diff options
388 files changed, 4643 insertions, 2282 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 19f4423e70d9..aefd358a5ca3 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -856,7 +856,8 @@ causing system reset or hang due to sending INIT from AP to BSP. - disable_counter_freezing [HW] + perf_v4_pmi= [X86,INTEL] + Format: <bool> Disable Intel PMU counter freezing feature. The feature only exists starting from Arch Perfmon v4 (Skylake and newer). @@ -3504,6 +3505,10 @@ before loading. See Documentation/blockdev/ramdisk.txt. + psi= [KNL] Enable or disable pressure stall information + tracking. + Format: <bool> + psmouse.proto= [HW,MOUSE] Highest PS2 mouse protocol extension to probe for; one of (bare|imps|exps|lifebook|any). psmouse.rate= [HW,MOUSE] Set desired mouse report rate, in reports @@ -4194,9 +4199,13 @@ spectre_v2= [X86] Control mitigation of Spectre variant 2 (indirect branch speculation) vulnerability. + The default operation protects the kernel from + user space attacks. - on - unconditionally enable - off - unconditionally disable + on - unconditionally enable, implies + spectre_v2_user=on + off - unconditionally disable, implies + spectre_v2_user=off auto - kernel detects whether your CPU model is vulnerable @@ -4206,6 +4215,12 @@ CONFIG_RETPOLINE configuration option, and the compiler with which the kernel was built. + Selecting 'on' will also enable the mitigation + against user space to user space task attacks. + + Selecting 'off' will disable both the kernel and + the user space protections. + Specific mitigations can also be selected manually: retpoline - replace indirect branches @@ -4215,6 +4230,48 @@ Not specifying this option is equivalent to spectre_v2=auto. + spectre_v2_user= + [X86] Control mitigation of Spectre variant 2 + (indirect branch speculation) vulnerability between + user space tasks + + on - Unconditionally enable mitigations. Is + enforced by spectre_v2=on + + off - Unconditionally disable mitigations. Is + enforced by spectre_v2=off + + prctl - Indirect branch speculation is enabled, + but mitigation can be enabled via prctl + per thread. The mitigation control state + is inherited on fork. + + prctl,ibpb + - Like "prctl" above, but only STIBP is + controlled per thread. IBPB is issued + always when switching between different user + space processes. + + seccomp + - Same as "prctl" above, but all seccomp + threads will enable the mitigation unless + they explicitly opt out. + + seccomp,ibpb + - Like "seccomp" above, but only STIBP is + controlled per thread. IBPB is issued + always when switching between different + user space processes. + + auto - Kernel selects the mitigation depending on + the available CPU features and vulnerability. + + Default mitigation: + If CONFIG_SECCOMP=y then "seccomp", otherwise "prctl" + + Not specifying this option is equivalent to + spectre_v2_user=auto. + spec_store_bypass_disable= [HW] Control Speculative Store Bypass (SSB) Disable mitigation (Speculative Store Bypass vulnerability) diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 76ccded8b74c..8f9577621144 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -57,6 +57,7 @@ stable kernels. | ARM | Cortex-A73 | #858921 | ARM64_ERRATUM_858921 | | ARM | Cortex-A55 | #1024718 | ARM64_ERRATUM_1024718 | | ARM | Cortex-A76 | #1188873 | ARM64_ERRATUM_1188873 | +| ARM | Cortex-A76 | #1286807 | ARM64_ERRATUM_1286807 | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | diff --git a/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt b/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt index adf20b2bdf71..fbc198d5dd39 100644 --- a/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt +++ b/Documentation/devicetree/bindings/phy/qcom-qmp-phy.txt @@ -40,24 +40,36 @@ Required properties: "ref" for 19.2 MHz ref clk, "com_aux" for phy common block aux clock, "ref_aux" for phy reference aux clock, + + For "qcom,ipq8074-qmp-pcie-phy": no clocks are listed. For "qcom,msm8996-qmp-pcie-phy" must contain: "aux", "cfg_ahb", "ref". For "qcom,msm8996-qmp-usb3-phy" must contain: "aux", "cfg_ahb", "ref". - For "qcom,qmp-v3-usb3-phy" must contain: + For "qcom,sdm845-qmp-usb3-phy" must contain: + "aux", "cfg_ahb", "ref", "com_aux". + For "qcom,sdm845-qmp-usb3-uni-phy" must contain: "aux", "cfg_ahb", "ref", "com_aux". + For "qcom,sdm845-qmp-ufs-phy" must contain: + "ref", "ref_aux". - resets: a list of phandles and reset controller specifier pairs, one for each entry in reset-names. - reset-names: "phy" for reset of phy block, "common" for phy common block reset, - "cfg" for phy's ahb cfg block reset (Optional). + "cfg" for phy's ahb cfg block reset. + + For "qcom,ipq8074-qmp-pcie-phy" must contain: + "phy", "common". For "qcom,msm8996-qmp-pcie-phy" must contain: - "phy", "common", "cfg". + "phy", "common", "cfg". For "qcom,msm8996-qmp-usb3-phy" must contain - "phy", "common". - For "qcom,ipq8074-qmp-pcie-phy" must contain: - "phy", "common". + "phy", "common". + For "qcom,sdm845-qmp-usb3-phy" must contain: + "phy", "common". + For "qcom,sdm845-qmp-usb3-uni-phy" must contain: + "phy", "common". + For "qcom,sdm845-qmp-ufs-phy": no resets are listed. - vdda-phy-supply: Phandle to a regulator supply to PHY core block. - vdda-pll-supply: Phandle to 1.8V regulator supply to PHY refclk pll block. @@ -79,9 +91,10 @@ Required properties for child node: - #phy-cells: must be 0 +Required properties child node of pcie and usb3 qmp phys: - clocks: a list of phandles and clock-specifier pairs, one for each entry in clock-names. - - clock-names: Must contain following for pcie and usb qmp phys: + - clock-names: Must contain following: "pipe<lane-number>" for pipe clock specific to each lane. - clock-output-names: Name of the PHY clock that will be the parent for the above pipe clock. @@ -91,9 +104,11 @@ Required properties for child node: (or) "pcie20_phy1_pipe_clk" +Required properties for child node of PHYs with lane reset, AKA: + "qcom,msm8996-qmp-pcie-phy" - resets: a list of phandles and reset controller specifier pairs, one for each entry in reset-names. - - reset-names: Must contain following for pcie qmp phys: + - reset-names: Must contain following: "lane<lane-number>" for reset specific to each lane. Example: diff --git a/Documentation/devicetree/bindings/spi/spi-uniphier.txt b/Documentation/devicetree/bindings/spi/spi-uniphier.txt index 504a4ecfc7b1..b04e66a52de5 100644 --- a/Documentation/devicetree/bindings/spi/spi-uniphier.txt +++ b/Documentation/devicetree/bindings/spi/spi-uniphier.txt @@ -5,18 +5,20 @@ UniPhier SoCs have SCSSI which supports SPI single channel. Required properties: - compatible: should be "socionext,uniphier-scssi" - reg: address and length of the spi master registers - - #address-cells: must be <1>, see spi-bus.txt - - #size-cells: must be <0>, see spi-bus.txt - - clocks: A phandle to the clock for the device. - - resets: A phandle to the reset control for the device. + - interrupts: a single interrupt specifier + - pinctrl-names: should be "default" + - pinctrl-0: pin control state for the default mode + - clocks: a phandle to the clock for the device + - resets: a phandle to the reset control for the device Example: spi0: spi@54006000 { compatible = "socionext,uniphier-scssi"; reg = <0x54006000 0x100>; - #address-cells = <1>; - #size-cells = <0>; + interrupts = <0 39 4>; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_spi0>; clocks = <&peri_clk 11>; resets = <&peri_rst 11>; }; diff --git a/Documentation/userspace-api/spec_ctrl.rst b/Documentation/userspace-api/spec_ctrl.rst index 32f3d55c54b7..c4dbe6f7cdae 100644 --- a/Documentation/userspace-api/spec_ctrl.rst +++ b/Documentation/userspace-api/spec_ctrl.rst @@ -92,3 +92,12 @@ Speculation misfeature controls * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_ENABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_DISABLE, 0, 0); * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_STORE_BYPASS, PR_SPEC_FORCE_DISABLE, 0, 0); + +- PR_SPEC_INDIR_BRANCH: Indirect Branch Speculation in User Processes + (Mitigate Spectre V2 style attacks against user processes) + + Invocations: + * prctl(PR_GET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, 0, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_ENABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_DISABLE, 0, 0); + * prctl(PR_SET_SPECULATION_CTRL, PR_SPEC_INDIRECT_BRANCH, PR_SPEC_FORCE_DISABLE, 0, 0); diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt index 7727db8f94bc..5e9b826b5f62 100644 --- a/Documentation/x86/boot.txt +++ b/Documentation/x86/boot.txt @@ -61,18 +61,6 @@ Protocol 2.12: (Kernel 3.8) Added the xloadflags field and extension fields to struct boot_params for loading bzImage and ramdisk above 4G in 64bit. -Protocol 2.13: (Kernel 3.14) Support 32- and 64-bit flags being set in - xloadflags to support booting a 64-bit kernel from 32-bit - EFI - -Protocol 2.14: (Kernel 4.20) Added acpi_rsdp_addr holding the physical - address of the ACPI RSDP table. - The bootloader updates version with: - 0x8000 | min(kernel-version, bootloader-version) - kernel-version being the protocol version supported by - the kernel and bootloader-version the protocol version - supported by the bootloader. - **** MEMORY LAYOUT The traditional memory map for the kernel loader, used for Image or @@ -209,7 +197,6 @@ Offset Proto Name Meaning 0258/8 2.10+ pref_address Preferred loading address 0260/4 2.10+ init_size Linear memory required during initialization 0264/4 2.11+ handover_offset Offset of handover entry point -0268/8 2.14+ acpi_rsdp_addr Physical address of RSDP table (1) For backwards compatibility, if the setup_sects field contains 0, the real value is 4. @@ -322,7 +309,7 @@ Protocol: 2.00+ Contains the magic number "HdrS" (0x53726448). Field name: version -Type: modify +Type: read Offset/size: 0x206/2 Protocol: 2.00+ @@ -330,12 +317,6 @@ Protocol: 2.00+ e.g. 0x0204 for version 2.04, and 0x0a11 for a hypothetical version 10.17. - Up to protocol version 2.13 this information is only read by the - bootloader. From protocol version 2.14 onwards the bootloader will - write the used protocol version or-ed with 0x8000 to the field. The - used protocol version will be the minimum of the supported protocol - versions of the bootloader and the kernel. - Field name: realmode_swtch Type: modify (optional) Offset/size: 0x208/4 @@ -763,17 +744,6 @@ Offset/size: 0x264/4 See EFI HANDOVER PROTOCOL below for more details. -Field name: acpi_rsdp_addr -Type: write -Offset/size: 0x268/8 -Protocol: 2.14+ - - This field can be set by the boot loader to tell the kernel the - physical address of the ACPI RSDP table. - - A value of 0 indicates the kernel should fall back to the standard - methods to locate the RSDP. - **** THE IMAGE CHECKSUM diff --git a/MAINTAINERS b/MAINTAINERS index d1973c3110f1..0390b4fa3ffe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1924,7 +1924,6 @@ ARM/QUALCOMM SUPPORT M: Andy Gross <andy.gross@linaro.org> M: David Brown <david.brown@linaro.org> L: linux-arm-msm@vger.kernel.org -L: linux-soc@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/soc/qcom/ F: arch/arm/boot/dts/qcom-*.dts @@ -2492,7 +2491,7 @@ F: drivers/net/wireless/ath/* ATHEROS ATH5K WIRELESS DRIVER M: Jiri Slaby <jirislaby@gmail.com> M: Nick Kossifidis <mickflemm@gmail.com> -M: "Luis R. Rodriguez" <mcgrof@do-not-panic.com> +M: Luis Chamberlain <mcgrof@kernel.org> L: linux-wireless@vger.kernel.org W: http://wireless.kernel.org/en/users/Drivers/ath5k S: Maintained @@ -2802,7 +2801,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git Q: https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147 S: Supported -F: arch/x86/net/bpf_jit* +F: arch/*/net/* F: Documentation/networking/filter.txt F: Documentation/bpf/ F: include/linux/bpf* @@ -2822,6 +2821,67 @@ F: tools/bpf/ F: tools/lib/bpf/ F: tools/testing/selftests/bpf/ +BPF JIT for ARM +M: Shubham Bansal <illusionist.neo@gmail.com> +L: netdev@vger.kernel.org +S: Maintained +F: arch/arm/net/ + +BPF JIT for ARM64 +M: Daniel Borkmann <daniel@iogearbox.net> +M: Alexei Starovoitov <ast@kernel.org> +M: Zi Shen Lim <zlim.lnx@gmail.com> +L: netdev@vger.kernel.org +S: Supported +F: arch/arm64/net/ + +BPF JIT for MIPS (32-BIT AND 64-BIT) +M: Paul Burton <paul.burton@mips.com> +L: netdev@vger.kernel.org +S: Maintained +F: arch/mips/net/ + +BPF JIT for NFP NICs +M: Jakub Kicinski <jakub.kicinski@netronome.com> +L: netdev@vger.kernel.org +S: Supported +F: drivers/net/ethernet/netronome/nfp/bpf/ + +BPF JIT for POWERPC (32-BIT AND 64-BIT) +M: Naveen N. Rao <naveen.n.rao@linux.ibm.com> +M: Sandipan Das <sandipan@linux.ibm.com> +L: netdev@vger.kernel.org +S: Maintained +F: arch/powerpc/net/ + +BPF JIT for S390 +M: Martin Schwidefsky <schwidefsky@de.ibm.com> +M: Heiko Carstens <heiko.carstens@de.ibm.com> +L: netdev@vger.kernel.org +S: Maintained +F: arch/s390/net/ +X: arch/s390/net/pnet.c + +BPF JIT for SPARC (32-BIT AND 64-BIT) +M: David S. Miller <davem@davemloft.net> +L: netdev@vger.kernel.org +S: Maintained +F: arch/sparc/net/ + +BPF JIT for X86 32-BIT +M: Wang YanQing <udknight@gmail.com> +L: netdev@vger.kernel.org +S: Maintained +F: arch/x86/net/bpf_jit_comp32.c + +BPF JIT for X86 64-BIT +M: Alexei Starovoitov <ast@kernel.org> +M: Daniel Borkmann <daniel@iogearbox.net> +L: netdev@vger.kernel.org +S: Supported +F: arch/x86/net/ +X: arch/x86/net/bpf_jit_comp32.c + BROADCOM B44 10/100 ETHERNET DRIVER M: Michael Chan <michael.chan@broadcom.com> L: netdev@vger.kernel.org @@ -2862,7 +2922,7 @@ F: drivers/staging/vc04_services BROADCOM BCM47XX MIPS ARCHITECTURE M: Hauke Mehrtens <hauke@hauke-m.de> M: RafaÅ‚ MiÅ‚ecki <zajec5@gmail.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/mips/brcm/ F: arch/mips/bcm47xx/* @@ -2871,7 +2931,6 @@ F: arch/mips/include/asm/mach-bcm47xx/* BROADCOM BCM5301X ARM ARCHITECTURE M: Hauke Mehrtens <hauke@hauke-m.de> M: RafaÅ‚ MiÅ‚ecki <zajec5@gmail.com> -M: Jon Mason <jonmason@broadcom.com> M: bcm-kernel-feedback-list@broadcom.com L: linux-arm-kernel@lists.infradead.org S: Maintained @@ -2926,7 +2985,7 @@ F: drivers/cpufreq/bmips-cpufreq.c BROADCOM BMIPS MIPS ARCHITECTURE M: Kevin Cernekee <cernekee@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org T: git git://github.com/broadcom/stblinux.git S: Maintained F: arch/mips/bmips/* @@ -3017,7 +3076,6 @@ F: drivers/net/ethernet/broadcom/genet/ BROADCOM IPROC ARM ARCHITECTURE M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> -M: Jon Mason <jonmason@broadcom.com> M: bcm-kernel-feedback-list@broadcom.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/broadcom/cygnus-linux.git @@ -3064,7 +3122,7 @@ F: include/uapi/rdma/bnxt_re-abi.h BROADCOM NVRAM DRIVER M: RafaÅ‚ MiÅ‚ecki <zajec5@gmail.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: drivers/firmware/broadcom/* @@ -4166,7 +4224,7 @@ F: net/decnet/ DECSTATION PLATFORM SUPPORT M: "Maciej W. Rozycki" <macro@linux-mips.org> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org W: http://www.linux-mips.org/wiki/DECstation S: Maintained F: arch/mips/dec/ @@ -5257,7 +5315,7 @@ EDAC-CAVIUM OCTEON M: Ralf Baechle <ralf@linux-mips.org> M: David Daney <david.daney@cavium.com> L: linux-edac@vger.kernel.org -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Supported F: drivers/edac/octeon_edac* @@ -5775,7 +5833,7 @@ F: include/uapi/linux/firewire*.h F: tools/firewire/ FIRMWARE LOADER (request_firmware) -M: Luis R. Rodriguez <mcgrof@kernel.org> +M: Luis Chamberlain <mcgrof@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/firmware_class/ @@ -7704,7 +7762,7 @@ F: Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt IOC3 ETHERNET DRIVER M: Ralf Baechle <ralf@linux-mips.org> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: drivers/net/ethernet/sgi/ioc3-eth.c @@ -8075,7 +8133,7 @@ F: tools/testing/selftests/ F: Documentation/dev-tools/kselftest* KERNEL USERMODE HELPER -M: "Luis R. Rodriguez" <mcgrof@kernel.org> +M: Luis Chamberlain <mcgrof@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: kernel/umh.c @@ -8132,7 +8190,7 @@ F: arch/arm64/kvm/ KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips) M: James Hogan <jhogan@kernel.org> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Supported F: arch/mips/include/uapi/asm/kvm* F: arch/mips/include/asm/kvm* @@ -8251,7 +8309,7 @@ F: mm/kmemleak.c F: mm/kmemleak-test.c KMOD KERNEL MODULE LOADER - USERMODE HELPER -M: "Luis R. Rodriguez" <mcgrof@kernel.org> +M: Luis Chamberlain <mcgrof@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: kernel/kmod.c @@ -8305,7 +8363,7 @@ F: drivers/net/dsa/lantiq_gswip.c LANTIQ MIPS ARCHITECTURE M: John Crispin <john@phrozen.org> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/lantiq F: drivers/soc/lantiq @@ -8868,7 +8926,7 @@ S: Maintained MARDUK (CREATOR CI40) DEVICE TREE SUPPORT M: Rahul Bedarkar <rahulbedarkar89@gmail.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/boot/dts/img/pistachio_marduk.dts @@ -9827,7 +9885,7 @@ F: drivers/dma/at_xdmac.c MICROSEMI MIPS SOCS M: Alexandre Belloni <alexandre.belloni@bootlin.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/generic/board-ocelot.c F: arch/mips/configs/generic/board-ocelot.config @@ -9867,7 +9925,7 @@ MIPS M: Ralf Baechle <ralf@linux-mips.org> M: Paul Burton <paul.burton@mips.com> M: James Hogan <jhogan@kernel.org> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org W: http://www.linux-mips.org/ T: git git://git.linux-mips.org/pub/scm/ralf/linux.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux.git @@ -9880,7 +9938,7 @@ F: drivers/platform/mips/ MIPS BOSTON DEVELOPMENT BOARD M: Paul Burton <paul.burton@mips.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/clock/img,boston-clock.txt F: arch/mips/boot/dts/img/boston.dts @@ -9890,7 +9948,7 @@ F: include/dt-bindings/clock/boston-clock.h MIPS GENERIC PLATFORM M: Paul Burton <paul.burton@mips.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Supported F: Documentation/devicetree/bindings/power/mti,mips-cpc.txt F: arch/mips/generic/ @@ -9898,7 +9956,7 @@ F: arch/mips/tools/generic-board-config.sh MIPS/LOONGSON1 ARCHITECTURE M: Keguang Zhang <keguang.zhang@gmail.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/loongson32/ F: arch/mips/include/asm/mach-loongson32/ @@ -9907,7 +9965,7 @@ F: drivers/*/*/*loongson1* MIPS/LOONGSON2 ARCHITECTURE M: Jiaxun Yang <jiaxun.yang@flygoat.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/loongson64/fuloong-2e/ F: arch/mips/loongson64/lemote-2f/ @@ -9917,7 +9975,7 @@ F: drivers/*/*/*loongson2* MIPS/LOONGSON3 ARCHITECTURE M: Huacai Chen <chenhc@lemote.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/loongson64/ F: arch/mips/include/asm/mach-loongson64/ @@ -9927,7 +9985,7 @@ F: drivers/*/*/*loongson3* MIPS RINT INSTRUCTION EMULATION M: Aleksandar Markovic <aleksandar.markovic@mips.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Supported F: arch/mips/math-emu/sp_rint.c F: arch/mips/math-emu/dp_rint.c @@ -10912,7 +10970,7 @@ F: include/linux/platform_data/i2c-omap.h ONION OMEGA2+ BOARD M: Harvey Hunt <harveyhuntnexus@gmail.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/boot/dts/ralink/omega2p.dts @@ -11821,7 +11879,7 @@ F: drivers/pinctrl/spear/ PISTACHIO SOC SUPPORT M: James Hartley <james.hartley@sondrel.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Odd Fixes F: arch/mips/pistachio/ F: arch/mips/include/asm/mach-pistachio/ @@ -12001,7 +12059,7 @@ F: kernel/printk/ F: include/linux/printk.h PRISM54 WIRELESS DRIVER -M: "Luis R. Rodriguez" <mcgrof@gmail.com> +M: Luis Chamberlain <mcgrof@kernel.org> L: linux-wireless@vger.kernel.org W: http://wireless.kernel.org/en/users/Drivers/p54 S: Obsolete @@ -12015,9 +12073,10 @@ S: Maintained F: fs/proc/ F: include/linux/proc_fs.h F: tools/testing/selftests/proc/ +F: Documentation/filesystems/proc.txt PROC SYSCTL -M: "Luis R. Rodriguez" <mcgrof@kernel.org> +M: Luis Chamberlain <mcgrof@kernel.org> M: Kees Cook <keescook@chromium.org> L: linux-kernel@vger.kernel.org L: linux-fsdevel@vger.kernel.org @@ -12480,7 +12539,7 @@ F: drivers/media/usb/rainshadow-cec/* RALINK MIPS ARCHITECTURE M: John Crispin <john@phrozen.org> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/ralink @@ -12500,7 +12559,7 @@ F: drivers/block/brd.c RANCHU VIRTUAL BOARD FOR MIPS M: Miodrag Dinic <miodrag.dinic@mips.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Supported F: arch/mips/generic/board-ranchu.c F: arch/mips/configs/generic/board-ranchu.config @@ -13950,6 +14009,7 @@ S: Supported F: Documentation/devicetree/bindings/sound/ F: Documentation/sound/soc/ F: sound/soc/ +F: include/dt-bindings/sound/ F: include/sound/soc* SOUNDWIRE SUBSYSTEM @@ -15235,7 +15295,7 @@ F: arch/um/os-Linux/drivers/ TURBOCHANNEL SUBSYSTEM M: "Maciej W. Rozycki" <macro@linux-mips.org> M: Ralf Baechle <ralf@linux-mips.org> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org Q: http://patchwork.linux-mips.org/project/linux-mips/list/ S: Maintained F: drivers/tc/ @@ -16056,7 +16116,7 @@ F: drivers/net/vmxnet3/ VOCORE VOCORE2 BOARD M: Harvey Hunt <harveyhuntnexus@gmail.com> -L: linux-mips@linux-mips.org +L: linux-mips@vger.kernel.org S: Maintained F: arch/mips/boot/dts/ralink/vocore2.dts @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 20 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Shy Crocodile # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/am3517-evm.dts b/arch/arm/boot/dts/am3517-evm.dts index d4d33cd7adad..1e2bb68231ad 100644 --- a/arch/arm/boot/dts/am3517-evm.dts +++ b/arch/arm/boot/dts/am3517-evm.dts @@ -228,7 +228,7 @@ vmmc-supply = <&vmmc_fixed>; bus-width = <4>; wp-gpios = <&gpio4 30 GPIO_ACTIVE_HIGH>; /* gpio_126 */ - cd-gpios = <&gpio4 31 GPIO_ACTIVE_HIGH>; /* gpio_127 */ + cd-gpios = <&gpio4 31 GPIO_ACTIVE_LOW>; /* gpio_127 */ }; &mmc3 { diff --git a/arch/arm/boot/dts/am3517-som.dtsi b/arch/arm/boot/dts/am3517-som.dtsi index dae6e458e59f..b1c988eed87c 100644 --- a/arch/arm/boot/dts/am3517-som.dtsi +++ b/arch/arm/boot/dts/am3517-som.dtsi @@ -163,7 +163,7 @@ compatible = "ti,wl1271"; reg = <2>; interrupt-parent = <&gpio6>; - interrupts = <10 IRQ_TYPE_LEVEL_HIGH>; /* gpio_170 */ + interrupts = <10 IRQ_TYPE_EDGE_RISING>; /* gpio_170 */ ref-clock-frequency = <26000000>; tcxo-clock-frequency = <26000000>; }; diff --git a/arch/arm/boot/dts/imx51-zii-rdu1.dts b/arch/arm/boot/dts/imx51-zii-rdu1.dts index e45a15ceb94b..69d753cac89a 100644 --- a/arch/arm/boot/dts/imx51-zii-rdu1.dts +++ b/arch/arm/boot/dts/imx51-zii-rdu1.dts @@ -492,12 +492,6 @@ pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; - eeprom@50 { - compatible = "atmel,24c04"; - pagesize = <16>; - reg = <0x50>; - }; - hpa1: amp@60 { compatible = "ti,tpa6130a2"; reg = <0x60>; diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi index ac343330d0c8..98b682a8080c 100644 --- a/arch/arm/boot/dts/logicpd-som-lv.dtsi +++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi @@ -129,7 +129,7 @@ }; &mmc3 { - interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>; + interrupts-extended = <&intc 94 &omap3_pmx_core 0x136>; pinctrl-0 = <&mmc3_pins &wl127x_gpio>; pinctrl-names = "default"; vmmc-supply = <&wl12xx_vmmc>; diff --git a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts index 9d5d53fbe9c0..c39cf2ca54da 100644 --- a/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts +++ b/arch/arm/boot/dts/logicpd-torpedo-37xx-devkit.dts @@ -35,7 +35,7 @@ * jumpering combinations for the long run. */ &mmc3 { - interrupts-extended = <&intc 94 &omap3_pmx_core2 0x46>; + interrupts-extended = <&intc 94 &omap3_pmx_core 0x136>; pinctrl-0 = <&mmc3_pins &mmc3_core2_pins>; pinctrl-names = "default"; vmmc-supply = <&wl12xx_vmmc>; diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi index 2075120cfc4d..d8bf939a3aff 100644 --- a/arch/arm/boot/dts/rk3288-veyron.dtsi +++ b/arch/arm/boot/dts/rk3288-veyron.dtsi @@ -10,7 +10,11 @@ #include "rk3288.dtsi" / { - memory@0 { + /* + * The default coreboot on veyron devices ignores memory@0 nodes + * and would instead create another memory node. + */ + memory { device_type = "memory"; reg = <0x0 0x0 0x0 0x80000000>; }; diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index 843052f14f1c..dd0dda6ed44b 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -314,7 +314,7 @@ 0x1 0x0 0x60000000 0x10000000 0x2 0x0 0x70000000 0x10000000 0x3 0x0 0x80000000 0x10000000>; - clocks = <&mck>; + clocks = <&h32ck>; status = "disabled"; nand_controller: nand-controller { diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c index 0142fcfcc3d3..bda949fd84e8 100644 --- a/arch/arm/kernel/ftrace.c +++ b/arch/arm/kernel/ftrace.c @@ -183,9 +183,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long frame_pointer) { unsigned long return_hooker = (unsigned long) &return_to_handler; - struct ftrace_graph_ent trace; unsigned long old; - int err; if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; @@ -193,21 +191,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, old = *parent; *parent = return_hooker; - trace.func = self_addr; - trace.depth = current->curr_ret_stack + 1; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { + if (function_graph_enter(old, self_addr, frame_pointer, NULL)) *parent = old; - return; - } - - err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer, NULL); - if (err == -EBUSY) { - *parent = old; - return; - } } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/arm/mach-davinci/da830.c b/arch/arm/mach-davinci/da830.c index 0bc5bd2665df..2cc9fe4c3a91 100644 --- a/arch/arm/mach-davinci/da830.c +++ b/arch/arm/mach-davinci/da830.c @@ -759,7 +759,9 @@ static struct davinci_id da830_ids[] = { }; static struct davinci_gpio_platform_data da830_gpio_platform_data = { - .ngpio = 128, + .no_auto_base = true, + .base = 0, + .ngpio = 128, }; int __init da830_register_gpio(void) diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c index 4528bbf0c861..e7b78df2bfef 100644 --- a/arch/arm/mach-davinci/da850.c +++ b/arch/arm/mach-davinci/da850.c @@ -719,7 +719,9 @@ int __init da850_register_vpif_capture(struct vpif_capture_config } static struct davinci_gpio_platform_data da850_gpio_platform_data = { - .ngpio = 144, + .no_auto_base = true, + .base = 0, + .ngpio = 144, }; int __init da850_register_gpio(void) diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c index 1fd3619f6a09..cf78da5ab054 100644 --- a/arch/arm/mach-davinci/devices-da8xx.c +++ b/arch/arm/mach-davinci/devices-da8xx.c @@ -701,6 +701,46 @@ static struct resource da8xx_gpio_resources[] = { }, { /* interrupt */ .start = IRQ_DA8XX_GPIO0, + .end = IRQ_DA8XX_GPIO0, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO1, + .end = IRQ_DA8XX_GPIO1, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO2, + .end = IRQ_DA8XX_GPIO2, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO3, + .end = IRQ_DA8XX_GPIO3, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO4, + .end = IRQ_DA8XX_GPIO4, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO5, + .end = IRQ_DA8XX_GPIO5, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO6, + .end = IRQ_DA8XX_GPIO6, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO7, + .end = IRQ_DA8XX_GPIO7, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DA8XX_GPIO8, .end = IRQ_DA8XX_GPIO8, .flags = IORESOURCE_IRQ, }, diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c index 9f7d38d12c88..4c6e0bef4509 100644 --- a/arch/arm/mach-davinci/dm355.c +++ b/arch/arm/mach-davinci/dm355.c @@ -548,12 +548,44 @@ static struct resource dm355_gpio_resources[] = { }, { /* interrupt */ .start = IRQ_DM355_GPIOBNK0, + .end = IRQ_DM355_GPIOBNK0, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM355_GPIOBNK1, + .end = IRQ_DM355_GPIOBNK1, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM355_GPIOBNK2, + .end = IRQ_DM355_GPIOBNK2, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM355_GPIOBNK3, + .end = IRQ_DM355_GPIOBNK3, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM355_GPIOBNK4, + .end = IRQ_DM355_GPIOBNK4, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM355_GPIOBNK5, + .end = IRQ_DM355_GPIOBNK5, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM355_GPIOBNK6, .end = IRQ_DM355_GPIOBNK6, .flags = IORESOURCE_IRQ, }, }; static struct davinci_gpio_platform_data dm355_gpio_platform_data = { + .no_auto_base = true, + .base = 0, .ngpio = 104, }; diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c index abcf2a5ed89b..01fb2b0c82de 100644 --- a/arch/arm/mach-davinci/dm365.c +++ b/arch/arm/mach-davinci/dm365.c @@ -267,12 +267,49 @@ static struct resource dm365_gpio_resources[] = { }, { /* interrupt */ .start = IRQ_DM365_GPIO0, + .end = IRQ_DM365_GPIO0, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM365_GPIO1, + .end = IRQ_DM365_GPIO1, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM365_GPIO2, + .end = IRQ_DM365_GPIO2, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM365_GPIO3, + .end = IRQ_DM365_GPIO3, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM365_GPIO4, + .end = IRQ_DM365_GPIO4, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM365_GPIO5, + .end = IRQ_DM365_GPIO5, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM365_GPIO6, + .end = IRQ_DM365_GPIO6, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM365_GPIO7, .end = IRQ_DM365_GPIO7, .flags = IORESOURCE_IRQ, }, }; static struct davinci_gpio_platform_data dm365_gpio_platform_data = { + .no_auto_base = true, + .base = 0, .ngpio = 104, .gpio_unbanked = 8, }; diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c index 0720da7809a6..38f92b7d413e 100644 --- a/arch/arm/mach-davinci/dm644x.c +++ b/arch/arm/mach-davinci/dm644x.c @@ -492,12 +492,34 @@ static struct resource dm644_gpio_resources[] = { }, { /* interrupt */ .start = IRQ_GPIOBNK0, + .end = IRQ_GPIOBNK0, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_GPIOBNK1, + .end = IRQ_GPIOBNK1, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_GPIOBNK2, + .end = IRQ_GPIOBNK2, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_GPIOBNK3, + .end = IRQ_GPIOBNK3, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_GPIOBNK4, .end = IRQ_GPIOBNK4, .flags = IORESOURCE_IRQ, }, }; static struct davinci_gpio_platform_data dm644_gpio_platform_data = { + .no_auto_base = true, + .base = 0, .ngpio = 71, }; diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c index 6bd2ed069d0d..7dc54b2a610f 100644 --- a/arch/arm/mach-davinci/dm646x.c +++ b/arch/arm/mach-davinci/dm646x.c @@ -442,12 +442,24 @@ static struct resource dm646x_gpio_resources[] = { }, { /* interrupt */ .start = IRQ_DM646X_GPIOBNK0, + .end = IRQ_DM646X_GPIOBNK0, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM646X_GPIOBNK1, + .end = IRQ_DM646X_GPIOBNK1, + .flags = IORESOURCE_IRQ, + }, + { + .start = IRQ_DM646X_GPIOBNK2, .end = IRQ_DM646X_GPIOBNK2, .flags = IORESOURCE_IRQ, }, }; static struct davinci_gpio_platform_data dm646x_gpio_platform_data = { + .no_auto_base = true, + .base = 0, .ngpio = 43, }; diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c index 3d191fd52910..17886744dbe6 100644 --- a/arch/arm/mach-omap1/board-ams-delta.c +++ b/arch/arm/mach-omap1/board-ams-delta.c @@ -750,6 +750,9 @@ static void modem_pm(struct uart_port *port, unsigned int state, unsigned old) struct modem_private_data *priv = port->private_data; int ret; + if (!priv) + return; + if (IS_ERR(priv->regulator)) return; diff --git a/arch/arm/mach-omap2/prm44xx.c b/arch/arm/mach-omap2/prm44xx.c index 7b95729e8359..38a1be6c3694 100644 --- a/arch/arm/mach-omap2/prm44xx.c +++ b/arch/arm/mach-omap2/prm44xx.c @@ -351,7 +351,7 @@ static void omap44xx_prm_reconfigure_io_chain(void) * to occur, WAKEUPENABLE bits must be set in the pad mux registers, and * omap44xx_prm_reconfigure_io_chain() must be called. No return value. */ -static void __init omap44xx_prm_enable_io_wakeup(void) +static void omap44xx_prm_enable_io_wakeup(void) { s32 inst = omap4_prmst_get_prm_dev_inst(); diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 787d7850e064..ea2ab0330e3a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -497,6 +497,24 @@ config ARM64_ERRATUM_1188873 If unsure, say Y. +config ARM64_ERRATUM_1286807 + bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation" + default y + select ARM64_WORKAROUND_REPEAT_TLBI + help + This option adds workaround for ARM Cortex-A76 erratum 1286807 + + On the affected Cortex-A76 cores (r0p0 to r3p0), if a virtual + address for a cacheable mapping of a location is being + accessed by a core while another core is remapping the virtual + address to a new physical page using the recommended + break-before-make sequence, then under very rare circumstances + TLBI+DSB completes before a read using the translation being + invalidated has been observed by other observers. The + workaround repeats the TLBI+DSB operation. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -566,9 +584,16 @@ config QCOM_FALKOR_ERRATUM_1003 is unchanged. Work around the erratum by invalidating the walk cache entries for the trampoline before entering the kernel proper. +config ARM64_WORKAROUND_REPEAT_TLBI + bool + help + Enable the repeat TLBI workaround for Falkor erratum 1009 and + Cortex-A76 erratum 1286807. + config QCOM_FALKOR_ERRATUM_1009 bool "Falkor E1009: Prematurely complete a DSB after a TLBI" default y + select ARM64_WORKAROUND_REPEAT_TLBI help On Falkor v1, the CPU may prematurely complete a DSB following a TLBI xxIS invalidate maintenance operation. Repeat the TLBI operation diff --git a/arch/arm64/boot/dts/qcom/msm8998-mtp.dtsi b/arch/arm64/boot/dts/qcom/msm8998-mtp.dtsi index b4276da1fb0d..11fd1fe8bdb5 100644 --- a/arch/arm64/boot/dts/qcom/msm8998-mtp.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998-mtp.dtsi @@ -241,3 +241,7 @@ }; }; }; + +&tlmm { + gpio-reserved-ranges = <0 4>, <81 4>; +}; diff --git a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts index eedfaf8922e2..d667eee4e6d0 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-mtp.dts @@ -352,6 +352,10 @@ status = "okay"; }; +&tlmm { + gpio-reserved-ranges = <0 4>, <81 4>; +}; + &uart9 { status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts index 2dceeea29b83..1e6a71066c16 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts @@ -153,7 +153,7 @@ }; &pcie0 { - ep-gpios = <&gpio4 RK_PC6 GPIO_ACTIVE_LOW>; + ep-gpios = <&gpio4 RK_PC6 GPIO_ACTIVE_HIGH>; num-lanes = <4>; pinctrl-names = "default"; pinctrl-0 = <&pcie_clkreqn_cpm>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi index 6c8c4ab044aa..56abbb08c133 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-rock960.dtsi @@ -57,18 +57,6 @@ regulator-always-on; vin-supply = <&vcc_sys>; }; - - vdd_log: vdd-log { - compatible = "pwm-regulator"; - pwms = <&pwm2 0 25000 0>; - regulator-name = "vdd_log"; - regulator-min-microvolt = <800000>; - regulator-max-microvolt = <1400000>; - regulator-always-on; - regulator-boot-on; - vin-supply = <&vcc_sys>; - }; - }; &cpu_l0 { diff --git a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi index affc3c309353..8d7b47f9dfbf 100644 --- a/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi +++ b/arch/arm64/boot/dts/ti/k3-am65-wakeup.dtsi @@ -36,7 +36,7 @@ wkup_uart0: serial@42300000 { compatible = "ti,am654-uart"; - reg = <0x00 0x42300000 0x00 0x100>; + reg = <0x42300000 0x100>; reg-shift = <2>; reg-io-width = <4>; interrupts = <GIC_SPI 697 IRQ_TYPE_LEVEL_HIGH>; diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index caa955f10e19..fac54fb050d0 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -56,6 +56,19 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) { return is_compat_task(); } + +#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME + +static inline bool arch_syscall_match_sym_name(const char *sym, + const char *name) +{ + /* + * Since all syscall functions have __arm64_ prefix, we must skip it. + * However, as we described above, we decided to ignore compat + * syscalls, so we don't care about __arm64_compat_ prefix here. + */ + return !strcmp(sym + 8, name); +} #endif /* ifndef __ASSEMBLY__ */ #endif /* __ASM_FTRACE_H */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index c3c0387aee18..5dfd23897dea 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -41,14 +41,14 @@ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op, \ ARM64_WORKAROUND_REPEAT_TLBI, \ - CONFIG_QCOM_FALKOR_ERRATUM_1009) \ + CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : ) #define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n" \ ALTERNATIVE("nop\n nop", \ "dsb ish\n tlbi " #op ", %0", \ ARM64_WORKAROUND_REPEAT_TLBI, \ - CONFIG_QCOM_FALKOR_ERRATUM_1009) \ + CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : "r" (arg)) #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index a509e35132d2..6ad715d67df8 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -570,6 +570,20 @@ static const struct midr_range arm64_harden_el2_vectors[] = { #endif +#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI + +static const struct midr_range arm64_repeat_tlbi_cpus[] = { +#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009 + MIDR_RANGE(MIDR_QCOM_FALKOR_V1, 0, 0, 0, 0), +#endif +#ifdef CONFIG_ARM64_ERRATUM_1286807 + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0), +#endif + {}, +}; + +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #if defined(CONFIG_ARM64_ERRATUM_826319) || \ defined(CONFIG_ARM64_ERRATUM_827319) || \ @@ -695,11 +709,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = is_kryo_midr, }, #endif -#ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009 +#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI { - .desc = "Qualcomm Technologies Falkor erratum 1009", + .desc = "Qualcomm erratum 1009, ARM erratum 1286807", .capability = ARM64_WORKAROUND_REPEAT_TLBI, - ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0), + ERRATA_MIDR_RANGE_LIST(arm64_repeat_tlbi_cpus), }, #endif #ifdef CONFIG_ARM64_ERRATUM_858921 diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 50986e388d2b..57e962290df3 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -216,8 +216,6 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, { unsigned long return_hooker = (unsigned long)&return_to_handler; unsigned long old; - struct ftrace_graph_ent trace; - int err; if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; @@ -229,18 +227,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, */ old = *parent; - trace.func = self_addr; - trace.depth = current->curr_ret_stack + 1; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) - return; - - err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer, NULL); - if (err == -EBUSY) - return; - else + if (!function_graph_enter(old, self_addr, frame_pointer, NULL)) *parent = return_hooker; } diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index a6fdaea07c63..89198017e8e6 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -351,7 +351,8 @@ static void build_epilogue(struct jit_ctx *ctx) * >0 - successfully JITed a 16-byte eBPF instruction. * <0 - failed to JIT. */ -static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) +static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, + bool extra_pass) { const u8 code = insn->code; const u8 dst = bpf2a64[insn->dst_reg]; @@ -625,12 +626,19 @@ emit_cond_jmp: case BPF_JMP | BPF_CALL: { const u8 r0 = bpf2a64[BPF_REG_0]; - const u64 func = (u64)__bpf_call_base + imm; + bool func_addr_fixed; + u64 func_addr; + int ret; - if (ctx->prog->is_func) - emit_addr_mov_i64(tmp, func, ctx); + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, + &func_addr, &func_addr_fixed); + if (ret < 0) + return ret; + if (func_addr_fixed) + /* We can use optimized emission here. */ + emit_a64_mov_i64(tmp, func_addr, ctx); else - emit_a64_mov_i64(tmp, func, ctx); + emit_addr_mov_i64(tmp, func_addr, ctx); emit(A64_BLR(tmp), ctx); emit(A64_MOV(1, r0, A64_R(0)), ctx); break; @@ -753,7 +761,7 @@ emit_cond_jmp: return 0; } -static int build_body(struct jit_ctx *ctx) +static int build_body(struct jit_ctx *ctx, bool extra_pass) { const struct bpf_prog *prog = ctx->prog; int i; @@ -762,7 +770,7 @@ static int build_body(struct jit_ctx *ctx) const struct bpf_insn *insn = &prog->insnsi[i]; int ret; - ret = build_insn(insn, ctx); + ret = build_insn(insn, ctx, extra_pass); if (ret > 0) { i++; if (ctx->image == NULL) @@ -858,7 +866,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* 1. Initial fake pass to compute ctx->idx. */ /* Fake pass to fill in ctx->offset. */ - if (build_body(&ctx)) { + if (build_body(&ctx, extra_pass)) { prog = orig_prog; goto out_off; } @@ -888,7 +896,7 @@ skip_init_ctx: build_prologue(&ctx, was_classic); - if (build_body(&ctx)) { + if (build_body(&ctx, extra_pass)) { bpf_jit_binary_free(header); prog = orig_prog; goto out_off; diff --git a/arch/ia64/include/asm/numa.h b/arch/ia64/include/asm/numa.h index ebef7f40aabb..c5c253cb9bd6 100644 --- a/arch/ia64/include/asm/numa.h +++ b/arch/ia64/include/asm/numa.h @@ -59,7 +59,9 @@ extern struct node_cpuid_s node_cpuid[NR_CPUS]; */ extern u8 numa_slit[MAX_NUMNODES * MAX_NUMNODES]; -#define node_distance(from,to) (numa_slit[(from) * MAX_NUMNODES + (to)]) +#define slit_distance(from,to) (numa_slit[(from) * MAX_NUMNODES + (to)]) +extern int __node_distance(int from, int to); +#define node_distance(from,to) __node_distance(from, to) extern int paddr_to_nid(unsigned long paddr); diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index 1dacbf5e9e09..41eb281709da 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -578,8 +578,8 @@ void __init acpi_numa_fixup(void) if (!slit_table) { for (i = 0; i < MAX_NUMNODES; i++) for (j = 0; j < MAX_NUMNODES; j++) - node_distance(i, j) = i == j ? LOCAL_DISTANCE : - REMOTE_DISTANCE; + slit_distance(i, j) = i == j ? + LOCAL_DISTANCE : REMOTE_DISTANCE; return; } @@ -592,7 +592,7 @@ void __init acpi_numa_fixup(void) if (!pxm_bit_test(j)) continue; node_to = pxm_to_node(j); - node_distance(node_from, node_to) = + slit_distance(node_from, node_to) = slit_table->entry[i * slit_table->locality_count + j]; } } diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index 3861d6e32d5f..a03803506b0c 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -36,6 +36,12 @@ struct node_cpuid_s node_cpuid[NR_CPUS] = */ u8 numa_slit[MAX_NUMNODES * MAX_NUMNODES]; +int __node_distance(int from, int to) +{ + return slit_distance(from, to); +} +EXPORT_SYMBOL(__node_distance); + /* Identify which cnode a physical address resides on */ int paddr_to_nid(unsigned long paddr) diff --git a/arch/microblaze/kernel/ftrace.c b/arch/microblaze/kernel/ftrace.c index d57563c58a26..224eea40e1ee 100644 --- a/arch/microblaze/kernel/ftrace.c +++ b/arch/microblaze/kernel/ftrace.c @@ -22,8 +22,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - int faulted, err; - struct ftrace_graph_ent trace; + int faulted; unsigned long return_hooker = (unsigned long) &return_to_handler; @@ -63,18 +62,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL); - if (err == -EBUSY) { + if (function_graph_enter(old, self_addr, 0, NULL)) *parent = old; - return; - } - - trace.func = self_addr; - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; - *parent = old; - } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h index 0170602a1e4e..6cf8ffb5367e 100644 --- a/arch/mips/include/asm/syscall.h +++ b/arch/mips/include/asm/syscall.h @@ -73,7 +73,7 @@ static inline unsigned long mips_get_syscall_arg(unsigned long *arg, #ifdef CONFIG_64BIT case 4: case 5: case 6: case 7: #ifdef CONFIG_MIPS32_O32 - if (test_thread_flag(TIF_32BIT_REGS)) + if (test_tsk_thread_flag(task, TIF_32BIT_REGS)) return get_user(*arg, (int *)usp + n); else #endif diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c index 7f3dfdbc3657..b122cbb4aad1 100644 --- a/arch/mips/kernel/ftrace.c +++ b/arch/mips/kernel/ftrace.c @@ -322,7 +322,6 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, unsigned long fp) { unsigned long old_parent_ra; - struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) &return_to_handler; int faulted, insns; @@ -369,12 +368,6 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, if (unlikely(faulted)) goto out; - if (ftrace_push_return_trace(old_parent_ra, self_ra, &trace.depth, fp, - NULL) == -EBUSY) { - *parent_ra_addr = old_parent_ra; - return; - } - /* * Get the recorded ip of the current mcount calling site in the * __mcount_loc section, which will be used to filter the function @@ -382,13 +375,10 @@ void prepare_ftrace_return(unsigned long *parent_ra_addr, unsigned long self_ra, */ insns = core_kernel_text(self_ra) ? 2 : MCOUNT_OFFSET_INSNS + 1; - trace.func = self_ra - (MCOUNT_INSN_SIZE * insns); + self_ra -= (MCOUNT_INSN_SIZE * insns); - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; + if (function_graph_enter(old_parent_ra, self_ra, fp, NULL)) *parent_ra_addr = old_parent_ra; - } return; out: ftrace_graph_stop(); diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c index 41b71c4352c2..c1ce6f43642b 100644 --- a/arch/mips/ralink/mt7620.c +++ b/arch/mips/ralink/mt7620.c @@ -84,7 +84,7 @@ static struct rt2880_pmx_func pcie_rst_grp[] = { }; static struct rt2880_pmx_func nd_sd_grp[] = { FUNC("nand", MT7620_GPIO_MODE_NAND, 45, 15), - FUNC("sd", MT7620_GPIO_MODE_SD, 45, 15) + FUNC("sd", MT7620_GPIO_MODE_SD, 47, 13) }; static struct rt2880_pmx_group mt7620a_pinmux_data[] = { diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c index a0a9679ad5de..8a41372551ff 100644 --- a/arch/nds32/kernel/ftrace.c +++ b/arch/nds32/kernel/ftrace.c @@ -211,29 +211,15 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, unsigned long frame_pointer) { unsigned long return_hooker = (unsigned long)&return_to_handler; - struct ftrace_graph_ent trace; unsigned long old; - int err; if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; old = *parent; - trace.func = self_addr; - trace.depth = current->curr_ret_stack + 1; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) - return; - - err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer, NULL); - - if (err == -EBUSY) - return; - - *parent = return_hooker; + if (!function_graph_enter(old, self_addr, frame_pointer, NULL)) + *parent = return_hooker; } noinline void ftrace_graph_caller(void) diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 6fa8535d3cce..e46a4157a894 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -30,7 +30,6 @@ static void __hot prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - struct ftrace_graph_ent trace; extern int parisc_return_to_handler; if (unlikely(ftrace_graph_is_dead())) @@ -41,19 +40,9 @@ static void __hot prepare_ftrace_return(unsigned long *parent, old = *parent; - trace.func = self_addr; - trace.depth = current->curr_ret_stack + 1; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) - return; - - if (ftrace_push_return_trace(old, self_addr, &trace.depth, - 0, NULL) == -EBUSY) - return; - - /* activate parisc_return_to_handler() as return point */ - *parent = (unsigned long) &parisc_return_to_handler; + if (!function_graph_enter(old, self_addr, 0, NULL)) + /* activate parisc_return_to_handler() as return point */ + *parent = (unsigned long) &parisc_return_to_handler; } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 4bf051d3e21e..b65c8a34ad6e 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -950,7 +950,6 @@ int ftrace_disable_ftrace_graph_caller(void) */ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) { - struct ftrace_graph_ent trace; unsigned long return_hooker; if (unlikely(ftrace_graph_is_dead())) @@ -961,18 +960,8 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) return_hooker = ppc_function_entry(return_to_handler); - trace.func = ip; - trace.depth = current->curr_ret_stack + 1; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) - goto out; - - if (ftrace_push_return_trace(parent, ip, &trace.depth, 0, - NULL) == -EBUSY) - goto out; - - parent = return_hooker; + if (!function_graph_enter(parent, ip, 0, NULL)) + parent = return_hooker; out: return parent; } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index d65b961661fb..a56f8413758a 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -983,6 +983,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu) ret = kvmhv_enter_nested_guest(vcpu); if (ret == H_INTERRUPT) { kvmppc_set_gpr(vcpu, 3, 0); + vcpu->arch.hcall_needed = 0; return -EINTR; } break; diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 50b129785aee..17482f5de3e2 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -166,7 +166,33 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) PPC_BLR(); } -static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func) +static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, + u64 func) +{ +#ifdef PPC64_ELF_ABI_v1 + /* func points to the function descriptor */ + PPC_LI64(b2p[TMP_REG_2], func); + /* Load actual entry point from function descriptor */ + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0); + /* ... and move it to LR */ + PPC_MTLR(b2p[TMP_REG_1]); + /* + * Load TOC from function descriptor at offset 8. + * We can clobber r2 since we get called through a + * function pointer (so caller will save/restore r2) + * and since we don't use a TOC ourself. + */ + PPC_BPF_LL(2, b2p[TMP_REG_2], 8); +#else + /* We can clobber r12 */ + PPC_FUNC_ADDR(12, func); + PPC_MTLR(12); +#endif + PPC_BLRL(); +} + +static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, + u64 func) { unsigned int i, ctx_idx = ctx->idx; @@ -273,7 +299,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, { const struct bpf_insn *insn = fp->insnsi; int flen = fp->len; - int i; + int i, ret; /* Start of epilogue code - will only be valid 2nd pass onwards */ u32 exit_addr = addrs[flen]; @@ -284,8 +310,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 src_reg = b2p[insn[i].src_reg]; s16 off = insn[i].off; s32 imm = insn[i].imm; + bool func_addr_fixed; + u64 func_addr; u64 imm64; - u8 *func; u32 true_cond; u32 tmp_idx; @@ -711,23 +738,15 @@ emit_clear: case BPF_JMP | BPF_CALL: ctx->seen |= SEEN_FUNC; - /* bpf function call */ - if (insn[i].src_reg == BPF_PSEUDO_CALL) - if (!extra_pass) - func = NULL; - else if (fp->aux->func && off < fp->aux->func_cnt) - /* use the subprog id from the off - * field to lookup the callee address - */ - func = (u8 *) fp->aux->func[off]->bpf_func; - else - return -EINVAL; - /* kernel helper call */ - else - func = (u8 *) __bpf_call_base + imm; - - bpf_jit_emit_func_call(image, ctx, (u64)func); + ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass, + &func_addr, &func_addr_fixed); + if (ret < 0) + return ret; + if (func_addr_fixed) + bpf_jit_emit_func_call_hlp(image, ctx, func_addr); + else + bpf_jit_emit_func_call_rel(image, ctx, func_addr); /* move return value from r3 to BPF_REG_0 */ PPC_MR(b2p[BPF_REG_0], 3); break; diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 1157b6b52d25..c433f6d3dd64 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -132,7 +132,6 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, { unsigned long return_hooker = (unsigned long)&return_to_handler; unsigned long old; - struct ftrace_graph_ent trace; int err; if (unlikely(atomic_read(¤t->tracing_graph_pause))) @@ -144,17 +143,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, */ old = *parent; - trace.func = self_addr; - trace.depth = current->curr_ret_stack + 1; - - if (!ftrace_graph_entry(&trace)) - return; - - err = ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer, parent); - if (err == -EBUSY) - return; - *parent = return_hooker; + if (function_graph_enter(old, self_addr, frame_pointer, parent)) + *parent = return_hooker; } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 84be7f02d0c2..39b13d71a8fe 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -203,22 +203,13 @@ device_initcall(ftrace_plt_init); */ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip) { - struct ftrace_graph_ent trace; - if (unlikely(ftrace_graph_is_dead())) goto out; if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; ip -= MCOUNT_INSN_SIZE; - trace.func = ip; - trace.depth = current->curr_ret_stack + 1; - /* Only trace if the calling function expects to. */ - if (!ftrace_graph_entry(&trace)) - goto out; - if (ftrace_push_return_trace(parent, ip, &trace.depth, 0, - NULL) == -EBUSY) - goto out; - parent = (unsigned long) return_to_handler; + if (!function_graph_enter(parent, ip, 0, NULL)) + parent = (unsigned long) return_to_handler; out: return parent; } diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 74091fd3101e..d5523adeddbf 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -346,6 +346,8 @@ static int __hw_perf_event_init(struct perf_event *event) break; case PERF_TYPE_HARDWARE: + if (is_sampling_event(event)) /* No sampling support */ + return -ENOENT; ev = attr->config; /* Count user space (problem-state) only */ if (!attr->exclude_user && attr->exclude_kernel) { diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 814f26520aa2..6791562779ee 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -131,6 +131,7 @@ void crst_table_downgrade(struct mm_struct *mm) } pgd = mm->pgd; + mm_dec_nr_pmds(mm); mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN); mm->context.asce_limit = _REGION3_SIZE; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 96dd9f7da250..1b04270e5460 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -321,8 +321,7 @@ int ftrace_disable_ftrace_graph_caller(void) void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) { unsigned long old; - int faulted, err; - struct ftrace_graph_ent trace; + int faulted; unsigned long return_hooker = (unsigned long)&return_to_handler; if (unlikely(ftrace_graph_is_dead())) @@ -365,18 +364,7 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr) return; } - err = ftrace_push_return_trace(old, self_addr, &trace.depth, 0, NULL); - if (err == -EBUSY) { + if (function_graph_enter(old, self_addr, 0, NULL)) __raw_writel(old, parent); - return; - } - - trace.func = self_addr; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - current->curr_ret_stack--; - __raw_writel(old, parent); - } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/sparc/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c index 915dda4ae412..684b84ce397f 100644 --- a/arch/sparc/kernel/ftrace.c +++ b/arch/sparc/kernel/ftrace.c @@ -126,20 +126,11 @@ unsigned long prepare_ftrace_return(unsigned long parent, unsigned long frame_pointer) { unsigned long return_hooker = (unsigned long) &return_to_handler; - struct ftrace_graph_ent trace; if (unlikely(atomic_read(¤t->tracing_graph_pause))) return parent + 8UL; - trace.func = self_addr; - trace.depth = current->curr_ret_stack + 1; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) - return parent + 8UL; - - if (ftrace_push_return_trace(parent, self_addr, &trace.depth, - frame_pointer, NULL) == -EBUSY) + if (function_graph_enter(parent, self_addr, frame_pointer, NULL)) return parent + 8UL; return return_hooker; diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 222785af550b..5fda4f7bf15d 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -791,7 +791,7 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src, } /* Just skip the save instruction and the ctx register move. */ -#define BPF_TAILCALL_PROLOGUE_SKIP 16 +#define BPF_TAILCALL_PROLOGUE_SKIP 32 #define BPF_TAILCALL_CNT_SP_OFF (STACK_BIAS + 128) static void build_prologue(struct jit_ctx *ctx) @@ -824,9 +824,15 @@ static void build_prologue(struct jit_ctx *ctx) const u8 vfp = bpf2sparc[BPF_REG_FP]; emit(ADD | IMMED | RS1(FP) | S13(STACK_BIAS) | RD(vfp), ctx); + } else { + emit_nop(ctx); } emit_reg_move(I0, O0, ctx); + emit_reg_move(I1, O1, ctx); + emit_reg_move(I2, O2, ctx); + emit_reg_move(I3, O3, ctx); + emit_reg_move(I4, O4, ctx); /* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */ } @@ -1270,6 +1276,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp2 = bpf2sparc[TMP_REG_2]; u32 opcode = 0, rs2; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + ctx->tmp_2_used = true; emit_loadimm(imm, tmp2, ctx); @@ -1308,6 +1317,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp = bpf2sparc[TMP_REG_1]; u32 opcode = 0, rs2; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + switch (BPF_SIZE(code)) { case BPF_W: opcode = ST32; @@ -1340,6 +1352,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp2 = bpf2sparc[TMP_REG_2]; const u8 tmp3 = bpf2sparc[TMP_REG_3]; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + ctx->tmp_1_used = true; ctx->tmp_2_used = true; ctx->tmp_3_used = true; @@ -1360,6 +1375,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) const u8 tmp2 = bpf2sparc[TMP_REG_2]; const u8 tmp3 = bpf2sparc[TMP_REG_3]; + if (insn->dst_reg == BPF_REG_FP) + ctx->saw_frame_pointer = true; + ctx->tmp_1_used = true; ctx->tmp_2_used = true; ctx->tmp_3_used = true; @@ -1425,12 +1443,12 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) struct bpf_prog *tmp, *orig_prog = prog; struct sparc64_jit_data *jit_data; struct bpf_binary_header *header; + u32 prev_image_size, image_size; bool tmp_blinded = false; bool extra_pass = false; struct jit_ctx ctx; - u32 image_size; u8 *image_ptr; - int pass; + int pass, i; if (!prog->jit_requested) return orig_prog; @@ -1461,61 +1479,82 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) header = jit_data->header; extra_pass = true; image_size = sizeof(u32) * ctx.idx; + prev_image_size = image_size; + pass = 1; goto skip_init_ctx; } memset(&ctx, 0, sizeof(ctx)); ctx.prog = prog; - ctx.offset = kcalloc(prog->len, sizeof(unsigned int), GFP_KERNEL); + ctx.offset = kmalloc_array(prog->len, sizeof(unsigned int), GFP_KERNEL); if (ctx.offset == NULL) { prog = orig_prog; goto out_off; } - /* Fake pass to detect features used, and get an accurate assessment - * of what the final image size will be. + /* Longest sequence emitted is for bswap32, 12 instructions. Pre-cook + * the offset array so that we converge faster. */ - if (build_body(&ctx)) { - prog = orig_prog; - goto out_off; - } - build_prologue(&ctx); - build_epilogue(&ctx); - - /* Now we know the actual image size. */ - image_size = sizeof(u32) * ctx.idx; - header = bpf_jit_binary_alloc(image_size, &image_ptr, - sizeof(u32), jit_fill_hole); - if (header == NULL) { - prog = orig_prog; - goto out_off; - } + for (i = 0; i < prog->len; i++) + ctx.offset[i] = i * (12 * 4); - ctx.image = (u32 *)image_ptr; -skip_init_ctx: - for (pass = 1; pass < 3; pass++) { + prev_image_size = ~0U; + for (pass = 1; pass < 40; pass++) { ctx.idx = 0; build_prologue(&ctx); - if (build_body(&ctx)) { - bpf_jit_binary_free(header); prog = orig_prog; goto out_off; } - build_epilogue(&ctx); if (bpf_jit_enable > 1) - pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass, - image_size - (ctx.idx * 4), + pr_info("Pass %d: size = %u, seen = [%c%c%c%c%c%c]\n", pass, + ctx.idx * 4, ctx.tmp_1_used ? '1' : ' ', ctx.tmp_2_used ? '2' : ' ', ctx.tmp_3_used ? '3' : ' ', ctx.saw_frame_pointer ? 