diff options
439 files changed, 5614 insertions, 2401 deletions
diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl index 640f65e79ef1..8e69345c37cc 100644 --- a/Documentation/ABI/testing/sysfs-class-cxl +++ b/Documentation/ABI/testing/sysfs-class-cxl @@ -244,3 +244,11 @@ Description: read only Returns 1 if the psl timebase register is synchronized with the core timebase register, 0 otherwise. Users: https://github.com/ibm-capi/libcxl + +What: /sys/class/cxl/<card>/tunneled_ops_supported +Date: May 2018 +Contact: linuxppc-dev@lists.ozlabs.org +Description: read only + Returns 1 if tunneled operations are supported in capi mode, + 0 otherwise. +Users: https://github.com/ibm-capi/libcxl diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst index d2b6fda3d67b..ab2fe0eda1d7 100644 --- a/Documentation/admin-guide/pm/intel_pstate.rst +++ b/Documentation/admin-guide/pm/intel_pstate.rst @@ -145,7 +145,7 @@ feature enabled.] In this mode ``intel_pstate`` registers utilization update callbacks with the CPU scheduler in order to run a P-state selection algorithm, either -``powersave`` or ``performance``, depending on the ``scaling_cur_freq`` policy +``powersave`` or ``performance``, depending on the ``scaling_governor`` policy setting in ``sysfs``. The current CPU frequency information to be made available from the ``scaling_cur_freq`` policy attribute in ``sysfs`` is periodically updated by those utilization update callbacks too. diff --git a/Documentation/admin-guide/pm/sleep-states.rst b/Documentation/admin-guide/pm/sleep-states.rst index 1e5c0f00cb2f..dbf5acd49f35 100644 --- a/Documentation/admin-guide/pm/sleep-states.rst +++ b/Documentation/admin-guide/pm/sleep-states.rst @@ -15,7 +15,7 @@ Sleep States That Can Be Supported ================================== Depending on its configuration and the capabilities of the platform it runs on, -the Linux kernel can support up to four system sleep states, includig +the Linux kernel can support up to four system sleep states, including hibernation and up to three variants of system suspend. The sleep states that can be supported by the kernel are listed below. diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt index 4bcd4b7f79f9..3d01948ea061 100644 --- a/Documentation/device-mapper/thin-provisioning.txt +++ b/Documentation/device-mapper/thin-provisioning.txt @@ -264,7 +264,10 @@ i) Constructor data device, but just remove the mapping. read_only: Don't allow any changes to be made to the pool - metadata. + metadata. This mode is only available after the + thin-pool has been created and first used in full + read/write mode. It cannot be specified on initial + thin-pool creation. error_if_no_space: Error IOs, instead of queueing, if no space. diff --git a/Documentation/devicetree/bindings/ata/ahci-platform.txt b/Documentation/devicetree/bindings/ata/ahci-platform.txt index f4006d3c9fdf..c760ecb81381 100644 --- a/Documentation/devicetree/bindings/ata/ahci-platform.txt +++ b/Documentation/devicetree/bindings/ata/ahci-platform.txt @@ -30,7 +30,6 @@ compatible: Optional properties: - dma-coherent : Present if dma operations are coherent - clocks : a list of phandle + clock specifier pairs -- resets : a list of phandle + reset specifier pairs - target-supply : regulator for SATA target power - phys : reference to the SATA PHY node - phy-names : must be "sata-phy" diff --git a/Documentation/devicetree/bindings/display/panel/panel-common.txt b/Documentation/devicetree/bindings/display/panel/panel-common.txt index 557fa765adcb..5d2519af4bb5 100644 --- a/Documentation/devicetree/bindings/display/panel/panel-common.txt +++ b/Documentation/devicetree/bindings/display/panel/panel-common.txt @@ -38,7 +38,7 @@ Display Timings require specific display timings. The panel-timing subnode expresses those timings as specified in the timing subnode section of the display timing bindings defined in - Documentation/devicetree/bindings/display/display-timing.txt. + Documentation/devicetree/bindings/display/panel/display-timing.txt. Connectivity diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt index aadfb236d53a..61315eaa7660 100644 --- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt +++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt @@ -26,6 +26,7 @@ Required Properties: - "renesas,dmac-r8a7794" (R-Car E2) - "renesas,dmac-r8a7795" (R-Car H3) - "renesas,dmac-r8a7796" (R-Car M3-W) + - "renesas,dmac-r8a77965" (R-Car M3-N) - "renesas,dmac-r8a77970" (R-Car V3M) - "renesas,dmac-r8a77980" (R-Car V3H) diff --git a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt index 93c3a6ae32f9..ac71daa46195 100644 --- a/Documentation/devicetree/bindings/net/can/rcar_canfd.txt +++ b/Documentation/devicetree/bindings/net/can/rcar_canfd.txt @@ -5,7 +5,9 @@ Required properties: - compatible: Must contain one or more of the following: - "renesas,rcar-gen3-canfd" for R-Car Gen3 compatible controller. - "renesas,r8a7795-canfd" for R8A7795 (R-Car H3) compatible controller. - - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3) compatible controller. + - "renesas,r8a7796-canfd" for R8A7796 (R-Car M3-W) compatible controller. + - "renesas,r8a77970-canfd" for R8A77970 (R-Car V3M) compatible controller. + - "renesas,r8a77980-canfd" for R8A77980 (R-Car V3H) compatible controller. When compatible with the generic version, nodes must list the SoC-specific version corresponding to the platform first, followed by the diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index c306f55d335b..890526dbfc26 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -18,6 +18,7 @@ Required properties: - "renesas,etheravb-r8a7795" for the R8A7795 SoC. - "renesas,etheravb-r8a7796" for the R8A7796 SoC. + - "renesas,etheravb-r8a77965" for the R8A77965 SoC. - "renesas,etheravb-r8a77970" for the R8A77970 SoC. - "renesas,etheravb-r8a77980" for the R8A77980 SoC. - "renesas,etheravb-r8a77995" for the R8A77995 SoC. diff --git a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt index ed5eb547afc8..64bc5c2a76da 100644 --- a/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt +++ b/Documentation/devicetree/bindings/pinctrl/allwinner,sunxi-pinctrl.txt @@ -56,9 +56,9 @@ pins it needs, and how they should be configured, with regard to muxer configuration, drive strength and pullups. If one of these options is not set, its actual value will be unspecified. -This driver supports the generic pin multiplexing and configuration -bindings. For details on each properties, you can refer to -./pinctrl-bindings.txt. +Allwinner A1X Pin Controller supports the generic pin multiplexing and +configuration bindings. For details on each properties, you can refer to + ./pinctrl-bindings.txt. Required sub-node properties: - pins diff --git a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt index a006ea4d065f..106808b55b6d 100644 --- a/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt +++ b/Documentation/devicetree/bindings/serial/renesas,sci-serial.txt @@ -43,6 +43,8 @@ Required properties: - "renesas,hscif-r8a7795" for R8A7795 (R-Car H3) HSCIF compatible UART. - "renesas,scif-r8a7796" for R8A7796 (R-Car M3-W) SCIF compatible UART. - "renesas,hscif-r8a7796" for R8A7796 (R-Car M3-W) HSCIF compatible UART. + - "renesas,scif-r8a77965" for R8A77965 (R-Car M3-N) SCIF compatible UART. + - "renesas,hscif-r8a77965" for R8A77965 (R-Car M3-N) HSCIF compatible UART. - "renesas,scif-r8a77970" for R8A77970 (R-Car V3M) SCIF compatible UART. - "renesas,hscif-r8a77970" for R8A77970 (R-Car V3M) HSCIF compatible UART. - "renesas,scif-r8a77980" for R8A77980 (R-Car V3H) SCIF compatible UART. diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt index b5f978a4cac6..a38d8bfae19c 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.txt +++ b/Documentation/devicetree/bindings/vendor-prefixes.txt @@ -182,6 +182,7 @@ karo Ka-Ro electronics GmbH keithkoep Keith & Koep GmbH keymile Keymile GmbH khadas Khadas +kiebackpeter Kieback & Peter GmbH kinetic Kinetic Technologies kingnovel Kingnovel Technology Co., Ltd. kosagi Sutajio Ko-Usagi PTE Ltd. diff --git a/Documentation/devicetree/overlay-notes.txt b/Documentation/devicetree/overlay-notes.txt index a4feb6dde8cd..725fb8d255c1 100644 --- a/Documentation/devicetree/overlay-notes.txt +++ b/Documentation/devicetree/overlay-notes.txt @@ -98,6 +98,14 @@ Finally, if you need to remove all overlays in one-go, just call of_overlay_remove_all() which will remove every single one in the correct order. +In addition, there is the option to register notifiers that get called on +overlay operations. See of_overlay_notifier_register/unregister and +enum of_overlay_notify_action for details. + +Note that a notifier callback is not supposed to store pointers to a device +tree node or its content beyond OF_OVERLAY_POST_REMOVE corresponding to the +respective node it received. + Overlay DTS Format ------------------ diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 758bf403a169..495b7742ab58 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1269,12 +1269,18 @@ struct kvm_cpuid_entry2 { __u32 padding[3]; }; -This ioctl returns x86 cpuid features which are supported by both the hardware -and kvm. Userspace can use the information returned by this ioctl to -construct cpuid information (for KVM_SET_CPUID2) that is consistent with -hardware, kernel, and userspace capabilities, and with user requirements (for -example, the user may wish to constrain cpuid to emulate older hardware, -or for feature consistency across a cluster). +This ioctl returns x86 cpuid features which are supported by both the +hardware and kvm in its default configuration. Userspace can use the +information returned by this ioctl to construct cpuid information (for +KVM_SET_CPUID2) that is consistent with hardware, kernel, and +userspace capabilities, and with user requirements (for example, the +user may wish to constrain cpuid to emulate older hardware, or for +feature consistency across a cluster). + +Note that certain capabilities, such as KVM_CAP_X86_DISABLE_EXITS, may +expose cpuid features (e.g. MONITOR) which are not supported by kvm in +its default configuration. If userspace enables such capabilities, it +is responsible for modifying the results of this ioctl appropriately. Userspace invokes KVM_GET_SUPPORTED_CPUID by passing a kvm_cpuid2 structure with the 'nent' field indicating the number of entries in the variable-size @@ -4603,3 +4609,12 @@ Architectures: s390 This capability indicates that kvm will implement the interfaces to handle reset, migration and nested KVM for branch prediction blocking. The stfle facility 82 should not be provided to the guest without this capability. + +8.14 KVM_CAP_HYPERV_TLBFLUSH + +Architectures: x86 + +This capability indicates that KVM supports paravirtualized Hyper-V TLB Flush +hypercalls: +HvFlushVirtualAddressSpace, HvFlushVirtualAddressSpaceEx, +HvFlushVirtualAddressList, HvFlushVirtualAddressListEx. diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt index d4f33eb805dd..ab022dcd0911 100644 --- a/Documentation/virtual/kvm/cpuid.txt +++ b/Documentation/virtual/kvm/cpuid.txt @@ -72,8 +72,8 @@ KVM_FEATURE_CLOCKSOURCE_STABLE_BIT || 24 || host will warn if no guest-side flag || value || meaning ================================================================================== -KVM_HINTS_DEDICATED || 0 || guest checks this feature bit to - || || determine if there is vCPU pinning - || || and there is no vCPU over-commitment, +KVM_HINTS_REALTIME || 0 || guest checks this feature bit to + || || determine that vCPUs are never + || || preempted for an unlimited time, || || allowing optimizations ---------------------------------------------------------------------------------- diff --git a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt b/Documentation/virtual/kvm/devices/arm-vgic-v3.txt index 9293b45abdb9..2408ab720ef7 100644 --- a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt +++ b/Documentation/virtual/kvm/devices/arm-vgic-v3.txt @@ -27,16 +27,42 @@ Groups: VCPU and all of the redistributor pages are contiguous. Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. This address needs to be 64K aligned. + + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION (rw, 64-bit) + The attribute data pointed to by kvm_device_attr.addr is a __u64 value: + bits: | 63 .... 52 | 51 .... 16 | 15 - 12 |11 - 0 + values: | count | base | flags | index + - index encodes the unique redistributor region index + - flags: reserved for future use, currently 0 + - base field encodes bits [51:16] of the guest physical base address + of the first redistributor in the region. + - count encodes the number of redistributors in the region. Must be + greater than 0. + There are two 64K pages for each redistributor in the region and + redistributors are laid out contiguously within the region. Regions + are filled with redistributors in the index order. The sum of all + region count fields must be greater than or equal to the number of + VCPUs. Redistributor regions must be registered in the incremental + index order, starting from index 0. + The characteristics of a specific redistributor region can be read + by presetting the index field in the attr data. + Only valid for KVM_DEV_TYPE_ARM_VGIC_V3. + + It is invalid to mix calls with KVM_VGIC_V3_ADDR_TYPE_REDIST and + KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION attributes. + Errors: -E2BIG: Address outside of addressable IPA range - -EINVAL: Incorrectly aligned address + -EINVAL: Incorrectly aligned address, bad redistributor region + count/index, mixed redistributor region attribute usage -EEXIST: Address already configured + -ENOENT: Attempt to read the characteristics of a non existing + redistributor region -ENXIO: The group or attribute is unknown/unsupported for this device or hardware support is missing. -EFAULT: Invalid user pointer for attr->addr. - KVM_DEV_ARM_VGIC_GRP_DIST_REGS KVM_DEV_ARM_VGIC_GRP_REDIST_REGS Attributes: diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt index f50d45b1e967..4a81bcc96bd6 100644 --- a/Documentation/virtual/kvm/mmu.txt +++ b/Documentation/virtual/kvm/mmu.txt @@ -465,5 +465,5 @@ Further reading =============== - NPT presentation from KVM Forum 2008 - http://www.linux-kvm.org/wiki/images/c/c8/KvmForum2008%24kdf2008_21.pdf + http://www.linux-kvm.org/images/c/c8/KvmForum2008%24kdf2008_21.pdf diff --git a/MAINTAINERS b/MAINTAINERS index df6e9bb2559a..d155d1e0dbc2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -137,9 +137,9 @@ Maintainers List (try to look for most precise areas first) ----------------------------------- 3C59X NETWORK DRIVER -M: Steffen Klassert <klassert@mathematik.tu-chemnitz.de> +M: Steffen Klassert <klassert@kernel.org> L: netdev@vger.kernel.org -S: Maintained +S: Odd Fixes F: Documentation/networking/vortex.txt F: drivers/net/ethernet/3com/3c59x.c @@ -3691,7 +3691,6 @@ F: drivers/cpufreq/arm_big_little_dt.c CPU POWER MONITORING SUBSYSTEM M: Thomas Renninger <trenn@suse.com> -M: Shuah Khan <shuahkh@osg.samsung.com> M: Shuah Khan <shuah@kernel.org> L: linux-pm@vger.kernel.org S: Maintained @@ -7696,10 +7695,10 @@ F: include/linux/sunrpc/ F: include/uapi/linux/sunrpc/ KERNEL SELFTEST FRAMEWORK -M: Shuah Khan <shuahkh@osg.samsung.com> M: Shuah Khan <shuah@kernel.org> L: linux-kselftest@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git +Q: https://patchwork.kernel.org/project/linux-kselftest/list/ S: Maintained F: tools/testing/selftests/ F: Documentation/dev-tools/kselftest* @@ -9873,7 +9872,7 @@ F: include/linux/platform_data/nxp-nci.h F: Documentation/devicetree/bindings/net/nfc/ NFS, SUNRPC, AND LOCKD CLIENTS -M: Trond Myklebust <trond.myklebust@primarydata.com> +M: Trond Myklebust <trond.myklebust@hammerspace.com> M: Anna Schumaker <anna.schumaker@netapp.com> L: linux-nfs@vger.kernel.org W: http://client.linux-nfs.org @@ -12222,7 +12221,7 @@ F: Documentation/s390/vfio-ccw.txt F: include/uapi/linux/vfio_ccw.h S390 ZCRYPT DRIVER -M: Harald Freudenberger <freude@de.ibm.com> +M: Harald Freudenberger <freude@linux.ibm.com> L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ S: Supported @@ -13266,6 +13265,12 @@ M: Jan-Benedict Glaw <jbglaw@lug-owl.de> S: Maintained F: arch/alpha/kernel/srm_env.c +ST STM32 I2C/SMBUS DRIVER +M: Pierre-Yves MORDRET <pierre-yves.mordret@st.com> +L: linux-i2c@vger.kernel.org +S: Maintained +F: drivers/i2c/busses/i2c-stm32* + STABLE BRANCH M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> L: stable@vger.kernel.org @@ -14650,7 +14655,6 @@ F: drivers/usb/common/usb-otg-fsm.c USB OVER IP DRIVER M: Valentina Manea <valentina.manea.m@gmail.com> -M: Shuah Khan <shuahkh@osg.samsung.com> M: Shuah Khan <shuah@kernel.org> L: linux-usb@vger.kernel.org S: Maintained @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Merciless Moray # *DOCUMENTATION* diff --git a/arch/Kconfig b/arch/Kconfig index 8e0d665c8d53..75dd23acf133 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -464,6 +464,10 @@ config GCC_PLUGIN_LATENT_ENTROPY config GCC_PLUGIN_STRUCTLEAK bool "Force initialization of variables containing userspace addresses" depends on GCC_PLUGINS + # Currently STRUCTLEAK inserts initialization out of live scope of + # variables from KASAN point of view. This leads to KASAN false + # positive reports. Prohibit this combination for now. + depends on !KASAN_EXTRA help This plugin zero-initializes any structures containing a __user attribute. This can prevent some classes of information diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi index bf343195697e..54111ed218b1 100644 --- a/arch/arm/boot/dts/imx35.dtsi +++ b/arch/arm/boot/dts/imx35.dtsi @@ -303,7 +303,7 @@ }; can1: can@53fe4000 { - compatible = "fsl,imx35-flexcan"; + compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan"; reg = <0x53fe4000 0x1000>; clocks = <&clks 33>, <&clks 33>; clock-names = "ipg", "per"; @@ -312,7 +312,7 @@ }; can2: can@53fe8000 { - compatible = "fsl,imx35-flexcan"; + compatible = "fsl,imx35-flexcan", "fsl,imx25-flexcan"; reg = <0x53fe8000 0x1000>; clocks = <&clks 34>, <&clks 34>; clock-names = "ipg", "per"; diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi index 7d647d043f52..3d65c0192f69 100644 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@ -551,7 +551,7 @@ }; can1: can@53fc8000 { - compatible = "fsl,imx53-flexcan"; + compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan"; reg = <0x53fc8000 0x4000>; interrupts = <82>; clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, @@ -561,7 +561,7 @@ }; can2: can@53fcc000 { - compatible = "fsl,imx53-flexcan"; + compatible = "fsl,imx53-flexcan", "fsl,imx25-flexcan"; reg = <0x53fcc000 0x4000>; interrupts = <83>; clocks = <&clks IMX5_CLK_CAN2_IPG_GATE>, diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c7c28c885a19..f079a2039c8a 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -280,6 +280,7 @@ void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); +static inline bool kvm_arch_check_sve_has_vhe(void) { return true; } static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} @@ -303,8 +304,13 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -/* All host FP/SIMD state is restored on guest exit, so nothing to save: */ -static inline void kvm_fpsimd_flush_cpu_state(void) {} +/* + * VFP/NEON switching is all done by the hyp switch code, so no need to + * coordinate with host context handling for this state: + */ +static inline void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) {} static inline void kvm_arm_vhe_guest_enter(void) {} static inline void kvm_arm_vhe_guest_exit(void) {} diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 707a1f06dc5d..f675162663f0 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -309,6 +309,22 @@ static inline unsigned int kvm_get_vmid_bits(void) return 8; } +/* + * We are not in the kvm->srcu critical section most of the time, so we take + * the SRCU read lock here. Since we copy the data from the user page, we + * can immediately drop the lock again. + */ +static inline int kvm_read_guest_lock(struct kvm *kvm, + gpa_t gpa, void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_read_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + static inline void *kvm_get_hyp_vector(void) { return kvm_ksym_ref(__kvm_hyp_vector); diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index caae4843cb70..16e006f708ca 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/arch/arm/include/uapi/asm/kvm.h @@ -91,6 +91,7 @@ struct kvm_regs { #define KVM_VGIC_V3_ADDR_TYPE_DIST 2 #define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 #define KVM_VGIC_ITS_ADDR_TYPE 4 +#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5 #define KVM_VGIC_V3_DIST_SIZE SZ_64K #define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index eb2cf4938f6d..b0d3820081c8 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1130,6 +1130,7 @@ endmenu config ARM64_SVE bool "ARM Scalable Vector Extension support" default y + depends on !KVM || ARM64_VHE help The Scalable Vector Extension (SVE) is an extension to the AArch64 execution state which complements and extends the SIMD functionality @@ -1155,6 +1156,12 @@ config ARM64_SVE booting the kernel. If unsure and you are not observing these symptoms, you should assume that it is safe to say Y. + CPUs that support SVE are architecturally required to support the + Virtualization Host Extensions (VHE), so the kernel makes no + provision for supporting SVE alongside KVM without VHE enabled. + Thus, you will need to enable CONFIG_ARM64_VHE if you want to support + KVM in the same kernel image. + config ARM64_MODULE_PLTS bool select HAVE_MOD_ARCH_SPECIFIC diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 09b0f2a80c8f..0a6b7133195e 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -11,9 +11,7 @@ #include <asm/cpucaps.h> #include <asm/cputype.h> -#include <asm/fpsimd.h> #include <asm/hwcap.h> -#include <asm/sigcontext.h> #include <asm/sysreg.h> /* @@ -510,33 +508,6 @@ static inline bool system_supports_sve(void) cpus_have_const_cap(ARM64_SVE); } -/* - * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE - * vector length. - * - * Use only if SVE is present. - * This function clobbers the SVE vector length. - */ -static inline u64 read_zcr_features(void) -{ - u64 zcr; - unsigned int vq_max; - - /* - * Set the maximum possible VL, and write zeroes to all other - * bits to see if they stick. - */ - sve_kernel_enable(NULL); - write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1); - - zcr = read_sysreg_s(SYS_ZCR_EL1); - zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */ - vq_max = sve_vq_from_vl(sve_get_vl()); - zcr |= vq_max - 1; /* set LEN field to maximum effective value */ - - return zcr; -} - #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 30014a9f8f2b..ea690b3562af 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -75,6 +75,7 @@ #define ARM_CPU_IMP_CAVIUM 0x43 #define ARM_CPU_IMP_BRCM 0x42 #define ARM_CPU_IMP_QCOM 0x51 +#define ARM_CPU_IMP_NVIDIA 0x4E #define ARM_CPU_PART_AEM_V8 0xD0F #define ARM_CPU_PART_FOUNDATION 0xD00 @@ -99,6 +100,9 @@ #define QCOM_CPU_PART_FALKOR 0xC00 #define QCOM_CPU_PART_KRYO 0x200 +#define NVIDIA_CPU_PART_DENVER 0x003 +#define NVIDIA_CPU_PART_CARMEL 0x004 + #define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53) #define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57) #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) @@ -114,6 +118,8 @@ #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1) #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR) #define MIDR_QCOM_KRYO MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_KRYO) +#define MIDR_NVIDIA_DENVER MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_DENVER) +#define MIDR_NVIDIA_CARMEL MIDR_CPU_MODEL(ARM_CPU_IMP_NVIDIA, NVIDIA_CPU_PART_CARMEL) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index aa7162ae93e3..fa92747a49c8 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -18,6 +18,8 @@ #include <asm/ptrace.h> #include <asm/errno.h> +#include <asm/processor.h> +#include <asm/sigcontext.h> #ifndef __ASSEMBLY__ @@ -41,6 +43,8 @@ struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); extern void fpsimd_load_state(struct user_fpsimd_state *state); +extern void fpsimd_save(void); + extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); @@ -49,12 +53,27 @@ extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); +extern void fpsimd_bind_task_to_cpu(void); +extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state); + extern void fpsimd_flush_task_state(struct task_struct *target); +extern void fpsimd_flush_cpu_state(void); extern void sve_flush_cpu_state(void); /* Maximum VL that SVE VL-agnostic software can transparently support */ #define SVE_VL_ARCH_MAX 0x100 +/* Offset of FFR in the SVE register dump */ +static inline size_t sve_ffr_offset(int vl) +{ + return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET; +} + +static inline void *sve_pffr(struct thread_struct *thread) +{ + return (char *)thread->sve_state + sve_ffr_offset(thread->sve_vl); +} + extern void sve_save_state(void *state, u32 *pfpsr); extern void sve_load_state(void const *state, u32 const *pfpsr, unsigned long vq_minus_1); @@ -63,6 +82,8 @@ extern unsigned int sve_get_vl(void); struct arm64_cpu_capabilities; extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern u64 read_zcr_features(void); + extern int __ro_after_init sve_max_vl; #ifdef CONFIG_ARM64_SVE diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index f6648a3e4152..821a7032c0f7 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -30,19 +30,19 @@ /* The hyp-stub will return this for any kvm_call_hyp() call */ #define ARM_EXCEPTION_HYP_GONE HVC_STUB_ERR -#define KVM_ARM64_DEBUG_DIRTY_SHIFT 0 -#define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT) +#ifndef __ASSEMBLY__ + +#include <linux/mm.h> /* Translate a kernel address of @sym into its equivalent linear mapping */ #define kvm_ksym_ref(sym) \ ({ \ void *val = &sym; \ if (!is_kernel_in_hyp_mode()) \ - val = phys_to_virt((u64)&sym - kimage_voffset); \ + val = lm_alias(&sym); \ val; \ }) -#ifndef __ASSEMBLY__ struct kvm; struct kvm_vcpu; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 469de8acd06f..a4ca202ff3f2 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -30,6 +30,7 @@ #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> +#include <asm/thread_info.