video_type(si)); + + if (screen_info_lfb_offset > resource_size(pr)) + return false; + if (size > resource_size(pr)) + return false; + if (resource_size(pr) - size < screen_info_lfb_offset) + return false; + + return true; +} + +void screen_info_apply_fixups(void) +{ + struct screen_info *si = &screen_info; + + if (screen_info_lfb_pdev) { + struct resource *pr = &screen_info_lfb_pdev->resource[screen_info_lfb_bar]; + + if (pr->start != screen_info_lfb_res.start) { + if (__screen_info_relocation_is_valid(si, pr)) { + /* + * Only update base if we have an actual + * relocation to a valid I/O range. + */ + __screen_info_set_lfb_base(si, pr->start + screen_info_lfb_offset); + pr_info("Relocating firmware framebuffer to offset %pa[d] within %pr\n", + &screen_info_lfb_offset, pr); + } else { + pr_warn("Invalid relocating, disabling firmware framebuffer\n"); + } + } + } +} + +static void screen_info_fixup_lfb(struct pci_dev *pdev) +{ + unsigned int type; + struct resource res[SCREEN_INFO_MAX_RESOURCES]; + size_t i, numres; + int ret; + const struct screen_info *si = &screen_info; + + if (screen_info_lfb_pdev) + return; // already found + + type = screen_info_video_type(si); + if (type != VIDEO_TYPE_EFI) + return; // only applies to EFI + + ret = screen_info_resources(si, res, ARRAY_SIZE(res)); + if (ret < 0) + return; + numres = ret; + + for (i = 0; i < numres; ++i) { + struct resource *r = &res[i]; + const struct resource *pr; + + if (!(r->flags & IORESOURCE_MEM)) + continue; + pr = pci_find_resource(pdev, r); + if (!pr) + continue; + + /* + * We've found a PCI device with the framebuffer + * resource. Store away the parameters to track + * relocation of the framebuffer aperture. + */ + screen_info_lfb_pdev = pdev; + screen_info_lfb_bar = pr - pdev->resource; + screen_info_lfb_offset = r->start - pr->start; + memcpy(&screen_info_lfb_res, r, sizeof(screen_info_lfb_res)); + } +} +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_ANY_ID, PCI_ANY_ID, PCI_BASE_CLASS_DISPLAY, 16, + screen_info_fixup_lfb); + +static struct pci_dev *__screen_info_pci_dev(struct resource *res) +{ + struct pci_dev *pdev = NULL; + const struct resource *r = NULL; + + if (!(res->flags & IORESOURCE_MEM)) + return NULL; + + while (!r && (pdev = pci_get_base_class(PCI_BASE_CLASS_DISPLAY, pdev))) { + r = pci_find_resource(pdev, res); + } + + return pdev; +} + +/** + * screen_info_pci_dev() - Return PCI parent device that contains screen_info's framebuffer + * @si: the screen_info + * + * Returns: + * The screen_info's parent device or NULL on success, or a pointer-encoded + * errno value otherwise. The value NULL is not an error. It signals that no + * PCI device has been found. + */ +struct pci_dev *screen_info_pci_dev(const struct screen_info *si) +{ + struct resource res[SCREEN_INFO_MAX_RESOURCES]; + ssize_t i, numres; + + numres = screen_info_resources(si, res, ARRAY_SIZE(res)); + if (numres < 0) + return ERR_PTR(numres); + + for (i = 0; i < numres; ++i) { + struct pci_dev *pdev = __screen_info_pci_dev(&res[i]); + + if (pdev) + return pdev; + } + + return NULL; +} +EXPORT_SYMBOL(screen_info_pci_dev); diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index dd065349fae3..4e999e1c1407 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1214,8 +1214,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, block_group->space_info->total_bytes -= block_group->length; block_group->space_info->bytes_readonly -= (block_group->length - block_group->zone_unusable); - block_group->space_info->bytes_zone_unusable -= - block_group->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info, + -block_group->zone_unusable); block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); @@ -1399,7 +1399,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes to readonly */ sinfo->bytes_readonly += cache->zone_unusable; - sinfo->bytes_zone_unusable -= cache->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, + -cache->zone_unusable); cache->zone_unusable = 0; } cache->ro++; @@ -3023,9 +3024,11 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) if (btrfs_is_zoned(cache->fs_info)) { /* Migrate zone_unusable bytes back */ cache->zone_unusable = - (cache->alloc_offset - cache->used) + + (cache->alloc_offset - cache->used - cache->pinned - + cache->reserved) + (cache->length - cache->zone_capacity); - sinfo->bytes_zone_unusable += cache->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo, + cache->zone_unusable); sinfo->bytes_readonly -= cache->zone_unusable; } num_bytes = cache->length - cache->reserved - diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index b89b558b1592..c6ecfd05e1db 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2749,7 +2749,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, readonly = true; } else if (btrfs_is_zoned(fs_info)) { /* Need reset before reusing in a zoned block group */ - space_info->bytes_zone_unusable += len; + btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info, + len); readonly = true; } spin_unlock(&cache->lock); diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index dcfc0425115e..f59e59976666 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2721,8 +2721,10 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, * If the block group is read-only, we should account freed space into * bytes_readonly. */ - if (!block_group->ro) + if (!block_group->ro) { block_group->zone_unusable += to_unusable; + WARN_ON(block_group->zone_unusable > block_group->length); + } spin_unlock(&ctl->tree_lock); if (!used) { spin_lock(&block_group->lock); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 3f7a9605e2d3..581bdd709ee0 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -312,7 +312,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, found->bytes_used += block_group->used; found->disk_used += block_group->used * factor; found->bytes_readonly += block_group->bytes_super; - found->bytes_zone_unusable += block_group->zone_unusable; + btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable); if (block_group->length > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -524,8 +524,7 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info, spin_lock(&cache->lock); avail = cache->length - cache->used - cache->pinned - - cache->reserved - cache->delalloc_bytes - - cache->bytes_super - cache->zone_unusable; + cache->reserved - cache->bytes_super - cache->zone_unusable; btrfs_info(fs_info, "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu delalloc %llu super %llu zone_unusable (%llu bytes available) %s", cache->start, cache->length, cache->used, cache->pinned, diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 0bb9d14e60a8..08a3bd10addc 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -197,6 +197,7 @@ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \ DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info"); DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); +DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d5eb8d44c6c8..cef119a2476b 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -453,6 +453,35 @@ static void ext4_map_blocks_es_recheck(handle_t *handle, } #endif /* ES_AGGRESSIVE_TEST */ +static int ext4_map_query_blocks(handle_t *handle, struct inode *inode, + struct ext4_map_blocks *map) +{ + unsigned int status; + int retval; + + if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) + retval = ext4_ext_map_blocks(handle, inode, map, 0); + else + retval = ext4_ind_map_blocks(handle, inode, map, 0); + + if (retval <= 0) + return retval; + + if (unlikely(retval != map->m_len)) { + ext4_warning(inode->i_sb, + "ES len assertion failed for inode " + "%lu: retval %d != map->m_len %d", + inode->i_ino, retval, map->m_len); + WARN_ON(1); + } + + status = map->m_flags & EXT4_MAP_UNWRITTEN ? + EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; + ext4_es_insert_extent(inode, map->m_lblk, map->m_len, + map->m_pblk, status); + return retval; +} + /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. @@ -1705,12 +1734,10 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { - if (ext4_es_is_hole(&es)) { - retval = 0; - down_read(&EXT4_I(inode)->i_data_sem); + if (ext4_es_is_hole(&es)) goto add_delayed; - } +found: /* * Delayed