'F' : ' ', ctx.saw_call ? 'C' : ' ', ctx.saw_tail_call ? 'T' : ' '); + + if (ctx.idx * 4 == prev_image_size) + break; + prev_image_size = ctx.idx * 4; + cond_resched(); + } + + /* Now we know the actual image size. */ + image_size = sizeof(u32) * ctx.idx; + header = bpf_jit_binary_alloc(image_size, &image_ptr, + sizeof(u32), jit_fill_hole); + if (header == NULL) { + prog = orig_prog; + goto out_off; + } + + ctx.image = (u32 *)image_ptr; +skip_init_ctx: + ctx.idx = 0; + + build_prologue(&ctx); + + if (build_body(&ctx)) { + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; + } + + build_epilogue(&ctx); + + if (ctx.idx * 4 != prev_image_size) { + pr_err("bpf_jit: Failed to converge, prev_size=%u size=%d\n", + prev_image_size, ctx.idx * 4); + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_off; } if (bpf_jit_enable > 1) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d734f3c8234..8689e794a43c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -444,10 +444,6 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. - Without compiler support, at least indirect branches in assembler - code are eliminated. Since this includes the syscall entry path, - it is not entirely pointless. - config INTEL_RDT bool "Intel Resource Director Technology support" depends on X86 && CPU_SUP_INTEL @@ -1004,13 +1000,7 @@ config NR_CPUS to the kernel image. config SCHED_SMT - bool "SMT (Hyperthreading) scheduler support" - depends on SMP - ---help--- - SMT scheduler support improves the CPU scheduler's decision making - when dealing with Intel Pentium 4 chips with HyperThreading at a - cost of slightly increased overhead in some places. If unsure say - N here. + def_bool y if SMP config SCHED_MC def_bool y diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 88398fdf8129..f5d7f4134524 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -220,9 +220,10 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre ifdef CONFIG_RETPOLINE -ifneq ($(RETPOLINE_CFLAGS),) - KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE +ifeq ($(RETPOLINE_CFLAGS),) + $(error You are building kernel with non-retpoline compiler, please update your compiler.) endif + KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) endif archscripts: scripts_basic diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 4c881c850125..850b8762e889 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -300,7 +300,7 @@ _start: # Part 2 of the header, from the old setup.S .ascii "HdrS" # header signature - .word 0x020e # header version number (>= 0x0105) + .word 0x020d # header version number (>= 0x0105) # or else old loadlin-1.5 will fail) .globl realmode_swtch realmode_swtch: .word 0, 0 # default_switch, SETUPSEG @@ -558,10 +558,6 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr init_size: .long INIT_SIZE # kernel initialization size handover_offset: .long 0 # Filled in by build.c -acpi_rsdp_addr: .quad 0 # 64-bit physical pointer to the - # ACPI RSDP table, added with - # version 2.14 - # End of setup header ##################################################### .section ".entrytext", "ax" diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 106911b603bd..374a19712e20 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -438,26 +438,6 @@ int x86_setup_perfctr(struct perf_event *event) if (config == -1LL) return -EINVAL; - /* - * Branch tracing: - */ - if (attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS && - !attr->freq && hwc->sample_period == 1) { - /* BTS is not supported by this architecture. */ - if (!x86_pmu.bts_active) - return -EOPNOTSUPP; - - /* BTS is currently only allowed for user-mode. */ - if (!attr->exclude_kernel) - return -EOPNOTSUPP; - - /* disallow bts if conflicting events are present */ - if (x86_add_exclusive(x86_lbr_exclusive_lbr)) - return -EBUSY; - - event->destroy = hw_perf_lbr_event_destroy; - } - hwc->config |= config; return 0; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 273c62e81546..ecc3e34ca955 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2306,14 +2306,18 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) return handled; } -static bool disable_counter_freezing; +static bool disable_counter_freezing = true; static int __init intel_perf_counter_freezing_setup(char *s) { - disable_counter_freezing = true; - pr_info("Intel PMU Counter freezing feature disabled\n"); + bool res; + + if (kstrtobool(s, &res)) + return -EINVAL; + + disable_counter_freezing = !res; return 1; } -__setup("disable_counter_freezing", intel_perf_counter_freezing_setup); +__setup("perf_v4_pmi=", intel_perf_counter_freezing_setup); /* * Simplified handler for Arch Perfmon v4: @@ -2470,16 +2474,7 @@ done: static struct event_constraint * intel_bts_constraints(struct perf_event *event) { - struct hw_perf_event *hwc = &event->hw; - unsigned int hw_event, bts_event; - - if (event->attr.freq) - return NULL; - - hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; - bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); - - if (unlikely(hw_event == bts_event && hwc->sample_period == 1)) + if (unlikely(intel_pmu_has_bts(event))) return &bts_constraint; return NULL; @@ -3098,6 +3093,43 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event) return flags; } +static int intel_pmu_bts_config(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + + if (unlikely(intel_pmu_has_bts(event))) { + /* BTS is not supported by this architecture. */ + if (!x86_pmu.bts_active) + return -EOPNOTSUPP; + + /* BTS is currently only allowed for user-mode. */ + if (!attr->exclude_kernel) + return -EOPNOTSUPP; + + /* BTS is not allowed for precise events. */ + if (attr->precise_ip) + return -EOPNOTSUPP; + + /* disallow bts if conflicting events are present */ + if (x86_add_exclusive(x86_lbr_exclusive_lbr)) + return -EBUSY; + + event->destroy = hw_perf_lbr_event_destroy; + } + + return 0; +} + +static int core_pmu_hw_config(struct perf_event *event) +{ + int ret = x86_pmu_hw_config(event); + + if (ret) + return ret; + + return intel_pmu_bts_config(event); +} + static int intel_pmu_hw_config(struct perf_event *event) { int ret = x86_pmu_hw_config(event); @@ -3105,6 +3137,10 @@ static int intel_pmu_hw_config(struct perf_event *event) if (ret) return ret; + ret = intel_pmu_bts_config(event); + if (ret) + return ret; + if (event->attr.precise_ip) { if (!event->attr.freq) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; @@ -3127,7 +3163,7 @@ static int intel_pmu_hw_config(struct perf_event *event) /* * BTS is set up earlier in this path, so don't account twice */ - if (!intel_pmu_has_bts(event)) { + if (!unlikely(intel_pmu_has_bts(event))) { /* disallow lbr if conflicting events are present */ if (x86_add_exclusive(x86_lbr_exclusive_lbr)) return -EBUSY; @@ -3596,7 +3632,7 @@ static __initconst const struct x86_pmu core_pmu = { .enable_all = core_pmu_enable_all, .enable = core_pmu_enable_event, .disable = x86_pmu_disable_event, - .hw_config = x86_pmu_hw_config, + .hw_config = core_pmu_hw_config, .schedule_events = x86_schedule_events, .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, .perfctr = MSR_ARCH_PERFMON_PERFCTR0, diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index adae087cecdd..78d7b7031bfc 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -859,11 +859,16 @@ static inline int amd_pmu_init(void) static inline bool intel_pmu_has_bts(struct perf_event *event) { - if (event->attr.config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS && - !event->attr.freq && event->hw.sample_period == 1) - return true; + struct hw_perf_event *hwc = &event->hw; + unsigned int hw_event, bts_event; + + if (event->attr.freq) + return false; + + hw_event = hwc->config & INTEL_ARCH_EVENT_MASK; + bts_event = x86_pmu.event_map(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); - return false; + return hw_event == bts_event && hwc->sample_period == 1; } int intel_pmu_save_and_restart(struct perf_event *event); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 5f7290e6e954..69dcdf195b61 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -226,7 +226,7 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) "3: movl $-2,%[err]\n\t" \ "jmp 2b\n\t" \ ".popsection\n\t" \ - _ASM_EXTABLE_UA(1b, 3b) \ + _ASM_EXTABLE(1b, 3b) \ : [err] "=r" (err) \ : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ : "memory") diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 55e51ff7e421..fbda5a917c5b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1094,7 +1094,8 @@ struct kvm_x86_ops { bool (*has_wbinvd_exit)(void); u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu); - void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); + /* Returns actual tsc_offset set in active VMCS */ + u64 (*write_l1_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 80f4a4f38c79..c8f73efb4ece 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -41,9 +41,10 @@ #define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ #define SPEC_CTRL_IBRS (1 << 0) /* Indirect Branch Restricted Speculation */ -#define SPEC_CTRL_STIBP (1 << 1) /* Single Thread Indirect Branch Predictors */ +#define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ +#define SPEC_CTRL_STIBP (1 << SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ #define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ -#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_SSBD (1 << SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB (1 << 0) /* Indirect Branch Prediction Barrier */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 80dc14422495..032b6009baab 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -3,6 +3,8 @@ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ +#include <linux/static_key.h> + #include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> @@ -162,11 +164,12 @@ _ASM_PTR " 999b\n\t" \ ".popsection\n\t" -#if defined(CONFIG_X86_64) && defined(RETPOLINE) +#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_64 /* - * Since the inline asm uses the %V modifier which is only in newer GCC, - * the 64-bit one is dependent on RETPOLINE not CONFIG_RETPOLINE. + * Inline asm uses the %V modifier which is only in newer GCC + * which is ensured when CONFIG_RETPOLINE is defined. */ # define CALL_NOSPEC \ ANNOTATE_NOSPEC_ALTERNATIVE \ @@ -181,7 +184,7 @@ X86_FEATURE_RETPOLINE_AMD) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) -#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE) +#else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET @@ -211,6 +214,7 @@ X86_FEATURE_RETPOLINE_AMD) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) @@ -219,13 +223,19 @@ /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, - SPECTRE_V2_RETPOLINE_MINIMAL, - SPECTRE_V2_RETPOLINE_MINIMAL_AMD, SPECTRE_V2_RETPOLINE_GENERIC, SPECTRE_V2_RETPOLINE_AMD, SPECTRE_V2_IBRS_ENHANCED, }; +/* The indirect branch speculation control variants */ +enum spectre_v2_user_mitigation { + SPECTRE_V2_USER_NONE, + SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_PRCTL, + SPECTRE_V2_USER_SECCOMP, +}; + /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, @@ -303,6 +313,10 @@ do { \ preempt_enable(); \ } while (0) +DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); +DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); +DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); + #endif /* __ASSEMBLY__ */ /* diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index ae7c2c5cd7f0..5393babc0598 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -53,12 +53,24 @@ static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn) return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); } +static inline u64 stibp_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_SPEC_IB < SPEC_CTRL_STIBP_SHIFT); + return (tifn & _TIF_SPEC_IB) >> (TIF_SPEC_IB - SPEC_CTRL_STIBP_SHIFT); +} + static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl) { BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); } +static inline unsigned long stibp_spec_ctrl_to_tif(u64 spec_ctrl) +{ + BUILD_BUG_ON(TIF_SPEC_IB < SPEC_CTRL_STIBP_SHIFT); + return (spec_ctrl & SPEC_CTRL_STIBP) << (TIF_SPEC_IB - SPEC_CTRL_STIBP_SHIFT); +} + static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn) { return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL; @@ -70,11 +82,7 @@ extern void speculative_store_bypass_ht_init(void); static inline void speculative_store_bypass_ht_init(void) { } #endif -extern void speculative_store_bypass_update(unsigned long tif); - -static inline void speculative_store_bypass_update_current(void) -{ - speculative_store_bypass_update(current_thread_info()->flags); -} +extern void speculation_ctrl_update(unsigned long tif); +extern void speculation_ctrl_update_current(void); #endif diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 36bd243843d6..7cf1a270d891 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -11,9 +11,6 @@ struct task_struct *__switch_to_asm(struct task_struct *prev, __visible struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next); -struct tss_struct; -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss); /* This runs runs on the previous thread's stack. */ static inline void prepare_switch_to(struct task_struct *next) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 2ff2a30a264f..82b73b75d67c 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -79,10 +79,12 @@ struct thread_info { #define TIF_SIGPENDING 2 /* signal pending */ #define TIF_NEED_RESCHED 3 /* rescheduling necessary */ #define TIF_SINGLESTEP 4 /* reenable singlestep on user return*/ -#define TIF_SSBD 5 /* Reduced data speculation */ +#define TIF_SSBD 5 /* Speculative store bypass disable */ #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SECCOMP 8 /* secure computing */ +#define TIF_SPEC_IB 9 /* Indirect branch speculation mitigation */ +#define TIF_SPEC_FORCE_UPDATE 10 /* Force speculation MSR update in context switch */ #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ #define TIF_UPROBE 12 /* breakpointed or singlestepping */ #define TIF_PATCH_PENDING 13 /* pending live patching update */ @@ -110,6 +112,8 @@ struct thread_info { #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) #define _TIF_SECCOMP (1 << TIF_SECCOMP) +#define _TIF_SPEC_IB (1 << TIF_SPEC_IB) +#define _TIF_SPEC_FORCE_UPDATE (1 << TIF_SPEC_FORCE_UPDATE) #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) #define _TIF_UPROBE (1 << TIF_UPROBE) #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) @@ -145,8 +149,18 @@ struct thread_info { _TIF_FSCHECK) /* flags to check in __switch_to() */ -#define _TIF_WORK_CTXSW \ - (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP|_TIF_SSBD) +#define _TIF_WORK_CTXSW_BASE \ + (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP| \ + _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) + +/* + * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated. + */ +#ifdef CONFIG_SMP +# define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE | _TIF_SPEC_IB) +#else +# define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE) +#endif #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index d760611cfc35..f4204bf377fc 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -169,10 +169,14 @@ struct tlb_state { #define LOADED_MM_SWITCHING ((struct mm_struct *)1) + /* Last user mm for optimizing IBPB */ + union { + struct mm_struct *last_user_mm; + unsigned long last_user_mm_ibpb; + }; + u16 loaded_mm_asid; u16 next_asid; - /* last user mm's ctx id */ - u64 last_ctx_id; /* * We can be in one of several states: diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 0f842104862c..b85a7c54c6a1 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -303,6 +303,4 @@ extern void x86_init_noop(void); extern void x86_init_uint_noop(unsigned int unused); extern bool x86_pnpbios_disabled(void); -void x86_verify_bootdata_version(void); - #endif diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 22f89d040ddd..60733f137e9a 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -16,9 +16,6 @@ #define RAMDISK_PROMPT_FLAG 0x8000 #define RAMDISK_LOAD_FLAG 0x4000 -/* version flags */ -#define VERSION_WRITTEN 0x8000 - /* loadflags */ #define LOADED_HIGH (1<<0) #define KASLR_FLAG (1<<1) @@ -89,7 +86,6 @@ struct setup_header { __u64 pref_address; __u32 init_size; __u32 handover_offset; - __u64 acpi_rsdp_addr; } __attribute__((packed)); struct sys_desc_table { @@ -159,7 +155,8 @@ struct boot_params { __u8 _pad2[4]; /* 0x054 */ __u64 tboot_addr; /* 0x058 */ struct ist_info ist_info; /* 0x060 */ - __u8 _pad3[16]; /* 0x070 */ + __u64 acpi_rsdp_addr; /* 0x070 */ + __u8 _pad3[8]; /* 0x078 */ __u8 hd0_info[16]; /* obsolete! */ /* 0x080 */ __u8 hd1_info[16]; /* obsolete! */ /* 0x090 */ struct sys_desc_table sys_desc_table; /* obsolete! */ /* 0x0a0 */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 92c76bf97ad8..06635fbca81c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1776,5 +1776,5 @@ void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) u64 x86_default_get_root_pointer(void) { - return boot_params.hdr.acpi_rsdp_addr; + return boot_params.acpi_rsdp_addr; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index c37e66e493bf..500278f5308e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/nospec.h> #include <linux/prctl.h> +#include <linux/sched/smt.h> #include <asm/spec-ctrl.h> #include <asm/cmdline.h> @@ -53,6 +54,13 @@ static u64 __ro_after_init x86_spec_ctrl_mask = SPEC_CTRL_IBRS; u64 __ro_after_init x86_amd_ls_cfg_base; u64 __ro_after_init x86_amd_ls_cfg_ssbd_mask; +/* Control conditional STIPB in switch_to() */ +DEFINE_STATIC_KEY_FALSE(switch_to_cond_stibp); +/* Control conditional IBPB in switch_mm() */ +DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); +/* Control unconditional IBPB in switch_mm() */ +DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb); + void __init check_bugs(void) { identify_boot_cpu(); @@ -123,31 +131,6 @@ void __init check_bugs(void) #endif } -/* The kernel command line selection */ -enum spectre_v2_mitigation_cmd { - SPECTRE_V2_CMD_NONE, - SPECTRE_V2_CMD_AUTO, - SPECTRE_V2_CMD_FORCE, - SPECTRE_V2_CMD_RETPOLINE, - SPECTRE_V2_CMD_RETPOLINE_GENERIC, - SPECTRE_V2_CMD_RETPOLINE_AMD, -}; - -static const char *spectre_v2_strings[] = { - [SPECTRE_V2_NONE] = "Vulnerable", - [SPECTRE_V2_RETPOLINE_MINIMAL] = "Vulnerable: Minimal generic ASM retpoline", - [SPECTRE_V2_RETPOLINE_MINIMAL_AMD] = "Vulnerable: Minimal AMD ASM retpoline", - [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", - [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", - [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", -}; - -#undef pr_fmt -#define pr_fmt(fmt) "Spectre V2 : " fmt - -static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = - SPECTRE_V2_NONE; - void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { @@ -169,6 +152,10 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) static_cpu_has(X86_FEATURE_AMD_SSBD)) hostval |= ssbd_tif_to_spec_ctrl(ti->flags); + /* Conditional STIBP enabled? */ + if (static_branch_unlikely(&switch_to_cond_stibp)) + hostval |= stibp_tif_to_spec_ctrl(ti->flags); + if (hostval != guestval) { msrval = setguest ? guestval : hostval; wrmsrl(MSR_IA32_SPEC_CTRL, msrval); @@ -202,7 +189,7 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) tif = setguest ? ssbd_spec_ctrl_to_tif(guestval) : ssbd_spec_ctrl_to_tif(hostval); - speculative_store_bypass_update(tif); + speculation_ctrl_update(tif); } } EXPORT_SYMBOL_GPL(x86_virt_spec_ctrl); @@ -217,6 +204,15 @@ static void x86_amd_ssb_disable(void) wrmsrl(MSR_AMD64_LS_CFG, msrval); } +#undef pr_fmt +#define pr_fmt(fmt) "Spectre V2 : " fmt + +static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + +static enum spectre_v2_user_mitigation spectre_v2_user __ro_after_init = + SPECTRE_V2_USER_NONE; + #ifdef RETPOLINE static bool spectre_v2_bad_module; @@ -238,67 +234,217 @@ static inline const char *spectre_v2_module_string(void) static inline const char *spectre_v2_module_string(void) { return ""; } #endif -static void __init spec2_print_if_insecure(const char *reason) +static inline bool match_option(const char *arg, int arglen, const char *opt) { - if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s selected on command line.\n", reason); + int len = strlen(opt); + + return len == arglen && !strncmp(arg, opt, len); } -static void __init spec2_print_if_secure(const char *reason) +/* The kernel command line selection for spectre v2 */ +enum spectre_v2_mitigation_cmd { + SPECTRE_V2_CMD_NONE, + SPECTRE_V2_CMD_AUTO, + SPECTRE_V2_CMD_FORCE, + SPECTRE_V2_CMD_RETPOLINE, + SPECTRE_V2_CMD_RETPOLINE_GENERIC, + SPECTRE_V2_CMD_RETPOLINE_AMD, +}; + +enum spectre_v2_user_cmd { + SPECTRE_V2_USER_CMD_NONE, + SPECTRE_V2_USER_CMD_AUTO, + SPECTRE_V2_USER_CMD_FORCE, + SPECTRE_V2_USER_CMD_PRCTL, + SPECTRE_V2_USER_CMD_PRCTL_IBPB, + SPECTRE_V2_USER_CMD_SECCOMP, + SPECTRE_V2_USER_CMD_SECCOMP_IBPB, +}; + +static const char * const spectre_v2_user_strings[] = { + [SPECTRE_V2_USER_NONE] = "User space: Vulnerable", + [SPECTRE_V2_USER_STRICT] = "User space: Mitigation: STIBP protection", + [SPECTRE_V2_USER_PRCTL] = "User space: Mitigation: STIBP via prctl", + [SPECTRE_V2_USER_SECCOMP] = "User space: Mitigation: STIBP via seccomp and prctl", +}; + +static const struct { + const char *option; + enum spectre_v2_user_cmd cmd; + bool secure; +} v2_user_options[] __initdata = { + { "auto", SPECTRE_V2_USER_CMD_AUTO, false }, + { "off", SPECTRE_V2_USER_CMD_NONE, false }, + { "on", SPECTRE_V2_USER_CMD_FORCE, true }, + { "prctl", SPECTRE_V2_USER_CMD_PRCTL, false }, + { "prctl,ibpb", SPECTRE_V2_USER_CMD_PRCTL_IBPB, false }, + { "seccomp", SPECTRE_V2_USER_CMD_SECCOMP, false }, + { "seccomp,ibpb", SPECTRE_V2_USER_CMD_SECCOMP_IBPB, false }, +}; + +static void __init spec_v2_user_print_cond(const char *reason, bool secure) { - if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) - pr_info("%s selected on command line.\n", reason); + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure) + pr_info("spectre_v2_user=%s forced on command line.\n", reason); } -static inline bool retp_compiler(void) +static enum spectre_v2_user_cmd __init +spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) { - return __is_defined(RETPOLINE); + char arg[20]; + int ret, i; + + switch (v2_cmd) { + case SPECTRE_V2_CMD_NONE: + return SPECTRE_V2_USER_CMD_NONE; + case SPECTRE_V2_CMD_FORCE: + return SPECTRE_V2_USER_CMD_FORCE; + default: + break; + } + + ret = cmdline_find_option(boot_command_line, "spectre_v2_user", + arg, sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_USER_CMD_AUTO; + + for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) { + if (match_option(arg, ret, v2_user_options[i].option)) { + spec_v2_user_print_cond(v2_user_options[i].option, + v2_user_options[i].secure); + return v2_user_options[i].cmd; + } + } + + pr_err("Unknown user space protection option (%s). Switching to AUTO select\n", arg); + return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool match_option(const char *arg, int arglen, const char *opt) +static void __init +spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) { - int len = strlen(opt); + enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE; + bool smt_possible = IS_ENABLED(CONFIG_SMP); + enum spectre_v2_user_cmd cmd; - return len == arglen && !strncmp(arg, opt, len); + if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP)) + return; + + if (cpu_smt_control == CPU_SMT_FORCE_DISABLED || + cpu_smt_control == CPU_SMT_NOT_SUPPORTED) + smt_possible = false; + + cmd = spectre_v2_parse_user_cmdline(v2_cmd); + switch (cmd) { + case SPECTRE_V2_USER_CMD_NONE: + goto set_mode; + case SPECTRE_V2_USER_CMD_FORCE: + mode = SPECTRE_V2_USER_STRICT; + break; + case SPECTRE_V2_USER_CMD_PRCTL: + case SPECTRE_V2_USER_CMD_PRCTL_IBPB: + mode = SPECTRE_V2_USER_PRCTL; + break; + case SPECTRE_V2_USER_CMD_AUTO: + case SPECTRE_V2_USER_CMD_SECCOMP: + case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: + if (IS_ENABLED(CONFIG_SECCOMP)) + mode = SPECTRE_V2_USER_SECCOMP; + else + mode = SPECTRE_V2_USER_PRCTL; + break; + } + + /* Initialize Indirect Branch Prediction Barrier */ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + setup_force_cpu_cap(X86_FEATURE_USE_IBPB); + + switch (cmd) { + case SPECTRE_V2_USER_CMD_FORCE: + case SPECTRE_V2_USER_CMD_PRCTL_IBPB: + case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: + static_branch_enable(&switch_mm_always_ibpb); + break; + case SPECTRE_V2_USER_CMD_PRCTL: + case SPECTRE_V2_USER_CMD_AUTO: + case SPECTRE_V2_USER_CMD_SECCOMP: + static_branch_enable(&switch_mm_cond_ibpb); + break; + default: + break; + } + + pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", + static_key_enabled(&switch_mm_always_ibpb) ? + "always-on" : "conditional"); + } + + /* If enhanced IBRS is enabled no STIPB required */ + if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + return; + + /* + * If SMT is not possible or STIBP is not available clear the STIPB + * mode. + */ + if (!smt_possible || !boot_cpu_has(X86_FEATURE_STIBP)) + mode = SPECTRE_V2_USER_NONE; +set_mode: + spectre_v2_user = mode; + /* Only print the STIBP mode when SMT possible */ + if (smt_possible) + pr_info("%s\n", spectre_v2_user_strings[mode]); } +static const char * const spectre_v2_strings[] = { + [SPECTRE_V2_NONE] = "Vulnerable", + [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", + [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", + [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", +}; + static const struct { const char *option; enum spectre_v2_mitigation_cmd cmd; bool secure; -} mitigation_options[] = { - { "off", SPECTRE_V2_CMD_NONE, false }, - { "on", SPECTRE_V2_CMD_FORCE, true }, - { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, - { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, - { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, - { "auto", SPECTRE_V2_CMD_AUTO, false }, +} mitigation_options[] __initdata = { + { "off", SPECTRE_V2_CMD_NONE, false }, + { "on", SPECTRE_V2_CMD_FORCE, true }, + { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "auto", SPECTRE_V2_CMD_AUTO, false }, }; +static void __init spec_v2_print_cond(const char *reason, bool secure) +{ + if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2) != secure) + pr_info("%s selected on command line.\n", reason); +} + static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) { + enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; char arg[20]; int ret, i; - enum spectre_v2_mitigation_cmd cmd = SPECTRE_V2_CMD_AUTO; if (cmdline_find_option_bool(boot_command_line, "nospectre_v2")) return SPECTRE_V2_CMD_NONE; - else { - ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); - if (ret < 0) - return SPECTRE_V2_CMD_AUTO; - for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { - if (!match_option(arg, ret, mitigation_options[i].option)) - continue; - cmd = mitigation_options[i].cmd; - break; - } + ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg)); + if (ret < 0) + return SPECTRE_V2_CMD_AUTO; - if (i >= ARRAY_SIZE(mitigation_options)) { - pr_err("unknown option (%s). Switching to AUTO select\n", arg); - return SPECTRE_V2_CMD_AUTO; - } + for (i = 0; i < ARRAY_SIZE(mitigation_options); i++) { + if (!match_option(arg, ret, mitigation_options[i].option)) + continue; + cmd = mitigation_options[i].cmd; + break; + } + + if (i >= ARRAY_SIZE(mitigation_options)) { + pr_err("unknown option (%s). Switching to AUTO select\n", arg); + return SPECTRE_V2_CMD_AUTO; } if ((cmd == SPECTRE_V2_CMD_RETPOLINE || @@ -316,54 +462,11 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } - if (mitigation_options[i].secure) - spec2_print_if_secure(mitigation_options[i].option); - else - spec2_print_if_insecure(mitigation_options[i].option); - + spec_v2_print_cond(mitigation_options[i].option, + mitigation_options[i].secure); return cmd; } -static bool stibp_needed(void) -{ - if (spectre_v2_enabled == SPECTRE_V2_NONE) - return false; - - if (!boot_cpu_has(X86_FEATURE_STIBP)) - return false; - - return true; -} - -static void update_stibp_msr(void *info) -{ - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); -} - -void arch_smt_update(void) -{ - u64 mask; - - if (!stibp_needed()) - return; - - mutex_lock(&spec_ctrl_mutex); - mask = x86_spec_ctrl_base; - if (cpu_smt_control == CPU_SMT_ENABLED) - mask |= SPEC_CTRL_STIBP; - else - mask &= ~SPEC_CTRL_STIBP; - - if (mask != x86_spec_ctrl_base) { - pr_info("Spectre v2 cross-process SMT mitigation: %s STIBP\n", - cpu_smt_control == CPU_SMT_ENABLED ? - "Enabling" : "Disabling"); - x86_spec_ctrl_base = mask; - on_each_cpu(update_stibp_msr, NULL, 1); - } - mutex_unlock(&spec_ctrl_mutex); -} - static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -417,14 +520,12 @@ retpoline_auto: pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); goto retpoline_generic; } - mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_AMD : - SPECTRE_V2_RETPOLINE_MINIMAL_AMD; + mode = SPECTRE_V2_RETPOLINE_AMD; setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); setup_force_cpu_cap(X86_FEATURE_RETPOLINE); } else { retpoline_generic: - mode = retp_compiler() ? SPECTRE_V2_RETPOLINE_GENERIC : - SPECTRE_V2_RETPOLINE_MINIMAL; + mode = SPECTRE_V2_RETPOLINE_GENERIC; setup_force_cpu_cap(X86_FEATURE_RETPOLINE); } @@ -443,12 +544,6 @@ specv2_set_mode: setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); - /* Initialize Indirect Branch Prediction Barrier if supported */ - if (boot_cpu_has(X86_FEATURE_IBPB)) { - setup_force_cpu_cap(X86_FEATURE_USE_IBPB); - pr_info("Spectre v2 mitigation: Enabling Indirect Branch Prediction Barrier\n"); - } - /* * Retpoline means the kernel is safe because it has no indirect * branches. Enhanced IBRS protects firmware too, so, enable restricted @@ -465,10 +560,67 @@ specv2_set_mode: pr_info("Enabling Restricted Speculation for firmware calls\n"); } + /* Set up IBPB and STIBP depending on the general spectre V2 command */ + spectre_v2_user_select_mitigation(cmd); + /* Enable STIBP if appropriate */ arch_smt_update(); } +static void update_stibp_msr(void * __unused) +{ + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); +} + +/* Update x86_spec_ctrl_base in case SMT state changed. */ +static void update_stibp_strict(void) +{ + u64 mask = x86_spec_ctrl_base & ~SPEC_CTRL_STIBP; + + if (sched_smt_active()) + mask |= SPEC_CTRL_STIBP; + + if (mask == x86_spec_ctrl_base) + return; + + pr_info("Update user space SMT mitigation: STIBP %s\n", + mask & SPEC_CTRL_STIBP ? "always-on" : "off"); + x86_spec_ctrl_base = mask; + on_each_cpu(update_stibp_msr, NULL, 1); +} + +/* Update the static key controlling the evaluation of TIF_SPEC_IB */ +static void update_indir_branch_cond(void) +{ + if (sched_smt_active()) + static_branch_enable(&switch_to_cond_stibp); + else + static_branch_disable(&switch_to_cond_stibp); +} + +void arch_smt_update(void) +{ + /* Enhanced IBRS implies STIBP. No update required. */ + if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + return; + + mutex_lock(&spec_ctrl_mutex); + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + break; + case SPECTRE_V2_USER_STRICT: + update_stibp_strict(); + break; + case SPECTRE_V2_USER_PRCTL: + case SPECTRE_V2_USER_SECCOMP: + update_indir_branch_cond(); + break; + } + + mutex_unlock(&spec_ctrl_mutex); +} + #undef pr_fmt #define pr_fmt(fmt) "Speculative Store Bypass: " fmt @@ -483,7 +635,7 @@ enum ssb_mitigation_cmd { SPEC_STORE_BYPASS_CMD_SECCOMP, }; -static const char *ssb_strings[] = { +static const char * const ssb_strings[] = { [SPEC_STORE_BYPASS_NONE] = "Vulnerable", [SPEC_STORE_BYPASS_DISABLE] = "Mitigation: Speculative Store Bypass disabled", [SPEC_STORE_BYPASS_PRCTL] = "Mitigation: Speculative Store Bypass disabled via prctl", @@ -493,7 +645,7 @@ static const char *ssb_strings[] = { static const struct { const char *option; enum ssb_mitigation_cmd cmd; -} ssb_mitigation_options[] = { +} ssb_mitigation_options[] __initdata = { { "auto", SPEC_STORE_BYPASS_CMD_AUTO }, /* Platform decides */ { "on", SPEC_STORE_BYPASS_CMD_ON }, /* Disable Speculative Store Bypass */ { "off", SPEC_STORE_BYPASS_CMD_NONE }, /* Don't touch Speculative Store Bypass */ @@ -604,10 +756,25 @@ static void ssb_select_mitigation(void) #undef pr_fmt #define pr_fmt(fmt) "Speculation prctl: " fmt -static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +static void task_update_spec_tif(struct task_struct *tsk) { - bool update; + /* Force the update of the real TIF bits */ + set_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE); + /* + * Immediately update the speculation control MSRs for the current + * task, but for a non-current task delay setting the CPU + * mitigation until it is scheduled next. + * + * This can only happen for SECCOMP mitigation. For PRCTL it's + * always the current task. + */ + if (tsk == current) + speculation_ctrl_update_current(); +} + +static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) +{ if (ssb_mode != SPEC_STORE_BYPASS_PRCTL && ssb_mode != SPEC_STORE_BYPASS_SECCOMP) return -ENXIO; @@ -618,28 +785,56 @@ static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl) if (task_spec_ssb_force_disable(task)) return -EPERM; task_clear_spec_ssb_disable(task); - update = test_and_clear_tsk_thread_flag(task, TIF_SSBD); + task_update_spec_tif(task); break; case PR_SPEC_DISABLE: task_set_spec_ssb_disable(task); - update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + task_update_spec_tif(task); break; case PR_SPEC_FORCE_DISABLE: task_set_spec_ssb_disable(task); task_set_spec_ssb_force_disable(task); - update = !test_and_set_tsk_thread_flag(task, TIF_SSBD); + task_update_spec_tif(task); break; default: return -ERANGE; } + return 0; +} - /* - * If being set on non-current task, delay setting the CPU - * mitigation until it is next scheduled. - */ - if (task == current && update) - speculative_store_bypass_update_current(); - +static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) +{ + switch (ctrl) { + case PR_SPEC_ENABLE: + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return 0; + /* + * Indirect branch speculation is always disabled in strict + * mode. + */ + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return -EPERM; + task_clear_spec_ib_disable(task); + task_update_spec_tif(task); + break; + case PR_SPEC_DISABLE: + case PR_SPEC_FORCE_DISABLE: + /* + * Indirect branch speculation is always allowed when + * mitigation is force disabled. + */ + if (spectre_v2_user == SPECTRE_V2_USER_NONE) + return -EPERM; + if (spectre_v2_user == SPECTRE_V2_USER_STRICT) + return 0; + task_set_spec_ib_disable(task); + if (ctrl == PR_SPEC_FORCE_DISABLE) + task_set_spec_ib_force_disable(task); + task_update_spec_tif(task); + break; + default: + return -ERANGE; + } return 0; } @@ -649,6 +844,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which, switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_set(task, ctrl); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_set(task, ctrl); default: return -ENODEV; } @@ -659,6 +856,8 @@ void arch_seccomp_spec_mitigate(struct task_struct *task) { if (ssb_mode == SPEC_STORE_BYPASS_SECCOMP) ssb_prctl_set(task, PR_SPEC_FORCE_DISABLE); + if (spectre_v2_user == SPECTRE_V2_USER_SECCOMP) + ib_prctl_set(task, PR_SPEC_FORCE_DISABLE); } #endif @@ -681,11 +880,35 @@ static int ssb_prctl_get(struct task_struct *task) } } +static int ib_prctl_get(struct task_struct *task) +{ + if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2)) + return PR_SPEC_NOT_AFFECTED; + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + return PR_SPEC_ENABLE; + case SPECTRE_V2_USER_PRCTL: + case SPECTRE_V2_USER_SECCOMP: + if (task_spec_ib_force_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_FORCE_DISABLE; + if (task_spec_ib_disable(task)) + return PR_SPEC_PRCTL | PR_SPEC_DISABLE; + return PR_SPEC_PRCTL | PR_SPEC_ENABLE; + case SPECTRE_V2_USER_STRICT: + return PR_SPEC_DISABLE; + default: + return PR_SPEC_NOT_AFFECTED; + } +} + int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) { switch (which) { case PR_SPEC_STORE_BYPASS: return ssb_prctl_get(task); + case PR_SPEC_INDIRECT_BRANCH: + return ib_prctl_get(task); default: return -ENODEV; } @@ -823,7 +1046,7 @@ early_param("l1tf", l1tf_cmdline); #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" #if IS_ENABLED(CONFIG_KVM_INTEL) -static const char *l1tf_vmx_states[] = { +static const char * const l1tf_vmx_states[] = { [VMENTER_L1D_FLUSH_AUTO] = "auto", [VMENTER_L1D_FLUSH_NEVER] = "vulnerable", [VMENTER_L1D_FLUSH_COND] = "conditional cache flushes", @@ -839,13 +1062,14 @@ static ssize_t l1tf_show_state(char *buf) if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && - cpu_smt_control == CPU_SMT_ENABLED)) + sched_smt_active())) { return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, l1tf_vmx_states[l1tf_vmx_mitigation]); + } return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, l1tf_vmx_states[l1tf_vmx_mitigation], - cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled"); + sched_smt_active() ? "vulnerable" : "disabled"); } #else static ssize_t l1tf_show_state(char *buf) @@ -854,11 +1078,39 @@ static ssize_t l1tf_show_state(char *buf) } #endif +static char *stibp_state(void) +{ + if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + return ""; + + switch (spectre_v2_user) { + case SPECTRE_V2_USER_NONE: + return ", STIBP: disabled"; + case SPECTRE_V2_USER_STRICT: + return ", STIBP: forced"; + case SPECTRE_V2_USER_PRCTL: + case SPECTRE_V2_USER_SECCOMP: + if (static_key_enabled(&switch_to_cond_stibp)) + return ", STIBP: conditional"; + } + return ""; +} + +static char *ibpb_state(void) +{ + if (boot_cpu_has(X86_FEATURE_IBPB)) { + if (static_key_enabled(&switch_mm_always_ibpb)) + return ", IBPB: always-on"; + if (static_key_enabled(&switch_mm_cond_ibpb)) + return ", IBPB: conditional"; + return ", IBPB: disabled"; + } + return ""; +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { - int ret; - if (!boot_cpu_has_bug(bug)) return sprintf(buf, "Not affected\n"); @@ -876,13 +1128,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return sprintf(buf, "Mitigation: __user pointer sanitization\n"); case X86_BUG_SPECTRE_V2: - ret = sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - boot_cpu_has(X86_FEATURE_USE_IBPB) ? ", IBPB" : "", + return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - (x86_spec_ctrl_base & SPEC_CTRL_STIBP) ? ", STIBP" : "", + stibp_state(), boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", spectre_v2_module_string()); - return ret; case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index dd33c357548f..e12454e21b8a 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -56,7 +56,7 @@ /* Threshold LVT offset is at MSR0xC0000410[15:12] */ #define SMCA_THR_LVT_OFF 0xF000 -static bool thresholding_en; +static bool thresholding_irq_en; static const char * const th_names[] = { "load_store", @@ -534,9 +534,8 @@ prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, set_offset: offset = setup_APIC_mce_threshold(offset, new); - - if ((offset == new) && (mce_threshold_vector != amd_threshold_interrupt)) - mce_threshold_vector = amd_threshold_interrupt; + if (offset == new) + thresholding_irq_en = true; done: mce_threshold_block_init(&b, offset); @@ -1357,9 +1356,6 @@ int mce_threshold_remove_device(unsigned int cpu) { unsigned int bank; - if (!thresholding_en) - return 0; - for (bank = 0; bank < mca_cfg.banks; ++bank) { if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; @@ -1377,9 +1373,6 @@ int mce_threshold_create_device(unsigned int cpu) struct threshold_bank **bp; int err = 0; - if (!thresholding_en) - return 0; - bp = per_cpu(threshold_banks, cpu); if (bp) return 0; @@ -1408,9 +1401,6 @@ static __init int threshold_init_device(void) { unsigned lcpu = 0; - if (mce_threshold_vector == amd_threshold_interrupt) - thresholding_en = true; - /* to hit CPUs online before the notifier is up */ for_each_online_cpu(lcpu) { int err = mce_threshold_create_device(lcpu); @@ -1419,6 +1409,9 @@ static __init int threshold_init_device(void) return err; } + if (thresholding_irq_en) + mce_threshold_vector = amd_threshold_interrupt; + return 0; } /* diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 61a949d84dfa..d99a8ee9e185 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -344,10 +344,10 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) sanitize_restored_xstate(tsk, &env, xfeatures, fx_only); } + local_bh_disable(); fpu->initialized = 1; - preempt_disable(); fpu__restore(fpu); - preempt_enable(); + local_bh_enable(); return err; } else { diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 01ebcb6f263e..7ee8067cbf45 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -994,7 +994,6 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, { unsigned long old; int faulted; - struct ftrace_graph_ent trace; unsigned long return_hooker = (unsigned long) &return_to_handler; @@ -1046,19 +1045,7 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, return; } - trace.func = self_addr; - trace.depth = current->curr_ret_stack + 1; - - /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { + if (function_graph_enter(old, self_addr, frame_pointer, parent)) *parent = old; - return; - } - - if (ftrace_push_return_trace(old, self_addr, &trace.depth, - frame_pointer, parent) == -EBUSY) { - *parent = old; - return; - } } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 76fa3b836598..ec6fefbfd3c0 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -37,7 +37,6 @@ asmlinkage __visible void __init i386_start_kernel(void) cr4_init_shadow(); sanitize_boot_params(&boot_params); - x86_verify_bootdata_version(); x86_early_init_platform_quirks(); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 7663a8eb602b..16b1cbd3a61e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -457,8 +457,6 @@ void __init x86_64_start_reservations(char *real_mode_data) if (!boot_params.hdr.version) copy_bootdata(__va(real_mode_data)); - x86_verify_bootdata_version(); - x86_early_init_platform_quirks(); switch (boot_params.hdr.hardware_subarch) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c93fcfdf1673..7d31192296a8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -40,6 +40,8 @@ #include <asm/prctl.h> #include <asm/spec-ctrl.h> +#include "process.h" + /* * per-CPU TSS segments. Threads are completely 'soft' on Linux, * no more per-task TSS's. The TSS size is kept cacheline-aligned @@ -252,11 +254,12 @@ void arch_setup_new_exec(void) enable_cpuid(); } -static inline void switch_to_bitmap(struct tss_struct *tss, - struct thread_struct *prev, +static inline void switch_to_bitmap(struct thread_struct *prev, struct thread_struct *next, unsigned long tifp, unsigned long tifn) { + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + if (tifn & _TIF_IO_BITMAP) { /* * Copy the relevant range of the IO bitmap. @@ -395,32 +398,85 @@ static __always_inline void amd_set_ssb_virt_state(unsigned long tifn) wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn)); } -static __always_inline void intel_set_ssb_state(unsigned long tifn) +/* + * Update the MSRs managing speculation control, during context switch. + * + * tifp: Previous task's thread flags + * tifn: Next task's thread flags + */ +static __always_inline void __speculation_ctrl_update(unsigned long tifp, + unsigned long tifn) { - u64 msr = x86_spec_ctrl_base | ssbd_tif_to_spec_ctrl(tifn); + unsigned long tif_diff = tifp ^ tifn; + u64 msr = x86_spec_ctrl_base; + bool updmsr = false; + + /* + * If TIF_SSBD is different, select the proper mitigation + * method. Note that if SSBD mitigation is disabled or permanentely + * enabled this branch can't be taken because nothing can set + * TIF_SSBD. + */ + if (tif_diff & _TIF_SSBD) { + if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) { + amd_set_ssb_virt_state(tifn); + } else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) { + amd_set_core_ssb_state(tifn); + } else if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + msr |= ssbd_tif_to_spec_ctrl(tifn); + updmsr = true; + } + } + + /* + * Only evaluate TIF_SPEC_IB if conditional STIBP is enabled, + * otherwise avoid the MSR write. + */ + if (IS_ENABLED(CONFIG_SMP) && + static_branch_unlikely(&switch_to_cond_stibp)) { + updmsr |= !!(tif_diff & _TIF_SPEC_IB); + msr |= stibp_tif_to_spec_ctrl(tifn); + } - wrmsrl(MSR_IA32_SPEC_CTRL, msr); + if (updmsr) + wrmsrl(MSR_IA32_SPEC_CTRL, msr); } -static __always_inline void __speculative_store_bypass_update(unsigned long tifn) +static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) { - if (static_cpu_has(X86_FEATURE_VIRT_SSBD)) - amd_set_ssb_virt_state(tifn); - else if (static_cpu_has(X86_FEATURE_LS_CFG_SSBD)) - amd_set_core_ssb_state(tifn); - else - intel_set_ssb_state(tifn); + if (test_and_clear_tsk_thread_flag(tsk, TIF_SPEC_FORCE_UPDATE)) { + if (task_spec_ssb_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SSBD); + else + clear_tsk_thread_flag(tsk, TIF_SSBD); + + if (task_spec_ib_disable(tsk)) + set_tsk_thread_flag(tsk, TIF_SPEC_IB); + else + clear_tsk_thread_flag(tsk, TIF_SPEC_IB); + } + /* Return the updated threadinfo flags*/ + return task_thread_info(tsk)->flags; } -void speculative_store_bypass_update(unsigned long tif) +void speculation_ctrl_update(unsigned long tif) { + /* Forced update. Make sure all relevant TIF flags are different */ preempt_disable(); - __speculative_store_bypass_update(tif); + __speculation_ctrl_update(~tif, tif); preempt_enable(); } -void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, - struct tss_struct *tss) +/* Called from seccomp/prctl update */ +void speculation_ctrl_update_current(void) +{ + preempt_disable(); + speculation_ctrl_update(speculation_ctrl_update_tif(current)); + preempt_enable(); +} + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev, *next; unsigned long tifp, tifn; @@ -430,7 +486,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, tifn = READ_ONCE(task_thread_info(next_p)->flags); tifp = READ_ONCE(task_thread_info(prev_p)->flags); - switch_to_bitmap(tss, prev, next, tifp, tifn); + switch_to_bitmap(prev, next, tifp, tifn); propagate_user_return_notify(prev_p, next_p); @@ -451,8 +507,15 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, if ((tifp ^ tifn) & _TIF_NOCPUID) set_cpuid_faulting(!!(tifn & _TIF_NOCPUID)); - if ((tifp ^ tifn) & _TIF_SSBD) - __speculative_store_bypass_update(tifn); + if (likely(!