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -216,8 +217,8 @@ struct kvm_vcpu_arch { /* Exception Information */ struct kvm_vcpu_fault_info fault; - /* Guest debug state */ - u64 debug_flags; + /* Miscellaneous vcpu state flags */ + u64 flags; /* * We maintain more than a single set of debug registers to support @@ -238,6 +239,10 @@ struct kvm_vcpu_arch { /* Pointer to host CPU context */ kvm_cpu_context_t *host_cpu_context; + + struct thread_info *host_thread_info; /* hyp VA */ + struct user_fpsimd_state *host_fpsimd_state; /* hyp VA */ + struct { /* {Break,watch}point registers */ struct kvm_guest_debug_arch regs; @@ -293,6 +298,12 @@ struct kvm_vcpu_arch { bool sysregs_loaded_on_cpu; }; +/* vcpu_arch flags field values: */ +#define KVM_ARM64_DEBUG_DIRTY (1 << 0) +#define KVM_ARM64_FP_ENABLED (1 << 1) /* guest FP regs loaded */ +#define KVM_ARM64_FP_HOST (1 << 2) /* host FP regs loaded */ +#define KVM_ARM64_HOST_SVE_IN_USE (1 << 3) /* backup for host TIF_SVE */ + #define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs) /* @@ -394,6 +405,19 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, kvm_call_hyp(__kvm_set_tpidr_el2, tpidr_el2); } +static inline bool kvm_arch_check_sve_has_vhe(void) +{ + /* + * The Arm architecture specifies that implementation of SVE + * requires VHE also to be implemented. The KVM code for arm64 + * relies on this when SVE is present: + */ + if (system_supports_sve()) + return has_vhe(); + else + return true; +} + static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {} @@ -420,15 +444,18 @@ static inline void __cpu_init_stage2(void) "PARange is %d bits, unsupported configuration!", parange); } -/* - * All host FP/SIMD state is restored on guest exit, so nothing needs - * doing here except in the SVE case: -*/ -static inline void kvm_fpsimd_flush_cpu_state(void) +/* Guest/host FPSIMD coordination helpers */ +int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); +void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu); + +#ifdef CONFIG_KVM /* Avoid conflicts with core headers if CONFIG_KVM=n */ +static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) { - if (system_supports_sve()) - sve_flush_cpu_state(); + return kvm_arch_vcpu_run_map_fp(vcpu); } +#endif static inline void kvm_arm_vhe_guest_enter(void) { diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 082110993647..6128992c2ded 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -360,6 +360,22 @@ static inline unsigned int kvm_get_vmid_bits(void) return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8; } +/* + * We are not in the kvm->srcu critical section most of the time, so we take + * the SRCU read lock here. Since we copy the data from the user page, we + * can immediately drop the lock again. + */ +static inline int kvm_read_guest_lock(struct kvm *kvm, + gpa_t gpa, void *data, unsigned long len) +{ + int srcu_idx = srcu_read_lock(&kvm->srcu); + int ret = kvm_read_guest(kvm, gpa, data, len); + + srcu_read_unlock(&kvm->srcu, srcu_idx); + + return ret; +} + #ifdef CONFIG_KVM_INDIRECT_VECTORS /* * EL2 vectors can be mapped and rerouted in a number of ways, diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 767598932549..c99e657fdd57 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -156,7 +156,9 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, /* Sync TPIDR_EL0 back to thread_struct for current */ void tls_preserve_current_state(void); -#define INIT_THREAD { } +#define INIT_THREAD { \ + .fpsimd_cpu = NR_CPUS, \ +} static inline void start_thread_common(struct pt_regs *regs, unsigned long pc) { @@ -244,6 +246,17 @@ void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused); void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused); void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused); +/* + * Not at the top of the file due to a direct #include cycle between + * <asm/fpsimd.h> and <asm/processor.h>. Deferring this #include + * ensures that contents of processor.h are visible to fpsimd.h even if + * processor.h is included first. + * + * These prctl helpers are the only things in this file that require + * fpsimd.h. The core code expects them to be in this header. + */ +#include <asm/fpsimd.h> + /* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) #define SVE_GET_VL() sve_get_current_vl() diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 740aa03c5f0d..af271f9a6c9f 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -45,12 +45,6 @@ struct thread_info { int preempt_count; /* 0 => preemptable, <0 => bug */ }; -#define INIT_THREAD_INFO(tsk) \ -{ \ - .preempt_count = INIT_PREEMPT_COUNT, \ - .addr_limit = KERNEL_DS, \ -} - #define thread_saved_pc(tsk) \ ((unsigned long)(tsk->thread.cpu_context.pc)) #define thread_saved_sp(tsk) \ @@ -117,5 +111,12 @@ void arch_release_task_struct(struct task_struct *tsk); _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ _TIF_NOHZ) +#define INIT_THREAD_INFO(tsk) \ +{ \ + .flags = _TIF_FOREIGN_FPSTATE, \ + .preempt_count = INIT_PREEMPT_COUNT, \ + .addr_limit = KERNEL_DS, \ +} + #endif /* __KERNEL__ */ #endif /* __ASM_THREAD_INFO_H */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 04b3256f8e6d..4e76630dd655 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -91,6 +91,7 @@ struct kvm_regs { #define KVM_VGIC_V3_ADDR_TYPE_DIST 2 #define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 #define KVM_VGIC_ITS_ADDR_TYPE 4 +#define KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION 5 #define KVM_VGIC_V3_DIST_SIZE SZ_64K #define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index a900befadfe8..e4a1182deff7 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -316,6 +316,7 @@ static const struct midr_range arm64_bp_harden_smccc_cpus[] = { MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1), MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR), + MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER), {}, }; diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 87a35364e750..7074c4cd0e0e 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -37,12 +37,14 @@ #include <linux/sched/task_stack.h> #include <linux/signal.h> #include <linux/slab.h> +#include <linux/stddef.h> #include <linux/sysctl.h> #include <asm/esr.h> #include <asm/fpsimd.h> #include <asm/cpufeature.h> #include <asm/cputype.h> +#include <asm/processor.h> #include <asm/simd.h> #include <asm/sigcontext.h> #include <asm/sysreg.h> @@ -118,7 +120,6 @@ */ struct fpsimd_last_state_struct { struct user_fpsimd_state *st; - bool sve_in_use; }; static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); @@ -159,19 +160,6 @@ static void sve_free(struct task_struct *task) __sve_free(task); } - -/* Offset of FFR in the SVE register dump */ -static size_t sve_ffr_offset(int vl) -{ - return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET; -} - -static void *sve_pffr(struct task_struct *task) -{ - return (char *)task->thread.sve_state + - sve_ffr_offset(task->thread.sve_vl); -} - static void change_cpacr(u64 val, u64 mask) { u64 cpacr = read_sysreg(CPACR_EL1); @@ -252,31 +240,24 @@ static void task_fpsimd_load(void) WARN_ON(!in_softirq() && !irqs_disabled()); if (system_supports_sve() && test_thread_flag(TIF_SVE)) - sve_load_state(sve_pffr(current), + sve_load_state(sve_pffr(¤t->thread), ¤t->thread.uw.fpsimd_state.fpsr, sve_vq_from_vl(current->thread.sve_vl) - 1); else fpsimd_load_state(¤t->thread.uw.fpsimd_state); - - if (system_supports_sve()) { - /* Toggle SVE trapping for userspace if needed */ - if (test_thread_flag(TIF_SVE)) - sve_user_enable(); - else - sve_user_disable(); - - /* Serialised by exception return to user */ - } } /* - * Ensure current's FPSIMD/SVE storage in thread_struct is up to date - * with respect to the CPU registers. + * Ensure FPSIMD/SVE storage in memory for the loaded context is up to + * date with respect to the CPU registers. * * Softirqs (and preemption) must be disabled. */ -static void task_fpsimd_save(void) +void fpsimd_save(void) { + struct user_fpsimd_state *st = __this_cpu_read(fpsimd_last_state.st); + /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ + WARN_ON(!in_softirq() && !irqs_disabled()); if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { @@ -291,10 +272,9 @@ static void task_fpsimd_save(void) return; } - sve_save_state(sve_pffr(current), - ¤t->thread.uw.fpsimd_state.fpsr); + sve_save_state(sve_pffr(¤t->thread), &st->fpsr); } else - fpsimd_save_state(¤t->thread.uw.fpsimd_state); + fpsimd_save_state(st); } } @@ -598,7 +578,7 @@ int sve_set_vector_length(struct task_struct *task, if (task == current) { local_bh_disable(); - task_fpsimd_save(); + fpsimd_save(); set_thread_flag(TIF_FOREIGN_FPSTATE); } @@ -618,10 +598,8 @@ int sve_set_vector_length(struct task_struct *task, task->thread.sve_vl = vl; out: - if (flags & PR_SVE_VL_INHERIT) - set_tsk_thread_flag(task, TIF_SVE_VL_INHERIT); - else - clear_tsk_thread_flag(task, TIF_SVE_VL_INHERIT); + update_tsk_thread_flag(task, TIF_SVE_VL_INHERIT, + flags & PR_SVE_VL_INHERIT); return 0; } @@ -765,6 +743,33 @@ void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) isb(); } +/* + * Read the pseudo-ZCR used by cpufeatures to identify the supported SVE + * vector length. + * + * Use only if SVE is present. + * This function clobbers the SVE vector length. + */ +u64 read_zcr_features(void) +{ + u64 zcr; + unsigned int vq_max; + + /* + * Set the maximum possible VL, and write zeroes to all other + * bits to see if they stick. + */ + sve_kernel_enable(NULL); + write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1); + + zcr = read_sysreg_s(SYS_ZCR_EL1); + zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */ + vq_max = sve_vq_from_vl(sve_get_vl()); + zcr |= vq_max - 1; /* set LEN field to maximum effective value */ + + return zcr; +} + void __init sve_setup(void) { u64 zcr; @@ -839,7 +844,7 @@ asmlinkage void do_sve_acc(unsigned int esr, struct pt_regs *regs) local_bh_disable(); - task_fpsimd_save(); + fpsimd_save(); fpsimd_to_sve(current); /* Force ret_to_user to reload the registers: */ @@ -892,31 +897,25 @@ asmlinkage void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs) void fpsimd_thread_switch(struct task_struct *next) { + bool wrong_task, wrong_cpu; + if (!system_supports_fpsimd()) return; + + /* Save unsaved fpsimd state, if any: */ + fpsimd_save(); + /* - * Save the current FPSIMD state to memory, but only if whatever is in - * the registers is in fact the most recent userland FPSIMD state of - * 'current'. + * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's + * state. For kernel threads, FPSIMD registers are never loaded + * and wrong_task and wrong_cpu will always be true. */ - if (current->mm) - task_fpsimd_save(); + wrong_task = __this_cpu_read(fpsimd_last_state.st) != + &next->thread.uw.fpsimd_state; + wrong_cpu = next->thread.fpsimd_cpu != smp_processor_id(); - if (next->mm) { - /* - * If we are switching to a task whose most recent userland - * FPSIMD state is already in the registers of *this* cpu, - * we can skip loading the state from memory. Otherwise, set - * the TIF_FOREIGN_FPSTATE flag so the state will be loaded - * upon the next return to userland. - */ - if (__this_cpu_read(fpsimd_last_state.st) == - &next->thread.uw.fpsimd_state - && next->thread.fpsimd_cpu == smp_processor_id()) - clear_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE); - else - set_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE); - } + update_tsk_thread_flag(next, TIF_FOREIGN_FPSTATE, + wrong_task || wrong_cpu); } void fpsimd_flush_thread(void) @@ -982,7 +981,7 @@ void fpsimd_preserve_current_state(void) return; local_bh_disable(); - task_fpsimd_save(); + fpsimd_save(); local_bh_enable(); } @@ -1002,14 +1001,33 @@ void fpsimd_signal_preserve_current_state(void) * Associate current's FPSIMD context with this cpu * Preemption must be disabled when calling this function. */ -static void fpsimd_bind_to_cpu(void) +void fpsimd_bind_task_to_cpu(void) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); last->st = ¤t->thread.uw.fpsimd_state; - last->sve_in_use = test_thread_flag(TIF_SVE); current->thread.fpsimd_cpu = smp_processor_id(); + + if (system_supports_sve()) { + /* Toggle SVE trapping for userspace if needed */ + if (test_thread_flag(TIF_SVE)) + sve_user_enable(); + else + sve_user_disable(); + + /* Serialised by exception return to user */ + } +} + +void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st) +{ + struct fpsimd_last_state_struct *last = + this_cpu_ptr(&fpsimd_last_state); + + WARN_ON(!in_softirq() && !irqs_disabled()); + + last->st = st; } /* @@ -1026,7 +1044,7 @@ void fpsimd_restore_current_state(void) if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { task_fpsimd_load(); - fpsimd_bind_to_cpu(); + fpsimd_bind_task_to_cpu(); } local_bh_enable(); @@ -1049,9 +1067,9 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) fpsimd_to_sve(current); task_fpsimd_load(); + fpsimd_bind_task_to_cpu(); - if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) - fpsimd_bind_to_cpu(); + clear_thread_flag(TIF_FOREIGN_FPSTATE); local_bh_enable(); } @@ -1064,29 +1082,12 @@ void fpsimd_flush_task_state(struct task_struct *t) t->thread.fpsimd_cpu = NR_CPUS; } -static inline void fpsimd_flush_cpu_state(void) +void fpsimd_flush_cpu_state(void) { __this_cpu_write(fpsimd_last_state.st, NULL); + set_thread_flag(TIF_FOREIGN_FPSTATE); } -/* - * Invalidate any task SVE state currently held in this CPU's regs. - * - * This is used to prevent the kernel from trying to reuse SVE register data - * that is detroyed by KVM guest enter/exit. This function should go away when - * KVM SVE support is implemented. Don't use it for anything else. - */ -#ifdef CONFIG_ARM64_SVE -void sve_flush_cpu_state(void) -{ - struct fpsimd_last_state_struct const *last = - this_cpu_ptr(&fpsimd_last_state); - - if (last->st && last->sve_in_use) - fpsimd_flush_cpu_state(); -} -#endif /* CONFIG_ARM64_SVE */ - #ifdef CONFIG_KERNEL_MODE_NEON DEFINE_PER_CPU(bool, kernel_neon_busy); @@ -1120,11 +1121,8 @@ void kernel_neon_begin(void) __this_cpu_write(kernel_neon_busy, true); - /* Save unsaved task fpsimd state, if any: */ - if (current->mm) { - task_fpsimd_save(); - set_thread_flag(TIF_FOREIGN_FPSTATE); - } + /* Save unsaved fpsimd state, if any: */ + fpsimd_save(); /* Invalidate any task state remaining in the fpsimd regs: */ fpsimd_flush_cpu_state(); @@ -1246,13 +1244,10 @@ static int fpsimd_cpu_pm_notifier(struct notifier_block *self, { switch (cmd) { case CPU_PM_ENTER: - if (current->mm) - task_fpsimd_save(); + fpsimd_save(); fpsimd_flush_cpu_state(); break; case CPU_PM_EXIT: - if (current->mm) - set_thread_flag(TIF_FOREIGN_FPSTATE); break; case CPU_PM_ENTER_FAILED: default: diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 7ff81fed46e1..78889c4546d7 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -44,6 +44,7 @@ #include <asm/compat.h> #include <asm/cpufeature.h> #include <asm/debug-monitors.h> +#include <asm/fpsimd.h> #include <asm/pgtable.h> #include <asm/stacktrace.h> #include <asm/syscall.h> diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index a2e3a5af1113..47b23bf617c7 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ config KVM select HAVE_KVM_IRQ_ROUTING select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS + select HAVE_KVM_VCPU_RUN_PID_CHANGE ---help--- Support hosting virtualized guest machines. We don't support KVM with 16K page tables yet, due to the multiple diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 93afff91cb7c..0f2a135ba15b 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -19,7 +19,7 @@ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o va_layout.o kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generic_v8.o -kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o +kvm-$(CONFIG_KVM_ARM_HOST) += vgic-sys-reg-v3.o fpsimd.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/aarch32.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic/vgic.o diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index a1f4ebdfe6d3..00d422336a45 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -103,7 +103,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY - * flag on vcpu->arch.debug_flags). Since the guest must not interfere + * flag on vcpu->arch.flags). Since the guest must not interfere * with the hardware state when debugging the guest, we must ensure that * trapping is enabled whenever we are debugging the guest using the * debug registers. @@ -111,7 +111,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) { - bool trap_debug = !(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY); + bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY); unsigned long mdscr; trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); @@ -184,7 +184,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) vcpu_write_sys_reg(vcpu, mdscr, MDSCR_EL1); vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state; - vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; trap_debug = true; trace_kvm_arm_set_regset("BKPTS", get_num_brps(), @@ -206,7 +206,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) /* If KDE or MDE are set, perform a full save/restore cycle. */ if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE)) - vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c new file mode 100644 index 000000000000..dc6ecfa5a2d2 --- /dev/null +++ b/arch/arm64/kvm/fpsimd.c @@ -0,0 +1,110 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * arch/arm64/kvm/fpsimd.c: Guest/host FPSIMD context coordination helpers + * + * Copyright 2018 Arm Limited + * Author: Dave Martin <Dave.Martin@arm.com> + */ +#include <linux/bottom_half.h> +#include <linux/sched.h> +#include <linux/thread_info.h> +#include <linux/kvm_host.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_host.h> +#include <asm/kvm_mmu.h> + +/* + * Called on entry to KVM_RUN unless this vcpu previously ran at least + * once and the most recent prior KVM_RUN for this vcpu was called from + * the same task as current (highly likely). + * + * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu), + * such that on entering hyp the relevant parts of current are already + * mapped. + */ +int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) +{ + int ret; + + struct thread_info *ti = ¤t->thread_info; + struct user_fpsimd_state *fpsimd = ¤t->thread.uw.fpsimd_state; + + /* + * Make sure the host task thread flags and fpsimd state are + * visible to hyp: + */ + ret = create_hyp_mappings(ti, ti + 1, PAGE_HYP); + if (ret) + goto error; + + ret = create_hyp_mappings(fpsimd, fpsimd + 1, PAGE_HYP); + if (ret) + goto error; + + vcpu->arch.host_thread_info = kern_hyp_va(ti); + vcpu->arch.host_fpsimd_state = kern_hyp_va(fpsimd); +error: + return ret; +} + +/* + * Prepare vcpu for saving the host's FPSIMD state and loading the guest's. + * The actual loading is done by the FPSIMD access trap taken to hyp. + * + * Here, we just set the correct metadata to indicate that the FPSIMD + * state in the cpu regs (if any) belongs to current on the host. + * + * TIF_SVE is backed up here, since it may get clobbered with guest state. + * This flag is restored by kvm_arch_vcpu_put_fp(vcpu). + */ +void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) +{ + BUG_ON(!current->mm); + + vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | KVM_ARM64_HOST_SVE_IN_USE); + vcpu->arch.flags |= KVM_ARM64_FP_HOST; + if (test_thread_flag(TIF_SVE)) + vcpu->arch.flags |= KVM_ARM64_HOST_SVE_IN_USE; +} + +/* + * If the guest FPSIMD state was loaded, update the host's context + * tracking data mark the CPU FPSIMD regs as dirty and belonging to vcpu + * so that they will be written back if the kernel clobbers them due to + * kernel-mode NEON before re-entry into the guest. + */ +void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) +{ + WARN_ON_ONCE(!irqs_disabled()); + + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { + fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.gp_regs.fp_regs); + clear_thread_flag(TIF_FOREIGN_FPSTATE); + clear_thread_flag(TIF_SVE); + } +} + +/* + * Write back the vcpu FPSIMD regs if they are dirty, and invalidate the + * cpu FPSIMD regs so that they can't be spuriously reused if this vcpu + * disappears and another task or vcpu appears that recycles the same + * struct fpsimd_state. + */ +void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) +{ + local_bh_disable(); + + update_thread_flag(TIF_SVE, + vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE); + + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { + /* Clean guest FP state to memory and invalidate cpu view */ + fpsimd_save(); + fpsimd_flush_cpu_state(); + } else if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { + /* Ensure user trap controls are correctly restored */ + fpsimd_bind_task_to_cpu(); + } + + local_bh_enable(); +} diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c index 3e717f66f011..50009766e5e5 100644 --- a/arch/arm64/kvm/hyp/debug-sr.c +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -163,7 +163,7 @@ void __hyp_text __debug_switch_to_guest(struct kvm_vcpu *vcpu) if (!has_vhe()) __debug_save_spe_nvhe(&vcpu->arch.host_debug_state.pmscr_el1); - if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)) + if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) return; host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); @@ -185,7 +185,7 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu) if (!has_vhe()) __debug_restore_spe_nvhe(vcpu->arch.host_debug_state.pmscr_el1); - if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)) + if (!(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) return; host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); @@ -196,7 +196,7 @@ void __hyp_text __debug_switch_to_host(struct kvm_vcpu *vcpu) __debug_save_state(vcpu, guest_dbg, guest_ctxt); __debug_restore_state(vcpu, host_dbg, host_ctxt); - vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY; + vcpu->arch.flags &= ~KVM_ARM64_DEBUG_DIRTY; } u32 __hyp_text __kvm_get_mdcr_el2(void) diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index e41a161d313a..fad1e164fe48 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -166,46 +166,3 @@ abort_guest_exit_end: orr x0, x0, x5 1: ret ENDPROC(__guest_exit) - -ENTRY(__fpsimd_guest_restore) - // x0: esr - // x1: vcpu - // x2-x29,lr: vcpu regs - // vcpu x0-x1 on the stack - stp x2, x3, [sp, #-16]! - stp x4, lr, [sp, #-16]! - -alternative_if_not ARM64_HAS_VIRT_HOST_EXTN - mrs x2, cptr_el2 - bic x2, x2, #CPTR_EL2_TFP - msr cptr_el2, x2 -alternative_else - mrs x2, cpacr_el1 - orr x2, x2, #CPACR_EL1_FPEN - msr cpacr_el1, x2 -alternative_endif - isb - - mov x3, x1 - - ldr x0, [x3, #VCPU_HOST_CONTEXT] - kern_hyp_va x0 - add x0, x0, #CPU_GP_REG_OFFSET(CPU_FP_REGS) - bl __fpsimd_save_state - - add x2, x3, #VCPU_CONTEXT - add x0, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS) - bl __fpsimd_restore_state - - // Skip restoring fpexc32 for AArch64 guests - mrs x1, hcr_el2 - tbnz x1, #HCR_RW_SHIFT, 1f - ldr x4, [x3, #VCPU_FPEXC32_EL2] - msr fpexc32_el2, x4 -1: - ldp x4, lr, [sp], #16 - ldp x2, x3, [sp], #16 - ldp x0, x1, [sp], #16 - - eret -ENDPROC(__fpsimd_guest_restore) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index bffece27b5c1..753b9d213651 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -113,25 +113,6 @@ el1_hvc_guest: el1_trap: get_vcpu_ptr x1, x0 - - mrs x0, esr_el2 - lsr x0, x0, #ESR_ELx_EC_SHIFT - /* - * x0: ESR_EC - * x1: vcpu pointer - */ - - /* - * We trap the first access to the FP/SIMD to save the host context - * and restore the guest context lazily. - * If FP/SIMD is not implemented, handle the trap and inject an - * undefined instruction exception to the guest. - */ -alternative_if_not ARM64_HAS_NO_FPSIMD - cmp x0, #ESR_ELx_EC_FP_ASIMD - b.eq __fpsimd_guest_restore -alternative_else_nop_endif - mov x0, #ARM_EXCEPTION_TRAP b __guest_exit diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index d9645236e474..2d45bd719a5d 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -21,21 +21,25 @@ #include <kvm/arm_psci.h> +#include <asm/cpufeature.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_host.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/fpsimd.h> #include <asm/debug-monitors.h> +#include <asm/processor.h> +#include <asm/thread_info.h> -static bool __hyp_text __fpsimd_enabled_nvhe(void) +/* Check whether the FP regs were dirtied while in the host-side run loop: */ +static bool __hyp_text update_fp_enabled(struct kvm_vcpu *vcpu) { - return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP); -} + if (vcpu->arch.host_thread_info->flags & _TIF_FOREIGN_FPSTATE) + vcpu->arch.flags &= ~(KVM_ARM64_FP_ENABLED | + KVM_ARM64_FP_HOST); -static bool fpsimd_enabled_vhe(void) -{ - return !!(read_sysreg(cpacr_el1) & CPACR_EL1_FPEN); + return !!(vcpu->arch.flags & KVM_ARM64_FP_ENABLED); } /* Save the 32-bit only FPSIMD system register state */ @@ -92,7 +96,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; - val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN); + val &= ~CPACR_EL1_ZEN; + if (!update_fp_enabled(vcpu)) + val &= ~CPACR_EL1_FPEN; + write_sysreg(val, cpacr_el1); write_sysreg(kvm_get_hyp_vector(), vbar_el1); @@ -105,7 +112,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) __activate_traps_common(vcpu); val = CPTR_EL2_DEFAULT; - val |= CPTR_EL2_TTA | CPTR_EL2_TFP | CPTR_EL2_TZ; + val |= CPTR_EL2_TTA | CPTR_EL2_TZ; + if (!update_fp_enabled(vcpu)) + val |= CPTR_EL2_TFP; + write_sysreg(val, cptr_el2); } @@ -318,6 +328,50 @@ static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu) } } +static bool __hyp_text __hyp_switch_fpsimd(struct kvm_vcpu *vcpu) +{ + struct user_fpsimd_state *host_fpsimd = vcpu->arch.host_fpsimd_state; + + if (has_vhe()) + write_sysreg(read_sysreg(cpacr_el1) | CPACR_EL1_FPEN, + cpacr_el1); + else + write_sysreg(read_sysreg(cptr_el2) & ~(u64)CPTR_EL2_TFP, + cptr_el2); + + isb(); + + if (vcpu->arch.flags & KVM_ARM64_FP_HOST) { + /* + * In the SVE case, VHE is assumed: it is enforced by + * Kconfig and kvm_arch_init(). + */ + if (system_supports_sve() && + (vcpu->arch.flags & KVM_ARM64_HOST_SVE_IN_USE)) { + struct thread_struct *thread = container_of( + host_fpsimd, + struct thread_struct, uw.fpsimd_state); + + sve_save_state(sve_pffr(thread), &host_fpsimd->fpsr); + } else { + __fpsimd_save_state(host_fpsimd); + } + + vcpu->arch.flags &= ~KVM_ARM64_FP_HOST; + } + + __fpsimd_restore_state(&vcpu->arch.ctxt.gp_regs.fp_regs); + + /* Skip restoring fpexc32 for AArch64 guests */ + if (!(read_sysreg(hcr_el2) & HCR_RW)) + write_sysreg(vcpu->arch.ctxt.sys_regs[FPEXC32_EL2], + fpexc32_el2); + + vcpu->arch.flags |= KVM_ARM64_FP_ENABLED; + + return true; +} + /* * Return true when we were able to fixup the guest exit and should return to * the guest, false when we should restore the host state and return to the @@ -334,11 +388,23 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) * same PC once the SError has been injected, and replay the * trapping instruction. */ - if (*exit_code == ARM_EXCEPTION_TRAP && !__populate_fault_info(vcpu)) + if (*exit_code != ARM_EXCEPTION_TRAP) + goto exit; + + /* + * We trap the first access to the FP/SIMD to save the host context + * and restore the guest context lazily. + * If FP/SIMD is not implemented, handle the trap and inject an + * undefined instruction exception to the guest. + */ + if (system_supports_fpsimd() && + kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_FP_ASIMD) + return __hyp_switch_fpsimd(vcpu); + + if (!