extent could be allocated by fallocate. * So we need to check it. @@ -1747,49 +1774,42 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock, down_read(&EXT4_I(inode)->i_data_sem); if (ext4_has_inline_data(inode)) retval = 0; - else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) - retval = ext4_ext_map_blocks(NULL, inode, map, 0); else - retval = ext4_ind_map_blocks(NULL, inode, map, 0); + retval = ext4_map_query_blocks(NULL, inode, map); + up_read(&EXT4_I(inode)->i_data_sem); + if (retval) + return retval; add_delayed: - if (retval == 0) { - int ret; - - /* - * XXX: __block_prepare_write() unmaps passed block, - * is it OK? - */ - - ret = ext4_insert_delayed_block(inode, map->m_lblk); - if (ret != 0) { - retval = ret; - goto out_unlock; + down_write(&EXT4_I(inode)->i_data_sem); + /* + * Page fault path (ext4_page_mkwrite does not take i_rwsem) + * and fallocate path (no folio lock) can race. Make sure we + * lookup the extent status tree here again while i_data_sem + * is held in write mode, before inserting a new da entry in + * the extent status tree. + */ + if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) { + if (!ext4_es_is_hole(&es)) { + up_write(&EXT4_I(inode)->i_data_sem); + goto found; } - - map_bh(bh, inode->i_sb, invalid_block); - set_buffer_new(bh); - set_buffer_delay(bh); - } else if (retval > 0) { - unsigned int status; - - if (unlikely(retval != map->m_len)) { - ext4_warning(inode->i_sb, - "ES len assertion failed for inode " - "%lu: retval %d != map->m_len %d", - inode->i_ino, retval, map->m_len); - WARN_ON(1); + } else if (!ext4_has_inline_data(inode)) { + retval = ext4_map_query_blocks(NULL, inode, map); + if (retval) { + up_write(&EXT4_I(inode)->i_data_sem); + return retval; } - - status = map->m_flags & EXT4_MAP_UNWRITTEN ? - EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; - ext4_es_insert_extent(inode, map->m_lblk, map->m_len, - map->m_pblk, status); } -out_unlock: - up_read((&EXT4_I(inode)->i_data_sem)); + retval = ext4_insert_delayed_block(inode, map->m_lblk); + up_write(&EXT4_I(inode)->i_data_sem); + if (retval) + return retval; + map_bh(bh, inode->i_sb, invalid_block); + set_buffer_new(bh); + set_buffer_delay(bh); return retval; } diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 22080606b876..804958c6de34 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -3350,7 +3350,9 @@ static int __get_segment_type_6(struct f2fs_io_info *fio) if (page_private_gcing(fio->page)) { if (fio->sbi->am.atgc_enabled && (fio->io_type == FS_DATA_IO) && - (fio->sbi->gc_mode != GC_URGENT_HIGH)) + (fio->sbi->gc_mode != GC_URGENT_HIGH) && + __is_valid_data_blkaddr(fio->old_blkaddr) && + !is_inode_flag_set(inode, FI_OPU_WRITE)) return CURSEG_ALL_DATA_ATGC; else return CURSEG_COLD_DATA; diff --git a/fs/file.c b/fs/file.c index a815f6eddc51..b64a84137c00 100644 --- a/fs/file.c +++ b/fs/file.c @@ -1124,6 +1124,7 @@ __releases(&files->file_lock) * tables and this condition does not arise without those. */ fdt = files_fdtable(files); + fd = array_index_nospec(fd, fdt->max_fds); tofree = fdt->fd[fd]; if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 5b5cdc747cef..071a71eb1a2d 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -480,12 +480,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb, make_empty_dir_inode(inode); } + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; if (root->set_ownership) - root->set_ownership(head, table, &inode->i_uid, &inode->i_gid); - else { - inode->i_uid = GLOBAL_ROOT_UID; - inode->i_gid = GLOBAL_ROOT_GID; - } + root->set_ownership(head, &inode->i_uid, &inode->i_gid); return inode; } diff --git a/include/linux/leds.h b/include/linux/leds.h index aa16dc2a8230..d3056bc6f0a1 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -474,6 +474,9 @@ struct led_trigger { int (*activate)(struct led_classdev *led_cdev); void (*deactivate)(struct led_classdev *led_cdev); + /* Brightness set by led_trigger_event */ + enum led_brightness brightness; + /* LED-private triggers have this set */ struct led_hw_trigger_type *trigger_type; @@ -527,22 +530,11 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) return led_cdev->trigger_data; } -/** - * led_trigger_rename_static - rename a trigger - * @name: the new trigger name - * @trig: the LED trigger to rename - * - * Change a LED trigger name by copying the string passed in - * name into current trigger name, which MUST be large - * enough for the new string. - * - * Note that name must NOT point to the same string used - * during LED registration, as that could lead to races. - * - * This is meant to be used on triggers with statically - * allocated name. - */ -void led_trigger_rename_static(const char *name, struct led_trigger *trig); +static inline enum led_brightness +led_trigger_get_brightness(const struct led_trigger *trigger) +{ + return trigger ? trigger->brightness : LED_OFF; +} #define module_led_trigger(__led_trigger) \ module_driver(__led_trigger, led_trigger_register, \ @@ -580,6 +572,12 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev) return NULL; } +static inline enum led_brightness +led_trigger_get_brightness(const struct led_trigger *trigger) +{ + return LED_OFF; +} + #endif /* CONFIG_LEDS_TRIGGERS */ /* Trigger specific enum */ diff --git a/include/linux/pci.h b/include/linux/pci.h index f14130011621..7b18a4b3efb0 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1182,6 +1182,8 @@ struct pci_dev *pci_get_slot(struct pci_bus *bus, unsigned int devfn); struct pci_dev *pci_get_domain_bus_and_slot(int domain, unsigned int bus, unsigned int devfn); struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from); +struct pci_dev *pci_get_base_class(unsigned int class, struct pci_dev *from); + int pci_dev_present(const struct pci_device_id *ids); int pci_bus_read_config_byte(struct pci_bus *bus, unsigned int devfn, @@ -1958,6 +1960,9 @@ static inline struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from) { return NULL; } +static inline struct pci_dev *pci_get_base_class(unsigned int class, + struct pci_dev *from) +{ return NULL; } static inline int pci_dev_present(const struct pci_device_id *ids) { return 0; } diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h index eab7081392d5..6a4a3cec4638 100644 --- a/include/linux/screen_info.h +++ b/include/linux/screen_info.h @@ -4,6 +4,142 @@ #include <uapi/linux/screen_info.h> +#include <linux/bits.h> + +/** + * SCREEN_INFO_MAX_RESOURCES - maximum number of resources per screen_info + */ +#define SCREEN_INFO_MAX_RESOURCES 3 + +struct pci_dev; +struct resource; + +static inline bool __screen_info_has_lfb(unsigned int type) +{ + return (type == VIDEO_TYPE_VLFB) || (type == VIDEO_TYPE_EFI); +} + +static inline u64 __screen_info_lfb_base(const struct screen_info *si) +{ + u64 lfb_base = si->lfb_base; + + if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE) + lfb_base |= (u64)si->ext_lfb_base << 32; + + return lfb_base; +} + +static inline void __screen_info_set_lfb_base(struct screen_info *si, u64 lfb_base) +{ + si->lfb_base = lfb_base & GENMASK_ULL(31, 0); + si->ext_lfb_base = (lfb_base & GENMASK_ULL(63, 32)) >> 32; + + if (si->ext_lfb_base) + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + else + si->capabilities &= ~VIDEO_CAPABILITY_64BIT_BASE; +} + +static inline u64 __screen_info_lfb_size(const struct screen_info *si, unsigned int type) +{ + u64 lfb_size = si->lfb_size; + + if (type == VIDEO_TYPE_VLFB) + lfb_size <<= 16; + return lfb_size; +} + +static inline bool __screen_info_vbe_mode_nonvga(const struct screen_info *si) +{ + /* + * VESA modes typically run on VGA hardware. Set bit 5 signals that this + * is not the case. Drivers can then not make use of VGA resources. See + * Sec 4.4 of the VBE 2.0 spec. + */ + return si->vesa_attributes & BIT(5); +} + +static inline unsigned int __screen_info_video_type(unsigned int type) +{ + switch (type) { + case VIDEO_TYPE_MDA: + case VIDEO_TYPE_CGA: + case VIDEO_TYPE_EGAM: + case VIDEO_TYPE_EGAC: + case VIDEO_TYPE_VGAC: + case VIDEO_TYPE_VLFB: + case VIDEO_TYPE_PICA_S3: + case VIDEO_TYPE_MIPS_G364: + case VIDEO_TYPE_SGI: + case VIDEO_TYPE_TGAC: + case VIDEO_TYPE_SUN: + case VIDEO_TYPE_SUNPCI: + case VIDEO_TYPE_PMAC: + case VIDEO_TYPE_EFI: + return