((tifp | tifn) & _TIF_SPEC_FORCE_UPDATE))) { + __speculation_ctrl_update(tifp, tifn); + } else { + speculation_ctrl_update_tif(prev_p); + tifn = speculation_ctrl_update_tif(next_p); + + /* Enforce MSR update to ensure consistent state */ + __speculation_ctrl_update(~tifn, tifn); + } } /* diff --git a/arch/x86/kernel/process.h b/arch/x86/kernel/process.h new file mode 100644 index 000000000000..898e97cf6629 --- /dev/null +++ b/arch/x86/kernel/process.h @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Code shared between 32 and 64 bit + +#include <asm/spec-ctrl.h> + +void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p); + +/* + * This needs to be inline to optimize for the common case where no extra + * work needs to be done. + */ +static inline void switch_to_extra(struct task_struct *prev, + struct task_struct *next) +{ + unsigned long next_tif = task_thread_info(next)->flags; + unsigned long prev_tif = task_thread_info(prev)->flags; + + if (IS_ENABLED(CONFIG_SMP)) { + /* + * Avoid __switch_to_xtra() invocation when conditional + * STIPB is disabled and the only different bit is + * TIF_SPEC_IB. For CONFIG_SMP=n TIF_SPEC_IB is not + * in the TIF_WORK_CTXSW masks. + */ + if (!static_branch_likely(&switch_to_cond_stibp)) { + prev_tif &= ~_TIF_SPEC_IB; + next_tif &= ~_TIF_SPEC_IB; + } + } + + /* + * __switch_to_xtra() handles debug registers, i/o bitmaps, + * speculation mitigations etc. + */ + if (unlikely(next_tif & _TIF_WORK_CTXSW_NEXT || + prev_tif & _TIF_WORK_CTXSW_PREV)) + __switch_to_xtra(prev, next); +} diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 5046a3c9dec2..d3e593eb189f 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -59,6 +59,8 @@ #include <asm/intel_rdt_sched.h> #include <asm/proto.h> +#include "process.h" + void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; @@ -232,7 +234,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ @@ -264,12 +265,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl)) set_iopl_mask(next->iopl); - /* - * Now maybe handle debug registers and/or IO bitmaps - */ - if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV || - task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) - __switch_to_xtra(prev_p, next_p, tss); + switch_to_extra(prev_p, next_p); /* * Leave lazy mode, flushing any hypercalls made here. diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0e0b4288a4b2..bbfbf017065c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -60,6 +60,8 @@ #include <asm/unistd_32_ia32.h> #endif +#include "process.h" + /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { @@ -553,7 +555,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) struct fpu *prev_fpu = &prev->fpu; struct fpu *next_fpu = &next->fpu; int cpu = smp_processor_id(); - struct tss_struct *tss = &per_cpu(cpu_tss_rw, cpu); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(irq_count) != -1); @@ -617,12 +618,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* Reload sp0. */ update_task_stack(next_p); - /* - * Now maybe reload the debug registers and handle I/O bitmaps - */ - if (unlikely(task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT || - task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV)) - __switch_to_xtra(prev_p, next_p, tss); + switch_to_extra(prev_p, next_p); #ifdef CONFIG_XEN_PV /* diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b74e7bfed6ab..d494b9bfe618 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1280,23 +1280,6 @@ void __init setup_arch(char **cmdline_p) unwind_init(); } -/* - * From boot protocol 2.14 onwards we expect the bootloader to set the - * version to "0x8000 | <used version>". In case we find a version >= 2.14 - * without the 0x8000 we assume the boot loader supports 2.13 only and - * reset the version accordingly. The 0x8000 flag is removed in any case. - */ -void __init x86_verify_bootdata_version(void) -{ - if (boot_params.hdr.version & VERSION_WRITTEN) - boot_params.hdr.version &= ~VERSION_WRITTEN; - else if (boot_params.hdr.version >= 0x020e) - boot_params.hdr.version = 0x020d; - - if (boot_params.hdr.version < 0x020e) - boot_params.hdr.acpi_rsdp_addr = 0; -} - #ifdef CONFIG_X86_32 static struct resource video_ram_resource = { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 89db20f8cb70..c4533d05c214 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -55,7 +55,7 @@ #define PRIo64 "o" /* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */ -#define apic_debug(fmt, arg...) +#define apic_debug(fmt, arg...) do {} while (0) /* 14 is the version for Xeon and Pentium 8.4.8*/ #define APIC_VERSION (0x14UL | ((KVM_APIC_LVT_NUM - 1) << 16)) @@ -576,6 +576,11 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); + if (unlikely(!map)) { + count = -EOPNOTSUPP; + goto out; + } + if (min > map->max_apic_id) goto out; /* Bits above cluster_size are masked in the caller. */ diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index cf5f572f2305..7c03c0f35444 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -5074,9 +5074,9 @@ static bool need_remote_flush(u64 old, u64 new) } static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, - const u8 *new, int *bytes) + int *bytes) { - u64 gentry; + u64 gentry = 0; int r; /* @@ -5088,22 +5088,12 @@ static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ *gpa &= ~(gpa_t)7; *bytes = 8; - r = kvm_vcpu_read_guest(vcpu, *gpa, &gentry, 8); - if (r) - gentry = 0; - new = (const u8 *)&gentry; } - switch (*bytes) { - case 4: - gentry = *(const u32 *)new; - break; - case 8: - gentry = *(const u64 *)new; - break; - default: - gentry = 0; - break; + if (*bytes == 4 || *bytes == 8) { + r = kvm_vcpu_read_guest_atomic(vcpu, *gpa, &gentry, *bytes); + if (r) + gentry = 0; } return gentry; @@ -5207,8 +5197,6 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes); - /* * No need to care whether allocation memory is successful * or not since pte prefetch is skiped if it does not have @@ -5217,6 +5205,9 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mmu_topup_memory_caches(vcpu); spin_lock(&vcpu->kvm->mmu_lock); + + gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes); + ++vcpu->kvm->stat.mmu_pte_write; kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 0e21ccc46792..cc6467b35a85 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1446,7 +1446,7 @@ static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu) return vcpu->arch.tsc_offset; } -static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); u64 g_tsc_offset = 0; @@ -1464,6 +1464,7 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) svm->vmcb->control.tsc_offset = offset + g_tsc_offset; mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + return svm->vmcb->control.tsc_offset; } static void avic_init_vmcb(struct vcpu_svm *svm) @@ -1664,20 +1665,23 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, static int avic_init_access_page(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - int ret; + int ret = 0; + mutex_lock(&kvm->slots_lock); if (kvm->arch.apic_access_page_done) - return 0; + goto out; - ret = x86_set_memory_region(kvm, - APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, - PAGE_SIZE); + ret = __x86_set_memory_region(kvm, + APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, + PAGE_SIZE); if (ret) - return ret; + goto out; kvm->arch.apic_access_page_done = true; - return 0; +out: + mutex_unlock(&kvm->slots_lock); + return ret; } static int avic_init_backing_page(struct kvm_vcpu *vcpu) @@ -2189,21 +2193,31 @@ out: return ERR_PTR(err); } +static void svm_clear_current_vmcb(struct vmcb *vmcb) +{ + int i; + + for_each_online_cpu(i) + cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL); +} + static void svm_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + /* + * The vmcb page can be recycled, causing a false negative in + * svm_vcpu_load(). So, ensure that no logical CPU has this + * vmcb page recorded as its current vmcb. + */ + svm_clear_current_vmcb(svm->vmcb); + __free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT)); __free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER); __free_page(virt_to_page(svm->nested.hsave)); __free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER); kvm_vcpu_uninit(vcpu); kmem_cache_free(kvm_vcpu_cache, svm); - /* - * The vmcb page can be recycled, causing a false negative in - * svm_vcpu_load(). So do a full IBPB now. - */ - indirect_branch_prediction_barrier(); } static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) @@ -7149,7 +7163,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .has_wbinvd_exit = svm_has_wbinvd_exit, .read_l1_tsc_offset = svm_read_l1_tsc_offset, - .write_tsc_offset = svm_write_tsc_offset, + .write_l1_tsc_offset = svm_write_l1_tsc_offset, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 4555077d69ce..02edd9960e9d 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -174,6 +174,7 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); * refer SDM volume 3b section 21.6.13 & 22.1.3. */ static unsigned int ple_gap = KVM_DEFAULT_PLE_GAP; +module_param(ple_gap, uint, 0444); static unsigned int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW; module_param(ple_window, uint, 0444); @@ -984,6 +985,7 @@ struct vcpu_vmx { struct shared_msr_entry *guest_msrs; int nmsrs; int save_nmsrs; + bool guest_msrs_dirty; unsigned long host_idt_base; #ifdef CONFIG_X86_64 u64 msr_host_kernel_gs_base; @@ -1306,7 +1308,7 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12, u16 error_code); static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu); -static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type); static DEFINE_PER_CPU(struct vmcs *, vmxarea); @@ -1610,12 +1612,6 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* We don't support disabling the feature for simplicity. */ - if (vmx->nested.enlightened_vmcs_enabled) - return 0; - - vmx->nested.enlightened_vmcs_enabled = true; - /* * vmcs_version represents the range of supported Enlightened VMCS * versions: lower 8 bits is the minimal version, higher 8 bits is the @@ -1625,6 +1621,12 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu, if (vmcs_version) *vmcs_version = (KVM_EVMCS_VERSION << 8) | 1; + /* We don't support disabling the feature for simplicity. */ + if (vmx->nested.enlightened_vmcs_enabled) + return 0; + + vmx->nested.enlightened_vmcs_enabled = true; + vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL; vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL; vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL; @@ -2897,6 +2899,20 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmx->req_immediate_exit = false; + /* + * Note that guest MSRs to be saved/restored can also be changed + * when guest state is loaded. This happens when guest transitions + * to/from long-mode by setting MSR_EFER.LMA. + */ + if (!vmx->loaded_cpu_state || vmx->guest_msrs_dirty) { + vmx->guest_msrs_dirty = false; + for (i = 0; i < vmx->save_nmsrs; ++i) + kvm_set_shared_msr(vmx->guest_msrs[i].index, + vmx->guest_msrs[i].data, + vmx->guest_msrs[i].mask); + + } + if (vmx->loaded_cpu_state) return; @@ -2957,11 +2973,6 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) vmcs_writel(HOST_GS_BASE, gs_base); host_state->gs_base = gs_base; } - - for (i = 0; i < vmx->save_nmsrs; ++i) - kvm_set_shared_msr(vmx->guest_msrs[i].index, - vmx->guest_msrs[i].data, - vmx->guest_msrs[i].mask); } static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx) @@ -3436,6 +3447,7 @@ static void setup_msrs(struct vcpu_vmx *vmx) move_msr_up(vmx, index, save_nmsrs++); vmx->save_nmsrs = save_nmsrs; + vmx->guest_msrs_dirty = true; if (cpu_has_vmx_msr_bitmap()) vmx_update_msr_bitmap(&vmx->vcpu); @@ -3452,11 +3464,9 @@ static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu) return vcpu->arch.tsc_offset; } -/* - * writes 'offset' into guest's timestamp counter offset register - */ -static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) +static u64 vmx_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { + u64 active_offset = offset; if (is_guest_mode(vcpu)) { /* * We're here if L1 chose not to trap WRMSR to TSC. According @@ -3464,17 +3474,16 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) * set for L2 remains unchanged, and still needs to be added * to the newly set TSC to get L2's TSC. */ - struct vmcs12 *vmcs12; - /* recalculate vmcs02.TSC_OFFSET: */ - vmcs12 = get_vmcs12(vcpu); - vmcs_write64(TSC_OFFSET, offset + - (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING) ? - vmcs12->tsc_offset : 0)); + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + if (nested_cpu_has(vmcs12, CPU_BASED_USE_TSC_OFFSETING)) + active_offset += vmcs12->tsc_offset; } else { trace_kvm_write_tsc_offset(vcpu->vcpu_id, vmcs_read64(TSC_OFFSET), offset); - vmcs_write64(TSC_OFFSET, offset); } + + vmcs_write64(TSC_OFFSET, active_offset); + return active_offset; } /* @@ -5944,7 +5953,7 @@ static void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type) { int f = sizeof(unsigned long); @@ -5982,7 +5991,7 @@ static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bit } } -static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type) { int f = sizeof(unsigned long); @@ -6020,7 +6029,7 @@ static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitm } } -static void __always_inline vmx_set_intercept_for_msr(unsigned long *msr_bitmap, +static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap, u32 msr, int type, bool value) { if (value) @@ -8664,8 +8673,6 @@ static int copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx) struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; - vmcs12->hdr.revision_id = evmcs->revision_id; - /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; @@ -9369,7 +9376,30 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, vmx->nested.hv_evmcs = kmap(vmx->nested.hv_evmcs_page); - if (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION) { + /* + * Currently, KVM only supports eVMCS version 1 + * (== KVM_EVMCS_VERSION) and thus we expect guest to set this + * value to first u32 field of eVMCS which should specify eVMCS + * VersionNumber. + * + * Guest should be aware of supported eVMCS versions by host by + * examining CPUID.0x4000000A.EAX[0:15]. Host userspace VMM is + * expected to set this CPUID leaf according to the value + * returned in vmcs_version from nested_enable_evmcs(). + * + * However, it turns out that Microsoft Hyper-V fails to comply + * to their own invented interface: When Hyper-V use eVMCS, it + * just sets first u32 field of eVMCS to revision_id specified + * in MSR_IA32_VMX_BASIC. Instead of used eVMCS version number + * which is one of the supported versions specified in + * CPUID.0x4000000A.EAX[0:15]. + * + * To overcome Hyper-V bug, we accept here either a supported + * eVMCS version or VMCS12 revision_id as valid values for first + * u32 field of eVMCS. + */ + if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) && + (vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) { nested_release_evmcs(vcpu); return 0; } @@ -9390,9 +9420,11 @@ static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu, * present in struct hv_enlightened_vmcs, ...). Make sure there * are no leftovers. */ - if (from_launch) - memset(vmx->nested.cached_vmcs12, 0, - sizeof(*vmx->nested.cached_vmcs12)); + if (from_launch) { + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + memset(vmcs12, 0, sizeof(*vmcs12)); + vmcs12->hdr.revision_id = VMCS12_REVISION; + } } return 1; @@ -15062,7 +15094,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, .read_l1_tsc_offset = vmx_read_l1_tsc_offset, - .write_tsc_offset = vmx_write_tsc_offset, + .write_l1_tsc_offset = vmx_write_l1_tsc_offset, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 5cd5647120f2..d02937760c3b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1665,8 +1665,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { - kvm_x86_ops->write_tsc_offset(vcpu, offset); - vcpu->arch.tsc_offset = offset; + vcpu->arch.tsc_offset = kvm_x86_ops->write_l1_tsc_offset(vcpu, offset); } static inline bool kvm_check_tsc_unstable(void) @@ -1794,7 +1793,8 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc); static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { - kvm_vcpu_write_tsc_offset(vcpu, vcpu->arch.tsc_offset + adjustment); + u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu); + kvm_vcpu_write_tsc_offset(vcpu, tsc_offset + adjustment); } static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) @@ -6918,6 +6918,7 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, clock_pairing.nsec = ts.tv_nsec; clock_pairing.tsc = kvm_read_l1_tsc(vcpu, cycle); clock_pairing.flags = 0; + memset(&clock_pairing.pad, 0, sizeof(clock_pairing.pad)); ret = 0; if (kvm_write_guest(vcpu->kvm, paddr, &clock_pairing, @@ -7455,7 +7456,8 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) else { if (vcpu->arch.apicv_active) kvm_x86_ops->sync_pir_to_irr(vcpu); - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); + if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } if (is_guest_mode(vcpu)) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index bddd6b3cee1d..03b6b4c2238d 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -7,7 +7,6 @@ #include <linux/export.h> #include <linux/cpu.h> #include <linux/debugfs.h> -#include <linux/ptrace.h> #include <asm/tlbflush.h> #include <asm/mmu_context.h> @@ -31,6 +30,12 @@ */ /* + * Use bit 0 to mangle the TIF_SPEC_IB state into the mm pointer which is + * stored in cpu_tlb_state.last_user_mm_ibpb. + */ +#define LAST_USER_MM_IBPB 0x1UL + +/* * We get here when we do something requiring a TLB invalidation * but could not go invalidate all of the contexts. We do the * necessary invalidation by clearing out the 'ctx_id' which @@ -181,17 +186,87 @@ static void sync_current_stack_to_mm(struct mm_struct *mm) } } -static bool ibpb_needed(struct task_struct *tsk, u64 last_ctx_id) +static inline unsigned long mm_mangle_tif_spec_ib(struct task_struct *next) +{ + unsigned long next_tif = task_thread_info(next)->flags; + unsigned long ibpb = (next_tif >> TIF_SPEC_IB) & LAST_USER_MM_IBPB; + + return (unsigned long)next->mm | ibpb; +} + +static void cond_ibpb(struct task_struct *next) { + if (!next || !next->mm) + return; + /* - * Check if the current (previous) task has access to the memory - * of the @tsk (next) task. If access is denied, make sure to - * issue a IBPB to stop user->user Spectre-v2 attacks. - * - * Note: __ptrace_may_access() returns 0 or -ERRNO. + * Both, the conditional and the always IBPB mode use the mm + * pointer to avoid the IBPB when switching between tasks of the + * same process. Using the mm pointer instead of mm->context.ctx_id + * opens a hypothetical hole vs. mm_struct reuse, which is more or + * less impossible to control by an attacker. Aside of that it + * would only affect the first schedule so the theoretically + * exposed data is not really interesting. */ - return (tsk && tsk->mm && tsk->mm->context.ctx_id != last_ctx_id && - ptrace_may_access_sched(tsk, PTRACE_MODE_SPEC_IBPB)); + if (static_branch_likely(&switch_mm_cond_ibpb)) { + unsigned long prev_mm, next_mm; + + /* + * This is a bit more complex than the always mode because + * it has to handle two cases: + * + * 1) Switch from a user space task (potential attacker) + * which has TIF_SPEC_IB set to a user space task + * (potential victim) which has TIF_SPEC_IB not set. + * + * 2) Switch from a user space task (potential attacker) + * which has TIF_SPEC_IB not set to a user space task + * (potential victim) which has TIF_SPEC_IB set. + * + * This could be done by unconditionally issuing IBPB when + * a task which has TIF_SPEC_IB set is either scheduled in + * or out. Though that results in two flushes when: + * + * - the same user space task is scheduled out and later + * scheduled in again and only a kernel thread ran in + * between. + * + * - a user space task belonging to the same process is + * scheduled in after a kernel thread ran in between + * + * - a user space task belonging to the same process is + * scheduled in immediately. + * + * Optimize this with reasonably small overhead for the + * above cases. Mangle the TIF_SPEC_IB bit into the mm + * pointer of the incoming task which is stored in + * cpu_tlbstate.last_user_mm_ibpb for comparison. + */ + next_mm = mm_mangle_tif_spec_ib(next); + prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_ibpb); + + /* + * Issue IBPB only if the mm's are different and one or + * both have the IBPB bit set. + */ + if (next_mm != prev_mm && + (next_mm | prev_mm) & LAST_USER_MM_IBPB) + indirect_branch_prediction_barrier(); + + this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, next_mm); + } + + if (static_branch_unlikely(&switch_mm_always_ibpb)) { + /* + * Only flush when switching to a user space task with a + * different context than the user space task which ran + * last on this CPU. + */ + if (this_cpu_read(cpu_tlbstate.last_user_mm) != next->mm) { + indirect_branch_prediction_barrier(); + this_cpu_write(cpu_tlbstate.last_user_mm, next->mm); + } + } } void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, @@ -292,22 +367,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, new_asid = prev_asid; need_flush = true; } else { - u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id); - /* * Avoid user/user BTB poisoning by flushing the branch * predictor when switching between processes. This stops * one process from doing Spectre-v2 attacks on another. - * - * As an optimization, flush indirect branches only when - * switching into a processes that can't be ptrace by the - * current one (as in such case, attacker has much more - * convenient way how to tamper with the next process than - * branch buffer poisoning). */ - if (static_cpu_has(X86_FEATURE_USE_IBPB) && - ibpb_needed(tsk, last_ctx_id)) - indirect_branch_prediction_barrier(); + cond_ibpb(tsk); if (IS_ENABLED(CONFIG_VMAP_STACK)) { /* @@ -365,14 +430,6 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); } - /* - * Record last user mm's context id, so we can avoid - * flushing branch buffer with IBPB if we switch back - * to the same user. - */ - if (next != &init_mm) - this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); - /* Make sure we write CR3 before loaded_mm. */ barrier(); @@ -441,7 +498,7 @@ void initialize_tlbstate_and_flush(void) write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ - this_cpu_write(cpu_tlbstate.last_ctx_id, mm->context.ctx_id); + this_cpu_write(cpu_tlbstate.last_user_mm_ibpb, LAST_USER_MM_IBPB); this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); this_cpu_write(cpu_tlbstate.next_asid, 1); this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, mm->context.ctx_id); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index e996e8e744cb..750f46ad018a 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -10,7 +10,6 @@ #include <xen/xen.h> #include <xen/features.h> #include <xen/page.h> -#include <xen/interface/memory.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -346,80 +345,3 @@ void xen_arch_unregister_cpu(int num) } EXPORT_SYMBOL(xen_arch_unregister_cpu); #endif - -#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG -void __init arch_xen_balloon_init(struct resource *hostmem_resource) -{ - struct xen_memory_map memmap; - int rc; - unsigned int i, last_guest_ram; - phys_addr_t max_addr = PFN_PHYS(max_pfn); - struct e820_table *xen_e820_table; - const struct e820_entry *entry; - struct resource *res; - - if (!xen_initial_domain()) - return; - - xen_e820_table = kmalloc(sizeof(*xen_e820_table), GFP_KERNEL); - if (!xen_e820_table) - return; - - memmap.nr_entries = ARRAY_SIZE(xen_e820_table->entries); - set_xen_guest_handle(memmap.buffer, xen_e820_table->entries); - rc = HYPERVISOR_memory_op(XENMEM_machine_memory_map, &memmap); - if (rc) { - pr_warn("%s: Can't read host e820 (%d)\n", __func__, rc); - goto out; - } - - last_guest_ram = 0; - for (i = 0; i < memmap.nr_entries; i++) { - if (xen_e820_table->entries[i].addr >= max_addr) - break; - if (xen_e820_table->entries[i].type == E820_TYPE_RAM) - last_guest_ram = i; - } - - entry = &xen_e820_table->entries[last_guest_ram]; - if (max_addr >= entry->addr + entry->size) - goto out; /* No unallocated host RAM. */ - - hostmem_resource->start = max_addr; - hostmem_resource->end = entry->addr + entry->size; - - /* - * Mark non-RAM regions between the end of dom0 RAM and end of host RAM - * as unavailable. The rest of that region can be used for hotplug-based - * ballooning. - */ - for (; i < memmap.nr_entries; i++) { - entry = &xen_e820_table->entries[i]; - - if (entry->type == E820_TYPE_RAM) - continue; - - if (entry->addr >= hostmem_resource->end) - break; - - res = kzalloc(sizeof(*res), GFP_KERNEL); - if (!res) - goto out; - - res->name = "Unavailable host RAM"; - res->start = entry->addr; - res->end = (entry->addr + entry->size < hostmem_resource->end) ? - entry->addr + entry->size : hostmem_resource->end; - rc = insert_resource(hostmem_resource, res); - if (rc) { - pr_warn("%s: Can't insert [%llx - %llx) (%d)\n", - __func__, res->start, res->end, rc); - kfree(res); - goto out; - } - } - - out: - kfree(xen_e820_table); -} -#endif /* CONFIG_XEN_BALLOON_MEMORY_HOTPLUG */ diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 2bce7958ce8b..0766a08bdf45 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -69,6 +69,11 @@ void xen_mc_flush(void) trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx); +#if MC_DEBUG + memcpy(b->debug, b->entries, + b->mcidx * sizeof(struct multicall_entry)); +#endif + switch (b->mcidx) { case 0: /* no-op */ @@ -87,32 +92,34 @@ void xen_mc_flush(void) break; default: -#if MC_DEBUG - memcpy(b->debug, b->entries, - b->mcidx * sizeof(struct multicall_entry)); -#endif - if (HYPERVISOR_multicall(b->entries, b->mcidx) != 0) BUG(); for (i = 0; i < b->mcidx; i++) if (b->entries[i].result < 0) ret++; + } + if (WARN_ON(ret)) { + pr_err("%d of %d multicall(s) failed: cpu %d\n", + ret, b->mcidx, smp_processor_id()); + for (i = 0; i < b->mcidx; i++) { + if (b->entries[i].result < 0) { #if MC_DEBUG - if (ret) { - printk(KERN_ERR "%d multicall(s) failed: cpu %d\n", - ret, smp_processor_id()); - dump_stack(); - for (i = 0; i < b->mcidx; i++) { - printk(KERN_DEBUG " call %2d/%d: op=%lu arg=[%lx] result=%ld\t%pF\n", - i+1, b->mcidx, + pr_err(" call %2d: op=%lu arg=[%lx] result=%ld\t%pF\n", + i + 1, b->debug[i].op, b->debug[i].args[0], b->entries[i].result, b->caller[i]); +#else + pr_err(" call %2d: op=%lu arg=[%lx] result=%ld\n", + i + 1, + b->entries[i].op, + b->entries[i].args[0], + b->entries[i].result); +#endif } } -#endif } b->mcidx = 0; @@ -126,8 +133,6 @@ void xen_mc_flush(void) b->cbidx = 0; local_irq_restore(flags); - - WARN_ON(ret); } struct multicall_space __xen_mc_entry(size_t args) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 1163e33121fb..075ed47993bb 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -808,6 +808,7 @@ char * __init xen_memory_setup(void) addr = xen_e820_table.entries[0].addr; size = xen_e820_table.entries[0].size; while (i < xen_e820_table.nr_entries) { + bool discard = false; chunk_size = size; type = xen_e820_table.entries[i].type; @@ -823,10 +824,11 @@ char * __init xen_memory_setup(void) xen_add_extra_mem(pfn_s, n_pfns); xen_max_p2m_pfn = pfn_s + n_pfns; } else - type = E820_TYPE_UNUSABLE; + discard = true; } - xen_align_and_add_e820_region(addr, chunk_size, type); + if (!discard) + xen_align_and_add_e820_region(addr, chunk_size, type); addr += chunk_size; size -= chunk_size; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 1c8a8816a402..3776122c87cc 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -3,22 +3,17 @@ * Split spinlock implementation out into its own file, so it can be * compiled in a FTRACE-compatible way. */ -#include <linux/kernel_stat.h> +#include <linux/kernel.h> #include <linux/spinlock.h> -#include <linux/debugfs.h> -#include <linux/log2.h> -#include <linux/gfp.h> #include <linux/slab.h> #include <linux/atomic.h> #include <asm/paravirt.h> #include <asm/qspinlock.h> -#include <xen/interface/xen.h> #include <xen/events.h> #include "xen-ops.h" -#include "debugfs.h" static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); diff --git a/arch/xtensa/kernel/asm-offsets.c b/arch/xtensa/kernel/asm-offsets.c index 67904f55f188..120dd746a147 100644 --- a/arch/xtensa/kernel/asm-offsets.c +++ b/arch/xtensa/kernel/asm-offsets.c @@ -94,14 +94,14 @@ int main(void) DEFINE(THREAD_SP, offsetof (struct task_struct, thread.sp)); DEFINE(THREAD_CPENABLE, offsetof (struct thread_info, cpenable)); #if XTENSA_HAVE_COPROCESSORS - DEFINE(THREAD_XTREGS_CP0, offsetof (struct thread_info, xtregs_cp)); - DEFINE(THREAD_XTREGS_CP1, offsetof (struct thread_info, xtregs_cp)); - DEFINE(THREAD_XTREGS_CP2, offsetof (struct thread_info, xtregs_cp)); - DEFINE(THREAD_XTREGS_CP3, offsetof (struct thread_info, xtregs_cp)); - DEFINE(THREAD_XTREGS_CP4, offsetof (struct thread_info, xtregs_cp)); - DEFINE(THREAD_XTREGS_CP5, offsetof (struct thread_info, xtregs_cp)); - DEFINE(THREAD_XTREGS_CP6, offsetof (struct thread_info, xtregs_cp)); - DEFINE(THREAD_XTREGS_CP7, offsetof (struct thread_info, xtregs_cp)); + DEFINE(THREAD_XTREGS_CP0, offsetof(struct thread_info, xtregs_cp.cp0)); + DEFINE(THREAD_XTREGS_CP1, offsetof(struct thread_info, xtregs_cp.cp1)); + DEFINE(THREAD_XTREGS_CP2, offsetof(struct thread_info, xtregs_cp.cp2)); + DEFINE(THREAD_XTREGS_CP3, offsetof(struct thread_info, xtregs_cp.cp3)); + DEFINE(THREAD_XTREGS_CP4, offsetof(struct thread_info, xtregs_cp.cp4)); + DEFINE(THREAD_XTREGS_CP5, offsetof(struct thread_info, xtregs_cp.cp5)); + DEFINE(THREAD_XTREGS_CP6, offsetof(struct thread_info, xtregs_cp.cp6)); + DEFINE(THREAD_XTREGS_CP7, offsetof(struct thread_info, xtregs_cp.cp7)); #endif DEFINE(THREAD_XTREGS_USER, offsetof (struct thread_info, xtregs_user)); DEFINE(XTREGS_USER_SIZE, sizeof(xtregs_user_t)); diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 483dcfb6e681..4bb68133a72a 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -94,18 +94,21 @@ void coprocessor_release_all(struct thread_info *ti) void coprocessor_flush_all(struct thread_info *ti) { - unsigned long cpenable; + unsigned long cpenable, old_cpenable; int i; preempt_disable(); + RSR_CPENABLE(old_cpenable); cpenable = ti->cpenable; + WSR_CPENABLE(cpenable); for (i = 0; i < XCHAL_CP_MAX; i++) { if ((cpenable & 1) != 0 && coprocessor_owner[i] == ti) coprocessor_flush(ti, i); cpenable >>= 1; } + WSR_CPENABLE(old_cpenable); preempt_enable(); } diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c index c0845cb1cbb9..d9541be0605a 100644 --- a/arch/xtensa/kernel/ptrace.c +++ b/arch/xtensa/kernel/ptrace.c @@ -127,12 +127,37 @@ static int ptrace_setregs(struct task_struct *child, void __user *uregs) } +#if XTENSA_HAVE_COPROCESSORS +#define CP_OFFSETS(cp) \ + { \ + .elf_xtregs_offset = offsetof(elf_xtregs_t, cp), \ + .ti_offset = offsetof(struct thread_info, xtregs_cp.cp), \ + .sz = sizeof(xtregs_ ## cp ## _t), \ + } + +static const struct { + size_t elf_xtregs_offset; + size_t ti_offset; + size_t sz; +} cp_offsets[] = { + CP_OFFSETS(cp0), + CP_OFFSETS(cp1), + CP_OFFSETS(cp2), + CP_OFFSETS(cp3), + CP_OFFSETS(cp4), + CP_OFFSETS(cp5), + CP_OFFSETS(cp6), + CP_OFFSETS(cp7), +}; +#endif + static int ptrace_getxregs(struct task_struct *child, void __user *uregs) { struct pt_regs *regs = task_pt_regs(child); struct thread_info *ti = task_thread_info(child); elf_xtregs_t __user *xtregs = uregs; int ret = 0; + int i __maybe_unused; if (!access_ok(VERIFY_WRITE, uregs, sizeof(elf_xtregs_t))) return -EIO; @@ -140,8 +165,13 @@ static int ptrace_getxregs(struct task_struct *child, void __user *uregs) #if XTENSA_HAVE_COPROCESSORS /* Flush all coprocessor registers to memory. */ coprocessor_flush_all(ti); - ret |= __copy_to_user(&xtregs->cp0, &ti->xtregs_cp, - sizeof(xtregs_coprocessor_t)); + + for (i = 0; i < ARRAY_SIZE(cp_offsets); ++i) + ret |= __copy_to_user((char __user *)xtregs + + cp_offsets[i].elf_xtregs_offset, + (const char *)ti + + cp_offsets[i].ti_offset, + cp_offsets[i].sz); #endif ret |= __copy_to_user(&xtregs->opt, ®s->xtregs_opt, sizeof(xtregs->opt)); @@ -157,6 +187,7 @@ static int ptrace_setxregs(struct task_struct *child, void __user *uregs) struct pt_regs *regs = task_pt_regs(child); elf_xtregs_t *xtregs = uregs; int ret = 0; + int i __maybe_unused; if (!access_ok(VERIFY_READ, uregs, sizeof(elf_xtregs_t))) return -EFAULT; @@ -166,8 +197,11 @@ static int ptrace_setxregs(struct task_struct *child, void __user *uregs) coprocessor_flush_all(ti); coprocessor_release_all(ti); - ret |= __copy_from_user(&ti->xtregs_cp, &xtregs->cp0, - sizeof(xtregs_coprocessor_t)); + for (i = 0; i < ARRAY_SIZE(cp_offsets); ++i) + ret |= __copy_from_user((char *)ti + cp_offsets[i].ti_offset, + (const char __user *)xtregs + + cp_offsets[i].elf_xtregs_offset, + cp_offsets[i].sz); #endif ret |= __copy_from_user(®s->xtregs_opt, &xtregs->opt, sizeof(xtregs->opt)); diff --git a/block/blk-merge.c b/block/blk-merge.c index e7696c47489a..7695034f4b87 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -820,7 +820,7 @@ static struct request *attempt_merge(struct request_queue *q, req->__data_len += blk_rq_bytes(next); - if (req_op(req) != REQ_OP_DISCARD) + if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); /* diff --git a/drivers/acpi/acpica/exserial.c b/drivers/acpi/acpica/exserial.c index 0d42f30e5b25..9920fac6413f 100644 --- a/drivers/acpi/acpica/exserial.c +++ b/drivers/acpi/acpica/exserial.c @@ -244,7 +244,6 @@ acpi_ex_write_serial_bus(union acpi_operand_object *source_desc, { acpi_status status; u32 buffer_length; - u32 data_length; void *buffer; union acpi_operand_object *buffer_desc; u32 function; @@ -282,14 +281,12 @@ acpi_ex_write_serial_bus(union acpi_operand_object *source_desc, case ACPI_ADR_SPACE_SMBUS: buffer_length = ACPI_SMBUS_BUFFER_SIZE; - data_length = ACPI_SMBUS_DATA_SIZE; function = ACPI_WRITE | (obj_desc->field.attribute << 16); break; case ACPI_ADR_SPACE_IPMI: buffer_length = ACPI_IPMI_BUFFER_SIZE; - data_length = ACPI_IPMI_DATA_SIZE; function = ACPI_WRITE; break; @@ -310,7 +307,6 @@ acpi_ex_write_serial_bus(union acpi_operand_object *source_desc, /* Add header length to get the full size of the buffer */ buffer_length += ACPI_SERIAL_HEADER_SIZE; - data_length = source_desc->buffer.pointer[1]; function = ACPI_WRITE | (accessor_type << 16); break; @@ -318,20 +314,6 @@ acpi_ex_write_serial_bus(union acpi_operand_object *source_desc, return_ACPI_STATUS(AE_AML_INVALID_SPACE_ID); } -#if 0 - OBSOLETE ? - /* Check for possible buffer overflow */ - if (data_length > source_desc->buffer.length) { - ACPI_ERROR((AE_INFO, - "Length in buffer header (%u)(%u) is greater than " - "the physical buffer length (%u) and will overflow", - data_length, buffer_length, - source_desc->buffer.length)); - - return_ACPI_STATUS(AE_AML_BUFFER_LIMIT); - } -#endif - /* Create the transfer/bidirectional/return buffer */ buffer_desc = acpi_ut_create_buffer_object(buffer_length); @@ -342,7 +324,8 @@ acpi_ex_write_serial_bus(union acpi_operand_object *source_desc, /* Copy the input buffer data to the transfer buffer */ buffer = buffer_desc->buffer.pointer; - memcpy(buffer, source_desc->buffer.pointer, data_length); + memcpy(buffer, source_desc->buffer.pointer, + min(buffer_length, source_desc->buffer.length)); /* Lock entire transaction if requested */ diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 2a361e22d38d..70f4e80b9246 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -700,7 +700,7 @@ static void iort_set_device_domain(struct device *dev, */ static struct irq_domain *iort_get_platform_device_domain(struct device *dev) { - struct acpi_iort_node *node, *msi_parent; + struct acpi_iort_node *node, *msi_parent = NULL; struct fwnode_handle *iort_fwnode; struct acpi_iort_its_group *its; int i; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 54fdd99df9be..9f2059d24ae2 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3004,7 +3004,6 @@ static void binder_transaction(struct binder_proc *proc, t->buffer = NULL; goto err_binder_alloc_buf_failed; } - t->buffer->allow_user_free = 0; t->buffer->debug_id = t->debug_id; t->buffer->transaction = t; t->buffer->target_node = target_node; @@ -3540,14 +3539,18 @@ static int binder_thread_write(struct binder_proc *proc, buffer = binder_alloc_prepare_to_free(&proc->alloc, data_ptr); - if (buffer == NULL) { - binder_user_error("%d:%d BC_FREE_BUFFER u%016llx no match\n", - proc->pid, thread->pid, (u64)data_ptr); - break; - } - if (!buffer->allow_user_free) { - binder_user_error("%d:%d BC_FREE_BUFFER u%016llx matched unreturned buffer\n", - proc->pid, thread->pid, (u64)data_ptr); + if (IS_ERR_OR_NULL(buffer)) { + if (PTR_ERR(buffer) == -EPERM) { + binder_user_error( + "%d:%d BC_FREE_BUFFER u%016llx matched unreturned or currently freeing buffer\n", + proc->pid, thread->pid, + (u64)data_ptr); + } else { + binder_user_error( + "%d:%d BC_FREE_BUFFER u%016llx no match\n", + proc->pid, thread->pid, + (u64)data_ptr); + } break; } binder_debug(BINDER_DEBUG_FREE_BUFFER, diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 52eb11edf000..022cd80e80cc 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -151,16 +151,12 @@ static struct binder_buffer *binder_alloc_prepare_to_free_locked( else { /* * Guard against user threads attempting to - * free the buffer twice + * free the buffer when in use by kernel or + * after it's already been freed. */ - if (buffer->free_in_progress) { - binder_alloc_debug(BINDER_DEBUG_USER_ERROR, - "%d:%d FREE_BUFFER u%016llx user freed buffer twice\n", - alloc->pid, current->pid, - (u64)user_ptr); - return NULL; - } - buffer->free_in_progress = 1; + if (!buffer->allow_user_free) + return ERR_PTR(-EPERM); + buffer->allow_user_free = 0; return buffer; } } @@ -500,7 +496,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( rb_erase(best_fit, &alloc->free_buffers); buffer->free = 0; - buffer->free_in_progress = 0; + buffer->allow_user_free = 0; binder_insert_allocated_buffer_locked(alloc, buffer); binder_alloc_debug(BINDER_DEBUG_BUFFER_ALLOC, "%d: binder_alloc_buf size %zd got %pK\n", diff --git a/drivers/android/binder_alloc.h b/drivers/android/binder_alloc.h index 9ef64e563856..fb3238c74c8a 100644 --- a/drivers/android/binder_alloc.h +++ b/drivers/android/binder_alloc.h @@ -50,8 +50,7 @@ struct binder_buffer { unsigned free:1; unsigned allow_user_free:1; unsigned async_transaction:1; - unsigned free_in_progress:1; - unsigned debug_id:28; + unsigned debug_id:29; struct binder_transaction *transaction; diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 4e46dc9e41ad..11e1663bdc4d 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -1410,7 +1410,7 @@ static int init_q(struct fs_dev *dev, struct queue *txq, int queue, func_enter (); - fs_dprintk (FS_DEBUG_INIT, "Inititing queue at %x: %d entries:\n", + fs_dprintk (FS_DEBUG_INIT, "Initializing queue at %x: %d entries:\n", queue, nentries); p = aligned_kmalloc (sz, GFP_KERNEL, 0x10); @@ -1443,7 +1443,7 @@ static int init_fp(struct fs_dev *dev, struct freepool *fp, int queue, { func_enter (); - fs_dprintk (FS_DEBUG_INIT, "Inititing free pool at %x:\n", queue); + fs_dprintk (FS_DEBUG_INIT, "Initializing free pool at %x:\n", queue); write_fs (dev, FP_CNF(queue), (bufsize * RBFP_RBS) | RBFP_RBSVAL | RBFP_CME); write_fs (dev, FP_SA(queue), 0); diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 4aaf00d2098b..e038e2b3b7ea 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -26,8 +26,14 @@ struct devres_node { struct devres { struct devres_node node; - /* -- 3 pointers */ - unsigned long long data[]; /* guarantee ull alignment */ + /* + * Some archs want to perform DMA into kmalloc caches + * and need a guaranteed alignment larger than + * the alignment of a 64-bit integer. + * Thus we use ARCH_KMALLOC_MINALIGN here and get exactly the same + * buffer alignment as if it was allocated by plain kmalloc(). + */ + u8 __aligned(ARCH_KMALLOC_MINALIGN) data[]; }; struct devres_group { diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c index 7cbac6e8c113..01d936c9fe89 100644 --- a/drivers/dma/at_hdmac.c +++ b/drivers/dma/at_hdmac.c @@ -1641,6 +1641,12 @@ static void atc_free_chan_resources(struct dma_chan *chan) atchan->descs_allocated = 0; atchan->status = 0; + /* + * Free atslave allocated in at_dma_xlate() + */ + kfree(chan->private); + chan->private = NULL; + dev_vdbg(chan2dev(chan), "free_chan_resources: done\n"); } @@ -1675,7 +1681,7 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec, dma_cap_zero(mask); dma_cap_set(DMA_SLAVE, mask); - atslave = devm_kzalloc(&dmac_pdev->dev, sizeof(*atslave), GFP_KERNEL); + atslave = kzalloc(sizeof(*atslave), GFP_KERNEL); if (!atslave) return NULL; @@ -2000,6 +2006,8 @@ static int at_dma_remove(struct platform_device *pdev) struct resource *io; at_dma_off(atdma); + if (pdev->dev.of_node) + of_dma_controller_free(pdev->dev.of_node); dma_async_device_unregister(&atdma->dma_common); dma_pool_destroy(atdma->memset_pool); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index fad7c62cfc0e..415849bab233 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -969,13 +969,33 @@ bool efi_is_table_address(unsigned long phys_addr) static DEFINE_SPINLOCK(efi_mem_reserve_persistent_lock); static struct linux_efi_memreserve *efi_memreserve_root __ro_after_init; -int efi_mem_reserve_persistent(phys_addr_t addr, u64 size) +static int __init efi_memreserve_map_root(void) +{ + if (efi.mem_reserve == EFI_INVALID_TABLE_ADDR) + return -ENODEV; + + efi_memreserve_root = memremap(efi.mem_reserve, + sizeof(*efi_memreserve_root), + MEMREMAP_WB); + if (WARN_ON_ONCE(!efi_memreserve_root)) + return -ENOMEM; + return 0; +} + +int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) { struct linux_efi_memreserve *rsv; + int rc; - if (!efi_memreserve_root) + if (efi_memreserve_root == (void *)ULONG_MAX) return -ENODEV; + if (!efi_memreserve_root) { + rc = efi_memreserve_map_root(); + if (rc) + return rc; + } + rsv = kmalloc(sizeof(*rsv), GFP_ATOMIC); if (!rsv) return -ENOMEM; @@ -993,14 +1013,10 @@ int efi_mem_reserve_persistent(phys_addr_t addr, u64 size) static int __init efi_memreserve_root_init(void) { - if (efi.mem_reserve == EFI_INVALID_TABLE_ADDR) - return -ENODEV; - - efi_memreserve_root = memremap(efi.mem_reserve, - sizeof(*efi_memreserve_root), - MEMREMAP_WB); - if (!efi_memreserve_root) - return -ENOMEM; + if (efi_memreserve_root) + return 0; + if (efi_memreserve_map_root()) + efi_memreserve_root = (void *)ULONG_MAX; return 0; } early_initcall(efi_memreserve_root_init); diff --git a/drivers/fsi/Kconfig b/drivers/fsi/Kconfig index af3a20dd5aa4..99c99a5d57fe 100644 --- a/drivers/fsi/Kconfig +++ b/drivers/fsi/Kconfig @@ -46,6 +46,7 @@ config FSI_MASTER_AST_CF tristate "FSI master based on Aspeed ColdFire coprocessor" depends on GPIOLIB depends on GPIO_ASPEED + select GENERIC_ALLOCATOR ---help--- This option enables a FSI master using the AST2400 and AST2500 GPIO lines driven by the internal ColdFire coprocessor. This requires diff --git a/drivers/fsi/fsi-scom.c b/drivers/fsi/fsi-scom.c index df94021dd9d1..81dc01ac2351 100644 --- a/drivers/fsi/fsi-scom.c +++ b/drivers/fsi/fsi-scom.c @@ -20,7 +20,6 @@ #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/slab.h> -#include <linux/cdev.h> #include <linux/list.h> #include <uapi/linux/fsi.h> diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 5c1564fcc24e..bdb29e51b417 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -258,7 +258,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) chips->chip.set = davinci_gpio_set; chips->chip.ngpio = ngpio; - chips->chip.base = -1; + chips->chip.base = pdata->no_auto_base ? pdata->base : -1; #ifdef CONFIG_OF_GPIO chips->chip.of_gpio_n_cells = 2; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index dad0e2342df9..0877ff9a9594 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -181,7 +181,7 @@ static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev, if (level == adev->vm_manager.root_level) /* For the root directory */ - return round_up(adev->vm_manager.max_pfn, 1 << shift) >> shift; + return round_up(adev->vm_manager.max_pfn, 1ULL << shift) >> shift; else if (level != AMDGPU_VM_PTB) /* Everything in between */ return 512; @@ -1656,9 +1656,11 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params, if (!amdgpu_vm_pt_descendant(adev, &cursor)) return -ENOENT; continue; - } else if (frag >= parent_shift) { + } else if (frag >= parent_shift && + cursor.level - 1 != adev->vm_manager.root_level) { /* If the fragment size is even larger than the parent - * shift we should go up one level and check it again. + * shift we should go up one level and check it again + * unless one level up is the root level. */ if (!amdgpu_vm_pt_ancestor(&cursor)) return -ENOENT; @@ -1666,10 +1668,10 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params, } /* Looks good so far, calculate parameters for the update */ - incr = AMDGPU_GPU_PAGE_SIZE << shift; + incr = (uint64_t)AMDGPU_GPU_PAGE_SIZE << shift; mask = amdgpu_vm_entries_mask(adev, cursor.level); pe_start = ((cursor.pfn >> shift) & mask) * 8; - entry_end = (mask + 1) << shift; + entry_end = (uint64_t)(mask + 1) << shift; entry_end += cursor.pfn & ~(entry_end - 1); entry_end = min(entry_end, end); @@ -1682,7 +1684,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params, flags | AMDGPU_PTE_FRAG(frag)); pe_start += nptes * 8; - dst += nptes * AMDGPU_GPU_PAGE_SIZE << shift; + dst += (uint64_t)nptes * AMDGPU_GPU_PAGE_SIZE << shift; frag_start = upd_end; if (frag_start >= frag_end) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 6d7baf59d6e1..21363b2b2ee5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -2440,12 +2440,13 @@ static void gfx_v9_0_rlc_start(struct amdgpu_device *adev) #endif WREG32_FIELD15(GC, 0, RLC_CNTL, RLC_ENABLE_F32, 1); + udelay(50); /* carrizo do enable cp interrupt after cp inited */ - if (!(adev->flags & AMD_IS_APU)) + if (!(adev->flags & AMD_IS_APU)) { gfx_v9_0_enable_gui_idle_interrupt(adev, true); - - udelay(50); + udelay(50); + } #ifdef AMDGPU_RLC_DEBUG_RETRY /* RLC_GPM_GENERAL_6 : RLC Ucode version */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index d02c32a1039c..1b0d209d8367 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -342,10 +342,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, master->connector_id); aconnector->mst_encoder = dm_dp_create_fake_mst_encoder(master); + drm_connector_attach_encoder(&aconnector->base, + &aconnector->mst_encoder->base); - /* - * TODO: understand why this one is needed - */ drm_object_attach_property( &connector->base, dev->mode_config.path_property, diff --git a/drivers/gpu/drm/ast/ast_main.c b/drivers/gpu/drm/ast/ast_main.c index dac355812adc..373700c05a00 100644 --- a/drivers/gpu/drm/ast/ast_main.c +++ b/drivers/gpu/drm/ast/ast_main.c @@ -583,7 +583,8 @@ void ast_driver_unload(struct drm_device *dev) drm_mode_config_cleanup(dev); ast_mm_fini(ast); - pci_iounmap(dev->pdev, ast->ioregs); + if (ast->ioregs != ast->regs + AST_IO_MM_OFFSET) + pci_iounmap(dev->pdev, ast->ioregs); pci_iounmap(dev->pdev, ast->regs); kfree(ast); } diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c index 7c6ac3cadb6b..8bb355d5d43d 100644 --- a/drivers/gpu/drm/ast/ast_mode.c +++ b/drivers/gpu/drm/ast/ast_mode.c @@ -973,9 +973,21 @@ static int get_clock(void *i2c_priv) { struct ast_i2c_chan *i2c = i2c_priv; struct ast_private *ast = i2c->dev->dev_private; - uint32_t val; + uint32_t val, val2, count, pass; + + count = 0; + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01; + do { + val2 = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01; + if (val == val2) { + pass++; + } else { + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4) & 0x01; + } + } while ((pass < 5) && (count++ < 0x10000)); - val = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x10) >> 4; return val & 1 ? 1 : 0; } @@ -983,9 +995,21 @@ static int get_data(void *i2c_priv) { struct ast_i2c_chan *i2c = i2c_priv; struct ast_private *ast = i2c->dev->dev_private; - uint32_t val; + uint32_t val, val2, count, pass; + + count = 0; + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01; + do { + val2 = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01; + if (val == val2) { + pass++; + } else { + pass = 0; + val = (ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5) & 0x01; + } + } while ((pass < 5) && (count++ < 0x10000)); - val = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x20) >> 5; return val & 1 ? 1 : 0; } @@ -998,7 +1022,7 @@ static void set_clock(void *i2c_priv, int clock) for (i = 0; i < 0x10000; i++) { ujcrb7 = ((clock & 0x01) ? 0 : 1); - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xfe, ujcrb7); + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xf4, ujcrb7); jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x01); if (ujcrb7 == jtemp) break; @@ -1014,7 +1038,7 @@ static void set_data(void *i2c_priv, int data) for (i = 0; i < 0x10000; i++) { ujcrb7 = ((data & 0x01) ? 0 : 1) << 2; - ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xfb, ujcrb7); + ast_set_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0xf1, ujcrb7); jtemp = ast_get_index_reg_mask(ast, AST_IO_CRTC_PORT, 0xb7, 0x04); if (ujcrb7 == jtemp) break; diff --git a/drivers/gpu/drm/drm_auth.c b/drivers/gpu/drm/drm_auth.c index d9c0f7573905..1669c42c40ed 100644 --- a/drivers/gpu/drm/drm_auth.c +++ b/drivers/gpu/drm/drm_auth.c @@ -142,6 +142,7 @@ static int drm_new_set_master(struct drm_device *dev, struct drm_file *fpriv) lockdep_assert_held_once(&dev->master_mutex); + WARN_ON(fpriv->is_master); old_master = fpriv->master; fpriv->master = drm_master_create(dev); if (!fpriv->master) { @@ -170,6 +171,7 @@ out_err: /* drop references and restore old master on failure */ drm_master_put(&fpriv->master); fpriv->master = old_master; + fpriv->is_master = 0; return ret; } diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index fe754022e356..359d37d5c958 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -61,10 +61,12 @@ static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm) } mutex_lock(&dev_priv->drm.struct_mutex); + mmio_hw_access_pre(dev_priv); ret = i915_gem_gtt_insert(&dev_priv->ggtt.vm, node, size, I915_GTT_PAGE_SIZE, I915_COLOR_UNEVICTABLE, start, end, flags); + mmio_hw_access_post(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); if (ret) gvt_err("fail to alloc %s gm space from host\n", diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 58e166effa45..c7103dd2d8d5 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2447,10 +2447,11 @@ static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) static void intel_vgpu_destroy_ggtt_mm(struct intel_vgpu *vgpu) { - struct intel_gvt_partial_pte *pos; + struct intel_gvt_partial_pte *pos, *next; - list_for_each_entry(pos, - &vgpu->gtt.ggtt_mm->ggtt_mm.partial_pte_list, list) { + list_for_each_entry_safe(pos, next, + &vgpu->gtt.ggtt_mm->ggtt_mm.partial_pte_list, + list) { gvt_dbg_mm("partial PTE update on hold 0x%lx : 0x%llx\n", pos->offset, pos->data); kfree(pos); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 36a5147cd01e..d6e02c15ef97 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -158,6 +158,8 @@ static void load_render_mocs(struct drm_i915_private *dev_priv) int ring_id, i; for (ring_id = 0; ring_id < ARRAY_SIZE(regs); ring_id++) { + if (!HAS_ENGINE(dev_priv, ring_id)) + continue; offset.reg = regs[ring_id]; for (i = 0; i < GEN9_MOCS_SIZE; i++) { gen9_render_mocs.control_table[ring_id][i] = diff --git a/drivers/gpu/drm/meson/meson_crtc.c b/drivers/gpu/drm/meson/meson_crtc.c index 05520202c967..191b314f9e9e 100644 --- a/drivers/gpu/drm/meson/meson_crtc.c +++ b/drivers/gpu/drm/meson/meson_crtc.c @@ -45,6 +45,7 @@ struct meson_crtc { struct drm_crtc base; struct drm_pending_vblank_event *event; struct meson_drm *priv; + bool enabled; }; #define to_meson_crtc(x) container_of(x, struct meson_crtc, base) @@ -80,8 +81,7 @@ static const struct drm_crtc_funcs meson_crtc_funcs = { }; -static void meson_crtc_atomic_enable(struct drm_crtc *crtc, - struct drm_crtc_state *old_state) +static void meson_crtc_enable(struct drm_crtc *crtc) { struct meson_crtc *meson_crtc = to_meson_crtc(crtc); struct drm_crtc_state *crtc_state = crtc->state; @@ -101,6 +101,22 @@ static void meson_crtc_atomic_enable(struct drm_crtc *crtc, writel_bits_relaxed(VPP_POSTBLEND_ENABLE, VPP_POSTBLEND_ENABLE, priv->io_base + _REG(VPP_MISC)); + drm_crtc_vblank_on(crtc); + + meson_crtc->enabled = true; +} + +static void meson_crtc_atomic_enable(struct drm_crtc *crtc, + struct drm_crtc_state *old_state) +{ + struct meson_crtc *meson_crtc = to_meson_crtc(crtc); + struct meson_drm *priv = meson_crtc->priv; + + DRM_DEBUG_DRIVER("\n"); + + if (!meson_crtc->enabled) + meson_crtc_enable(crtc); + priv->viu.osd1_enabled = true; } @@ -110,6 +126,8 @@ static void meson_crtc_atomic_disable(struct drm_crtc *crtc, struct meson_crtc *meson_crtc = to_meson_crtc(crtc); struct meson_drm *priv = meson_crtc->priv; + drm_crtc_vblank_off(crtc); + priv->viu.osd1_enabled = false; priv->viu.osd1_commit = false; @@ -124,6 +142,8 @@ static void meson_crtc_atomic_disable(struct drm_crtc *crtc, crtc->state->event = NULL; } + + meson_crtc->enabled = false; } static void meson_crtc_atomic_begin(struct drm_crtc *crtc, @@ -132,6 +152,9 @@ static void meson_crtc_atomic_begin(struct drm_crtc *crtc, struct meson_crtc *meson_crtc = to_meson_crtc(crtc); unsigned long flags; + if (crtc->state->enable && !meson_crtc->enabled) + meson_crtc_enable(crtc); + if (crtc->state->event) { WARN_ON(drm_crtc_vblank_get(crtc) != 0); diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c index df7247cd93f9..2cb2ad26d716 100644 --- a/drivers/gpu/drm/meson/meson_dw_hdmi.c +++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c @@ -706,6 +706,7 @@ static const struct regmap_config meson_dw_hdmi_regmap_config = { .reg_read = meson_dw_hdmi_reg_read, .reg_write = meson_dw_hdmi_reg_write, .max_register = 0x10000, + .fast_io = true, }; static bool meson_hdmi_connector_is_available(struct device *dev) diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c index acbbad3e322c..be76f3d64bf2 100644 --- a/drivers/gpu/drm/meson/meson_venc.c +++ b/drivers/gpu/drm/meson/meson_venc.c @@ -71,6 +71,7 @@ */ /* HHI Registers */ +#define HHI_GCLK_MPEG2 0x148 /* 0x52 offset in data sheet */ #define HHI_VDAC_CNTL0 0x2F4 /* 0xbd offset in data sheet */ #define HHI_VDAC_CNTL1 0x2F8 /* 0xbe offset in data sheet */ #define HHI_HDMI_PHY_CNTL0 0x3a0 /* 0xe8 offset in data sheet */ @@ -714,6 +715,7 @@ struct meson_hdmi_venc_vic_mode { { 5, &meson_hdmi_encp_mode_1080i60 }, { 20, &meson_hdmi_encp_mode_1080i50 }, { 32, &meson_hdmi_encp_mode_1080p24 }, + { 33, &meson_hdmi_encp_mode_1080p50 }, { 34, &meson_hdmi_encp_mode_1080p30 }, { 31, &meson_hdmi_encp_mode_1080p50 }, { 16, &meson_hdmi_encp_mode_1080p60 }, @@ -1530,10 +1532,12 @@ unsigned int meson_venci_get_field(struct meson_drm *priv) void meson_venc_enable_vsync(struct meson_drm *priv) { writel_relaxed(2, priv->io_base + _REG(VENC_INTCTRL)); + regmap_update_bits(priv->hhi, HHI_GCLK_MPEG2, BIT(25), BIT(25)); } void meson_venc_disable_vsync(struct meson_drm *priv) { + regmap_update_bits(priv->hhi, HHI_GCLK_MPEG2, BIT(25), 0); writel_relaxed(0, priv->io_base + _REG(VENC_INTCTRL)); } diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index 6bcfa527c180..26a0857878bf 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -184,18 +184,18 @@ void meson_viu_set_osd_lut(struct meson_drm *priv, enum viu_lut_sel_e lut_sel, if (lut_sel == VIU_LUT_OSD_OETF) { writel(0, priv->io_base + _REG(addr_port)); - for (i = 0; i < 20; i++) + for (i = 0; i < (OSD_OETF_LUT_SIZE / 2); i++) writel(r_map[i * 2] | (r_map[i * 2 + 1] << 16), priv->io_base + _REG(data_port)); writel(r_map[OSD_OETF_LUT_SIZE - 1] | (g_map[0] << 16), priv->io_base + _REG(data_port)); - for (i = 0; i < 20; i++) + for (i = 0; i < (OSD_OETF_LUT_SIZE / 2); i++) writel(g_map[i * 2 + 1] | (g_map[i * 2 + 2] << 16), priv->io_base + _REG(data_port)); - for (i = 0; i < 20; i++) + for (i = 0; i < (OSD_OETF_LUT_SIZE / 2); i++) writel(b_map[i * 2] | (b_map[i * 2 + 1] << 16), priv->io_base + _REG(data_port)); @@ -211,18 +211,18 @@ void meson_viu_set_osd_lut(struct meson_drm *priv, enum viu_lut_sel_e lut_sel, } else if (lut_sel == VIU_LUT_OSD_EOTF) { writel(0, priv->io_base + _REG(addr_port)); - for (i = 0; i < 20; i++) + for (i = 0; i < (OSD_EOTF_LUT_SIZE / 2); i++) writel(r_map[i * 2] | (r_map[i * 2 + 1] << 16), priv->io_base + _REG(data_port)); writel(r_map[OSD_EOTF_LUT_SIZE - 1] | (g_map[0] << 16), priv->io_base + _REG(data_port)); - for (i = 0; i < 20; i++) + for (i = 0; i < (OSD_EOTF_LUT_SIZE / 2); i++) writel(g_map[i * 2 + 1] | (g_map[i * 2 + 2] << 16), priv->io_base + _REG(data_port)); - for (i = 0; i < 20; i++) + for (i = 0; i < (OSD_EOTF_LUT_SIZE / 2); i++) writel(b_map[i * 2] | (b_map[i * 2 + 1] << 16), priv->io_base + _REG(data_port)); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_group.c b/drivers/gpu/drm/rcar-du/rcar_du_group.c index d85f0a1c1581..cebf313c6e1f 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_group.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_group.c @@ -202,10 +202,25 @@ void rcar_du_group_put(struct rcar_du_group *rgrp) static void __rcar_du_group_start_stop(struct rcar_du_group *rgrp, bool start) { - struct rcar_du_crtc *rcrtc = &rgrp->dev->crtcs[rgrp->index * 2]; + struct rcar_du_device *rcdu = rgrp->dev; + + /* + * Group start/stop is controlled by the DRES and DEN bits of DSYSR0 + * for the first group and DSYSR2 for the second group. On most DU + * instances, this maps to the first CRTC of the group, and we can just + * use rcar_du_crtc_dsysr_clr_set() to access the correct DSYSR. On + * M3-N, however, DU2 doesn't exist, but DSYSR2 does. We thus need to + * access the register directly using group read/write. + */ + if (rcdu->info->channels_mask & BIT(rgrp->index * 2)) { + struct rcar_du_crtc *rcrtc = &rgrp->dev->crtcs[rgrp->index * 2]; - rcar_du_crtc_dsysr_clr_set(rcrtc, DSYSR_DRES | DSYSR_DEN, - start ? DSYSR_DEN : DSYSR_DRES); + rcar_du_crtc_dsysr_clr_set(rcrtc, DSYSR_DRES | DSYSR_DEN, + start ? DSYSR_DEN : DSYSR_DRES); + } else { + rcar_du_group_write(rgrp, DSYSR, + start ? DSYSR_DEN : DSYSR_DRES); + } } void rcar_du_group_start_stop(struct rcar_du_group *rgrp, bool start) diff --git a/drivers/hid/hid-sensor-custom.c b/drivers/hid/hid-sensor-custom.c index e8a114157f87..bb012bc032e0 100644 --- a/drivers/hid/hid-sensor-custom.c +++ b/drivers/hid/hid-sensor-custom.c @@ -358,7 +358,7 @@ static ssize_t show_value(struct device *dev, struct device_attribute *attr, sensor_inst->hsdev, sensor_inst->hsdev->usage, usage, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, false); } else if (!strncmp(name, "units", strlen("units"))) value = sensor_inst->fields[field_index].attribute.units; else if (!strncmp(name, "unit-expo", strlen("unit-expo"))) diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 2b63487057c2..4256fdc5cd6d 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -299,7 +299,8 @@ EXPORT_SYMBOL_GPL(sensor_hub_get_feature); int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag) + enum sensor_hub_read_flags flag, + bool is_signed) { struct sensor_hub_data *data = hid_get_drvdata(hsdev->hdev); unsigned long flags; @@ -331,10 +332,16 @@ int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, &hsdev->pending.ready, HZ*5); switch (hsdev->pending.raw_size) { case 1: - ret_val = *(u8 *)hsdev->pending.raw_data; + if (is_signed) + ret_val = *(s8 *)hsdev->pending.raw_data; + else + ret_val = *(u8 *)hsdev->pending.raw_data; break; case 2: - ret_val = *(u16 *)hsdev->pending.raw_data; + if (is_signed) + ret_val = *(s16 *)hsdev->pending.raw_data; + else + ret_val = *(u16 *)hsdev->pending.raw_data; break; case 4: ret_val = *(u32 *)hsdev->pending.raw_data; diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index f96a77b18bb9..ce0ba2062723 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -516,6 +516,14 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, } wait_for_completion(&msginfo->waitevent); + if (msginfo->response.gpadl_created.creation_status != 0) { + pr_err("Failed to establish GPADL: err = 0x%x\n", + msginfo->response.gpadl_created.creation_status); + + ret = -EDQUOT; + goto cleanup; + } + if (channel->rescind) { ret = -ENODEV; goto cleanup; diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index 71d3445ba869..07ee19573b3f 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -274,7 +274,7 @@ static int ina2xx_get_value(struct ina2xx_data *data, u8 reg, break; case INA2XX_CURRENT: /* signed register, result in mA */ - val = regval * data->current_lsb_uA; + val = (s16)regval * data->current_lsb_uA; val = DIV_ROUND_CLOSEST(val, 1000); break; case INA2XX_CALIBRATION: @@ -491,7 +491,7 @@ static int ina2xx_probe(struct i2c_client *client, } data->groups[group++] = &ina2xx_group; - if (id->driver_data == ina226) + if (chip == ina226) data->groups[group++] = &ina226_group; hwmon_dev = devm_hwmon_device_register_with_groups(dev, client->name, @@ -500,7 +500,7 @@ static int ina2xx_probe(struct i2c_client *client, return PTR_ERR(hwmon_dev); dev_info(dev, "power monitor %s (Rshunt = %li uOhm)\n", - id->name, data->rshunt); + client->name, data->rshunt); return 0; } diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c index de46577c7d5a..d8fa4bea4bc8 100644 --- a/drivers/hwmon/mlxreg-fan.c +++ b/drivers/hwmon/mlxreg-fan.c @@ -51,7 +51,7 @@ */ #define MLXREG_FAN_GET_RPM(rval, d, s) (DIV_ROUND_CLOSEST(15000000 * 100, \ ((rval) + (s)) * (d))) -#define MLXREG_FAN_GET_FAULT(val, mask) (!!