__populate_fault_info(vcpu)) return true; - if (static_branch_unlikely(&vgic_v2_cpuif_trap) && - *exit_code == ARM_EXCEPTION_TRAP) { + if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { bool valid; valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW && @@ -350,12 +416,8 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (valid) { int ret = __vgic_v2_perform_cpuif_access(vcpu); - if (ret == 1) { - if (__skip_instr(vcpu)) - return true; - else - *exit_code = ARM_EXCEPTION_TRAP; - } + if (ret == 1 && __skip_instr(vcpu)) + return true; if (ret == -1) { /* Promote an illegal access to an @@ -368,23 +430,21 @@ static bool __hyp_text fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; *exit_code = ARM_EXCEPTION_EL1_SERROR; } + + goto exit; } } if (static_branch_unlikely(&vgic_v3_cpuif_trap) && - *exit_code == ARM_EXCEPTION_TRAP && (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 || kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) { int ret = __vgic_v3_perform_cpuif_access(vcpu); - if (ret == 1) { - if (__skip_instr(vcpu)) - return true; - else - *exit_code = ARM_EXCEPTION_TRAP; - } + if (ret == 1 && __skip_instr(vcpu)) + return true; } +exit: /* Return to the host kernel and handle the exit */ return false; } @@ -394,7 +454,6 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; - bool fp_enabled; u64 exit_code; host_ctxt = vcpu->arch.host_cpu_context; @@ -416,19 +475,14 @@ int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); - fp_enabled = fpsimd_enabled_vhe(); - sysreg_save_guest_state_vhe(guest_ctxt); __deactivate_traps(vcpu); sysreg_restore_host_state_vhe(host_ctxt); - if (fp_enabled) { - __fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs); - __fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs); + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) __fpsimd_save_fpexc32(vcpu); - } __debug_switch_to_host(vcpu); @@ -440,7 +494,6 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) { struct kvm_cpu_context *host_ctxt; struct kvm_cpu_context *guest_ctxt; - bool fp_enabled; u64 exit_code; vcpu = kern_hyp_va(vcpu); @@ -472,8 +525,6 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); - fp_enabled = __fpsimd_enabled_nvhe(); - __sysreg_save_state_nvhe(guest_ctxt); __sysreg32_save_state(vcpu); __timer_disable_traps(vcpu); @@ -484,11 +535,8 @@ int __hyp_text __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu) __sysreg_restore_state_nvhe(host_ctxt); - if (fp_enabled) { - __fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs); - __fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs); + if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) __fpsimd_save_fpexc32(vcpu); - } /* * This must come after restoring the host sysregs, since a non-VHE diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index b3894df6bf1a..35bc16832efe 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -196,7 +196,7 @@ void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu) sysreg[DACR32_EL2] = read_sysreg(dacr32_el2); sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2); - if (has_vhe() || vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY) + if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY) sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2); } @@ -218,7 +218,7 @@ void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu) write_sysreg(sysreg[DACR32_EL2], dacr32_el2); write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2); - if (has_vhe() || vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY) + if (has_vhe() || vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY) write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2); } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 6e3b969391fd..a4363735d3f8 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -31,7 +31,6 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> @@ -338,7 +337,7 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, { if (p->is_write) { vcpu_write_sys_reg(vcpu, p->regval, r->reg); - vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; } else { p->regval = vcpu_read_sys_reg(vcpu, r->reg); } @@ -369,7 +368,7 @@ static void reg_to_dbg(struct kvm_vcpu *vcpu, } *dbg_reg = val; - vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; } static void dbg_to_reg(struct kvm_vcpu *vcpu, @@ -1441,7 +1440,7 @@ static bool trap_debug32(struct kvm_vcpu *vcpu, { if (p->is_write) { vcpu_cp14(vcpu, r->reg) = p->regval; - vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; } else { p->regval = vcpu_cp14(vcpu, r->reg); } @@ -1473,7 +1472,7 @@ static bool trap_xvr(struct kvm_vcpu *vcpu, val |= p->regval << 32; *dbg_reg = val; - vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; } else { p->regval = *dbg_reg >> 32; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9f3c47acf8ff..1b18b4722420 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -646,8 +646,10 @@ static int keep_initrd __initdata; void __init free_initrd_mem(unsigned long start, unsigned long end) { - if (!keep_initrd) + if (!keep_initrd) { free_reserved_area((void *)start, (void *)end, 0, "initrd"); + memblock_free(__virt_to_phys(start), end - start); + } } static int __init keepinitrd_setup(char *__unused) diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index 9abddde372ab..b2dabd06659d 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -69,17 +69,30 @@ struct dyn_arch_ftrace { #endif #if defined(CONFIG_FTRACE_SYSCALLS) && !defined(__ASSEMBLY__) -#ifdef PPC64_ELF_ABI_v1 +/* + * Some syscall entry functions on powerpc start with "ppc_" (fork and clone, + * for instance) or ppc32_/ppc64_. We should also match the sys_ variant with + * those. + */ #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME +#ifdef PPC64_ELF_ABI_v1 +static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) +{ + /* We need to skip past the initial dot, and the __se_sys alias */ + return !strcmp(sym + 1, name) || + (!strncmp(sym, ".__se_sys", 9) && !strcmp(sym + 6, name)) || + (!strncmp(sym, ".ppc_", 5) && !strcmp(sym + 5, name + 4)) || + (!strncmp(sym, ".ppc32_", 7) && !strcmp(sym + 7, name + 4)) || + (!strncmp(sym, ".ppc64_", 7) && !strcmp(sym + 7, name + 4)); +} +#else static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { - /* - * Compare the symbol name with the system call name. Skip the .sys or .SyS - * prefix from the symbol name and the sys prefix from the system call name and - * just match the rest. This is only needed on ppc64 since symbol names on - * 32bit do not start with a period so the generic function will work. - */ - return !strcmp(sym + 4, name + 3); + return !strcmp(sym, name) || + (!strncmp(sym, "__se_sys", 8) && !strcmp(sym + 5, name)) || + (!strncmp(sym, "ppc_", 4) && !strcmp(sym + 4, name + 4)) || + (!strncmp(sym, "ppc32_", 6) && !strcmp(sym + 6, name + 4)) || + (!strncmp(sym, "ppc64_", 6) && !strcmp(sym + 6, name + 4)); } #endif #endif /* CONFIG_FTRACE_SYSCALLS && !__ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h index 4185f1c96125..3f109a3e3edb 100644 --- a/arch/powerpc/include/asm/paca.h +++ b/arch/powerpc/include/asm/paca.h @@ -165,7 +165,6 @@ struct paca_struct { u64 saved_msr; /* MSR saved here by enter_rtas */ u16 trap_save; /* Used when bad stack is encountered */ u8 irq_soft_mask; /* mask for irq soft masking */ - u8 soft_enabled; /* irq soft-enable flag */ u8 irq_happened; /* irq happened while soft-disabled */ u8 io_sync; /* writel() needs spin_unlock sync */ u8 irq_work_pending; /* IRQ_WORK interrupt while soft-disable */ diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index 9f421641a35c..16b077801a5f 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -91,6 +91,7 @@ extern int start_topology_update(void); extern int stop_topology_update(void); extern int prrn_is_enabled(void); extern int find_and_online_cpu_nid(int cpu); +extern int timed_topology_update(int nsecs); #else static inline int start_topology_update(void) { @@ -108,16 +109,12 @@ static inline int find_and_online_cpu_nid(int cpu) { return 0; } +static inline int timed_topology_update(int nsecs) +{ + return 0; +} #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */ -#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_NEED_MULTIPLE_NODES) -#if defined(CONFIG_PPC_SPLPAR) -extern int timed_topology_update(int nsecs); -#else -#define timed_topology_update(nsecs) -#endif /* CONFIG_PPC_SPLPAR */ -#endif /* CONFIG_HOTPLUG_CPU || CONFIG_NEED_MULTIPLE_NODES */ - #include <asm-generic/topology.h> #ifdef CONFIG_SMP diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c index 1bceb95f422d..5584247f5029 100644 --- a/arch/powerpc/platforms/powernv/opal-nvram.c +++ b/arch/powerpc/platforms/powernv/opal-nvram.c @@ -44,6 +44,10 @@ static ssize_t opal_nvram_read(char *buf, size_t count, loff_t *index) return count; } +/* + * This can be called in the panic path with interrupts off, so use + * mdelay in that case. + */ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) { s64 rc = OPAL_BUSY; @@ -58,10 +62,16 @@ static ssize_t opal_nvram_write(char *buf, size_t count, loff_t *index) while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_write_nvram(__pa(buf), count, off); if (rc == OPAL_BUSY_EVENT) { - msleep(OPAL_BUSY_DELAY_MS); + if (in_interrupt() || irqs_disabled()) + mdelay(OPAL_BUSY_DELAY_MS); + else + msleep(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); } else if (rc == OPAL_BUSY) { - msleep(OPAL_BUSY_DELAY_MS); + if (in_interrupt() || irqs_disabled()) + mdelay(OPAL_BUSY_DELAY_MS); + else + msleep(OPAL_BUSY_DELAY_MS); } } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 6176fe9795ca..941d8cc6c9f5 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -261,9 +261,9 @@ CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_TABLES_IPV4=m +CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NF_TABLES_ARP=m +CONFIG_NF_TABLES_ARP=y CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m @@ -284,7 +284,7 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_TABLES_IPV6=m +CONFIG_NF_TABLES_IPV6=y CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m @@ -305,7 +305,7 @@ CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m -CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NF_TABLES_BRIDGE=y CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m @@ -604,7 +604,6 @@ CONFIG_DETECT_HUNG_TASK=y CONFIG_WQ_WATCHDOG=y CONFIG_PANIC_ON_OOPS=y CONFIG_DEBUG_TIMEKEEPING=y -CONFIG_DEBUG_WW_MUTEX_SLOWPATH=y CONFIG_PROVE_LOCKING=y CONFIG_LOCK_STAT=y CONFIG_DEBUG_LOCKDEP=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index c105bcc6d7a6..eb6f75f24208 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -259,9 +259,9 @@ CONFIG_IP_VS_NQ=m CONFIG_IP_VS_FTP=m CONFIG_IP_VS_PE_SIP=m CONFIG_NF_CONNTRACK_IPV4=m -CONFIG_NF_TABLES_IPV4=m +CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_CHAIN_ROUTE_IPV4=m -CONFIG_NF_TABLES_ARP=m +CONFIG_NF_TABLES_ARP=y CONFIG_NFT_CHAIN_NAT_IPV4=m CONFIG_IP_NF_IPTABLES=m CONFIG_IP_NF_MATCH_AH=m @@ -282,7 +282,7 @@ CONFIG_IP_NF_ARPTABLES=m CONFIG_IP_NF_ARPFILTER=m CONFIG_IP_NF_ARP_MANGLE=m CONFIG_NF_CONNTRACK_IPV6=m -CONFIG_NF_TABLES_IPV6=m +CONFIG_NF_TABLES_IPV6=y CONFIG_NFT_CHAIN_ROUTE_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_IP6_NF_IPTABLES=m @@ -303,7 +303,7 @@ CONFIG_IP6_NF_RAW=m CONFIG_IP6_NF_SECURITY=m CONFIG_IP6_NF_NAT=m CONFIG_IP6_NF_TARGET_MASQUERADE=m -CONFIG_NF_TABLES_BRIDGE=m +CONFIG_NF_TABLES_BRIDGE=y CONFIG_RDS=m CONFIG_RDS_RDMA=m CONFIG_RDS_TCP=m diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S index e8077f0971f8..2bf01ba44107 100644 --- a/arch/s390/crypto/crc32be-vx.S +++ b/arch/s390/crypto/crc32be-vx.S @@ -13,6 +13,7 @@ */ #include <linux/linkage.h> +#include <asm/nospec-insn.h> #include <asm/vx-insn.h> /* Vector register range containing CRC-32 constants */ @@ -67,6 +68,8 @@ .previous + GEN_BR_THUNK %r14 + .text /* * The CRC-32 function(s) use these calling conventions: @@ -203,6 +206,6 @@ ENTRY(crc32_be_vgfm_16) .Ldone: VLGVF %r2,%v2,3 - br %r14 + BR_EX %r14 .previous diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S index d8c67a58c0c5..7d6f568bd3ad 100644 --- a/arch/s390/crypto/crc32le-vx.S +++ b/arch/s390/crypto/crc32le-vx.S @@ -14,6 +14,7 @@ */ #include <linux/linkage.h> +#include <asm/nospec-insn.h> #include <asm/vx-insn.h> /* Vector register range containing CRC-32 constants */ @@ -76,6 +77,7 @@ .previous + GEN_BR_THUNK %r14 .text @@ -264,6 +266,6 @@ crc32_le_vgfm_generic: .Ldone: VLGVF %r2,%v2,2 - br %r14 + BR_EX %r14 .previous diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h new file mode 100644 index 000000000000..a01f81186e86 --- /dev/null +++ b/arch/s390/include/asm/nospec-insn.h @@ -0,0 +1,196 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_NOSPEC_ASM_H +#define _ASM_S390_NOSPEC_ASM_H + +#include <asm/alternative-asm.h> +#include <asm/asm-offsets.h> +#include <asm/dwarf.h> + +#ifdef __ASSEMBLY__ + +#ifdef CONFIG_EXPOLINE + +_LC_BR_R1 = __LC_BR_R1 + +/* + * The expoline macros are used to create thunks in the same format + * as gcc generates them. The 'comdat' section flag makes sure that + * the various thunks are merged into a single copy. + */ + .macro __THUNK_PROLOG_NAME name + .pushsection .text.\name,"axG",@progbits,\name,comdat + .globl \name + .hidden \name + .type \name,@function +\name: + CFI_STARTPROC + .endm + + .macro __THUNK_EPILOG + CFI_ENDPROC + .popsection + .endm + + .macro __THUNK_PROLOG_BR r1,r2 + __THUNK_PROLOG_NAME __s390x_indirect_jump_r\r2\()use_r\r1 + .endm + + .macro __THUNK_PROLOG_BC d0,r1,r2 + __THUNK_PROLOG_NAME __s390x_indirect_branch_\d0\()_\r2\()use_\r1 + .endm + + .macro __THUNK_BR r1,r2 + jg __s390x_indirect_jump_r\r2\()use_r\r1 + .endm + + .macro __THUNK_BC d0,r1,r2 + jg __s390x_indirect_branch_\d0\()_\r2\()use_\r1 + .endm + + .macro __THUNK_BRASL r1,r2,r3 + brasl \r1,__s390x_indirect_jump_r\r3\()use_r\r2 + .endm + + .macro __DECODE_RR expand,reg,ruse + .set __decode_fail,1 + .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + .ifc \reg,%r\r1 + .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + .ifc \ruse,%r\r2 + \expand \r1,\r2 + .set __decode_fail,0 + .endif + .endr + .endif + .endr + .if __decode_fail == 1 + .error "__DECODE_RR failed" + .endif + .endm + + .macro __DECODE_RRR expand,rsave,rtarget,ruse + .set __decode_fail,1 + .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + .ifc \rsave,%r\r1 + .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + .ifc \rtarget,%r\r2 + .irp r3,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + .ifc \ruse,%r\r3 + \expand \r1,\r2,\r3 + .set __decode_fail,0 + .endif + .endr + .endif + .endr + .endif + .endr + .if __decode_fail == 1 + .error "__DECODE_RRR failed" + .endif + .endm + + .macro __DECODE_DRR expand,disp,reg,ruse + .set __decode_fail,1 + .irp r1,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + .ifc \reg,%r\r1 + .irp r2,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15 + .ifc \ruse,%r\r2 + \expand \disp,\r1,\r2 + .set __decode_fail,0 + .endif + .endr + .endif + .endr + .if __decode_fail == 1 + .error "__DECODE_DRR failed" + .endif + .endm + + .macro __THUNK_EX_BR reg,ruse + # Be very careful when adding instructions to this macro! + # The ALTERNATIVE replacement code has a .+10 which targets + # the "br \reg" after the code has been patched. +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + exrl 0,555f + j . +#else + .ifc \reg,%r1 + ALTERNATIVE "ex %r0,_LC_BR_R1", ".insn ril,0xc60000000000,0,.+10", 35 + j . + .else + larl \ruse,555f + ex 0,0(\ruse) + j . + .endif +#endif +555: br \reg + .endm + + .macro __THUNK_EX_BC disp,reg,ruse +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + exrl 0,556f + j . +#else + larl \ruse,556f + ex 0,0(\ruse) + j . +#endif +556: b \disp(\reg) + .endm + + .macro GEN_BR_THUNK reg,ruse=%r1 + __DECODE_RR __THUNK_PROLOG_BR,\reg,\ruse + __THUNK_EX_BR \reg,\ruse + __THUNK_EPILOG + .endm + + .macro GEN_B_THUNK disp,reg,ruse=%r1 + __DECODE_DRR __THUNK_PROLOG_BC,\disp,\reg,\ruse + __THUNK_EX_BC \disp,\reg,\ruse + __THUNK_EPILOG + .endm + + .macro BR_EX reg,ruse=%r1 +557: __DECODE_RR __THUNK_BR,\reg,\ruse + .pushsection .s390_indirect_branches,"a",@progbits + .long 557b-. + .popsection + .endm + + .macro B_EX disp,reg,ruse=%r1 +558: __DECODE_DRR __THUNK_BC,\disp,\reg,\ruse + .pushsection .s390_indirect_branches,"a",@progbits + .long 558b-. + .popsection + .endm + + .macro BASR_EX rsave,rtarget,ruse=%r1 +559: __DECODE_RRR __THUNK_BRASL,\rsave,\rtarget,\ruse + .pushsection .s390_indirect_branches,"a",@progbits + .long 559b-. + .popsection + .endm + +#else + .macro GEN_BR_THUNK reg,ruse=%r1 + .endm + + .macro GEN_B_THUNK disp,reg,ruse=%r1 + .endm + + .macro BR_EX reg,ruse=%r1 + br \reg + .endm + + .macro B_EX disp,reg,ruse=%r1 + b \disp(\reg) + .endm + + .macro BASR_EX rsave,rtarget,ruse=%r1 + basr \rsave,\rtarget + .endm +#endif + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_S390_NOSPEC_ASM_H */ diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h index e297bcfc476f..6090670df51f 100644 --- a/arch/s390/include/asm/purgatory.h +++ b/arch/s390/include/asm/purgatory.h @@ -13,5 +13,11 @@ int verify_sha256_digest(void); +extern u64 kernel_entry; +extern u64 kernel_type; + +extern u64 crash_start; +extern u64 crash_size; + #endif /* __ASSEMBLY__ */ #endif /* _S390_PURGATORY_H_ */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 84ea6225efb4..f92dd8ed3884 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -65,6 +65,7 @@ obj-y += nospec-branch.o extra-y += head.o head64.o vmlinux.lds +obj-$(CONFIG_SYSFS) += nospec-sysfs.o CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE) obj-$(CONFIG_MODULES) += module.o diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index eb2a5c0443cd..11aea745a2a6 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -181,6 +181,7 @@ int main(void) OFFSET(__LC_MACHINE_FLAGS, lowcore, machine_flags); OFFSET(__LC_PREEMPT_COUNT, lowcore, preempt_count); OFFSET(__LC_GMAP, lowcore, gmap); + OFFSET(__LC_BR_R1, lowcore, br_r1_trampoline); /* software defined ABI-relevant lowcore locations 0xe00 - 0xe20 */ OFFSET(__LC_DUMP_REIPL, lowcore, ipib); /* hardware defined lowcore locations 0x1000 - 0x18ff */ diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S index f6c56009e822..b65874b0b412 100644 --- a/arch/s390/kernel/base.S +++ b/arch/s390/kernel/base.S @@ -9,18 +9,22 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/nospec-insn.h> #include <asm/ptrace.h> #include <asm/sigp.h> + GEN_BR_THUNK %r9 + GEN_BR_THUNK %r14 + ENTRY(s390_base_mcck_handler) basr %r13,0 0: lg %r15,__LC_PANIC_STACK # load panic stack aghi %r15,-STACK_FRAME_OVERHEAD larl %r1,s390_base_mcck_handler_fn - lg %r1,0(%r1) - ltgr %r1,%r1 + lg %r9,0(%r1) + ltgr %r9,%r9 jz 1f - basr %r14,%r1 + BASR_EX %r14,%r9 1: la %r1,4095 lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1) lpswe __LC_MCK_OLD_PSW @@ -37,10 +41,10 @@ ENTRY(s390_base_ext_handler) basr %r13,0 0: aghi %r15,-STACK_FRAME_OVERHEAD larl %r1,s390_base_ext_handler_fn - lg %r1,0(%r1) - ltgr %r1,%r1 + lg %r9,0(%r1) + ltgr %r9,%r9 jz 1f - basr %r14,%r1 + BASR_EX %r14,%r9 1: lmg %r0,%r15,__LC_SAVE_AREA_ASYNC ni __LC_EXT_OLD_PSW+1,0xfd # clear wait state bit lpswe __LC_EXT_OLD_PSW @@ -57,10 +61,10 @@ ENTRY(s390_base_pgm_handler) basr %r13,0 0: aghi %r15,-STACK_FRAME_OVERHEAD larl %r1,s390_base_pgm_handler_fn - lg %r1,0(%r1) - ltgr %r1,%r1 + lg %r9,0(%r1) + ltgr %r9,%r9 jz 1f - basr %r14,%r1 + BASR_EX %r14,%r9 lmg %r0,%r15,__LC_SAVE_AREA_SYNC lpswe __LC_PGM_OLD_PSW 1: lpswe disabled_wait_psw-0b(%r13) @@ -117,7 +121,7 @@ ENTRY(diag308_reset) larl %r4,.Lcontinue_psw # Restore PSW flags lpswe 0(%r4) .Lcontinue: - br %r14 + BR_EX %r14 .align 16 .Lrestart_psw: .long 0x00080000,0x80000000 + .Lrestart_part2 diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 3f22f139a041..f03402efab4b 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -28,6 +28,7 @@ #include <asm/setup.h> #include <asm/nmi.h> #include <asm/export.h> +#include <asm/nospec-insn.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 8 @@ -183,67 +184,9 @@ _LPP_OFFSET = __LC_LPP "jnz .+8; .long 0xb2e8d000", 82 .endm -#ifdef CONFIG_EXPOLINE - - .macro GEN_BR_THUNK name,reg,tmp - .section .text.\name,"axG",@progbits,\name,comdat - .globl \name - .hidden \name - .type \name,@function -\name: - CFI_STARTPROC -#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES - exrl 0,0f -#else - larl \tmp,0f - ex 0,0(\tmp) -#endif - j . -0: br \reg - CFI_ENDPROC - .endm - - GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1 - GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1 - GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11 - - .macro BASR_R14_R9 -0: brasl %r14,__s390x_indirect_jump_r1use_r9 - .pushsection .s390_indirect_branches,"a",@progbits - .long 0b-. - .popsection - .endm - - .macro BR_R1USE_R14 -0: jg __s390x_indirect_jump_r1use_r14 - .pushsection .s390_indirect_branches,"a",@progbits - .long 0b-. - .popsection - .endm - - .macro BR_R11USE_R14 -0: jg __s390x_indirect_jump_r11use_r14 - .pushsection .s390_indirect_branches,"a",@progbits - .long 0b-. - .popsection - .endm - -#else /* CONFIG_EXPOLINE */ - - .macro BASR_R14_R9 - basr %r14,%r9 - .endm - - .macro BR_R1USE_R14 - br %r14 - .endm - - .macro BR_R11USE_R14 - br %r14 - .endm - -#endif /* CONFIG_EXPOLINE */ - + GEN_BR_THUNK %r9 + GEN_BR_THUNK %r14 + GEN_BR_THUNK %r14,%r11 .section .kprobes.text, "ax" .Ldummy: @@ -260,7 +203,7 @@ _LPP_OFFSET = __LC_LPP ENTRY(__bpon) .globl __bpon BPON - BR_R1USE_R14 + BR_EX %r14 /* * Scheduler resume function, called by switch_to @@ -284,7 +227,7 @@ ENTRY(__switch_to) mvc __LC_CURRENT_PID(4,%r0),0(%r3) # store pid of next lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40 - BR_R1USE_R14 + BR_EX %r14 .L__critical_start: @@ -351,7 +294,7 @@ sie_exit: xgr %r5,%r5 lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers lg %r2,__SF_SIE_REASON(%r15) # return exit reason code - BR_R1USE_R14 + BR_EX %r14 .Lsie_fault: lghi %r14,-EFAULT stg %r14,__SF_SIE_REASON(%r15) # set exit reason code @@ -410,7 +353,7 @@ ENTRY(system_call) lgf %r9,0(%r8,%r10) # get system call add. TSTMSK __TI_flags(%r12),_TIF_TRACE jnz .Lsysc_tracesys - BASR_R14_R9 # call sys_xxxx + BASR_EX %r14,%r9 # call sys_xxxx stg %r2,__PT_R2(%r11) # store return value .Lsysc_return: @@ -595,7 +538,7 @@ ENTRY(system_call) lmg %r3,%r7,__PT_R3(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lg %r2,__PT_ORIG_GPR2(%r11) - BASR_R14_R9 # call sys_xxx + BASR_EX %r14,%r9 # call sys_xxx stg %r2,__PT_R2(%r11) # store return value .Lsysc_tracenogo: TSTMSK __TI_flags(%r12),_TIF_TRACE @@ -619,7 +562,7 @@ ENTRY(ret_from_fork) lmg %r9,%r10,__PT_R9(%r11) # load gprs ENTRY(kernel_thread_starter) la %r2,0(%r10) - BASR_R14_R9 + BASR_EX %r14,%r9 j .Lsysc_tracenogo /* @@ -701,7 +644,7 @@ ENTRY(pgm_check_handler) je .Lpgm_return lgf %r9,0(%r10,%r1) # load address of handler routine lgr %r2,%r11 # pass pointer to pt_regs - BASR_R14_R9 # branch to interrupt-handler + BASR_EX %r14,%r9 # branch to interrupt-handler .Lpgm_return: LOCKDEP_SYS_EXIT tm __PT_PSW+1(%r11),0x01 # returning to user ? @@ -1019,7 +962,7 @@ ENTRY(psw_idle) stpt __TIMER_IDLE_ENTER(%r2) .Lpsw_idle_lpsw: lpswe __SF_EMPTY(%r15) - BR_R1USE_R14 + BR_EX %r14 .Lpsw_idle_end: /* @@ -1061,7 +1004,7 @@ ENTRY(save_fpu_regs) .Lsave_fpu_regs_done: oi __LC_CPU_FLAGS+7,_CIF_FPU .Lsave_fpu_regs_exit: - BR_R1USE_R14 + BR_EX %r14 .Lsave_fpu_regs_end: EXPORT_SYMBOL(save_fpu_regs) @@ -1107,7 +1050,7 @@ load_fpu_regs: .Lload_fpu_regs_done: ni __LC_CPU_FLAGS+7,255-_CIF_FPU .Lload_fpu_regs_exit: - BR_R1USE_R14 + BR_EX %r14 .Lload_fpu_regs_end: .L__critical_end: @@ -1322,7 +1265,7 @@ cleanup_critical: jl 0f clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end jl .Lcleanup_load_fpu_regs -0: BR_R11USE_R14 +0: BR_EX %r14 .align 8 .Lcleanup_table: @@ -1358,7 +1301,7 @@ cleanup_critical: ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce larl %r9,sie_exit # skip forward to sie_exit - BR_R11USE_R14 + BR_EX %r14 #endif .Lcleanup_system_call: @@ -1412,7 +1355,7 @@ cleanup_critical: stg %r15,56(%r11) # r15 stack pointer # set new psw address and exit larl %r9,.Lsysc_do_svc - BR_R11USE_R14 + BR_EX %r14,%r11 .Lcleanup_system_call_insn: .quad system_call .quad .Lsysc_stmg @@ -1424,7 +1367,7 @@ cleanup_critical: .Lcleanup_sysc_tif: larl %r9,.Lsysc_tif - BR_R11USE_R14 + BR_EX %r14,%r11 .Lcleanup_sysc_restore: # check if stpt has been executed @@ -1441,14 +1384,14 @@ cleanup_critical: mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) 1: lmg %r8,%r9,__LC_RETURN_PSW - BR_R11USE_R14 + BR_EX %r14,%r11 .Lcleanup_sysc_restore_insn: .quad .Lsysc_exit_timer .quad .Lsysc_done - 4 .Lcleanup_io_tif: larl %r9,.Lio_tif - BR_R11USE_R14 + BR_EX %r14,%r11 .Lcleanup_io_restore: # check if stpt has been executed @@ -1462,7 +1405,7 @@ cleanup_critical: mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) 1: lmg %r8,%r9,__LC_RETURN_PSW - BR_R11USE_R14 + BR_EX %r14,%r11 .Lcleanup_io_restore_insn: .quad .Lio_exit_timer .quad .Lio_done - 4 @@ -1515,17 +1458,17 @@ cleanup_critical: # prepare return psw nihh %r8,0xfcfd # clear irq & wait state bits lg %r9,48(%r11) # return from psw_idle - BR_R11USE_R14 + BR_EX %r14,%r11 .Lcleanup_idle_insn: .quad .Lpsw_idle_lpsw .Lcleanup_save_fpu_regs: larl %r9,save_fpu_regs - BR_R11USE_R14 + BR_EX %r14,%r11 .Lcleanup_load_fpu_regs: larl %r9,load_fpu_regs - BR_R11USE_R14 + BR_EX %r14,%r11 /* * Integer constants diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 94f2099bceb0..3d17c41074ca 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -176,10 +176,9 @@ void do_softirq_own_stack(void) new -= STACK_FRAME_OVERHEAD; ((struct stack_frame *) new)->back_chain = old; asm volatile(" la 15,0(%0)\n" - " basr 14,%2\n" + " brasl 14,__do_softirq\n" " la 15,0(%1)\n" - : : "a" (new), "a" (old), - "a" (__do_softirq) + : : "a" (new), "a" (old) : "0", "1", "2", "3", "4", "5", "14", "cc", "memory" ); } else { diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 82df7d80fab2..27110f3294ed 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -9,13 +9,17 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/ftrace.h> +#include <asm/nospec-insn.h> #include <asm/ptrace.h> #include <asm/export.h> + GEN_BR_THUNK %r1 + GEN_BR_THUNK %r14 + .section .kprobes.text, "ax" ENTRY(ftrace_stub) - br %r14 + BR_EX %r14 #define STACK_FRAME_SIZE (STACK_FRAME_OVERHEAD + __PT_SIZE) #define STACK_PTREGS (STACK_FRAME_OVERHEAD) @@ -23,7 +27,7 @@ ENTRY(ftrace_stub) #define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) ENTRY(_mcount) - br %r14 + BR_EX %r14 EXPORT_SYMBOL(_mcount) @@ -53,7 +57,7 @@ ENTRY(ftrace_caller) #endif lgr %r3,%r14 la %r5,STACK_PTREGS(%r15) - basr %r14,%r1 + BASR_EX %r14,%r1 #ifdef CONFIG_FUNCTION_GRAPH_TRACER # The j instruction gets runtime patched to a nop instruction. # See ftrace_enable_ftrace_graph_caller. @@ -68,7 +72,7 @@ ftrace_graph_caller_end: #endif lg %r1,(STACK_PTREGS_PSW+8)(%r15) lmg %r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15) - br %r1 + BR_EX %r1 #ifdef CONFIG_FUNCTION_GRAPH_TRACER @@ -81,6 +85,6 @@ ENTRY(return_to_handler) aghi %r15,STACK_FRAME_OVERHEAD lgr %r14,%r2 lmg %r2,%r5,32(%r15) - br %r14 + BR_EX %r14 #endif diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c index 46d49a11663f..8ad6a7128b3a 100644 --- a/arch/s390/kernel/nospec-branch.c +++ b/arch/s390/kernel/nospec-branch.