type; + default: + return 0; + } +} + +/** + * screen_info_video_type() - Decodes the video type from struct screen_info + * @si: an instance of struct screen_info + * + * Returns: + * A VIDEO_TYPE_ constant representing si's type of video display, or 0 otherwise. + */ +static inline unsigned int screen_info_video_type(const struct screen_info *si) +{ + unsigned int type; + + // check if display output is on + if (!si->orig_video_isVGA) + return 0; + + // check for a known VIDEO_TYPE_ constant + type = __screen_info_video_type(si->orig_video_isVGA); + if (type) + return si->orig_video_isVGA; + + // check if text mode has been initialized + if (!si->orig_video_lines || !si->orig_video_cols) + return 0; + + // 80x25 text, mono + if (si->orig_video_mode == 0x07) { + if ((si->orig_video_ega_bx & 0xff) != 0x10) + return VIDEO_TYPE_EGAM; + else + return VIDEO_TYPE_MDA; + } + + // EGA/VGA, 16 colors + if ((si->orig_video_ega_bx & 0xff) != 0x10) { + if (si->orig_video_isVGA) + return VIDEO_TYPE_VGAC; + else + return VIDEO_TYPE_EGAC; + } + + // the rest... + return VIDEO_TYPE_CGA; +} + +ssize_t screen_info_resources(const struct screen_info *si, struct resource *r, size_t num); + +#if defined(CONFIG_PCI) +void screen_info_apply_fixups(void); +struct pci_dev *screen_info_pci_dev(const struct screen_info *si); +#else +static inline void screen_info_apply_fixups(void) +{ } +static inline struct pci_dev *screen_info_pci_dev(const struct screen_info *si) +{ + return NULL; +} +#endif + extern struct screen_info screen_info; #endif /* _SCREEN_INFO_H */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 61b40ea81f4d..698a71422a14 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -205,7 +205,6 @@ struct ctl_table_root { struct ctl_table_set default_set; struct ctl_table_set *(*lookup)(struct ctl_table_root *root); void (*set_ownership)(struct ctl_table_header *head, - struct ctl_table *table, kuid_t *uid, kgid_t *gid); int (*permissions)(struct ctl_table_header *head, struct ctl_table *table); }; diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index b2db2c2f1c57..3c4d5ef6d446 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -2430,6 +2430,14 @@ DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned, TP_ARGS(fs_info, sinfo, old, diff) ); +DEFINE_EVENT(btrfs__space_info_update, update_bytes_zone_unusable, + + TP_PROTO(const struct btrfs_fs_info *fs_info, + const struct btrfs_space_info *sinfo, u64 old, s64 diff), + + TP_ARGS(fs_info, sinfo, old, diff) +); + DECLARE_EVENT_CLASS(btrfs_raid56_bio, TP_PROTO(const struct btrfs_raid_bio *rbio, diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h index 563e48617374..54e8fb5a229c 100644 --- a/include/trace/events/mptcp.h +++ b/include/trace/events/mptcp.h @@ -34,7 +34,7 @@ TRACE_EVENT(mptcp_subflow_get_send, struct sock *ssk; __entry->active = mptcp_subflow_active(subflow); - __entry->backup = subflow->backup; + __entry->backup = subflow->backup || subflow->request_bkup; if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock)) __entry->free = sk_stream_memory_free(subflow->tcp_sock); diff --git a/init/Kconfig b/init/Kconfig index e403a2925635..e173364abd6c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1898,6 +1898,7 @@ config RUST depends on !MODVERSIONS depends on !GCC_PLUGINS depends on !RANDSTRUCT + depends on !SHADOW_CALL_STACK depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE help Enables Rust support in the kernel. diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c index 8c62e443f78b..b2f39a86f473 100644 --- a/ipc/ipc_sysctl.c +++ b/ipc/ipc_sysctl.c @@ -14,6 +14,7 @@ #include <linux/ipc_namespace.h> #include <linux/msg.h> #include <linux/slab.h> +#include <linux/cred.h> #include "util.h" static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write, @@ -190,25 +191,56 @@ static int set_is_seen(struct ctl_table_set *set) return ¤t->nsproxy->ipc_ns->ipc_set == set; } +static void ipc_set_ownership(struct ctl_table_header *head, + kuid_t *uid, kgid_t *gid) +{ + struct ipc_namespace *ns = + container_of(head->set, struct ipc_namespace, ipc_set); + + kuid_t ns_root_uid = make_kuid(ns->user_ns, 0); + kgid_t ns_root_gid = make_kgid(ns->user_ns, 0); + + *uid = uid_valid(ns_root_uid) ? ns_root_uid : GLOBAL_ROOT_UID; + *gid = gid_valid(ns_root_gid) ? ns_root_gid : GLOBAL_ROOT_GID; +} + static int ipc_permissions(struct ctl_table_header *head, struct ctl_table *table) { int mode = table->mode; #ifdef CONFIG_CHECKPOINT_RESTORE - struct ipc_namespace *ns = current->nsproxy->ipc_ns; + struct ipc_namespace *ns = + container_of(head->set, struct ipc_namespace, ipc_set); if (((table->data == &ns->ids[IPC_SEM_IDS].next_id) || (table->data == &ns->ids[IPC_MSG_IDS].next_id) || (table->data == &ns->ids[IPC_SHM_IDS].next_id)) && checkpoint_restore_ns_capable(ns->user_ns)) mode = 0666; + else #endif - return mode; + { + kuid_t ns_root_uid; + kgid_t ns_root_gid; + + ipc_set_ownership(head, &ns_root_uid, &ns_root_gid); + + if (uid_eq(current_euid(), ns_root_uid)) + mode >>= 6; + + else if (in_egroup_p(ns_root_gid)) + mode >>= 3; + } + + mode &= 7; + + return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = ipc_permissions, + .set_ownership = ipc_set_ownership, }; bool setup_ipc_sysctls(struct ipc_namespace *ns) diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index ebb5ed81c151..6bb1c5397c69 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -12,6 +12,7 @@ #include <linux/stat.h> #include <linux/capability.h> #include <linux/slab.h> +#include <linux/cred.h> static int msg_max_limit_min = MIN_MSGMAX; static int msg_max_limit_max = HARD_MSGMAX; @@ -76,8 +77,42 @@ static int set_is_seen(struct ctl_table_set *set) return ¤t->nsproxy->ipc_ns->mq_set == set; } +static void mq_set_ownership(struct ctl_table_header *head, + kuid_t *uid, kgid_t *gid) +{ + struct ipc_namespace *ns = + container_of(head->set, struct ipc_namespace, mq_set); + + kuid_t ns_root_uid = make_kuid(ns->user_ns, 0); + kgid_t ns_root_gid = make_kgid(ns->user_ns, 0); + + *uid = uid_valid(ns_root_uid) ? ns_root_uid : GLOBAL_ROOT_UID; + *gid = gid_valid(ns_root_gid) ? ns_root_gid : GLOBAL_ROOT_GID; +} + +static int mq_permissions(struct ctl_table_header *head, struct ctl_table *table) +{ + int mode = table->mode; + kuid_t ns_root_uid; + kgid_t ns_root_gid; + + mq_set_ownership(head, &ns_root_uid, &ns_root_gid); + + if (uid_eq(current_euid(), ns_root_uid)) + mode >>= 6; + + else if (in_egroup_p(ns_root_gid)) + mode >>= 3; + + mode &= 7; + + return (mode << 6) | (mode << 3) | mode; +} + static struct ctl_table_root set_root = { .lookup = set_lookup, + .permissions = mq_permissions, + .set_ownership = mq_set_ownership, }; bool setup_mq_sysctls(struct ipc_namespace *ns) diff --git a/mm/Kconfig b/mm/Kconfig index 264a2df5ecf5..ece4f2847e2b 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -704,6 +704,17 @@ config HUGETLB_PAGE_SIZE_VARIABLE config CONTIG_ALLOC def_bool (MEMORY_ISOLATION && COMPACTION) || CMA +config PCP_BATCH_SCALE_MAX + int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free" + default 5 + range 0 6 + help + In page allocator, PCP (Per-CPU pageset) is refilled and drained in + batches. The batch number is scaled automatically to improve page + allocation/free throughput. But too large scale factor may hurt + latency. This option sets the upper limit of scale factor to limit + the maximum latency. + config PHYS_ADDR_T_64BIT def_bool 64BIT diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e99d3223f0fc..39bdbfb5313f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2185,14 +2185,21 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp) */ static void drain_pages_zone(unsigned int cpu, struct zone *zone) { - struct per_cpu_pages *pcp; + struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); + int count; - pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu); - if (pcp->count) { + do { spin_lock(&pcp->lock); - free_pcppages_bulk(zone, pcp->count, pcp, 0); + count = pcp->count; + if (count) { + int to_drain = min(count, + pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX); + + free_pcppages_bulk(zone, to_drain, pcp, 0); + count -= to_drain; + } spin_unlock(&pcp->lock); - } + } while (count); } /* @@ -2343,7 +2350,7 @@ static