((val) ^ (mask))) +#define MLXREG_FAN_GET_FAULT(val, mask) (!((val) ^ (mask))) #define MLXREG_FAN_PWM_DUTY2STATE(duty) (DIV_ROUND_CLOSEST((duty) * \ MLXREG_FAN_MAX_STATE, \ MLXREG_FAN_MAX_DUTY)) diff --git a/drivers/hwmon/raspberrypi-hwmon.c b/drivers/hwmon/raspberrypi-hwmon.c index be5ba4690895..0d0457245e7d 100644 --- a/drivers/hwmon/raspberrypi-hwmon.c +++ b/drivers/hwmon/raspberrypi-hwmon.c @@ -115,7 +115,6 @@ static int rpi_hwmon_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct rpi_hwmon_data *data; - int ret; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) @@ -124,11 +123,6 @@ static int rpi_hwmon_probe(struct platform_device *pdev) /* Parent driver assure that firmware is correct */ data->fw = dev_get_drvdata(dev->parent); - /* Init throttled */ - ret = rpi_firmware_property(data->fw, RPI_FIRMWARE_GET_THROTTLED, - &data->last_throttled, - sizeof(data->last_throttled)); - data->hwmon_dev = devm_hwmon_device_register_with_info(dev, "rpi_volt", data, &rpi_chip_info, diff --git a/drivers/hwmon/w83795.c b/drivers/hwmon/w83795.c index 49276bbdac3d..1bb80f992aa8 100644 --- a/drivers/hwmon/w83795.c +++ b/drivers/hwmon/w83795.c @@ -1691,7 +1691,7 @@ store_sf_setup(struct device *dev, struct device_attribute *attr, * somewhere else in the code */ #define SENSOR_ATTR_TEMP(index) { \ - SENSOR_ATTR_2(temp##index##_type, S_IRUGO | (index < 4 ? S_IWUSR : 0), \ + SENSOR_ATTR_2(temp##index##_type, S_IRUGO | (index < 5 ? S_IWUSR : 0), \ show_temp_mode, store_temp_mode, NOT_USED, index - 1), \ SENSOR_ATTR_2(temp##index##_input, S_IRUGO, show_temp, \ NULL, TEMP_READ, index - 1), \ diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index 41d97faf5013..38ff374a3ca4 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -149,6 +149,7 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; struct hid_sensor_hub_device *hsdev = accel_state->common_attributes.hsdev; @@ -158,12 +159,14 @@ static int accel_3d_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&accel_state->common_attributes, true); report_id = accel_state->accel[chan->scan_index].report_id; + min = accel_state->accel[chan->scan_index].logical_minimum; address = accel_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( accel_state->common_attributes.hsdev, hsdev->usage, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state(&accel_state->common_attributes, diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c index 36941e69f959..88e857c4baf4 100644 --- a/drivers/iio/gyro/hid-sensor-gyro-3d.c +++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c @@ -111,6 +111,7 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -118,13 +119,15 @@ static int gyro_3d_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&gyro_state->common_attributes, true); report_id = gyro_state->gyro[chan->scan_index].report_id; + min = gyro_state->gyro[chan->scan_index].logical_minimum; address = gyro_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( gyro_state->common_attributes.hsdev, HID_USAGE_SENSOR_GYRO_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state(&gyro_state->common_attributes, diff --git a/drivers/iio/humidity/hid-sensor-humidity.c b/drivers/iio/humidity/hid-sensor-humidity.c index beab6d6fd6e1..4bc95f31c730 100644 --- a/drivers/iio/humidity/hid-sensor-humidity.c +++ b/drivers/iio/humidity/hid-sensor-humidity.c @@ -75,7 +75,8 @@ static int humidity_read_raw(struct iio_dev *indio_dev, HID_USAGE_SENSOR_HUMIDITY, HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY, humid_st->humidity_attr.report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + humid_st->humidity_attr.logical_minimum < 0); hid_sensor_power_state(&humid_st->common_attributes, false); return IIO_VAL_INT; diff --git a/drivers/iio/light/hid-sensor-als.c b/drivers/iio/light/hid-sensor-als.c index 406caaee9a3c..94f33250ba5a 100644 --- a/drivers/iio/light/hid-sensor-als.c +++ b/drivers/iio/light/hid-sensor-als.c @@ -93,6 +93,7 @@ static int als_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -102,8 +103,8 @@ static int als_read_raw(struct iio_dev *indio_dev, case CHANNEL_SCAN_INDEX_INTENSITY: case CHANNEL_SCAN_INDEX_ILLUM: report_id = als_state->als_illum.report_id; - address = - HID_USAGE_SENSOR_LIGHT_ILLUM; + min = als_state->als_illum.logical_minimum; + address = HID_USAGE_SENSOR_LIGHT_ILLUM; break; default: report_id = -1; @@ -116,7 +117,8 @@ static int als_read_raw(struct iio_dev *indio_dev, als_state->common_attributes.hsdev, HID_USAGE_SENSOR_ALS, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&als_state->common_attributes, false); } else { diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c index 45107f7537b5..cf5a0c242609 100644 --- a/drivers/iio/light/hid-sensor-prox.c +++ b/drivers/iio/light/hid-sensor-prox.c @@ -73,6 +73,7 @@ static int prox_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -81,8 +82,8 @@ static int prox_read_raw(struct iio_dev *indio_dev, switch (chan->scan_index) { case CHANNEL_SCAN_INDEX_PRESENCE: report_id = prox_state->prox_attr.report_id; - address = - HID_USAGE_SENSOR_HUMAN_PRESENCE; + min = prox_state->prox_attr.logical_minimum; + address = HID_USAGE_SENSOR_HUMAN_PRESENCE; break; default: report_id = -1; @@ -95,7 +96,8 @@ static int prox_read_raw(struct iio_dev *indio_dev, prox_state->common_attributes.hsdev, HID_USAGE_SENSOR_PROX, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&prox_state->common_attributes, false); } else { diff --git a/drivers/iio/magnetometer/hid-sensor-magn-3d.c b/drivers/iio/magnetometer/hid-sensor-magn-3d.c index d55c4885211a..f3c0d41e5a8c 100644 --- a/drivers/iio/magnetometer/hid-sensor-magn-3d.c +++ b/drivers/iio/magnetometer/hid-sensor-magn-3d.c @@ -163,21 +163,23 @@ static int magn_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; switch (mask) { case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&magn_state->magn_flux_attributes, true); - report_id = - magn_state->magn[chan->address].report_id; + report_id = magn_state->magn[chan->address].report_id; + min = magn_state->magn[chan->address].logical_minimum; address = magn_3d_addresses[chan->address]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( magn_state->magn_flux_attributes.hsdev, HID_USAGE_SENSOR_COMPASS_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { *val = 0; hid_sensor_power_state( diff --git a/drivers/iio/magnetometer/st_magn_buffer.c b/drivers/iio/magnetometer/st_magn_buffer.c index 0a9e8fadfa9d..37ab30566464 100644 --- a/drivers/iio/magnetometer/st_magn_buffer.c +++ b/drivers/iio/magnetometer/st_magn_buffer.c @@ -30,11 +30,6 @@ int st_magn_trig_set_state(struct iio_trigger *trig, bool state) return st_sensors_set_dataready_irq(indio_dev, state); } -static int st_magn_buffer_preenable(struct iio_dev *indio_dev) -{ - return st_sensors_set_enable(indio_dev, true); -} - static int st_magn_buffer_postenable(struct iio_dev *indio_dev) { int err; @@ -50,7 +45,7 @@ static int st_magn_buffer_postenable(struct iio_dev *indio_dev) if (err < 0) goto st_magn_buffer_postenable_error; - return err; + return st_sensors_set_enable(indio_dev, true); st_magn_buffer_postenable_error: kfree(mdata->buffer_data); @@ -63,11 +58,11 @@ static int st_magn_buffer_predisable(struct iio_dev *indio_dev) int err; struct st_sensor_data *mdata = iio_priv(indio_dev); - err = iio_triggered_buffer_predisable(indio_dev); + err = st_sensors_set_enable(indio_dev, false); if (err < 0) goto st_magn_buffer_predisable_error; - err = st_sensors_set_enable(indio_dev, false); + err = iio_triggered_buffer_predisable(indio_dev); st_magn_buffer_predisable_error: kfree(mdata->buffer_data); @@ -75,7 +70,6 @@ st_magn_buffer_predisable_error: } static const struct iio_buffer_setup_ops st_magn_buffer_setup_ops = { - .preenable = &st_magn_buffer_preenable, .postenable = &st_magn_buffer_postenable, .predisable = &st_magn_buffer_predisable, }; diff --git a/drivers/iio/orientation/hid-sensor-incl-3d.c b/drivers/iio/orientation/hid-sensor-incl-3d.c index 1e5451d1ff88..bdc5e4554ee4 100644 --- a/drivers/iio/orientation/hid-sensor-incl-3d.c +++ b/drivers/iio/orientation/hid-sensor-incl-3d.c @@ -111,21 +111,23 @@ static int incl_3d_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; switch (mask) { case IIO_CHAN_INFO_RAW: hid_sensor_power_state(&incl_state->common_attributes, true); - report_id = - incl_state->incl[chan->scan_index].report_id; + report_id = incl_state->incl[chan->scan_index].report_id; + min = incl_state->incl[chan->scan_index].logical_minimum; address = incl_3d_addresses[chan->scan_index]; if (report_id >= 0) *val = sensor_hub_input_attr_get_raw_value( incl_state->common_attributes.hsdev, HID_USAGE_SENSOR_INCLINOMETER_3D, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); else { hid_sensor_power_state(&incl_state->common_attributes, false); diff --git a/drivers/iio/pressure/hid-sensor-press.c b/drivers/iio/pressure/hid-sensor-press.c index 4c437918f1d2..d7b1c00ceb4d 100644 --- a/drivers/iio/pressure/hid-sensor-press.c +++ b/drivers/iio/pressure/hid-sensor-press.c @@ -77,6 +77,7 @@ static int press_read_raw(struct iio_dev *indio_dev, int report_id = -1; u32 address; int ret_type; + s32 min; *val = 0; *val2 = 0; @@ -85,8 +86,8 @@ static int press_read_raw(struct iio_dev *indio_dev, switch (chan->scan_index) { case CHANNEL_SCAN_INDEX_PRESSURE: report_id = press_state->press_attr.report_id; - address = - HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE; + min = press_state->press_attr.logical_minimum; + address = HID_USAGE_SENSOR_ATMOSPHERIC_PRESSURE; break; default: report_id = -1; @@ -99,7 +100,8 @@ static int press_read_raw(struct iio_dev *indio_dev, press_state->common_attributes.hsdev, HID_USAGE_SENSOR_PRESSURE, address, report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + min < 0); hid_sensor_power_state(&press_state->common_attributes, false); } else { diff --git a/drivers/iio/temperature/hid-sensor-temperature.c b/drivers/iio/temperature/hid-sensor-temperature.c index beaf6fd3e337..b592fc4f007e 100644 --- a/drivers/iio/temperature/hid-sensor-temperature.c +++ b/drivers/iio/temperature/hid-sensor-temperature.c @@ -76,7 +76,8 @@ static int temperature_read_raw(struct iio_dev *indio_dev, HID_USAGE_SENSOR_TEMPERATURE, HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE, temp_st->temperature_attr.report_id, - SENSOR_HUB_SYNC); + SENSOR_HUB_SYNC, + temp_st->temperature_attr.logical_minimum < 0); hid_sensor_power_state( &temp_st->common_attributes, false); diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index ee366199b169..25d43c8f1c2a 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -767,8 +767,10 @@ static int netdevice_event(struct notifier_block *this, unsigned long event, case NETDEV_CHANGEADDR: cmds[0] = netdev_del_cmd; - cmds[1] = add_default_gid_cmd; - cmds[2] = add_cmd; + if (ndev->reg_state == NETREG_REGISTERED) { + cmds[1] = add_default_gid_cmd; + cmds[2] = add_cmd; + } break; case NETDEV_CHANGEUPPER: diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 2b4c5e7dd5a1..676c1fd1119d 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -137,15 +137,6 @@ static void ib_umem_notifier_release(struct mmu_notifier *mn, up_read(&per_mm->umem_rwsem); } -static int invalidate_page_trampoline(struct ib_umem_odp *item, u64 start, - u64 end, void *cookie) -{ - ib_umem_notifier_start_account(item); - item->umem.context->invalidate_range(item, start, start + PAGE_SIZE); - ib_umem_notifier_end_account(item); - return 0; -} - static int invalidate_range_start_trampoline(struct ib_umem_odp *item, u64 start, u64 end, void *cookie) { @@ -553,12 +544,13 @@ out: put_page(page); if (remove_existing_mapping && umem->context->invalidate_range) { - invalidate_page_trampoline( + ib_umem_notifier_start_account(umem_odp); + umem->context->invalidate_range( umem_odp, - ib_umem_start(umem) + (page_index >> umem->page_shift), - ib_umem_start(umem) + ((page_index + 1) >> - umem->page_shift), - NULL); + ib_umem_start(umem) + (page_index << umem->page_shift), + ib_umem_start(umem) + + ((page_index + 1) << umem->page_shift)); + ib_umem_notifier_end_account(umem_odp); ret = -EAGAIN; } diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index cf2282654210..77f095e5fbe3 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -1268,6 +1268,7 @@ static int bnxt_re_ib_reg(struct bnxt_re_dev *rdev) /* Registered a new RoCE device instance to netdev */ rc = bnxt_re_register_netdev(rdev); if (rc) { + rtnl_unlock(); pr_err("Failed to register with netedev: %#x\n", rc); return -EINVAL; } @@ -1466,6 +1467,7 @@ static void bnxt_re_task(struct work_struct *work) "Failed to register with IB: %#x", rc); bnxt_re_remove_one(rdev); bnxt_re_dev_unreg(rdev); + goto exit; } break; case NETDEV_UP: @@ -1489,6 +1491,7 @@ static void bnxt_re_task(struct work_struct *work) } smp_mb__before_atomic(); atomic_dec(&rdev->sched_count); +exit: kfree(re_work); } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index a4c62ae23a9a..3beb1523e17c 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1756,10 +1756,9 @@ static int hns_roce_v2_set_mac(struct hns_roce_dev *hr_dev, u8 phy_port, return hns_roce_cmq_send(hr_dev, &desc, 1); } -static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, - unsigned long mtpt_idx) +static int set_mtpt_pbl(struct hns_roce_v2_mpt_entry *mpt_entry, + struct hns_roce_mr *mr) { - struct hns_roce_v2_mpt_entry *mpt_entry; struct scatterlist *sg; u64 page_addr; u64 *pages; @@ -1767,6 +1766,53 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, int len; int entry; + mpt_entry->pbl_size = cpu_to_le32(mr->pbl_size); + mpt_entry->pbl_ba_l = cpu_to_le32(lower_32_bits(mr->pbl_ba >> 3)); + roce_set_field(mpt_entry->byte_48_mode_ba, + V2_MPT_BYTE_48_PBL_BA_H_M, V2_MPT_BYTE_48_PBL_BA_H_S, + upper_32_bits(mr->pbl_ba >> 3)); + + pages = (u64 *)__get_free_page(GFP_KERNEL); + if (!pages) + return -ENOMEM; + + i = 0; + for_each_sg(mr->umem->sg_head.sgl, sg, mr->umem->nmap, entry) { + len = sg_dma_len(sg) >> PAGE_SHIFT; + for (j = 0; j < len; ++j) { + page_addr = sg_dma_address(sg) + + (j << mr->umem->page_shift); + pages[i] = page_addr >> 6; + /* Record the first 2 entry directly to MTPT table */ + if (i >= HNS_ROCE_V2_MAX_INNER_MTPT_NUM - 1) + goto found; + i++; + } + } +found: + mpt_entry->pa0_l = cpu_to_le32(lower_32_bits(pages[0])); + roce_set_field(mpt_entry->byte_56_pa0_h, V2_MPT_BYTE_56_PA0_H_M, + V2_MPT_BYTE_56_PA0_H_S, upper_32_bits(pages[0])); + + mpt_entry->pa1_l = cpu_to_le32(lower_32_bits(pages[1])); + roce_set_field(mpt_entry->byte_64_buf_pa1, V2_MPT_BYTE_64_PA1_H_M, + V2_MPT_BYTE_64_PA1_H_S, upper_32_bits(pages[1])); + roce_set_field(mpt_entry->byte_64_buf_pa1, + V2_MPT_BYTE_64_PBL_BUF_PG_SZ_M, + V2_MPT_BYTE_64_PBL_BUF_PG_SZ_S, + mr->pbl_buf_pg_sz + PG_SHIFT_OFFSET); + + free_page((unsigned long)pages); + + return 0; +} + +static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, + unsigned long mtpt_idx) +{ + struct hns_roce_v2_mpt_entry *mpt_entry; + int ret; + mpt_entry = mb_buf; memset(mpt_entry, 0, sizeof(*mpt_entry)); @@ -1781,7 +1827,6 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, mr->pbl_ba_pg_sz + PG_SHIFT_OFFSET); roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PD_M, V2_MPT_BYTE_4_PD_S, mr->pd); - mpt_entry->byte_4_pd_hop_st = cpu_to_le32(mpt_entry->byte_4_pd_hop_st); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RA_EN_S, 0); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_R_INV_EN_S, 1); @@ -1796,13 +1841,11 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, (mr->access & IB_ACCESS_REMOTE_WRITE ? 1 : 0)); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, (mr->access & IB_ACCESS_LOCAL_WRITE ? 1 : 0)); - mpt_entry->byte_8_mw_cnt_en = cpu_to_le32(mpt_entry->byte_8_mw_cnt_en); roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_PA_S, mr->type == MR_TYPE_MR ? 0 : 1); roce_set_bit(mpt_entry->byte_12_mw_pa, V2_MPT_BYTE_12_INNER_PA_VLD_S, 1); - mpt_entry->byte_12_mw_pa = cpu_to_le32(mpt_entry->byte_12_mw_pa); mpt_entry->len_l = cpu_to_le32(lower_32_bits(mr->size)); mpt_entry->len_h = cpu_to_le32(upper_32_bits(mr->size)); @@ -1813,53 +1856,9 @@ static int hns_roce_v2_write_mtpt(void *mb_buf, struct hns_roce_mr *mr, if (mr->type == MR_TYPE_DMA) return 0; - mpt_entry->pbl_size = cpu_to_le32(mr->pbl_size); - - mpt_entry->pbl_ba_l = cpu_to_le32(lower_32_bits(mr->pbl_ba >> 3)); - roce_set_field(mpt_entry->byte_48_mode_ba, V2_MPT_BYTE_48_PBL_BA_H_M, - V2_MPT_BYTE_48_PBL_BA_H_S, - upper_32_bits(mr->pbl_ba >> 3)); - mpt_entry->byte_48_mode_ba = cpu_to_le32(mpt_entry->byte_48_mode_ba); - - pages = (u64 *)__get_free_page(GFP_KERNEL); - if (!pages) - return -ENOMEM; - - i = 0; - for_each_sg(mr->umem->sg_head.sgl, sg, mr->umem->nmap, entry) { - len = sg_dma_len(sg) >> PAGE_SHIFT; - for (j = 0; j < len; ++j) { - page_addr = sg_dma_address(sg) + - (j << mr->umem->page_shift); - pages[i] = page_addr >> 6; - - /* Record the first 2 entry directly to MTPT table */ - if (i >= HNS_ROCE_V2_MAX_INNER_MTPT_NUM - 1) - goto found; - i++; - } - } - -found: - mpt_entry->pa0_l = cpu_to_le32(lower_32_bits(pages[0])); - roce_set_field(mpt_entry->byte_56_pa0_h, V2_MPT_BYTE_56_PA0_H_M, - V2_MPT_BYTE_56_PA0_H_S, - upper_32_bits(pages[0])); - mpt_entry->byte_56_pa0_h = cpu_to_le32(mpt_entry->byte_56_pa0_h); - - mpt_entry->pa1_l = cpu_to_le32(lower_32_bits(pages[1])); - roce_set_field(mpt_entry->byte_64_buf_pa1, V2_MPT_BYTE_64_PA1_H_M, - V2_MPT_BYTE_64_PA1_H_S, upper_32_bits(pages[1])); + ret = set_mtpt_pbl(mpt_entry, mr); - free_page((unsigned long)pages); - - roce_set_field(mpt_entry->byte_64_buf_pa1, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_M, - V2_MPT_BYTE_64_PBL_BUF_PG_SZ_S, - mr->pbl_buf_pg_sz + PG_SHIFT_OFFSET); - mpt_entry->byte_64_buf_pa1 = cpu_to_le32(mpt_entry->byte_64_buf_pa1); - - return 0; + return ret; } static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev, @@ -1868,6 +1867,7 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev, u64 size, void *mb_buf) { struct hns_roce_v2_mpt_entry *mpt_entry = mb_buf; + int ret = 0; if (flags & IB_MR_REREG_PD) { roce_set_field(mpt_entry->byte_4_pd_hop_st, V2_MPT_BYTE_4_PD_M, @@ -1880,14 +1880,14 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev, V2_MPT_BYTE_8_BIND_EN_S, (mr_access_flags & IB_ACCESS_MW_BIND ? 1 : 0)); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, - V2_MPT_BYTE_8_ATOMIC_EN_S, - (mr_access_flags & IB_ACCESS_REMOTE_ATOMIC ? 1 : 0)); + V2_MPT_BYTE_8_ATOMIC_EN_S, + mr_access_flags & IB_ACCESS_REMOTE_ATOMIC ? 1 : 0); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RR_EN_S, - (mr_access_flags & IB_ACCESS_REMOTE_READ ? 1 : 0)); + mr_access_flags & IB_ACCESS_REMOTE_READ ? 1 : 0); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_RW_EN_S, - (mr_access_flags & IB_ACCESS_REMOTE_WRITE ? 1 : 0)); + mr_access_flags & IB_ACCESS_REMOTE_WRITE ? 1 : 0); roce_set_bit(mpt_entry->byte_8_mw_cnt_en, V2_MPT_BYTE_8_LW_EN_S, - (mr_access_flags & IB_ACCESS_LOCAL_WRITE ? 1 : 0)); + mr_access_flags & IB_ACCESS_LOCAL_WRITE ? 1 : 0); } if (flags & IB_MR_REREG_TRANS) { @@ -1896,21 +1896,13 @@ static int hns_roce_v2_rereg_write_mtpt(struct hns_roce_dev *hr_dev, mpt_entry->len_l = cpu_to_le32(lower_32_bits(size)); mpt_entry->len_h = cpu_to_le32(upper_32_bits(size)); - mpt_entry->pbl_size = cpu_to_le32(mr->pbl_size); - mpt_entry->pbl_ba_l = - cpu_to_le32(lower_32_bits(mr->pbl_ba >> 3)); - roce_set_field(mpt_entry->byte_48_mode_ba, - V2_MPT_BYTE_48_PBL_BA_H_M, - V2_MPT_BYTE_48_PBL_BA_H_S, - upper_32_bits(mr->pbl_ba >> 3)); - mpt_entry->byte_48_mode_ba = - cpu_to_le32(mpt_entry->byte_48_mode_ba); - mr->iova = iova; mr->size = size; + + ret = set_mtpt_pbl(mpt_entry, mr); } - return 0; + return ret; } static int hns_roce_v2_frmr_write_mtpt(void *mb_buf, struct hns_roce_mr *mr) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index e9c428071df3..3569fda07e07 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1094,31 +1094,26 @@ enum mlx5_ib_width { MLX5_IB_WIDTH_12X = 1 << 4 }; -static int translate_active_width(struct ib_device *ibdev, u8 active_width, +static void translate_active_width(struct ib_device *ibdev, u8 active_width, u8 *ib_width) { struct mlx5_ib_dev *dev = to_mdev(ibdev); - int err = 0; - if (active_width & MLX5_IB_WIDTH_1X) { + if (active_width & MLX5_IB_WIDTH_1X) *ib_width = IB_WIDTH_1X; - } else if (active_width & MLX5_IB_WIDTH_2X) { - mlx5_ib_dbg(dev, "active_width %d is not supported by IB spec\n", - (int)active_width); - err = -EINVAL; - } else if (active_width & MLX5_IB_WIDTH_4X) { + else if (active_width & MLX5_IB_WIDTH_4X) *ib_width = IB_WIDTH_4X; - } else if (active_width & MLX5_IB_WIDTH_8X) { + else if (active_width & MLX5_IB_WIDTH_8X) *ib_width = IB_WIDTH_8X; - } else if (active_width & MLX5_IB_WIDTH_12X) { + else if (active_width & MLX5_IB_WIDTH_12X) *ib_width = IB_WIDTH_12X; - } else { - mlx5_ib_dbg(dev, "Invalid active_width %d\n", + else { + mlx5_ib_dbg(dev, "Invalid active_width %d, setting width to default value: 4x\n", (int)active_width); - err = -EINVAL; + *ib_width = IB_WIDTH_4X; } - return err; + return; } static int mlx5_mtu_to_ib_mtu(int mtu) @@ -1225,10 +1220,8 @@ static int mlx5_query_hca_port(struct ib_device *ibdev, u8 port, if (err) goto out; - err = translate_active_width(ibdev, ib_link_width_oper, - &props->active_width); - if (err) - goto out; + translate_active_width(ibdev, ib_link_width_oper, &props->active_width); + err = mlx5_query_port_ib_proto_oper(mdev, &props->active_speed, port); if (err) goto out; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index b04eb6775326..2cc3d69ab6f6 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -674,6 +674,15 @@ next_mr: goto srcu_unlock; } + if (!mr->umem->is_odp) { + mlx5_ib_dbg(dev, "skipping non ODP MR (lkey=0x%06x) in page fault handler.\n", + key); + if (bytes_mapped) + *bytes_mapped += bcnt; + ret = 0; + goto srcu_unlock; + } + ret = pagefault_mr(dev, mr, io_virt, bcnt, bytes_mapped); if (ret < 0) goto srcu_unlock; @@ -735,6 +744,7 @@ next_mr: head = frame; bcnt -= frame->bcnt; + offset = 0; } break; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 6841c0f9237f..3747cc681b18 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -2633,8 +2633,7 @@ static int to_mlx5_access_flags(struct mlx5_ib_qp *qp, if (access_flags & IB_ACCESS_REMOTE_READ) *hw_access_flags |= MLX5_QP_BIT_RRE; - if ((access_flags & IB_ACCESS_REMOTE_ATOMIC) && - qp->ibqp.qp_type == IB_QPT_RC) { + if (access_flags & IB_ACCESS_REMOTE_ATOMIC) { int atomic_mode; atomic_mode = get_atomic_mode(dev, qp->ibqp.qp_type); @@ -4678,17 +4677,18 @@ static int _mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, goto out; } - if (wr->opcode == IB_WR_LOCAL_INV || - wr->opcode == IB_WR_REG_MR) { + if (wr->opcode == IB_WR_REG_MR) { fence = dev->umr_fence; next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL; - } else if (wr->send_flags & IB_SEND_FENCE) { - if (qp->next_fence) - fence = MLX5_FENCE_MODE_SMALL_AND_FENCE; - else - fence = MLX5_FENCE_MODE_FENCE; - } else { - fence = qp->next_fence; + } else { + if (wr->send_flags & IB_SEND_FENCE) { + if (qp->next_fence) + fence = MLX5_FENCE_MODE_SMALL_AND_FENCE; + else + fence = MLX5_FENCE_MODE_FENCE; + } else { + fence = qp->next_fence; + } } switch (ibqp->qp_type) { diff --git a/drivers/infiniband/sw/rdmavt/ah.c b/drivers/infiniband/sw/rdmavt/ah.c index 89ec0f64abfc..084bb4baebb5 100644 --- a/drivers/infiniband/sw/rdmavt/ah.c +++ b/drivers/infiniband/sw/rdmavt/ah.c @@ -91,13 +91,15 @@ EXPORT_SYMBOL(rvt_check_ah); * rvt_create_ah - create an address handle * @pd: the protection domain * @ah_attr: the attributes of the AH + * @udata: pointer to user's input output buffer information. * * This may be called from interrupt context. * * Return: newly allocated ah */ struct ib_ah *rvt_create_ah(struct ib_pd *pd, - struct rdma_ah_attr *ah_attr) + struct rdma_ah_attr *ah_attr, + struct ib_udata *udata) { struct rvt_ah *ah; struct rvt_dev_info *dev = ib_to_rvt(pd->device); diff --git a/drivers/infiniband/sw/rdmavt/ah.h b/drivers/infiniband/sw/rdmavt/ah.h index 16105af99189..25271b48a683 100644 --- a/drivers/infiniband/sw/rdmavt/ah.h +++ b/drivers/infiniband/sw/rdmavt/ah.h @@ -51,7 +51,8 @@ #include <rdma/rdma_vt.h> struct ib_ah *rvt_create_ah(struct ib_pd *pd, - struct rdma_ah_attr *ah_attr); + struct rdma_ah_attr *ah_attr, + struct ib_udata *udata); int rvt_destroy_ah(struct ib_ah *ibah); int rvt_modify_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); int rvt_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index 946b623ba5eb..4ff3d98fa6a4 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -1124,7 +1124,9 @@ u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task, IB_MR_CHECK_SIG_STATUS, &mr_status); if (ret) { pr_err("ib_check_mr_status failed, ret %d\n", ret); - goto err; + /* Not a lot we can do, return ambiguous guard error */ + *sector = 0; + return 0x1; } if (mr_status.fail_status & IB_MR_CHECK_SIG_STATUS) { @@ -1152,9 +1154,6 @@ u8 iser_check_task_pi_status(struct iscsi_iser_task *iser_task, } return 0; -err: - /* Not alot we can do here, return ambiguous guard error */ - return 0x1; } void iser_err_comp(struct ib_wc *wc, const char *type) diff --git a/drivers/misc/mic/scif/scif_rma.c b/drivers/misc/mic/scif/scif_rma.c index c824329f7012..0e4193cb08cf 100644 --- a/drivers/misc/mic/scif/scif_rma.c +++ b/drivers/misc/mic/scif/scif_rma.c @@ -416,7 +416,7 @@ static int scif_create_remote_lookup(struct scif_dev *remote_dev, if (err) goto error_window; err = scif_map_page(&window->num_pages_lookup.lookup[j], - vmalloc_dma_phys ? + vmalloc_num_pages ? vmalloc_to_page(&window->num_pages[i]) : virt_to_page(&window->num_pages[i]), remote_dev); diff --git a/drivers/mtd/nand/bbt.c b/drivers/mtd/nand/bbt.c index 56cde38b92c0..044adf913854 100644 --- a/drivers/mtd/nand/bbt.c +++ b/drivers/mtd/nand/bbt.c @@ -27,7 +27,8 @@ int nanddev_bbt_init(struct nand_device *nand) unsigned int nwords = DIV_ROUND_UP(nblocks * bits_per_block, BITS_PER_LONG); - nand->bbt.cache = kzalloc(nwords, GFP_KERNEL); + nand->bbt.cache = kcalloc(nwords, sizeof(*nand->bbt.cache), + GFP_KERNEL); if (!nand->bbt.cache) return -ENOMEM; diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 93c9bc8931fc..1fdd2834fbcb 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -2995,12 +2995,13 @@ static int spi_nor_init_non_uniform_erase_map(struct spi_nor *nor, const u32 *smpt) { struct spi_nor_erase_map *map = &nor->erase_map; - const struct spi_nor_erase_type *erase = map->erase_type; + struct spi_nor_erase_type *erase = map->erase_type; struct spi_nor_erase_region *region; u64 offset; u32 region_count; int i, j; - u8 erase_type, uniform_erase_type; + u8 uniform_erase_type, save_uniform_erase_type; + u8 erase_type, regions_erase_type; region_count = SMPT_MAP_REGION_COUNT(*smpt); /* @@ -3014,6 +3015,7 @@ static int spi_nor_init_non_uniform_erase_map(struct spi_nor *nor, map->regions = region; uniform_erase_type = 0xff; + regions_erase_type = 0; offset = 0; /* Populate regions. */ for (i = 0; i < region_count; i++) { @@ -3030,13 +3032,38 @@ static int spi_nor_init_non_uniform_erase_map(struct spi_nor *nor, */ uniform_erase_type &= erase_type; + /* + * regions_erase_type mask will indicate all the erase types + * supported in this configuration map. + */ + regions_erase_type |= erase_type; + offset = (region[i].offset & ~SNOR_ERASE_FLAGS_MASK) + region[i].size; } + save_uniform_erase_type = map->uniform_erase_type; map->uniform_erase_type = spi_nor_sort_erase_mask(map, uniform_erase_type); + if (!regions_erase_type) { + /* + * Roll back to the previous uniform_erase_type mask, SMPT is + * broken. + */ + map->uniform_erase_type = save_uniform_erase_type; + return -EINVAL; + } + + /* + * BFPT advertises all the erase types supported by all the possible + * map configurations. Mask out the erase types that are not supported + * by the current map configuration. + */ + for (i = 0; i < SNOR_ERASE_TYPE_MAX; i++) + if (!(regions_erase_type & BIT(erase[i].idx))) + spi_nor_set_erase_type(&erase[i], 0, 0xFF); + spi_nor_region_mark_end(®ion[i - 1]); return 0; diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 55af04fa03a7..6c8dcb65ff03 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -1441,6 +1441,9 @@ static void nic_remove(struct pci_dev *pdev) { struct nicpf *nic = pci_get_drvdata(pdev); + if (!nic) + return; + if (nic->flags & NIC_SRIOV_ENABLED) pci_disable_sriov(pdev); diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index be268dcde8fa..f9a4e76c5a8b 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -915,10 +915,8 @@ static int hip04_mac_probe(struct platform_device *pdev) } ret = register_netdev(ndev); - if (ret) { - free_netdev(ndev); + if (ret) goto alloc_fail; - } return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 21c2688d6308..a3f45335437c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1413,7 +1413,7 @@ void __i40e_del_filter(struct i40e_vsi *vsi, struct i40e_mac_filter *f) } vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; - set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->state); + set_bit(__I40E_MACVLAN_SYNC_PENDING, vsi->back->state); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index add1e457886d..433c8e688c78 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -33,7 +33,7 @@ static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi) } /** - * i40e_add_xsk_umem - Store an UMEM for a certain ring/qid + * i40e_add_xsk_umem - Store a UMEM for a certain ring/qid * @vsi: Current VSI * @umem: UMEM to store * @qid: Ring/qid to associate with the UMEM @@ -56,7 +56,7 @@ static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem, } /** - * i40e_remove_xsk_umem - Remove an UMEM for a certain ring/qid + * i40e_remove_xsk_umem - Remove a UMEM for a certain ring/qid * @vsi: Current VSI * @qid: Ring/qid associated with the UMEM **/ @@ -130,7 +130,7 @@ static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem) } /** - * i40e_xsk_umem_enable - Enable/associate an UMEM to a certain ring/qid + * i40e_xsk_umem_enable - Enable/associate a UMEM to a certain ring/qid * @vsi: Current VSI * @umem: UMEM * @qid: Rx ring to associate UMEM to @@ -189,7 +189,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, } /** - * i40e_xsk_umem_disable - Diassociate an UMEM from a certain ring/qid + * i40e_xsk_umem_disable - Disassociate a UMEM from a certain ring/qid * @vsi: Current VSI * @qid: Rx ring to associate UMEM to * @@ -255,12 +255,12 @@ int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, } /** - * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM + * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid * @vsi: Current VSI * @umem: UMEM to enable/associate to a ring, or NULL to disable * @qid: Rx ring to (dis)associate UMEM (from)to * - * This function enables or disables an UMEM to a certain ring. + * This function enables or disables a UMEM to a certain ring. * * Returns 0 on success, <0 on failure **/ @@ -276,7 +276,7 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, * @rx_ring: Rx ring * @xdp: xdp_buff used as input to the XDP program * - * This function enables or disables an UMEM to a certain ring. + * This function enables or disables a UMEM to a certain ring. * * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR} **/ diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index c54ebedca6da..c393cb2c0f16 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -842,6 +842,7 @@ s32 igb_pll_workaround_i210(struct e1000_hw *hw) nvm_word = E1000_INVM_DEFAULT_AL; tmp_nvm = nvm_word | E1000_INVM_PLL_WO_VAL; igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, E1000_PHY_PLL_FREQ_PAGE); + phy_word = E1000_PHY_PLL_UNCONF; for (i = 0; i < E1000_MAX_PLL_TRIES; i++) { /* check current state directly from internal PHY */ igb_read_phy_reg_82580(hw, E1000_PHY_PLL_FREQ_REG, &phy_word); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 10dbaf4f6e80..9c42f741ed5e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -2262,7 +2262,9 @@ static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, *autoneg = false; if (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1) { *speed = IXGBE_LINK_SPEED_1GB_FULL; return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 867cddba840f..e8ca98c070f6 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1672,7 +1672,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight) netif_wake_queue(adapter->netdev); } - if (!napi_complete_done(napi, weight)) + if (!napi_complete(napi)) goto done; /* enable isr */ @@ -1681,7 +1681,7 @@ static int lan743x_tx_napi_poll(struct napi_struct *napi, int weight) lan743x_csr_read(adapter, INT_STS); done: - return weight; + return 0; } static void lan743x_tx_ring_cleanup(struct lan743x_tx *tx) @@ -1870,9 +1870,9 @@ static int lan743x_tx_open(struct lan743x_tx *tx) tx->vector_flags = lan743x_intr_get_vector_flags(adapter, INT_BIT_DMA_TX_ (tx->channel_number)); - netif_napi_add(adapter->netdev, - &tx->napi, lan743x_tx_napi_poll, - tx->ring_size - 1); + netif_tx_napi_add(adapter->netdev, + &tx->napi, lan743x_tx_napi_poll, + tx->ring_size - 1); napi_enable(&tx->napi); data = 0; @@ -3017,6 +3017,7 @@ static const struct dev_pm_ops lan743x_pm_ops = { static const struct pci_device_id lan743x_pcidev_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) }, + { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7431) }, { 0, } }; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 0e82b6368798..2d6eea18973e 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -548,6 +548,7 @@ struct lan743x_adapter; /* SMSC acquired EFAR late 1990's, MCHP acquired SMSC 2012 */ #define PCI_VENDOR_ID_SMSC PCI_VENDOR_ID_EFAR #define PCI_DEVICE_ID_SMSC_LAN7430 (0x7430) +#define PCI_DEVICE_ID_SMSC_LAN7431 (0x7431) #define PCI_CONFIG_LENGTH (0x1000) diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 78a638ec7c0a..979f1e4bc18b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -6071,7 +6071,7 @@ static const char * const s_igu_fifo_error_strs[] = { "no error", "length error", "function disabled", - "VF sent command to attnetion address", + "VF sent command to attention address", "host sent prod update command", "read of during interrupt register while in MIMD mode", "access to PXP BAR reserved address", diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index ef9538ee53d0..82412691ee66 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -3605,7 +3605,7 @@ static const char velocity_gstrings[][ETH_GSTRING_LEN] = { "tx_jumbo", "rx_mac_control_frames", "tx_mac_control_frames", - "rx_frame_alignement_errors", + "rx_frame_alignment_errors", "rx_long_ok", "rx_long_err", "tx_sqe_errors", diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index ab33d1777132..23ee3967c166 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2197,6 +2197,14 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) new_driver->mdiodrv.driver.remove = phy_remove; new_driver->mdiodrv.driver.owner = owner; + /* The following works around an issue where the PHY driver doesn't bind + * to the device, resulting in the genphy driver being used instead of + * the dedicated driver. The root cause of the issue isn't known yet + * and seems to be in the base driver core. Once this is fixed we may + * remove this workaround. + */ + new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS; + retval = driver_register(&new_driver->mdiodrv.driver); if (retval) { pr_err("%s: Error %d in registering driver\n", diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c index e9f101c9bae2..bfbb39f93554 100644 --- a/drivers/net/rionet.c +++ b/drivers/net/rionet.c @@ -216,9 +216,9 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev) * it just report sending a packet to the target * (without actual packet transfer). */ - dev_kfree_skb_any(skb); ndev->stats.tx_packets++; ndev->stats.tx_bytes += skb->len; + dev_kfree_skb_any(skb); } } diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 7275761a1177..3d8a70d3ea9b 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -140,7 +140,6 @@ struct ipheth_device { struct usb_device *udev; struct usb_interface *intf; struct net_device *net; - struct sk_buff *tx_skb; struct urb *tx_urb; struct urb *rx_urb; unsigned char *tx_buf; @@ -230,6 +229,7 @@ static void ipheth_rcvbulk_callback(struct urb *urb) case -ENOENT: case -ECONNRESET: case -ESHUTDOWN: + case -EPROTO: return; case 0: break; @@ -281,7 +281,6 @@ static void ipheth_sndbulk_callback(struct urb *urb) dev_err(&dev->intf->dev, "%s: urb status: %d\n", __func__, status); - dev_kfree_skb_irq(dev->tx_skb); if (status == 0) netif_wake_queue(dev->net); else @@ -423,7 +422,7 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net) if (skb->len > IPHETH_BUF_SIZE) { WARN(1, "%s: skb too large: %d bytes\n", __func__, skb->len); dev->net->stats.tx_dropped++; - dev_kfree_skb_irq(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -443,12 +442,11 @@ static int ipheth_tx(struct sk_buff *skb, struct net_device *net) dev_err(&dev->intf->dev, "%s: usb_submit_urb: %d\n", __func__, retval); dev->net->stats.tx_errors++; - dev_kfree_skb_irq(skb); + dev_kfree_skb_any(skb); } else { - dev->tx_skb = skb; - dev->net->stats.tx_packets++; dev->net->stats.tx_bytes += skb->len; + dev_consume_skb_any(skb); netif_stop_queue(net); } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 559d567693b8..3cf1b773158e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3314,6 +3314,9 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl) struct nvme_ns *ns, *next; LIST_HEAD(ns_list); + /* prevent racing with ns scanning */ + flush_work(&ctrl->scan_work); + /* * The dead states indicates the controller was not gracefully * disconnected. In that case, we won't be able to flush any data while @@ -3476,7 +3479,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) nvme_mpath_stop(ctrl); nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); - flush_work(&ctrl->scan_work); cancel_work_sync(&ctrl->fw_act_work); if (ctrl->ops->stop_ctrl) ctrl->ops->stop_ctrl(ctrl); @@ -3585,7 +3587,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, return 0; out_free_name: - kfree_const(dev->kobj.name); + kfree_const(ctrl->device->kobj.name); out_release_instance: ida_simple_remove(&nvme_instance_ida, ctrl->instance); out: @@ -3607,7 +3609,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl) down_read(&ctrl->namespaces_rwsem); /* Forcibly unquiesce queues to avoid blocking dispatch */ - if (ctrl->admin_q) + if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q)) blk_mq_unquiesce_queue(ctrl->admin_q); list_for_each_entry(ns, &ctrl->namespaces, list) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 54032c466636..feb86b59170e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1752,12 +1752,12 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq, struct nvme_fc_queue *queue = &ctrl->queues[queue_idx]; int res; - nvme_req(rq)->ctrl = &ctrl->ctrl; res = __nvme_fc_init_request(ctrl, queue, &op->op, rq, queue->rqcnt++); if (res) return res; op->op.fcp_req.first_sgl = &op->sgl[0]; op->op.fcp_req.private = &op->priv[0]; + nvme_req(rq)->ctrl = &ctrl->ctrl; return res; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index cee79cb388af..081cbdcce880 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -531,6 +531,9 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) static inline int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { + if (ctrl->subsys->cmic & (1 << 3)) + dev_warn(ctrl->device, +"Please enable CONFIG_NVME_MULTIPATH for full support of multi-port devices.\n"); return 0; } static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index d181cafedc58..ab6ec7295bf9 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -184,6 +184,7 @@ static int nvme_rdma_alloc_qe(struct ib_device *ibdev, struct nvme_rdma_qe *qe, qe->dma = ib_dma_map_single(ibdev, qe->data, capsule_size, dir); if (ib_dma_mapping_error(ibdev, qe->dma)) { kfree(qe->data); + qe->data = NULL; return -ENOMEM; } @@ -823,6 +824,7 @@ out_free_tagset: out_free_async_qe: nvme_rdma_free_qe(ctrl->device->dev, &ctrl->async_event_sqe, sizeof(struct nvme_command), DMA_TO_DEVICE); + ctrl->async_event_sqe.data = NULL; out_free_queue: nvme_rdma_free_queue(&ctrl->queues[0]); return error; diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 5a4b47958073..38a08805a30c 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -579,10 +579,8 @@ int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) */ count = of_count_phandle_with_args(dev->of_node, "operating-points-v2", NULL); - if (count != 1) - return -ENODEV; - - index = 0; + if (count == 1) + index = 0; } opp_table = dev_pm_opp_get_opp_table_indexed(dev, index); diff --git a/drivers/opp/ti-opp-supply.c b/drivers/opp/ti-opp-supply.c index 3f4fb4dbbe33..1c69c404df11 100644 --- a/drivers/opp/ti-opp-supply.c +++ b/drivers/opp/ti-opp-supply.c @@ -417,7 +417,6 @@ static struct platform_driver ti_opp_supply_driver = { .probe = ti_opp_supply_probe, .driver = { .name = "ti_opp_supply", - .owner = THIS_MODULE, .of_match_table = of_match_ptr(ti_opp_supply_of_match), }, }; diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 2cbef2d7c207..88af6bff945f 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -81,8 +81,6 @@ struct imx6_pcie { #define PCIE_PL_PFLR_FORCE_LINK (1 << 15) #define PCIE_PHY_DEBUG_R0 (PL_OFFSET + 0x28) #define PCIE_PHY_DEBUG_R1 (PL_OFFSET + 0x2c) -#define PCIE_PHY_DEBUG_R1_XMLH_LINK_IN_TRAINING (1 << 29) -#define PCIE_PHY_DEBUG_R1_XMLH_LINK_UP (1 << 4) #define PCIE_PHY_CTRL (PL_OFFSET + 0x114) #define PCIE_PHY_CTRL_DATA_LOC 0 @@ -711,12 +709,6 @@ static int imx6_pcie_host_init(struct pcie_port *pp) return 0; } -static int imx6_pcie_link_up(struct dw_pcie *pci) -{ - return dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R1) & - PCIE_PHY_DEBUG_R1_XMLH_LINK_UP; -} - static const struct dw_pcie_host_ops imx6_pcie_host_ops = { .host_init = imx6_pcie_host_init, }; @@ -749,7 +741,7 @@ static int imx6_add_pcie_port(struct imx6_pcie *imx6_pcie, } static const struct dw_pcie_ops dw_pcie_ops = { - .link_up = imx6_pcie_link_up, + /* No special ops needed, but pcie-designware still expects this struct */ }; #ifdef CONFIG_PM_SLEEP diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c index 3724d3ef7008..7aa9a82b7ebd 100644 --- a/drivers/pci/controller/dwc/pci-layerscape.c +++ b/drivers/pci/controller/dwc/pci-layerscape.c @@ -88,7 +88,7 @@ static void ls_pcie_disable_outbound_atus(struct ls_pcie *pcie) int i; for (i = 0; i < PCIE_IATU_NUM; i++) - dw_pcie_disable_atu(pcie->pci, DW_PCIE_REGION_OUTBOUND, i); + dw_pcie_disable_atu(pcie->pci, i, DW_PCIE_REGION_OUTBOUND); } static int ls1021_pcie_link_up(struct dw_pcie *pci) diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 1e7b02221eac..de8635af4cde 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -440,7 +440,6 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, tbl_offset = dw_pcie_readl_dbi(pci, reg); bir = (tbl_offset & PCI_MSIX_TABLE_BIR); tbl_offset &= PCI_MSIX_TABLE_OFFSET; - tbl_offset >>= 3; reg = PCI_BASE_ADDRESS_0 + (4 * bir); bar_addr_upper = 0; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index d068f11d08a7..c9d8e3c837de 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5556,9 +5556,13 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) u32 lnkcap2, lnkcap; /* - * PCIe r4.0 sec 7.5.3.18 recommends using the Supported Link - * Speeds Vector in Link Capabilities 2 when supported, falling - * back to Max Link Speed in Link Capabilities otherwise. + * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18. The + * implementation note there recommends using the Supported Link + * Speeds Vector in Link Capabilities 2 when supported. + * + * Without Link Capabilities 2, i.e., prior to PCIe r3.0, software + * should use the Supported Link Speeds field in Link Capabilities, + * where only 2.5 GT/s and 5.0 GT/s speeds were defined. */ pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2); if (lnkcap2) { /* PCIe r3.0-compliant */ @@ -5574,16 +5578,10 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev) } pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap); - if (lnkcap) { - if (lnkcap & PCI_EXP_LNKCAP_SLS_16_0GB) - return PCIE_SPEED_16_0GT; - else if (lnkcap & PCI_EXP_LNKCAP_SLS_8_0GB) - return PCIE_SPEED_8_0GT; - else if (lnkcap & PCI_EXP_LNKCAP_SLS_5_0GB) - return PCIE_SPEED_5_0GT; - else if (lnkcap & PCI_EXP_LNKCAP_SLS_2_5GB) - return PCIE_SPEED_2_5GT; - } + if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB) + return PCIE_SPEED_5_0GT; + else if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_2_5GB) + return PCIE_SPEED_2_5GT; return PCI_SPEED_UNKNOWN; } diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index 9ce531194f8a..6d4b44b569bc 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -231,6 +231,7 @@ static const struct qusb2_phy_cfg sdm845_phy_cfg = { .mask_core_ready = CORE_READY_STATUS, .has_pll_override = true, .autoresume_en = BIT(0), + .update_tune1_with_efuse = true, }; static const char * const qusb2_phy_vreg_names[] = { @@ -402,10 +403,10 @@ static void qusb2_phy_set_tune2_param(struct qusb2_phy *qphy) /* * Read efuse register having TUNE2/1 parameter's high nibble. - * If efuse register shows value as 0x0, or if we fail to find - * a valid efuse register settings, then use default value - * as 0xB for high nibble that we have already set while - * configuring phy. + * If efuse register shows value as 0x0 (indicating value is not + * fused), or if we fail to find a valid efuse register setting, + * then use default value for high nibble that we have already + * set while configuring the phy. */ val = nvmem_cell_read(qphy->cell, NULL); if (IS_ERR(val) || !val[0]) { @@ -415,12 +416,13 @@ static void qusb2_phy_set_tune2_param(struct qusb2_phy *qphy) /* Fused TUNE1/2 value is the higher nibble only */ if (cfg->update_tune1_with_efuse) - qusb2_setbits(qphy->base, cfg->regs[QUSB2PHY_PORT_TUNE1], - val[0] << 0x4); + qusb2_write_mask(qphy->base, cfg->regs[QUSB2PHY_PORT_TUNE1], + val[0] << HSTX_TRIM_SHIFT, + HSTX_TRIM_MASK); else - qusb2_setbits(qphy->base, cfg->regs[QUSB2PHY_PORT_TUNE2], - val[0] << 0x4); - + qusb2_write_mask(qphy->base, cfg->regs[QUSB2PHY_PORT_TUNE2], + val[0] << HSTX_TRIM_SHIFT, + HSTX_TRIM_MASK); } static int qusb2_phy_set_mode(struct phy *phy, enum phy_mode mode) diff --git a/drivers/phy/socionext/Kconfig b/drivers/phy/socionext/Kconfig index 467e8147972b..9c85231a6dbc 100644 --- a/drivers/phy/socionext/Kconfig +++ b/drivers/phy/socionext/Kconfig @@ -26,7 +26,8 @@ config PHY_UNIPHIER_USB3 config PHY_UNIPHIER_PCIE tristate "Uniphier PHY driver for PCIe controller" - depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF + depends on ARCH_UNIPHIER || COMPILE_TEST + depends on OF && HAS_IOMEM default PCIE_UNIPHIER select GENERIC_PHY help diff --git a/drivers/rtc/rtc-hid-sensor-time.c b/drivers/rtc/rtc-hid-sensor-time.c index 2751dba850c6..3e1abb455472 100644 --- a/drivers/rtc/rtc-hid-sensor-time.c +++ b/drivers/rtc/rtc-hid-sensor-time.c @@ -213,7 +213,7 @@ static int hid_rtc_read_time(struct device *dev, struct rtc_time *tm) /* get a report with all values through requesting one value */ sensor_hub_input_attr_get_raw_value(time_state->common_attributes.hsdev, HID_USAGE_SENSOR_TIME, hid_time_addresses[0], - time_state->info[0].report_id, SENSOR_HUB_SYNC); + time_state->info[0].report_id, SENSOR_HUB_SYNC, false); /* wait for all values (event) */ ret = wait_for_completion_killable_timeout( &time_state->comp_last_time, HZ*6); diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index fd77e46eb3b2..70a006ba4d05 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -387,8 +387,10 @@ static int ccwchain_calc_length(u64 iova, struct channel_program *cp) * orb specified one of the unsupported formats, we defer * checking for IDAWs in unsupported formats to here. */ - if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw)) + if ((!cp->orb.cmd.c64 || cp->orb.cmd.i2k) && ccw_is_idal(ccw)) { + kfree(p); return -EOPNOTSUPP; + } if ((!ccw_is_chain(ccw)) && (!ccw_is_tic(ccw))) break; @@ -528,7 +530,7 @@ static int ccwchain_fetch_direct(struct ccwchain *chain, ret = pfn_array_alloc_pin(pat->pat_pa, cp->mdev, ccw->cda, ccw->count); if (ret < 0) - goto out_init; + goto out_unpin; /* Translate this direct ccw to a idal ccw. */ idaws = kcalloc(ret, sizeof(*idaws), GFP_DMA | GFP_KERNEL); diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c index f47d16b5810b..a10cec0e86eb 100644 --- a/drivers/s390/cio/vfio_ccw_drv.c +++ b/drivers/s390/cio/vfio_ccw_drv.c @@ -22,7 +22,7 @@ #include "vfio_ccw_private.h" struct workqueue_struct *vfio_ccw_work_q; -struct kmem_cache *vfio_ccw_io_region; +static struct kmem_cache *vfio_ccw_io_region; /* * Helpers @@ -134,14 +134,14 @@ static int vfio_ccw_sch_probe(struct subchannel *sch) if (ret) goto out_free; - ret = vfio_ccw_mdev_reg(sch); - if (ret) - goto out_disable; - INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo); atomic_set(&private->avail, 1); private->state = VFIO_CCW_STATE_STANDBY; + ret = vfio_ccw_mdev_reg(sch); + if (ret) + goto out_disable; + return 0; out_disable: diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 048665e4f13d..9f5a201c4c87 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -775,6 +775,8 @@ static int ap_device_probe(struct device *dev) drvres = ap_drv->flags & AP_DRIVER_FLAG_DEFAULT; if (!!devres != !!drvres) return -ENODEV; + /* (re-)init queue's state machine */ + ap_queue_reinit_state(to_ap_queue(dev)); } /* Add queue/card to list of active queues/cards */ @@ -807,6 +809,8 @@ static int ap_device_remove(struct device *dev) struct ap_device *ap_dev = to_ap_dev(dev); struct ap_driver *ap_drv = ap_dev->drv; + if (is_queue_dev(dev)) + ap_queue_remove(to_ap_queue(dev)); if (ap_drv->remove) ap_drv->remove(ap_dev); @@ -1444,10 +1448,6 @@ static void ap_scan_bus(struct work_struct *unused) aq->ap_dev.device.parent = &ac->ap_dev.device; dev_set_name(&aq->ap_dev.device, "%02x.