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/module.h> #include <linux/device.h> -#include <linux/cpu.h> #include <asm/nospec-branch.h> static int __init nobp_setup_early(char *str) @@ -44,24 +43,6 @@ static int __init nospec_report(void) } arch_initcall(nospec_report); -#ifdef CONFIG_SYSFS -ssize_t cpu_show_spectre_v1(struct device *dev, - struct device_attribute *attr, char *buf) -{ - return sprintf(buf, "Mitigation: __user pointer sanitization\n"); -} - -ssize_t cpu_show_spectre_v2(struct device *dev, - struct device_attribute *attr, char *buf) -{ - if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) - return sprintf(buf, "Mitigation: execute trampolines\n"); - if (__test_facility(82, S390_lowcore.alt_stfle_fac_list)) - return sprintf(buf, "Mitigation: limited branch prediction.\n"); - return sprintf(buf, "Vulnerable\n"); -} -#endif - #ifdef CONFIG_EXPOLINE int nospec_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF); @@ -112,7 +93,6 @@ static void __init_or_module __nospec_revert(s32 *start, s32 *end) s32 *epo; /* Second part of the instruction replace is always a nop */ - memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4); for (epo = start; epo < end; epo++) { instr = (u8 *) epo + *epo; if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04) @@ -133,18 +113,34 @@ static void __init_or_module __nospec_revert(s32 *start, s32 *end) br = thunk + (*(int *)(thunk + 2)) * 2; else continue; - if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0) + /* Check for unconditional branch 0x07f? or 0x47f???? */ + if ((br[0] & 0xbf) != 0x07 || (br[1] & 0xf0) != 0xf0) continue; + + memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x07, 0x00 }, 4); switch (type) { case BRCL_EXPOLINE: - /* brcl to thunk, replace with br + nop */ insnbuf[0] = br[0]; insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f); + if (br[0] == 0x47) { + /* brcl to b, replace with bc + nopr */ + insnbuf[2] = br[2]; + insnbuf[3] = br[3]; + } else { + /* brcl to br, replace with bcr + nop */ + } break; case BRASL_EXPOLINE: - /* brasl to thunk, replace with basr + nop */ - insnbuf[0] = 0x0d; insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f); + if (br[0] == 0x47) { + /* brasl to b, replace with bas + nopr */ + insnbuf[0] = 0x4d; + insnbuf[2] = br[2]; + insnbuf[3] = br[3]; + } else { + /* brasl to br, replace with basr + nop */ + insnbuf[0] = 0x0d; + } break; } diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c new file mode 100644 index 000000000000..8affad5f18cb --- /dev/null +++ b/arch/s390/kernel/nospec-sysfs.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/device.h> +#include <linux/cpu.h> +#include <asm/facility.h> +#include <asm/nospec-branch.h> + +ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) + return sprintf(buf, "Mitigation: execute trampolines\n"); + if (__test_facility(82, S390_lowcore.alt_stfle_fac_list)) + return sprintf(buf, "Mitigation: limited branch prediction\n"); + return sprintf(buf, "Vulnerable\n"); +} diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 1c9ddd7aa5ec..0292d68e7dde 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -753,6 +753,10 @@ static int __hw_perf_event_init(struct perf_event *event) */ rate = 0; if (attr->freq) { + if (!attr->sample_freq) { + err = -EINVAL; + goto out; + } rate = freq_to_sample_rate(&si, attr->sample_freq); rate = hw_limit_rate(&si, rate); attr->freq = 0; diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S index 73cc3750f0d3..7f14adf512c6 100644 --- a/arch/s390/kernel/reipl.S +++ b/arch/s390/kernel/reipl.S @@ -7,8 +7,11 @@ #include <linux/linkage.h> #include <asm/asm-offsets.h> +#include <asm/nospec-insn.h> #include <asm/sigp.h> + GEN_BR_THUNK %r9 + # # Issue "store status" for the current CPU to its prefix page # and call passed function afterwards @@ -67,9 +70,9 @@ ENTRY(store_status) st %r4,0(%r1) st %r5,4(%r1) stg %r2,8(%r1) - lgr %r1,%r2 + lgr %r9,%r2 lgr %r2,%r3 - br %r1 + BR_EX %r9 .section .bss .align 8 diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S index e99187149f17..a049a7b9d6e8 100644 --- a/arch/s390/kernel/swsusp.S +++ b/arch/s390/kernel/swsusp.S @@ -13,6 +13,7 @@ #include <asm/ptrace.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> +#include <asm/nospec-insn.h> #include <asm/sigp.h> /* @@ -24,6 +25,8 @@ * (see below) in the resume process. * This function runs with disabled interrupts. */ + GEN_BR_THUNK %r14 + .section .text ENTRY(swsusp_arch_suspend) stmg %r6,%r15,__SF_GPRS(%r15) @@ -103,7 +106,7 @@ ENTRY(swsusp_arch_suspend) spx 0x318(%r1) lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) lghi %r2,0 - br %r14 + BR_EX %r14 /* * Restore saved memory image to correct place and restore register context. @@ -197,11 +200,10 @@ pgm_check_entry: larl %r15,init_thread_union ahi %r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER) larl %r2,.Lpanic_string - larl %r3,sclp_early_printk lghi %r1,0 sam31 sigp %r1,%r0,SIGP_SET_ARCHITECTURE - basr %r14,%r3 + brasl %r14,sclp_early_printk larl %r3,.Ldisabled_wait_31 lpsw 0(%r3) 4: @@ -267,7 +269,7 @@ restore_registers: /* Return 0 */ lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) lghi %r2,0 - br %r14 + BR_EX %r14 .section .data..nosave,"aw",@progbits .align 8 diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S index 495c9c4bacc7..2311f15be9cf 100644 --- a/arch/s390/lib/mem.S +++ b/arch/s390/lib/mem.S @@ -7,6 +7,9 @@ #include <linux/linkage.h> #include <asm/export.h> +#include <asm/nospec-insn.h> + + GEN_BR_THUNK %r14 /* * void *memmove(void *dest, const void *src, size_t n) @@ -33,14 +36,14 @@ ENTRY(memmove) .Lmemmove_forward_remainder: larl %r5,.Lmemmove_mvc ex %r4,0(%r5) - br %r14 + BR_EX %r14 .Lmemmove_reverse: ic %r0,0(%r4,%r3) stc %r0,0(%r4,%r1) brctg %r4,.Lmemmove_reverse ic %r0,0(%r4,%r3) stc %r0,0(%r4,%r1) - br %r14 + BR_EX %r14 .Lmemmove_mvc: mvc 0(1,%r1),0(%r3) EXPORT_SYMBOL(memmove) @@ -77,7 +80,7 @@ ENTRY(memset) .Lmemset_clear_remainder: larl %r3,.Lmemset_xc ex %r4,0(%r3) - br %r14 + BR_EX %r14 .Lmemset_fill: cghi %r4,1 lgr %r1,%r2 @@ -95,10 +98,10 @@ ENTRY(memset) stc %r3,0(%r1) larl %r5,.Lmemset_mvc ex %r4,0(%r5) - br %r14 + BR_EX %r14 .Lmemset_fill_exit: stc %r3,0(%r1) - br %r14 + BR_EX %r14 .Lmemset_xc: xc 0(1,%r1),0(%r1) .Lmemset_mvc: @@ -121,7 +124,7 @@ ENTRY(memcpy) .Lmemcpy_remainder: larl %r5,.Lmemcpy_mvc ex %r4,0(%r5) - br %r14 + BR_EX %r14 .Lmemcpy_loop: mvc 0(256,%r1),0(%r3) la %r1,256(%r1) @@ -159,10 +162,10 @@ ENTRY(__memset\bits) \insn %r3,0(%r1) larl %r5,.L__memset_mvc\bits ex %r4,0(%r5) - br %r14 + BR_EX %r14 .L__memset_exit\bits: \insn %r3,0(%r2) - br %r14 + BR_EX %r14 .L__memset_mvc\bits: mvc \bytes(1,%r1),0(%r1) .endm diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S index 25bb4643c4f4..9f794869c1b0 100644 --- a/arch/s390/net/bpf_jit.S +++ b/arch/s390/net/bpf_jit.S @@ -9,6 +9,7 @@ */ #include <linux/linkage.h> +#include <asm/nospec-insn.h> #include "bpf_jit.h" /* @@ -54,7 +55,7 @@ ENTRY(sk_load_##NAME##_pos); \ clg %r3,STK_OFF_HLEN(%r15); /* Offset + SIZE > hlen? */ \ jh sk_load_##NAME##_slow; \ LOAD %r14,-SIZE(%r3,%r12); /* Get data from skb */ \ - b OFF_OK(%r6); /* Return */ \ + B_EX OFF_OK,%r6; /* Return */ \ \ sk_load_##NAME##_slow:; \ lgr %r2,%r7; /* Arg1 = skb pointer */ \ @@ -64,11 +65,14 @@ sk_load_##NAME##_slow:; \ brasl %r14,skb_copy_bits; /* Get data from skb */ \ LOAD %r14,STK_OFF_TMP(%r15); /* Load from temp bufffer */ \ ltgr %r2,%r2; /* Set cc to (%r2 != 0) */ \ - br %r6; /* Return */ + BR_EX %r6; /* Return */ sk_load_common(word, 4, llgf) /* r14 = *(u32 *) (skb->data+offset) */ sk_load_common(half, 2, llgh) /* r14 = *(u16 *) (skb->data+offset) */ + GEN_BR_THUNK %r6 + GEN_B_THUNK OFF_OK,%r6 + /* * Load 1 byte from SKB (optimized version) */ @@ -80,7 +84,7 @@ ENTRY(sk_load_byte_pos) clg %r3,STK_OFF_HLEN(%r15) # Offset >= hlen? jnl sk_load_byte_slow llgc %r14,0(%r3,%r12) # Get byte from skb - b OFF_OK(%r6) # Return OK + B_EX OFF_OK,%r6 # Return OK sk_load_byte_slow: lgr %r2,%r7 # Arg1 = skb pointer @@ -90,7 +94,7 @@ sk_load_byte_slow: brasl %r14,skb_copy_bits # Get data from skb llgc %r14,STK_OFF_TMP(%r15) # Load result from temp buffer ltgr %r2,%r2 # Set cc to (%r2 != 0) - br %r6 # Return cc + BR_EX %r6 # Return cc #define sk_negative_common(NAME, SIZE, LOAD) \ sk_load_##NAME##_slow_neg:; \ @@ -104,7 +108,7 @@ sk_load_##NAME##_slow_neg:; \ jz bpf_error; \ LOAD %r14,0(%r2); /* Get data from pointer */ \ xr %r3,%r3; /* Set cc to zero */ \ - br %r6; /* Return cc */ + BR_EX %r6; /* Return cc */ sk_negative_common(word, 4, llgf) sk_negative_common(half, 2, llgh) @@ -113,4 +117,4 @@ sk_negative_common(byte, 1, llgc) bpf_error: # force a return 0 from jit handler ltgr %r15,%r15 # Set condition code - br %r6 + BR_EX %r6 diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 78a19c93b380..dd2bcf0e7d00 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -25,6 +25,8 @@ #include <linux/bpf.h> #include <asm/cacheflush.h> #include <asm/dis.h> +#include <asm/facility.h> +#include <asm/nospec-branch.h> #include <asm/set_memory.h> #include "bpf_jit.h" @@ -41,6 +43,8 @@ struct bpf_jit { int base_ip; /* Base address for literal pool */ int ret0_ip; /* Address of return 0 */ int exit_ip; /* Address of exit */ + int r1_thunk_ip; /* Address of expoline thunk for 'br %r1' */ + int r14_thunk_ip; /* Address of expoline thunk for 'br %r14' */ int tail_call_start; /* Tail call start offset */ int labels[1]; /* Labels for local jumps */ }; @@ -250,6 +254,19 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1) REG_SET_SEEN(b2); \ }) +#define EMIT6_PCREL_RILB(op, b, target) \ +({ \ + int rel = (target - jit->prg) / 2; \ + _EMIT6(op | reg_high(b) << 16 | rel >> 16, rel & 0xffff); \ + REG_SET_SEEN(b); \ +}) + +#define EMIT6_PCREL_RIL(op, target) \ +({ \ + int rel = (target - jit->prg) / 2; \ + _EMIT6(op | rel >> 16, rel & 0xffff); \ +}) + #define _EMIT6_IMM(op, imm) \ ({ \ unsigned int __imm = (imm); \ @@ -469,8 +486,45 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth) EMIT4(0xb9040000, REG_2, BPF_REG_0); /* Restore registers */ save_restore_regs(jit, REGS_RESTORE, stack_depth); + if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) { + jit->r14_thunk_ip = jit->prg; + /* Generate __s390_indirect_jump_r14 thunk */ + if (test_facility(35)) { + /* exrl %r0,.+10 */ + EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10); + } else { + /* larl %r1,.+14 */ + EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14); + /* ex 0,0(%r1) */ + EMIT4_DISP(0x44000000, REG_0, REG_1, 0); + } + /* j . */ + EMIT4_PCREL(0xa7f40000, 0); + } /* br %r14 */ _EMIT2(0x07fe); + + if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable && + (jit->seen & SEEN_FUNC)) { + jit->r1_thunk_ip = jit->prg; + /* Generate __s390_indirect_jump_r1 thunk */ + if (test_facility(35)) { + /* exrl %r0,.+10 */ + EMIT6_PCREL_RIL(0xc6000000, jit->prg + 10); + /* j . */ + EMIT4_PCREL(0xa7f40000, 0); + /* br %r1 */ + _EMIT2(0x07f1); + } else { + /* larl %r1,.+14 */ + EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14); + /* ex 0,S390_lowcore.br_r1_tampoline */ + EMIT4_DISP(0x44000000, REG_0, REG_0, + offsetof(struct lowcore, br_r1_trampoline)); + /* j . */ + EMIT4_PCREL(0xa7f40000, 0); + } + } } /* @@ -966,8 +1020,13 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i /* lg %w1,<d(imm)>(%l) */ EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L, EMIT_CONST_U64(func)); - /* basr %r14,%w1 */ - EMIT2(0x0d00, REG_14, REG_W1); + if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) { + /* brasl %r14,__s390_indirect_jump_r1 */ + EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip); + } else { + /* basr %r14,%w1 */ + EMIT2(0x0d00, REG_14, REG_W1); + } /* lgr %b0,%r2: load return value into %b0 */ EMIT4(0xb9040000, BPF_REG_0, REG_2); if ((jit->seen & SEEN_SKB) && diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 97fe29316476..1851eaeee131 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -9,6 +9,7 @@ config SUPERH select HAVE_IDE if HAS_IOPORT_MAP select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP + select NO_BOOTMEM select ARCH_DISCARD_MEMBLOCK select HAVE_OPROFILE select HAVE_GENERIC_DMA_COHERENT diff --git a/arch/sh/kernel/cpu/sh2/probe.c b/arch/sh/kernel/cpu/sh2/probe.c index 4205f6d42b69..a5bd03642678 100644 --- a/arch/sh/kernel/cpu/sh2/probe.c +++ b/arch/sh/kernel/cpu/sh2/probe.c @@ -43,7 +43,11 @@ void __ref cpu_probe(void) #endif #if defined(CONFIG_CPU_J2) +#if defined(CONFIG_SMP) unsigned cpu = hard_smp_processor_id(); +#else + unsigned cpu = 0; +#endif if (cpu == 0) of_scan_flat_dt(scan_cache, NULL); if (j2_ccr_base) __raw_writel(0x80000303, j2_ccr_base + 4*cpu); if (cpu != 0) return; diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index d34e998b809f..c286cf5da6e7 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -11,7 +11,6 @@ #include <linux/ioport.h> #include <linux/init.h> #include <linux/initrd.h> -#include <linux/bootmem.h> #include <linux/console.h> #include <linux/root_dev.h> #include <linux/utsname.h> diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c index 8ce98691d822..f1b44697ad68 100644 --- a/arch/sh/mm/consistent.c +++ b/arch/sh/mm/consistent.c @@ -59,7 +59,9 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order); - *dma_handle = virt_to_phys(ret) - PFN_PHYS(dev->dma_pfn_offset); + *dma_handle = virt_to_phys(ret); + if (!WARN_ON(!dev)) + *dma_handle -= PFN_PHYS(dev->dma_pfn_offset); return ret_nocache; } @@ -69,9 +71,12 @@ void dma_generic_free_coherent(struct device *dev, size_t size, unsigned long attrs) { int order = get_order(size); - unsigned long pfn = (dma_handle >> PAGE_SHIFT) + dev->dma_pfn_offset; + unsigned long pfn = dma_handle >> PAGE_SHIFT; int k; + if (!WARN_ON(!dev)) + pfn += dev->dma_pfn_offset; + for (k = 0; k < (1 << order); k++) __free_pages(pfn_to_page(pfn + k), 0); @@ -143,7 +148,7 @@ int __init platform_resource_setup_memory(struct platform_device *pdev, if (!memsize) return 0; - buf = dma_alloc_coherent(NULL, memsize, &dma_handle, GFP_KERNEL); + buf = dma_alloc_coherent(&pdev->dev, memsize, &dma_handle, GFP_KERNEL); if (!buf) { pr_warning("%s: unable to allocate memory\n", name); return -ENOMEM; diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index ce0bbaa7e404..4034035fbede 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -211,59 +211,15 @@ void __init allocate_pgdat(unsigned int nid) NODE_DATA(nid) = __va(phys); memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - - NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; #endif NODE_DATA(nid)->node_start_pfn = start_pfn; NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; } -static void __init bootmem_init_one_node(unsigned int nid) -{ - unsigned long total_pages, paddr; - unsigned long end_pfn; - struct pglist_data *p; - - p = NODE_DATA(nid); - - /* Nothing to do.. */ - if (!p->node_spanned_pages) - return; - - end_pfn = pgdat_end_pfn(p); - - total_pages = bootmem_bootmap_pages(p->node_spanned_pages); - - paddr = memblock_alloc(total_pages << PAGE_SHIFT, PAGE_SIZE); - if (!paddr) - panic("Can't allocate bootmap for nid[%d]\n", nid); - - init_bootmem_node(p, paddr >> PAGE_SHIFT, p->node_start_pfn, end_pfn); - - free_bootmem_with_active_regions(nid, end_pfn); - - /* - * XXX Handle initial reservations for the system memory node - * only for the moment, we'll refactor this later for handling - * reservations in other nodes. - */ - if (nid == 0) { - struct memblock_region *reg; - - /* Reserve the sections we're already using. */ - for_each_memblock(reserved, reg) { - reserve_bootmem(reg->base, reg->size, BOOTMEM_DEFAULT); - } - } - - sparse_memory_present_with_active_regions(nid); -} - static void __init do_init_bootmem(void) { struct memblock_region *reg; - int i; /* Add active regions with valid PFNs. */ for_each_memblock(memory, reg) { @@ -279,9 +235,12 @@ static void __init do_init_bootmem(void) plat_mem_setup(); - for_each_online_node(i) - bootmem_init_one_node(i); + for_each_memblock(memory, reg) { + int nid = memblock_get_region_node(reg); + memory_present(nid, memblock_region_memory_base_pfn(reg), + memblock_region_memory_end_pfn(reg)); + } sparse_init(); } @@ -322,7 +281,6 @@ void __init paging_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; unsigned long vaddr, end; - int nid; sh_mv.mv_mem_init(); @@ -377,21 +335,7 @@ void __init paging_init(void) kmap_coherent_init(); memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); - - for_each_online_node(nid) { - pg_data_t *pgdat = NODE_DATA(nid); - unsigned long low, start_pfn; - - start_pfn = pgdat->bdata->node_min_pfn; - low = pgdat->bdata->node_low_pfn; - - if (max_zone_pfns[ZONE_NORMAL] < low) - max_zone_pfns[ZONE_NORMAL] = low; - - printk("Node %u: start_pfn = 0x%lx, low = 0x%lx\n", - nid, start_pfn, low); - } - + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; free_area_init_nodes(max_zone_pfns); } diff --git a/arch/sh/mm/numa.c b/arch/sh/mm/numa.c index 05713d190247..830e8b3684e4 100644 --- a/arch/sh/mm/numa.c +++ b/arch/sh/mm/numa.c @@ -8,7 +8,6 @@ * for more details. */ #include <linux/module.h> -#include <linux/bootmem.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/numa.h> @@ -26,9 +25,7 @@ EXPORT_SYMBOL_GPL(node_data); */ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end) { - unsigned long bootmap_pages; unsigned long start_pfn, end_pfn; - unsigned long bootmem_paddr; /* Don't allow bogus node assignment */ BUG_ON(nid >= MAX_NUMNODES || nid <= 0); @@ -48,25 +45,9 @@ void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end) SMP_CACHE_BYTES, end)); memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; NODE_DATA(nid)->node_start_pfn = start_pfn; NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn; - /* Node-local bootmap */ - bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn); - bootmem_paddr = memblock_alloc_base(bootmap_pages << PAGE_SHIFT, - PAGE_SIZE, end); - init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT, - start_pfn, end_pfn); - - free_bootmem_with_active_regions(nid, end_pfn); - - /* Reserve the pgdat and bootmap space with the bootmem allocator */ - reserve_bootmem_node(NODE_DATA(nid), start_pfn << PAGE_SHIFT, - sizeof(struct pglist_data), BOOTMEM_DEFAULT); - reserve_bootmem_node(NODE_DATA(nid), bootmem_paddr, - bootmap_pages << PAGE_SHIFT, BOOTMEM_DEFAULT); - /* It's up */ node_set_online(nid); diff --git a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c b/arch/x86/entry/vdso/vdso32/vdso-fakesections.c deleted file mode 100644 index 541468e25265..000000000000 --- a/arch/x86/entry/vdso/vdso32/vdso-fakesections.c +++ /dev/null @@ -1 +0,0 @@ -#include "../vdso-fakesections.c" diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index a6006e7bb729..45b2b1c93d04 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -27,6 +27,7 @@ #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/device.h> +#include <linux/nospec.h> #include <asm/apic.h> #include <asm/stacktrace.h> @@ -304,17 +305,20 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event *event) config = attr->config; - cache_type = (config >> 0) & 0xff; + cache_type = (config >> 0) & 0xff; if (cache_type >= PERF_COUNT_HW_CACHE_MAX) return -EINVAL; + cache_type = array_index_nospec(cache_type, PERF_COUNT_HW_CACHE_MAX); cache_op = (config >> 8) & 0xff; if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX) return -EINVAL; + cache_op = array_index_nospec(cache_op, PERF_COUNT_HW_CACHE_OP_MAX); cache_result = (config >> 16) & 0xff; if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) return -EINVAL; + cache_result = array_index_nospec(cache_result, PERF_COUNT_HW_CACHE_RESULT_MAX); val = hw_cache_event_ids[cache_type][cache_op][cache_result]; @@ -421,6 +425,8 @@ int x86_setup_perfctr(struct perf_event *event) if (attr->config >= x86_pmu.max_events) return -EINVAL; + attr->config = array_index_nospec((unsigned long)attr->config, x86_pmu.max_events); + /* * The generic map: */ diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 9aca448bb8e6..9f8084f18d58 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -92,6 +92,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include "../perf_event.h" @@ -302,6 +303,7 @@ static int cstate_pmu_event_init(struct perf_event *event) } else if (event->pmu == &cstate_pkg_pmu) { if (cfg >= PERF_CSTATE_PKG_EVENT_MAX) return -EINVAL; + cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX); if (!pkg_msr[cfg].attr) return -EINVAL; event->hw.event_base = pkg_msr[cfg].msr; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index e7edf19e64c2..b4771a6ddbc1 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/intel-family.h> enum perf_msr_id { @@ -158,9 +159,6 @@ static int msr_event_init(struct perf_event *event) if (event->attr.type != event->pmu->type) return -ENOENT; - if (cfg >= PERF_MSR_EVENT_MAX) - return -EINVAL; - /* unsupported modes and filters */ if (event->attr.exclude_user || event->attr.exclude_kernel || @@ -171,6 +169,11 @@ static int msr_event_init(struct perf_event *event) event->attr.sample_period) /* no sampling */ return -EINVAL; + if (cfg >= PERF_MSR_EVENT_MAX) + return -EINVAL; + + cfg = array_index_nospec((unsigned long)cfg, PERF_MSR_EVENT_MAX); + if (!msr[cfg].attr) return -EINVAL; diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile index 367a8203cfcf..b173d404e3df 100644 --- a/arch/x86/hyperv/Makefile +++ b/arch/x86/hyperv/Makefile @@ -1 +1,2 @@ -obj-y := hv_init.o mmu.o +obj-y := hv_init.o mmu.o +obj-$(CONFIG_X86_64) += hv_apic.o diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c new file mode 100644 index 000000000000..f68855499391 --- /dev/null +++ b/arch/x86/hyperv/hv_apic.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Hyper-V specific APIC code. + * + * Copyright (C) 2018, Microsoft, Inc. + * + * Author : K. Y. Srinivasan <kys@microsoft.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for more + * details. + * + */ + +#include <linux/types.h> +#include <linux/version.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> +#include <linux/clockchips.h> +#include <linux/hyperv.h> +#include <linux/slab.h> +#include <linux/cpuhotplug.h> +#include <asm/hypervisor.h> +#include <asm/mshyperv.h> +#include <asm/apic.h> + +static struct apic orig_apic; + +static u64 hv_apic_icr_read(void) +{ + u64 reg_val; + + rdmsrl(HV_X64_MSR_ICR, reg_val); + return reg_val; +} + +static void hv_apic_icr_write(u32 low, u32 id) +{ + u64 reg_val; + + reg_val = SET_APIC_DEST_FIELD(id); + reg_val = reg_val << 32; + reg_val |= low; + + wrmsrl(HV_X64_MSR_ICR, reg_val); +} + +static u32 hv_apic_read(u32 reg) +{ + u32 reg_val, hi; + + switch (reg) { + case APIC_EOI: + rdmsr(HV_X64_MSR_EOI, reg_val, hi); + return reg_val; + case APIC_TASKPRI: + rdmsr(HV_X64_MSR_TPR, reg_val, hi); + return reg_val; + + default: + return native_apic_mem_read(reg); + } +} + +static void hv_apic_write(u32 reg, u32 val) +{ + switch (reg) { + case APIC_EOI: + wrmsr(HV_X64_MSR_EOI, val, 0); + break; + case APIC_TASKPRI: + wrmsr(HV_X64_MSR_TPR, val, 0); + break; + default: + native_apic_mem_write(reg, val); + } +} + +static void hv_apic_eoi_write(u32 reg, u32 val) +{ + wrmsr(HV_X64_MSR_EOI, val, 0); +} + +/* + * IPI implementation on Hyper-V. + */ +static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector) +{ + struct ipi_arg_ex **arg; + struct ipi_arg_ex *ipi_arg; + unsigned long flags; + int nr_bank = 0; + int ret = 1; + + local_irq_save(flags); + arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); + + ipi_arg = *arg; + if (unlikely(!ipi_arg)) + goto ipi_mask_ex_done; + + ipi_arg->vector = vector; + ipi_arg->reserved = 0; + ipi_arg->vp_set.valid_bank_mask = 0; + + if (!cpumask_equal(mask, cpu_present_mask)) { + ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; + nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask); + } + if (!nr_bank) + ipi_arg->vp_set.format = HV_GENERIC_SET_ALL; + + ret = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank, + ipi_arg, NULL); + +ipi_mask_ex_done: + local_irq_restore(flags); + return ((ret == 0) ? true : false); +} + +static bool __send_ipi_mask(const struct cpumask *mask, int vector) +{ + int cur_cpu, vcpu; + struct ipi_arg_non_ex **arg; + struct ipi_arg_non_ex *ipi_arg; + int ret = 1; + unsigned long flags; + + if (cpumask_empty(mask)) + return true; + + if (!hv_hypercall_pg) + return false; + + if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + return false; + + if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + return __send_ipi_mask_ex(mask, vector); + + local_irq_save(flags); + arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg); + + ipi_arg = *arg; + if (unlikely(!ipi_arg)) + goto ipi_mask_done; + + ipi_arg->vector = vector; + ipi_arg->reserved = 0; + ipi_arg->cpu_mask = 0; + + for_each_cpu(cur_cpu, mask) { + vcpu = hv_cpu_number_to_vp_number(cur_cpu); + /* + * This particular version of the IPI hypercall can + * only target upto 64 CPUs. + */ + if (vcpu >= 64) + goto ipi_mask_done; + + __set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask); + } + + ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL); + +ipi_mask_done: + local_irq_restore(flags); + return ((ret == 0) ? true : false); +} + +static bool __send_ipi_one(int cpu, int vector) +{ + struct cpumask mask = CPU_MASK_NONE; + + cpumask_set_cpu(cpu, &mask); + return __send_ipi_mask(&mask, vector); +} + +static void hv_send_ipi(int cpu, int vector) +{ + if (!__send_ipi_one(cpu, vector)) + orig_apic.send_IPI(cpu, vector); +} + +static void hv_send_ipi_mask(const struct cpumask *mask, int vector) +{ + if (!__send_ipi_mask(mask, vector)) + orig_apic.send_IPI_mask(mask, vector); +} + +static void hv_send_ipi_mask_allbutself(const struct cpumask *mask, int vector) +{ + unsigned int this_cpu = smp_processor_id(); + struct cpumask new_mask; + const struct cpumask *local_mask; + + cpumask_copy(&new_mask, mask); + cpumask_clear_cpu(this_cpu, &new_mask); + local_mask = &new_mask; + if (!__send_ipi_mask(local_mask, vector)) + orig_apic.send_IPI_mask_allbutself(mask, vector); +} + +static void hv_send_ipi_allbutself(int vector) +{ + hv_send_ipi_mask_allbutself(cpu_online_mask, vector); +} + +static void hv_send_ipi_all(int vector) +{ + if (!__send_ipi_mask(cpu_online_mask, vector)) + orig_apic.send_IPI_all(vector); +} + +static void hv_send_ipi_self(int vector) +{ + if (!