int nr_pcp_free(struct per_cpu_pages *pcp, int high, bool free_high) * freeing of pages without any allocation. */ batch <<= pcp->free_factor; - if (batch < max_nr_free) + if (batch < max_nr_free && pcp->free_factor < CONFIG_PCP_BATCH_SCALE_MAX) pcp->free_factor++; batch = clamp(batch, min_nr_free, max_nr_free); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index b3f5714dab34..6dab0c99c82c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2862,6 +2862,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev) */ filter_policy = hci_update_accept_list_sync(hdev); + /* If suspended and filter_policy set to 0x00 (no acceptlist) then + * passive scanning cannot be started since that would require the host + * to be woken up to process the reports. + */ + if (hdev->suspended && !filter_policy) { + /* Check if accept list is empty then there is no need to scan + * while suspended. + */ + if (list_empty(&hdev->le_accept_list)) + return 0; + + /* If there are devices is the accept_list that means some + * devices could not be programmed which in non-suspended case + * means filter_policy needs to be set to 0x00 so the host needs + * to filter, but since this is treating suspended case we + * can ignore device needing host to filter to allow devices in + * the acceptlist to be able to wakeup the system. + */ + filter_policy = 0x01; + } + /* When the controller is using random resolvable addresses and * with that having LE privacy enabled, then controllers with * Extended Scanner Filter Policies support can now enable support diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7ea66de1442c..8573dad6d817 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3263,7 +3263,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (ifm->ifi_index > 0) dev = __dev_get_by_index(tgt_net, ifm->ifi_index); else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) - dev = rtnl_dev_get(net, tb); + dev = rtnl_dev_get(tgt_net, tb); else if (tb[IFLA_GROUP]) err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP])); else diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 56f6ecc43451..12ca666d6e2c 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = { static int __init iptable_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv4_table, - iptable_nat_table_init); + int ret; + /* net->gen->ptr[iptable_nat_net_id] must be allocated + * before calling iptable_nat_table_init(). + */ + ret = register_pernet_subsys(&iptable_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&iptable_nat_net_ops); - if (ret < 0) { - xt_unregister_template(&nf_nat_ipv4_table); - return ret; - } + ret = xt_register_template(&nf_nat_ipv4_table, + iptable_nat_table_init); + if (ret < 0) + unregister_pernet_subsys(&iptable_nat_net_ops); return ret; } static void __exit iptable_nat_exit(void) { - unregister_pernet_subsys(&iptable_nat_net_ops); xt_unregister_template(&nf_nat_ipv4_table); + unregister_pernet_subsys(&iptable_nat_net_ops); } module_init(iptable_nat_init); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 3b4dafefb4b0..e14356207795 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -424,7 +424,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) } /* Try to redo what tcp_v4_send_synack did. */ - req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW); + req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? : + dst_metric(&rt->dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 91c3d8264059..1e3202f2b7a8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1723,7 +1723,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) space = tcp_space_from_win(sk, val); if (space > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, space); - tcp_sk(sk)->window_clamp = val; + WRITE_ONCE(tcp_sk(sk)->window_clamp, val); } return 0; } @@ -3386,7 +3386,7 @@ int tcp_set_window_clamp(struct sock *sk, int val) if (!val) { if (sk->sk_state != TCP_CLOSE) return -EINVAL; - tp->window_clamp = 0; + WRITE_ONCE(tp->window_clamp, 0); } else { u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? @@ -3395,7 +3395,7 @@ int tcp_set_window_clamp(struct sock *sk, int val) if (new_window_clamp == old_window_clamp) return 0; - tp->window_clamp = new_window_clamp; + WRITE_ONCE(tp->window_clamp, new_window_clamp); if (new_window_clamp < old_window_clamp) { /* need to apply the reserved mem provisioning only * when shrinking the window clamp @@ -4020,7 +4020,7 @@ int do_tcp_getsockopt(struct sock *sk, int level, TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: - val = tp->window_clamp; + val = READ_ONCE(tp->window_clamp); break; case TCP_INFO: { struct tcp_info info; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c2e4dac42453..d0364cff65c9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -570,19 +570,20 @@ static void tcp_init_buffer_space(struct sock *sk) maxwin = tcp_full_space(sk); if (tp->window_clamp >= maxwin) { - tp->window_clamp = maxwin; + WRITE_ONCE(tp->window_clamp, maxwin); if (tcp_app_win && maxwin > 4 * tp->advmss) - tp->window_clamp = max(maxwin - - (maxwin >> tcp_app_win), - 4 * tp->advmss); + WRITE_ONCE(tp->window_clamp, + max(maxwin - (maxwin >> tcp_app_win), + 4 * tp->advmss)); } /* Force reservation of one segment. */ if (tcp_app_win && tp->window_clamp > 2 * tp->advmss && tp->window_clamp + tp->advmss > maxwin) - tp->window_clamp = max(2 * tp->advmss, maxwin - tp->advmss); + WRITE_ONCE(tp->window_clamp, + max(2 * tp->advmss, maxwin - tp->advmss)); tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; @@ -747,8 +748,7 @@ void tcp_rcv_space_adjust(struct sock *sk) * <prev RTT . ><current RTT .. ><next RTT .... > */ - if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && - !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) { u64 rcvwin, grow; int rcvbuf; @@ -764,11 +764,22 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin), READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); - if (rcvbuf > sk->sk_rcvbuf) { - WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); + if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + if (rcvbuf > sk->sk_rcvbuf) { + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); - /* Make the window clamp follow along. */ - tp->window_clamp = tcp_win_from_space(sk, rcvbuf); + /* Make the window clamp follow along. */ + WRITE_ONCE(tp->window_clamp, + tcp_win_from_space(sk, rcvbuf)); + } + } else { + /* Make the window clamp follow along while being bounded + * by SO_RCVBUF. + */ + int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf)); + + if (clamp > tp->window_clamp) + WRITE_ONCE(tp->window_clamp, clamp); } } tp->rcvq_space.space = copied; @@ -6347,7 +6358,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (!tp->rx_opt.wscale_ok) { tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0; - tp->window_clamp = min(tp->window_clamp, 65535U); + WRITE_ONCE(tp->window_clamp, + min(tp->window_clamp, 65535U)); } if (tp->rx_opt.saw_tstamp) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5631041ae12c..15c49d559db5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -203,16 +203,17 @@ static inline void tcp_event_ack_sent(struct sock *sk, u32 rcv_nxt) * This MUST be enforced by all callers. */ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, - __u32 *rcv_wnd, __u32 *window_clamp, + __u32 *rcv_wnd, __u32 *__window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); + u32 window_clamp = READ_ONCE(*__window_clamp); /* If no clamp set the clamp to the max possible scaled window */ - if (*window_clamp == 0) - (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); - space = min(*window_clamp, space); + if (window_clamp == 0) + window_clamp = (U16_MAX << TCP_MAX_WSCALE); + space = min(window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) @@ -239,12 +240,13 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, /* Set window scaling on max possible window */ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); space = max_t(u32, space, READ_ONCE(sysctl_rmem_max)); - space = min_t(u32, space, *window_clamp); + space = min_t(u32, space, window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, 0, TCP_MAX_WSCALE); } /* Set the clamp no higher than max representable value */ - (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); + WRITE_ONCE(*__window_clamp, + min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp)); } EXPORT_SYMBOL(tcp_select_initial_window); @@ -3787,7 +3789,7 @@ static void tcp_connect_init(struct sock *sk) tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) - tp->window_clamp = dst_metric(dst, RTAX_WINDOW); + WRITE_ONCE(tp->window_clamp, dst_metric(dst, RTAX_WINDOW)); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); @@ -3795,7 +3797,7 @@ static void tcp_connect_init(struct sock *sk) /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) - tp->window_clamp = tcp_full_space(sk); + WRITE_ONCE(tp->window_clamp, tcp_full_space(sk)); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 68debc78189c..2062ab94721e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { + bool unknown = false; int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; @@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev, break; #endif default: - if (ndisc_is_useropt(dev, nd_opt)) { - ndopts->nd_useropts_end = nd_opt; - if (!ndopts->nd_useropts) - ndopts->nd_useropts = nd_opt; - } else { - /* - * Unknown options must be silently ignored, - * to accommodate future extension to the - * protocol. - */ - ND_PRINTK(2, notice, - "%s: ignored unsupported option; type=%d, len=%d\n", - __func__, - nd_opt->nd_opt_type, - nd_opt->nd_opt_len); - } + unknown = true; + } + if (ndisc_is_useropt(dev, nd_opt)) { + ndopts->nd_useropts_end = nd_opt; + if (!ndopts->nd_useropts) + ndopts->nd_useropts = nd_opt; + } else if (unknown) { + /* + * Unknown options must be silently ignored, + * to accommodate future extension to the + * protocol. + */ + ND_PRINTK(2, notice, + "%s: ignored unsupported option; type=%d, len=%d\n", + __func__, + nd_opt->nd_opt_type, + nd_opt->nd_opt_len); } next_opt: opt_len -= l; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index bf3cb3a13600..52d597b16b65 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = { static int __init ip6table_nat_init(void) { - int ret = xt_register_template(&nf_nat_ipv6_table, - ip6table_nat_table_init); + int ret; + /* net->gen->ptr[ip6table_nat_net_id] must be allocated + * before calling ip6t_nat_register_lookups(). + */ + ret = register_pernet_subsys(&ip6table_nat_net_ops); if (ret < 0) return ret; - ret = register_pernet_subsys(&ip6table_nat_net_ops); + ret = xt_register_template(&nf_nat_ipv6_table, + ip6table_nat_table_init); if (ret) - xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); return ret; } static void __exit ip6table_nat_exit(void) { - unregister_pernet_subsys(&ip6table_nat_net_ops); xt_unregister_template(&nf_nat_ipv6_table); + unregister_pernet_subsys(&ip6table_nat_net_ops); } module_init(ip6table_nat_init); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8698b49dfc8d..593ead8a45d7 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -243,7 +243,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; } - req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); + req->rsk_window_clamp = READ_ONCE(tp->window_clamp) ? :dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ full_space = tcp_full_space(sk); if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 498a0c35b7bb..815b1df0b2d1 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data) struct iucv_sock *iucv = iucv_sk(sk); struct iucv_path *path = iucv->path; - if (iucv->path) { - iucv->path = NULL; + /* Whoever resets the path pointer, must sever and free it. */ + if (xchg(&iucv->path, NULL)) { if (with_user_data) { low_nmcpy(user_data, iucv->src_name); high_nmcpy(user_data, iucv->dst_name); diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index c30405e76833..7884217f33eb 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS), SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN), SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX), + SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX), + SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX), SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC), SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX), SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index dd7fd1f246b5..443604462ace 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -12,7 +12,9 @@ enum linux_mptcp_mib_field { MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */ + MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */ + MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */ diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 63fc0758c22d..85aafa94cc8a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, return true; } else if (subflow_req->mp_join) { opts->suboptions = OPTION_MPTCP_MPJ_SYNACK; - opts->backup = subflow_req->backup; + opts->backup = subflow_req->request_bkup; opts->join_id = subflow_req->local_id; opts->thmac = subflow_req->thmac; opts->nonce = subflow_req->local_nonce; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index f58bf77d76b8..db621933b203 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -476,7 +476,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con slow = lock_sock_fast(ssk); if (prio) { subflow->send_mp_prio = 1; - subflow->backup = backup; subflow->request_bkup = backup; } @@ -1432,6 +1431,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, ret = remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= ret; mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } @@ -1565,16 +1565,25 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; + int anno_nr = 0; list_for_each_entry(entry, rm_list, list) { - if ((remove_anno_list_by_saddr(msk, &entry->addr) || - lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) && - alist.nr < MPTCP_RM_IDS_MAX) - alist.ids[alist.nr++] = entry->addr.id; + if (alist.nr >= MPTCP_RM_IDS_MAX) + break; + + /* only delete if either announced or matching a subflow */ + if (remove_anno_list_by_saddr(msk, &entry->addr)) + anno_nr++; + else if (!lookup_subflow_by_saddr(&msk->conn_list, + &entry->addr)) + continue; + + alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= anno_nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } @@ -1587,17 +1596,18 @@ void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { - if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && - slist.nr < MPTCP_RM_IDS_MAX) + if (slist.nr < MPTCP_RM_IDS_MAX && + lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) slist.ids[slist.nr++] = entry->addr.id; - if (remove_anno_list_by_saddr(msk, &entry->addr) && - alist.nr < MPTCP_RM_IDS_MAX) + if (alist.nr < MPTCP_RM_IDS_MAX && + remove_anno_list_by_saddr(msk, &entry->addr)) alist.ids[alist.nr++] = entry->addr.id; } if (alist.nr) { spin_lock_bh(&msk->pm.lock); + msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); spin_unlock_bh(&msk->pm.lock); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index fbf2b2676073..c1d652a3f7a9 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -352,8 +352,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_orphan(skb); /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) + if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); goto drop; + } has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -842,16 +844,13 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) sk_rbuf = ssk_rbuf; /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); + if (__mptcp_rmem(sk) > sk_rbuf) return; - } /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); - if (move_skbs_to_msk(msk, ssk)) + if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); - mptcp_data_unlock(sk); } @@ -1418,13 +1417,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } mptcp_for_each_subflow(msk, subflow) { + bool backup = subflow->backup || subflow->request_bkup; + trace_mptcp_subflow_get_send(subflow); ssk = mptcp_subflow_tcp_sock(subflow); if (!mptcp_subflow_active(subflow)) continue; tout = max(tout, mptcp_timeout_from_subflow(subflow)); - nr_active += !subflow->backup; + nr_active += !backup; pace = subflow->avg_pacing_rate; if (unlikely(!pace)) { /* init pacing rate from socket */ @@ -1435,9 +1436,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk) } linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace); - if (linger_time < send_info[subflow->backup].linger_time) { - send_info[subflow->backup].ssk = ssk; - send_info[subflow->backup].linger_time = linger_time; + if (linger_time < send_info[backup].linger_time) { + send_info[backup].ssk = ssk; + send_info[backup].linger_time = linger_time; } } __mptcp_set_timeout(sk, tout); @@ -1918,6 +1919,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, if (!