%04x", id, dom); - /* Start with a device reset */ - spin_lock_bh(&aq->lock); - ap_wait(ap_sm_event(aq, AP_EVENT_POLL)); - spin_unlock_bh(&aq->lock); /* Register device */ rc = device_register(&aq->ap_dev.device); if (rc) { diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 3eed1b36c876..bfc66e4a9de1 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -254,6 +254,7 @@ struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type); void ap_queue_remove(struct ap_queue *aq); void ap_queue_suspend(struct ap_device *ap_dev); void ap_queue_resume(struct ap_device *ap_dev); +void ap_queue_reinit_state(struct ap_queue *aq); struct ap_card *ap_card_create(int id, int queue_depth, int raw_device_type, int comp_device_type, unsigned int functions); diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c index 66f7334bcb03..0aa4b3ccc948 100644 --- a/drivers/s390/crypto/ap_queue.c +++ b/drivers/s390/crypto/ap_queue.c @@ -718,5 +718,20 @@ void ap_queue_remove(struct ap_queue *aq) { ap_flush_queue(aq); del_timer_sync(&aq->timeout); + + /* reset with zero, also clears irq registration */ + spin_lock_bh(&aq->lock); + ap_zapq(aq->qid); + aq->state = AP_STATE_BORKED; + spin_unlock_bh(&aq->lock); } EXPORT_SYMBOL(ap_queue_remove); + +void ap_queue_reinit_state(struct ap_queue *aq) +{ + spin_lock_bh(&aq->lock); + aq->state = AP_STATE_RESET_START; + ap_wait(ap_sm_event(aq, AP_EVENT_POLL)); + spin_unlock_bh(&aq->lock); +} +EXPORT_SYMBOL(ap_queue_reinit_state); diff --git a/drivers/s390/crypto/zcrypt_cex2a.c b/drivers/s390/crypto/zcrypt_cex2a.c index 146f54f5cbb8..c50f3e86cc74 100644 --- a/drivers/s390/crypto/zcrypt_cex2a.c +++ b/drivers/s390/crypto/zcrypt_cex2a.c @@ -196,7 +196,6 @@ static void zcrypt_cex2a_queue_remove(struct ap_device *ap_dev) struct ap_queue *aq = to_ap_queue(&ap_dev->device); struct zcrypt_queue *zq = aq->private; - ap_queue_remove(aq); if (zq) zcrypt_queue_unregister(zq); } diff --git a/drivers/s390/crypto/zcrypt_cex2c.c b/drivers/s390/crypto/zcrypt_cex2c.c index 546f67676734..35c7c6672713 100644 --- a/drivers/s390/crypto/zcrypt_cex2c.c +++ b/drivers/s390/crypto/zcrypt_cex2c.c @@ -251,7 +251,6 @@ static void zcrypt_cex2c_queue_remove(struct ap_device *ap_dev) struct ap_queue *aq = to_ap_queue(&ap_dev->device); struct zcrypt_queue *zq = aq->private; - ap_queue_remove(aq); if (zq) zcrypt_queue_unregister(zq); } diff --git a/drivers/s390/crypto/zcrypt_cex4.c b/drivers/s390/crypto/zcrypt_cex4.c index f9d4c6c7521d..582ffa7e0f18 100644 --- a/drivers/s390/crypto/zcrypt_cex4.c +++ b/drivers/s390/crypto/zcrypt_cex4.c @@ -275,7 +275,6 @@ static void zcrypt_cex4_queue_remove(struct ap_device *ap_dev) struct ap_queue *aq = to_ap_queue(&ap_dev->device); struct zcrypt_queue *zq = aq->private; - ap_queue_remove(aq); if (zq) zcrypt_queue_unregister(zq); } diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 4bce5ae65a55..254065271867 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -4518,8 +4518,8 @@ static int qeth_snmp_command_cb(struct qeth_card *card, { struct qeth_ipa_cmd *cmd; struct qeth_arp_query_info *qinfo; - struct qeth_snmp_cmd *snmp; unsigned char *data; + void *snmp_data; __u16 data_len; QETH_CARD_TEXT(card, 3, "snpcmdcb"); @@ -4527,7 +4527,6 @@ static int qeth_snmp_command_cb(struct qeth_card *card, cmd = (struct qeth_ipa_cmd *) sdata; data = (unsigned char *)((char *)cmd - reply->offset); qinfo = (struct qeth_arp_query_info *) reply->param; - snmp = &cmd->data.setadapterparms.data.snmp; if (cmd->hdr.return_code) { QETH_CARD_TEXT_(card, 4, "scer1%x", cmd->hdr.return_code); @@ -4540,10 +4539,15 @@ static int qeth_snmp_command_cb(struct qeth_card *card, return 0; } data_len = *((__u16 *)QETH_IPA_PDU_LEN_PDU1(data)); - if (cmd->data.setadapterparms.hdr.seq_no == 1) - data_len -= (__u16)((char *)&snmp->data - (char *)cmd); - else - data_len -= (__u16)((char *)&snmp->request - (char *)cmd); + if (cmd->data.setadapterparms.hdr.seq_no == 1) { + snmp_data = &cmd->data.setadapterparms.data.snmp; + data_len -= offsetof(struct qeth_ipa_cmd, + data.setadapterparms.data.snmp); + } else { + snmp_data = &cmd->data.setadapterparms.data.snmp.request; + data_len -= offsetof(struct qeth_ipa_cmd, + data.setadapterparms.data.snmp.request); + } /* check if there is enough room in userspace */ if ((qinfo->udata_len - qinfo->udata_offset) < data_len) { @@ -4556,16 +4560,9 @@ static int qeth_snmp_command_cb(struct qeth_card *card, QETH_CARD_TEXT_(card, 4, "sseqn%i", cmd->data.setadapterparms.hdr.seq_no); /*copy entries to user buffer*/ - if (cmd->data.setadapterparms.hdr.seq_no == 1) { - memcpy(qinfo->udata + qinfo->udata_offset, - (char *)snmp, - data_len + offsetof(struct qeth_snmp_cmd, data)); - qinfo->udata_offset += offsetof(struct qeth_snmp_cmd, data); - } else { - memcpy(qinfo->udata + qinfo->udata_offset, - (char *)&snmp->request, data_len); - } + memcpy(qinfo->udata + qinfo->udata_offset, snmp_data, data_len); qinfo->udata_offset += data_len; + /* check if all replies received ... */ QETH_CARD_TEXT_(card, 4, "srtot%i", cmd->data.setadapterparms.hdr.used_total); diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 3dc31627c655..0c2867deb36f 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -522,11 +522,11 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id) mdata->xfer_len = min(MTK_SPI_MAX_FIFO_SIZE, len); mtk_spi_setup_packet(master); - cnt = len / 4; + cnt = mdata->xfer_len / 4; iowrite32_rep(mdata->base + SPI_TX_DATA_REG, trans->tx_buf + mdata->num_xfered, cnt); - remainder = len % 4; + remainder = mdata->xfer_len % 4; if (remainder > 0) { reg_val = 0; memcpy(®_val, diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c index f024c3fc3679..2fd8881fcd65 100644 --- a/drivers/spi/spi-omap2-mcspi.c +++ b/drivers/spi/spi-omap2-mcspi.c @@ -1540,13 +1540,26 @@ static int omap2_mcspi_remove(struct platform_device *pdev) /* work with hotplug and coldplug */ MODULE_ALIAS("platform:omap2_mcspi"); -#ifdef CONFIG_SUSPEND -static int omap2_mcspi_suspend_noirq(struct device *dev) +static int __maybe_unused omap2_mcspi_suspend(struct device *dev) { - return pinctrl_pm_select_sleep_state(dev); + struct spi_master *master = dev_get_drvdata(dev); + struct omap2_mcspi *mcspi = spi_master_get_devdata(master); + int error; + + error = pinctrl_pm_select_sleep_state(dev); + if (error) + dev_warn(mcspi->dev, "%s: failed to set pins: %i\n", + __func__, error); + + error = spi_master_suspend(master); + if (error) + dev_warn(mcspi->dev, "%s: master suspend failed: %i\n", + __func__, error); + + return pm_runtime_force_suspend(dev); } -static int omap2_mcspi_resume_noirq(struct device *dev) +static int __maybe_unused omap2_mcspi_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct omap2_mcspi *mcspi = spi_master_get_devdata(master); @@ -1557,17 +1570,17 @@ static int omap2_mcspi_resume_noirq(struct device *dev) dev_warn(mcspi->dev, "%s: failed to set pins: %i\n", __func__, error); - return 0; -} + error = spi_master_resume(master); + if (error) + dev_warn(mcspi->dev, "%s: master resume failed: %i\n", + __func__, error); -#else -#define omap2_mcspi_suspend_noirq NULL -#define omap2_mcspi_resume_noirq NULL -#endif + return pm_runtime_force_resume(dev); +} static const struct dev_pm_ops omap2_mcspi_pm_ops = { - .suspend_noirq = omap2_mcspi_suspend_noirq, - .resume_noirq = omap2_mcspi_resume_noirq, + SET_SYSTEM_SLEEP_PM_OPS(omap2_mcspi_suspend, + omap2_mcspi_resume) .runtime_resume = omap_mcspi_runtime_resume, }; diff --git a/drivers/staging/comedi/comedi.h b/drivers/staging/comedi/comedi.h index e90b17775284..09a940066c0e 100644 --- a/drivers/staging/comedi/comedi.h +++ b/drivers/staging/comedi/comedi.h @@ -1005,35 +1005,38 @@ enum i8254_mode { * and INSN_DEVICE_CONFIG_GET_ROUTES. */ #define NI_NAMES_BASE 0x8000u + +#define _TERM_N(base, n, x) ((base) + ((x) & ((n) - 1))) + /* * not necessarily all allowed 64 PFIs are valid--certainly not for all devices */ -#define NI_PFI(x) (NI_NAMES_BASE + ((x) & 0x3f)) +#define NI_PFI(x) _TERM_N(NI_NAMES_BASE, 64, x) /* 8 trigger lines by standard, Some devices cannot talk to all eight. */ -#define TRIGGER_LINE(x) (NI_PFI(-1) + 1 + ((x) & 0x7)) +#define TRIGGER_LINE(x) _TERM_N(NI_PFI(-1) + 1, 8, x) /* 4 RTSI shared MUXes to route signals to/from TRIGGER_LINES on NI hardware */ -#define NI_RTSI_BRD(x) (TRIGGER_LINE(-1) + 1 + ((x) & 0x3)) +#define NI_RTSI_BRD(x) _TERM_N(TRIGGER_LINE(-1) + 1, 4, x) /* *** Counter/timer names : 8 counters max *** */ -#define NI_COUNTER_NAMES_BASE (NI_RTSI_BRD(-1) + 1) -#define NI_MAX_COUNTERS 7 -#define NI_CtrSource(x) (NI_COUNTER_NAMES_BASE + ((x) & NI_MAX_COUNTERS)) +#define NI_MAX_COUNTERS 8 +#define NI_COUNTER_NAMES_BASE (NI_RTSI_BRD(-1) + 1) +#define NI_CtrSource(x) _TERM_N(NI_COUNTER_NAMES_BASE, NI_MAX_COUNTERS, x) /* Gate, Aux, A,B,Z are all treated, at times as gates */ -#define NI_GATES_NAMES_BASE (NI_CtrSource(-1) + 1) -#define NI_CtrGate(x) (NI_GATES_NAMES_BASE + ((x) & NI_MAX_COUNTERS)) -#define NI_CtrAux(x) (NI_CtrGate(-1) + 1 + ((x) & NI_MAX_COUNTERS)) -#define NI_CtrA(x) (NI_CtrAux(-1) + 1 + ((x) & NI_MAX_COUNTERS)) -#define NI_CtrB(x) (NI_CtrA(-1) + 1 + ((x) & NI_MAX_COUNTERS)) -#define NI_CtrZ(x) (NI_CtrB(-1) + 1 + ((x) & NI_MAX_COUNTERS)) -#define NI_GATES_NAMES_MAX NI_CtrZ(-1) -#define NI_CtrArmStartTrigger(x) (NI_CtrZ(-1) + 1 + ((x) & NI_MAX_COUNTERS)) +#define NI_GATES_NAMES_BASE (NI_CtrSource(-1) + 1) +#define NI_CtrGate(x) _TERM_N(NI_GATES_NAMES_BASE, NI_MAX_COUNTERS, x) +#define NI_CtrAux(x) _TERM_N(NI_CtrGate(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrA(x) _TERM_N(NI_CtrAux(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrB(x) _TERM_N(NI_CtrA(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrZ(x) _TERM_N(NI_CtrB(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_GATES_NAMES_MAX NI_CtrZ(-1) +#define NI_CtrArmStartTrigger(x) _TERM_N(NI_CtrZ(-1) + 1, NI_MAX_COUNTERS, x) #define NI_CtrInternalOutput(x) \ - (NI_CtrArmStartTrigger(-1) + 1 + ((x) & NI_MAX_COUNTERS)) + _TERM_N(NI_CtrArmStartTrigger(-1) + 1, NI_MAX_COUNTERS, x) /** external pin(s) labeled conveniently as Ctr<i>Out. */ -#define NI_CtrOut(x) (NI_CtrInternalOutput(-1) + 1 + ((x) & NI_MAX_COUNTERS)) +#define NI_CtrOut(x) _TERM_N(NI_CtrInternalOutput(-1) + 1, NI_MAX_COUNTERS, x) /** For Buffered sampling of ctr -- x series capability. */ -#define NI_CtrSampleClock(x) (NI_CtrOut(-1) + 1 + ((x) & NI_MAX_COUNTERS)) -#define NI_COUNTER_NAMES_MAX NI_CtrSampleClock(-1) +#define NI_CtrSampleClock(x) _TERM_N(NI_CtrOut(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_COUNTER_NAMES_MAX NI_CtrSampleClock(-1) enum ni_common_signal_names { /* PXI_Star: this is a non-NI-specific signal */ diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c index 2d1e0325d04d..5edf59ac6706 100644 --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -2843,7 +2843,8 @@ static int ni_ao_insn_config(struct comedi_device *dev, return ni_ao_arm(dev, s); case INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS: /* we don't care about actual channels */ - data[1] = board->ao_speed; + /* data[3] : chanlist_len */ + data[1] = board->ao_speed * data[3]; data[2] = 0; return 0; default: diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index dd121f66fa2d..c912c70b3ef7 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -108,17 +108,6 @@ static int cedrus_request_validate(struct media_request *req) unsigned int count; unsigned int i; - count = vb2_request_buffer_cnt(req); - if (!count) { - v4l2_info(&ctx->dev->v4l2_dev, - "No buffer was provided with the request\n"); - return -ENOENT; - } else if (count > 1) { - v4l2_info(&ctx->dev->v4l2_dev, - "More than one buffer was provided with the request\n"); - return -EINVAL; - } - list_for_each_entry(obj, &req->objects, list) { struct vb2_buffer *vb; @@ -133,6 +122,17 @@ static int cedrus_request_validate(struct media_request *req) if (!ctx) return -ENOENT; + count = vb2_request_buffer_cnt(req); + if (!count) { + v4l2_info(&ctx->dev->v4l2_dev, + "No buffer was provided with the request\n"); + return -ENOENT; + } else if (count > 1) { + v4l2_info(&ctx->dev->v4l2_dev, + "More than one buffer was provided with the request\n"); + return -EINVAL; + } + parent_hdl = &ctx->hdl; hdl = v4l2_ctrl_request_hdl_find(req, parent_hdl); diff --git a/drivers/staging/most/core.c b/drivers/staging/most/core.c index 6a18cf73c85e..18936cdb1083 100644 --- a/drivers/staging/most/core.c +++ b/drivers/staging/most/core.c @@ -351,7 +351,7 @@ static ssize_t set_datatype_show(struct device *dev, for (i = 0; i < ARRAY_SIZE(ch_data_type); i++) { if (c->cfg.data_type & ch_data_type[i].most_ch_data_type) - return snprintf(buf, PAGE_SIZE, ch_data_type[i].name); + return snprintf(buf, PAGE_SIZE, "%s", ch_data_type[i].name); } return snprintf(buf, PAGE_SIZE, "unconfigured\n"); } diff --git a/drivers/staging/mt7621-dma/mtk-hsdma.c b/drivers/staging/mt7621-dma/mtk-hsdma.c index df6ebf41bdea..5831f816c17b 100644 --- a/drivers/staging/mt7621-dma/mtk-hsdma.c +++ b/drivers/staging/mt7621-dma/mtk-hsdma.c @@ -335,6 +335,8 @@ static int mtk_hsdma_start_transfer(struct mtk_hsdam_engine *hsdma, /* tx desc */ src = sg->src_addr; for (i = 0; i < chan->desc->num_sgs; i++) { + tx_desc = &chan->tx_ring[chan->tx_idx]; + if (len > HSDMA_MAX_PLEN) tlen = HSDMA_MAX_PLEN; else @@ -344,7 +346,6 @@ static int mtk_hsdma_start_transfer(struct mtk_hsdam_engine *hsdma, tx_desc->addr1 = src; tx_desc->flags |= HSDMA_DESC_PLEN1(tlen); } else { - tx_desc = &chan->tx_ring[chan->tx_idx]; tx_desc->addr0 = src; tx_desc->flags = HSDMA_DESC_PLEN0(tlen); diff --git a/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c b/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c index b8566ed898f1..aa98fbb17013 100644 --- a/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c +++ b/drivers/staging/mt7621-pinctrl/pinctrl-rt2880.c @@ -82,7 +82,7 @@ static int rt2880_pinctrl_dt_node_to_map(struct pinctrl_dev *pctrldev, struct property *prop; const char *function_name, *group_name; int ret; - int ngroups; + int ngroups = 0; unsigned int reserved_maps = 0; for_each_node_with_property(np_config, "group") diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c index 85077947b9b8..85aba8a503cd 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_recv.c @@ -109,12 +109,12 @@ static void update_recvframe_phyinfo(union recv_frame *precvframe, rx_bssid = get_hdr_bssid(wlanhdr); pkt_info.bssid_match = ((!IsFrameTypeCtrl(wlanhdr)) && !pattrib->icv_err && !pattrib->crc_err && - !ether_addr_equal(rx_bssid, my_bssid)); + ether_addr_equal(rx_bssid, my_bssid)); rx_ra = get_ra(wlanhdr); my_hwaddr = myid(&padapter->eeprompriv); pkt_info.to_self = pkt_info.bssid_match && - !ether_addr_equal(rx_ra, my_hwaddr); + ether_addr_equal(rx_ra, my_hwaddr); pkt_info.is_beacon = pkt_info.bssid_match && diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c index af2234798fa8..db553f2e4c0b 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_cfg80211.c @@ -1277,7 +1277,7 @@ static int cfg80211_rtw_get_station(struct wiphy *wiphy, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS); sinfo->tx_packets = psta->sta_stats.tx_pkts; - + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED); } /* for Ad-Hoc/AP mode */ diff --git a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c index 28bfdbdc6e76..b8631baf128d 100644 --- a/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c +++ b/drivers/staging/rtl8723bs/os_dep/ioctl_linux.c @@ -2289,7 +2289,7 @@ static int rtw_wx_read32(struct net_device *dev, exit: kfree(ptmp); - return 0; + return ret; } static int rtw_wx_write32(struct net_device *dev, diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c index ea789376de0f..45de21c210c1 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c @@ -1795,6 +1795,7 @@ vchiq_compat_ioctl_await_completion(struct file *file, struct vchiq_await_completion32 args32; struct vchiq_completion_data32 completion32; unsigned int *msgbufcount32; + unsigned int msgbufcount_native; compat_uptr_t msgbuf32; void *msgbuf; void **msgbufptr; @@ -1906,7 +1907,11 @@ vchiq_compat_ioctl_await_completion(struct file *file, sizeof(completion32))) return -EFAULT; - args32.msgbufcount--; + if (get_user(msgbufcount_native, &args->msgbufcount)) + return -EFAULT; + + if (!msgbufcount_native) + args32.msgbufcount--; msgbufcount32 = &((struct vchiq_await_completion32 __user *)arg)->msgbufcount; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 52ff854f0d6c..cd96994dc094 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -863,6 +863,30 @@ static ssize_t key_store(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR(key, 0600, key_show, key_store); +static void nvm_authenticate_start(struct tb_switch *sw) +{ + struct pci_dev *root_port; + + /* + * During host router NVM upgrade we should not allow root port to + * go into D3cold because some root ports cannot trigger PME + * itself. To be on the safe side keep the root port in D0 during + * the whole upgrade process. + */ + root_port = pci_find_pcie_root_port(sw->tb->nhi->pdev); + if (root_port) + pm_runtime_get_noresume(&root_port->dev); +} + +static void nvm_authenticate_complete(struct tb_switch *sw) +{ + struct pci_dev *root_port; + + root_port = pci_find_pcie_root_port(sw->tb->nhi->pdev); + if (root_port) + pm_runtime_put(&root_port->dev); +} + static ssize_t nvm_authenticate_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -912,10 +936,18 @@ static ssize_t nvm_authenticate_store(struct device *dev, sw->nvm->authenticating = true; - if (!tb_route(sw)) + if (!tb_route(sw)) { + /* + * Keep root port from suspending as long as the + * NVM upgrade process is running. + */ + nvm_authenticate_start(sw); ret = nvm_authenticate_host(sw); - else + if (ret) + nvm_authenticate_complete(sw); + } else { ret = nvm_authenticate_device(sw); + } pm_runtime_mark_last_busy(&sw->dev); pm_runtime_put_autosuspend(&sw->dev); } @@ -1334,6 +1366,10 @@ static int tb_switch_add_dma_port(struct tb_switch *sw) if (ret <= 0) return ret; + /* Now we can allow root port to suspend again */ + if (!tb_route(sw)) + nvm_authenticate_complete(sw); + if (status) { tb_sw_info(sw, "switch flash authentication failed\n"); tb_switch_set_uuid(sw); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index f9ff03e6af93..0690fcff0ea2 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -209,6 +209,9 @@ static const struct usb_device_id usb_quirk_list[] = { /* Microsoft LifeCam-VX700 v2.0 */ { USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Cherry Stream G230 2.0 (G85-231) and 3.0 (G85-232) */ + { USB_DEVICE(0x046a, 0x0023), .driver_info = USB_QUIRK_RESET_RESUME }, + /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */ { USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT }, { USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 9faad896b3a1..9f92ee03dde7 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1470,9 +1470,6 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) unsigned transfer_in_flight; unsigned started; - if (dep->flags & DWC3_EP_STALL) - return 0; - if (dep->number > 1) trb = dwc3_ep_prev_trb(dep, dep->trb_enqueue); else @@ -1494,8 +1491,6 @@ int __dwc3_gadget_ep_set_halt(struct dwc3_ep *dep, int value, int protocol) else dep->flags |= DWC3_EP_STALL; } else { - if (!(dep->flags & DWC3_EP_STALL)) - return 0; ret = dwc3_send_clear_stall_ep_cmd(dep); if (ret) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index 1000d864929c..0f026d445e31 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -401,12 +401,12 @@ done: static void rx_fill(struct eth_dev *dev, gfp_t gfp_flags) { struct usb_request *req; - struct usb_request *tmp; unsigned long flags; /* fill unused rxq slots with some skb */ spin_lock_irqsave(&dev->req_lock, flags); - list_for_each_entry_safe(req, tmp, &dev->rx_reqs, list) { + while (!list_empty(&dev->rx_reqs)) { + req = list_first_entry(&dev->rx_reqs, struct usb_request, list); list_del_init(&req->list); spin_unlock_irqrestore(&dev->req_lock, flags); @@ -1125,7 +1125,6 @@ void gether_disconnect(struct gether *link) { struct eth_dev *dev = link->ioport; struct usb_request *req; - struct usb_request *tmp; WARN_ON(!dev); if (!dev) @@ -1142,7 +1141,8 @@ void gether_disconnect(struct gether *link) */ usb_ep_disable(link->in_ep); spin_lock(&dev->req_lock); - list_for_each_entry_safe(req, tmp, &dev->tx_reqs, list) { + while (!list_empty(&dev->tx_reqs)) { + req = list_first_entry(&dev->tx_reqs, struct usb_request, list); list_del(&req->list); spin_unlock(&dev->req_lock); @@ -1154,7 +1154,8 @@ void gether_disconnect(struct gether *link) usb_ep_disable(link->out_ep); spin_lock(&dev->req_lock); - list_for_each_entry_safe(req, tmp, &dev->rx_reqs, list) { + while (!list_empty(&dev->rx_reqs)) { + req = list_first_entry(&dev->rx_reqs, struct usb_request, list); list_del(&req->list); spin_unlock(&dev->req_lock); diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index 3a16431da321..fcf13ef33b31 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -2033,6 +2033,7 @@ static inline int machine_without_vbus_sense(void) { return machine_is_omap_innovator() || machine_is_omap_osk() + || machine_is_omap_palmte() || machine_is_sx1() /* No known omap7xx boards with vbus sense */ || cpu_is_omap7xx(); @@ -2041,7 +2042,7 @@ static inline int machine_without_vbus_sense(void) static int omap_udc_start(struct usb_gadget *g, struct usb_gadget_driver *driver) { - int status = -ENODEV; + int status; struct omap_ep *ep; unsigned long flags; @@ -2079,6 +2080,7 @@ static int omap_udc_start(struct usb_gadget *g, goto done; } } else { + status = 0; if (can_pullup(udc)) pullup_enable(udc); else @@ -2593,9 +2595,22 @@ omap_ep_setup(char *name, u8 addr, u8 type, static void omap_udc_release(struct device *dev) { - complete(udc->done); + pullup_disable(udc); + if (!IS_ERR_OR_NULL(udc->transceiver)) { + usb_put_phy(udc->transceiver); + udc->transceiver = NULL; + } + omap_writew(0, UDC_SYSCON1); + remove_proc_file(); + if (udc->dc_clk) { + if (udc->clk_requested) + omap_udc_enable_clock(0); + clk_put(udc->hhc_clk); + clk_put(udc->dc_clk); + } + if (udc->done) + complete(udc->done); kfree(udc); - udc = NULL; } static int @@ -2627,6 +2642,7 @@ omap_udc_setup(struct platform_device *odev, struct usb_phy *xceiv) udc->gadget.speed = USB_SPEED_UNKNOWN; udc->gadget.max_speed = USB_SPEED_FULL; udc->gadget.name = driver_name; + udc->gadget.quirk_ep_out_aligned_size = 1; udc->transceiver = xceiv; /* ep0 is special; put it right after the SETUP buffer */ @@ -2867,8 +2883,8 @@ bad_on_1710: udc->clr_halt = UDC_RESET_EP; /* USB general purpose IRQ: ep0, state changes, dma, etc */ - status = request_irq(pdev->resource[1].start, omap_udc_irq, - 0, driver_name, udc); + status = devm_request_irq(&pdev->dev, pdev->resource[1].start, + omap_udc_irq, 0, driver_name, udc); if (status != 0) { ERR("can't get irq %d, err %d\n", (int) pdev->resource[1].start, status); @@ -2876,20 +2892,20 @@ bad_on_1710: } /* USB "non-iso" IRQ (PIO for all but ep0) */ - status = request_irq(pdev->resource[2].start, omap_udc_pio_irq, - 0, "omap_udc pio", udc); + status = devm_request_irq(&pdev->dev, pdev->resource[2].start, + omap_udc_pio_irq, 0, "omap_udc pio", udc); if (status != 0) { ERR("can't get irq %d, err %d\n", (int) pdev->resource[2].start, status); - goto cleanup2; + goto cleanup1; } #ifdef USE_ISO - status = request_irq(pdev->resource[3].start, omap_udc_iso_irq, - 0, "omap_udc iso", udc); + status = devm_request_irq(&pdev->dev, pdev->resource[3].start, + omap_udc_iso_irq, 0, "omap_udc iso", udc); if (status != 0) { ERR("can't get irq %d, err %d\n", (int) pdev->resource[3].start, status); - goto cleanup3; + goto cleanup1; } #endif if (cpu_is_omap16xx() || cpu_is_omap7xx()) { @@ -2900,23 +2916,8 @@ bad_on_1710: } create_proc_file(); - status = usb_add_gadget_udc_release(&pdev->dev, &udc->gadget, - omap_udc_release); - if (status) - goto cleanup4; - - return 0; - -cleanup4: - remove_proc_file(); - -#ifdef USE_ISO -cleanup3: - free_irq(pdev->resource[2].start, udc); -#endif - -cleanup2: - free_irq(pdev->resource[1].start, udc); + return usb_add_gadget_udc_release(&pdev->dev, &udc->gadget, + omap_udc_release); cleanup1: kfree(udc); @@ -2943,42 +2944,15 @@ static int omap_udc_remove(struct platform_device *pdev) { DECLARE_COMPLETION_ONSTACK(done); - if (!udc) - return -ENODEV; - - usb_del_gadget_udc(&udc->gadget); - if (udc->driver) - return -EBUSY; - udc->done = &done; - pullup_disable(udc); - if (!IS_ERR_OR_NULL(udc->transceiver)) { - usb_put_phy(udc->transceiver); - udc->transceiver = NULL; - } - omap_writew(0, UDC_SYSCON1); - - remove_proc_file(); - -#ifdef USE_ISO - free_irq(pdev->resource[3].start, udc); -#endif - free_irq(pdev->resource[2].start, udc); - free_irq(pdev->resource[1].start, udc); + usb_del_gadget_udc(&udc->gadget); - if (udc->dc_clk) { - if (udc->clk_requested) - omap_udc_enable_clock(0); - clk_put(udc->hhc_clk); - clk_put(udc->dc_clk); - } + wait_for_completion(&done); release_mem_region(pdev->resource[0].start, pdev->resource[0].end - pdev->resource[0].start + 1); - wait_for_completion(&done); - return 0; } diff --git a/drivers/usb/storage/unusual_realtek.h b/drivers/usb/storage/unusual_realtek.h index d17cd95b55bb..6b2140f966ef 100644 --- a/drivers/usb/storage/unusual_realtek.h +++ b/drivers/usb/storage/unusual_realtek.h @@ -27,4 +27,14 @@ UNUSUAL_DEV(0x0bda, 0x0159, 0x0000, 0x9999, "USB Card Reader", USB_SC_DEVICE, USB_PR_DEVICE, init_realtek_cr, 0), +UNUSUAL_DEV(0x0bda, 0x0177, 0x0000, 0x9999, + "Realtek", + "USB Card Reader", + USB_SC_DEVICE, USB_PR_DEVICE, init_realtek_cr, 0), + +UNUSUAL_DEV(0x0bda, 0x0184, 0x0000, 0x9999, + "Realtek", + "USB Card Reader", + USB_SC_DEVICE, USB_PR_DEVICE, init_realtek_cr, 0), + #endif /* defined(CONFIG_USB_STORAGE_REALTEK) || ... */ diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index fdfc64f5acea..221b7333d067 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -251,25 +251,10 @@ static void release_memory_resource(struct resource *resource) kfree(resource); } -/* - * Host memory not allocated to dom0. We can use this range for hotplug-based - * ballooning. - * - * It's a type-less resource. Setting IORESOURCE_MEM will make resource - * management algorithms (arch_remove_reservations()) look into guest e820, - * which we don't want. - */ -static struct resource hostmem_resource = { - .name = "Host RAM", -}; - -void __attribute__((weak)) __init arch_xen_balloon_init(struct resource *res) -{} - static struct resource *additional_memory_resource(phys_addr_t size) { - struct resource *res, *res_hostmem; - int ret = -ENOMEM; + struct resource *res; + int ret; res = kzalloc(sizeof(*res), GFP_KERNEL); if (!res) @@ -278,42 +263,13 @@ static struct resource *additional_memory_resource(phys_addr_t size) res->name = "System RAM"; res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; - res_hostmem = kzalloc(sizeof(*res), GFP_KERNEL); - if (res_hostmem) { - /* Try to grab a range from hostmem */ - res_hostmem->name = "Host memory"; - ret = allocate_resource(&hostmem_resource, res_hostmem, - size, 0, -1, - PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); - } - - if (!ret) { - /* - * Insert this resource into iomem. Because hostmem_resource - * tracks portion of guest e820 marked as UNUSABLE noone else - * should try to use it. - */ - res->start = res_hostmem->start; - res->end = res_hostmem->end; - ret = insert_resource(&iomem_resource, res); - if (ret < 0) { - pr_err("Can't insert iomem_resource [%llx - %llx]\n", - res->start, res->end); - release_memory_resource(res_hostmem); - res_hostmem = NULL; - res->start = res->end = 0; - } - } - - if (ret) { - ret = allocate_resource(&iomem_resource, res, - size, 0, -1, - PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); - if (ret < 0) { - pr_err("Cannot allocate new System RAM resource\n"); - kfree(res); - return NULL; - } + ret = allocate_resource(&iomem_resource, res, + size, 0, -1, + PAGES_PER_SECTION * PAGE_SIZE, NULL, NULL); + if (ret < 0) { + pr_err("Cannot allocate new System RAM resource\n"); + kfree(res); + return NULL; } #ifdef CONFIG_SPARSEMEM @@ -325,7 +281,6 @@ static struct resource *additional_memory_resource(phys_addr_t size) pr_err("New System RAM resource outside addressable RAM (%lu > %lu)\n", pfn, limit); release_memory_resource(res); - release_memory_resource(res_hostmem); return NULL; } } @@ -750,8 +705,6 @@ static int __init balloon_init(void) set_online_page_callback(&xen_online_page); register_memory_notifier(&xen_memory_nb); register_sysctl_table(xen_root); - - arch_xen_balloon_init(&hostmem_resource); #endif #ifdef CONFIG_XEN_PV diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 2f11ca72a281..77224d8f3e6f 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -385,8 +385,8 @@ static int create_active(struct sock_mapping *map, int *evtchn) out_error: if (*evtchn >= 0) xenbus_free_evtchn(pvcalls_front_dev, *evtchn); - kfree(map->active.data.in); - kfree(map->active.ring); + free_pages((unsigned long)map->active.data.in, PVCALLS_RING_ORDER); + free_page((unsigned long)map->active.ring); return ret; } diff --git a/drivers/xen/xlate_mmu.c b/drivers/xen/xlate_mmu.c index 23f1387b3ef7..e7df65d32c91 100644 --- a/drivers/xen/xlate_mmu.c +++ b/drivers/xen/xlate_mmu.c @@ -36,6 +36,7 @@ #include <asm/xen/hypervisor.h> #include <xen/xen.h> +#include <xen/xen-ops.h> #include <xen/page.h> #include <xen/interface/xen.h> #include <xen/interface/memory.h> diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 43dea3b00c29..8a2562e3a316 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -1075,8 +1075,6 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, if (fc->ac.error < 0) return; - d_drop(new_dentry); - inode = afs_iget(fc->vnode->vfs_inode.i_sb, fc->key, newfid, newstatus, newcb, fc->cbi); if (IS_ERR(inode)) { @@ -1090,7 +1088,7 @@ static void afs_vnode_new_inode(struct afs_fs_cursor *fc, vnode = AFS_FS_I(inode); set_bit(AFS_VNODE_NEW_CONTENT, &vnode->flags); afs_vnode_commit_status(fc, vnode, 0); - d_add(new_dentry, inode); + d_instantiate(new_dentry, inode); } /* diff --git a/fs/afs/fs_probe.c b/fs/afs/fs_probe.c index d049cb459742..fde6b4d4121e 100644 --- a/fs/afs/fs_probe.c +++ b/fs/afs/fs_probe.c @@ -61,8 +61,11 @@ void afs_fileserver_probe_result(struct afs_call *call) afs_io_error(call, afs_io_error_fs_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -132,12 +135,14 @@ out: static int afs_do_probe_fileserver(struct afs_net *net, struct afs_server *server, struct key *key, - unsigned int server_index) + unsigned int server_index, + struct afs_error *_e) { struct afs_addr_cursor ac = { .index = 0, }; - int ret; + bool in_progress = false; + int err; _enter("%pU", &server->uuid); @@ -151,15 +156,17 @@ static int afs_do_probe_fileserver(struct afs_net *net, server->probe.rtt = UINT_MAX; for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { - ret = afs_fs_get_capabilities(net, server, &ac, key, server_index, + err = afs_fs_get_capabilities(net, server, &ac, key, server_index, true); - if (ret != -EINPROGRESS) { - afs_fs_probe_done(server); - return ret; - } + if (err == -EINPROGRESS) + in_progress = true; + else + afs_prioritise_error(_e, err, ac.abort_code); } - return 0; + if (!in_progress) + afs_fs_probe_done(server); + return in_progress; } /* @@ -169,21 +176,23 @@ int afs_probe_fileservers(struct afs_net *net, struct key *key, struct afs_server_list *list) { struct afs_server *server; - int i, ret; + struct afs_error e; + bool in_progress = false; + int i; + e.error = 0; + e.responded = false; for (i = 0; i < list->nr_servers; i++) { server = list->servers[i].server; if (test_bit(AFS_SERVER_FL_PROBED, &server->flags)) continue; - if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags)) { - ret = afs_do_probe_fileserver(net, server, key, i); - if (ret) - return ret; - } + if (!test_and_set_bit_lock(AFS_SERVER_FL_PROBING, &server->flags) && + afs_do_probe_fileserver(net, server, key, i, &e)) + in_progress = true; } - return 0; + return in_progress ? 0 : e.error; } /* diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 4c6d8e1112c2..6b17d3620414 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -382,7 +382,7 @@ void afs_zap_data(struct afs_vnode *vnode) int afs_validate(struct afs_vnode *vnode, struct key *key) { time64_t now = ktime_get_real_seconds(); - bool valid = false; + bool valid; int ret; _enter("{v={%llx:%llu} fl=%lx},%x", @@ -402,15 +402,21 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->cb_v_break = vnode->volume->cb_v_break; valid = false; } else if (vnode->status.type == AFS_FTYPE_DIR && - test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) && - vnode->cb_expires_at - 10 > now) { - valid = true; - } else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) && - vnode->cb_expires_at - 10 > now) { + (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags) || + vnode->cb_expires_at - 10 <= now)) { + valid = false; + } else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) || + vnode->cb_expires_at - 10 <= now) { + valid = false; + } else { valid = true; } } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { valid = true; + } else { + vnode->cb_s_break = vnode->cb_interest->server->cb_s_break; + vnode->cb_v_break = vnode->volume->cb_v_break; + valid = false; } read_sequnlock_excl(&vnode->cb_lock); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 5da3b09b7518..8871b9e8645f 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -696,6 +696,14 @@ struct afs_interface { }; /* + * Error prioritisation and accumulation. + */ +struct afs_error { + short error; /* Accumulated error */ + bool responded; /* T if server responded */ +}; + +/* * Cursor for iterating over a server's address list. */ struct afs_addr_cursor { @@ -1015,6 +1023,7 @@ static inline void __afs_stat(atomic_t *s) * misc.c */ extern int afs_abort_to_error(u32); +extern void afs_prioritise_error(struct afs_error *, int, u32); /* * mntpt.c diff --git a/fs/afs/misc.c b/fs/afs/misc.c index 700a5fa7f4ec..bbb1fd51b019 100644 --- a/fs/afs/misc.c +++ b/fs/afs/misc.c @@ -118,3 +118,55 @@ int afs_abort_to_error(u32 abort_code) default: return -EREMOTEIO; } } + +/* + * Select the error to report from a set of errors. + */ +void afs_prioritise_error(struct afs_error *e, int error, u32 abort_code) +{ + switch (error) { + case 0: + return; + default: + if (e->error == -ETIMEDOUT || + e->error == -ETIME) + return; + case -ETIMEDOUT: + case -ETIME: + if (e->error == -ENOMEM || + e->error == -ENONET) + return; + case -ENOMEM: + case -ENONET: + if (e->error == -ERFKILL) + return; + case -ERFKILL: + if (e->error == -EADDRNOTAVAIL) + return; + case -EADDRNOTAVAIL: + if (e->error == -ENETUNREACH) + return; + case -ENETUNREACH: + if (e->error == -EHOSTUNREACH) + return; + case -EHOSTUNREACH: + if (e->error == -EHOSTDOWN) + return; + case -EHOSTDOWN: + if (e->error == -ECONNREFUSED) + return; + case -ECONNREFUSED: + if (e->error == -ECONNRESET) + return; + case -ECONNRESET: /* Responded, but call expired. */ + if (e->responded) + return; + e->error = error; + return; + + case -ECONNABORTED: + e->responded = true; + e->error = afs_abort_to_error(abort_code); + return; + } +} diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index 00504254c1c2..c3ae324781f8 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -136,7 +136,8 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) struct afs_addr_list *alist; struct afs_server *server; struct afs_vnode *vnode = fc->vnode; - u32 rtt, abort_code; + struct afs_error e; + u32 rtt; int error = fc->ac.error, i; _enter("%lx[%d],%lx[%d],%d,%d", @@ -306,8 +307,11 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) if (fc->error != -EDESTADDRREQ) goto iterate_address; /* Fall through */ + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: _debug("no conn"); fc->error = error; @@ -446,50 +450,15 @@ no_more_servers: if (fc->flags & AFS_FS_CURSOR_VBUSY) goto restart_from_beginning; - abort_code = 0; - error = -EDESTADDRREQ; + e.error = -EDESTADDRREQ; + e.responded = false; for (i = 0; i < fc->server_list->nr_servers; i++) { struct afs_server *s = fc->server_list->servers[i].server; - int probe_error = READ_ONCE(s->probe.error); - switch (probe_error) { - case 0: - continue; - default: - if (error == -ETIMEDOUT || - error == -ETIME) - continue; - case -ETIMEDOUT: - case -ETIME: - if (error == -ENOMEM || - error == -ENONET) - continue; - case -ENOMEM: - case -ENONET: - if (error == -ENETUNREACH) - continue; - case -ENETUNREACH: - if (error == -EHOSTUNREACH) - continue; - case -EHOSTUNREACH: - if (error == -ECONNREFUSED) - continue; - case -ECONNREFUSED: - if (error == -ECONNRESET) - continue; - case -ECONNRESET: /* Responded, but call expired. */ - if (error == -ECONNABORTED) - continue; - case -ECONNABORTED: - abort_code = s->probe.abort_code; - error = probe_error; - continue; - } + afs_prioritise_error(&e, READ_ONCE(s->probe.error), + s->probe.abort_code); } - if (error == -ECONNABORTED) - error = afs_abort_to_error(abort_code); - failed_set_error: fc->error = error; failed: @@ -553,8 +522,11 @@ bool afs_select_current_fileserver(struct afs_fs_cursor *fc) _leave(" = f [abort]"); return false; + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -633,6 +605,7 @@ int afs_end_vnode_operation(struct afs_fs_cursor *fc) struct afs_net *net = afs_v2net(fc->vnode); if (fc->error == -EDESTADDRREQ || + fc->error == -EADDRNOTAVAIL || fc->error == -ENETUNREACH || fc->error == -EHOSTUNREACH) afs_dump_edestaddrreq(fc); diff --git a/fs/afs/vl_probe.c b/fs/afs/vl_probe.c index c0f616bd70cb..f0b032976487 100644 --- a/fs/afs/vl_probe.c +++ b/fs/afs/vl_probe.c @@ -61,8 +61,11 @@ void afs_vlserver_probe_result(struct afs_call *call) afs_io_error(call, afs_io_error_vl_probe_fail); goto out; case -ECONNRESET: /* Responded, but call expired. */ + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -129,15 +132,17 @@ out: * Probe all of a vlserver's addresses to find out the best route and to * query its capabilities. */ -static int afs_do_probe_vlserver(struct afs_net *net, - struct afs_vlserver *server, - struct key *key, - unsigned int server_index) +static bool afs_do_probe_vlserver(struct afs_net *net, + struct afs_vlserver *server, + struct key *key, + unsigned int server_index, + struct afs_error *_e) { struct afs_addr_cursor ac = { .index = 0, }; - int ret; + bool in_progress = false; + int err; _enter("%s", server->name); @@ -151,15 +156,17 @@ static int afs_do_probe_vlserver(struct afs_net *net, server->probe.rtt = UINT_MAX; for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++) { - ret = afs_vl_get_capabilities(net, &ac, key, server, + err = afs_vl_get_capabilities(net, &ac, key, server, server_index, true); - if (ret != -EINPROGRESS) { - afs_vl_probe_done(server); - return ret; - } + if (err == -EINPROGRESS) + in_progress = true; + else + afs_prioritise_error(_e, err, ac.abort_code); } - return 0; + if (!in_progress) + afs_vl_probe_done(server); + return in_progress; } /* @@ -169,21 +176,23 @@ int afs_send_vl_probes(struct afs_net *net, struct key *key, struct afs_vlserver_list *vllist) { struct afs_vlserver *server; - int i, ret; + struct afs_error e; + bool in_progress = false; + int i; + e.error = 0; + e.responded = false; for (i = 0; i < vllist->nr_servers; i++) { server = vllist->servers[i].server; if (test_bit(AFS_VLSERVER_FL_PROBED, &server->flags)) continue; - if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags)) { - ret = afs_do_probe_vlserver(net, server, key, i); - if (ret) - return ret; - } + if (!test_and_set_bit_lock(AFS_VLSERVER_FL_PROBING, &server->flags) && + afs_do_probe_vlserver(net, server, key, i, &e)) + in_progress = true; } - return 0; + return in_progress ? 0 : e.error; } /* diff --git a/fs/afs/vl_rotate.c b/fs/afs/vl_rotate.c index b64a284b99d2..7adde83a0648 100644 --- a/fs/afs/vl_rotate.c +++ b/fs/afs/vl_rotate.c @@ -71,8 +71,9 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc) { struct afs_addr_list *alist; struct afs_vlserver *vlserver; + struct afs_error e; u32 rtt; - int error = vc->ac.error, abort_code, i; + int error = vc->ac.error, i; _enter("%lx[%d],%lx[%d],%d,%d", vc->untried, vc->index, @@ -119,8 +120,11 @@ bool afs_select_vlserver(struct afs_vl_cursor *vc) goto failed; } + case -ERFKILL: + case -EADDRNOTAVAIL: case -ENETUNREACH: case -EHOSTUNREACH: + case -EHOSTDOWN: case -ECONNREFUSED: case -ETIMEDOUT: case -ETIME: @@ -235,50 +239,15 @@ no_more_servers: if (vc->flags & AFS_VL_CURSOR_RETRY) goto restart_from_beginning; - abort_code = 0; - error = -EDESTADDRREQ; + e.error = -EDESTADDRREQ; + e.responded = false; for (i = 0; i < vc->server_list->nr_servers; i++) { struct afs_vlserver *s = vc->server_list->servers[i].server; - int probe_error = READ_ONCE(s->probe.error); - switch (probe_error) { - case 0: - continue; - default: - if (error == -ETIMEDOUT || - error == -ETIME) - continue; - case -ETIMEDOUT: - case -ETIME: - if (error == -ENOMEM || - error == -ENONET) - continue; - case -ENOMEM: - case -ENONET: - if (error == -ENETUNREACH) - continue; - case -ENETUNREACH: - if (error == -EHOSTUNREACH) - continue; - case -EHOSTUNREACH: - if (error == -ECONNREFUSED) - continue; - case -ECONNREFUSED: - if (error == -ECONNRESET) - continue; - case -ECONNRESET: /* Responded, but call expired. */ - if (error == -ECONNABORTED) - continue; - case -ECONNABORTED: - abort_code = s->probe.abort_code; - error = probe_error; - continue; - } + afs_prioritise_error(&e, READ_ONCE(s->probe.error), + s->probe.abort_code); } - if (error == -ECONNABORTED) - error = afs_abort_to_error(abort_code); - failed_set_error: vc->error = error; failed: @@ -341,6 +310,7 @@ int afs_end_vlserver_operation(struct afs_vl_cursor *vc) struct afs_net *net = vc->cell->net; if (vc->error == -EDESTADDRREQ || + vc->error == -EADDRNOTAVAIL || vc->error == -ENETUNREACH || vc->error == -EHOSTUNREACH) afs_vl_dump_edestaddrreq(vc); @@ -1436,6 +1436,7 @@ static int aio_prep_rw(struct kiocb *req, struct iocb *iocb) ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); + fput(req->ki_filp); return ret; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 3f0b6d1936e8..6d776717d8b3 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -477,9 +477,9 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, int mirror_num = 0; int failed_mirror = 0; - clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; while (1) { + clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags); ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE, mirror_num); if (!ret) { @@ -493,15 +493,6 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info, break; } - /* - * This buffer's crc is fine, but its contents are corrupted, so - * there is no reason to read the other copies, they won't be - * any less wrong. - */ - if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags) || - ret == -EUCLEAN) - break; - num_copies = btrfs_num_copies(fs_info, eb->start, eb->len); if (num_copies == 1) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a3c22e16509b..58e93bce3036 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2089,6 +2089,30 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) atomic_inc(&root->log_batch); /* + * Before we acquired the inode's lock, someone may have dirtied more + * pages in the target range. We need to make sure that writeback for + * any such pages does not start while we are logging the inode, because + * if it does, any of the following might happen when we are not doing a + * full inode sync: + * + * 1) We log an extent after its writeback finishes but before its + * checksums are added to the csum tree, leading to -EIO errors + * when attempting to read the extent after a log replay. + * + * 2) We can end up logging an extent before its writeback finishes. + * Therefore after the log replay we will have a file extent item + * pointing to an unwritten extent (and no data checksums as well). + * + * So trigger writeback for any eventual new dirty pages and then we + * wait for all ordered extents to complete below. + */ + ret = start_ordered_ops(inode, start, end); + if (ret) { + inode_unlock(inode); + goto out; + } + + /* * We have to do this here to avoid the priority inversion of waiting on * IO of a lower priority task while holding a transaciton open. */ diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 45868fd76209..f70825af6438 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2659,7 +2659,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, int i; u64 *i_qgroups; struct btrfs_fs_info *fs_info = trans->fs_info; - struct btrfs_root *quota_root = fs_info->quota_root; + struct btrfs_root *quota_root; struct btrfs_qgroup *srcgroup; struct btrfs_qgroup *dstgroup; u32 level_size = 0; @@ -2669,6 +2669,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid, if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) goto out; + quota_root = fs_info->quota_root; if (!quota_root) { ret = -EINVAL; goto out; diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 924116f654a1..a3f75b8926d4 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3959,6 +3959,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc) restart: if (update_backref_cache(trans, &rc->backref_cache)) { btrfs_end_transaction(trans); + trans = NULL; continue; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 094cc1444a90..5be83b5a1b43 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -3340,7 +3340,8 @@ static void free_pending_move(struct send_ctx *sctx, struct pending_dir_move *m) kfree(m); } -static void tail_append_pending_moves(struct pending_dir_move *moves, +static void tail_append_pending_moves(struct send_ctx *sctx, + struct pending_dir_move *moves, struct list_head *stack) { if (list_empty(&moves->list)) { @@ -3351,6 +3352,10 @@ static void tail_append_pending_moves(struct pending_dir_move *moves, list_add_tail(&moves->list, stack); list_splice_tail(&list, stack); } + if (!RB_EMPTY_NODE(&moves->node)) { + rb_erase(&moves->node, &sctx->pending_dir_moves); + RB_CLEAR_NODE(&moves->node); + } } static int apply_children_dir_moves(struct send_ctx *sctx) @@ -3365,7 +3370,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx) return 0; INIT_LIST_HEAD(&stack); - tail_append_pending_moves(pm, &stack); + tail_append_pending_moves(sctx, pm, &stack); while (!list_empty(&stack)) { pm = list_first_entry(&stack, struct pending_dir_move, list); @@ -3376,7 +3381,7 @@ static int apply_children_dir_moves(struct send_ctx *sctx) goto out; pm = get_pending_dir_moves(sctx, parent_ino); if (pm) - tail_append_pending_moves(pm, &stack); + tail_append_pending_moves(sctx, pm, &stack); } return 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cbc9d0d2c12d..645fc81e2a94 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2237,6 +2237,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, vol = memdup_user((void __user *)arg, sizeof(*vol)); if (IS_ERR(vol)) return PTR_ERR(vol); + vol->name[BTRFS_PATH_NAME_MAX] = '\0'; switch (cmd) { case BTRFS_IOC_SCAN_DEV: diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 95983c744164..1645fcfd9691 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -244,11 +244,13 @@ wait_for_old_object: ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &xobject->flags)); - cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_retry); + cache->cache.ops->put_object(&xobject->fscache, + (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_retry); goto try_again; requeue: - cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo); + cache->cache.ops->put_object(&xobject->fscache, + (enum fscache_obj_ref_trace)cachefiles_obj_put_wait_timeo); _leave(" = -ETIMEDOUT"); return -ETIMEDOUT; } @@ -336,7 +338,7 @@ static int cachefiles_bury_object(struct cachefiles_cache *cache, try_again: /* first step is to make up a grave dentry in the graveyard */ sprintf(nbuffer, "%08x%08x", - (uint32_t) get_seconds(), + (uint32_t) ktime_get_real_seconds(), (uint32_t) atomic_inc_return(&cache->gravecounter)); /* do the multiway lock magic */ diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 40f7595aad10..8a577409d030 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -535,7 +535,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { + put_page(backpage); + backpage = NULL; put_page(netpage); + netpage = NULL; fscache_retrieval_complete(op, 1); continue; } @@ -608,7 +611,10 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, netpage->index, cachefiles_gfp); if (ret < 0) { if (ret == -EEXIST) { + put_page(backpage); + backpage = NULL; put_page(netpage); + netpage = NULL; fscache_retrieval_complete(op, 1); continue; } @@ -962,11 +968,8 @@ void cachefiles_uncache_page(struct fscache_object *_object, struct page *page) __releases(&object->fscache.cookie->lock) { struct cachefiles_object *object; - struct cachefiles_cache *cache; object = container_of(_object, struct cachefiles_object, fscache); - cache = container_of(object->fscache.cache, - struct cachefiles_cache, cache); _enter("%p,{%lu}", object, page->index); diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 0a29a00aed2e..511e6c68156a 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -135,7 +135,8 @@ int cachefiles_update_object_xattr(struct cachefiles_object *object, struct dentry *dentry = object->dentry; int ret; - ASSERT(dentry); + if (!dentry) + return -ESTALE; _enter("%p,#%d", object, auxdata->len); diff --git a/fs/direct-io.c b/fs/direct-io.c index 722d17c88edb..41a0e97252ae 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -325,8 +325,8 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) */ dio->iocb->ki_pos += transferred; - if (dio->op == REQ_OP_WRITE) - ret = generic_write_sync(dio->iocb, transferred); + if (ret > 0 && dio->op == REQ_OP_WRITE) + ret = generic_write_sync(dio->iocb, ret); dio->iocb->ki_complete(dio->iocb, ret, 0); } diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 645158dc33f1..c69927bed4ef 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -77,7 +77,7 @@ static bool dentry_connected(struct dentry *dentry) struct dentry *parent = dget_parent(dentry); dput(dentry); - if (IS_ROOT(dentry)) { + if (dentry == parent) { dput(parent); return false; } @@ -147,6 +147,7 @@ static struct dentry *reconnect_one(struct vfsmount *mnt, tmp = lookup_one_len_unlocked(nbuf, parent, strlen(nbuf)); if (IS_ERR(tmp)) { dprintk("%s: lookup failed: %d\n", __func__, PTR_ERR(tmp)); + err = PTR_ERR(tmp); goto out_err; } if (tmp != dentry) { diff --git a/fs/ext2/super.c b/fs/ext2/super.c index cb91baa4275d..eb11502e3fcd 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -892,6 +892,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) if (sb->s_magic != EXT2_SUPER_MAGIC) goto cantfind_ext2; + opts.s_mount_opt = 0; /* Set defaults before we parse the mount options */ def_mount_opts = le32_to_cpu(es->s_default_mount_opts); if (def_mount_opts & EXT2_DEFM_DEBUG) diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 62d9a659a8ff..dd8f10db82e9 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -612,9 +612,9 @@ skip_replace: } cleanup: - brelse(bh); if (!(bh && header == HDR(bh))) kfree(header); + brelse(bh); up_write(&EXT2_I(inode)->xattr_sem); return error; diff --git a/fs/fscache/object.c b/fs/fscache/object.c index 9edc920f651f..6d9cb1719de5 100644 --- a/fs/fscache/object.c +++ b/fs/fscache/object.c @@ -730,6 +730,9 @@ static const struct fscache_state *fscache_drop_object(struct fscache_object *ob if (awaken) wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); + if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) + wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); + /* Prevent a race with our last child, which has to signal EV_CLEARED * before dropping our spinlock. diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c index 98b96ffb95ed..19017d296173 100644 --- a/fs/hfs/btree.c +++ b/fs/hfs/btree.c @@ -338,13 +338,14 @@ void hfs_bmap_free(struct hfs_bnode *node) nidx -= len * 8; i = node->next; - hfs_bnode_put(node); if (!i) { /* panic */; pr_crit("unable to free bnode %u. bmap not found!\n", node->this); + hfs_bnode_put(node); return; } + hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c index 236efe51eca6..66774f4cb4fd 100644 --- a/fs/hfsplus/btree.c +++ b/fs/hfsplus/btree.c @@ -466,14 +466,15 @@ void hfs_bmap_free(struct hfs_bnode *node) nidx -= len * 8; i = node->next; - hfs_bnode_put(node); if (!i) { /* panic */; pr_crit("unable to free bnode %u. " "bmap not found!\n", node->this); + hfs_bnode_put(node); return; } + hfs_bnode_put(node); node = hfs_bnode_find(tree, i); if (IS_ERR(node)) return; diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c index 9f88188060db..4bf8d5854b27 100644 --- a/fs/ocfs2/export.c +++ b/fs/ocfs2/export.c @@ -125,10 +125,10 @@ check_err: check_gen: if (handle->ih_generation != inode->i_generation) { - iput(inode); trace_ocfs2_get_dentry_generation((unsigned long long)blkno, handle->ih_generation, inode->i_generation); + iput(inode); result = ERR_PTR(-ESTALE); goto bail; } diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 3f1685d7d43b..1565dd8e8856 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -157,18 +157,14 @@ out: } /* - * lock allocators, and reserving appropriate number of bits for - * meta blocks and data clusters. - * - * in some cases, we don't need to reserve clusters, just let data_ac - * be NULL. + * lock allocator, and reserve appropriate number of bits for + * meta blocks. */ -static int ocfs2_lock_allocators_move_extents(struct inode *inode, +static int ocfs2_lock_meta_allocator_move_extents(struct inode *inode, struct ocfs2_extent_tree *et, u32 clusters_to_move, u32 extents_to_split, struct ocfs2_alloc_context **meta_ac, - struct ocfs2_alloc_context **data_ac, int extra_blocks, int *credits) { @@ -193,13 +189,6 @@ static int ocfs2_lock_allocators_move_extents(struct inode *inode, goto out; } - if (data_ac) { - ret = ocfs2_reserve_clusters(osb, clusters_to_move, data_ac); - if (ret) { - mlog_errno(ret); - goto out; - } - } *credits += ocfs2_calc_extend_credits(osb->sb, et->et_root_el); @@ -259,10 +248,10 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } } - ret = ocfs2_lock_allocators_move_extents(inode, &context->et, *len, 1, - &context->meta_ac, - &context->data_ac, - extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + *len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out; @@ -285,6 +274,21 @@ static int ocfs2_defrag_extent(struct ocfs2_move_extents_context *context, } } + /* + * Make sure ocfs2_reserve_cluster is called after + * __ocfs2_flush_truncate_log, otherwise, dead lock may happen. + * + * If ocfs2_reserve_cluster is called + * before __ocfs2_flush_truncate_log, dead lock on global bitmap + * may happen. + * + */ + ret = ocfs2_reserve_clusters(osb, *len, &context->data_ac); + if (ret) { + mlog_errno(ret); + goto out_unlock_mutex; + } + handle = ocfs2_start_trans(osb, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); @@ -617,9 +621,10 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context, } } - ret = ocfs2_lock_allocators_move_extents(inode, &context->et, len, 1, - &context->meta_ac, - NULL, extra_blocks, &credits); + ret = ocfs2_lock_meta_allocator_move_extents(inode, &context->et, + len, 1, + &context->meta_ac, + extra_blocks, &credits); if (ret) { mlog_errno(ret); goto out; diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c index ffcff6516e89..e02a9039b5ea 100644 --- a/fs/pstore/ram.c +++ b/fs/pstore/ram.c @@ -816,17 +816,14 @@ static int ramoops_probe(struct platform_device *pdev) cxt->pstore.data = cxt; /* - * Console can handle any buffer size, so prefer LOG_LINE_MAX. If we - * have to handle dumps, we must have at least record_size buffer. And - * for ftrace, bufsize is irrelevant (if bufsize is 0, buf will be - * ZERO_SIZE_PTR). + * Since bufsize is only used for dmesg crash dumps, it + * must match the size of the dprz record (after PRZ header + * and ECC bytes have been accounted for). */ - if (cxt->console_size) - cxt->pstore.bufsize = 1024; /* LOG_LINE_MAX */ - cxt->pstore.bufsize = max(cxt->record_size, cxt->pstore.bufsize); - cxt->pstore.buf = kmalloc(cxt->pstore.bufsize, GFP_KERNEL); + cxt->pstore.bufsize = cxt->dprzs[0]->buffer_size; + cxt->pstore.buf = kzalloc(cxt->pstore.bufsize, GFP_KERNEL); if (!cxt->pstore.buf) { - pr_err("cannot allocate pstore buffer\n"); + pr_err("cannot allocate pstore crash dump buffer\n"); err = -ENOMEM; goto fail_clear; } diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 499a20a5a010..273736f41be3 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -275,7 +275,7 @@ static int __sysv_write_inode(struct inode *inode, int wait) } } brelse(bh); - return 0; + return err; } int sysv_write_inode(struct inode *inode, struct writeback_control *wbc) diff --git a/fs/udf/super.c b/fs/udf/super.c index 8f2f56d9a1bb..e3d684ea3203 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -827,16 +827,20 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block) ret = udf_dstrCS0toChar(sb, outstr, 31, pvoldesc->volIdent, 32); - if (ret < 0) - goto out_bh; - - strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret); + if (ret < 0) { + strcpy(UDF_SB(sb)->s_volume_ident, "InvalidName"); + pr_warn("incorrect volume identification, setting to " + "'InvalidName'\n"); + } else { + strncpy(UDF_SB(sb)->s_volume_ident, outstr, ret); + } udf_debug("volIdent[] = '%s'\n", UDF_SB(sb)->s_volume_ident); ret = udf_dstrCS0toChar(sb, outstr, 127, pvoldesc->volSetIdent, 128); - if (ret < 0) + if (ret < 0) { + ret = 0; goto out_bh; - + } outstr[ret] = 0; udf_debug("volSetIdent[] = '%s'\n", outstr); diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index 45234791fec2..5fcfa96463eb 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -351,6 +351,11 @@ try_again: return u_len; } +/* + * Convert CS0 dstring to output charset. Warning: This function may truncate + * input string if it is too long as it is used for informational strings only + * and it is better to truncate the string than to refuse mounting a media. + */ int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len, const uint8_t *ocu_i, int i_len) { @@ -359,9 +364,12 @@ int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len, if (i_len > 0) { s_len = ocu_i[i_len - 1]; if (s_len >= i_len) { - pr_err("incorrect dstring lengths (%d/%d)\n", - s_len, i_len); - return -EINVAL; + pr_warn("incorrect dstring lengths (%d/%d)," + " truncating\n", s_len, i_len); + s_len = i_len - 1; + /* 2-byte encoding? Need to round properly... */ + if (ocu_i[0] == 16) + s_len -= (s_len - 1) & 2; } } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 356d2b8568c1..cd58939dc977 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1361,6 +1361,19 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, ret = -EINVAL; if (!vma_can_userfault(cur)) goto out_unlock; + + /* + * UFFDIO_COPY will fill file holes even without + * PROT_WRITE. This check enforces that if this is a + * MAP_SHARED, the process has write permission to the backing + * file. If VM_MAYWRITE is set it also enforces that on a + * MAP_SHARED vma: there is no F_WRITE_SEAL and no further + * F_WRITE_SEAL can be taken until the vma is destroyed. + */ + ret = -EPERM; + if (unlikely(!(cur->vm_flags & VM_MAYWRITE))) + goto out_unlock; + /* * If this vma contains ending address, and huge pages * check alignment. @@ -1406,6 +1419,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, BUG_ON(!vma_can_userfault(vma)); BUG_ON(vma->vm_userfaultfd_ctx.ctx && vma->vm_userfaultfd_ctx.ctx != ctx); + WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); /* * Nothing to do: this vma is already registered into this @@ -1552,6 +1566,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, cond_resched(); BUG_ON(!vma_can_userfault(vma)); + WARN_ON(!