__send_ipi_one(smp_processor_id(), vector)) + orig_apic.send_IPI_self(vector); +} + +void __init hv_apic_init(void) +{ + if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) { + if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) + pr_info("Hyper-V: Using ext hypercalls for IPI\n"); + else + pr_info("Hyper-V: Using IPI hypercalls\n"); + /* + * Set the IPI entry points. + */ + orig_apic = *apic; + + apic->send_IPI = hv_send_ipi; + apic->send_IPI_mask = hv_send_ipi_mask; + apic->send_IPI_mask_allbutself = hv_send_ipi_mask_allbutself; + apic->send_IPI_allbutself = hv_send_ipi_allbutself; + apic->send_IPI_all = hv_send_ipi_all; + apic->send_IPI_self = hv_send_ipi_self; + } + + if (ms_hyperv.hints & HV_X64_APIC_ACCESS_RECOMMENDED) { + pr_info("Hyper-V: Using MSR based APIC access\n"); + apic_set_eoi_write(hv_apic_eoi_write); + apic->read = hv_apic_read; + apic->write = hv_apic_write; + apic->icr_write = hv_apic_icr_write; + apic->icr_read = hv_apic_icr_read; + } +} diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index cfecc2272f2d..4c431e1c1eff 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -91,12 +91,19 @@ EXPORT_SYMBOL_GPL(hv_vp_index); struct hv_vp_assist_page **hv_vp_assist_page; EXPORT_SYMBOL_GPL(hv_vp_assist_page); +void __percpu **hyperv_pcpu_input_arg; +EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg); + u32 hv_max_vp_index; static int hv_cpu_init(unsigned int cpu) { u64 msr_vp_index; struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; + void **input_arg; + + input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); + *input_arg = page_address(alloc_page(GFP_KERNEL)); hv_get_vp_index(msr_vp_index); @@ -217,6 +224,16 @@ static int hv_cpu_die(unsigned int cpu) { struct hv_reenlightenment_control re_ctrl; unsigned int new_cpu; + unsigned long flags; + void **input_arg; + void *input_pg = NULL; + + local_irq_save(flags); + input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg); + input_pg = *input_arg; + *input_arg = NULL; + local_irq_restore(flags); + free_page((unsigned long)input_pg); if (hv_vp_assist_page && hv_vp_assist_page[cpu]) wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0); @@ -242,8 +259,9 @@ static int hv_cpu_die(unsigned int cpu) * * 1. Setup the hypercall page. * 2. Register Hyper-V specific clocksource. + * 3. Setup Hyper-V specific APIC entry points. */ -void hyperv_init(void) +void __init hyperv_init(void) { u64 guest_id, required_msrs; union hv_x64_msr_hypercall_contents hypercall_msr; @@ -259,6 +277,16 @@ void hyperv_init(void) if ((ms_hyperv.features & required_msrs) != required_msrs) return; + /* + * Allocate the per-CPU state for the hypercall input arg. + * If this allocation fails, we will not be able to setup + * (per-CPU) hypercall input page and thus this failure is + * fatal on Hyper-V. + */ + hyperv_pcpu_input_arg = alloc_percpu(void *); + + BUG_ON(hyperv_pcpu_input_arg == NULL); + /* Allocate percpu VP index */ hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index), GFP_KERNEL); @@ -296,7 +324,7 @@ void hyperv_init(void) hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); - hyper_alloc_mmu(); + hv_apic_init(); /* * Register Hyper-V specific clocksource. diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 56c9ebac946f..de27615c51ea 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -13,32 +13,9 @@ #define CREATE_TRACE_POINTS #include <asm/trace/hyperv.h> -/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ -struct hv_flush_pcpu { - u64 address_space; - u64 flags; - u64 processor_mask; - u64 gva_list[]; -}; - -/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ -struct hv_flush_pcpu_ex { - u64 address_space; - u64 flags; - struct { - u64 format; - u64 valid_bank_mask; - u64 bank_contents[]; - } hv_vp_set; - u64 gva_list[]; -}; - /* Each gva in gva_list encodes up to 4096 pages to flush */ #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE) -static struct hv_flush_pcpu __percpu **pcpu_flush; - -static struct hv_flush_pcpu_ex __percpu **pcpu_flush_ex; /* * Fills in gva_list starting from offset. Returns the number of items added. @@ -70,53 +47,18 @@ static inline int fill_gva_list(u64 gva_list[], int offset, return gva_n - offset; } -/* Return the number of banks in the resulting vp_set */ -static inline int cpumask_to_vp_set(struct hv_flush_pcpu_ex *flush, - const struct cpumask *cpus) -{ - int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; - - /* valid_bank_mask can represent up to 64 banks */ - if (hv_max_vp_index / 64 >= 64) - return 0; - - /* - * Clear all banks up to the maximum possible bank as hv_flush_pcpu_ex - * structs are not cleared between calls, we risk flushing unneeded - * vCPUs otherwise. - */ - for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) - flush->hv_vp_set.bank_contents[vcpu_bank] = 0; - - /* - * Some banks may end up being empty but this is acceptable. - */ - for_each_cpu(cpu, cpus) { - vcpu = hv_cpu_number_to_vp_number(cpu); - vcpu_bank = vcpu / 64; - vcpu_offset = vcpu % 64; - __set_bit(vcpu_offset, (unsigned long *) - &flush->hv_vp_set.bank_contents[vcpu_bank]); - if (vcpu_bank >= nr_bank) - nr_bank = vcpu_bank + 1; - } - flush->hv_vp_set.valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0); - - return nr_bank; -} - static void hyperv_flush_tlb_others(const struct cpumask *cpus, const struct flush_tlb_info *info) { int cpu, vcpu, gva_n, max_gvas; - struct hv_flush_pcpu **flush_pcpu; - struct hv_flush_pcpu *flush; + struct hv_tlb_flush **flush_pcpu; + struct hv_tlb_flush *flush; u64 status = U64_MAX; unsigned long flags; trace_hyperv_mmu_flush_tlb_others(cpus, info); - if (!pcpu_flush || !hv_hypercall_pg) + if (!hv_hypercall_pg) goto do_native; if (cpumask_empty(cpus)) @@ -124,10 +66,8 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, local_irq_save(flags); - flush_pcpu = this_cpu_ptr(pcpu_flush); - - if (unlikely(!*flush_pcpu)) - *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + flush_pcpu = (struct hv_tlb_flush **) + this_cpu_ptr(hyperv_pcpu_input_arg); flush = *flush_pcpu; @@ -196,14 +136,14 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, const struct flush_tlb_info *info) { int nr_bank = 0, max_gvas, gva_n; - struct hv_flush_pcpu_ex **flush_pcpu; - struct hv_flush_pcpu_ex *flush; + struct hv_tlb_flush_ex **flush_pcpu; + struct hv_tlb_flush_ex *flush; u64 status = U64_MAX; unsigned long flags; trace_hyperv_mmu_flush_tlb_others(cpus, info); - if (!pcpu_flush_ex || !hv_hypercall_pg) + if (!hv_hypercall_pg) goto do_native; if (cpumask_empty(cpus)) @@ -211,10 +151,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, local_irq_save(flags); - flush_pcpu = this_cpu_ptr(pcpu_flush_ex); - - if (unlikely(!*flush_pcpu)) - *flush_pcpu = page_address(alloc_page(GFP_ATOMIC)); + flush_pcpu = (struct hv_tlb_flush_ex **) + this_cpu_ptr(hyperv_pcpu_input_arg); flush = *flush_pcpu; @@ -239,8 +177,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus, flush->hv_vp_set.valid_bank_mask = 0; if (!cpumask_equal(cpus, cpu_present_mask)) { - flush->hv_vp_set.format = HV_GENERIC_SET_SPARCE_4K; - nr_bank = cpumask_to_vp_set(flush, cpus); + flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K; + nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus); } if (!nr_bank) { @@ -296,14 +234,3 @@ void hyperv_setup_mmu_ops(void) pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex; } } - -void hyper_alloc_mmu(void) -{ - if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED)) - return; - - if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) - pcpu_flush = alloc_percpu(struct hv_flush_pcpu *); - else - pcpu_flush_ex = alloc_percpu(struct hv_flush_pcpu_ex *); -} diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 416cb0e0c496..b8c89265baf0 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -164,6 +164,11 @@ */ #define HV_X64_DEPRECATING_AEOI_RECOMMENDED (1 << 9) +/* + * Recommend using cluster IPI hypercalls. + */ +#define HV_X64_CLUSTER_IPI_RECOMMENDED (1 << 10) + /* Recommend using the newer ExProcessorMasks interface */ #define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED (1 << 11) @@ -303,6 +308,9 @@ struct ms_hyperv_tsc_page { /* TSC emulation after migration */ #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 +/* Nested features (CPUID 0x4000000A) EAX */ +#define HV_X64_NESTED_MSR_BITMAP BIT(19) + struct hv_reenlightenment_control { __u64 vector:8; __u64 reserved1:8; @@ -329,12 +337,17 @@ struct hv_tsc_emulation_status { #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) +#define HV_IPI_LOW_VECTOR 0x10 +#define HV_IPI_HIGH_VECTOR 0xff + /* Declare the various hypercall operations. */ #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST 0x0003 #define HVCALL_NOTIFY_LONG_SPIN_WAIT 0x0008 +#define HVCALL_SEND_IPI 0x000b #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX 0x0013 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX 0x0014 +#define HVCALL_SEND_IPI_EX 0x0015 #define HVCALL_POST_MESSAGE 0x005c #define HVCALL_SIGNAL_EVENT 0x005d @@ -360,7 +373,7 @@ struct hv_tsc_emulation_status { #define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3) enum HV_GENERIC_SET_FORMAT { - HV_GENERIC_SET_SPARCE_4K, + HV_GENERIC_SET_SPARSE_4K, HV_GENERIC_SET_ALL, }; @@ -668,7 +681,11 @@ struct hv_enlightened_vmcs { u32 hv_clean_fields; u32 hv_padding_32; u32 hv_synthetic_controls; - u32 hv_enlightenments_control; + struct { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 reserved:30; + } hv_enlightenments_control; u32 hv_vp_id; u64 hv_vm_id; @@ -706,4 +723,38 @@ struct hv_enlightened_vmcs { #define HV_STIMER_AUTOENABLE (1ULL << 3) #define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) +struct ipi_arg_non_ex { + u32 vector; + u32 reserved; + u64 cpu_mask; +}; + +struct hv_vpset { + u64 format; + u64 valid_bank_mask; + u64 bank_contents[]; +}; + +struct ipi_arg_ex { + u32 vector; + u32 reserved; + struct hv_vpset vp_set; +}; + +/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ +struct hv_tlb_flush { + u64 address_space; + u64 flags; + u64 processor_mask; + u64 gva_list[]; +}; + +/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ +struct hv_tlb_flush_ex { + u64 address_space; + u64 flags; + struct hv_vpset hv_vp_set; + u64 gva_list[]; +}; + #endif diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c25775fad4ed..0ebe659f2802 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -258,7 +258,8 @@ union kvm_mmu_page_role { unsigned smep_andnot_wp:1; unsigned smap_andnot_wp:1; unsigned ad_disabled:1; - unsigned :7; + unsigned guest_mode:1; + unsigned :6; /* * This is left at the top of the word so that @@ -476,6 +477,7 @@ struct kvm_vcpu_hv { struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); + cpumask_t tlb_lush; }; struct kvm_vcpu_arch { @@ -995,7 +997,7 @@ struct kvm_x86_ops { void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); - void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); + void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); @@ -1277,6 +1279,7 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu); +void kvm_mmu_free_roots(struct kvm_vcpu *vcpu); gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index b90e79610cf7..3cd14311edfa 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -122,6 +122,7 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) extern struct clocksource *hyperv_cs; extern void *hv_hypercall_pg; +extern void __percpu **hyperv_pcpu_input_arg; static inline u64 hv_do_hypercall(u64 control, void *input, void *output) { @@ -258,9 +259,41 @@ static inline int hv_cpu_number_to_vp_number(int cpu_number) return hv_vp_index[cpu_number]; } -void hyperv_init(void); +static inline int cpumask_to_vpset(struct hv_vpset *vpset, + const struct cpumask *cpus) +{ + int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1; + + /* valid_bank_mask can represent up to 64 banks */ + if (hv_max_vp_index / 64 >= 64) + return 0; + + /* + * Clear all banks up to the maximum possible bank as hv_tlb_flush_ex + * structs are not cleared between calls, we risk flushing unneeded + * vCPUs otherwise. + */ + for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++) + vpset->bank_contents[vcpu_bank] = 0; + + /* + * Some banks may end up being empty but this is acceptable. + */ + for_each_cpu(cpu, cpus) { + vcpu = hv_cpu_number_to_vp_number(cpu); + vcpu_bank = vcpu / 64; + vcpu_offset = vcpu % 64; + __set_bit(vcpu_offset, (unsigned long *) + &vpset->bank_contents[vcpu_bank]); + if (vcpu_bank >= nr_bank) + nr_bank = vcpu_bank + 1; + } + vpset->valid_bank_mask = GENMASK_ULL(nr_bank - 1, 0); + return nr_bank; +} + +void __init hyperv_init(void); void hyperv_setup_mmu_ops(void); -void hyper_alloc_mmu(void); void hyperv_report_panic(struct pt_regs *regs, long err); bool hv_is_hyperv_initialized(void); void hyperv_cleanup(void); @@ -269,6 +302,13 @@ void hyperv_reenlightenment_intr(struct pt_regs *regs); void set_hv_tscchange_cb(void (*cb)(void)); void clear_hv_tscchange_cb(void); void hyperv_stop_tsc_emulation(void); + +#ifdef CONFIG_X86_64 +void hv_apic_init(void); +#else +static inline void hv_apic_init(void) {} +#endif + #else /* CONFIG_HYPERV */ static inline void hyperv_init(void) {} static inline bool hv_is_hyperv_initialized(void) { return false; } diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 5db8b0b10766..425e6b8b9547 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -207,7 +207,9 @@ enum vmcs_field { EPTP_LIST_ADDRESS = 0x00002024, EPTP_LIST_ADDRESS_HIGH = 0x00002025, VMREAD_BITMAP = 0x00002026, + VMREAD_BITMAP_HIGH = 0x00002027, VMWRITE_BITMAP = 0x00002028, + VMWRITE_BITMAP_HIGH = 0x00002029, XSS_EXIT_BITMAP = 0x0000202C, XSS_EXIT_BITMAP_HIGH = 0x0000202D, TSC_MULTIPLIER = 0x00002032, diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 4c851ebb3ceb..0ede697c3961 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -29,7 +29,7 @@ #define KVM_FEATURE_PV_TLB_FLUSH 9 #define KVM_FEATURE_ASYNC_PF_VMEXIT 10 -#define KVM_HINTS_DEDICATED 0 +#define KVM_HINTS_REALTIME 0 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index c88e0b127810..b481b95bd8f6 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -14,8 +14,11 @@ #include <asm/amd_nb.h> #define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 +#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec /* Protect the PCI config register pairs used for SMN and DF indirect access. */ static DEFINE_MUTEX(smn_mutex); @@ -24,6 +27,7 @@ static u32 *flush_words; static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, {} }; @@ -39,6 +43,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, {} }; @@ -51,6 +56,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, {} }; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 7867417cfaff..5b2300b818af 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -457,7 +457,7 @@ static void __init sev_map_percpu_data(void) static void __init kvm_smp_prepare_cpus(unsigned int max_cpus) { native_smp_prepare_cpus(max_cpus); - if (kvm_para_has_hint(KVM_HINTS_DEDICATED)) + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) static_branch_disable(&virt_spin_lock_key); } @@ -553,7 +553,7 @@ static void __init kvm_guest_init(void) } if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_DEDICATED) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) pv_mmu_ops.flush_tlb_others = kvm_flush_tlb_others; @@ -649,7 +649,7 @@ static __init int kvm_setup_pv_tlb_flush(void) int cpu; if (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && - !kvm_para_has_hint(KVM_HINTS_DEDICATED) && + !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { for_each_possible_cpu(cpu) { zalloc_cpumask_var_node(per_cpu_ptr(&__pv_tlb_mask, cpu), @@ -745,7 +745,7 @@ void __init kvm_spinlock_init(void) if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) return; - if (kvm_para_has_hint(KVM_HINTS_DEDICATED)) + if (kvm_para_has_hint(KVM_HINTS_REALTIME)) return; __pv_init_lock_hash(); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 82055b90a8b3..72d8c492d71d 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -403,7 +403,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, const u32 kvm_cpuid_7_0_ecx_x86_features = F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | - F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG); + F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | + F(CLDEMOTE); /* cpuid 7.0.edx*/ const u32 kvm_cpuid_7_0_edx_x86_features = diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index b3705ae52824..143b7ae52624 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -4189,7 +4189,9 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) maxphyaddr = eax & 0xff; else maxphyaddr = 36; - rsvd = rsvd_bits(maxphyaddr, 62); + rsvd = rsvd_bits(maxphyaddr, 63); + if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PCIDE) + rsvd &= ~CR3_PCID_INVD; } if (new_val & rsvd) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 98618e397342..14e0d0ae4e0a 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1242,6 +1242,121 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return kvm_hv_get_msr(vcpu, msr, pdata); } +static __always_inline int get_sparse_bank_no(u64 valid_bank_mask, int bank_no) +{ + int i = 0, j; + + if (!(valid_bank_mask & BIT_ULL(bank_no))) + return -1; + + for (j = 0; j < bank_no; j++) + if (valid_bank_mask & BIT_ULL(j)) + i++; + + return i; +} + +static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, + u16 rep_cnt, bool ex) +{ + struct kvm *kvm = current_vcpu->kvm; + struct kvm_vcpu_hv *hv_current = ¤t_vcpu->arch.hyperv; + struct hv_tlb_flush_ex flush_ex; + struct hv_tlb_flush flush; + struct kvm_vcpu *vcpu; + unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)] = {0}; + unsigned long valid_bank_mask = 0; + u64 sparse_banks[64]; + int sparse_banks_len, i; + bool all_cpus; + + if (!ex) { + if (unlikely(kvm_read_guest(kvm, ingpa, &flush, sizeof(flush)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + + trace_kvm_hv_flush_tlb(flush.processor_mask, + flush.address_space, flush.flags); + + sparse_banks[0] = flush.processor_mask; + all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS; + } else { + if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex, + sizeof(flush_ex)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + + trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, + flush_ex.hv_vp_set.format, + flush_ex.address_space, + flush_ex.flags); + + valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask; + all_cpus = flush_ex.hv_vp_set.format != + HV_GENERIC_SET_SPARSE_4K; + + sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) * + sizeof(sparse_banks[0]); + + if (!sparse_banks_len && !all_cpus) + goto ret_success; + + if (!all_cpus && + kvm_read_guest(kvm, + ingpa + offsetof(struct hv_tlb_flush_ex, + hv_vp_set.bank_contents), + sparse_banks, + sparse_banks_len)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } + + cpumask_clear(&hv_current->tlb_lush); + + kvm_for_each_vcpu(i, vcpu, kvm) { + struct kvm_vcpu_hv *hv = &vcpu->arch.hyperv; + int bank = hv->vp_index / 64, sbank = 0; + + if (!all_cpus) { + /* Banks >64 can't be represented */ + if (bank >= 64) + continue; + + /* Non-ex hypercalls can only address first 64 vCPUs */ + if (!ex && bank) + continue; + + if (ex) { + /* + * Check is the bank of this vCPU is in sparse + * set and get the sparse bank number. + */ + sbank = get_sparse_bank_no(valid_bank_mask, + bank); + + if (sbank < 0) + continue; + } + + if (!(sparse_banks[sbank] & BIT_ULL(hv->vp_index % 64))) + continue; + } + + /* + * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we + * can't analyze it here, flush TLB regardless of the specified + * address space. + */ + __set_bit(i, vcpu_bitmap); + } + + kvm_make_vcpus_request_mask(kvm, + KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP, + vcpu_bitmap, &hv_current->tlb_lush); + +ret_success: + /* We always do full TLB flush, set rep_done = rep_cnt. */ + return (u64)HV_STATUS_SUCCESS | + ((u64)rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); +} + bool kvm_hv_hypercall_enabled(struct kvm *kvm) { return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE; @@ -1265,7 +1380,7 @@ static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) struct kvm_run *run = vcpu->run; kvm_hv_hypercall_set_result(vcpu, run->hyperv.u.hcall.result); - return 1; + return kvm_skip_emulated_instruction(vcpu); } static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) @@ -1296,8 +1411,10 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, bool fast, u64 param) if (param & ~KVM_HYPERV_CONN_ID_MASK) return HV_STATUS_INVALID_HYPERCALL_INPUT; - /* conn_to_evt is protected by vcpu->kvm->srcu */ + /* the eventfd is protected by vcpu->kvm->srcu, but conn_to_evt isn't */ + rcu_read_lock(); eventfd = idr_find(&vcpu->kvm->arch.hyperv.conn_to_evt, param); + rcu_read_unlock(); if (!eventfd) return HV_STATUS_INVALID_PORT_ID; @@ -1309,7 +1426,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { u64 param, ingpa, outgpa, ret = HV_STATUS_SUCCESS; uint16_t code, rep_idx, rep_cnt; - bool fast, longmode; + bool fast, longmode, rep; /* * hypercall generates UD from non zero cpl and real mode @@ -1339,31 +1456,34 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) #endif code = param & 0xffff; - fast = (param >> 16) & 0x1; - rep_cnt = (param >> 32) & 0xfff; - rep_idx = (param >> 48) & 0xfff; + fast = !!(param & HV_HYPERCALL_FAST_BIT); + rep_cnt = (param >> HV_HYPERCALL_REP_COMP_OFFSET) & 0xfff; + rep_idx = (param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff; + rep = !!(rep_cnt || rep_idx); trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); - /* Hypercall continuation is not supported yet */ - if (rep_cnt || rep_idx) { - ret = HV_STATUS_INVALID_HYPERCALL_CODE; - goto set_result; - } - switch (code) { case HVCALL_NOTIFY_LONG_SPIN_WAIT: + if (unlikely(rep)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } kvm_vcpu_on_spin(vcpu, true); break; case HVCALL_SIGNAL_EVENT: + if (unlikely(rep)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } ret = kvm_hvcall_signal_event(vcpu, fast, ingpa); if (ret != HV_STATUS_INVALID_PORT_ID) break; /* maybe userspace knows this conn_id: fall through */ case HVCALL_POST_MESSAGE: /* don't bother userspace if it has no way to handle it */ - if (!vcpu_to_synic(vcpu)->active) { - ret = HV_STATUS_INVALID_HYPERCALL_CODE; + if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } vcpu->run->exit_reason = KVM_EXIT_HYPERV; @@ -1374,12 +1494,39 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; return 0; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: + if (unlikely(fast || !rep_cnt || rep_idx)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } + ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false); + break; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: + if (unlikely(fast || rep)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } + ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, false); + break; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: + if (unlikely(fast || !rep_cnt || rep_idx)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } + ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true); + break; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: + if (unlikely(fast || rep)) { + ret = HV_STATUS_INVALID_HYPERCALL_INPUT; + break; + } + ret = kvm_hv_flush_tlb(vcpu, ingpa, rep_cnt, true); + break; default: ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; } -set_result: kvm_hv_hypercall_set_result(vcpu, ret); return 1; } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index b74c9c1405b9..776391cf69a5 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1990,13 +1990,11 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) } } - if ((old_value ^ value) & X2APIC_ENABLE) { - if (value & X2APIC_ENABLE) { - kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); - kvm_x86_ops->set_virtual_x2apic_mode(vcpu, true); - } else - kvm_x86_ops->set_virtual_x2apic_mode(vcpu, false); - } + if (((old_value ^ value) & X2APIC_ENABLE) && (value & X2APIC_ENABLE)) + kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); + + if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) + kvm_x86_ops->set_virtual_apic_mode(vcpu); apic->base_address = apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_BASE; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index edce055e9fd7..ed0ed39abd36 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -16,6 +16,13 @@ #define APIC_BUS_CYCLE_NS 1 #define APIC_BUS_FREQUENCY (1000000000ULL / APIC_BUS_CYCLE_NS) +enum lapic_mode { + LAPIC_MODE_DISABLED = 0, + LAPIC_MODE_INVALID = X2APIC_ENABLE, + LAPIC_MODE_XAPIC = MSR_IA32_APICBASE_ENABLE, + LAPIC_MODE_X2APIC = MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE, +}; + struct kvm_timer { struct hrtimer timer; s64 period; /* unit: ns */ @@ -89,6 +96,7 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); +enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); @@ -220,4 +228,10 @@ void kvm_lapic_switch_to_hv_timer(struct kvm_vcpu *vcpu); void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu); bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu); void kvm_lapic_restart_hv_timer(struct kvm_vcpu *vcpu); + +static inline enum lapic_mode kvm_apic_mode(u64 apic_base) +{ + return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); +} + #endif diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 8494dbae41b9..f440d43c8d5a 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -222,7 +222,6 @@ static const u64 shadow_acc_track_saved_bits_mask = PT64_EPT_READABLE_MASK | static const u64 shadow_acc_track_saved_bits_shift = PT64_SECOND_AVAIL_BITS_SHIFT; static void mmu_spte_set(u64 *sptep, u64 spte); -static void mmu_free_roots(struct kvm_vcpu *vcpu); void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value) { @@ -3342,51 +3341,48 @@ out_unlock: return RET_PF_RETRY; } - -static void mmu_free_roots(struct kvm_vcpu *vcpu) +static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, + struct list_head *invalid_list) { - int i; struct kvm_mmu_page *sp; - LIST_HEAD(invalid_list); - if (!VALID_PAGE(vcpu->arch.mmu.root_hpa)) + if (!VALID_PAGE(*root_hpa)) return; - if (vcpu->arch.mmu.shadow_root_level >= PT64_ROOT_4LEVEL && - (vcpu->arch.mmu.root_level >= PT64_ROOT_4LEVEL || - vcpu->arch.mmu.direct_map)) { - hpa_t root = vcpu->arch.mmu.root_hpa; + sp = page_header(*root_hpa & PT64_BASE_ADDR_MASK); + --sp->root_count; + if (!sp->root_count && sp->role.invalid) + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); - spin_lock(&vcpu->kvm->mmu_lock); - sp = page_header(root); - --sp->root_count; - if (!sp->root_count && sp->role.invalid) { - kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); - kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - } - spin_unlock(&vcpu->kvm->mmu_lock); - vcpu->arch.mmu.root_hpa = INVALID_PAGE; + *root_hpa = INVALID_PAGE; +} + +void kvm_mmu_free_roots(struct kvm_vcpu *vcpu) +{ + int i; + LIST_HEAD(invalid_list); + struct kvm_mmu *mmu = &vcpu->arch.mmu; + + if (!VALID_PAGE(mmu->root_hpa)) return; - } spin_lock(&vcpu->kvm->mmu_lock); - for (i = 0; i < 4; ++i) { - hpa_t root = vcpu->arch.mmu.pae_root[i]; - if (root) { - root &= PT64_BASE_ADDR_MASK; - sp = page_header(root); - --sp->root_count; - if (!sp->root_count && sp->role.invalid) - kvm_mmu_prepare_zap_page(vcpu->kvm, sp, - &invalid_list); - } - vcpu->arch.mmu.pae_root[i] = INVALID_PAGE; + if (mmu->shadow_root_level >= PT64_ROOT_4LEVEL && + (mmu->root_level >= PT64_ROOT_4LEVEL || mmu->direct_map)) { + mmu_free_root_page(vcpu->kvm, &mmu->root_hpa, &invalid_list); + } else { + for (i = 0; i < 4; ++i) + if (mmu->pae_root[i] != 0) + mmu_free_root_page(vcpu->kvm, &mmu->pae_root[i], + &invalid_list); + mmu->root_hpa = INVALID_PAGE; } + kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); spin_unlock(&vcpu->kvm->mmu_lock); - vcpu->arch.mmu.root_hpa = INVALID_PAGE; } +EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); static int mmu_check_root(struct kvm_vcpu *vcpu, gfn_t root_gfn) { @@ -3719,7 +3715,6 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct) */ return RET_PF_RETRY; } -EXPORT_SYMBOL_GPL(handle_mmio_page_fault); static bool page_fault_handle_page_track(struct kvm_vcpu *vcpu, u32 error_code, gfn_t gfn) @@ -3811,6 +3806,14 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, struct kvm_memory_slot *slot; bool async; + /* + * Don't expose private memslots to L2. + */ + if (is_guest_mode(vcpu) && !kvm_is_visible_gfn(vcpu->kvm, gfn)) { + *pfn = KVM_PFN_NOSLOT; + return false; + } + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); async = false; *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); @@ -3950,7 +3953,7 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu) { - mmu_free_roots(vcpu); + kvm_mmu_free_roots(vcpu); } static unsigned long get_cr3(struct kvm_vcpu *vcpu) @@ -4472,6 +4475,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) struct kvm_mmu *context = &vcpu->arch.mmu; context->base_role.word = 0; + context->base_role.guest_mode = is_guest_mode(vcpu); context->base_role.smm = is_smm(vcpu); context->base_role.ad_disabled = (shadow_accessed_mask == 0); context->page_fault = tdp_page_fault; @@ -4538,6 +4542,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu) = smep && !is_write_protection(vcpu); context->base_role.smap_andnot_wp = smap && !is_write_protection(vcpu); + context->base_role.guest_mode = is_guest_mode(vcpu); context->base_role.smm = is_smm(vcpu); reset_shadow_zero_bits_mask(vcpu, context); } @@ -4563,7 +4568,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->root_hpa = INVALID_PAGE; context->direct_map = false; context->base_role.ad_disabled = !accessed_dirty; - + context->base_role.guest_mode = 1; update_permission_bitmask(vcpu, context, true); update_pkru_bitmask(vcpu, context, true); update_last_nonleaf_level(vcpu, context); @@ -4663,7 +4668,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { - mmu_free_roots(vcpu); + kvm_mmu_free_roots(vcpu); WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa)); } EXPORT_SYMBOL_GPL(kvm_mmu_unload); @@ -4824,6 +4829,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, mask.smep_andnot_wp = 1; mask.smap_andnot_wp = 1; mask.smm = 1; + mask.guest_mode = 1; mask.ad_disabled = 1; /* diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1fc05e428aba..de21d5c5168b 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1762,7 +1762,10 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, unsigned long npages, npinned, size; unsigned long locked, lock_limit; struct page **pages; - int first, last; + unsigned long first, last; + + if (ulen == 0 || uaddr + ulen < uaddr) + return NULL; /* Calculate number of pages. */ first = (uaddr & PAGE_MASK) >> PAGE_SHIFT; @@ -5036,7 +5039,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) set_cr_intercept(svm, INTERCEPT_CR8_WRITE); } -static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) +static void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { return; } @@ -6925,6 +6928,9 @@ static int svm_register_enc_region(struct kvm *kvm, if (!sev_guest(kvm)) return -ENOTTY; + if (range->addr > ULONG_MAX || range->size > ULONG_MAX) + return -EINVAL; + region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) return -ENOMEM; @@ -7076,7 +7082,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, - .