(flags & MSG_PEEK)) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; + msk->bytes_consumed += count; } break; } @@ -1928,6 +1930,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); + msk->bytes_consumed += count; } if (copied >= len) @@ -2023,7 +2026,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) ssk = mptcp_subflow_tcp_sock(subflow); slow = lock_sock_fast(ssk); WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf); - tcp_sk(ssk)->window_clamp = window_clamp; + WRITE_ONCE(tcp_sk(ssk)->window_clamp, window_clamp); tcp_cleanup_rbuf(ssk, 1); unlock_sock_fast(ssk, slow); } @@ -2752,6 +2755,7 @@ static void __mptcp_init_sock(struct sock *sk) msk->rmem_fwd_alloc = 0; WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; + msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -2984,16 +2988,9 @@ void __mptcp_unaccepted_force_close(struct sock *sk) __mptcp_destroy_sock(sk); } -static __poll_t mptcp_check_readable(struct mptcp_sock *msk) +static __poll_t mptcp_check_readable(struct sock *sk) { - /* Concurrent splices from sk_receive_queue into receive_queue will - * always show at least one non-empty queue when checked in this order. - */ - if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) && - skb_queue_empty_lockless(&msk->receive_queue)) - return 0; - - return EPOLLIN | EPOLLRDNORM; + return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0; } static void mptcp_check_listen_stop(struct sock *sk) @@ -3031,7 +3028,7 @@ bool __mptcp_close(struct sock *sk, long timeout) goto cleanup; } - if (mptcp_check_readable(msk) || timeout < 0) { + if (mptcp_data_avail(msk) || timeout < 0) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ @@ -3157,6 +3154,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->snd_data_fin_enable = false; msk->rcv_fastclose = false; msk->use_64bit_ack = false; + msk->bytes_consumed = 0; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); @@ -3983,7 +3981,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { - mask |= mptcp_check_readable(msk); + mask |= mptcp_check_readable(sk); if (shutdown & SEND_SHUTDOWN) mask |= EPOLLOUT | EPOLLWRNORM; else @@ -4021,6 +4019,7 @@ static const struct proto_ops mptcp_stream_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct inet_protosw mptcp_protosw = { @@ -4122,6 +4121,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct proto mptcp_v6_prot; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 93ba48f4ae38..c28ac5dfd0b5 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -268,6 +268,7 @@ struct mptcp_sock { atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; u64 bytes_retrans; + u64 bytes_consumed; int rmem_fwd_alloc; int snd_burst; int old_wspace; @@ -418,6 +419,7 @@ struct mptcp_subflow_request_sock { u16 mp_capable : 1, mp_join : 1, backup : 1, + request_bkup : 1, csum_reqd : 1, allow_join_id0 : 1; u8 local_id; @@ -674,6 +676,24 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk); int mptcp_sched_get_send(struct mptcp_sock *msk); int mptcp_sched_get_retrans(struct mptcp_sock *msk); +static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) +{ + return READ_ONCE(msk->bytes_received) - READ_ONCE(msk->bytes_consumed); +} + +static inline bool mptcp_epollin_ready(const struct sock *sk) +{ + /* mptcp doesn't have to deal with small skbs in the receive queue, + * at it can always coalesce them + */ + return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) || + READ_ONCE(tcp_memory_pressure); +} + +int mptcp_set_rcvlowat(struct sock *sk, int val); + static inline bool __tcp_can_send(const struct sock *ssk) { /* only send if our side has not closed yet */ @@ -748,6 +768,7 @@ static inline bool mptcp_is_fully_established(struct sock *sk) return inet_sk_state_load(sk) == TCP_ESTABLISHED && READ_ONCE(mptcp_sk(sk)->fully_established); } + void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index cc04b5e29dd3..bdfeecea814f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1521,9 +1521,55 @@ void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) msk_owned_by_me(msk); + ssk->sk_rcvlowat = 0; + if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { sync_socket_options(msk, ssk); subflow->setsockopt_seq = msk->setsockopt_seq; } } + +/* unfortunately this is different enough from the tcp version so + * that we can't factor it out + */ +int mptcp_set_rcvlowat(struct sock *sk, int val) +{ + struct mptcp_subflow_context *subflow; + int space, cap; + + /* bpf can land here with a wrong sk type */ + if (sk->sk_protocol == IPPROTO_TCP) + return -EINVAL; + + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + cap = sk->sk_rcvbuf >> 1; + else + cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; + val = min(val, cap); + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); + + /* Check if we need to signal EPOLLIN right now */ + if (mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); + + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + return 0; + + space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val); + if (space <= sk->sk_rcvbuf) + return 0; + + /* propagate the rcvbuf changes to all the subflows */ + WRITE_ONCE(sk->sk_rcvbuf, space); + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + WRITE_ONCE(ssk->sk_rcvbuf, space); + WRITE_ONCE(tcp_sk(ssk)->window_clamp, val); + unlock_sock_fast(ssk, slow); + } + return 0; +} diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 23ee96c6abcb..bc1efc178772 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -166,6 +166,9 @@ static int subflow_check_req(struct request_sock *req, return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); + + if (mp_opt.backup) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX); } if (opt_mp_capable && listener->request_mptcp) { @@ -558,6 +561,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->mp_join = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); + if (subflow->backup) + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX); + if (subflow_use_different_dport(msk, sk)) { pr_debug("synack inet_dport=%d %d", ntohs(inet_sk(sk)->inet_dport), @@ -1192,14 +1198,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; - u32 incr; + struct tcp_sock *tp = tcp_sk(ssk); + u32 offset, incr, avail_len; + + offset = tp->copied_seq - TCP_SKB_CB(skb)->seq; + if (WARN_ON_ONCE(offset > skb->len)) + goto out; - incr = limit >= skb->len ? skb->len + fin : limit; + avail_len = skb->len - offset; + incr = limit >= avail_len ? avail_len + fin : limit; - pr_debug("discarding=%d len=%d seq=%d", incr, skb->len, - subflow->map_subflow_seq); + pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len, + offset, subflow->map_subflow_seq); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA); tcp_sk(ssk)->copied_seq += incr; + +out: if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq)) sk_eat_skb(ssk, skb); if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) @@ -1432,10 +1446,18 @@ static void subflow_data_ready(struct sock *sk) WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && !subflow->mp_join && !