(vma->vm_flags & VM_MAYWRITE)); /* * Nothing to do: this vma is already registered into this diff --git a/include/linux/filter.h b/include/linux/filter.h index de629b706d1d..448dcc448f1f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -866,6 +866,10 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr); void bpf_jit_free(struct bpf_prog *fp); +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed); + struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 34cf0fdd7dc7..610815e3f1aa 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -196,8 +196,7 @@ static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) static inline void fscache_retrieval_complete(struct fscache_retrieval *op, int n_pages) { - atomic_sub(n_pages, &op->n_pages); - if (atomic_read(&op->n_pages) <= 0) + if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) fscache_op_complete(&op->op, false); } diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index a397907e8d72..dd16e8218db3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -777,8 +777,8 @@ struct ftrace_ret_stack { extern void return_to_handler(void); extern int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, - unsigned long frame_pointer, unsigned long *retp); +function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp); unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, unsigned long ret, unsigned long *retp); diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 331dc377c275..dc12f5c4b076 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -177,6 +177,7 @@ int sensor_hub_input_get_attribute_info(struct hid_sensor_hub_device *hsdev, * @attr_usage_id: Attribute usage id as per spec * @report_id: Report id to look for * @flag: Synchronous or asynchronous read +* @is_signed: If true then fields < 32 bits will be sign-extended * * Issues a synchronous or asynchronous read request for an input attribute. * Returns data upto 32 bits. @@ -190,7 +191,8 @@ enum sensor_hub_read_flags { int sensor_hub_input_attr_get_raw_value(struct hid_sensor_hub_device *hsdev, u32 usage_id, u32 attr_usage_id, u32 report_id, - enum sensor_hub_read_flags flag + enum sensor_hub_read_flags flag, + bool is_signed ); /** diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dbff9ff28f2c..34e17e6f8942 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -2473,14 +2473,15 @@ struct mlx5_ifc_xrc_srqc_bits { u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 dbr_umem_valid[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_at_46[0x2]; + u8 reserved_at_46[0x1]; + u8 dbr_umem_valid[0x1]; u8 cqn[0x18]; u8 reserved_at_60[0x20]; @@ -6689,9 +6690,12 @@ struct mlx5_ifc_create_xrc_srq_in_bits { struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_at_280[0x40]; + u8 reserved_at_280[0x60]; + u8 xrc_srq_umem_valid[0x1]; - u8 reserved_at_2c1[0x5bf]; + u8 reserved_at_2e1[0x1f]; + + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h index b8d95564bd53..14edb795ab43 100644 --- a/include/linux/netfilter/nf_conntrack_proto_gre.h +++ b/include/linux/netfilter/nf_conntrack_proto_gre.h @@ -21,6 +21,19 @@ struct nf_ct_gre_keymap { struct nf_conntrack_tuple tuple; }; +enum grep_conntrack { + GRE_CT_UNREPLIED, + GRE_CT_REPLIED, + GRE_CT_MAX +}; + +struct netns_proto_gre { + struct nf_proto_net nf; + rwlock_t keymap_lock; + struct list_head keymap_list; + unsigned int gre_timeouts[GRE_CT_MAX]; +}; + /* add new tuple->key_reply pair to keymap */ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t); diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h index f92a47e18034..a93841bfb9f7 100644 --- a/include/linux/platform_data/gpio-davinci.h +++ b/include/linux/platform_data/gpio-davinci.h @@ -17,6 +17,8 @@ #define __DAVINCI_GPIO_PLATFORM_H struct davinci_gpio_platform_data { + bool no_auto_base; + u32 base; u32 ngpio; u32 gpio_unbanked; }; diff --git a/include/linux/psi.h b/include/linux/psi.h index 8e0725aac0aa..7006008d5b72 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,6 +1,7 @@ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H +#include <linux/jump_label.h> #include <linux/psi_types.h> #include <linux/sched.h> @@ -9,7 +10,7 @@ struct css_set; #ifdef CONFIG_PSI -extern bool psi_disabled; +extern struct static_key_false psi_disabled; void psi_init(void); diff --git a/include/linux/pstore.h b/include/linux/pstore.h index a15bc4d48752..30fcec375a3a 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -90,7 +90,10 @@ struct pstore_record { * * @buf_lock: spinlock to serialize access to @buf * @buf: preallocated crash dump buffer - * @bufsize: size of @buf available for crash dump writes + * @bufsize: size of @buf available for crash dump bytes (must match + * smallest number of bytes available for writing to a + * backend entry, since compressed bytes don't take kindly + * to being truncated) * * @read_mutex: serializes @open, @read, @close, and @erase callbacks * @flags: bitfield of frontends the backend can accept writes for diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index 6c2ffed907f5..de20ede2c5c8 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -64,15 +64,12 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); #define PTRACE_MODE_NOAUDIT 0x04 #define PTRACE_MODE_FSCREDS 0x08 #define PTRACE_MODE_REALCREDS 0x10 -#define PTRACE_MODE_SCHED 0x20 -#define PTRACE_MODE_IBPB 0x40 /* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */ #define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS) #define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS) #define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS) -#define PTRACE_MODE_SPEC_IBPB (PTRACE_MODE_ATTACH_REALCREDS | PTRACE_MODE_IBPB) /** * ptrace_may_access - check whether the caller is permitted to access @@ -90,20 +87,6 @@ extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead); */ extern bool ptrace_may_access(struct task_struct *task, unsigned int mode); -/** - * ptrace_may_access - check whether the caller is permitted to access - * a target task. - * @task: target task - * @mode: selects type of access and caller credentials - * - * Returns true on success, false on denial. - * - * Similar to ptrace_may_access(). Only to be called from context switch - * code. Does not call into audit and the regular LSM hooks due to locking - * constraints. - */ -extern bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode); - static inline int ptrace_reparented(struct task_struct *child) { return !same_thread_group(child->real_parent, child->parent); diff --git a/include/linux/sched.h b/include/linux/sched.h index a51c13c2b1a0..291a9bd5b97f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1116,6 +1116,7 @@ struct task_struct { #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* Index of current stored address in ret_stack: */ int curr_ret_stack; + int curr_ret_depth; /* Stack of return addresses for return function tracing: */ struct ftrace_ret_stack *ret_stack; @@ -1453,6 +1454,8 @@ static inline bool is_percpu_thread(void) #define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ #define PFA_SPEC_SSB_DISABLE 3 /* Speculative Store Bypass disabled */ #define PFA_SPEC_SSB_FORCE_DISABLE 4 /* Speculative Store Bypass force disabled*/ +#define PFA_SPEC_IB_DISABLE 5 /* Indirect branch speculation restricted */ +#define PFA_SPEC_IB_FORCE_DISABLE 6 /* Indirect branch speculation permanently restricted */ #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1484,6 +1487,13 @@ TASK_PFA_CLEAR(SPEC_SSB_DISABLE, spec_ssb_disable) TASK_PFA_TEST(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) TASK_PFA_SET(SPEC_SSB_FORCE_DISABLE, spec_ssb_force_disable) +TASK_PFA_TEST(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_SET(SPEC_IB_DISABLE, spec_ib_disable) +TASK_PFA_CLEAR(SPEC_IB_DISABLE, spec_ib_disable) + +TASK_PFA_TEST(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) +TASK_PFA_SET(SPEC_IB_FORCE_DISABLE, spec_ib_force_disable) + static inline void current_restore_flags(unsigned long orig_flags, unsigned long flags) { diff --git a/include/linux/sched/smt.h b/include/linux/sched/smt.h new file mode 100644 index 000000000000..59d3736c454c --- /dev/null +++ b/include/linux/sched/smt.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_SCHED_SMT_H +#define _LINUX_SCHED_SMT_H + +#include <linux/static_key.h> + +#ifdef CONFIG_SCHED_SMT +extern struct static_key_false sched_smt_present; + +static __always_inline bool sched_smt_active(void) +{ + return static_branch_likely(&sched_smt_present); +} +#else +static inline bool sched_smt_active(void) { return false; } +#endif + +void arch_smt_update(void); + +#endif diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 40b0b4c1bf7b..df20f8bdbfa3 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -83,8 +83,8 @@ static inline int ptrace_report_syscall(struct pt_regs *regs) * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * - * This will be called if %TIF_SYSCALL_TRACE has been set, when the - * current task has just entered the kernel for a system call. + * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, + * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 538ba1a58f5b..e9de8ad0bad7 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -166,7 +166,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ - int __maybe_unused idx = 0; \ + int __maybe_unused __idx = 0; \ \ if (!(cond)) \ return; \ @@ -182,7 +182,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * doesn't work from the idle path. \ */ \ if (rcuidle) { \ - idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + __idx = srcu_read_lock_notrace(&tracepoint_srcu);\ rcu_irq_enter_irqson(); \ } \ \ @@ -198,7 +198,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) \ if (rcuidle) { \ rcu_irq_exit_irqson(); \ - srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + srcu_read_unlock_notrace(&tracepoint_srcu, __idx);\ } \ \ preempt_enable_notrace(); \ diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h index cd24be4c4a99..13d55206bb9f 100644 --- a/include/net/netfilter/ipv4/nf_nat_masquerade.h +++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h @@ -9,7 +9,7 @@ nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, const struct nf_nat_range2 *range, const struct net_device *out); -void nf_nat_masquerade_ipv4_register_notifier(void); +int nf_nat_masquerade_ipv4_register_notifier(void); void nf_nat_masquerade_ipv4_unregister_notifier(void); #endif /*_NF_NAT_MASQUERADE_IPV4_H_ */ diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h index 0c3b5ebf0bb8..2917bf95c437 100644 --- a/include/net/netfilter/ipv6/nf_nat_masquerade.h +++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h @@ -5,7 +5,7 @@ unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out); -void nf_nat_masquerade_ipv6_register_notifier(void); +int nf_nat_masquerade_ipv6_register_notifier(void); void nf_nat_masquerade_ipv6_unregister_notifier(void); #endif /* _NF_NAT_MASQUERADE_IPV6_H_ */ diff --git a/include/sound/soc.h b/include/sound/soc.h index f1dab1f4b194..70c10a8f3e90 100644 --- a/include/sound/soc.h +++ b/include/sound/soc.h @@ -1192,7 +1192,7 @@ struct snd_soc_pcm_runtime { ((i) < rtd->num_codecs) && ((dai) = rtd->codec_dais[i]); \ (i)++) #define for_each_rtd_codec_dai_rollback(rtd, i, dai) \ - for (; ((i--) >= 0) && ((dai) = rtd->codec_dais[i]);) + for (; ((--i) >= 0) && ((dai) = rtd->codec_dais[i]);) /* mixer control */ diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index f07b270d4fc4..9a4bdfadab07 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -107,6 +107,8 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, #ifdef CREATE_TRACE_POINTS static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p) { + unsigned int state; + #ifdef CONFIG_SCHED_DEBUG BUG_ON(p != current); #endif /* CONFIG_SCHED_DEBUG */ @@ -118,7 +120,15 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct * if (preempt) return TASK_REPORT_MAX; - return 1 << task_state_index(p); + /* + * task_state_index() uses fls() and returns a value from 0-8 range. + * Decrement it by 1 (except TASK_RUNNING state i.e 0) before using + * it for left shift operation to get the correct task->state + * mapping. + */ + state = task_state_index(p); + + return state ? (1 << (state - 1)) : state; } #endif /* CREATE_TRACE_POINTS */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) diff --git a/include/xen/balloon.h b/include/xen/balloon.h index 61f410fd74e4..4914b93a23f2 100644 --- a/include/xen/balloon.h +++ b/include/xen/balloon.h @@ -44,8 +44,3 @@ static inline void xen_balloon_init(void) { } #endif - -#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG -struct resource; -void arch_xen_balloon_init(struct resource *hostmem_resource); -#endif diff --git a/init/Kconfig b/init/Kconfig index a4112e95724a..cf5b5a0dcbc2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -509,6 +509,15 @@ config PSI Say N if unsure. +config PSI_DEFAULT_DISABLED + bool "Require boot parameter to enable pressure stall information tracking" + default n + depends on PSI + help + If set, pressure stall information tracking will be disabled + per default but can be enabled through passing psi_enable=1 + on the kernel commandline during boot. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION diff --git a/init/initramfs.c b/init/initramfs.c index 640557788026..f6f4a1e4cd54 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -291,16 +291,6 @@ static int __init do_reset(void) return 1; } -static int __init maybe_link(void) -{ - if (nlink >= 2) { - char *old = find_link(major, minor, ino, mode, collected); - if (old) - return (ksys_link(old, collected) < 0) ? -1 : 1; - } - return 0; -} - static void __init clean_path(char *path, umode_t fmode) { struct kstat st; @@ -313,6 +303,18 @@ static void __init clean_path(char *path, umode_t fmode) } } +static int __init maybe_link(void) +{ + if (nlink >= 2) { + char *old = find_link(major, minor, ino, mode, collected); + if (old) { + clean_path(collected, 0); + return (ksys_link(old, collected) < 0) ? -1 : 1; + } + } + return 0; +} + static __initdata int wfd; static int __init do_name(void) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1a796e0799ec..b1a3545d0ec8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -672,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed) +{ + s16 off = insn->off; + s32 imm = insn->imm; + u8 *addr; + + *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; + if (!*func_addr_fixed) { + /* Place-holder address till the last pass has collected + * all addresses for JITed subprograms in which case we + * can pick them up from prog->aux. + */ + if (!extra_pass) + addr = NULL; + else if (prog->aux->func && + off >= 0 && off < prog->aux->func_cnt) + addr = (u8 *)prog->aux->func[off]->bpf_func; + else + return -EINVAL; + } else { + /* Address of a BPF helper call. Since part of the core + * kernel, it's always at a fixed location. __bpf_call_base + * and the helper with imm relative to it are both in core + * kernel. + */ + addr = (u8 *)__bpf_call_base + imm; + } + + *func_addr = (unsigned long)addr; + return 0; +} + static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index c97a8f968638..bed9d48a7ae9 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return -ENOENT; new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, + map->value_size, + __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, map->numa_node); if (!new) return -ENOMEM; diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8bbd72d3a121..b384ea9f3254 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -7,6 +7,7 @@ #include <linux/bpf.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/capability.h> #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ @@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) /* Called from syscall */ static int queue_stack_map_alloc_check(union bpf_attr *attr) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || + attr->value_size == 0 || attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) return -EINVAL; @@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { int ret, numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; - u32 size, value_size; - u64 queue_size, cost; - - size = attr->max_entries + 1; - value_size = attr->value_size; - - queue_size = sizeof(*qs) + (u64) value_size * size; + u64 size, queue_size, cost; - cost = queue_size; + size = (u64) attr->max_entries + 1; + cost = queue_size = sizeof(*qs) + size * attr->value_size; if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1971ca325fb4..6dd419550aba 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5650,7 +5650,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { - if (env->subprog_info[i].start < off) + if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 3c7f3b4c453c..91d5c38eb7e5 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -10,6 +10,7 @@ #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/task.h> +#include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> @@ -367,6 +368,12 @@ static void lockdep_release_cpus_lock(void) #endif /* CONFIG_HOTPLUG_CPU */ +/* + * Architectures that need SMT-specific errata handling during SMT hotplug + * should override this. + */ +void __weak arch_smt_update(void) { } + #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; EXPORT_SYMBOL_GPL(cpu_smt_control); @@ -1011,6 +1018,7 @@ out: * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); + arch_smt_update(); return ret; } @@ -1139,6 +1147,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); + arch_smt_update(); return ret; } @@ -2055,12 +2064,6 @@ static void cpuhp_online_cpu_device(unsigned int cpu) kobject_uevent(&dev->kobj, KOBJ_ONLINE); } -/* - * Architectures that need SMT-specific errata handling during SMT hotplug - * should override this. - */ -void __weak arch_smt_update(void) { }; - static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 96d4bee83489..322e97bbb437 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -829,7 +829,7 @@ static int prepare_uprobe(struct uprobe *uprobe, struct file *file, BUG_ON((uprobe->offset & ~PAGE_MASK) + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); - smp_wmb(); /* pairs with rmb() in find_active_uprobe() */ + smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */ set_bit(UPROBE_COPY_INSN, &uprobe->flags); out: @@ -2178,10 +2178,18 @@ static void handle_swbp(struct pt_regs *regs) * After we hit the bp, _unregister + _register can install the * new and not-yet-analyzed uprobe at the same address, restart. */ - smp_rmb(); /* pairs with wmb() in install_breakpoint() */ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) goto out; + /* + * Pairs with the smp_wmb() in prepare_uprobe(). + * + * Guarantees that if we see the UPROBE_COPY_INSN bit set, then + * we must also see the stores to &uprobe->arch performed by the + * prepare_uprobe() call. + */ + smp_rmb(); + /* Tracing handlers use ->utask to communicate with fetch methods */ if (!get_utask()) goto out; diff --git a/kernel/kcov.c b/kernel/kcov.c index 3ebd09efe72a..97959d7b77e2 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -56,7 +56,7 @@ struct kcov { struct task_struct *t; }; -static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) +static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) { unsigned int mode; @@ -78,7 +78,7 @@ static bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t) return mode == needed_mode; } -static unsigned long canonicalize_ip(unsigned long ip) +static notrace unsigned long canonicalize_ip(unsigned long ip) { #ifdef CONFIG_RANDOMIZE_BASE ip -= kaslr_offset(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 80b34dffdfb9..c2cee9db5204 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -261,9 +261,6 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state) static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) { - if (mode & PTRACE_MODE_SCHED) - return false; - if (mode & PTRACE_MODE_NOAUDIT) return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE); else @@ -331,16 +328,9 @@ ok: !ptrace_has_cap(mm->user_ns, mode))) return -EPERM; - if (mode & PTRACE_MODE_SCHED) - return 0; return security_ptrace_access_check(task, mode); } -bool ptrace_may_access_sched(struct task_struct *task, unsigned int mode) -{ - return __ptrace_may_access(task, mode | PTRACE_MODE_SCHED); -} - bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 091e089063be..6fedf3a98581 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5738,15 +5738,10 @@ int sched_cpu_activate(unsigned int cpu) #ifdef CONFIG_SCHED_SMT /* - * The sched_smt_present static key needs to be evaluated on every - * hotplug event because at boot time SMT might be disabled when - * the number of booted CPUs is limited. - * - * If then later a sibling gets hotplugged, then the key would stay - * off and SMT scheduling would never be functional. + * When going up, increment the number of cores with SMT present. */ - if (cpumask_weight(cpu_smt_mask(cpu)) > 1) - static_branch_enable_cpuslocked(&sched_smt_present); + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_inc_cpuslocked(&sched_smt_present); #endif set_cpu_active(cpu, true); @@ -5790,6 +5785,14 @@ int sched_cpu_deactivate(unsigned int cpu) */ synchronize_rcu_mult(call_rcu, call_rcu_sched); +#ifdef CONFIG_SCHED_SMT + /* + * When going down, decrement the number of cores with SMT present. + */ + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_dec_cpuslocked(&sched_smt_present); +#endif + if (!sched_smp_initialized) return 0; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 3d7355d7c3e3..fe24de3fbc93 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -136,8 +136,18 @@ static int psi_bug __read_mostly; -bool psi_disabled __read_mostly; -core_param(psi_disabled, psi_disabled, bool, 0644); +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +bool psi_enable; +#else +bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi); /* Running averages - we need to be higher-res than loadavg */ #define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ @@ -169,8 +179,10 @@ static void group_init(struct psi_group *group) void __init psi_init(void) { - if (psi_disabled) + if (!psi_enable) { + static_branch_enable(&psi_disabled); return; + } psi_period = jiffies_to_nsecs(PSI_FREQ); group_init(&psi_system); @@ -549,7 +561,7 @@ void psi_memstall_enter(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; *flags = current->flags & PF_MEMSTALL; @@ -579,7 +591,7 @@ void psi_memstall_leave(unsigned long *flags) struct rq_flags rf; struct rq *rq; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (*flags) @@ -600,7 +612,7 @@ void psi_memstall_leave(unsigned long *flags) #ifdef CONFIG_CGROUPS int psi_cgroup_alloc(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return 0; cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); @@ -612,7 +624,7 @@ int psi_cgroup_alloc(struct cgroup *cgroup) void psi_cgroup_free(struct cgroup *cgroup) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; cancel_delayed_work_sync(&cgroup->psi.clock_work); @@ -637,7 +649,7 @@ void cgroup_move_task(struct task_struct *task, struct css_set *to) struct rq_flags rf; struct rq *rq; - if (psi_disabled) { + if (static_branch_likely(&psi_disabled)) { /* * Lame to do this here, but the scheduler cannot be locked * from the outside, so we move cgroups from inside sched/. @@ -673,7 +685,7 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) { int full; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; update_stats(group); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 618577fc9aa8..4e524ab589c9 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -23,6 +23,7 @@ #include <linux/sched/prio.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> +#include <linux/sched/smt.h> #include <linux/sched/stat.h> #include <linux/sched/sysctl.h> #include <linux/sched/task.h> @@ -936,9 +937,6 @@ static inline int cpu_of(struct rq *rq) #ifdef CONFIG_SCHED_SMT - -extern struct static_key_false sched_smt_present; - extern void __update_idle_core(struct rq *rq); static inline void update_idle_core(struct rq *rq) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 4904c4677000..aa0de240fb41 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -66,7 +66,7 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) { int clear = 0, set = TSK_RUNNING; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!wakeup || p->sched_psi_wake_requeue) { @@ -86,7 +86,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) { int clear = TSK_RUNNING, set = 0; - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (!sleep) { @@ -102,7 +102,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) static inline void psi_ttwu_dequeue(struct task_struct *p) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; /* * Is the task being migrated during a wakeup? Make sure to @@ -128,7 +128,7 @@ static inline void psi_ttwu_dequeue(struct task_struct *p) static inline void psi_task_tick(struct rq *rq) { - if (psi_disabled) + if (static_branch_likely(&psi_disabled)) return; if (unlikely(rq->curr->flags & PF_MEMSTALL)) diff --git a/kernel/stackleak.c b/kernel/stackleak.c index e42892926244..08cb57eed389 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -11,6 +11,7 @@ */ #include <linux/stackleak.h> +#include <linux/kprobes.h> #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE #include <linux/jump_label.h> @@ -47,7 +48,7 @@ int stack_erasing_sysctl(struct ctl_table *table, int write, #define skip_erasing() false #endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ -asmlinkage void stackleak_erase(void) +asmlinkage void notrace stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ unsigned long kstack_ptr = current->lowest_stack; @@ -101,6 +102,7 @@ asmlinkage void stackleak_erase(void) /* Reset the 'lowest_stack' value for the next syscall */ current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } +NOKPROBE_SYMBOL(stackleak_erase); void __used stackleak_track_stack(void) { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 08fcfe440c63..9864a35c8bb5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; - i++; - if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + /* disallow any further format extensions */ + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; - if (fmt[i - 1] == 's') { + if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f536f601bd46..77734451cb05 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -817,7 +817,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip, #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - int index = trace->depth; + int index = current->curr_ret_stack; function_profile_call(trace->func, 0, NULL, NULL); @@ -852,7 +852,7 @@ static void profile_graph_return(struct ftrace_graph_ret *trace) if (!fgraph_graph_time) { int index; - index = trace->depth; + index = current->curr_ret_stack; /* Append this call time to the parent time to subtract */ if (index) @@ -6814,6 +6814,7 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list) atomic_set(&t->tracing_graph_pause, 0); atomic_set(&t->trace_overrun, 0); t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* Make sure the tasks see the -1 first: */ smp_wmb(); t->ret_stack = ret_stack_list[start++]; @@ -7038,6 +7039,7 @@ graph_init_task(struct task_struct *t, struct ftrace_ret_stack *ret_stack) void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { t->curr_ret_stack = -1; + t->curr_ret_depth = -1; /* * The idle task has no parent, it either has its own * stack or no stack at all. @@ -7068,6 +7070,7 @@ void ftrace_graph_init_task(struct task_struct *t) /* Make sure we do not use the parent ret_stack */ t->ret_stack = NULL; t->curr_ret_stack = -1; + t->curr_ret_depth = -1; if (ftrace_graph_active) { struct ftrace_ret_stack *ret_stack; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 3b8c0e24ab30..447bd96ee658 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -512,12 +512,44 @@ enum { * can only be modified by current, we can reuse trace_recursion. */ TRACE_IRQ_BIT, + + /* Set if the function is in the set_graph_function file */ + TRACE_GRAPH_BIT, + + /* + * In the very unlikely case that an interrupt came in + * at a start of graph tracing, and we want to trace + * the function in that interrupt, the depth can be greater + * than zero, because of the preempted start of a previous + * trace. In an even more unlikely case, depth could be 2 + * if a softirq interrupted the start of graph tracing, + * followed by an interrupt preempting a start of graph + * tracing in the softirq, and depth can even be 3 + * if an NMI came in at the start of an interrupt function + * that preempted a softirq start of a function that + * preempted normal context!!!! Luckily, it can't be + * greater than 3, so the next two bits are a mask + * of what the depth is when we set TRACE_GRAPH_BIT + */ + + TRACE_GRAPH_DEPTH_START_BIT, + TRACE_GRAPH_DEPTH_END_BIT, }; #define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0) #define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0) #define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit))) +#define trace_recursion_depth() \ + (((current)->trace_recursion >> TRACE_GRAPH_DEPTH_START_BIT) & 3) +#define trace_recursion_set_depth(depth) \ + do { \ + current->trace_recursion &= \ + ~(3 << TRACE_GRAPH_DEPTH_START_BIT); \ + current->trace_recursion |= \ + ((depth) & 3) << TRACE_GRAPH_DEPTH_START_BIT; \ + } while (0) + #define TRACE_CONTEXT_BITS 4 #define TRACE_FTRACE_START TRACE_FTRACE_BIT @@ -843,8 +875,9 @@ extern void __trace_graph_return(struct trace_array *tr, extern struct ftrace_hash *ftrace_graph_hash; extern struct ftrace_hash *ftrace_graph_notrace_hash; -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { + unsigned long addr = trace->func; int ret = 0; preempt_disable_notrace(); @@ -855,6 +888,14 @@ static inline int ftrace_graph_addr(unsigned long addr) } if (ftrace_lookup_ip(ftrace_graph_hash, addr)) { + + /* + * This needs to be cleared on the return functions + * when the depth is zero. + */ + trace_recursion_set(TRACE_GRAPH_BIT); + trace_recursion_set_depth(trace->depth); + /* * If no irqs are to be traced, but a set_graph_function * is set, and called by an interrupt handler, we still @@ -872,6 +913,13 @@ out: return ret; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ + if (trace_recursion_test(TRACE_GRAPH_BIT) && + trace->depth == trace_recursion_depth()) + trace_recursion_clear(TRACE_GRAPH_BIT); +} + static inline int ftrace_graph_notrace_addr(unsigned long addr) { int ret = 0; @@ -885,7 +933,7 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) return ret; } #else -static inline int ftrace_graph_addr(unsigned long addr) +static inline int ftrace_graph_addr(struct ftrace_graph_ent *trace) { return 1; } @@ -894,6 +942,8 @@ static inline int ftrace_graph_notrace_addr(unsigned long addr) { return 0; } +static inline void ftrace_graph_addr_finish(struct ftrace_graph_ret *trace) +{ } #endif /* CONFIG_DYNAMIC_FTRACE */ extern unsigned int fgraph_max_depth; @@ -901,7 +951,8 @@ extern unsigned int fgraph_max_depth; static inline bool ftrace_graph_ignore_func(struct ftrace_graph_ent *trace) { /* trace it when it is-nested-in or is a function enabled. */ - return !(trace->depth || ftrace_graph_addr(trace->func)) || + return !(trace_recursion_test(TRACE_GRAPH_BIT) || + ftrace_graph_addr(trace)) || (trace->depth < 0) || (fgraph_max_depth && trace->depth >= fgraph_max_depth); } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 169b3c44ee97..086af4f5c3e8 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -118,8 +118,8 @@ print_graph_duration(struct trace_array *tr, unsigned long long duration, struct trace_seq *s, u32 flags); /* Add a function return address to the trace stack on thread info.*/ -int -ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, +static int +ftrace_push_return_trace(unsigned long ret, unsigned long func, unsigned long frame_pointer, unsigned long *retp) { unsigned long long calltime; @@ -177,9 +177,31 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth, #ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR current->ret_stack[index].retp = retp; #endif - *depth = current->curr_ret_stack; + return 0; +} + +int function_graph_enter(unsigned long ret, unsigned long func, + unsigned long frame_pointer, unsigned long *retp) +{ + struct ftrace_graph_ent trace; + + trace.func = func; + trace.depth = ++current->curr_ret_depth; + + if (ftrace_push_return_trace(ret, func, + frame_pointer, retp)) + goto out; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + goto out_ret; return 0; + out_ret: + current->curr_ret_stack--; + out: + current->curr_ret_depth--; + return -EBUSY; } /* Retrieve a function return address to the trace stack on thread info.*/ @@ -241,7 +263,13 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, trace->func = current->ret_stack[index].func; trace->calltime = current->ret_stack[index].calltime; trace->overrun = atomic_read(¤t->trace_overrun); - trace->depth = index; + trace->depth = current->curr_ret_depth--; + /* + * We still want to trace interrupts coming in if + * max_depth is set to 1. Make sure the decrement is + * seen before ftrace_graph_return. + */ + barrier(); } /* @@ -255,6 +283,12 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) ftrace_pop_return_trace(&trace, &ret, frame_pointer); trace.rettime = trace_clock_local(); + ftrace_graph_return(&trace); + /* + * The ftrace_graph_return() may still access the current + * ret_stack structure, we need to make sure the update of + * curr_ret_stack is after that. + */ barrier(); current->curr_ret_stack--; /* @@ -267,13 +301,6 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer) return ret; } - /* - * The trace should run after decrementing the ret counter - * in case an interrupt were to come in. We don't want to - * lose the interrupt if max_depth is set. - */ - ftrace_graph_return(&trace); - if (unlikely(!ret)) { ftrace_graph_stop(); WARN_ON(1); @@ -482,6 +509,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace) int cpu; int pc; + ftrace_graph_addr_finish(trace); + local_irq_save(flags); cpu = raw_smp_processor_id(); data = per_cpu_ptr(tr->trace_buffer.data, cpu); @@ -505,6 +534,8 @@ void set_graph_array(struct trace_array *tr) static void trace_graph_thresh_return(struct ftrace_graph_ret *trace) { + ftrace_graph_addr_finish(trace); + if (tracing_thresh && (trace->rettime - trace->calltime < tracing_thresh)) return; diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index b7357f9f82a3..98ea6d28df15 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -208,6 +208,8 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_dec(tr, &data, &flags)) return; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index a86b303e6c67..7d04b9890755 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -270,6 +270,8 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace) unsigned long flags; int pc; + ftrace_graph_addr_finish(trace); + if (!func_prolog_preempt_disable(tr, &data, &pc)) return; diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 70935ed91125..14afeeb7d6ef 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -135,7 +135,6 @@ static void fill_pool(void) if (!new) return; - kmemleak_ignore(new); raw_spin_lock_irqsave(&pool_lock, flags); hlist_add_head(&new->node, &obj_pool); debug_objects_allocated++; @@ -1128,7 +1127,6 @@ static int __init debug_objects_replace_static_objects(void) obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL); if (!obj) goto free; - kmemleak_ignore(obj); hlist_add_head(&obj->node, &objects); } @@ -1184,7 +1182,8 @@ void __init debug_objects_mem_init(void) obj_cache = kmem_cache_create("debug_objects_cache", sizeof (struct debug_obj), 0, - SLAB_DEBUG_OBJECTS, NULL); + SLAB_DEBUG_OBJECTS | SLAB_NOLEAKTRACE, + NULL); if (!obj_cache || debug_objects_replace_static_objects()) { debug_objects_enabled = 0; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 7ebccb5c1637..54c248526b55 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -560,6 +560,38 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes, return bytes; } +static size_t csum_and_copy_to_pipe_iter(const void *addr, size_t bytes, + __wsum *csum, struct iov_iter *i) +{ + struct pipe_inode_info *pipe = i->pipe; + size_t n, r; + size_t off = 0; + __wsum sum = *csum, next; + int idx; + + if (!sanity(i)) + return 0; + + bytes = n = push_pipe(i, bytes, &idx, &r); + if (unlikely(!n)) + return 0; + for ( ; n; idx = next_idx(idx, pipe), r = 0) { + size_t chunk = min_t(size_t, n, PAGE_SIZE - r); + char *p = kmap_atomic(pipe->bufs[idx].page); + next = csum_partial_copy_nocheck(addr, p + r, chunk, 0); + sum = csum_block_add(sum, next, off); + kunmap_atomic(p); + i->idx = idx; + i->iov_offset = r + chunk; + n -= chunk; + off += chunk; + addr += chunk; + } + i->count -= bytes; + *csum = sum; + return bytes; +} + size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; @@ -1438,8 +1470,12 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, const char *from = addr; __wsum sum, next; size_t off = 0; + + if (unlikely(iov_iter_is_pipe(i))) + return csum_and_copy_to_pipe_iter(addr, bytes, csum, i); + sum = *csum; - if (unlikely(iov_iter_is_pipe(i) || iov_iter_is_discard(i))) { + if (unlikely(iov_iter_is_discard(i))) { WARN_ON(1); /* for now */ return 0; } diff --git a/lib/test_hexdump.c b/lib/test_hexdump.c index 626f580b4ff7..5144899d3c6b 100644 --- a/lib/test_hexdump.c +++ b/lib/test_hexdump.c @@ -99,7 +99,7 @@ static void __init test_hexdump_prepare_test(size_t len, int rowsize, const char *q = *result++; size_t amount = strlen(q); - strncpy(p, q, amount); + memcpy(p, q, amount); p += amount; *p++ = ' '; diff --git a/lib/test_kmod.c b/lib/test_kmod.c index e3ddd836491f..d82d022111e0 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -1214,7 +1214,6 @@ void unregister_test_dev_kmod(struct kmod_test_device *test_dev) dev_info(test_dev->dev, "removing interface\n"); misc_deregister(&test_dev->misc_dev); - kfree(&test_dev->misc_dev.name); mutex_unlock(&test_dev->config_mutex); mutex_unlock(&test_dev->trigger_mutex); @@ -702,12 +702,11 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, if (!vma || start >= vma->vm_end) { vma = find_extend_vma(mm, start); if (!vma && in_gate_area(mm, start)) { - int ret; ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, pages ? &pages[i] : NULL); if (ret) - return i ? : ret; + goto out; ctx.page_mask = 0; goto next_page; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 55478ab3c83b..622cced74fd9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2350,7 +2350,7 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, } } -static void freeze_page(struct page *page) +static void unmap_page(struct page *page) { enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; @@ -2365,7 +2365,7 @@ static void freeze_page(struct page *page) VM_BUG_ON_PAGE(!unmap_success, page); } -static void unfreeze_page(struct page *page) +static void remap_page(struct page *page) { int i; if (PageTransHuge(page)) { @@ -2402,6 +2402,12 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_unevictable) | (1L << PG_dirty))); + /* ->mapping in first tail page is compound_mapcount */ + VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, + page_tail); + page_tail->mapping = head->mapping; + page_tail->index = head->index + tail; + /* Page flags must be visible before we make the page non-compound. */ smp_wmb(); @@ -2422,12 +2428,6 @@ static void __split_huge_page_tail(struct page *head, int tail, if (page_is_idle(head)) set_page_idle(page_tail); - /* ->mapping in first tail page is compound_mapcount */ - VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, - page_tail); - page_tail->mapping = head->mapping; - - page_tail->index = head->index + tail; page_cpupid_xchg_last(page_tail, page_cpupid_last(head)); /* @@ -2439,12 +2439,11 @@ static void __split_huge_page_tail(struct page *head, int tail, } static void __split_huge_page(struct page *page, struct list_head *list, - unsigned long flags) + pgoff_t end, unsigned long flags) { struct page *head = compound_head(page); struct zone *zone = page_zone(head); struct lruvec *lruvec; - pgoff_t end = -1; int i; lruvec = mem_cgroup_page_lruvec(head, zone->zone_pgdat); @@ -2452,9 +2451,6 @@ static void __split_huge_page(struct page *page, struct list_head *list, /* complete memcg works before add pages to LRU */ mem_cgroup_split_huge_fixup(head); - if (!PageAnon(page)) - end = DIV_ROUND_UP(i_size_read(head->mapping->host), PAGE_SIZE); - for (i = HPAGE_PMD_NR - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); /* Some pages can be beyond i_size: drop them from page cache */ @@ -2483,7 +2479,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); - unfreeze_page(head); + remap_page(head); for (i = 0; i < HPAGE_PMD_NR; i++) { struct page *subpage = head + i; @@ -2626,6 +2622,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) int count, mapcount, extra_pins, ret; bool mlocked; unsigned long flags; + pgoff_t end; VM_BUG_ON_PAGE(is_huge_zero_page(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); @@ -2648,6 +2645,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) ret = -EBUSY; goto out; } + end = -1; mapping = NULL; anon_vma_lock_write(anon_vma); } else { @@ -2661,10 +2659,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) anon_vma = NULL; i_mmap_lock_read(mapping); + + /* + *__split_huge_page() may need to trim off pages beyond EOF: + * but on 32-bit, i_size_read() takes an irq-unsafe seqlock, + * which cannot be nested inside the page tree lock. So note + * end now: i_size itself may be changed at any moment, but + * head page lock is good enough to serialize the trimming. + */ + end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); } /* - * Racy check if we can split the page, before freeze_page() will + * Racy check if we can split the page, before unmap_page() will * split PMDs */ if (!can_split_huge_page(head, &extra_pins)) { @@ -2673,7 +2680,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } mlocked = PageMlocked(page); - freeze_page(head); + unmap_page(head); VM_BUG_ON_PAGE(compound_mapcount(head), head); /* Make sure the page is not on per-CPU pagevec as it takes pin */ @@ -2707,7 +2714,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (mapping) __dec_node_page_state(page, NR_SHMEM_THPS); spin_unlock(&pgdata->split_queue_lock); - __split_huge_page(page, list, flags); + __split_huge_page(page, list, end, flags); if (PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) }; @@ -2727,7 +2734,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) fail: if (mapping) xa_unlock(&mapping->i_pages); spin_unlock_irqrestore(zone_lru_lock(page_zone(head)), flags); - unfreeze_page(head); + remap_page(head); ret = -EBUSY; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7f2a28ab46d5..705a3e9cc910 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4080,7 +4080,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, /* fallback to copy_from_user outside mmap_sem */ if (unlikely(ret)) { - ret = -EFAULT; + ret = -ENOENT; *pagep = page; /* don't free the page */ goto out; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index c13625c1ad5e..8e2ff195ecb3 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1287,7 +1287,7 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * collapse_shmem - collapse small tmpfs/shmem pages into huge one. * * Basic scheme is simple, details are more complex: - * - allocate and freeze a new huge page; + * - allocate and lock a new huge page; * - scan page cache replacing old pages with the new one * + swap in pages if necessary; * + fill in gaps; @@ -1295,11 +1295,11 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * - if replacing succeeds: * + copy data over; * + free old pages; - * + unfreeze huge page; + * + unlock huge page; * - if replacing failed; * + put all pages back and unfreeze them; * + restore gaps in the page cache; - * + free huge page; + * + unlock and free huge page; */ static void collapse_shmem(struct mm_struct *mm, struct address_space *mapping, pgoff_t start, @@ -1329,19 +1329,6 @@ static void collapse_shmem(struct mm_struct *mm, goto out; } - new_page->index = start; - new_page->mapping = mapping; - __SetPageSwapBacked(new_page); - __SetPageLocked(new_page); - BUG_ON(!page_ref_freeze(new_page, 1)); - - /* - * At this point the new_page is 'frozen' (page_count() is zero), - * locked and not up-to-date. It's safe to insert it into the page - * cache, because nobody would be able to map it or use it in other - * way until we unfreeze it. - */ - /* This will be less messy when we use multi-index entries */ do { xas_lock_irq(&xas); @@ -1349,19 +1336,44 @@ static void collapse_shmem(struct mm_struct *mm, if (!xas_error(&xas)) break; xas_unlock_irq(&xas); - if (!xas_nomem(&xas, GFP_KERNEL)) + if (!xas_nomem(&xas, GFP_KERNEL)) { + mem_cgroup_cancel_charge(new_page, memcg, true); + result = SCAN_FAIL; goto out; + } } while (1); + __SetPageLocked(new_page); + __SetPageSwapBacked(new_page); + new_page->index = start; + new_page->mapping = mapping; + + /* + * At this point the new_page is locked and not up-to-date. + * It's safe to insert it into the page cache, because nobody would + * be able to map it or use it in another way until we unlock it. + */ + xas_set(&xas, start); for (index = start; index < end; index++) { struct page *page = xas_next(&xas); VM_BUG_ON(index != xas.xa_index); if (!page) { + /* + * Stop if extent has been truncated or hole-punched, + * and is now completely empty. + */ + if (index == start) { + if (!xas_next_entry(&xas, end - 1)) { + result = SCAN_TRUNCATED; + goto xa_locked; + } + xas_set(&xas, index); + } if (!shmem_charge(mapping->host, 1)) { result = SCAN_FAIL; - break; + goto xa_locked; } xas_store(&xas, new_page + (index % HPAGE_PMD_NR)); nr_none++; @@ -1376,13 +1388,12 @@ static void collapse_shmem(struct mm_struct *mm, result = SCAN_FAIL; goto xa_unlocked; } - xas_lock_irq(&xas); - xas_set(&xas, index); } else if (trylock_page(page)) { get_page(page); + xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; - break; + goto xa_locked; } /* @@ -1391,17 +1402,24 @@ static void collapse_shmem(struct mm_struct *mm, */ VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageUptodate(page), page); - VM_BUG_ON_PAGE(PageTransCompound(page), page); + + /* + * If file was truncated then extended, or hole-punched, before + * we locked the first page, then a THP might be there already. + */ + if (PageTransCompound(page)) { + result = SCAN_PAGE_COMPOUND; + goto out_unlock; + } if (page_mapping(page) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } - xas_unlock_irq(&xas); if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; - goto out_isolate_failed; + goto out_unlock; } if (page_mapped(page)) @@ -1421,7 +1439,9 @@ static void collapse_shmem(struct mm_struct *mm, */ if (!page_ref_freeze(page, 3)) { result = SCAN_PAGE_COUNT; - goto out_lru; + xas_unlock_irq(&xas); + putback_lru_page(page); + goto out_unlock; } /* @@ -1433,71 +1453,74 @@ static void collapse_shmem(struct mm_struct *mm, /* Finally, replace with the new page. */ xas_store(&xas, new_page + (index % HPAGE_PMD_NR)); continue; -out_lru: - xas_unlock_irq(&xas); - putback_lru_page(page); -out_isolate_failed: - unlock_page(page); - put_page(page); - goto xa_unlocked; out_unlock: unlock_page(page); put_page(page); - break; + goto xa_unlocked; } - xas_unlock_irq(&xas); + __inc_node_page_state(new_page, NR_SHMEM_THPS); + if (nr_none) { + struct zone *zone = page_zone(new_page); + + __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none); + __mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none); + } + +xa_locked: + xas_unlock_irq(&xas); xa_unlocked: + if (result == SCAN_SUCCEED) { struct page *page, *tmp; - struct zone *zone = page_zone(new_page); /* * Replacing old pages with new one has succeeded, now we * need to copy the content and free the old pages. */ + index = start; list_for_each_entry_safe(page, tmp, &pagelist, lru) { + while (index < page->index) { + clear_highpage(new_page + (index % HPAGE_PMD_NR)); + index++; + } copy_highpage(new_page + (page->index % HPAGE_PMD_NR), page); list_del(&page->lru); - unlock_page(page); - page_ref_unfreeze(page, 1); page->mapping = NULL; + page_ref_unfreeze(page, 1); ClearPageActive(page); ClearPageUnevictable(page); + unlock_page(page); put_page(page); + index++; } - - local_irq_disable(); - __inc_node_page_state(new_page, NR_SHMEM_THPS); - if (nr_none) { - __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none); - __mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none); + while (index < end) { + clear_highpage(new_page + (index % HPAGE_PMD_NR)); + index++; } - local_irq_enable(); - /* - * Remove pte page tables, so we can re-fault - * the page as huge. - */ - retract_page_tables(mapping, start); - - /* Everything is ready, let's unfreeze the new_page */ - set_page_dirty(new_page); SetPageUptodate(new_page); - page_ref_unfreeze(new_page, HPAGE_PMD_NR); + page_ref_add(new_page, HPAGE_PMD_NR - 1); + set_page_dirty(new_page); mem_cgroup_commit_charge(new_page, memcg, false, true); lru_cache_add_anon(new_page); - unlock_page(new_page); + /* + * Remove pte page tables, so we can re-fault the page as huge. + */ + retract_page_tables(mapping, start); *hpage = NULL; khugepaged_pages_collapsed++; } else { struct page *page; + /* Something went wrong: roll back page cache changes */ - shmem_uncharge(mapping->host, nr_none); xas_lock_irq(&xas); + mapping->nrpages -= nr_none; + shmem_uncharge(mapping->host, nr_none); + xas_set(&xas, start); xas_for_each(&xas, page, end - 1) { page = list_first_entry_or_null(&pagelist, @@ -1519,19 +1542,18 @@ xa_unlocked: xas_store(&xas, page); xas_pause(&xas); xas_unlock_irq(&xas); - putback_lru_page(page); unlock_page(page); + putback_lru_page(page); xas_lock_irq(&xas); } VM_BUG_ON(nr_none); xas_unlock_irq(&xas); - /* Unfreeze new_page, caller would take care about freeing it */ - page_ref_unfreeze(new_page, 1); mem_cgroup_cancel_charge(new_page, memcg, true); - unlock_page(new_page); new_page->mapping = NULL; } + + unlock_page(new_page); out: VM_BUG_ON(!list_empty(&pagelist)); /* TODO: tracepoints */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6847177dc4a1..2ec9cc407216 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5813,8 +5813,10 @@ void __meminit init_currently_empty_zone(struct zone *zone, unsigned long size) { struct pglist_data *pgdat = zone->zone_pgdat; + int zone_idx = zone_idx(zone) + 1; - pgdat->nr_zones = zone_idx(zone) + 1; + if (zone_idx > pgdat->nr_zones) + pgdat->nr_zones = zone_idx; zone->zone_start_pfn = zone_start_pfn; diff --git a/mm/rmap.c b/mm/rmap.c index 1e79fac3186b..85b7f9423352 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1627,16 +1627,9 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, address + PAGE_SIZE); } else { /* - * We should not need to notify here as we reach this - * case only from freeze_page() itself only call from - * split_huge_page_to_list() so everything below must - * be true: - * - page is not anonymous - * - page is locked - * - * So as it is a locked file back page thus it can not - * be remove from the page cache and replace by a new - * page before mmu_notifier_invalidate_range_end so no + * This is a locked file-backed page, thus it cannot + * be removed from the page cache and replaced by a new + * page before mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table to * point at new page while a device still is using this * page. diff --git a/mm/shmem.c b/mm/shmem.c index d44991ea5ed4..cddc72ac44d8 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -297,12 +297,14 @@ bool shmem_charge(struct inode *inode, long pages) if (!shmem_inode_acct_block(inode, pages)) return false; + /* nrpages adjustment first, then shmem_recalc_inode() when balanced */ + inode->i_mapping->nrpages += pages; + spin_lock_irqsave(&info->lock, flags); info->alloced += pages; inode->i_blocks += pages * BLOCKS_PER_PAGE; shmem_recalc_inode(inode); spin_unlock_irqrestore(&info->lock, flags); - inode->i_mapping->nrpages += pages; return true; } @@ -312,6 +314,8 @@ void shmem_uncharge(struct inode *inode, long pages) struct shmem_inode_info *info = SHMEM_I(inode); unsigned long flags; + /* nrpages adjustment done by __delete_from_page_cache() or caller */ + spin_lock_irqsave(&info->lock, flags); info->alloced -= pages; inode->i_blocks -= pages * BLOCKS_PER_PAGE; @@ -1509,11 +1513,13 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, { struct page *oldpage, *newpage; struct address_space *swap_mapping; + swp_entry_t entry; pgoff_t swap_index; int error; oldpage = *pagep; - swap_index = page_private(oldpage); + entry.val = page_private(oldpage); + swap_index = swp_offset(entry); swap_mapping = page_mapping(oldpage); /* @@ -1532,7 +1538,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, __SetPageLocked(newpage); __SetPageSwapBacked(newpage); SetPageUptodate(newpage); - set_page_private(newpage, swap_index); + set_page_private(newpage, entry.val); SetPageSwapCache(newpage); /* @@ -2214,6 +2220,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, struct page *page; pte_t _dst_pte, *dst_pte; int ret; + pgoff_t offset, max_off; ret = -ENOMEM; if (!shmem_inode_acct_block(inode, 1)) @@ -2236,7 +2243,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, *pagep = page; shmem_inode_unacct_blocks(inode, 1); /* don't free the page */ - return -EFAULT; + return -ENOENT; } } else { /* mfill_zeropage_atomic */ clear_highpage(page); @@ -2251,6 +2258,12 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, __SetPageSwapBacked(page); __SetPageUptodate(page); + ret = -EFAULT; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) + goto out_release; + ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false); if (ret) goto out_release; @@ -2265,9 +2278,25 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, _dst_pte = mk_pte(page, dst_vma->vm_page_prot); if (dst_vma->vm_flags & VM_WRITE) _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); + else { + /* + * We don't set the pte dirty if the vma has no + * VM_WRITE permission, so mark the page dirty or it + * could be freed from under us. We could do it + * unconditionally before unlock_page(), but doing it + * only if VM_WRITE is not set is faster. + */ + set_page_dirty(page); + } - ret = -EEXIST; dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + + ret = -EFAULT; + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + if (unlikely(offset >= max_off)) + goto out_release_uncharge_unlock; + + ret = -EEXIST; if (!pte_none(*dst_pte)) goto out_release_uncharge_unlock; @@ -2285,13 +2314,15 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); - unlock_page(page); pte_unmap_unlock(dst_pte, ptl); + unlock_page(page); ret = 0; out: return ret; out_release_uncharge_unlock: pte_unmap_unlock(dst_pte, ptl); + ClearPageDirty(page); + delete_from_page_cache(page); out_release_uncharge: mem_cgroup_cancel_charge(page, memcg, false); out_release: diff --git a/mm/truncate.c b/mm/truncate.c index 45d68e90b703..798e7ccfb030 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -517,9 +517,13 @@ void truncate_inode_pages_final(struct address_space *mapping) */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); - - truncate_inode_pages(mapping, 0); } + + /* + * Cleancache needs notification even if there are no pages or shadow + * entries. + */ + truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 5029f241908f..458acda96f20 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -33,6 +33,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, void *page_kaddr; int ret; struct page *page; + pgoff_t offset, max_off; + struct inode *inode; if (!