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, + .set_virtual_apic_mode = svm_set_virtual_apic_mode, .get_enable_apicv = svm_get_enable_apicv, .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 9807c314c478..0f997683404f 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -1367,6 +1367,57 @@ TRACE_EVENT(kvm_hv_timer_state, __entry->vcpu_id, __entry->hv_timer_in_use) ); + +/* + * Tracepoint for kvm_hv_flush_tlb. + */ +TRACE_EVENT(kvm_hv_flush_tlb, + TP_PROTO(u64 processor_mask, u64 address_space, u64 flags), + TP_ARGS(processor_mask, address_space, flags), + + TP_STRUCT__entry( + __field(u64, processor_mask) + __field(u64, address_space) + __field(u64, flags) + ), + + TP_fast_assign( + __entry->processor_mask = processor_mask; + __entry->address_space = address_space; + __entry->flags = flags; + ), + + TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx", + __entry->processor_mask, __entry->address_space, + __entry->flags) +); + +/* + * Tracepoint for kvm_hv_flush_tlb_ex. + */ +TRACE_EVENT(kvm_hv_flush_tlb_ex, + TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags), + TP_ARGS(valid_bank_mask, format, address_space, flags), + + TP_STRUCT__entry( + __field(u64, valid_bank_mask) + __field(u64, format) + __field(u64, address_space) + __field(u64, flags) + ), + + TP_fast_assign( + __entry->valid_bank_mask = valid_bank_mask; + __entry->format = format; + __entry->address_space = address_space; + __entry->flags = flags; + ), + + TP_printk("valid_bank_mask 0x%llx format 0x%llx " + "address_space 0x%llx flags 0x%llx", + __entry->valid_bank_mask, __entry->format, + __entry->address_space, __entry->flags) +); #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index c7668806163f..e50beb76d846 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -242,7 +242,11 @@ struct shared_msr_entry { * underlying hardware which will be used to run L2. * This structure is packed to ensure that its layout is identical across * machines (necessary for live migration). - * If there are changes in this struct, VMCS12_REVISION must be changed. + * + * IMPORTANT: Changing the layout of existing fields in this structure + * will break save/restore compatibility with older kvm releases. When + * adding new fields, either use space in the reserved padding* arrays + * or add the new fields to the end of the structure. */ typedef u64 natural_width; struct __packed vmcs12 { @@ -265,17 +269,14 @@ struct __packed vmcs12 { u64 virtual_apic_page_addr; u64 apic_access_addr; u64 posted_intr_desc_addr; - u64 vm_function_control; u64 ept_pointer; u64 eoi_exit_bitmap0; u64 eoi_exit_bitmap1; u64 eoi_exit_bitmap2; u64 eoi_exit_bitmap3; - u64 eptp_list_address; u64 xss_exit_bitmap; u64 guest_physical_address; u64 vmcs_link_pointer; - u64 pml_address; u64 guest_ia32_debugctl; u64 guest_ia32_pat; u64 guest_ia32_efer; @@ -288,7 +289,12 @@ struct __packed vmcs12 { u64 host_ia32_pat; u64 host_ia32_efer; u64 host_ia32_perf_global_ctrl; - u64 padding64[8]; /* room for future expansion */ + u64 vmread_bitmap; + u64 vmwrite_bitmap; + u64 vm_function_control; + u64 eptp_list_address; + u64 pml_address; + u64 padding64[3]; /* room for future expansion */ /* * To allow migration of L1 (complete with its L2 guests) between * machines of different natural widths (32 or 64 bit), we cannot have @@ -397,7 +403,6 @@ struct __packed vmcs12 { u16 guest_ldtr_selector; u16 guest_tr_selector; u16 guest_intr_status; - u16 guest_pml_index; u16 host_es_selector; u16 host_cs_selector; u16 host_ss_selector; @@ -405,12 +410,172 @@ struct __packed vmcs12 { u16 host_fs_selector; u16 host_gs_selector; u16 host_tr_selector; + u16 guest_pml_index; }; /* + * For save/restore compatibility, the vmcs12 field offsets must not change. + */ +#define CHECK_OFFSET(field, loc) \ + BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \ + "Offset of " #field " in struct vmcs12 has changed.") + +static inline void vmx_check_vmcs12_offsets(void) { + CHECK_OFFSET(revision_id, 0); + CHECK_OFFSET(abort, 4); + CHECK_OFFSET(launch_state, 8); + CHECK_OFFSET(io_bitmap_a, 40); + CHECK_OFFSET(io_bitmap_b, 48); + CHECK_OFFSET(msr_bitmap, 56); + CHECK_OFFSET(vm_exit_msr_store_addr, 64); + CHECK_OFFSET(vm_exit_msr_load_addr, 72); + CHECK_OFFSET(vm_entry_msr_load_addr, 80); + CHECK_OFFSET(tsc_offset, 88); + CHECK_OFFSET(virtual_apic_page_addr, 96); + CHECK_OFFSET(apic_access_addr, 104); + CHECK_OFFSET(posted_intr_desc_addr, 112); + CHECK_OFFSET(ept_pointer, 120); + CHECK_OFFSET(eoi_exit_bitmap0, 128); + CHECK_OFFSET(eoi_exit_bitmap1, 136); + CHECK_OFFSET(eoi_exit_bitmap2, 144); + CHECK_OFFSET(eoi_exit_bitmap3, 152); + CHECK_OFFSET(xss_exit_bitmap, 160); + CHECK_OFFSET(guest_physical_address, 168); + CHECK_OFFSET(vmcs_link_pointer, 176); + CHECK_OFFSET(guest_ia32_debugctl, 184); + CHECK_OFFSET(guest_ia32_pat, 192); + CHECK_OFFSET(guest_ia32_efer, 200); + CHECK_OFFSET(guest_ia32_perf_global_ctrl, 208); + CHECK_OFFSET(guest_pdptr0, 216); + CHECK_OFFSET(guest_pdptr1, 224); + CHECK_OFFSET(guest_pdptr2, 232); + CHECK_OFFSET(guest_pdptr3, 240); + CHECK_OFFSET(guest_bndcfgs, 248); + CHECK_OFFSET(host_ia32_pat, 256); + CHECK_OFFSET(host_ia32_efer, 264); + CHECK_OFFSET(host_ia32_perf_global_ctrl, 272); + CHECK_OFFSET(vmread_bitmap, 280); + CHECK_OFFSET(vmwrite_bitmap, 288); + CHECK_OFFSET(vm_function_control, 296); + CHECK_OFFSET(eptp_list_address, 304); + CHECK_OFFSET(pml_address, 312); + CHECK_OFFSET(cr0_guest_host_mask, 344); + CHECK_OFFSET(cr4_guest_host_mask, 352); + CHECK_OFFSET(cr0_read_shadow, 360); + CHECK_OFFSET(cr4_read_shadow, 368); + CHECK_OFFSET(cr3_target_value0, 376); + CHECK_OFFSET(cr3_target_value1, 384); + CHECK_OFFSET(cr3_target_value2, 392); + CHECK_OFFSET(cr3_target_value3, 400); + CHECK_OFFSET(exit_qualification, 408); + CHECK_OFFSET(guest_linear_address, 416); + CHECK_OFFSET(guest_cr0, 424); + CHECK_OFFSET(guest_cr3, 432); + CHECK_OFFSET(guest_cr4, 440); + CHECK_OFFSET(guest_es_base, 448); + CHECK_OFFSET(guest_cs_base, 456); + CHECK_OFFSET(guest_ss_base, 464); + CHECK_OFFSET(guest_ds_base, 472); + CHECK_OFFSET(guest_fs_base, 480); + CHECK_OFFSET(guest_gs_base, 488); + CHECK_OFFSET(guest_ldtr_base, 496); + CHECK_OFFSET(guest_tr_base, 504); + CHECK_OFFSET(guest_gdtr_base, 512); + CHECK_OFFSET(guest_idtr_base, 520); + CHECK_OFFSET(guest_dr7, 528); + CHECK_OFFSET(guest_rsp, 536); + CHECK_OFFSET(guest_rip, 544); + CHECK_OFFSET(guest_rflags, 552); + CHECK_OFFSET(guest_pending_dbg_exceptions, 560); + CHECK_OFFSET(guest_sysenter_esp, 568); + CHECK_OFFSET(guest_sysenter_eip, 576); + CHECK_OFFSET(host_cr0, 584); + CHECK_OFFSET(host_cr3, 592); + CHECK_OFFSET(host_cr4, 600); + CHECK_OFFSET(host_fs_base, 608); + CHECK_OFFSET(host_gs_base, 616); + CHECK_OFFSET(host_tr_base, 624); + CHECK_OFFSET(host_gdtr_base, 632); + CHECK_OFFSET(host_idtr_base, 640); + CHECK_OFFSET(host_ia32_sysenter_esp, 648); + CHECK_OFFSET(host_ia32_sysenter_eip, 656); + CHECK_OFFSET(host_rsp, 664); + CHECK_OFFSET(host_rip, 672); + CHECK_OFFSET(pin_based_vm_exec_control, 744); + CHECK_OFFSET(cpu_based_vm_exec_control, 748); + CHECK_OFFSET(exception_bitmap, 752); + CHECK_OFFSET(page_fault_error_code_mask, 756); + CHECK_OFFSET(page_fault_error_code_match, 760); + CHECK_OFFSET(cr3_target_count, 764); + CHECK_OFFSET(vm_exit_controls, 768); + CHECK_OFFSET(vm_exit_msr_store_count, 772); + CHECK_OFFSET(vm_exit_msr_load_count, 776); + CHECK_OFFSET(vm_entry_controls, 780); + CHECK_OFFSET(vm_entry_msr_load_count, 784); + CHECK_OFFSET(vm_entry_intr_info_field, 788); + CHECK_OFFSET(vm_entry_exception_error_code, 792); + CHECK_OFFSET(vm_entry_instruction_len, 796); + CHECK_OFFSET(tpr_threshold, 800); + CHECK_OFFSET(secondary_vm_exec_control, 804); + CHECK_OFFSET(vm_instruction_error, 808); + CHECK_OFFSET(vm_exit_reason, 812); + CHECK_OFFSET(vm_exit_intr_info, 816); + CHECK_OFFSET(vm_exit_intr_error_code, 820); + CHECK_OFFSET(idt_vectoring_info_field, 824); + CHECK_OFFSET(idt_vectoring_error_code, 828); + CHECK_OFFSET(vm_exit_instruction_len, 832); + CHECK_OFFSET(vmx_instruction_info, 836); + CHECK_OFFSET(guest_es_limit, 840); + CHECK_OFFSET(guest_cs_limit, 844); + CHECK_OFFSET(guest_ss_limit, 848); + CHECK_OFFSET(guest_ds_limit, 852); + CHECK_OFFSET(guest_fs_limit, 856); + CHECK_OFFSET(guest_gs_limit, 860); + CHECK_OFFSET(guest_ldtr_limit, 864); + CHECK_OFFSET(guest_tr_limit, 868); + CHECK_OFFSET(guest_gdtr_limit, 872); + CHECK_OFFSET(guest_idtr_limit, 876); + CHECK_OFFSET(guest_es_ar_bytes, 880); + CHECK_OFFSET(guest_cs_ar_bytes, 884); + CHECK_OFFSET(guest_ss_ar_bytes, 888); + CHECK_OFFSET(guest_ds_ar_bytes, 892); + CHECK_OFFSET(guest_fs_ar_bytes, 896); + CHECK_OFFSET(guest_gs_ar_bytes, 900); + CHECK_OFFSET(guest_ldtr_ar_bytes, 904); + CHECK_OFFSET(guest_tr_ar_bytes, 908); + CHECK_OFFSET(guest_interruptibility_info, 912); + CHECK_OFFSET(guest_activity_state, 916); + CHECK_OFFSET(guest_sysenter_cs, 920); + CHECK_OFFSET(host_ia32_sysenter_cs, 924); + CHECK_OFFSET(vmx_preemption_timer_value, 928); + CHECK_OFFSET(virtual_processor_id, 960); + CHECK_OFFSET(posted_intr_nv, 962); + CHECK_OFFSET(guest_es_selector, 964); + CHECK_OFFSET(guest_cs_selector, 966); + CHECK_OFFSET(guest_ss_selector, 968); + CHECK_OFFSET(guest_ds_selector, 970); + CHECK_OFFSET(guest_fs_selector, 972); + CHECK_OFFSET(guest_gs_selector, 974); + CHECK_OFFSET(guest_ldtr_selector, 976); + CHECK_OFFSET(guest_tr_selector, 978); + CHECK_OFFSET(guest_intr_status, 980); + CHECK_OFFSET(host_es_selector, 982); + CHECK_OFFSET(host_cs_selector, 984); + CHECK_OFFSET(host_ss_selector, 986); + CHECK_OFFSET(host_ds_selector, 988); + CHECK_OFFSET(host_fs_selector, 990); + CHECK_OFFSET(host_gs_selector, 992); + CHECK_OFFSET(host_tr_selector, 994); + CHECK_OFFSET(guest_pml_index, 996); +} + +/* * VMCS12_REVISION is an arbitrary id that should be changed if the content or * layout of struct vmcs12 is changed. MSR_IA32_VMX_BASIC returns this id, and * VMPTRLD verifies that the VMCS region that L1 is loading contains this id. + * + * IMPORTANT: Changing this value will break save/restore compatibility with + * older kvm releases. */ #define VMCS12_REVISION 0x11e57ed0 @@ -481,7 +646,8 @@ struct nested_vmx { bool sync_shadow_vmcs; bool dirty_vmcs12; - bool change_vmcs01_virtual_x2apic_mode; + bool change_vmcs01_virtual_apic_mode; + /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; @@ -761,6 +927,7 @@ static const unsigned short vmcs_field_to_offset_table[] = { FIELD64(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr), FIELD64(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr), FIELD64(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr), + FIELD64(PML_ADDRESS, pml_address), FIELD64(TSC_OFFSET, tsc_offset), FIELD64(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr), FIELD64(APIC_ACCESS_ADDR, apic_access_addr), @@ -772,10 +939,11 @@ static const unsigned short vmcs_field_to_offset_table[] = { FIELD64(EOI_EXIT_BITMAP2, eoi_exit_bitmap2), FIELD64(EOI_EXIT_BITMAP3, eoi_exit_bitmap3), FIELD64(EPTP_LIST_ADDRESS, eptp_list_address), + FIELD64(VMREAD_BITMAP, vmread_bitmap), + FIELD64(VMWRITE_BITMAP, vmwrite_bitmap), FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap), FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address), FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer), - FIELD64(PML_ADDRESS, pml_address), FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl), FIELD64(GUEST_IA32_PAT, guest_ia32_pat), FIELD64(GUEST_IA32_EFER, guest_ia32_efer), @@ -1089,6 +1257,16 @@ static inline u16 evmcs_read16(unsigned long field) return *(u16 *)((char *)current_evmcs + offset); } +static inline void evmcs_touch_msr_bitmap(void) +{ + if (unlikely(!current_evmcs)) + return; + + if (current_evmcs->hv_enlightenments_control.msr_bitmap) + current_evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; +} + static void evmcs_load(u64 phys_addr) { struct hv_vp_assist_page *vp_ap = @@ -1173,6 +1351,7 @@ static inline u32 evmcs_read32(unsigned long field) { return 0; } static inline u16 evmcs_read16(unsigned long field) { return 0; } static inline void evmcs_load(u64 phys_addr) {} static inline void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) {} +static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ static inline bool is_exception_n(u32 intr_info, u8 vector) @@ -1393,6 +1572,11 @@ static inline bool cpu_has_vmx_invept_global(void) return vmx_capability.ept & VMX_EPT_EXTENT_GLOBAL_BIT; } +static inline bool cpu_has_vmx_invvpid_individual_addr(void) +{ + return vmx_capability.vpid & VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT; +} + static inline bool cpu_has_vmx_invvpid_single(void) { return vmx_capability.vpid & VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT; @@ -1494,6 +1678,12 @@ static inline bool cpu_has_vmx_vmfunc(void) SECONDARY_EXEC_ENABLE_VMFUNC; } +static bool vmx_umip_emulated(void) +{ + return vmcs_config.cpu_based_2nd_exec_ctrl & + SECONDARY_EXEC_DESC; +} + static inline bool report_flexpriority(void) { return flexpriority_enabled; @@ -4213,6 +4403,14 @@ static int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) if (!loaded_vmcs->msr_bitmap) goto out_vmcs; memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE); + + if (static_branch_unlikely(&enable_evmcs) && + (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { + struct hv_enlightened_vmcs *evmcs = + (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs; + + evmcs->hv_enlightenments_control.msr_bitmap = 1; + } } return 0; @@ -4761,14 +4959,16 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) else hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON; - if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_DESC); - hw_cr4 &= ~X86_CR4_UMIP; - } else if (!is_guest_mode(vcpu) || - !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) - vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) { + if (cr4 & X86_CR4_UMIP) { + vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_DESC); + hw_cr4 &= ~X86_CR4_UMIP; + } else if (!is_guest_mode(vcpu) || + !nested_cpu_has2(get_vmcs12(vcpu), SECONDARY_EXEC_DESC)) + vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, + SECONDARY_EXEC_DESC); + } if (cr4 & X86_CR4_VMXE) { /* @@ -5324,6 +5524,9 @@ static void __always_inline vmx_disable_intercept_for_msr(unsigned long *msr_bit if (!cpu_has_vmx_msr_bitmap()) return; + if (static_branch_unlikely(&enable_evmcs)) + evmcs_touch_msr_bitmap(); + /* * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals * have the write-low and read-high bitmap offsets the wrong way round. @@ -5359,6 +5562,9 @@ static void __always_inline vmx_enable_intercept_for_msr(unsigned long *msr_bitm if (!cpu_has_vmx_msr_bitmap()) return; + if (static_branch_unlikely(&enable_evmcs)) + evmcs_touch_msr_bitmap(); + /* * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals * have the write-low and read-high bitmap offsets the wrong way round. @@ -8312,12 +8518,19 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: - if (is_noncanonical_address(operand.gla, vcpu)) { + if (!operand.vpid || + is_noncanonical_address(operand.gla, vcpu)) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); return kvm_skip_emulated_instruction(vcpu); } - /* fall through */ + if (cpu_has_vmx_invvpid_individual_addr() && + vmx->nested.vpid02) { + __invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR, + vmx->nested.vpid02, operand.gla); + } else + __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); + break; case VMX_VPID_EXTENT_SINGLE_CONTEXT: case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL: if (!operand.vpid) { @@ -8325,15 +8538,16 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); return kvm_skip_emulated_instruction(vcpu); } + __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); break; case VMX_VPID_EXTENT_ALL_CONTEXT: + __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); break; default: WARN_ON_ONCE(1); return kvm_skip_emulated_instruction(vcpu); } - __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); nested_vmx_succeed(vcpu); return kvm_skip_emulated_instruction(vcpu); @@ -8837,11 +9051,13 @@ static bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason) case EXIT_REASON_TPR_BELOW_THRESHOLD: return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW); case EXIT_REASON_APIC_ACCESS: - return nested_cpu_has2(vmcs12, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); case EXIT_REASON_APIC_WRITE: case EXIT_REASON_EOI_INDUCED: - /* apic_write and eoi_induced should exit unconditionally. */ + /* + * The controls for "virtualize APIC accesses," "APIC- + * register virtualization," and "virtual-interrupt + * delivery" only come from vmcs12. + */ return true; case EXIT_REASON_EPT_VIOLATION: /* @@ -9248,31 +9464,43 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) vmcs_write32(TPR_THRESHOLD, irr); } -static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) +static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu) { u32 sec_exec_control; + if (!lapic_in_kernel(vcpu)) + return; + /* Postpone execution until vmcs01 is the current VMCS. */ if (is_guest_mode(vcpu)) { - to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true; + to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true; return; } - if (!cpu_has_vmx_virtualize_x2apic_mode()) - return; - if (!cpu_need_tpr_shadow(vcpu)) return; sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL); + sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE); - if (set) { - sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - } else { - sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; - sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmx_flush_tlb(vcpu, true); + switch (kvm_get_apic_mode(vcpu)) { + case LAPIC_MODE_INVALID: + WARN_ONCE(true, "Invalid local APIC state"); + case LAPIC_MODE_DISABLED: + break; + case LAPIC_MODE_XAPIC: + if (flexpriority_enabled) { + sec_exec_control |= + SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + vmx_flush_tlb(vcpu, true); + } + break; + case LAPIC_MODE_X2APIC: + if (cpu_has_vmx_virtualize_x2apic_mode()) + sec_exec_control |= + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + break; } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); @@ -9281,24 +9509,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) { - struct vcpu_vmx *vmx = to_vmx(vcpu); - - /* - * Currently we do not handle the nested case where L2 has an - * APIC access page of its own; that page is still pinned. - * Hence, we skip the case where the VCPU is in guest mode _and_ - * L1 prepared an APIC access page for L2. - * - * For the case where L1 and L2 share the same APIC access page - * (flexpriority=Y but SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES clear - * in the vmcs12), this function will only update either the vmcs01 - * or the vmcs02. If the former, the vmcs02 will be updated by - * prepare_vmcs02. If the latter, the vmcs01 will be updated in - * the next L2->L1 exit. - */ - if (!is_guest_mode(vcpu) || - !nested_cpu_has2(get_vmcs12(&vmx->vcpu), - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { + if (!is_guest_mode(vcpu)) { vmcs_write64(APIC_ACCESS_ADDR, hpa); vmx_flush_tlb(vcpu, true); } @@ -9497,12 +9708,6 @@ static bool vmx_xsaves_supported(void) SECONDARY_EXEC_XSAVES; } -static bool vmx_umip_emulated(void) -{ - return vmcs_config.cpu_based_2nd_exec_ctrl & - SECONDARY_EXEC_DESC; -} - static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx) { u32 exit_intr_info; @@ -10378,11 +10583,6 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu, vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); } - } else if (!(nested_cpu_has_virt_x2apic_mode(vmcs12)) && - cpu_need_virtualize_apic_accesses(&vmx->vcpu)) { - vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); - kvm_vcpu_reload_apic_access_page(vcpu); } if (nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW)) { @@ -10862,8 +11062,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne return 0; } -static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - bool from_vmentry) +static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -10997,13 +11196,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * is assigned to entry_failure_code on failure. */ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, - bool from_vmentry, u32 *entry_failure_code) + u32 *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); u32 exec_control, vmcs12_exec_ctrl; if (vmx->nested.dirty_vmcs12) { - prepare_vmcs02_full(vcpu, vmcs12, from_vmentry); + prepare_vmcs02_full(vcpu, vmcs12); vmx->nested.dirty_vmcs12 = false; } @@ -11023,7 +11222,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * HOST_FS_BASE, HOST_GS_BASE. */ - if (from_vmentry && + if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) { kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl); @@ -11031,7 +11230,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, kvm_set_dr(vcpu, 7, vcpu->arch.dr7); vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.vmcs01_debugctl); } - if (from_vmentry) { + if (vmx->nested.nested_run_pending) { vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, vmcs12->vm_entry_intr_info_field); vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, @@ -11163,7 +11362,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, ~VM_ENTRY_IA32E_MODE) | (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE)); - if (from_vmentry && + if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)) { vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); vcpu->arch.pat = vmcs12->guest_ia32_pat; @@ -11188,7 +11387,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) { if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) { vmx->nested.last_vpid = vmcs12->virtual_processor_id; - __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true); + __vmx_flush_tlb(vcpu, vmx->nested.vpid02, true); } } else { vmx_flush_tlb(vcpu, true); @@ -11231,7 +11430,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_set_cr4(vcpu, vmcs12->guest_cr4); vmcs_writel(CR4_READ_SHADOW, nested_read_cr4(vmcs12)); - if (from_vmentry && + if (vmx->nested.nested_run_pending && (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) vcpu->arch.efer = vmcs12->guest_ia32_efer; else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) @@ -11409,7 +11608,7 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, return 0; } -static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) +static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); @@ -11429,7 +11628,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry) vcpu->arch.tsc_offset += vmcs12->tsc_offset; r = EXIT_REASON_INVALID_STATE; - if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) + if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) goto fail; nested_get_vmcs12_pages(vcpu, vmcs12); @@ -11531,20 +11730,22 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * the nested entry. */ - ret = enter_vmx_non_root_mode(vcpu, true); - if (ret) + vmx->nested.nested_run_pending = 1; + ret = enter_vmx_non_root_mode(vcpu); + if (ret) { + vmx->nested.nested_run_pending = 0; return ret; + } /* * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken * by event injection, halt vcpu. */ if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) && - !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) + !