(state & TCPF_CLOSE)); - if (mptcp_subflow_data_available(sk)) + if (mptcp_subflow_data_available(sk)) { mptcp_data_ready(parent, sk); - else if (unlikely(sk->sk_err)) + + /* subflow-level lowat test are not relevant. + * respect the msk-level threshold eventually mandating an immediate ack + */ + if (mptcp_data_avail(msk) < parent->sk_rcvlowat && + (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } else if (unlikely(sk->sk_err)) { subflow_error_report(sk); + } } static void subflow_write_space(struct sock *ssk) @@ -1968,6 +1990,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; + new_ctx->request_bkup = subflow_req->request_bkup; WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 3ac19516ed80..50d24e240e8f 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -44,6 +44,8 @@ static DEFINE_MUTEX(zones_mutex); struct zones_ht_key { struct net *net; u16 zone; + /* Note : pad[] must be the last field. */ + u8 pad[]; }; struct tcf_ct_flow_table { @@ -60,7 +62,7 @@ struct tcf_ct_flow_table { static const struct rhashtable_params zones_params = { .head_offset = offsetof(struct tcf_ct_flow_table, node), .key_offset = offsetof(struct tcf_ct_flow_table, key), - .key_len = sizeof_field(struct tcf_ct_flow_table, key), + .key_len = offsetof(struct zones_ht_key, pad), .automatic_shrinking = true, }; diff --git a/net/sysctl_net.c b/net/sysctl_net.c index 051ed5f6fc93..a0a7a79991f9 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -54,7 +54,6 @@ static int net_ctl_permissions(struct ctl_table_header *head, } static void net_ctl_set_ownership(struct ctl_table_header *head, - struct ctl_table *table, kuid_t *uid, kgid_t *gid) { struct net *net = container_of(head->set, struct net, sysctls); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 9bba233b5a6e..72d78dbc55ff 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1057,6 +1057,7 @@ void cfg80211_connect_done(struct net_device *dev, cfg80211_hold_bss( bss_from_pub(params->links[link].bss)); ev->cr.links[link].bss = params->links[link].bss; + ev->cr.links[link].status = params->links[link].status; if (params->links[link].addr) { ev->cr.links[link].addr = next; diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c index e90b27a135e6..d9dacfbe4a9a 100644 --- a/sound/core/seq/seq_ump_convert.c +++ b/sound/core/seq/seq_ump_convert.c @@ -1192,44 +1192,53 @@ static int cvt_sysex_to_ump(struct snd_seq_client *dest, { struct snd_seq_ump_event ev_cvt; unsigned char status; - u8 buf[6], *xbuf; + u8 buf[8], *xbuf; int offset = 0; int len, err; + bool finished = false; if (!snd_seq_ev_is_variable(event)) return 0; setup_ump_event(&ev_cvt, event); - for (;;) { + while (!finished) { len = snd_seq_expand_var_event_at(event, sizeof(buf), buf, offset); if (len <= 0) break; - if (WARN_ON(len > 6)) + if (WARN_ON(len > sizeof(buf))) break; - offset += len; + xbuf = buf; + status = UMP_SYSEX_STATUS_CONTINUE; + /* truncate the sysex start-marker */ if (*xbuf == UMP_MIDI1_MSG_SYSEX_START) { status = UMP_SYSEX_STATUS_START; - xbuf++; len--; - if (len > 0 && xbuf[len - 1] == UMP_MIDI1_MSG_SYSEX_END) { + offset++; + xbuf++; + } + + /* if the last of this packet or the 1st byte of the next packet + * is the end-marker, finish the transfer with this packet + */ + if (len > 0 && len < 8 && + xbuf[len - 1] == UMP_MIDI1_MSG_SYSEX_END) { + if (status == UMP_SYSEX_STATUS_START) status = UMP_SYSEX_STATUS_SINGLE; - len--; - } - } else { - if (xbuf[len - 1] == UMP_MIDI1_MSG_SYSEX_END) { + else status = UMP_SYSEX_STATUS_END; - len--; - } else { - status = UMP_SYSEX_STATUS_CONTINUE; - } + len--; + finished = true; } + + len = min(len, 6); fill_sysex7_ump(dest_port, ev_cvt.ump, status, xbuf, len); err = __snd_seq_deliver_single_event(dest, dest_port, (struct snd_seq_event *)&ev_cvt, atomic, hop); if (err < 0) return err; + offset += len; } return 0; } diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c index c9f153f85ae6..5f0f8d9c08d1 100644 --- a/sound/firewire/amdtp-stream.c +++ b/sound/firewire/amdtp-stream.c @@ -77,6 +77,8 @@ // overrun. Actual device can skip more, then this module stops the packet streaming. #define IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES 5 +static void pcm_period_work(struct work_struct *work); + /** * amdtp_stream_init - initialize an AMDTP stream structure * @s: the AMDTP stream to initialize @@ -105,6 +107,7 @@ int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit, s->flags = flags; s->context = ERR_PTR(-1); mutex_init(&s->mutex); + INIT_WORK(&s->period_work, pcm_period_work); s->packet_index = 0; init_waitqueue_head(&s->ready_wait); @@ -347,6 +350,7 @@ EXPORT_SYMBOL(amdtp_stream_get_max_payload); */ void amdtp_stream_pcm_prepare(struct amdtp_stream *s) { + cancel_work_sync(&s->period_work); s->pcm_buffer_pointer = 0; s->pcm_period_pointer = 0; } @@ -611,19 +615,21 @@ static void update_pcm_pointers(struct amdtp_stream *s, // The program in user process should periodically check the status of intermediate // buffer associated to PCM substream to process PCM frames in the buffer, instead // of receiving notification of period elapsed by poll wait. - if (!pcm->runtime->no_period_wakeup) { - if (in_softirq()) { - // In software IRQ context for 1394 OHCI. - snd_pcm_period_elapsed(pcm); - } else { - // In process context of ALSA PCM application under acquired lock of - // PCM substream. - snd_pcm_period_elapsed_under_stream_lock(pcm); - } - } + if (!pcm->runtime->no_period_wakeup) + queue_work(system_highpri_wq, &s->period_work); } } +static void pcm_period_work(struct work_struct *work) +{ + struct amdtp_stream *s = container_of(work, struct amdtp_stream, + period_work); + struct snd_pcm_substream *pcm = READ_ONCE(s->pcm); + + if (pcm) + snd_pcm_period_elapsed(pcm); +} + static int queue_packet(struct amdtp_stream *s, struct fw_iso_packet *params, bool sched_irq) { @@ -1852,11 +1858,14 @@ unsigned long amdtp_domain_stream_pcm_pointer(struct amdtp_domain *d, { struct amdtp_stream *irq_target = d->irq_target; - // Process isochronous packets queued till recent isochronous cycle to handle PCM frames. if (irq_target && amdtp_stream_running(irq_target)) { - // In software IRQ context, the call causes dead-lock to disable the tasklet - // synchronously. - if (!in_softirq()) + // use wq to prevent AB/BA deadlock competition for + // substream lock: + // fw_iso_context_flush_completions() acquires + // lock by ohci_flush_iso_completions(), + // amdtp-stream process_rx_packets() attempts to + // acquire same lock by snd_pcm_elapsed() + if (current_work() != &s->period_work) fw_iso_context_flush_completions(irq_target->context); } @@ -1912,6 +1921,7 @@ static void amdtp_stream_stop(struct amdtp_stream *s) return; } + cancel_work_sync(&s->period_work); fw_iso_context_stop(s->context); fw_iso_context_destroy(s->context); s->context = ERR_PTR(-1); diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h index a1ed2e80f91a..775db3fc4959 100644 --- a/sound/firewire/amdtp-stream.h +++ b/sound/firewire/amdtp-stream.h @@ -191,6 +191,7 @@ struct amdtp_stream { /* For a PCM substream processing. */ struct snd_pcm_substream *pcm; + struct work_struct period_work; snd_pcm_uframes_t pcm_buffer_pointer; unsigned int pcm_period_pointer; unsigned int pcm_frame_multiplier; diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h index 8556031bcd68..f31cb31d4636 100644 --- a/sound/pci/hda/hda_controller.h +++ b/sound/pci/hda/hda_controller.h @@ -28,7 +28,7 @@ #else #define AZX_DCAPS_I915_COMPONENT 0 /* NOP */ #endif -/* 14 unused */ +#define AZX_DCAPS_AMD_ALLOC_FIX (1 << 14) /* AMD allocation workaround */ #define AZX_DCAPS_CTX_WORKAROUND (1 << 15) /* X-Fi workaround */ #define AZX_DCAPS_POSFIX_LPIB (1 << 16) /* Use LPIB as default */ #define AZX_DCAPS_AMD_WORKAROUND (1 << 17) /* AMD-specific workaround */ diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index a6a9d353fe63..d5c9f113e477 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -40,6 +40,7 @@ #ifdef CONFIG_X86 /* for snoop control */ +#include <linux/dma-map-ops.h> #include <asm/set_memory.h> #include <asm/cpufeature.h> #endif @@ -301,7 +302,7 @@ enum { /* quirks for ATI HDMI with snoop off */ #define AZX_DCAPS_PRESET_ATI_HDMI_NS \ - (AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_SNOOP_OFF) + (AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_AMD_ALLOC_FIX) /* quirks for AMD SB */ #define AZX_DCAPS_PRESET_AMD_SB \ @@ -1715,6 +1716,13 @@ static void azx_check_snoop_available(struct azx *chip) if (chip->driver_caps & AZX_DCAPS_SNOOP_OFF) snoop = false; +#ifdef CONFIG_X86 + /* check the presence of DMA ops (i.e. IOMMU), disable snoop conditionally */ + if ((chip->driver_caps & AZX_DCAPS_AMD_ALLOC_FIX) && + !get_dma_ops(chip->card->dev)) + snoop = false; +#endif + chip->snoop = snoop; if (!snoop) { dev_info(chip->card->dev, "Force to non-snoop mode\n"); diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index e8209178d87b..af921364195e 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -21,12 +21,6 @@ #include "hda_jack.h" #include "hda_generic.h" -enum { - CX_HEADSET_NOPRESENT = 0, - CX_HEADSET_PARTPRESENT, - CX_HEADSET_ALLPRESENT, -}; - struct