*pagep) { ret = -ENOMEM; @@ -48,7 +50,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, /* fallback to copy_from_user outside mmap_sem */ if (unlikely(ret)) { - ret = -EFAULT; + ret = -ENOENT; *pagep = page; /* don't free the page */ goto out; @@ -73,8 +75,17 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, if (dst_vma->vm_flags & VM_WRITE) _dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte)); - ret = -EEXIST; dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + if (dst_vma->vm_file) { + /* the shmem MAP_PRIVATE case requires checking the i_size */ + inode = dst_vma->vm_file->f_inode; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + ret = -EFAULT; + if (unlikely(offset >= max_off)) + goto out_release_uncharge_unlock; + } + ret = -EEXIST; if (!pte_none(*dst_pte)) goto out_release_uncharge_unlock; @@ -108,11 +119,22 @@ static int mfill_zeropage_pte(struct mm_struct *dst_mm, pte_t _dst_pte, *dst_pte; spinlock_t *ptl; int ret; + pgoff_t offset, max_off; + struct inode *inode; _dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr), dst_vma->vm_page_prot)); - ret = -EEXIST; dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl); + if (dst_vma->vm_file) { + /* the shmem MAP_PRIVATE case requires checking the i_size */ + inode = dst_vma->vm_file->f_inode; + offset = linear_page_index(dst_vma, dst_addr); + max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); + ret = -EFAULT; + if (unlikely(offset >= max_off)) + goto out_unlock; + } + ret = -EEXIST; if (!pte_none(*dst_pte)) goto out_unlock; set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); @@ -205,8 +227,9 @@ retry: if (!dst_vma || !is_vm_hugetlb_page(dst_vma)) goto out_unlock; /* - * Only allow __mcopy_atomic_hugetlb on userfaultfd - * registered ranges. + * Check the vma is registered in uffd, this is + * required to enforce the VM_MAYWRITE check done at + * uffd registration time. */ if (!dst_vma->vm_userfaultfd_ctx.ctx) goto out_unlock; @@ -274,7 +297,7 @@ retry: cond_resched(); - if (unlikely(err == -EFAULT)) { + if (unlikely(err == -ENOENT)) { up_read(&dst_mm->mmap_sem); BUG_ON(!page); @@ -380,7 +403,17 @@ static __always_inline ssize_t mfill_atomic_pte(struct mm_struct *dst_mm, { ssize_t err; - if (vma_is_anonymous(dst_vma)) { + /* + * The normal page fault path for a shmem will invoke the + * fault, fill the hole in the file and COW it right away. The + * result generates plain anonymous memory. So when we are + * asked to fill an hole in a MAP_PRIVATE shmem mapping, we'll + * generate anonymous memory directly without actually filling + * the hole. For the MAP_PRIVATE case the robustness check + * only happens in the pagetable (to verify it's still none) + * and not in the radix tree. + */ + if (!(dst_vma->vm_flags & VM_SHARED)) { if (!zeropage) err = mcopy_atomic_pte(dst_mm, dst_pmd, dst_vma, dst_addr, src_addr, page); @@ -449,13 +482,9 @@ retry: if (!dst_vma) goto out_unlock; /* - * Be strict and only allow __mcopy_atomic on userfaultfd - * registered ranges to prevent userland errors going - * unnoticed. As far as the VM consistency is concerned, it - * would be perfectly safe to remove this check, but there's - * no useful usage for __mcopy_atomic ouside of userfaultfd - * registered ranges. This is after all why these are ioctls - * belonging to the userfaultfd and not syscalls. + * Check the vma is registered in uffd, this is required to + * enforce the VM_MAYWRITE check done at uffd registration + * time. */ if (!dst_vma->vm_userfaultfd_ctx.ctx) goto out_unlock; @@ -489,7 +518,8 @@ retry: * dst_vma. */ err = -ENOMEM; - if (vma_is_anonymous(dst_vma) && unlikely(anon_vma_prepare(dst_vma))) + if (!(dst_vma->vm_flags & VM_SHARED) && + unlikely(anon_vma_prepare(dst_vma))) goto out_unlock; while (src_addr < src_start + len) { @@ -530,7 +560,7 @@ retry: src_addr, &page, zeropage); cond_resched(); - if (unlikely(err == -EFAULT)) { + if (unlikely(err == -ENOENT)) { void *page_kaddr; up_read(&dst_mm->mmap_sem); diff --git a/net/core/filter.c b/net/core/filter.c index e521c5ebc7d1..9a1327eb25fa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4852,18 +4852,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, } else { struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr; struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr; - u16 hnum = ntohs(tuple->ipv6.dport); int sdif = inet6_sdif(skb); if (proto == IPPROTO_TCP) sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0, src6, tuple->ipv6.sport, - dst6, hnum, + dst6, ntohs(tuple->ipv6.dport), dif, sdif, &refcounted); else if (likely(ipv6_bpf_stub)) sk = ipv6_bpf_stub->udp6_lib_lookup(net, src6, tuple->ipv6.sport, - dst6, hnum, + dst6, tuple->ipv6.dport, dif, sdif, &udp_table, skb); #endif diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c09219e7f230..5dbec21856f4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -939,7 +939,7 @@ static int __ip_append_data(struct sock *sk, unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; - unsigned int pagedlen = 0; + unsigned int pagedlen; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; @@ -956,6 +956,7 @@ alloc_new_skb: if (datalen > mtu - fragheaderlen) datalen = maxfraglen - fragheaderlen; fraglen = datalen + fragheaderlen; + pagedlen = 0; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index ce1512b02cb2..fd3f9e8a74da 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -81,9 +81,12 @@ static int __init masquerade_tg_init(void) int ret; ret = xt_register_target(&masquerade_tg_reg); + if (ret) + return ret; - if (ret == 0) - nf_nat_masquerade_ipv4_register_notifier(); + ret = nf_nat_masquerade_ipv4_register_notifier(); + if (ret) + xt_unregister_target(&masquerade_tg_reg); return ret; } diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index a9d5e013e555..41327bb99093 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -147,28 +147,50 @@ static struct notifier_block masq_inet_notifier = { .notifier_call = masq_inet_event, }; -static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0); +static int masq_refcnt; +static DEFINE_MUTEX(masq_mutex); -void nf_nat_masquerade_ipv4_register_notifier(void) +int nf_nat_masquerade_ipv4_register_notifier(void) { + int ret = 0; + + mutex_lock(&masq_mutex); /* check if the notifier was already set */ - if (atomic_inc_return(&masquerade_notifier_refcount) > 1) - return; + if (++masq_refcnt > 1) + goto out_unlock; /* Register for device down reports */ - register_netdevice_notifier(&masq_dev_notifier); + ret = register_netdevice_notifier(&masq_dev_notifier); + if (ret) + goto err_dec; /* Register IP address change reports */ - register_inetaddr_notifier(&masq_inet_notifier); + ret = register_inetaddr_notifier(&masq_inet_notifier); + if (ret) + goto err_unregister; + + mutex_unlock(&masq_mutex); + return ret; + +err_unregister: + unregister_netdevice_notifier(&masq_dev_notifier); +err_dec: + masq_refcnt--; +out_unlock: + mutex_unlock(&masq_mutex); + return ret; } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier); void nf_nat_masquerade_ipv4_unregister_notifier(void) { + mutex_lock(&masq_mutex); /* check if the notifier still has clients */ - if (atomic_dec_return(&masquerade_notifier_refcount) > 0) - return; + if (--masq_refcnt > 0) + goto out_unlock; unregister_netdevice_notifier(&masq_dev_notifier); unregister_inetaddr_notifier(&masq_inet_notifier); +out_unlock: + mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier); diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index f1193e1e928a..6847de1d1db8 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -69,7 +69,9 @@ static int __init nft_masq_ipv4_module_init(void) if (ret < 0) return ret; - nf_nat_masquerade_ipv4_register_notifier(); + ret = nf_nat_masquerade_ipv4_register_notifier(); + if (ret) + nft_unregister_expr(&nft_masq_ipv4_type); return ret; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1e37c1388189..a9d9555a973f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -579,10 +579,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; u32 delta_us; - if (!delta) - delta = 1; - delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - tcp_rcv_rtt_update(tp, delta_us, 0); + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + tcp_rcv_rtt_update(tp, delta_us, 0); + } } } @@ -2910,9 +2912,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) { u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - seq_rtt_us = ca_rtt_us = delta_us; + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + ca_rtt_us = seq_rtt_us; + } } rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5f8b6d3cd855..091c53925e4d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -40,15 +40,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 elapsed, start_ts; + s32 remaining; start_ts = tcp_retransmit_stamp(sk); if (!icsk->icsk_user_timeout || !start_ts) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; - if (elapsed >= icsk->icsk_user_timeout) + remaining = icsk->icsk_user_timeout - elapsed; + if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ - else - return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed)); + + return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); } /** @@ -209,7 +211,7 @@ static bool retransmits_timed_out(struct sock *sk, (boundary - linear_backoff_thresh) * TCP_RTO_MAX; timeout = jiffies_to_msecs(timeout); } - return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout; + return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 89e0d5118afe..827a3f5ff3bb 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1354,7 +1354,7 @@ emsgsize: unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; - unsigned int pagedlen = 0; + unsigned int pagedlen; alloc_new_skb: /* There's no room in the current skb */ if (skb) @@ -1378,6 +1378,7 @@ alloc_new_skb: if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; + pagedlen = 0; if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 5ae8e1c51079..8b075f0bc351 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -24,7 +24,8 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) unsigned int hh_len; struct dst_entry *dst; struct flowi6 fl6 = { - .flowi6_oif = sk ? sk->sk_bound_dev_if : 0, + .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : + rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 491f808e356a..29c7f1915a96 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -58,8 +58,12 @@ static int __init masquerade_tg6_init(void) int err; err = xt_register_target(&masquerade_tg6_reg); - if (err == 0) - nf_nat_masquerade_ipv6_register_notifier(); + if (err) + return err; + + err = nf_nat_masquerade_ipv6_register_notifier(); + if (err) + xt_unregister_target(&masquerade_tg6_reg); return err; } diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 3e4bf2286abe..0ad0da5a2600 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -132,8 +132,8 @@ static void iterate_cleanup_work(struct work_struct *work) * of ipv6 addresses being deleted), we also need to add an upper * limit to the number of queued work items. */ -static int masq_inet_event(struct notifier_block *this, - unsigned long event, void *ptr) +static int masq_inet6_event(struct notifier_block *this, + unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; const struct net_device *dev; @@ -171,30 +171,53 @@ static int masq_inet_event(struct notifier_block *this, return NOTIFY_DONE; } -static struct notifier_block masq_inet_notifier = { - .notifier_call = masq_inet_event, +static struct notifier_block masq_inet6_notifier = { + .notifier_call = masq_inet6_event, }; -static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0); +static int masq_refcnt; +static DEFINE_MUTEX(masq_mutex); -void nf_nat_masquerade_ipv6_register_notifier(void) +int nf_nat_masquerade_ipv6_register_notifier(void) { + int ret = 0; + + mutex_lock(&masq_mutex); /* check if the notifier is already set */ - if (atomic_inc_return(&masquerade_notifier_refcount) > 1) - return; + if (++masq_refcnt > 1) + goto out_unlock; + + ret = register_netdevice_notifier(&masq_dev_notifier); + if (ret) + goto err_dec; + + ret = register_inet6addr_notifier(&masq_inet6_notifier); + if (ret) + goto err_unregister; - register_netdevice_notifier(&masq_dev_notifier); - register_inet6addr_notifier(&masq_inet_notifier); + mutex_unlock(&masq_mutex); + return ret; + +err_unregister: + unregister_netdevice_notifier(&masq_dev_notifier); +err_dec: + masq_refcnt--; +out_unlock: + mutex_unlock(&masq_mutex); + return ret; } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier); void nf_nat_masquerade_ipv6_unregister_notifier(void) { + mutex_lock(&masq_mutex); /* check if the notifier still has clients */ - if (atomic_dec_return(&masquerade_notifier_refcount) > 0) - return; + if (--masq_refcnt > 0) + goto out_unlock; - unregister_inet6addr_notifier(&masq_inet_notifier); + unregister_inet6addr_notifier(&masq_inet6_notifier); unregister_netdevice_notifier(&masq_dev_notifier); +out_unlock: + mutex_unlock(&masq_mutex); } EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier); diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index dd0122f3cffe..e06c82e9dfcd 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -70,7 +70,9 @@ static int __init nft_masq_ipv6_module_init(void) if (ret < 0) return ret; - nf_nat_masquerade_ipv6_register_notifier(); + ret = nf_nat_masquerade_ipv6_register_notifier(); + if (ret) + nft_unregister_expr(&nft_masq_ipv6_type); return ret; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 83395bf6dc35..432141f04af3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3980,6 +3980,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) static struct notifier_block ip_vs_dst_notifier = { .notifier_call = ip_vs_dst_event, +#ifdef CONFIG_IP_VS_IPV6 + .priority = ADDRCONF_NOTIFY_PRIORITY + 5, +#endif }; int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index 02ca7df793f5..b6d0f6deea86 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -49,6 +49,7 @@ struct nf_conncount_tuple { struct nf_conntrack_zone zone; int cpu; u32 jiffies32; + bool dead; struct rcu_head rcu_head; }; @@ -106,15 +107,16 @@ nf_conncount_add(struct nf_conncount_list *list, conn->zone = *zone; conn->cpu = raw_smp_processor_id(); conn->jiffies32 = (u32)jiffies; - spin_lock(&list->list_lock); + conn->dead = false; + spin_lock_bh(&list->list_lock); if (list->dead == true) { kmem_cache_free(conncount_conn_cachep, conn); - spin_unlock(&list->list_lock); + spin_unlock_bh(&list->list_lock); return NF_CONNCOUNT_SKIP; } list_add_tail(&conn->node, &list->head); list->count++; - spin_unlock(&list->list_lock); + spin_unlock_bh(&list->list_lock); return NF_CONNCOUNT_ADDED; } EXPORT_SYMBOL_GPL(nf_conncount_add); @@ -132,19 +134,22 @@ static bool conn_free(struct nf_conncount_list *list, { bool free_entry = false; - spin_lock(&list->list_lock); + spin_lock_bh(&list->list_lock); - if (list->count == 0) { - spin_unlock(&list->list_lock); - return free_entry; + if (conn->dead) { + spin_unlock_bh(&list->list_lock); + return free_entry; } list->count--; + conn->dead = true; list_del_rcu(&conn->node); - if (list->count == 0) + if (list->count == 0) { + list->dead = true; free_entry = true; + } - spin_unlock(&list->list_lock); + spin_unlock_bh(&list->list_lock); call_rcu(&conn->rcu_head, __conn_free); return free_entry; } @@ -245,7 +250,7 @@ void nf_conncount_list_init(struct nf_conncount_list *list) { spin_lock_init(&list->list_lock); INIT_LIST_HEAD(&list->head); - list->count = 1; + list->count = 0; list->dead = false; } EXPORT_SYMBOL_GPL(nf_conncount_list_init); @@ -259,6 +264,7 @@ bool nf_conncount_gc_list(struct net *net, struct nf_conn *found_ct; unsigned int collected = 0; bool free_entry = false; + bool ret = false; list_for_each_entry_safe(conn, conn_n, &list->head, node) { found = find_or_evict(net, list, conn, &free_entry); @@ -288,7 +294,15 @@ bool nf_conncount_gc_list(struct net *net, if (collected > CONNCOUNT_GC_MAX_NODES) return false; } - return false; + + spin_lock_bh(&list->list_lock); + if (!list->count) { + list->dead = true; + ret = true; + } + spin_unlock_bh(&list->list_lock); + + return ret; } EXPORT_SYMBOL_GPL(nf_conncount_gc_list); @@ -309,11 +323,8 @@ static void tree_nodes_free(struct rb_root *root, while (gc_count) { rbconn = gc_nodes[--gc_count]; spin_lock(&rbconn->list.list_lock); - if (rbconn->list.count == 0 && rbconn->list.dead == false) { - rbconn->list.dead = true; - rb_erase(&rbconn->node, root); - call_rcu(&rbconn->rcu_head, __tree_nodes_free); - } + rb_erase(&rbconn->node, root); + call_rcu(&rbconn->rcu_head, __tree_nodes_free); spin_unlock(&rbconn->list.list_lock); } } @@ -414,6 +425,7 @@ insert_tree(struct net *net, nf_conncount_list_init(&rbconn->list); list_add(&conn->node, &rbconn->list.head); count = 1; + rbconn->list.count = count; rb_link_node(&rbconn->node, parent, rbnode); rb_insert_color(&rbconn->node, root); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 9b48dc8b4b88..2a5e56c6d8d9 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -43,24 +43,12 @@ #include <linux/netfilter/nf_conntrack_proto_gre.h> #include <linux/netfilter/nf_conntrack_pptp.h> -enum grep_conntrack { - GRE_CT_UNREPLIED, - GRE_CT_REPLIED, - GRE_CT_MAX -}; - static const unsigned int gre_timeouts[GRE_CT_MAX] = { [GRE_CT_UNREPLIED] = 30*HZ, [GRE_CT_REPLIED] = 180*HZ, }; static unsigned int proto_gre_net_id __read_mostly; -struct netns_proto_gre { - struct nf_proto_net nf; - rwlock_t keymap_lock; - struct list_head keymap_list; - unsigned int gre_timeouts[GRE_CT_MAX]; -}; static inline struct netns_proto_gre *gre_pernet(struct net *net) { @@ -402,6 +390,8 @@ static int __init nf_ct_proto_gre_init(void) { int ret; + BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0); + ret = register_pernet_subsys(&proto_gre_net_ops); if (ret < 0) goto out_pernet; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 42487d01a3ed..2e61aab6ed73 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2457,7 +2457,7 @@ err: static void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) { - struct nft_expr *expr; + struct nft_expr *expr, *next; /* * Careful: some expressions might not be initialized in case this @@ -2465,8 +2465,9 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, */ expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { + next = nft_expr_next(expr); nf_tables_expr_destroy(ctx, expr); - expr = nft_expr_next(expr); + expr = next; } kfree(rule); } @@ -2589,17 +2590,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, if (chain->use == UINT_MAX) return -EOVERFLOW; - } - - if (nla[NFTA_RULE_POSITION]) { - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) - return -EOPNOTSUPP; - pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); - old_rule = __nft_rule_lookup(chain, pos_handle); - if (IS_ERR(old_rule)) { - NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); - return PTR_ERR(old_rule); + if (nla[NFTA_RULE_POSITION]) { + pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); + old_rule = __nft_rule_lookup(chain, pos_handle); + if (IS_ERR(old_rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); + return PTR_ERR(old_rule); + } } } @@ -2669,21 +2667,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, } if (nlh->nlmsg_flags & NLM_F_REPLACE) { - if (!nft_is_active_next(net, old_rule)) { - err = -ENOENT; - goto err2; - } - trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE, - old_rule); + trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule); if (trans == NULL) { err = -ENOMEM; goto err2; } - nft_deactivate_next(net, old_rule); - chain->use--; - - if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) { - err = -ENOMEM; + err = nft_delrule(&ctx, old_rule); + if (err < 0) { + nft_trans_destroy(trans); goto err2; } @@ -6324,7 +6315,7 @@ static void nf_tables_commit_chain_free_rules_old(struct nft_rule **rules) call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old); } -static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *chain) +static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) { struct nft_rule **g0, **g1; bool next_genbit; @@ -6441,11 +6432,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) /* step 2. Make rules_gen_X visible to packet path */ list_for_each_entry(table, &net->nft.tables, list) { - list_for_each_entry(chain, &table->chains, list) { - if (!nft_is_active_next(net, chain)) - continue; - nf_tables_commit_chain_active(net, chain); - } + list_for_each_entry(chain, &table->chains, list) + nf_tables_commit_chain(net, chain); } /* diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index a518eb162344..109b0d27345a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -455,7 +455,8 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, case IPPROTO_TCP: timeouts = nf_tcp_pernet(net)->timeouts; break; - case IPPROTO_UDP: + case IPPROTO_UDP: /* fallthrough */ + case IPPROTO_UDPLITE: timeouts = nf_udp_pernet(net)->timeouts; break; case IPPROTO_DCCP: @@ -471,11 +472,21 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, timeouts = nf_sctp_pernet(net)->timeouts; #endif break; + case IPPROTO_GRE: +#ifdef CONFIG_NF_CT_PROTO_GRE + if (l4proto->net_id) { + struct netns_proto_gre *net_gre; + + net_gre = net_generic(net, *l4proto->net_id); + timeouts = net_gre->gre_timeouts; + } +#endif + break; case 255: timeouts = &nf_generic_pernet(net)->timeout; break; default: - WARN_ON_ONCE(1); + WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto); break; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 9d0ede474224..7334e0b80a5e 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -520,6 +520,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, void *info) { struct xt_match *match = expr->ops->data; + struct module *me = match->me; struct xt_mtdtor_param par; par.net = ctx->net; @@ -530,7 +531,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr, par.match->destroy(&par); if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(match->me); + module_put(me); } static void diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index e82d9a966c45..974525eb92df 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -214,7 +214,9 @@ static int __init nft_flow_offload_module_init(void) { int err; - register_netdevice_notifier(&flow_offload_netdev_notifier); + err = register_netdevice_notifier(&flow_offload_netdev_notifier); + if (err) + goto err; err = nft_register_expr(&nft_flow_offload_type); if (err < 0) @@ -224,6 +226,7 @@ static int __init nft_flow_offload_module_init(void) register_expr: unregister_netdevice_notifier(&flow_offload_netdev_notifier); +err: return err; } diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index dec843cadf46..9e05c86ba5c4 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -201,18 +201,8 @@ static __net_init int xt_rateest_net_init(struct net *net) return 0; } -static void __net_exit xt_rateest_net_exit(struct net *net) -{ - struct xt_rateest_net *xn = net_generic(net, xt_rateest_id); - int i; - - for (i = 0; i < ARRAY_SIZE(xn->hash); i++) - WARN_ON_ONCE(!hlist_empty(&xn->hash[i])); -} - static struct pernet_operations xt_rateest_net_ops = { .init = xt_rateest_net_init, - .exit = xt_rateest_net_exit, .id = &xt_rateest_id, .size = sizeof(struct xt_rateest_net), }; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 3e7d259e5d8d..1ad4017f9b73 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -295,9 +295,10 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, /* copy match config into hashtable config */ ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3); - - if (ret) + if (ret) { + vfree(hinfo); return ret; + } hinfo->cfg.size = size; if (hinfo->cfg.max == 0) @@ -814,7 +815,6 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); - if (ret) return ret; @@ -830,7 +830,6 @@ hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) int ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); - if (ret) return ret; @@ -921,7 +920,6 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 1); - if (ret) return ret; @@ -940,7 +938,6 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par) return ret; ret = cfg_copy(&cfg, (void *)&info->cfg, 2); - if (ret) return ret; diff --git a/net/sctp/output.c b/net/sctp/output.c index b0e74a3e77ec..025f48e14a91 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -410,6 +410,7 @@ static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb) head->truesize += skb->truesize; head->data_len += skb->len; head->len += skb->len; + refcount_add(skb->truesize, &head->sk->sk_wmem_alloc); __skb_header_release(skb); } diff --git a/net/tipc/node.c b/net/tipc/node.c index 2afc4f8c37a7..488019766433 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -584,12 +584,15 @@ static void tipc_node_clear_links(struct tipc_node *node) /* tipc_node_cleanup - delete nodes that does not * have active links for NODE_CLEANUP_AFTER time */ -static int tipc_node_cleanup(struct tipc_node *peer) +static bool tipc_node_cleanup(struct tipc_node *peer) { struct tipc_net *tn = tipc_net(peer->net); bool deleted = false; - spin_lock_bh(&tn->node_list_lock); + /* If lock held by tipc_node_stop() the node will be deleted anyway */ + if (!spin_trylock_bh(&tn->node_list_lock)) + return false; + tipc_node_write_lock(peer); if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) { diff --git a/scripts/Makefile.build b/scripts/Makefile.build index a8e7ba9f73e8..6a6be9f440cf 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -236,10 +236,8 @@ ifdef CONFIG_GCOV_KERNEL objtool_args += --no-unreachable endif ifdef CONFIG_RETPOLINE -ifneq ($(RETPOLINE_CFLAGS),) objtool_args += --retpoline endif -endif ifdef CONFIG_MODVERSIONS diff --git a/scripts/unifdef.c b/scripts/unifdef.c index 7493c0ee51cc..db00e3e30a59 100644 --- a/scripts/unifdef.c +++ b/scripts/unifdef.c @@ -395,7 +395,7 @@ usage(void) * When we have processed a group that starts off with a known-false * #if/#elif sequence (which has therefore been deleted) followed by a * #elif that we don't understand and therefore must keep, we edit the - * latter into a #if to keep the nesting correct. We use strncpy() to + * latter into a #if to keep the nesting correct. We use memcpy() to * overwrite the 4 byte token "elif" with "if " without a '\0' byte. * * When we find a true #elif in a group, the following block will @@ -450,7 +450,7 @@ static void Idrop (void) { Fdrop(); ignoreon(); } static void Itrue (void) { Ftrue(); ignoreon(); } static void Ifalse(void) { Ffalse(); ignoreon(); } /* modify this line */ -static void Mpass (void) { strncpy(keyword, "if ", 4); Pelif(); } +static void Mpass (void) { memcpy(keyword, "if ", 4); Pelif(); } static void Mtrue (void) { keywordedit("else"); state(IS_TRUE_MIDDLE); } static void Melif (void) { keywordedit("endif"); state(IS_FALSE_TRAILER); } static void Melse (void) { keywordedit("endif"); state(IS_FALSE_ELSE); } diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index 74b951f55608..9cec81209617 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -80,6 +80,9 @@ static const struct nlmsg_perm nlmsg_route_perms[] = { RTM_NEWSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETSTATS, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_NEWCACHEREPORT, NETLINK_ROUTE_SOCKET__NLMSG_READ }, + { RTM_NEWCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_DELCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_GETCHAIN, NETLINK_ROUTE_SOCKET__NLMSG_READ }, }; static const struct nlmsg_perm nlmsg_tcpdiag_perms[] = @@ -158,7 +161,11 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) switch (sclass) { case SECCLASS_NETLINK_ROUTE_SOCKET: - /* RTM_MAX always point to RTM_SETxxxx, ie RTM_NEWxxx + 3 */ + /* RTM_MAX always points to RTM_SETxxxx, ie RTM_NEWxxx + 3. + * If the BUILD_BUG_ON() below fails you must update the + * structures at the top of this file with the new mappings + * before updating the BUILD_BUG_ON() macro! + */ BUILD_BUG_ON(RTM_MAX != (RTM_NEWCHAIN + 3)); err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms, sizeof(nlmsg_route_perms)); @@ -170,6 +177,10 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) break; case SECCLASS_NETLINK_XFRM_SOCKET: + /* If the BUILD_BUG_ON() below fails you must update the + * structures at the top of this file with the new mappings + * before updating the BUILD_BUG_ON() macro! + */ BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_MAPPING); err = nlmsg_perm(nlmsg_type, perm, nlmsg_xfrm_perms, sizeof(nlmsg_xfrm_perms)); diff --git a/sound/core/control.c b/sound/core/control.c index 9aa15bfc7936..649d3217590e 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -348,6 +348,40 @@ static int snd_ctl_find_hole(struct snd_card *card, unsigned int count) return 0; } +/* add a new kcontrol object; call with card->controls_rwsem locked */ +static int __snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) +{ + struct snd_ctl_elem_id id; + unsigned int idx; + unsigned int count; + + id = kcontrol->id; + if (id.index > UINT_MAX - kcontrol->count) + return -EINVAL; + + if (snd_ctl_find_id(card, &id)) { + dev_err(card->dev, + "control %i:%i:%i:%s:%i is already present\n", + id.iface, id.device, id.subdevice, id.name, id.index); + return -EBUSY; + } + + if (snd_ctl_find_hole(card, kcontrol->count) < 0) + return -ENOMEM; + + list_add_tail(&kcontrol->list, &card->controls); + card->controls_count += kcontrol->count; + kcontrol->id.numid = card->last_numid + 1; + card->last_numid += kcontrol->count; + + id = kcontrol->id; + count = kcontrol->count; + for (idx = 0; idx < count; idx++, id.index++, id.numid++) + snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); + + return 0; +} + /** * snd_ctl_add - add the control instance to the card * @card: the card instance @@ -364,45 +398,18 @@ static int snd_ctl_find_hole(struct snd_card *card, unsigned int count) */ int snd_ctl_add(struct snd_card *card, struct snd_kcontrol *kcontrol) { - struct snd_ctl_elem_id id; - unsigned int idx; - unsigned int count; int err = -EINVAL; if (! kcontrol) return err; if (snd_BUG_ON(!card || !kcontrol->info)) goto error; - id = kcontrol->id; - if (id.index > UINT_MAX - kcontrol->count) - goto error; down_write(&card->controls_rwsem); - if (snd_ctl_find_id(card, &id)) { - up_write(&card->controls_rwsem); - dev_err(card->dev, "control %i:%i:%i:%s:%i is already present\n", - id.iface, - id.device, - id.subdevice, - id.name, - id.index); - err = -EBUSY; - goto error; - } - if (snd_ctl_find_hole(card, kcontrol->count) < 0) { - up_write(&card->controls_rwsem); - err = -ENOMEM; - goto error; - } - list_add_tail(&kcontrol->list, &card->controls); - card->controls_count += kcontrol->count; - kcontrol->id.numid = card->last_numid + 1; - card->last_numid += kcontrol->count; - id = kcontrol->id; - count = kcontrol->count; + err = __snd_ctl_add(card, kcontrol); up_write(&card->controls_rwsem); - for (idx = 0; idx < count; idx++, id.index++, id.numid++) - snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_ADD, &id); + if (err < 0) + goto error; return 0; error: @@ -1361,9 +1368,12 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, kctl->tlv.c = snd_ctl_elem_user_tlv; /* This function manage to free the instance on failure. */ - err = snd_ctl_add(card, kctl); - if (err < 0) - return err; + down_write(&card->controls_rwsem); + err = __snd_ctl_add(card, kctl); + if (err < 0) { + snd_ctl_free_one(kctl); + goto unlock; + } offset = snd_ctl_get_ioff(kctl, &info->id); snd_ctl_build_ioff(&info->id, kctl, offset); /* @@ -1374,10 +1384,10 @@ static int snd_ctl_elem_add(struct snd_ctl_file *file, * which locks the element. */ - down_write(&card->controls_rwsem); card->user_ctl_count++; - up_write(&card->controls_rwsem); + unlock: + up_write(&card->controls_rwsem); return 0; } diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c index 32453f81b95a..3a5008837576 100644 --- a/sound/isa/wss/wss_lib.c +++ b/sound/isa/wss/wss_lib.c @@ -1531,7 +1531,6 @@ static int snd_wss_playback_open(struct snd_pcm_substream *substream) if (err < 0) { if (chip->release_dma) chip->release_dma(chip, chip->dma_private_data, chip->dma1); - snd_free_pages(runtime->dma_area, runtime->dma_bytes); return err; } chip->playback_substream = substream; @@ -1572,7 +1571,6 @@ static int snd_wss_capture_open(struct snd_pcm_substream *substream) if (err < 0) { if (chip->release_dma) chip->release_dma(chip, chip->dma_private_data, chip->dma2); - snd_free_pages(runtime->dma_area, runtime->dma_bytes); return err; } chip->capture_substream = substream; diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c index f4459d1a9d67..27b468f057dd 100644 --- a/sound/pci/ac97/ac97_codec.c +++ b/sound/pci/ac97/ac97_codec.c @@ -824,7 +824,7 @@ static int snd_ac97_put_spsa(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_ { struct snd_ac97 *ac97 = snd_kcontrol_chip(kcontrol); int reg = kcontrol->private_value & 0xff; - int shift = (kcontrol->private_value >> 8) & 0xff; + int shift = (kcontrol->private_value >> 8) & 0x0f; int mask = (kcontrol->private_value >> 16) & 0xff; // int invert = (kcontrol->private_value >> 24) & 0xff; unsigned short value, old, new; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index d8eb2b5f51ae..0bbdf1a01e76 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2169,6 +2169,8 @@ static struct snd_pci_quirk power_save_blacklist[] = { /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ SND_PCI_QUIRK(0x1849, 0xc892, "Asrock B85M-ITX", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ + SND_PCI_QUIRK(0x1849, 0x0397, "Asrock N68C-S UCC", 0), + /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ SND_PCI_QUIRK(0x1849, 0x7662, "Asrock H81M-HDS", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 970bc44a378b..06f93032d0cc 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -388,6 +388,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec) case 0x10ec0285: case 0x10ec0298: case 0x10ec0289: + case 0x10ec0300: alc_update_coef_idx(codec, 0x10, 1<<9, 0); break; case 0x10ec0275: @@ -2830,6 +2831,7 @@ enum { ALC269_TYPE_ALC215, ALC269_TYPE_ALC225, ALC269_TYPE_ALC294, + ALC269_TYPE_ALC300, ALC269_TYPE_ALC700, }; @@ -2864,6 +2866,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec) case ALC269_TYPE_ALC215: case ALC269_TYPE_ALC225: case ALC269_TYPE_ALC294: + case ALC269_TYPE_ALC300: case ALC269_TYPE_ALC700: ssids = alc269_ssids; break; @@ -5358,6 +5361,16 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec, spec->gen.preferred_dacs = preferred_pairs; } +/* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */ +static void alc285_fixup_invalidate_dacs(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + snd_hda_override_wcaps(codec, 0x03, 0); +} + /* for hda_fixup_thinkpad_acpi() */ #include "thinkpad_helper.c" @@ -5495,6 +5508,8 @@ enum { ALC255_FIXUP_DELL_HEADSET_MIC, ALC295_FIXUP_HP_X360, ALC221_FIXUP_HP_HEADSET_MIC, + ALC285_FIXUP_LENOVO_HEADPHONE_NOISE, + ALC295_FIXUP_HP_AUTO_MUTE, }; static const struct hda_fixup alc269_fixups[] = { @@ -5659,6 +5674,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC269_FIXUP_HP_MUTE_LED_MIC3] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_hp_mute_led_mic3, + .chained = true, + .chain_id = ALC295_FIXUP_HP_AUTO_MUTE }, [ALC269_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, @@ -6362,6 +6379,14 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MIC }, + [ALC285_FIXUP_LENOVO_HEADPHONE_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_invalidate_dacs, + }, + [ALC295_FIXUP_HP_AUTO_MUTE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_auto_mute_via_amp, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6532,6 +6557,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), @@ -7034,6 +7060,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x19, 0x03a11020}, {0x21, 0x0321101f}), + SND_HDA_PIN_QUIRK(0x10ec0285, 0x17aa, "Lenovo", ALC285_FIXUP_LENOVO_HEADPHONE_NOISE, + {0x12, 0x90a60130}, + {0x14, 0x90170110}, + {0x19, 0x04a11040}, + {0x21, 0x04211020}), SND_HDA_PIN_QUIRK(0x10ec0288, 0x1028, "Dell", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE, {0x12, 0x90a60120}, {0x14, 0x90170110}, @@ -7295,6 +7326,10 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; /* ALC2x4 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x6b, 0x0018, (1<<4) | (1<<3)); /* UAJ MIC Vref control by verb */ break; + case 0x10ec0300: + spec->codec_variant = ALC269_TYPE_ALC300; + spec->gen.mixer_nid = 0; /* no loopback on ALC300 */ + break; case 0x10ec0700: case 0x10ec0701: case 0x10ec0703: @@ -8405,6 +8440,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = { HDA_CODEC_ENTRY(0x10ec0295, "ALC295", patch_alc269), HDA_CODEC_ENTRY(0x10ec0298, "ALC298", patch_alc269), HDA_CODEC_ENTRY(0x10ec0299, "ALC299", patch_alc269), + HDA_CODEC_ENTRY(0x10ec0300, "ALC300", patch_alc269), HDA_CODEC_REV_ENTRY(0x10ec0861, 0x100340, "ALC660", patch_alc861), HDA_CODEC_ENTRY(0x10ec0660, "ALC660-VD", patch_alc861vd), HDA_CODEC_ENTRY(0x10ec0861, "ALC861", patch_alc861), diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c index 4e9854889a95..e63d6e33df48 100644 --- a/sound/soc/codecs/hdac_hdmi.c +++ b/sound/soc/codecs/hdac_hdmi.c @@ -2187,11 +2187,6 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) */ snd_hdac_codec_read(hdev, hdev->afg, 0, AC_VERB_SET_POWER_STATE, AC_PWRST_D3); - err = snd_hdac_display_power(bus, false); - if (err < 0) { - dev_err(dev, "Cannot turn on display power on i915\n"); - return err; - } hlink = snd_hdac_ext_bus_get_link(bus, dev_name(dev)); if (!hlink) { @@ -2201,7 +2196,11 @@ static int hdac_hdmi_runtime_suspend(struct device *dev) snd_hdac_ext_bus_link_put(bus, hlink); - return 0; + err = snd_hdac_display_power(bus, false); + if (err < 0) + dev_err(dev, "Cannot turn off display power on i915\n"); + + return err; } static int hdac_hdmi_runtime_resume(struct device *dev) diff --git a/sound/soc/codecs/pcm186x.h b/sound/soc/codecs/pcm186x.h index 2c6ba55bf394..bb3f0c42a1cd 100644 --- a/sound/soc/codecs/pcm186x.h +++ b/sound/soc/codecs/pcm186x.h @@ -139,7 +139,7 @@ enum pcm186x_type { #define PCM186X_MAX_REGISTER PCM186X_CURR_TRIM_CTRL /* PCM186X_PAGE */ -#define PCM186X_RESET 0xff +#define PCM186X_RESET 0xfe /* PCM186X_ADCX_INPUT_SEL_X */ #define PCM186X_ADC_INPUT_SEL_POL BIT(7) diff --git a/sound/soc/codecs/pcm3060.c b/sound/soc/codecs/pcm3060.c index 494d9d662be8..771b46e1974b 100644 --- a/sound/soc/codecs/pcm3060.c +++ b/sound/soc/codecs/pcm3060.c @@ -198,20 +198,16 @@ static const struct snd_kcontrol_new pcm3060_dapm_controls[] = { }; static const struct snd_soc_dapm_widget pcm3060_dapm_widgets[] = { - SND_SOC_DAPM_OUTPUT("OUTL+"), - SND_SOC_DAPM_OUTPUT("OUTR+"), - SND_SOC_DAPM_OUTPUT("OUTL-"), - SND_SOC_DAPM_OUTPUT("OUTR-"), + SND_SOC_DAPM_OUTPUT("OUTL"), + SND_SOC_DAPM_OUTPUT("OUTR"), SND_SOC_DAPM_INPUT("INL"), SND_SOC_DAPM_INPUT("INR"), }; static const struct snd_soc_dapm_route pcm3060_dapm_map[] = { - { "OUTL+", NULL, "Playback" }, - { "OUTR+", NULL, "Playback" }, - { "OUTL-", NULL, "Playback" }, - { "OUTR-", NULL, "Playback" }, + { "OUTL", NULL, "Playback" }, + { "OUTR", NULL, "Playback" }, { "Capture", NULL, "INL" }, { "Capture", NULL, "INR" }, diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index a53dc174bbf0..66501b8dc46f 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -765,38 +765,41 @@ static unsigned int wm_adsp_region_to_reg(struct wm_adsp_region const *mem, static void wm_adsp2_show_fw_status(struct wm_adsp *dsp) { - u16 scratch[4]; + unsigned int scratch[4]; + unsigned int addr = dsp->base + ADSP2_SCRATCH0; + unsigned int i; int ret; - ret = regmap_raw_read(dsp->regmap, dsp->base + ADSP2_SCRATCH0, - scratch, sizeof(scratch)); - if (ret) { - adsp_err(dsp, "Failed to read SCRATCH regs: %d\n", ret); - return; + for (i = 0; i < ARRAY_SIZE(scratch); ++i) { + ret = regmap_read(dsp->regmap, addr + i, &scratch[i]); + if (ret) { + adsp_err(dsp, "Failed to read SCRATCH%u: %d\n", i, ret); + return; + } } adsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", - be16_to_cpu(scratch[0]), - be16_to_cpu(scratch[1]), - be16_to_cpu(scratch[2]), - be16_to_cpu(scratch[3])); + scratch[0], scratch[1], scratch[2], scratch[3]); } static void wm_adsp2v2_show_fw_status(struct wm_adsp *dsp) { - u32 scratch[2]; + unsigned int scratch[2]; int ret; - ret = regmap_raw_read(dsp->regmap, dsp->base + ADSP2V2_SCRATCH0_1, - scratch, sizeof(scratch)); - + ret = regmap_read(dsp->regmap, dsp->base + ADSP2V2_SCRATCH0_1, + &scratch[0]); if (ret) { - adsp_err(dsp, "Failed to read SCRATCH regs: %d\n", ret); + adsp_err(dsp, "Failed to read SCRATCH0_1: %d\n", ret); return; } - scratch[0] = be32_to_cpu(scratch[0]); - scratch[1] = be32_to_cpu(scratch[1]); + ret = regmap_read(dsp->regmap, dsp->base + ADSP2V2_SCRATCH2_3, + &scratch[1]); + if (ret) { + adsp_err(dsp, "Failed to read SCRATCH2_3: %d\n", ret); + return; + } adsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", scratch[0] & 0xFFFF, diff --git a/sound/soc/intel/Kconfig b/sound/soc/intel/Kconfig index 0caa1f4eb94d..18e717703685 100644 --- a/sound/soc/intel/Kconfig +++ b/sound/soc/intel/Kconfig @@ -101,22 +101,42 @@ config SND_SST_ATOM_HIFI2_PLATFORM_ACPI codec, then enable this option by saying Y or m. This is a recommended option -config SND_SOC_INTEL_SKYLAKE_SSP_CLK - tristate - config SND_SOC_INTEL_SKYLAKE tristate "SKL/BXT/KBL/GLK/CNL... Platforms" depends on PCI && ACPI + select SND_SOC_INTEL_SKYLAKE_COMMON + help + If you have a Intel Skylake/Broxton/ApolloLake/KabyLake/ + GeminiLake or CannonLake platform with the DSP enabled in the BIOS + then enable this option by saying Y or m. + +if SND_SOC_INTEL_SKYLAKE + +config SND_SOC_INTEL_SKYLAKE_SSP_CLK + tristate + +config SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC + bool "HDAudio codec support" + help + If you have a Intel Skylake/Broxton/ApolloLake/KabyLake/ + GeminiLake or CannonLake platform with an HDaudio codec + then enable this option by saying Y + +config SND_SOC_INTEL_SKYLAKE_COMMON + tristate select SND_HDA_EXT_CORE select SND_HDA_DSP_LOADER select SND_SOC_TOPOLOGY select SND_SOC_INTEL_SST + select SND_SOC_HDAC_HDA if SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC select SND_SOC_ACPI_INTEL_MATCH help If you have a Intel Skylake/Broxton/ApolloLake/KabyLake/ GeminiLake or CannonLake platform with the DSP enabled in the BIOS then enable this option by saying Y or m. +endif ## SND_SOC_INTEL_SKYLAKE + config SND_SOC_ACPI_INTEL_MATCH tristate select SND_SOC_ACPI if ACPI diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig index 73ca1350aa31..b177db2a0dbb 100644 --- a/sound/soc/intel/boards/Kconfig +++ b/sound/soc/intel/boards/Kconfig @@ -293,16 +293,6 @@ config SND_SOC_INTEL_KBL_DA7219_MAX98927_MACH Say Y if you have such a device. If unsure select "N". -config SND_SOC_INTEL_SKL_HDA_DSP_GENERIC_MACH - tristate "SKL/KBL/BXT/APL with HDA Codecs" - select SND_SOC_HDAC_HDMI - select SND_SOC_HDAC_HDA - help - This adds support for ASoC machine driver for Intel platforms - SKL/KBL/BXT/APL with iDisp, HDA audio codecs. - Say Y or m if you have such a device. This is a recommended option. - If unsure select "N". - config SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH tristate "GLK with RT5682 and MAX98357A in I2S Mode" depends on MFD_INTEL_LPSS && I2C && ACPI @@ -319,4 +309,18 @@ config SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH endif ## SND_SOC_INTEL_SKYLAKE +if SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC + +config SND_SOC_INTEL_SKL_HDA_DSP_GENERIC_MACH + tristate "SKL/KBL/BXT/APL with HDA Codecs" + select SND_SOC_HDAC_HDMI + # SND_SOC_HDAC_HDA is already selected + help + This adds support for ASoC machine driver for Intel platforms + SKL/KBL/BXT/APL with iDisp, HDA audio codecs. + Say Y or m if you have such a device. This is a recommended option. + If unsure select "N". + +endif ## SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC + endif ## SND_SOC_INTEL_MACH diff --git a/sound/soc/intel/boards/cht_bsw_max98090_ti.c b/sound/soc/intel/boards/cht_bsw_max98090_ti.c index db6976f4ddaa..9d9f6e41d81c 100644 --- a/sound/soc/intel/boards/cht_bsw_max98090_ti.c +++ b/sound/soc/intel/boards/cht_bsw_max98090_ti.c @@ -19,6 +19,7 @@ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ +#include <linux/dmi.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/slab.h> @@ -35,6 +36,8 @@ #define CHT_PLAT_CLK_3_HZ 19200000 #define CHT_CODEC_DAI "HiFi" +#define QUIRK_PMC_PLT_CLK_0 0x01 + struct cht_mc_private { struct clk *mclk; struct snd_soc_jack jack; @@ -385,11 +388,29 @@ static struct snd_soc_card snd_soc_card_cht = { .num_controls = ARRAY_SIZE(cht_mc_controls), }; +static const struct dmi_system_id cht_max98090_quirk_table[] = { + { + /* Swanky model Chromebook (Toshiba Chromebook 2) */ + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "Swanky"), + }, + .driver_data = (void *)QUIRK_PMC_PLT_CLK_0, + }, + {} +}; + static int snd_cht_mc_probe(struct platform_device *pdev) { + const struct dmi_system_id *dmi_id; struct device *dev = &pdev->dev; int ret_val = 0; struct cht_mc_private *drv; + const char *mclk_name; + int quirks = 0; + + dmi_id = dmi_first_match(cht_max98090_quirk_table); + if (dmi_id) + quirks = (unsigned long)dmi_id->driver_data; drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL); if (!drv) @@ -411,11 +432,16 @@ static int snd_cht_mc_probe(struct platform_device *pdev) snd_soc_card_cht.dev = &pdev->dev; snd_soc_card_set_drvdata(&snd_soc_card_cht, drv); - drv->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3"); + if (quirks & QUIRK_PMC_PLT_CLK_0) + mclk_name = "pmc_plt_clk_0"; + else + mclk_name = "pmc_plt_clk_3"; + + drv->mclk = devm_clk_get(&pdev->dev, mclk_name); if (IS_ERR(drv->mclk)) { dev_err(&pdev->dev, - "Failed to get MCLK from pmc_plt_clk_3: %ld\n", - PTR_ERR(drv->mclk)); + "Failed to get MCLK from %s: %ld\n", + mclk_name, PTR_ERR(drv->mclk)); return PTR_ERR(drv->mclk); } diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index 29225623b4b4..7487f388e65d 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -37,7 +37,9 @@ #include "skl.h" #include "skl-sst-dsp.h" #include "skl-sst-ipc.h" +#if IS_ENABLED(CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC) #include "../../../soc/codecs/hdac_hda.h" +#endif /* * initialize the PCI registers @@ -658,6 +660,8 @@ static void skl_clock_device_unregister(struct skl *skl) platform_device_unregister(skl->clk_dev); } +#if IS_ENABLED(CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC) + #define IDISP_INTEL_VENDOR_ID 0x80860000 /* @@ -676,6 +680,8 @@ static void load_codec_module(struct hda_codec *codec) #endif } +#endif /* CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC */ + /* * Probe the given codec address */ @@ -685,9 +691,11 @@ static int probe_codec(struct hdac_bus *bus, int addr) (AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID; unsigned int res = -1; struct skl *skl = bus_to_skl(bus); +#if IS_ENABLED(CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC) struct hdac_hda_priv *hda_codec; - struct hdac_device *hdev; int err; +#endif + struct hdac_device *hdev; mutex_lock(&bus->cmd_mutex); snd_hdac_bus_send_cmd(bus, cmd); @@ -697,6 +705,7 @@ static int probe_codec(struct hdac_bus *bus, int addr) return -EIO; dev_dbg(bus->dev, "codec #%d probed OK: %x\n", addr, res); +#if IS_ENABLED(CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC) hda_codec = devm_kzalloc(&skl->pci->dev, sizeof(*hda_codec), GFP_KERNEL); if (!hda_codec) @@ -715,6 +724,13 @@ static int probe_codec(struct hdac_bus *bus, int addr) load_codec_module(&hda_codec->codec); } return 0; +#else + hdev = devm_kzalloc(&skl->pci->dev, sizeof(*hdev), GFP_KERNEL); + if (!hdev) + return -ENOMEM; + + return snd_hdac_ext_bus_device_init(bus, addr, hdev); +#endif /* CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC */ } /* Codec initialization */ @@ -815,6 +831,12 @@ static void skl_probe_work(struct work_struct *work) } } + /* + * we are done probing so decrement link counts + */ + list_for_each_entry(hlink, &bus->hlink_list, list) + snd_hdac_ext_bus_link_put(bus, hlink); + if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) { err = snd_hdac_display_power(bus, false); if (err < 0) { @@ -824,12 +846,6 @@ static void skl_probe_work(struct work_struct *work) } } - /* - * we are done probing so decrement link counts - */ - list_for_each_entry(hlink, &bus->hlink_list, list) - snd_hdac_ext_bus_link_put(bus, hlink); - /* configure PM */ pm_runtime_put_noidle(bus->dev); pm_runtime_allow(bus->dev); @@ -870,7 +886,7 @@ static int skl_create(struct pci_dev *pci, hbus = skl_to_hbus(skl); bus = skl_to_bus(skl); -#if IS_ENABLED(CONFIG_SND_SOC_HDAC_HDA) +#if IS_ENABLED(CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC) ext_ops = snd_soc_hdac_hda_get_ops(); #endif snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops, ext_ops); diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c index d5ae9eb8c756..fed45b41f9d3 100644 --- a/sound/soc/omap/omap-abe-twl6040.c +++ b/sound/soc/omap/omap-abe-twl6040.c @@ -36,6 +36,8 @@ #include "../codecs/twl6040.h" struct abe_twl6040 { + struct snd_soc_card card; + struct snd_soc_dai_link dai_links[2]; int jack_detection; /* board can detect jack events */ int mclk_freq; /* MCLK frequency speed for twl6040 */ }; @@ -208,40 +210,10 @@ static int omap_abe_dmic_init(struct snd_soc_pcm_runtime *rtd) ARRAY_SIZE(dmic_audio_map)); } -/* Digital audio interface glue - connects codec <--> CPU */ -static struct snd_soc_dai_link abe_twl6040_dai_links[] = { - { - .name = "TWL6040", - .stream_name = "TWL6040", - .codec_dai_name = "twl6040-legacy", - .codec_name = "twl6040-codec", - .init = omap_abe_twl6040_init, - .ops = &omap_abe_ops, - }, - { - .name = "DMIC", - .stream_name = "DMIC Capture", - .codec_dai_name = "dmic-hifi", - .codec_name = "dmic-codec", - .init = omap_abe_dmic_init, - .ops = &omap_abe_dmic_ops, - }, -}; - -/* Audio machine driver */ -static struct snd_soc_card omap_abe_card = { - .owner = THIS_MODULE, - - .dapm_widgets = twl6040_dapm_widgets, - .num_dapm_widgets = ARRAY_SIZE(twl6040_dapm_widgets), - .dapm_routes = audio_map, - .num_dapm_routes = ARRAY_SIZE(audio_map), -}; - static int omap_abe_probe(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; - struct snd_soc_card *card = &omap_abe_card; + struct snd_soc_card *card; struct device_node *dai_node; struct abe_twl6040 *priv; int num_links = 0; @@ -252,12 +224,18 @@ static int omap_abe_probe(struct platform_device *pdev) return -ENODEV; } - card->dev = &pdev->dev; - priv = devm_kzalloc(&pdev->dev, sizeof(struct abe_twl6040), GFP_KERNEL); if (priv == NULL) return -ENOMEM; + card = &priv->card; + card->dev = &pdev->dev; + card->owner = THIS_MODULE; + card->dapm_widgets = twl6040_dapm_widgets; + card->num_dapm_widgets = ARRAY_SIZE(twl6040_dapm_widgets); + card->dapm_routes = audio_map; + card->num_dapm_routes = ARRAY_SIZE(audio_map); + if (snd_soc_of_parse_card_name(card, "ti,model")) { dev_err(&pdev->dev, "Card name is not provided\n"); return -ENODEV; @@ -274,14 +252,27 @@ static int omap_abe_probe(struct platform_device *pdev) dev_err(&pdev->dev, "McPDM node is not provided\n"); return -EINVAL; } - abe_twl6040_dai_links[0].cpu_of_node = dai_node; - abe_twl6040_dai_links[0].platform_of_node = dai_node; + + priv->dai_links[0].name = "DMIC"; + priv->dai_links[0].stream_name = "TWL6040"; + priv->dai_links[0].cpu_of_node = dai_node; + priv->dai_links[0].platform_of_node = dai_node; + priv->dai_links[0].codec_dai_name = "twl6040-legacy"; + priv->dai_links[0].codec_name = "twl6040-codec"; + priv->dai_links[0].init = omap_abe_twl6040_init; + priv->dai_links[0].ops = &omap_abe_ops; dai_node = of_parse_phandle(node, "ti,dmic", 0); if (dai_node) { num_links = 2; - abe_twl6040_dai_links[1].cpu_of_node = dai_node; - abe_twl6040_dai_links[1].platform_of_node = dai_node; + priv->dai_links[1].name = "TWL6040"; + priv->dai_links[1].stream_name = "DMIC Capture"; + priv->dai_links[1].cpu_of_node = dai_node; + priv->dai_links[1].platform_of_node = dai_node; + priv->dai_links[1].codec_dai_name = "dmic-hifi"; + priv->dai_links[1].codec_name = "dmic-codec"; + priv->dai_links[1].init = omap_abe_dmic_init; + priv->dai_links[1].ops = &omap_abe_dmic_ops; } else { num_links = 1; } @@ -300,7 +291,7 @@ static int omap_abe_probe(struct platform_device *pdev) return -ENODEV; } - card->dai_link = abe_twl6040_dai_links; + card->dai_link = priv->dai_links; card->num_links = num_links; snd_soc_card_set_drvdata(card, priv); diff --git a/sound/soc/omap/omap-dmic.c b/sound/soc/omap/omap-dmic.c index fe966272bd0c..cba9645b6487 100644 --- a/sound/soc/omap/omap-dmic.c +++ b/sound/soc/omap/omap-dmic.c @@ -48,6 +48,8 @@ struct omap_dmic { struct device *dev; void __iomem *io_base; struct clk *fclk; + struct pm_qos_request pm_qos_req; + int latency; int fclk_freq; int out_freq; int clk_div; @@ -124,6 +126,8 @@ static void omap_dmic_dai_shutdown(struct snd_pcm_substream *substream, mutex_lock(&dmic->mutex); + pm_qos_remove_request(&dmic->pm_qos_req); + if (!dai->active) dmic->active = 0; @@ -228,6 +232,8 @@ static int omap_dmic_dai_hw_params(struct snd_pcm_substream *substream, /* packet size is threshold * channels */ dma_data = snd_soc_dai_get_dma_data(dai, substream); dma_data->maxburst = dmic->threshold * channels; + dmic->latency = (OMAP_DMIC_THRES_MAX - dmic->threshold) * USEC_PER_SEC / + params_rate(params); return 0; } @@ -238,6 +244,9 @@ static int omap_dmic_dai_prepare(struct snd_pcm_substream *substream, struct omap_dmic *dmic = snd_soc_dai_get_drvdata(dai); u32 ctrl; + if (pm_qos_request_active(&dmic->pm_qos_req)) + pm_qos_update_request(&dmic->pm_qos_req, dmic->latency); + /* Configure uplink threshold */ omap_dmic_write(dmic, OMAP_DMIC_FIFO_CTRL_REG, dmic->threshold); diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c index d0ebb6b9bfac..2d6decbfc99e 100644 --- a/sound/soc/omap/omap-mcbsp.c +++ b/sound/soc/omap/omap-mcbsp.c @@ -308,9 +308,9 @@ static int omap_mcbsp_dai_hw_params(struct snd_pcm_substream *substream, pkt_size = channels; } - latency = ((((buffer_size - pkt_size) / channels) * 1000) - / (params->rate_num / params->rate_den)); - + latency = (buffer_size - pkt_size) / channels; + latency = latency * USEC_PER_SEC / + (params->rate_num / params->rate_den); mcbsp->latency[substream->stream] = latency; omap_mcbsp_set_threshold(substream, pkt_size); diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c index 4c1be36c2207..7d5bdc5a2890 100644 --- a/sound/soc/omap/omap-mcpdm.c +++ b/sound/soc/omap/omap-mcpdm.c @@ -54,6 +54,8 @@ struct omap_mcpdm { unsigned long phys_base; void __iomem *io_base; int irq; + struct pm_qos_request pm_qos_req; + int latency[2]; struct mutex mutex; @@ -277,6 +279,9 @@ static void omap_mcpdm_dai_shutdown(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + int tx = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK); + int stream1 = tx ? SNDRV_PCM_STREAM_PLAYBACK : SNDRV_PCM_STREAM_CAPTURE; + int