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK)) { + vmx->nested.nested_run_pending = 0; return kvm_vcpu_halt(vcpu); - - vmx->nested.nested_run_pending = 1; - + } return 1; out: @@ -11916,12 +12117,20 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, load_vmcs12_mmu_host_state(vcpu, vmcs12); - if (enable_vpid) { - /* - * Trivially support vpid by letting L2s share their parent - * L1's vpid. TODO: move to a more elaborate solution, giving - * each L2 its own vpid and exposing the vpid feature to L1. - */ + /* + * If vmcs01 don't use VPID, CPU flushes TLB on every + * VMEntry/VMExit. Thus, no need to flush TLB. + * + * If vmcs12 uses VPID, TLB entries populated by L2 are + * tagged with vmx->nested.vpid02 while L1 entries are tagged + * with vmx->vpid. Thus, no need to flush TLB. + * + * Therefore, flush TLB only in case vmcs01 uses VPID and + * vmcs12 don't use VPID as in this case L1 & L2 TLB entries + * are both tagged with vmx->vpid. + */ + if (enable_vpid && + !(nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02)) { vmx_flush_tlb(vcpu, true); } @@ -12060,10 +12269,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); - if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { - vmx->nested.change_vmcs01_virtual_x2apic_mode = false; - vmx_set_virtual_x2apic_mode(vcpu, - vcpu->arch.apic_base & X2APIC_ENABLE); + if (vmx->nested.change_vmcs01_virtual_apic_mode) { + vmx->nested.change_vmcs01_virtual_apic_mode = false; + vmx_set_virtual_apic_mode(vcpu); } else if (!nested_cpu_has_ept(vmcs12) && nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { @@ -12606,7 +12814,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase) if (vmx->nested.smm.guest_mode) { vcpu->arch.hflags &= ~HF_SMM_MASK; - ret = enter_vmx_non_root_mode(vcpu, false); + ret = enter_vmx_non_root_mode(vcpu); vcpu->arch.hflags |= HF_SMM_MASK; if (ret) return ret; @@ -12691,7 +12899,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, - .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, + .set_virtual_apic_mode = vmx_set_virtual_apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .get_enable_apicv = vmx_get_enable_apicv, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, @@ -12803,6 +13011,7 @@ static int __init vmx_init(void) rcu_assign_pointer(crash_vmclear_loaded_vmcss, crash_vmclear_local_loaded_vmcss); #endif + vmx_check_vmcs12_offsets(); return 0; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 51ecd381793b..22bd20fedd6d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -114,7 +114,7 @@ module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); static bool __read_mostly report_ignored_msrs = true; module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); -unsigned int min_timer_period_us = 500; +unsigned int min_timer_period_us = 200; module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); static bool __read_mostly kvmclock_periodic_sync = true; @@ -318,23 +318,27 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_apic_base); +enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu) +{ + return kvm_apic_mode(kvm_get_apic_base(vcpu)); +} +EXPORT_SYMBOL_GPL(kvm_get_apic_mode); + int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - u64 old_state = vcpu->arch.apic_base & - (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); - u64 new_state = msr_info->data & - (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE); + enum lapic_mode old_mode = kvm_get_apic_mode(vcpu); + enum lapic_mode new_mode = kvm_apic_mode(msr_info->data); u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff | (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); - if ((msr_info->data & reserved_bits) || new_state == X2APIC_ENABLE) - return 1; - if (!msr_info->host_initiated && - ((new_state == MSR_IA32_APICBASE_ENABLE && - old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) || - (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) && - old_state == 0))) + if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) return 1; + if (!msr_info->host_initiated) { + if (old_mode == LAPIC_MODE_X2APIC && new_mode == LAPIC_MODE_XAPIC) + return 1; + if (old_mode == LAPIC_MODE_DISABLED && new_mode == LAPIC_MODE_X2APIC) + return 1; + } kvm_lapic_set_base(vcpu, msr_info->data); return 0; @@ -843,7 +847,10 @@ EXPORT_SYMBOL_GPL(kvm_set_cr4); int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { #ifdef CONFIG_X86_64 - cr3 &= ~CR3_PCID_INVD; + bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); + + if (pcid_enabled) + cr3 &= ~CR3_PCID_INVD; #endif if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) { @@ -853,7 +860,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu) && - (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 62))) + (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63))) return 1; else if (is_pae(vcpu) && is_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -1757,7 +1764,7 @@ static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp) return mode; } -static int do_realtime(struct timespec *ts, u64 *tsc_timestamp) +static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -1790,7 +1797,7 @@ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) } /* returns true if host is using TSC based clocksource */ -static bool kvm_get_walltime_and_clockread(struct timespec *ts, +static bool kvm_get_walltime_and_clockread(struct timespec64 *ts, u64 *tsc_timestamp) { /* checked again under seqlock below */ @@ -2864,6 +2871,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: case KVM_CAP_HYPERV_EVENTFD: + case KVM_CAP_HYPERV_TLBFLUSH: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -6619,7 +6627,7 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) { struct kvm_clock_pairing clock_pairing; - struct timespec ts; + struct timespec64 ts; u64 cycle; int ret; @@ -6671,12 +6679,13 @@ void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit, r; - - r = kvm_skip_emulated_instruction(vcpu); + int op_64_bit; - if (kvm_hv_hypercall_enabled(vcpu->kvm)) - return kvm_hv_hypercall(vcpu); + if (kvm_hv_hypercall_enabled(vcpu->kvm)) { + if (!kvm_hv_hypercall(vcpu)) + return 0; + goto out; + } nr = kvm_register_read(vcpu, VCPU_REGS_RAX); a0 = kvm_register_read(vcpu, VCPU_REGS_RBX); @@ -6697,7 +6706,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) if (kvm_x86_ops->get_cpl(vcpu) != 0) { ret = -KVM_EPERM; - goto out; + goto out_error; } switch (nr) { @@ -6717,12 +6726,14 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) ret = -KVM_ENOSYS; break; } -out: +out_error: if (!op_64_bit) ret = (u32)ret; kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + +out: ++vcpu->stat.hypercalls; - return r; + return kvm_skip_emulated_instruction(vcpu); } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 826898701045..19c1ff542387 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -65,6 +65,19 @@ static void __init xen_hvm_init_mem_mapping(void) { early_memunmap(HYPERVISOR_shared_info, PAGE_SIZE); HYPERVISOR_shared_info = __va(PFN_PHYS(shared_info_pfn)); + + /* + * The virtual address of the shared_info page has changed, so + * the vcpu_info pointer for VCPU 0 is now stale. + * + * The prepare_boot_cpu callback will re-initialize it via + * xen_vcpu_setup, but we can't rely on that to be called for + * old Xen versions (xen_have_vector_callback == 0). + * + * It is, in any case, bad to have a stale vcpu_info pointer + * so reset it now. + */ + xen_vcpu_info_reset(0); } static void __init init_hvm_pv_info(void) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index d33e7dbe3129..2d76106788a3 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -42,13 +42,11 @@ xmaddr_t arbitrary_virt_to_machine(void *vaddr) } EXPORT_SYMBOL_GPL(arbitrary_virt_to_machine); -static void xen_flush_tlb_all(void) +static noinline void xen_flush_tlb_all(void) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb_all(0); - preempt_disable(); mcs = xen_mc_entry(sizeof(*op)); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 486c0a34d00b..2c30cabfda90 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1310,13 +1310,11 @@ unsigned long xen_read_cr2_direct(void) return this_cpu_read(xen_vcpu_info.arch.cr2); } -static void xen_flush_tlb(void) +static noinline void xen_flush_tlb(void) { struct mmuext_op *op; struct multicall_space mcs; - trace_xen_mmu_flush_tlb(0); - preempt_disable(); mcs = xen_mc_entry(sizeof(*op)); diff --git a/drivers/acpi/acpica/acnamesp.h b/drivers/acpi/acpica/acnamesp.h index 514aaf948ea9..3825df923480 100644 --- a/drivers/acpi/acpica/acnamesp.h +++ b/drivers/acpi/acpica/acnamesp.h @@ -56,6 +56,10 @@ acpi_status acpi_ns_initialize_objects(void); acpi_status acpi_ns_initialize_devices(u32 flags); +acpi_status +acpi_ns_init_one_package(acpi_handle obj_handle, + u32 level, void *context, void **return_value); + /* * nsload - Namespace loading */ diff --git a/drivers/acpi/acpica/exconfig.c b/drivers/acpi/acpica/exconfig.c index 99d92cb32803..f85c6f3271f6 100644 --- a/drivers/acpi/acpica/exconfig.c +++ b/drivers/acpi/acpica/exconfig.c @@ -174,6 +174,13 @@ acpi_ex_load_table_op(struct acpi_walk_state *walk_state, return_ACPI_STATUS(status); } + /* Complete the initialization/resolution of package objects */ + + status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, 0, + acpi_ns_init_one_package, NULL, NULL, + NULL); + /* Parameter Data (optional) */ if (parameter_node) { @@ -430,6 +437,13 @@ acpi_ex_load_op(union acpi_operand_object *obj_desc, return_ACPI_STATUS(status); } + /* Complete the initialization/resolution of package objects */ + + status = acpi_ns_walk_namespace(ACPI_TYPE_PACKAGE, ACPI_ROOT_OBJECT, + ACPI_UINT32_MAX, 0, + acpi_ns_init_one_package, NULL, NULL, + NULL); + /* Store the ddb_handle into the Target operand */ status = acpi_ex_store(ddb_handle, target, walk_state); diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c index 77f2b5f4948a..d77257d1c827 100644 --- a/drivers/acpi/acpica/nsinit.c +++ b/drivers/acpi/acpica/nsinit.c @@ -242,6 +242,58 @@ error_exit: /******************************************************************************* * + * FUNCTION: acpi_ns_init_one_package + * + * PARAMETERS: obj_handle - Node + * level - Current nesting level + * context - Not used + * return_value - Not used + * + * RETURN: Status + * + * DESCRIPTION: Callback from acpi_walk_namespace. Invoked for every package + * within the namespace. Used during dynamic load of an SSDT. + * + ******************************************************************************/ + +acpi_status +acpi_ns_init_one_package(acpi_handle obj_handle, + u32 level, void *context, void **return_value) +{ + acpi_status status; + union acpi_operand_object *obj_desc; + struct acpi_namespace_node *node = + (struct acpi_namespace_node *)obj_handle; + + obj_desc = acpi_ns_get_attached_object(node); + if (!obj_desc) { + return (AE_OK); + } + + /* Exit if package is already initialized */ + + if (obj_desc->package.flags & AOPOBJ_DATA_VALID) { + return (AE_OK); + } + + status = acpi_ds_get_package_arguments(obj_desc); + if (ACPI_FAILURE(status)) { + return (AE_OK); + } + + status = + acpi_ut_walk_package_tree(obj_desc, NULL, + acpi_ds_init_package_element, NULL); + if (ACPI_FAILURE(status)) { + return (AE_OK); + } + + obj_desc->package.flags |= AOPOBJ_DATA_VALID; + return (AE_OK); +} + +/******************************************************************************* + * * FUNCTION: acpi_ns_init_one_object * * PARAMETERS: obj_handle - Node @@ -360,27 +412,11 @@ acpi_ns_init_one_object(acpi_handle obj_handle, case ACPI_TYPE_PACKAGE: - info->package_init++; - status = acpi_ds_get_package_arguments(obj_desc); - if (ACPI_FAILURE(status)) { - break; - } - - ACPI_DEBUG_PRINT_RAW((ACPI_DB_PARSE, - "%s: Completing resolution of Package elements\n", - ACPI_GET_FUNCTION_NAME)); + /* Complete the initialization/resolution of the package object */ - /* - * Resolve all named references in package objects (and all - * sub-packages). This action has been deferred until the entire - * namespace has been loaded, in order to support external and - * forward references from individual package elements (05/2017). - */ - status = acpi_ut_walk_package_tree(obj_desc, NULL, - acpi_ds_init_package_element, - NULL); - - obj_desc->package.flags |= AOPOBJ_DATA_VALID; + info->package_init++; + status = + acpi_ns_init_one_package(obj_handle, level, NULL, NULL); break; default: diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 1ff17799769d..6389c88b3500 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -698,7 +698,7 @@ static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class, DPRINTK("ENTER\n"); - ahci_stop_engine(ap); + hpriv->stop_engine(ap); rc = sata_link_hardreset(link, sata_ehc_deb_timing(&link->eh_context), deadline, &online, NULL); @@ -724,7 +724,7 @@ static int ahci_p5wdh_hardreset(struct ata_link *link, unsigned int *class, bool online; int rc; - ahci_stop_engine(ap); + hpriv->stop_engine(ap); /* clear D2H reception area to properly wait for D2H FIS */ ata_tf_init(link->device, &tf); @@ -788,7 +788,7 @@ static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class, DPRINTK("ENTER\n"); - ahci_stop_engine(ap); + hpriv->stop_engine(ap); for (i = 0; i < 2; i++) { u16 val; diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 4356ef1d28a8..824bd399f02e 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -350,7 +350,6 @@ struct ahci_host_priv { u32 em_msg_type; /* EM message type */ bool got_runtime_pm; /* Did we do pm_runtime_get? */ struct clk *clks[AHCI_MAX_CLKS]; /* Optional */ - struct reset_control *rsts; /* Optional */ struct regulator **target_pwrs; /* Optional */ /* * If platform uses PHYs. There is a 1:1 relation between the port number and @@ -366,6 +365,13 @@ struct ahci_host_priv { * be overridden anytime before the host is activated. */ void (*start_engine)(struct ata_port *ap); + /* + * Optional ahci_stop_engine override, if not set this gets set to the + * default ahci_stop_engine during ahci_save_initial_config, this can + * be overridden anytime before the host is activated. + */ + int (*stop_engine)(struct ata_port *ap); + irqreturn_t (*irq_handler)(int irq, void *dev_instance); /* only required for per-port MSI(-X) support */ diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c index de7128d81e9c..0045dacd814b 100644 --- a/drivers/ata/ahci_mvebu.c +++ b/drivers/ata/ahci_mvebu.c @@ -62,6 +62,60 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv) writel(0x80, hpriv->mmio + AHCI_VENDOR_SPECIFIC_0_DATA); } +/** + * ahci_mvebu_stop_engine + * + * @ap: Target ata port + * + * Errata Ref#226 - SATA Disk HOT swap issue when connected through + * Port Multiplier in FIS-based Switching mode. + * + * To avoid the issue, according to design, the bits[11:8, 0] of + * register PxFBS are cleared when Port Command and Status (0x18) bit[0] + * changes its value from 1 to 0, i.e. falling edge of Port + * Command and Status bit[0] sends PULSE that resets PxFBS + * bits[11:8; 0]. + * + * This function is used to override function of "ahci_stop_engine" + * from libahci.c by adding the mvebu work around(WA) to save PxFBS + * value before the PxCMD ST write of 0, then restore PxFBS value. + * + * Return: 0 on success; Error code otherwise. + */ +int ahci_mvebu_stop_engine(struct ata_port *ap) +{ + void __iomem *port_mmio = ahci_port_base(ap); + u32 tmp, port_fbs; + + tmp = readl(port_mmio + PORT_CMD); + + /* check if the HBA is idle */ + if ((tmp & (PORT_CMD_START | PORT_CMD_LIST_ON)) == 0) + return 0; + + /* save the port PxFBS register for later restore */ + port_fbs = readl(port_mmio + PORT_FBS); + + /* setting HBA to idle */ + tmp &= ~PORT_CMD_START; + writel(tmp, port_mmio + PORT_CMD); + + /* + * bit #15 PxCMD signal doesn't clear PxFBS, + * restore the PxFBS register right after clearing the PxCMD ST, + * no need to wait for the PxCMD bit #15. + */ + writel(port_fbs, port_mmio + PORT_FBS); + + /* wait for engine to stop. This could be as long as 500 msec */ + tmp = ata_wait_register(ap, port_mmio + PORT_CMD, + PORT_CMD_LIST_ON, PORT_CMD_LIST_ON, 1, 500); + if (tmp & PORT_CMD_LIST_ON) + return -EIO; + + return 0; +} + #ifdef CONFIG_PM_SLEEP static int ahci_mvebu_suspend(struct platform_device *pdev, pm_message_t state) { @@ -112,6 +166,8 @@ static int ahci_mvebu_probe(struct platform_device *pdev) if (rc) return rc; + hpriv->stop_engine = ahci_mvebu_stop_engine; + if (of_device_is_compatible(pdev->dev.of_node, "marvell,armada-380-ahci")) { dram = mv_mbus_dram_info(); diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c index 2685f28160f7..cfdef4d44ae9 100644 --- a/drivers/ata/ahci_qoriq.c +++ b/drivers/ata/ahci_qoriq.c @@ -96,7 +96,7 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class, DPRINTK("ENTER\n"); - ahci_stop_engine(ap); + hpriv->stop_engine(ap); /* * There is a errata on ls1021a Rev1.0 and Rev2.0 which is: diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index c2b5941d9184..ad58da7c9aff 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -165,7 +165,7 @@ static int xgene_ahci_restart_engine(struct ata_port *ap) PORT_CMD_ISSUE, 0x0, 1, 100)) return -EBUSY; - ahci_stop_engine(ap); + hpriv->stop_engine(ap); ahci_start_fis_rx(ap); /* @@ -421,7 +421,7 @@ static int xgene_ahci_hardreset(struct ata_link *link, unsigned int *class, portrxfis_saved = readl(port_mmio + PORT_FIS_ADDR); portrxfishi_saved = readl(port_mmio + PORT_FIS_ADDR_HI); - ahci_stop_engine(ap); + hpriv->stop_engine(ap); rc = xgene_ahci_do_hardreset(link, deadline, &online); diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 7adcf3caabd0..e5d90977caec 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -560,6 +560,9 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv) if (!hpriv->start_engine) hpriv->start_engine = ahci_start_engine; + if (!hpriv->stop_engine) + hpriv->stop_engine = ahci_stop_engine; + if (!hpriv->irq_handler) hpriv->irq_handler = ahci_single_level_irq_intr; } @@ -897,9 +900,10 @@ static void ahci_start_port(struct ata_port *ap) static int ahci_deinit_port(struct ata_port *ap, const char **emsg) { int rc; + struct ahci_host_priv *hpriv = ap->host->private_data; /* disable DMA */ - rc = ahci_stop_engine(ap); + rc = hpriv->stop_engine(ap); if (rc) { *emsg = "failed to stop engine"; return rc; @@ -1310,7 +1314,7 @@ int ahci_kick_engine(struct ata_port *ap) int busy, rc; /* stop engine */ - rc = ahci_stop_engine(ap); + rc = hpriv->stop_engine(ap); if (rc) goto out_restart; @@ -1549,7 +1553,7 @@ int ahci_do_hardreset(struct ata_link *link, unsigned int *class, DPRINTK("ENTER\n"); - ahci_stop_engine(ap); + hpriv->stop_engine(ap); /* clear D2H reception area to properly wait for D2H FIS */ ata_tf_init(link->device, &tf); @@ -2075,14 +2079,14 @@ void ahci_error_handler(struct ata_port *ap) if (!(ap->pflags & ATA_PFLAG_FROZEN)) { /* restart engine */ - ahci_stop_engine(ap); + hpriv->stop_engine(ap); hpriv->start_engine(ap); } sata_pmp_error_handler(ap); if (!ata_dev_enabled(ap->link.device)) - ahci_stop_engine(ap); + hpriv->stop_engine(ap); } EXPORT_SYMBOL_GPL(ahci_error_handler); @@ -2129,7 +2133,7 @@ static void ahci_set_aggressive_devslp(struct ata_port *ap, bool sleep) return; /* set DITO, MDAT, DETO and enable DevSlp, need to stop engine first */ - rc = ahci_stop_engine(ap); + rc = hpriv->stop_engine(ap); if (rc) return; @@ -2189,7 +2193,7 @@ static void ahci_enable_fbs(struct ata_port *ap) return; } - rc = ahci_stop_engine(ap); + rc = hpriv->stop_engine(ap); if (rc) return; @@ -2222,7 +2226,7 @@ static void ahci_disable_fbs(struct ata_port *ap) return; } - rc = ahci_stop_engine(ap); + rc = hpriv->stop_engine(ap); if (rc) return; diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 46a762442dc5..30cc8f1a31e1 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -25,7 +25,6 @@ #include <linux/phy/phy.h> #include <linux/pm_runtime.h> #include <linux/of_platform.h> -#include <linux/reset.h> #include "ahci.h" static void ahci_host_stop(struct ata_host *host); @@ -196,8 +195,7 @@ EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators); * following order: * 1) Regulator * 2) Clocks (through ahci_platform_enable_clks) - * 3) Resets - * 4) Phys + * 3) Phys * * If resource enabling fails at any point the previous enabled resources * are disabled in reverse order. @@ -217,19 +215,12 @@ int ahci_platform_enable_resources(struct ahci_host_priv *hpriv) if (rc) goto disable_regulator; - rc = reset_control_deassert(hpriv->rsts); - if (rc) - goto disable_clks; - rc = ahci_platform_enable_phys(hpriv); if (rc) - goto disable_resets; + goto disable_clks; return 0; -disable_resets: - reset_control_assert(hpriv->rsts); - disable_clks: ahci_platform_disable_clks(hpriv); @@ -248,15 +239,12 @@ EXPORT_SYMBOL_GPL(ahci_platform_enable_resources); * following order: * 1) Phys * 2) Clocks (through ahci_platform_disable_clks) - * 3) Resets - * 4) Regulator + * 3) Regulator */ void ahci_platform_disable_resources(struct ahci_host_priv *hpriv) { ahci_platform_disable_phys(hpriv); - reset_control_assert(hpriv->rsts); - ahci_platform_disable_clks(hpriv); ahci_platform_disable_regulators(hpriv); @@ -405,12 +393,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev) hpriv->clks[i] = clk; } - hpriv->rsts = devm_reset_control_array_get_optional_shared(dev); - if (IS_ERR(hpriv->rsts)) { - rc = PTR_ERR(hpriv->rsts); - goto err_out; - } - hpriv->nports = child_nodes = of_get_child_count(dev->of_node); /* diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 8bc71ca61e7f..68596bd4cf06 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4549,6 +4549,12 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, + /* This specific Samsung model/firmware-rev does not handle LPM well */ + { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, + + /* Sandisk devices which are known to not handle LPM well */ + { "SanDisk SD7UB3Q*G1001", NULL, ATA_HORKAGE_NOLPM, }, + /* devices that don't properly handle queued TRIM commands */ { "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index c016829a38fd..513b260bcff1 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -175,8 +175,8 @@ static void ata_eh_handle_port_resume(struct ata_port *ap) { } #endif /* CONFIG_PM */ -static void __ata_ehi_pushv_desc(struct ata_eh_info *ehi, const char *fmt, - va_list args) +static __printf(2, 0) void __ata_ehi_pushv_desc(struct ata_eh_info *ehi, + const char *fmt, va_list args) { ehi->desc_len += vscnprintf(ehi->desc + ehi->desc_len, ATA_EH_DESC_LEN - ehi->desc_len, diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c index aafb8cc03523..e67815b896fc 100644 --- a/drivers/ata/sata_highbank.c +++ b/drivers/ata/sata_highbank.c @@ -410,7 +410,7 @@ static int ahci_highbank_hardreset(struct ata_link *link, unsigned int *class, int rc; int retry = 100; - ahci_stop_engine(ap); + hpriv->stop_engine(ap); /* clear D2H reception area to properly wait for D2H FIS */ ata_tf_init(link->device, &tf); diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 4b1995e2d044..010ca101d412 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -285,13 +285,13 @@ static const struct sil24_cerr_info { [PORT_CERR_INCONSISTENT] = { AC_ERR_HSM, ATA_EH_RESET, "protocol mismatch" }, [PORT_CERR_DIRECTION] = { AC_ERR_HSM, ATA_EH_RESET, - "data directon mismatch" }, + "data direction mismatch" }, [PORT_CERR_UNDERRUN] = { AC_ERR_HSM, ATA_EH_RESET, "ran out of SGEs while writing" }, [PORT_CERR_OVERRUN] = { AC_ERR_HSM, ATA_EH_RESET, "ran out of SGEs while reading" }, [PORT_CERR_PKT_PROT] = { AC_ERR_HSM, ATA_EH_RESET, - "invalid data directon for ATAPI CDB" }, + "invalid data direction for ATAPI CDB" }, [PORT_CERR_SGT_BOUNDARY] = { AC_ERR_SYSTEM, ATA_EH_RESET, "SGT not on qword boundary" }, [PORT_CERR_SGT_TGTABRT] = { AC_ERR_HOST_BUS, ATA_EH_RESET, diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index d97c05690faa..4e46dc9e41ad 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -191,7 +191,7 @@ static char *res_strings[] = { "reserved 37", "reserved 38", "reserved 39", - "reseverd 40", + "reserved 40", "reserved 41", "reserved 42", "reserved 43", diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c index 1ef67db03c8e..9c9a22958717 100644 --- a/drivers/atm/zatm.c +++ b/drivers/atm/zatm.c @@ -28,6 +28,7 @@ #include <asm/io.h> #include <linux/atomic.h> #include <linux/uaccess.h> +#include <linux/nospec.h> #include "uPD98401.h" #include "uPD98402.h" @@ -1458,6 +1459,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg) return -EFAULT; if (pool < 0 || pool > ZATM_LAST_POOL) return -EINVAL; + pool = array_index_nospec(pool, + ZATM_LAST_POOL + 1); spin_lock_irqsave(&zatm_dev->lock, flags); info = zatm_dev->pool_info[pool]; if (cmd == ZATM_GETPOOLZ) { diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 8e8b04cc569a..33b36fea1d73 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -2366,7 +2366,9 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes) osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd", "copyup"); osd_req_op_cls_request_data_bvecs(obj_req->osd_req, 0, - obj_req->copyup_bvecs, bytes); + obj_req->copyup_bvecs, + obj_req->copyup_bvec_count, + bytes); switch (obj_req->img_request->op_type) { case OBJ_OP_WRITE: diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index c8c8b0b8d333..b937cc1e2c07 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -231,6 +231,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0930, 0x0227), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0b05, 0x17d0), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x0036), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311d), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0x311e), .driver_info = BTUSB_ATH3012 }, @@ -263,7 +264,6 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 }, /* QCA ROME chipset */ - { USB_DEVICE(0x0cf3, 0x3004), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe009), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe010), .driver_info = BTUSB_QCA_ROME }, @@ -399,6 +399,13 @@ static const struct dmi_system_id btusb_needs_reset_resume_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 3060"), }, }, + { + /* Dell XPS 9360 (QCA ROME device 0cf3:e300) */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "XPS 13 9360"), + }, + }, {} }; @@ -2852,6 +2859,12 @@ static int btusb_config_oob_wake(struct hci_dev *hdev) } #endif +static void btusb_check_needs_reset_resume(struct usb_interface *intf) +{ + if (dmi_check_system(btusb_needs_reset_resume_table)) + interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; +} + static int btusb_probe(struct usb_interface *intf, const struct usb_device_id *id) { @@ -2974,9 +2987,6 @@ static int btusb_probe(struct usb_interface *intf, hdev->send = btusb_send_frame; hdev->notify = btusb_notify; - if (dmi_check_system(btusb_needs_reset_resume_table)) - interface_to_usbdev(intf)->quirks |= USB_QUIRK_RESET_RESUME; - #ifdef CONFIG_PM err = btusb_config_oob_wake(hdev); if (err) @@ -3064,6 +3074,7 @@ static int btusb_probe(struct usb_interface *intf, data->setup_on_usb = btusb_setup_qca; hdev->set_bdaddr = btusb_set_bdaddr_ath3012; set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); + btusb_check_needs_reset_resume(intf); } #ifdef