conexant_spec { struct hda_gen_spec gen; @@ -48,7 +42,6 @@ struct conexant_spec { unsigned int gpio_led; unsigned int gpio_mute_led_mask; unsigned int gpio_mic_led_mask; - unsigned int headset_present_flag; bool is_cx8070_sn6140; }; @@ -250,48 +243,19 @@ static void cx_process_headset_plugin(struct hda_codec *codec) } } -static void cx_update_headset_mic_vref(struct hda_codec *codec, unsigned int res) +static void cx_update_headset_mic_vref(struct hda_codec *codec, struct hda_jack_callback *event) { - unsigned int phone_present, mic_persent, phone_tag, mic_tag; - struct conexant_spec *spec = codec->spec; + unsigned int mic_present; /* In cx8070 and sn6140, the node 16 can only be config to headphone or disabled, * the node 19 can only be config to microphone or disabled. * Check hp&mic tag to process headset pulgin&plugout. */ - phone_tag = snd_hda_codec_read(codec, 0x16, 0, AC_VERB_GET_UNSOLICITED_RESPONSE, 0x0); - mic_tag = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_UNSOLICITED_RESPONSE, 0x0); - if ((phone_tag & (res >> AC_UNSOL_RES_TAG_SHIFT)) || - (mic_tag & (res >> AC_UNSOL_RES_TAG_SHIFT))) { - phone_present = snd_hda_codec_read(codec, 0x16, 0, AC_VERB_GET_PIN_SENSE, 0x0); - if (!(phone_present & AC_PINSENSE_PRESENCE)) {/* headphone plugout */ - spec->headset_present_flag = CX_HEADSET_NOPRESENT; - snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x20); - return; - } - if (spec->headset_present_flag == CX_HEADSET_NOPRESENT) { - spec->headset_present_flag = CX_HEADSET_PARTPRESENT; - } else if (spec->headset_present_flag == CX_HEADSET_PARTPRESENT) { - mic_persent = snd_hda_codec_read(codec, 0x19, 0, - AC_VERB_GET_PIN_SENSE, 0x0); - /* headset is present */ - if ((phone_present & AC_PINSENSE_PRESENCE) && - (mic_persent & AC_PINSENSE_PRESENCE)) { - cx_process_headset_plugin(codec); - spec->headset_present_flag = CX_HEADSET_ALLPRESENT; - } - } - } -} - -static void cx_jack_unsol_event(struct hda_codec *codec, unsigned int res) -{ - struct conexant_spec *spec = codec->spec; - - if (spec->is_cx8070_sn6140) - cx_update_headset_mic_vref(codec, res); - - snd_hda_jack_unsol_event(codec, res); + mic_present = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_PIN_SENSE, 0x0); + if (!(mic_present & AC_PINSENSE_PRESENCE)) /* mic plugout */ + snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x20); + else + cx_process_headset_plugin(codec); } #ifdef CONFIG_PM @@ -307,7 +271,7 @@ static const struct hda_codec_ops cx_auto_patch_ops = { .build_pcms = snd_hda_gen_build_pcms, .init = cx_auto_init, .free = cx_auto_free, - .unsol_event = cx_jack_unsol_event, + .unsol_event = snd_hda_jack_unsol_event, #ifdef CONFIG_PM .suspend = cx_auto_suspend, .check_power_status = snd_hda_gen_check_power_status, @@ -1167,7 +1131,7 @@ static int patch_conexant_auto(struct hda_codec *codec) case 0x14f11f86: case 0x14f11f87: spec->is_cx8070_sn6140 = true; - spec->headset_present_flag = CX_HEADSET_NOPRESENT; + snd_hda_jack_detect_enable_callback(codec, 0x19, cx_update_headset_mic_vref); break; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index f3aca1c38b77..0b33a0077145 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9639,6 +9639,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF), + SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK), SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC), diff --git a/sound/usb/stream.c b/sound/usb/stream.c index d5409f387945..e14c725acebf 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -244,8 +244,8 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits, SNDRV_CHMAP_FR, /* right front */ SNDRV_CHMAP_FC, /* center front */ SNDRV_CHMAP_LFE, /* LFE */ - SNDRV_CHMAP_SL, /* left surround */ - SNDRV_CHMAP_SR, /* right surround */ + SNDRV_CHMAP_RL, /* left surround */ + SNDRV_CHMAP_RR, /* right surround */ SNDRV_CHMAP_FLC, /* left of center */ SNDRV_CHMAP_FRC, /* right of center */ SNDRV_CHMAP_RC, /* surround */ diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index aee937d14fbb..09e6b4e1401c 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1126,7 +1126,7 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node, bool hide_unresolved) { - struct machine *machine = maps__machine(node->ms.maps); + struct machine *machine = node->ms.maps ? maps__machine(node->ms.maps) : NULL; maps__put(al->maps); al->maps = maps__get(node->ms.maps); diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index d2043ec3bf6d..4209b9569039 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1115,11 +1115,11 @@ int main_loop_s(int listensock) return 1; } - if (--cfg_repeat > 0) { - if (cfg_input) - close(fd); + if (cfg_input) + close(fd); + + if (--cfg_repeat > 0) goto again; - } return 0; } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 231a95a8de9e..a2dae2a3a93e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1778,6 +1778,8 @@ chk_prio_nr() { local mp_prio_nr_tx=$1 local mp_prio_nr_rx=$2 + local mpj_syn=$3 + local mpj_syn_ack=$4 local count print_check "ptx" @@ -1799,6 +1801,26 @@ chk_prio_nr() else print_ok fi + + print_check "syn backup" + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynBackupRx") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$mpj_syn" ]; then + fail_test "got $count JOIN[s] syn with Backup expected $mpj_syn" + else + print_ok + fi + + print_check "synack backup" + count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckBackupRx") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$mpj_syn_ack" ]; then + fail_test "got $count JOIN[s] synack with Backup expected $mpj_syn_ack" + else + print_ok + fi } chk_subflow_nr() @@ -2751,11 +2773,24 @@ backup_tests() sflags=nobackup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 fi # single address, backup if reset "single address, backup" && + continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup + pm_nl_set_limits $ns2 1 1 + sflags=nobackup speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 0 0 1 + fi + + # single address, switch to backup + if reset "single address, switch to backup" && continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 pm_nl_add_endpoint $ns1 10.0.2.1 flags signal @@ -2764,20 +2799,20 @@ backup_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 1 + chk_prio_nr 1 1 0 0 fi # single address with port, backup if reset "single address with port, backup" && continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup port 10100 pm_nl_set_limits $ns2 1 1 - sflags=backup speed=slow \ + sflags=nobackup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_add_nr 1 1 - chk_prio_nr 1 1 + chk_prio_nr 1 0 0 1 fi if reset "mpc backup" && @@ -2786,17 +2821,26 @@ backup_tests() speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 0 1 + chk_prio_nr 0 1 0 0 fi if reset "mpc backup both sides" && continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then - pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal,backup pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup + + # 10.0.2.2 (non-backup) -> 10.0.1.1 (backup) + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + # 10.0.1.2 (backup) -> 10.0.2.1 (non-backup) + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + ip -net "$ns2" route add 10.0.2.1 via 10.0.1.1 dev ns2eth1 # force this path + speed=slow \ run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr 0 0 0 - chk_prio_nr 1 1 + chk_join_nr 2 2 2 + chk_prio_nr 1 1 1 1 fi if reset "mpc switch to backup" && @@ -2805,7 +2849,7 @@ backup_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 0 1 + chk_prio_nr 0 1 0 0 fi if reset "mpc switch to backup both sides" && @@ -2815,7 +2859,7 @@ backup_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 0 0 0 - chk_prio_nr 1 1 + chk_prio_nr 1 1 0 0 fi } @@ -3215,7 +3259,7 @@ fullmesh_tests() addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 chk_rm_nr 0 1 fi @@ -3228,7 +3272,7 @@ fullmesh_tests() sflags=nobackup,nofullmesh speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 - chk_prio_nr 0 1 + chk_prio_nr 0 1 1 0 chk_rm_nr 0 1 fi } @@ -3407,7 +3451,7 @@ userspace_tests() sflags=backup speed=slow \ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 0 - chk_prio_nr 0 0 + chk_prio_nr 0 0 0 0 fi # userspace pm type prevents rm_addr