stream2 = tx ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK; mutex_lock(&mcpdm->mutex); @@ -289,6 +294,14 @@ static void omap_mcpdm_dai_shutdown(struct snd_pcm_substream *substream, } } + if (mcpdm->latency[stream2]) + pm_qos_update_request(&mcpdm->pm_qos_req, + mcpdm->latency[stream2]); + else if (mcpdm->latency[stream1]) + pm_qos_remove_request(&mcpdm->pm_qos_req); + + mcpdm->latency[stream1] = 0; + mutex_unlock(&mcpdm->mutex); } @@ -300,7 +313,7 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream, int stream = substream->stream; struct snd_dmaengine_dai_dma_data *dma_data; u32 threshold; - int channels; + int channels, latency; int link_mask = 0; channels = params_channels(params); @@ -344,14 +357,25 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream, dma_data->maxburst = (MCPDM_DN_THRES_MAX - threshold) * channels; + latency = threshold; } else { /* If playback is not running assume a stereo stream to come */ if (!mcpdm->config[!stream].link_mask) mcpdm->config[!stream].link_mask = (0x3 << 3); dma_data->maxburst = threshold * channels; + latency = (MCPDM_DN_THRES_MAX - threshold); } + /* + * The DMA must act to a DMA request within latency time (usec) to avoid + * under/overflow + */ + mcpdm->latency[stream] = latency * USEC_PER_SEC / params_rate(params); + + if (!mcpdm->latency[stream]) + mcpdm->latency[stream] = 10; + /* Check if we need to restart McPDM with this stream */ if (mcpdm->config[stream].link_mask && mcpdm->config[stream].link_mask != link_mask) @@ -366,6 +390,20 @@ static int omap_mcpdm_prepare(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + struct pm_qos_request *pm_qos_req = &mcpdm->pm_qos_req; + int tx = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK); + int stream1 = tx ? SNDRV_PCM_STREAM_PLAYBACK : SNDRV_PCM_STREAM_CAPTURE; + int stream2 = tx ? SNDRV_PCM_STREAM_CAPTURE : SNDRV_PCM_STREAM_PLAYBACK; + int latency = mcpdm->latency[stream2]; + + /* Prevent omap hardware from hitting off between FIFO fills */ + if (!latency || mcpdm->latency[stream1] < latency) + latency = mcpdm->latency[stream1]; + + if (pm_qos_request_active(pm_qos_req)) + pm_qos_update_request(pm_qos_req, latency); + else if (latency) + pm_qos_add_request(pm_qos_req, PM_QOS_CPU_DMA_LATENCY, latency); if (!omap_mcpdm_active(mcpdm)) { omap_mcpdm_start(mcpdm); @@ -427,6 +465,9 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai) free_irq(mcpdm->irq, (void *)mcpdm); pm_runtime_disable(mcpdm->dev); + if (pm_qos_request_active(&mcpdm->pm_qos_req)) + pm_qos_remove_request(&mcpdm->pm_qos_req); + return 0; } diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c index eb1b9da05dd4..4715527054e5 100644 --- a/sound/soc/qcom/common.c +++ b/sound/soc/qcom/common.c @@ -13,6 +13,7 @@ int qcom_snd_parse_of(struct snd_soc_card *card) struct device_node *cpu = NULL; struct device *dev = card->dev; struct snd_soc_dai_link *link; + struct of_phandle_args args; int ret, num_links; ret = snd_soc_of_parse_card_name(card, "model"); @@ -47,12 +48,14 @@ int qcom_snd_parse_of(struct snd_soc_card *card) goto err; } - link->cpu_of_node = of_parse_phandle(cpu, "sound-dai", 0); - if (!link->cpu_of_node) { + ret = of_parse_phandle_with_args(cpu, "sound-dai", + "#sound-dai-cells", 0, &args); + if (ret) { dev_err(card->dev, "error getting cpu phandle\n"); - ret = -EINVAL; goto err; } + link->cpu_of_node = args.np; + link->id = args.args[0]; ret = snd_soc_of_get_dai_name(cpu, &link->cpu_dai_name); if (ret) { diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c index 60ff4a2d3577..8f6c8fc073a9 100644 --- a/sound/soc/qcom/qdsp6/q6afe-dai.c +++ b/sound/soc/qcom/qdsp6/q6afe-dai.c @@ -1112,204 +1112,204 @@ static int q6afe_of_xlate_dai_name(struct snd_soc_component *component, } static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = { - SND_SOC_DAPM_AIF_OUT("HDMI_RX", "HDMI Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_RX", "Slimbus Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_RX", "Slimbus1 Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_RX", "Slimbus2 Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_RX", "Slimbus3 Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_RX", "Slimbus4 Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_RX", "Slimbus5 Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_RX", "Slimbus6 Playback", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_0_TX", "Slimbus Capture", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_1_TX", "Slimbus1 Capture", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_2_TX", "Slimbus2 Capture", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_3_TX", "Slimbus3 Capture", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_4_TX", "Slimbus4 Capture", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_5_TX", "Slimbus5 Capture", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_6_TX", "Slimbus6 Capture", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_RX", "Quaternary MI2S Playback", + SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("QUAT_MI2S_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_MI2S_TX", "Quaternary MI2S Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_MI2S_RX", "Tertiary MI2S Playback", + SND_SOC_DAPM_AIF_IN("TERT_MI2S_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_MI2S_TX", "Tertiary MI2S Capture", + SND_SOC_DAPM_AIF_OUT("TERT_MI2S_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_MI2S_RX", "Secondary MI2S Playback", + SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_MI2S_TX", "Secondary MI2S Capture", + SND_SOC_DAPM_AIF_OUT("SEC_MI2S_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_MI2S_RX_SD1", + SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX_SD1", "Secondary MI2S Playback SD1", 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRI_MI2S_RX", "Primary MI2S Playback", + SND_SOC_DAPM_AIF_IN("PRI_MI2S_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRI_MI2S_TX", "Primary MI2S Capture", + SND_SOC_DAPM_AIF_OUT("PRI_MI2S_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_0", "Primary TDM0 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_1", "Primary TDM1 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_2", "Primary TDM2 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_3", "Primary TDM3 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_4", "Primary TDM4 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_5", "Primary TDM5 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_6", "Primary TDM6 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_RX_7", "Primary TDM7 Playback", + SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_0", "Primary TDM0 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_1", "Primary TDM1 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_2", "Primary TDM2 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_3", "Primary TDM3 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_4", "Primary TDM4 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_5", "Primary TDM5 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_6", "Primary TDM6 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_TX_7", "Primary TDM7 Capture", + SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_0", "Secondary TDM0 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_1", "Secondary TDM1 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_2", "Secondary TDM2 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_3", "Secondary TDM3 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_4", "Secondary TDM4 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_5", "Secondary TDM5 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_6", "Secondary TDM6 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SEC_TDM_RX_7", "Secondary TDM7 Playback", + SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_0", "Secondary TDM0 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_1", "Secondary TDM1 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_2", "Secondary TDM2 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_3", "Secondary TDM3 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_4", "Secondary TDM4 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_5", "Secondary TDM5 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_6", "Secondary TDM6 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SEC_TDM_TX_7", "Secondary TDM7 Capture", + SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_0", "Tertiary TDM0 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_1", "Tertiary TDM1 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_2", "Tertiary TDM2 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_3", "Tertiary TDM3 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_4", "Tertiary TDM4 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_5", "Tertiary TDM5 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_6", "Tertiary TDM6 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("TERT_TDM_RX_7", "Tertiary TDM7 Playback", + SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_0", "Tertiary TDM0 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_1", "Tertiary TDM1 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_2", "Tertiary TDM2 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_3", "Tertiary TDM3 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_4", "Tertiary TDM4 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_5", "Tertiary TDM5 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_6", "Tertiary TDM6 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("TERT_TDM_TX_7", "Tertiary TDM7 Capture", + SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_0", "Quaternary TDM0 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_1", "Quaternary TDM1 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_2", "Quaternary TDM2 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_3", "Quaternary TDM3 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_4", "Quaternary TDM4 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_5", "Quaternary TDM5 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_6", "Quaternary TDM6 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUAT_TDM_RX_7", "Quaternary TDM7 Playback", + SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_0", "Quaternary TDM0 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_1", "Quaternary TDM1 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_2", "Quaternary TDM2 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_3", "Quaternary TDM3 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_4", "Quaternary TDM4 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_5", "Quaternary TDM5 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_6", "Quaternary TDM6 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUAT_TDM_TX_7", "Quaternary TDM7 Capture", + SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_0", "Quinary TDM0 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_1", "Quinary TDM1 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_2", "Quinary TDM2 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_3", "Quinary TDM3 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_4", "Quinary TDM4 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_5", "Quinary TDM5 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_6", "Quinary TDM6 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("QUIN_TDM_RX_7", "Quinary TDM7 Playback", + SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_7", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_0", "Quinary TDM0 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_0", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_1", "Quinary TDM1 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_1", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_2", "Quinary TDM2 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_2", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_3", "Quinary TDM3 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_3", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_4", "Quinary TDM4 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_4", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_5", "Quinary TDM5 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_5", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_6", "Quinary TDM6 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_6", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("QUIN_TDM_TX_7", "Quinary TDM7 Capture", + SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_7", NULL, 0, 0, 0, 0), }; diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c index 000775b4bba8..829b5e987b2a 100644 --- a/sound/soc/qcom/qdsp6/q6afe.c +++ b/sound/soc/qcom/qdsp6/q6afe.c @@ -49,14 +49,14 @@ #define AFE_PORT_I2S_SD1 0x2 #define AFE_PORT_I2S_SD2 0x3 #define AFE_PORT_I2S_SD3 0x4 -#define AFE_PORT_I2S_SD0_MASK BIT(0x1) -#define AFE_PORT_I2S_SD1_MASK BIT(0x2) -#define AFE_PORT_I2S_SD2_MASK BIT(0x3) -#define AFE_PORT_I2S_SD3_MASK BIT(0x4) -#define AFE_PORT_I2S_SD0_1_MASK GENMASK(2, 1) -#define AFE_PORT_I2S_SD2_3_MASK GENMASK(4, 3) -#define AFE_PORT_I2S_SD0_1_2_MASK GENMASK(3, 1) -#define AFE_PORT_I2S_SD0_1_2_3_MASK GENMASK(4, 1) +#define AFE_PORT_I2S_SD0_MASK BIT(0x0) +#define AFE_PORT_I2S_SD1_MASK BIT(0x1) +#define AFE_PORT_I2S_SD2_MASK BIT(0x2) +#define AFE_PORT_I2S_SD3_MASK BIT(0x3) +#define AFE_PORT_I2S_SD0_1_MASK GENMASK(1, 0) +#define AFE_PORT_I2S_SD2_3_MASK GENMASK(3, 2) +#define AFE_PORT_I2S_SD0_1_2_MASK GENMASK(2, 0) +#define AFE_PORT_I2S_SD0_1_2_3_MASK GENMASK(3, 0) #define AFE_PORT_I2S_QUAD01 0x5 #define AFE_PORT_I2S_QUAD23 0x6 #define AFE_PORT_I2S_6CHS 0x7 diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c index a16c71c03058..86115de5c1b2 100644 --- a/sound/soc/qcom/qdsp6/q6asm-dai.c +++ b/sound/soc/qcom/qdsp6/q6asm-dai.c @@ -122,7 +122,6 @@ static struct snd_pcm_hardware q6asm_dai_hardware_playback = { .rate_max = 48000, \ }, \ .name = "MultiMedia"#num, \ - .probe = fe_dai_probe, \ .id = MSM_FRONTEND_DAI_MULTIMEDIA##num, \ } @@ -511,38 +510,6 @@ static void q6asm_dai_pcm_free(struct snd_pcm *pcm) } } -static const struct snd_soc_dapm_route afe_pcm_routes[] = { - {"MM_DL1", NULL, "MultiMedia1 Playback" }, - {"MM_DL2", NULL, "MultiMedia2 Playback" }, - {"MM_DL3", NULL, "MultiMedia3 Playback" }, - {"MM_DL4", NULL, "MultiMedia4 Playback" }, - {"MM_DL5", NULL, "MultiMedia5 Playback" }, - {"MM_DL6", NULL, "MultiMedia6 Playback" }, - {"MM_DL7", NULL, "MultiMedia7 Playback" }, - {"MM_DL7", NULL, "MultiMedia8 Playback" }, - {"MultiMedia1 Capture", NULL, "MM_UL1"}, - {"MultiMedia2 Capture", NULL, "MM_UL2"}, - {"MultiMedia3 Capture", NULL, "MM_UL3"}, - {"MultiMedia4 Capture", NULL, "MM_UL4"}, - {"MultiMedia5 Capture", NULL, "MM_UL5"}, - {"MultiMedia6 Capture", NULL, "MM_UL6"}, - {"MultiMedia7 Capture", NULL, "MM_UL7"}, - {"MultiMedia8 Capture", NULL, "MM_UL8"}, - -}; - -static int fe_dai_probe(struct snd_soc_dai *dai) -{ - struct snd_soc_dapm_context *dapm; - - dapm = snd_soc_component_get_dapm(dai->component); - snd_soc_dapm_add_routes(dapm, afe_pcm_routes, - ARRAY_SIZE(afe_pcm_routes)); - - return 0; -} - - static const struct snd_soc_component_driver q6asm_fe_dai_component = { .name = DRV_NAME, .ops = &q6asm_dai_ops, diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index c6b51571be94..d61b8404f7da 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -909,6 +909,25 @@ static const struct snd_soc_dapm_route intercon[] = { {"MM_UL6", NULL, "MultiMedia6 Mixer"}, {"MM_UL7", NULL, "MultiMedia7 Mixer"}, {"MM_UL8", NULL, "MultiMedia8 Mixer"}, + + {"MM_DL1", NULL, "MultiMedia1 Playback" }, + {"MM_DL2", NULL, "MultiMedia2 Playback" }, + {"MM_DL3", NULL, "MultiMedia3 Playback" }, + {"MM_DL4", NULL, "MultiMedia4 Playback" }, + {"MM_DL5", NULL, "MultiMedia5 Playback" }, + {"MM_DL6", NULL, "MultiMedia6 Playback" }, + {"MM_DL7", NULL, "MultiMedia7 Playback" }, + {"MM_DL8", NULL, "MultiMedia8 Playback" }, + + {"MultiMedia1 Capture", NULL, "MM_UL1"}, + {"MultiMedia2 Capture", NULL, "MM_UL2"}, + {"MultiMedia3 Capture", NULL, "MM_UL3"}, + {"MultiMedia4 Capture", NULL, "MM_UL4"}, + {"MultiMedia5 Capture", NULL, "MM_UL5"}, + {"MultiMedia6 Capture", NULL, "MM_UL6"}, + {"MultiMedia7 Capture", NULL, "MM_UL7"}, + {"MultiMedia8 Capture", NULL, "MM_UL8"}, + }; static int routing_hw_params(struct snd_pcm_substream *substream, diff --git a/sound/soc/rockchip/rockchip_pcm.c b/sound/soc/rockchip/rockchip_pcm.c index 9e7b5fa4cf59..4ac78d7a4b2d 100644 --- a/sound/soc/rockchip/rockchip_pcm.c +++ b/sound/soc/rockchip/rockchip_pcm.c @@ -33,6 +33,7 @@ static const struct snd_pcm_hardware snd_rockchip_hardware = { static const struct snd_dmaengine_pcm_config rk_dmaengine_pcm_config = { .pcm_hardware = &snd_rockchip_hardware, + .prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config, .prealloc_buffer_size = 32 * 1024, }; diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index fcb4df23248c..6ec78f3096dd 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -306,7 +306,7 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, if (rsnd_ssi_is_multi_slave(mod, io)) return 0; - if (ssi->rate) { + if (ssi->usrcnt > 1) { if (ssi->rate != rate) { dev_err(dev, "SSI parent/child should use same rate\n"); return -EINVAL; diff --git a/sound/soc/soc-acpi.c b/sound/soc/soc-acpi.c index b8e72b52db30..4fb29f0e561e 100644 --- a/sound/soc/soc-acpi.c +++ b/sound/soc/soc-acpi.c @@ -10,11 +10,17 @@ struct snd_soc_acpi_mach * snd_soc_acpi_find_machine(struct snd_soc_acpi_mach *machines) { struct snd_soc_acpi_mach *mach; + struct snd_soc_acpi_mach *mach_alt; for (mach = machines; mach->id[0]; mach++) { if (acpi_dev_present(mach->id, NULL, -1)) { - if (mach->machine_quirk) - mach = mach->machine_quirk(mach); + if (mach->machine_quirk) { + mach_alt = mach->machine_quirk(mach); + if (!mach_alt) + continue; /* not full match, ignore */ + mach = mach_alt; + } + return mach; } } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 6ddcf12bc030..b29d0f65611e 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -2131,6 +2131,7 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card) } card->instantiated = 1; + dapm_mark_endpoints_dirty(card); snd_soc_dapm_sync(&card->dapm); mutex_unlock(&card->mutex); mutex_unlock(&client_mutex); diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c index ea05cc91aa05..211589b0b2ef 100644 --- a/sound/soc/stm/stm32_sai_sub.c +++ b/sound/soc/stm/stm32_sai_sub.c @@ -390,7 +390,7 @@ static int stm32_sai_add_mclk_provider(struct stm32_sai_sub_data *sai) char *mclk_name, *p, *s = (char *)pname; int ret, i = 0; - mclk = devm_kzalloc(dev, sizeof(mclk), GFP_KERNEL); + mclk = devm_kzalloc(dev, sizeof(*mclk), GFP_KERNEL); if (!mclk) return -ENOMEM; diff --git a/sound/soc/sunxi/Kconfig b/sound/soc/sunxi/Kconfig index 66aad0d3f9c7..8134c3c94229 100644 --- a/sound/soc/sunxi/Kconfig +++ b/sound/soc/sunxi/Kconfig @@ -31,7 +31,7 @@ config SND_SUN8I_CODEC_ANALOG config SND_SUN50I_CODEC_ANALOG tristate "Allwinner sun50i Codec Analog Controls Support" depends on (ARM64 && ARCH_SUNXI) || COMPILE_TEST - select SND_SUNXI_ADDA_PR_REGMAP + select SND_SUN8I_ADDA_PR_REGMAP help Say Y or M if you want to add support for the analog controls for the codec embedded in Allwinner A64 SoC. diff --git a/sound/soc/sunxi/sun8i-codec.c b/sound/soc/sunxi/sun8i-codec.c index 522a72fde78d..92c5de026c43 100644 --- a/sound/soc/sunxi/sun8i-codec.c +++ b/sound/soc/sunxi/sun8i-codec.c @@ -481,7 +481,11 @@ static const struct snd_soc_dapm_route sun8i_codec_dapm_routes[] = { { "Right Digital DAC Mixer", "AIF1 Slot 0 Digital DAC Playback Switch", "AIF1 Slot 0 Right"}, - /* ADC routes */ + /* ADC Routes */ + { "AIF1 Slot 0 Right ADC", NULL, "ADC" }, + { "AIF1 Slot 0 Left ADC", NULL, "ADC" }, + + /* ADC Mixer Routes */ { "Left Digital ADC Mixer", "AIF1 Data Digital ADC Capture Switch", "AIF1 Slot 0 Left ADC" }, { "Right Digital ADC Mixer", "AIF1 Data Digital ADC Capture Switch", @@ -605,16 +609,10 @@ err_pm_disable: static int sun8i_codec_remove(struct platform_device *pdev) { - struct snd_soc_card *card = platform_get_drvdata(pdev); - struct sun8i_codec *scodec = snd_soc_card_get_drvdata(card); - pm_runtime_disable(&pdev->dev); if (!pm_runtime_status_suspended(&pdev->dev)) sun8i_codec_runtime_suspend(&pdev->dev); - clk_disable_unprepare(scodec->clk_module); - clk_disable_unprepare(scodec->clk_bus); - return 0; } diff --git a/sound/sparc/cs4231.c b/sound/sparc/cs4231.c index e73c962590eb..079063d8038d 100644 --- a/sound/sparc/cs4231.c +++ b/sound/sparc/cs4231.c @@ -1146,10 +1146,8 @@ static int snd_cs4231_playback_open(struct snd_pcm_substream *substream) runtime->hw = snd_cs4231_playback; err = snd_cs4231_open(chip, CS4231_MODE_PLAY); - if (err < 0) { - snd_free_pages(runtime->dma_area, runtime->dma_bytes); + if (err < 0) return err; - } chip->playback_substream = substream; chip->p_periods_sent = 0; snd_pcm_set_sync(substream); @@ -1167,10 +1165,8 @@ static int snd_cs4231_capture_open(struct snd_pcm_substream *substream) runtime->hw = snd_cs4231_capture; err = snd_cs4231_open(chip, CS4231_MODE_RECORD); - if (err < 0) { - snd_free_pages(runtime->dma_area, runtime->dma_bytes); + if (err < 0) return err; - } chip->capture_substream = substream; chip->c_periods_sent = 0; snd_pcm_set_sync(substream); diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 849953e5775c..37fc0447c071 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3382,5 +3382,15 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), .ifnum = QUIRK_NO_INTERFACE } }, +/* Dell WD19 Dock */ +{ + USB_DEVICE(0x0bda, 0x402e), + .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) { + .vendor_name = "Dell", + .product_name = "WD19 Dock", + .profile_name = "Dell-WD15-Dock", + .ifnum = QUIRK_NO_INTERFACE + } +}, #undef USB_DEVICE_VENDOR_SPEC diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 89a048c2faec..28c4a502b419 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -331,6 +331,8 @@ #define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */ #define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */ #define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */ +#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */ +#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */ /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */ #define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* MCA overflow recovery support */ diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index edbe81534c6d..d07ccf8a23f7 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -137,4 +137,10 @@ EXAMPLES SEE ALSO ======== - **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8) + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-prog**\ (8), + **bpftool-map**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index f55a2daed59b..7bb787cfa971 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -171,4 +171,10 @@ The following three commands are equivalent: SEE ALSO ======== - **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8) + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-prog**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 408ec30d8872..ed87c9b619ad 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -136,4 +136,10 @@ EXAMPLES SEE ALSO ======== - **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8) + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-prog**\ (8), + **bpftool-map**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst index e3eb0eab7641..f4c5e5538bb8 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst @@ -78,4 +78,10 @@ EXAMPLES SEE ALSO ======== - **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8) + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-prog**\ (8), + **bpftool-map**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-net**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index ac4e904b10fb..ecf618807125 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -124,7 +124,8 @@ OPTIONS Generate human-readable JSON output. Implies **-j**. -f, --bpffs - Show file names of pinned programs. + When showing BPF programs, show file names of pinned + programs. EXAMPLES ======== @@ -206,4 +207,10 @@ EXAMPLES SEE ALSO ======== - **bpftool**\ (8), **bpftool-map**\ (8), **bpftool-cgroup**\ (8) + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool**\ (8), + **bpftool-map**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 04cd4f92ab89..129b7a9c0f9b 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -63,5 +63,10 @@ OPTIONS SEE ALSO ======== - **bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8) - **bpftool-perf**\ (8), **bpftool-net**\ (8) + **bpf**\ (2), + **bpf-helpers**\ (7), + **bpftool-prog**\ (8), + **bpftool-map**\ (8), + **bpftool-cgroup**\ (8), + **bpftool-net**\ (8), + **bpftool-perf**\ (8) diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 25af85304ebe..70fd48d79f61 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -130,16 +130,17 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen) return 0; } -int open_obj_pinned(char *path) +int open_obj_pinned(char *path, bool quiet) { int fd; fd = bpf_obj_get(path); if (fd < 0) { - p_err("bpf obj get (%s): %s", path, - errno == EACCES && !is_bpffs(dirname(path)) ? - "directory not in bpf file system (bpffs)" : - strerror(errno)); + if (!quiet) + p_err("bpf obj get (%s): %s", path, + errno == EACCES && !is_bpffs(dirname(path)) ? + "directory not in bpf file system (bpffs)" : + strerror(errno)); return -1; } @@ -151,7 +152,7 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type) enum bpf_obj_type type; int fd; - fd = open_obj_pinned(path); + fd = open_obj_pinned(path, false); if (fd < 0) return -1; @@ -304,7 +305,7 @@ char *get_fdinfo(int fd, const char *key) return NULL; } - while ((n = getline(&line, &line_n, fdi))) { + while ((n = getline(&line, &line_n, fdi)) > 0) { char *value; int len; @@ -384,7 +385,7 @@ int build_pinned_obj_table(struct pinned_obj_table *tab, while ((ftse = fts_read(fts))) { if (!(ftse->fts_info & FTS_F)) continue; - fd = open_obj_pinned(ftse->fts_path); + fd = open_obj_pinned(ftse->fts_path, true); if (fd < 0) continue; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 28322ace2856..a8bf1e2d9818 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -127,7 +127,7 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv, int get_fd_type(int fd); const char *get_fd_type_name(enum bpf_obj_type type); char *get_fdinfo(int fd, const char *key); -int open_obj_pinned(char *path); +int open_obj_pinned(char *path, bool quiet); int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type); int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)); int do_pin_fd(int fd, const char *name); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 5302ee282409..ccee180dfb76 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -357,10 +357,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) if (!hash_empty(prog_table.table)) { struct pinned_obj *obj; - printf("\n"); hash_for_each_possible(prog_table.table, obj, hash, info->id) { if (obj->id == info->id) - printf("\tpinned %s\n", obj->path); + printf("\n\tpinned %s", obj->path); } } @@ -845,6 +844,7 @@ static int do_load(int argc, char **argv) } NEXT_ARG(); } else if (is_prefix(*argv, "map")) { + void *new_map_replace; char *endptr, *name; int fd; @@ -878,12 +878,15 @@ static int do_load(int argc, char **argv) if (fd < 0) goto err_free_reuse_maps; - map_replace = reallocarray(map_replace, old_map_fds + 1, - sizeof(*map_replace)); - if (!map_replace) { + new_map_replace = reallocarray(map_replace, + old_map_fds + 1, + sizeof(*map_replace)); + if (!new_map_replace) { p_err("mem alloc failed"); goto err_free_reuse_maps; } + map_replace = new_map_replace; + map_replace[old_map_fds].idx = idx; map_replace[old_map_fds].name = name; map_replace[old_map_fds].fd = fd; diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index f216b2f5c3d7..d74bb9414d7c 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -33,6 +33,7 @@ FEATURE_TESTS_BASIC := \ dwarf_getlocations \ fortify-source \ sync-compare-and-swap \ + get_current_dir_name \ glibc \ gtk2 \ gtk2-infobar \ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 0516259be70f..304b984f11b9 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -7,6 +7,7 @@ FILES= \ test-dwarf_getlocations.bin \ test-fortify-source.bin \ test-sync-compare-and-swap.bin \ + test-get_current_dir_name.bin \ test-glibc.bin \ test-gtk2.bin \ test-gtk2-infobar.bin \ @@ -101,6 +102,9 @@ $(OUTPUT)test-bionic.bin: $(OUTPUT)test-libelf.bin: $(BUILD) -lelf +$(OUTPUT)test-get_current_dir_name.bin: + $(BUILD) + $(OUTPUT)test-glibc.bin: $(BUILD) diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c index 8dc20a61341f..56722bfe6bdd 100644 --- a/tools/build/feature/test-all.c +++ b/tools/build/feature/test-all.c @@ -34,6 +34,10 @@ # include "test-libelf-mmap.c" #undef main +#define main main_test_get_current_dir_name +# include "test-get_current_dir_name.c" +#undef main + #define main main_test_glibc # include "test-glibc.c" #undef main @@ -174,6 +178,7 @@ int main(int argc, char *argv[]) main_test_hello(); main_test_libelf(); main_test_libelf_mmap(); + main_test_get_current_dir_name(); main_test_glibc(); main_test_dwarf(); main_test_dwarf_getlocations(); diff --git a/tools/build/feature/test-get_current_dir_name.c b/tools/build/feature/test-get_current_dir_name.c new file mode 100644 index 000000000000..573000f93212 --- /dev/null +++ b/tools/build/feature/test-get_current_dir_name.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE +#include <unistd.h> +#include <stdlib.h> + +int main(void) +{ + free(get_current_dir_name()); + return 0; +} diff --git a/tools/include/uapi/asm-generic/ioctls.h b/tools/include/uapi/asm-generic/ioctls.h index 040651735662..cdc9f4ca8c27 100644 --- a/tools/include/uapi/asm-generic/ioctls.h +++ b/tools/include/uapi/asm-generic/ioctls.h @@ -79,6 +79,8 @@ #define TIOCGPTLCK _IOR('T', 0x39, int) /* Get Pty lock state */ #define TIOCGEXCL _IOR('T', 0x40, int) /* Get exclusive mode state */ #define TIOCGPTPEER _IO('T', 0x41) /* Safely open the slave */ +#define TIOCGISO7816 _IOR('T', 0x42, struct serial_iso7816) +#define TIOCSISO7816 _IOWR('T', 0x43, struct serial_iso7816) #define FIONCLEX 0x5450 #define FIOCLEX 0x5451 diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index 7f5634ce8e88..a4446f452040 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -529,6 +529,28 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51 +/* + * Once upon a time we supposed that writes through the GGTT would be + * immediately in physical memory (once flushed out of the CPU path). However, + * on a few different processors and chipsets, this is not necessarily the case + * as the writes appear to be buffered internally. Thus a read of the backing + * storage (physical memory) via a different path (with different physical tags + * to the indirect write via the GGTT) will see stale values from before + * the GGTT write. Inside the kernel, we can for the most part keep track of + * the different read/write domains in use (e.g. set-domain), but the assumption + * of coherency is baked into the ABI, hence reporting its true state in this + * parameter. + * + * Reports true when writes via mmap_gtt are immediately visible following an + * lfence to flush the WCB. + * + * Reports false when writes via mmap_gtt are indeterminately delayed in an in + * internal buffer and are _not_ immediately visible to third parties accessing + * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC + * communications channel when reporting false is strongly disadvised. + */ +#define I915_PARAM_MMAP_GTT_COHERENT 52 + typedef struct drm_i915_getparam { __s32 param; /* diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h new file mode 100644 index 000000000000..401d0c1e612d --- /dev/null +++ b/tools/include/uapi/linux/pkt_cls.h @@ -0,0 +1,612 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_PKT_CLS_H +#define __LINUX_PKT_CLS_H + +#include <linux/types.h> +#include <linux/pkt_sched.h> + +#define TC_COOKIE_MAX_SIZE 16 + +/* Action attributes */ +enum { + TCA_ACT_UNSPEC, + TCA_ACT_KIND, + TCA_ACT_OPTIONS, + TCA_ACT_INDEX, + TCA_ACT_STATS, + TCA_ACT_PAD, + TCA_ACT_COOKIE, + __TCA_ACT_MAX +}; + +#define TCA_ACT_MAX __TCA_ACT_MAX +#define TCA_OLD_COMPAT (TCA_ACT_MAX+1) +#define TCA_ACT_MAX_PRIO 32 +#define TCA_ACT_BIND 1 +#define TCA_ACT_NOBIND 0 +#define TCA_ACT_UNBIND 1 +#define TCA_ACT_NOUNBIND 0 +#define TCA_ACT_REPLACE 1 +#define TCA_ACT_NOREPLACE 0 + +#define TC_ACT_UNSPEC (-1) +#define TC_ACT_OK 0 +#define TC_ACT_RECLASSIFY 1 +#define TC_ACT_SHOT 2 +#define TC_ACT_PIPE 3 +#define TC_ACT_STOLEN 4 +#define TC_ACT_QUEUED 5 +#define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 +#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu" + * and don't further process the frame + * in hardware. For sw path, this is + * equivalent of TC_ACT_STOLEN - drop + * the skb and act like everything + * is alright. + */ +#define TC_ACT_VALUE_MAX TC_ACT_TRAP + +/* There is a special kind of actions called "extended actions", + * which need a value parameter. These have a local opcode located in + * the highest nibble, starting from 1. The rest of the bits + * are used to carry the value. These two parts together make + * a combined opcode. + */ +#define __TC_ACT_EXT_SHIFT 28 +#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT) +#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1) +#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK)) +#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode) + +#define TC_ACT_JUMP __TC_ACT_EXT(1) +#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) +#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN + +/* Action type identifiers*/ +enum { + TCA_ID_UNSPEC=0, + TCA_ID_POLICE=1, + /* other actions go here */ + __TCA_ID_MAX=255 +}; + +#define TCA_ID_MAX __TCA_ID_MAX + +struct tc_police { + __u32 index; + int action; +#define TC_POLICE_UNSPEC TC_ACT_UNSPEC +#define TC_POLICE_OK TC_ACT_OK +#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY +#define TC_POLICE_SHOT TC_ACT_SHOT +#define TC_POLICE_PIPE TC_ACT_PIPE + + __u32 limit; + __u32 burst; + __u32 mtu; + struct tc_ratespec rate; + struct tc_ratespec peakrate; + int refcnt; + int bindcnt; + __u32 capab; +}; + +struct tcf_t { + __u64 install; + __u64 lastuse; + __u64 expires; + __u64 firstuse; +}; + +struct tc_cnt { + int refcnt; + int bindcnt; +}; + +#define tc_gen \ + __u32 index; \ + __u32 capab; \ + int action; \ + int refcnt; \ + int bindcnt + +enum { + TCA_POLICE_UNSPEC, + TCA_POLICE_TBF, + TCA_POLICE_RATE, + TCA_POLICE_PEAKRATE, + TCA_POLICE_AVRATE, + TCA_POLICE_RESULT, + TCA_POLICE_TM, + TCA_POLICE_PAD, + __TCA_POLICE_MAX +#define TCA_POLICE_RESULT TCA_POLICE_RESULT +}; + +#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1) + +/* tca flags definitions */ +#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */ +#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */ +#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */ +#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */ +#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */ + +/* U32 filters */ + +#define TC_U32_HTID(h) ((h)&0xFFF00000) +#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20) +#define TC_U32_HASH(h) (((h)>>12)&0xFF) +#define TC_U32_NODE(h) ((h)&0xFFF) +#define TC_U32_KEY(h) ((h)&0xFFFFF) +#define TC_U32_UNSPEC 0 +#define TC_U32_ROOT (0xFFF00000) + +enum { + TCA_U32_UNSPEC, + TCA_U32_CLASSID, + TCA_U32_HASH, + TCA_U32_LINK, + TCA_U32_DIVISOR, + TCA_U32_SEL, + TCA_U32_POLICE, + TCA_U32_ACT, + TCA_U32_INDEV, + TCA_U32_PCNT, + TCA_U32_MARK, + TCA_U32_FLAGS, + TCA_U32_PAD, + __TCA_U32_MAX +}; + +#define TCA_U32_MAX (__TCA_U32_MAX - 1) + +struct tc_u32_key { + __be32 mask; + __be32 val; + int off; + int offmask; +}; + +struct tc_u32_sel { + unsigned char flags; + unsigned char offshift; + unsigned char nkeys; + + __be16 offmask; + __u16 off; + short offoff; + + short hoff; + __be32 hmask; + struct tc_u32_key keys[0]; +}; + +struct tc_u32_mark { + __u32 val; + __u32 mask; + __u32 success; +}; + +struct tc_u32_pcnt { + __u64 rcnt; + __u64 rhit; + __u64 kcnts[0]; +}; + +/* Flags */ + +#define TC_U32_TERMINAL 1 +#define TC_U32_OFFSET 2 +#define TC_U32_VAROFFSET 4 +#define TC_U32_EAT 8 + +#define TC_U32_MAXDEPTH 8 + + +/* RSVP filter */ + +enum { + TCA_RSVP_UNSPEC, + TCA_RSVP_CLASSID, + TCA_RSVP_DST, + TCA_RSVP_SRC, + TCA_RSVP_PINFO, + TCA_RSVP_POLICE, + TCA_RSVP_ACT, + __TCA_RSVP_MAX +}; + +#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 ) + +struct tc_rsvp_gpi { + __u32 key; + __u32 mask; + int offset; +}; + +struct tc_rsvp_pinfo { + struct tc_rsvp_gpi dpi; + struct tc_rsvp_gpi spi; + __u8 protocol; + __u8 tunnelid; + __u8 tunnelhdr; + __u8 pad; +}; + +/* ROUTE filter */ + +enum { + TCA_ROUTE4_UNSPEC, + TCA_ROUTE4_CLASSID, + TCA_ROUTE4_TO, + TCA_ROUTE4_FROM, + TCA_ROUTE4_IIF, + TCA_ROUTE4_POLICE, + TCA_ROUTE4_ACT, + __TCA_ROUTE4_MAX +}; + +#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1) + + +/* FW filter */ + +enum { + TCA_FW_UNSPEC, + TCA_FW_CLASSID, + TCA_FW_POLICE, + TCA_FW_INDEV, /* used by CONFIG_NET_CLS_IND */ + TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */ + TCA_FW_MASK, + __TCA_FW_MAX +}; + +#define TCA_FW_MAX (__TCA_FW_MAX - 1) + +/* TC index filter */ + +enum { + TCA_TCINDEX_UNSPEC, + TCA_TCINDEX_HASH, + TCA_TCINDEX_MASK, + TCA_TCINDEX_SHIFT, + TCA_TCINDEX_FALL_THROUGH, + TCA_TCINDEX_CLASSID, + TCA_TCINDEX_POLICE, + TCA_TCINDEX_ACT, + __TCA_TCINDEX_MAX +}; + +#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1) + +/* Flow filter */ + +enum { + FLOW_KEY_SRC, + FLOW_KEY_DST, + FLOW_KEY_PROTO, + FLOW_KEY_PROTO_SRC, + FLOW_KEY_PROTO_DST, + FLOW_KEY_IIF, + FLOW_KEY_PRIORITY, + FLOW_KEY_MARK, + FLOW_KEY_NFCT, + FLOW_KEY_NFCT_SRC, + FLOW_KEY_NFCT_DST, + FLOW_KEY_NFCT_PROTO_SRC, + FLOW_KEY_NFCT_PROTO_DST, + FLOW_KEY_RTCLASSID, + FLOW_KEY_SKUID, + FLOW_KEY_SKGID, + FLOW_KEY_VLAN_TAG, + FLOW_KEY_RXHASH, + __FLOW_KEY_MAX, +}; + +#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1) + +enum { + FLOW_MODE_MAP, + FLOW_MODE_HASH, +}; + +enum { + TCA_FLOW_UNSPEC, + TCA_FLOW_KEYS, + TCA_FLOW_MODE, + TCA_FLOW_BASECLASS, + TCA_FLOW_RSHIFT, + TCA_FLOW_ADDEND, + TCA_FLOW_MASK, + TCA_FLOW_XOR, + TCA_FLOW_DIVISOR, + TCA_FLOW_ACT, + TCA_FLOW_POLICE, + TCA_FLOW_EMATCHES, + TCA_FLOW_PERTURB, + __TCA_FLOW_MAX +}; + +#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1) + +/* Basic filter */ + +enum { + TCA_BASIC_UNSPEC, + TCA_BASIC_CLASSID, + TCA_BASIC_EMATCHES, + TCA_BASIC_ACT, + TCA_BASIC_POLICE, + __TCA_BASIC_MAX +}; + +#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1) + + +/* Cgroup classifier */ + +enum { + TCA_CGROUP_UNSPEC, + TCA_CGROUP_ACT, + TCA_CGROUP_POLICE, + TCA_CGROUP_EMATCHES, + __TCA_CGROUP_MAX, +}; + +#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1) + +/* BPF classifier */ + +#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0) + +enum { + TCA_BPF_UNSPEC, + TCA_BPF_ACT, + TCA_BPF_POLICE, + TCA_BPF_CLASSID, + TCA_BPF_OPS_LEN, + TCA_BPF_OPS, + TCA_BPF_FD, + TCA_BPF_NAME, + TCA_BPF_FLAGS, + TCA_BPF_FLAGS_GEN, + TCA_BPF_TAG, + TCA_BPF_ID, + __TCA_BPF_MAX, +}; + +#define TCA_BPF_MAX (__TCA_BPF_MAX - 1) + +/* Flower classifier */ + +enum { + TCA_FLOWER_UNSPEC, + TCA_FLOWER_CLASSID, + TCA_FLOWER_INDEV, + TCA_FLOWER_ACT, + TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_TYPE, /* be16 */ + TCA_FLOWER_KEY_IP_PROTO, /* u8 */ + TCA_FLOWER_KEY_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_TCP_SRC, /* be16 */ + TCA_FLOWER_KEY_TCP_DST, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC, /* be16 */ + TCA_FLOWER_KEY_UDP_DST, /* be16 */ + + TCA_FLOWER_FLAGS, + TCA_FLOWER_KEY_VLAN_ID, /* be16 */ + TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */ + + TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */ + + TCA_FLOWER_KEY_SCTP_SRC, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST, /* be16 */ + + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */ + + TCA_FLOWER_KEY_FLAGS, /* be32 */ + TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */ + + TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */ + + TCA_FLOWER_KEY_ARP_SIP, /* be32 */ + TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_OP, /* u8 */ + TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */ + TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */ + + TCA_FLOWER_KEY_MPLS_TTL, /* u8 - 8 bits */ + TCA_FLOWER_KEY_MPLS_BOS, /* u8 - 1 bit */ + TCA_FLOWER_KEY_MPLS_TC, /* u8 - 3 bits */ + TCA_FLOWER_KEY_MPLS_LABEL, /* be32 - 20 bits */ + + TCA_FLOWER_KEY_TCP_FLAGS, /* be16 */ + TCA_FLOWER_KEY_TCP_FLAGS_MASK, /* be16 */ + + TCA_FLOWER_KEY_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_CVLAN_ID, /* be16 */ + TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_ENC_OPTS, + TCA_FLOWER_KEY_ENC_OPTS_MASK, + + TCA_FLOWER_IN_HW_COUNT, + + __TCA_FLOWER_MAX, +}; + +#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPTS_UNSPEC, + TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested + * TCA_FLOWER_KEY_ENC_OPT_GENEVE_ + * attributes + */ + __TCA_FLOWER_KEY_ENC_OPTS_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */ + + __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1) + +enum { + TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), +}; + +/* Match-all classifier */ + +enum { + TCA_MATCHALL_UNSPEC, + TCA_MATCHALL_CLASSID, + TCA_MATCHALL_ACT, + TCA_MATCHALL_FLAGS, + __TCA_MATCHALL_MAX, +}; + +#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1) + +/* Extended Matches */ + +struct tcf_ematch_tree_hdr { + __u16 nmatches; + __u16 progid; +}; + +enum { + TCA_EMATCH_TREE_UNSPEC, + TCA_EMATCH_TREE_HDR, + TCA_EMATCH_TREE_LIST, + __TCA_EMATCH_TREE_MAX +}; +#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1) + +struct tcf_ematch_hdr { + __u16 matchid; + __u16 kind; + __u16 flags; + __u16 pad; /* currently unused */ +}; + +/* 0 1 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 + * +-----------------------+-+-+---+ + * | Unused |S|I| R | + * +-----------------------+-+-+---+ + * + * R(2) ::= relation to next ematch + * where: 0 0 END (last ematch) + * 0 1 AND + * 1 0 OR + * 1 1 Unused (invalid) + * I(1) ::= invert result + * S(1) ::= simple payload + */ +#define TCF_EM_REL_END 0 +#define TCF_EM_REL_AND (1<<0) +#define TCF_EM_REL_OR (1<<1) +#define TCF_EM_INVERT (1<<2) +#define TCF_EM_SIMPLE (1<<3) + +#define TCF_EM_REL_MASK 3 +#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK) + +enum { + TCF_LAYER_LINK, + TCF_LAYER_NETWORK, + TCF_LAYER_TRANSPORT, + __TCF_LAYER_MAX +}; +#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1) + +/* Ematch type assignments + * 1..32767 Reserved for ematches inside kernel tree + * 32768..65535 Free to use, not reliable + */ +#define TCF_EM_CONTAINER 0 +#define TCF_EM_CMP 1 +#define TCF_EM_NBYTE 2 +#define TCF_EM_U32 3 +#define TCF_EM_META 4 +#define TCF_EM_TEXT 5 +#define TCF_EM_VLAN 6 +#define TCF_EM_CANID 7 +#define TCF_EM_IPSET 8 +#define TCF_EM_IPT 9 +#define TCF_EM_MAX 9 + +enum { + TCF_EM_PROG_TC +}; + +enum { + TCF_EM_OPND_EQ, + TCF_EM_OPND_GT, + TCF_EM_OPND_LT +}; + +#endif diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index c0d7ea0bf5b6..b17201edfa09 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -212,6 +212,7 @@ struct prctl_mm_map { #define PR_SET_SPECULATION_CTRL 53 /* Speculation control variants */ # define PR_SPEC_STORE_BYPASS 0 +# define PR_SPEC_INDIRECT_BRANCH 1 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */ # define PR_SPEC_NOT_AFFECTED 0 # define PR_SPEC_PRCTL (1UL << 0) diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h new file mode 100644 index 000000000000..6e89a5df49a4 --- /dev/null +++ b/tools/include/uapi/linux/tc_act/tc_bpf.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_TC_BPF_H +#define __LINUX_TC_BPF_H + +#include <linux/pkt_cls.h> + +#define TCA_ACT_BPF 13 + +struct tc_act_bpf { + tc_gen; +}; + +enum { + TCA_ACT_BPF_UNSPEC, + TCA_ACT_BPF_TM, + TCA_ACT_BPF_PARMS, + TCA_ACT_BPF_OPS_LEN, + TCA_ACT_BPF_OPS, + TCA_ACT_BPF_FD, + TCA_ACT_BPF_NAME, + TCA_ACT_BPF_PAD, + TCA_ACT_BPF_TAG, + TCA_ACT_BPF_ID, + __TCA_ACT_BPF_MAX, +}; +#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) + +#endif diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index 6dbb9fae0f9d..b8f3cca8e58b 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -31,6 +31,8 @@ #include "elf.h" #include "warn.h" +#define MAX_NAME_LEN 128 + struct section *find_section_by_name(struct elf *elf, const char *name) { struct section *sec; @@ -298,6 +300,8 @@ static int read_symbols(struct elf *elf) /* Create parent/child links for any cold subfunctions */ list_for_each_entry(sec, &elf->sections, list) { list_for_each_entry(sym, &sec->symbol_list, list) { + char pname[MAX_NAME_LEN + 1]; + size_t pnamelen; if (sym->type != STT_FUNC) continue; sym->pfunc = sym->cfunc = sym; @@ -305,14 +309,21 @@ static int read_symbols(struct elf *elf) if (!coldstr) continue; - coldstr[0] = '\0'; - pfunc = find_symbol_by_name(elf, sym->name); - coldstr[0] = '.'; + pnamelen = coldstr - sym->name; + if (pnamelen > MAX_NAME_LEN) { + WARN("%s(): parent function name exceeds maximum length of %d characters", + sym->name, MAX_NAME_LEN); + return -1; + } + + strncpy(pname, sym->name, pnamelen); + pname[pnamelen] = '\0'; + pfunc = find_symbol_by_name(elf, pname); if (!pfunc) { WARN("%s(): can't find parent function", sym->name); - goto err; + return -1; } sym->pfunc = pfunc; diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index e30d20fb482d..a0e8c23f9125 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -299,6 +299,11 @@ ifndef NO_BIONIC endif endif +ifeq ($(feature-get_current_dir_name), 1) + CFLAGS += -DHAVE_GET_CURRENT_DIR_NAME +endif + + ifdef NO_LIBELF NO_DWARF := 1 NO_DEMANGLE := 1 diff --git a/tools/perf/tests/attr/base-record b/tools/perf/tests/attr/base-record index 37940665f736..efd0157b9d22 100644 --- a/tools/perf/tests/attr/base-record +++ b/tools/perf/tests/attr/base-record @@ -9,7 +9,7 @@ size=112 config=0 sample_period=* sample_type=263 -read_format=0 +read_format=0|4 disabled=1 inherit=1 pinned=0 diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c index 5d2a7fd8d407..eae59ad15ce3 100644 --- a/tools/perf/trace/beauty/ioctl.c +++ b/tools/perf/trace/beauty/ioctl.c @@ -31,6 +31,7 @@ static size_t ioctl__scnprintf_tty_cmd(int nr, int dir, char *bf, size_t size) "TCSETSW2", "TCSETSF2", "TIOCGRS48", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK", "TIOCGDEV", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG", "TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", [_IOC_NR(TIOCGEXCL)] = "TIOCGEXCL", "TIOCGPTPEER", + "TIOCGISO7816", "TIOCSISO7816", [_IOC_NR(FIONCLEX)] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG", "TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS", "TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI", diff --git a/tools/perf/util/Build b/tools/perf/util/Build index ecd9f9ceda77..b7bf201fe8a8 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -10,6 +10,7 @@ libperf-y += evlist.o libperf-y += evsel.o libperf-y += evsel_fprintf.o libperf-y += find_bit.o +libperf-y += get_current_dir_name.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d37bb1566cd9..dbc0466db368 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1092,7 +1092,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->exclude_user = 1; } - if (evsel->own_cpus) + if (evsel->own_cpus || evsel->unit) evsel->attr.read_format |= PERF_FORMAT_ID; /* diff --git a/tools/perf/util/get_current_dir_name.c b/tools/perf/util/get_current_dir_name.c new file mode 100644 index 000000000000..267aa609a582 --- /dev/null +++ b/tools/perf/util/get_current_dir_name.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> +// +#ifndef HAVE_GET_CURRENT_DIR_NAME +#include "util.h" +#include <unistd.h> +#include <stdlib.h> +#include <stdlib.h> + +/* Android's 'bionic' library, for one, doesn't have this */ + +char *get_current_dir_name(void) +{ + char pwd[PATH_MAX]; + + return getcwd(pwd, sizeof(pwd)) == NULL ? NULL : strdup(pwd); +} +#endif // HAVE_GET_CURRENT_DIR_NAME diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c index cf8bd123cf73..aed170bd4384 100644 --- a/tools/perf/util/namespaces.c +++ b/tools/perf/util/namespaces.c @@ -18,6 +18,7 @@ #include <stdio.h> #include <string.h> #include <unistd.h> +#include <asm/bug.h> struct namespaces *namespaces__new(struct namespaces_event *event) { @@ -186,6 +187,7 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, char curpath[PATH_MAX]; int oldns = -1; int newns = -1; + char *oldcwd = NULL; if (nc == NULL) return; @@ -199,9 +201,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, if (snprintf(curpath, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX) return; + oldcwd = get_current_dir_name(); + if (!oldcwd) + return; + oldns = open(curpath, O_RDONLY); if (oldns < 0) - return; + goto errout; newns = open(nsi->mntns_path, O_RDONLY); if (newns < 0) @@ -210,11 +216,13 @@ void nsinfo__mountns_enter(struct nsinfo *nsi, if (setns(newns, CLONE_NEWNS) < 0) goto errout; + nc->oldcwd = oldcwd; nc->oldns = oldns; nc->newns = newns; return; errout: + free(oldcwd); if (oldns > -1) close(oldns); if (newns > -1) @@ -223,11 +231,16 @@ errout: void nsinfo__mountns_exit(struct nscookie *nc) { - if (nc == NULL || nc->oldns == -1 || nc->newns == -1) + if (nc == NULL || nc->oldns == -1 || nc->newns == -1 || !nc->oldcwd) return; setns(nc->oldns, CLONE_NEWNS); + if (nc->oldcwd) { + WARN_ON_ONCE(chdir(nc->oldcwd)); + zfree(&nc->oldcwd); + } + if (nc->oldns > -1) { close(nc->oldns); nc->oldns = -1; diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h index cae1a9a39722..d5f46c09ea31 100644 --- a/tools/perf/util/namespaces.h +++ b/tools/perf/util/namespaces.h @@ -38,6 +38,7 @@ struct nsinfo { struct nscookie { int oldns; int newns; + char *oldcwd; }; int nsinfo__init(struct nsinfo *nsi); diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 14508ee7707a..ece040b799f6 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -59,6 +59,10 @@ int fetch_kernel_version(unsigned int *puint, const char *perf_tip(const char *dirpath); +#ifndef HAVE_GET_CURRENT_DIR_NAME +char *get_current_dir_name(void); +#endif + #ifndef HAVE_SCHED_GETCPU_SUPPORT int sched_getcpu(void); #endif diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index f1fe492c8e17..f0017c831e57 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -24,6 +24,7 @@ TARGETS += memory-hotplug TARGETS += mount TARGETS += mqueue TARGETS += net +TARGETS += netfilter TARGETS += nsfs TARGETS += powerpc TARGETS += proc diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c index 7887df693399..44ed7f29f8ab 100644 --- a/tools/testing/selftests/bpf/test_netcnt.c +++ b/tools/testing/selftests/bpf/test_netcnt.c @@ -81,7 +81,10 @@ int main(int argc, char **argv) goto err; } - assert(system("ping localhost -6 -c 10000 -f -q > /dev/null") == 0); + if (system("which ping6 &>/dev/null") == 0) + assert(!system("ping6 localhost -c 10000 -f -q > /dev/null")); + else + assert(!system("ping -6 localhost -c 10000 -f -q > /dev/null")); if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL, &prog_cnt)) { diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 6f61df62f690..550b7e46bf4a 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -13896,6 +13896,25 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = ACCEPT, }, + { + "calls: ctx read at start of subprog", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5), + BPF_JMP_REG(BPF_JSGT, BPF_REG_0, BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SOCKET_FILTER, + .errstr_unpriv = "function calls to other bpf functions are allowed for root only", + .result_unpriv = REJECT, + .result = ACCEPT, + }, }; static int probe_filter_length(const struct bpf_insn *fp) diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile new file mode 100644 index 000000000000..47ed6cef93fb --- /dev/null +++ b/tools/testing/selftests/netfilter/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for netfilter selftests + +TEST_PROGS := nft_trans_stress.sh + +include ../lib.mk diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config new file mode 100644 index 000000000000..1017313e41a8 --- /dev/null +++ b/tools/testing/selftests/netfilter/config @@ -0,0 +1,2 @@ +CONFIG_NET_NS=y +NF_TABLES_INET=y diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh new file mode 100755 index 000000000000..f1affd12c4b1 --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh @@ -0,0 +1,78 @@ +#!/bin/bash +# +# This test is for stress-testing the nf_tables config plane path vs. +# packet path processing: Make sure we never release rules that are +# still visible to other cpus. +# +# set -e + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +testns=testns1 +tables="foo bar baz quux" + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +tmp=$(mktemp) + +for table in $tables; do + echo add table inet "$table" >> "$tmp" + echo flush table inet "$table" >> "$tmp" + + echo "add chain inet $table INPUT { type filter hook input priority 0; }" >> "$tmp" + echo "add chain inet $table OUTPUT { type filter hook output priority 0; }" >> "$tmp" + for c in $(seq 1 400); do + chain=$(printf "chain%03u" "$c") + echo "add chain inet $table $chain" >> "$tmp" + done + + for c in $(seq 1 400); do + chain=$(printf "chain%03u" "$c") + for BASE in INPUT OUTPUT; do + echo "add rule inet $table $BASE counter jump $chain" >> "$tmp" + done + echo "add rule inet $table $chain counter return" >> "$tmp" + done +done + +ip netns add "$testns" +ip -netns "$testns" link set lo up + +lscpu | grep ^CPU\(s\): | ( read cpu cpunum ; +cpunum=$((cpunum-1)) +for i in $(seq 0 $cpunum);do + mask=$(printf 0x%x $((1<<$i))) + ip netns exec "$testns" taskset $mask ping -4 127.0.0.1 -fq > /dev/null & + ip netns exec "$testns" taskset $mask ping -6 ::1 -fq > /dev/null & +done) + +sleep 1 + +for i in $(seq 1 10) ; do ip netns exec "$testns" nft -f "$tmp" & done + +for table in $tables;do + randsleep=$((RANDOM%10)) + sleep $randsleep + ip netns exec "$testns" nft delete table inet $table 2>/dev/null +done + +randsleep=$((RANDOM%10)) +sleep $randsleep + +pkill -9 ping + +wait + +rm -f "$tmp" +ip netns del "$testns" diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c index 6f1f4a6e1ecb..85744425b08d 100644 --- a/tools/testing/selftests/proc/proc-self-map-files-002.c +++ b/tools/testing/selftests/proc/proc-self-map-files-002.c @@ -13,7 +13,7 @@ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -/* Test readlink /proc/self/map_files/... with address 0. */ +/* Test readlink /proc/self/map_files/... with minimum address. */ #include <errno.h> #include <sys/types.h> #include <sys/stat.h> @@ -47,6 +47,11 @@ static void fail(const char *fmt, unsigned long a, unsigned long b) int main(void) { const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE); +#ifdef __arm__ + unsigned long va = 2 * PAGE_SIZE; +#else + unsigned long va = 0; +#endif void *p; int fd; unsigned long a, b; @@ -55,7 +60,7 @@ int main(void) if (fd == -1) return 1; - p = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); + p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0); if (p == MAP_FAILED) { if (errno == EPERM) return 2; |