CONFIG_BT_HCIBTUSB_RTL diff --git a/drivers/char/agp/uninorth-agp.c b/drivers/char/agp/uninorth-agp.c index c381c8e396fc..79d8c84693a1 100644 --- a/drivers/char/agp/uninorth-agp.c +++ b/drivers/char/agp/uninorth-agp.c @@ -195,7 +195,7 @@ static int uninorth_insert_memory(struct agp_memory *mem, off_t pg_start, int ty return 0; } -int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type) +static int uninorth_remove_memory(struct agp_memory *mem, off_t pg_start, int type) { size_t i; u32 *gp; @@ -470,7 +470,7 @@ static int uninorth_free_gatt_table(struct agp_bridge_data *bridge) return 0; } -void null_cache_flush(void) +static void null_cache_flush(void) { mb(); } diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 41492e980ef4..34968a381d0f 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -266,15 +266,13 @@ config COMMON_CLK_STM32MP157 Support for stm32mp157 SoC family clocks config COMMON_CLK_STM32F - bool "Clock driver for stm32f4 and stm32f7 SoC families" - depends on MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746 + def_bool COMMON_CLK && (MACH_STM32F429 || MACH_STM32F469 || MACH_STM32F746) help ---help--- Support for stm32f4 and stm32f7 SoC families clocks config COMMON_CLK_STM32H7 - bool "Clock driver for stm32h7 SoC family" - depends on MACH_STM32H743 + def_bool COMMON_CLK && MACH_STM32H743 help ---help--- Support for stm32h7 SoC family clocks diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c index 114ecbb94ec5..12320118f8de 100644 --- a/drivers/clk/imx/clk-imx6ul.c +++ b/drivers/clk/imx/clk-imx6ul.c @@ -464,7 +464,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node) clk_set_rate(clks[IMX6UL_CLK_AHB], 99000000); /* Change periph_pre clock to pll2_bus to adjust AXI rate to 264MHz */ - clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_PLL3_USB_OTG]); + clk_set_parent(clks[IMX6UL_CLK_PERIPH_CLK2_SEL], clks[IMX6UL_CLK_OSC]); clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_CLK2]); clk_set_parent(clks[IMX6UL_CLK_PERIPH_PRE], clks[IMX6UL_CLK_PLL2_BUS]); clk_set_parent(clks[IMX6UL_CLK_PERIPH], clks[IMX6UL_CLK_PERIPH_PRE]); diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index de55c7d57438..96b35b8b3606 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -20,7 +20,7 @@ config ACPI_CPPC_CPUFREQ config ARM_ARMADA_37XX_CPUFREQ tristate "Armada 37xx CPUFreq support" - depends on ARCH_MVEBU + depends on ARCH_MVEBU && CPUFREQ_DT help This adds the CPUFreq driver support for Marvell Armada 37xx SoCs. The Armada 37xx PMU supports 4 frequency and VDD levels. diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index 77e485557498..6f693b7d5220 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -384,7 +384,7 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set) if (set) reg |= bit; else - reg &= bit; + reg &= ~bit; iowrite32(reg, addr); spin_unlock_irqrestore(&gpio->lock, flags); diff --git a/drivers/gpio/gpio-pci-idio-16.c b/drivers/gpio/gpio-pci-idio-16.c index 1948724d8c36..25d16b2af1c3 100644 --- a/drivers/gpio/gpio-pci-idio-16.c +++ b/drivers/gpio/gpio-pci-idio-16.c @@ -116,9 +116,9 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip, unsigned long word_mask; const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0); unsigned long port_state; - u8 __iomem ports[] = { - idio16gpio->reg->out0_7, idio16gpio->reg->out8_15, - idio16gpio->reg->in0_7, idio16gpio->reg->in8_15, + void __iomem *ports[] = { + &idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15, + &idio16gpio->reg->in0_7, &idio16gpio->reg->in8_15, }; /* clear bits array to a clean slate */ @@ -143,7 +143,7 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip, } /* read bits from current gpio port */ - port_state = ioread8(ports + i); + port_state = ioread8(ports[i]); /* store acquired bits at respective bits array offset */ bits[word_index] |= port_state << word_offset; diff --git a/drivers/gpio/gpio-pcie-idio-24.c b/drivers/gpio/gpio-pcie-idio-24.c index 835607ecf658..f953541e7890 100644 --- a/drivers/gpio/gpio-pcie-idio-24.c +++ b/drivers/gpio/gpio-pcie-idio-24.c @@ -206,10 +206,10 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip, unsigned long word_mask; const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0); unsigned long port_state; - u8 __iomem ports[] = { - idio24gpio->reg->out0_7, idio24gpio->reg->out8_15, - idio24gpio->reg->out16_23, idio24gpio->reg->in0_7, - idio24gpio->reg->in8_15, idio24gpio->reg->in16_23, + void __iomem *ports[] = { + &idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15, + &idio24gpio->reg->out16_23, &idio24gpio->reg->in0_7, + &idio24gpio->reg->in8_15, &idio24gpio->reg->in16_23, }; const unsigned long out_mode_mask = BIT(1); @@ -217,7 +217,7 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip, bitmap_zero(bits, chip->ngpio); /* get bits are evaluated a gpio port register at a time */ - for (i = 0; i < ARRAY_SIZE(ports); i++) { + for (i = 0; i < ARRAY_SIZE(ports) + 1; i++) { /* gpio offset in bits array */ bits_offset = i * gpio_reg_size; @@ -236,7 +236,7 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip, /* read bits from current gpio port (port 6 is TTL GPIO) */ if (i < 6) - port_state = ioread8(ports + i); + port_state = ioread8(ports[i]); else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask) port_state = ioread8(&idio24gpio->reg->ttl_out0_7); else @@ -301,9 +301,9 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip, const unsigned long port_mask = GENMASK(gpio_reg_size, 0); unsigned long flags; unsigned int out_state; - u8 __iomem ports[] = { - idio24gpio->reg->out0_7, idio24gpio->reg->out8_15, - idio24gpio->reg->out16_23 + void __iomem *ports[] = { + &idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15, + &idio24gpio->reg->out16_23 }; const unsigned long out_mode_mask = BIT(1); const unsigned int ttl_offset = 48; @@ -327,9 +327,9 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip, raw_spin_lock_irqsave(&idio24gpio->lock, flags); /* process output lines */ - out_state = ioread8(ports + i) & ~gpio_mask; + out_state = ioread8(ports[i]) & ~gpio_mask; out_state |= (*bits >> bits_offset) & gpio_mask; - iowrite8(out_state, ports + i); + iowrite8(out_state, ports[i]); raw_spin_unlock_irqrestore(&idio24gpio->lock, flags); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 43aeb07343ec..d8ccb500872f 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -497,7 +497,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) struct gpiohandle_request handlereq; struct linehandle_state *lh; struct file *file; - int fd, i, ret; + int fd, i, count = 0, ret; u32 lflags; if (copy_from_user(&handlereq, ip, sizeof(handlereq))) @@ -558,6 +558,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) if (ret) goto out_free_descs; lh->descs[i] = desc; + count = i; if (lflags & GPIOHANDLE_REQUEST_ACTIVE_LOW) set_bit(FLAG_ACTIVE_LOW, &desc->flags); @@ -628,7 +629,7 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip) out_put_unused_fd: put_unused_fd(fd); out_free_descs: - for (; i >= 0; i--) + for (i = 0; i < count; i++) gpiod_free(lh->descs[i]); kfree(lh->label); out_free_lh: @@ -902,7 +903,7 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip) desc = &gdev->descs[offset]; ret = gpiod_request(desc, le->label); if (ret) - goto out_free_desc; + goto out_free_label; le->desc = desc; le->eflags = eflags; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 09d35051fdd6..3fabf9f97022 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -419,9 +419,11 @@ int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id) if (other) { signed long r; - r = dma_fence_wait_timeout(other, false, MAX_SCHEDULE_TIMEOUT); + r = dma_fence_wait(other, true); if (r < 0) { - DRM_ERROR("Error (%ld) waiting for fence!\n", r); + if (r != -ERESTARTSYS) + DRM_ERROR("Error (%ld) waiting for fence!\n", r); + return r; } } 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 ace9ad578ca0..4304d9e408b8 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 @@ -83,21 +83,22 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ? I2C_MOT_TRUE : I2C_MOT_FALSE; enum ddc_result res; - ssize_t read_bytes; + uint32_t read_bytes = msg->size; if (WARN_ON(msg->size > 16)) return -E2BIG; switch (msg->request & ~DP_AUX_I2C_MOT) { case DP_AUX_NATIVE_READ: - read_bytes = dal_ddc_service_read_dpcd_data( + res = dal_ddc_service_read_dpcd_data( TO_DM_AUX(aux)->ddc_service, false, I2C_MOT_UNDEF, msg->address, msg->buffer, - msg->size); - return read_bytes; + msg->size, + &read_bytes); + break; case DP_AUX_NATIVE_WRITE: res = dal_ddc_service_write_dpcd_data( TO_DM_AUX(aux)->ddc_service, @@ -108,14 +109,15 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, msg->size); break; case DP_AUX_I2C_READ: - read_bytes = dal_ddc_service_read_dpcd_data( + res = dal_ddc_service_read_dpcd_data( TO_DM_AUX(aux)->ddc_service, true, mot, msg->address, msg->buffer, - msg->size); - return read_bytes; + msg->size, + &read_bytes); + break; case DP_AUX_I2C_WRITE: res = dal_ddc_service_write_dpcd_data( TO_DM_AUX(aux)->ddc_service, @@ -137,7 +139,9 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux, r == DDC_RESULT_SUCESSFULL); #endif - return msg->size; + if (res != DDC_RESULT_SUCESSFULL) + return -EIO; + return read_bytes; } static enum drm_connector_status diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 985fe8c22875..10a5807a7e8b 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -70,6 +70,10 @@ static enum bp_result get_firmware_info_v3_1( struct bios_parser *bp, struct dc_firmware_info *info); +static enum bp_result get_firmware_info_v3_2( + struct bios_parser *bp, + struct dc_firmware_info *info); + static struct atom_hpd_int_record *get_hpd_record(struct bios_parser *bp, struct atom_display_object_path_v2 *object); @@ -1321,9 +1325,11 @@ static enum bp_result bios_parser_get_firmware_info( case 3: switch (revision.minor) { case 1: - case 2: result = get_firmware_info_v3_1(bp, info); break; + case 2: + result = get_firmware_info_v3_2(bp, info); + break; default: break; } @@ -1383,6 +1389,84 @@ static enum bp_result get_firmware_info_v3_1( return BP_RESULT_OK; } +static enum bp_result get_firmware_info_v3_2( + struct bios_parser *bp, + struct dc_firmware_info *info) +{ + struct atom_firmware_info_v3_2 *firmware_info; + struct atom_display_controller_info_v4_1 *dce_info = NULL; + struct atom_common_table_header *header; + struct atom_data_revision revision; + struct atom_smu_info_v3_2 *smu_info_v3_2 = NULL; + struct atom_smu_info_v3_3 *smu_info_v3_3 = NULL; + + if (!info) + return BP_RESULT_BADINPUT; + + firmware_info = GET_IMAGE(struct atom_firmware_info_v3_2, + DATA_TABLES(firmwareinfo)); + + dce_info = GET_IMAGE(struct atom_display_controller_info_v4_1, + DATA_TABLES(dce_info)); + + if (!firmware_info || !dce_info) + return BP_RESULT_BADBIOSTABLE; + + memset(info, 0, sizeof(*info)); + + header = GET_IMAGE(struct atom_common_table_header, + DATA_TABLES(smu_info)); + get_atom_data_table_revision(header, &revision); + + if (revision.minor == 2) { + /* Vega12 */ + smu_info_v3_2 = GET_IMAGE(struct atom_smu_info_v3_2, + DATA_TABLES(smu_info)); + + if (!smu_info_v3_2) + return BP_RESULT_BADBIOSTABLE; + + info->default_engine_clk = smu_info_v3_2->bootup_dcefclk_10khz * 10; + } else if (revision.minor == 3) { + /* Vega20 */ + smu_info_v3_3 = GET_IMAGE(struct atom_smu_info_v3_3, + DATA_TABLES(smu_info)); + + if (!smu_info_v3_3) + return BP_RESULT_BADBIOSTABLE; + + info->default_engine_clk = smu_info_v3_3->bootup_dcefclk_10khz * 10; + } + + // We need to convert from 10KHz units into KHz units. + info->default_memory_clk = firmware_info->bootup_mclk_in10khz * 10; + + /* 27MHz for Vega10 & Vega12; 100MHz for Vega20 */ + info->pll_info.crystal_frequency = dce_info->dce_refclk_10khz * 10; + /* Hardcode frequency if BIOS gives no DCE Ref Clk */ + if (info->pll_info.crystal_frequency == 0) { + if (revision.minor == 2) + info->pll_info.crystal_frequency = 27000; + else if (revision.minor == 3) + info->pll_info.crystal_frequency = 100000; + } + /*dp_phy_ref_clk is not correct for atom_display_controller_info_v4_2, but we don't use it*/ + info->dp_phy_ref_clk = dce_info->dpphy_refclk_10khz * 10; + info->i2c_engine_ref_clk = dce_info->i2c_engine_refclk_10khz * 10; + + /* Get GPU PLL VCO Clock */ + if (bp->cmd_tbl.get_smu_clock_info != NULL) { + if (revision.minor == 2) + info->smu_gpu_pll_output_freq = + bp->cmd_tbl.get_smu_clock_info(bp, SMU9_SYSPLL0_ID) * 10; + else if (revision.minor == 3) + info->smu_gpu_pll_output_freq = + bp->cmd_tbl.get_smu_clock_info(bp, SMU11_SYSPLL3_0_ID) * 10; + } + + return BP_RESULT_OK; +} + static enum bp_result bios_parser_get_encoder_cap_info( struct dc_bios *dcb, struct graphics_object_id object_id, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index 49c2face1e7a..ae48d603ebd6 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -629,13 +629,14 @@ bool dal_ddc_service_query_ddc_data( return ret; } -ssize_t dal_ddc_service_read_dpcd_data( +enum ddc_result dal_ddc_service_read_dpcd_data( struct ddc_service *ddc, bool i2c, enum i2c_mot_mode mot, uint32_t address, uint8_t *data, - uint32_t len) + uint32_t len, + uint32_t *read) { struct aux_payload read_payload = { .i2c_over_aux = i2c, @@ -652,6 +653,8 @@ ssize_t dal_ddc_service_read_dpcd_data( .mot = mot }; + *read = 0; + if (len > DEFAULT_AUX_MAX_DATA_SIZE) { BREAK_TO_DEBUGGER(); return DDC_RESULT_FAILED_INVALID_OPERATION; @@ -661,7 +664,8 @@ ssize_t dal_ddc_service_read_dpcd_data( ddc->ctx->i2caux, ddc->ddc_pin, &command)) { - return (ssize_t)command.payloads->length; + *read = command.payloads->length; + return DDC_RESULT_SUCESSFULL; } return DDC_RESULT_FAILED_OPERATION; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index ade5b8ee9c3c..132eef3826e2 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -66,8 +66,8 @@ struct dc_plane_state *dc_create_plane_state(struct dc *dc) { struct dc *core_dc = dc; - struct dc_plane_state *plane_state = kzalloc(sizeof(*plane_state), - GFP_KERNEL); + struct dc_plane_state *plane_state = kvzalloc(sizeof(*plane_state), + GFP_KERNEL); if (NULL == plane_state) return NULL; @@ -120,7 +120,7 @@ static void dc_plane_state_free(struct kref *kref) { struct dc_plane_state *plane_state = container_of(kref, struct dc_plane_state, refcount); destruct(plane_state); - kfree(plane_state); + kvfree(plane_state); } void dc_plane_state_release(struct dc_plane_state *plane_state) @@ -136,7 +136,7 @@ void dc_gamma_retain(struct dc_gamma *gamma) static void dc_gamma_free(struct kref *kref) { struct dc_gamma *gamma = container_of(kref, struct dc_gamma, refcount); - kfree(gamma); + kvfree(gamma); } void dc_gamma_release(struct dc_gamma **gamma) @@ -147,7 +147,7 @@ void dc_gamma_release(struct dc_gamma **gamma) struct dc_gamma *dc_create_gamma(void) { - struct dc_gamma *gamma = kzalloc(sizeof(*gamma), GFP_KERNEL); + struct dc_gamma *gamma = kvzalloc(sizeof(*gamma), GFP_KERNEL); if (gamma == NULL) goto alloc_fail; @@ -167,7 +167,7 @@ void dc_transfer_func_retain(struct dc_transfer_func *tf) static void dc_transfer_func_free(struct kref *kref) { struct dc_transfer_func *tf = container_of(kref, struct dc_transfer_func, refcount); - kfree(tf); + kvfree(tf); } void dc_transfer_func_release(struct dc_transfer_func *tf) @@ -177,7 +177,7 @@ void dc_transfer_func_release(struct dc_transfer_func *tf) struct dc_transfer_func *dc_create_transfer_func(void) { - struct dc_transfer_func *tf = kzalloc(sizeof(*tf), GFP_KERNEL); + struct dc_transfer_func *tf = kvzalloc(sizeof(*tf), GFP_KERNEL); if (tf == NULL) goto alloc_fail; diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h index 090b7a8dd67b..30b3a08b91be 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h +++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h @@ -102,13 +102,14 @@ bool dal_ddc_service_query_ddc_data( uint8_t *read_buf, uint32_t read_size); -ssize_t dal_ddc_service_read_dpcd_data( +enum ddc_result dal_ddc_service_read_dpcd_data( struct ddc_service *ddc, bool i2c, enum i2c_mot_mode mot, uint32_t address, uint8_t *data, - uint32_t len); + uint32_t len, + uint32_t *read); enum ddc_result dal_ddc_service_write_dpcd_data( struct ddc_service *ddc, diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index 9831cb5eaa7c..9b0a04f99ac8 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -113,9 +113,14 @@ #define AI_GREENLAND_P_A0 1 #define AI_GREENLAND_P_A1 2 +#define AI_UNKNOWN 0xFF -#define ASICREV_IS_GREENLAND_M(eChipRev) (eChipRev < AI_UNKNOWN) -#define ASICREV_IS_GREENLAND_P(eChipRev) (eChipRev < AI_UNKNOWN) +#define AI_VEGA12_P_A0 20 +#define ASICREV_IS_GREENLAND_M(eChipRev) (eChipRev < AI_VEGA12_P_A0) +#define ASICREV_IS_GREENLAND_P(eChipRev) (eChipRev < AI_VEGA12_P_A0) + +#define ASICREV_IS_VEGA12_P(eChipRev) ((eChipRev >= AI_VEGA12_P_A0) && (eChipRev < AI_UNKNOWN)) +#define ASICREV_IS_VEGA12_p(eChipRev) ((eChipRev >= AI_VEGA12_P_A0) && (eChipRev < AI_UNKNOWN)) /* DCN1_0 */ #define INTERNAL_REV_RAVEN_A0 0x00 /* First spin of Raven */ diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c index e7e374f56864..b3747a019deb 100644 --- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c +++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c @@ -1093,19 +1093,19 @@ bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf, output_tf->type = TF_TYPE_DISTRIBUTED_POINTS; - rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS), - GFP_KERNEL); + rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS), + GFP_KERNEL); if (!rgb_user) goto rgb_user_alloc_fail; - rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS), - GFP_KERNEL); + rgb_regamma = kvzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + _EXTRA_POINTS), + GFP_KERNEL); if (!rgb_regamma) goto rgb_regamma_alloc_fail; - axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + 3), - GFP_KERNEL); + axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + 3), + GFP_KERNEL); if (!axix_x) goto axix_x_alloc_fail; - coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL); + coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL); if (!coeff) goto coeff_alloc_fail; @@ -1157,13 +1157,13 @@ bool mod_color_calculate_regamma_params(struct dc_transfer_func *output_tf, ret = true; - kfree(coeff); + kvfree(coeff); coeff_alloc_fail: - kfree(axix_x); + kvfree(axix_x); axix_x_alloc_fail: - kfree(rgb_regamma); + kvfree(rgb_regamma); rgb_regamma_alloc_fail: - kfree(rgb_user); + kvfree(rgb_user); rgb_user_alloc_fail: return ret; } @@ -1192,19 +1192,19 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf, input_tf->type = TF_TYPE_DISTRIBUTED_POINTS; - rgb_user = kzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS), - GFP_KERNEL); + rgb_user = kvzalloc(sizeof(*rgb_user) * (ramp->num_entries + _EXTRA_POINTS), + GFP_KERNEL); if (!rgb_user) goto rgb_user_alloc_fail; - curve = kzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS), - GFP_KERNEL); + curve = kvzalloc(sizeof(*curve) * (MAX_HW_POINTS + _EXTRA_POINTS), + GFP_KERNEL); if (!curve) goto curve_alloc_fail; - axix_x = kzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS), - GFP_KERNEL); + axix_x = kvzalloc(sizeof(*axix_x) * (ramp->num_entries + _EXTRA_POINTS), + GFP_KERNEL); if (!axix_x) goto axix_x_alloc_fail; - coeff = kzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL); + coeff = kvzalloc(sizeof(*coeff) * (MAX_HW_POINTS + _EXTRA_POINTS), GFP_KERNEL); if (!coeff) goto coeff_alloc_fail; @@ -1246,13 +1246,13 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf, ret = true; - kfree(coeff); + kvfree(coeff); coeff_alloc_fail: - kfree(axix_x); + kvfree(axix_x); axix_x_alloc_fail: - kfree(curve); + kvfree(curve); curve_alloc_fail: - kfree(rgb_user); + kvfree(rgb_user); rgb_user_alloc_fail: return ret; @@ -1281,8 +1281,9 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans, } ret = true; } else if (trans == TRANSFER_FUNCTION_PQ) { - rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + - _EXTRA_POINTS), GFP_KERNEL); + rgb_regamma = kvzalloc(sizeof(*rgb_regamma) * + (MAX_HW_POINTS + _EXTRA_POINTS), + GFP_KERNEL); if (!rgb_regamma) goto rgb_regamma_alloc_fail; points->end_exponent = 7; @@ -1302,11 +1303,12 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans, } ret = true; - kfree(rgb_regamma); + kvfree(rgb_regamma); } else if (trans == TRANSFER_FUNCTION_SRGB || trans == TRANSFER_FUNCTION_BT709) { - rgb_regamma = kzalloc(sizeof(*rgb_regamma) * (MAX_HW_POINTS + - _EXTRA_POINTS), GFP_KERNEL); + rgb_regamma = kvzalloc(sizeof(*rgb_regamma) * + (MAX_HW_POINTS + _EXTRA_POINTS), + GFP_KERNEL); if (!rgb_regamma) goto rgb_regamma_alloc_fail; points->end_exponent = 0; @@ -1324,7 +1326,7 @@ bool mod_color_calculate_curve(enum dc_transfer_func_predefined trans, } ret = true; - kfree(rgb_regamma); + kvfree(rgb_regamma); } rgb_regamma_alloc_fail: return ret; @@ -1348,8 +1350,9 @@ bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans, } ret = true; } else if (trans == TRANSFER_FUNCTION_PQ) { - rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS + - _EXTRA_POINTS), GFP_KERNEL); + rgb_degamma = kvzalloc(sizeof(*rgb_degamma) * + (MAX_HW_POINTS + _EXTRA_POINTS), + GFP_KERNEL); if (!rgb_degamma) goto rgb_degamma_alloc_fail; @@ -1364,11 +1367,12 @@ bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans, } ret = true; - kfree(rgb_degamma); + kvfree(rgb_degamma); } else if (trans == TRANSFER_FUNCTION_SRGB || trans == TRANSFER_FUNCTION_BT709) { - rgb_degamma = kzalloc(sizeof(*rgb_degamma) * (MAX_HW_POINTS + - _EXTRA_POINTS), GFP_KERNEL); + rgb_degamma = kvzalloc(sizeof(*rgb_degamma) * + (MAX_HW_POINTS + _EXTRA_POINTS), + GFP_KERNEL); if (!rgb_degamma) goto rgb_degamma_alloc_fail; @@ -1382,7 +1386,7 @@ bool mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans, } ret = true; - kfree(rgb_degamma); + kvfree(rgb_degamma); } points->end_exponent = 0; points->x_point_at_y1_red = 1; diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index 0f5ad54d3fd3..de177ce8ca80 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -501,6 +501,32 @@ enum atom_cooling_solution_id{ LIQUID_COOLING = 0x01 }; +struct atom_firmware_info_v3_2 { + struct atom_common_table_header table_header; + uint32_t firmware_revision; + uint32_t bootup_sclk_in10khz; + uint32_t bootup_mclk_in10khz; + uint32_t firmware_capability; // enum atombios_firmware_capability + uint32_t main_call_parser_entry; /* direct address of main parser call in VBIOS binary. */ + uint32_t bios_scratch_reg_startaddr; // 1st bios scratch register dword address + uint16_t bootup_vddc_mv; + uint16_t bootup_vddci_mv; + uint16_t bootup_mvddc_mv; + uint16_t bootup_vddgfx_mv; + uint8_t mem_module_id; + uint8_t coolingsolution_id; /*0: Air cooling; 1: Liquid cooling ... */ + uint8_t reserved1[2]; + uint32_t mc_baseaddr_high; + uint32_t mc_baseaddr_low; + uint8_t board_i2c_feature_id; // enum of atom_board_i2c_feature_id_def + uint8_t board_i2c_feature_gpio_id; // i2c id find in gpio_lut data table gpio_id + uint8_t board_i2c_feature_slave_addr; + uint8_t reserved3; + uint16_t bootup_mvddq_mv; + uint16_t bootup_mvpp_mv; + uint32_t zfbstartaddrin16mb; + uint32_t reserved2[3]; +}; /* *************************************************************************** @@ -1169,7 +1195,29 @@ struct atom_gfx_info_v2_2 uint32_t rlc_gpu_timer_refclk; }; - +struct atom_gfx_info_v2_3 { + struct atom_common_table_header table_header; + uint8_t gfxip_min_ver; + uint8_t gfxip_max_ver; + uint8_t max_shader_engines; + uint8_t max_tile_pipes; + uint8_t max_cu_per_sh; + uint8_t max_sh_per_se; + uint8_t max_backends_per_se; + uint8_t max_texture_channel_caches; + uint32_t regaddr_cp_dma_src_addr; + uint32_t regaddr_cp_dma_src_addr_hi; + uint32_t regaddr_cp_dma_dst_addr; + uint32_t regaddr_cp_dma_dst_addr_hi; + uint32_t regaddr_cp_dma_command; + uint32_t regaddr_cp_status; + uint32_t regaddr_rlc_gpu_clock_32; + uint32_t rlc_gpu_timer_refclk; + uint8_t active_cu_per_sh; + uint8_t active_rb_per_se; + uint16_t gcgoldenoffset; + uint32_t rm21_sram_vmin_value; +}; /* *************************************************************************** @@ -1198,6 +1246,76 @@ struct atom_smu_info_v3_1 uint8_t fw_ctf_polarity; // GPIO polarity for CTF }; +struct atom_smu_info_v3_2 { + struct atom_common_table_header table_header; + uint8_t smuip_min_ver; + uint8_t smuip_max_ver; + uint8_t smu_rsd1; + uint8_t gpuclk_ss_mode; + uint16_t sclk_ss_percentage; + uint16_t sclk_ss_rate_10hz; + uint16_t gpuclk_ss_percentage; // in unit of 0.001% + uint16_t gpuclk_ss_rate_10hz; + uint32_t core_refclk_10khz; + uint8_t ac_dc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for AC/DC switching, =0xff means invalid + uint8_t ac_dc_polarity; // GPIO polarity for AC/DC switching + uint8_t vr0hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR0 HOT event, =0xff means invalid + uint8_t vr0hot_polarity; // GPIO polarity for VR0 HOT event + uint8_t vr1hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid + uint8_t vr1hot_polarity; // GPIO polarity for VR1 HOT event + uint8_t fw_ctf_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid + uint8_t fw_ctf_polarity; // GPIO polarity for CTF + uint8_t pcc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid + uint8_t pcc_gpio_polarity; // GPIO polarity for CTF + uint16_t smugoldenoffset; + uint32_t gpupll_vco_freq_10khz; + uint32_t bootup_smnclk_10khz; + uint32_t bootup_socclk_10khz; + uint32_t bootup_mp0clk_10khz; + uint32_t bootup_mp1clk_10khz; + uint32_t bootup_lclk_10khz; + uint32_t bootup_dcefclk_10khz; + uint32_t ctf_threshold_override_value; + uint32_t reserved[5]; +}; + +struct atom_smu_info_v3_3 { + struct atom_common_table_header table_header; + uint8_t smuip_min_ver; + uint8_t smuip_max_ver; + uint8_t smu_rsd1; + uint8_t gpuclk_ss_mode; + uint16_t sclk_ss_percentage; + uint16_t sclk_ss_rate_10hz; + uint16_t gpuclk_ss_percentage; // in unit of 0.001% + uint16_t gpuclk_ss_rate_10hz; + uint32_t core_refclk_10khz; + uint8_t ac_dc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for AC/DC switching, =0xff means invalid + uint8_t ac_dc_polarity; // GPIO polarity for AC/DC switching + uint8_t vr0hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR0 HOT event, =0xff means invalid + uint8_t vr0hot_polarity; // GPIO polarity for VR0 HOT event + uint8_t vr1hot_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for VR1 HOT event , =0xff means invalid + uint8_t vr1hot_polarity; // GPIO polarity for VR1 HOT event + uint8_t fw_ctf_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for CTF, =0xff means invalid + uint8_t fw_ctf_polarity; // GPIO polarity for CTF + uint8_t pcc_gpio_bit; // GPIO bit shift in SMU_GPIOPAD_A configured for PCC, =0xff means invalid + uint8_t pcc_gpio_polarity; // GPIO polarity for CTF + uint16_t smugoldenoffset; + uint32_t gpupll_vco_freq_10khz; + uint32_t bootup_smnclk_10khz; + uint32_t bootup_socclk_10khz; + uint32_t bootup_mp0clk_10khz; + uint32_t bootup_mp1clk_10khz; + uint32_t bootup_lclk_10khz; + uint32_t bootup_dcefclk_10khz; + uint32_t ctf_threshold_override_value; + uint32_t syspll3_0_vco_freq_10khz; + uint32_t syspll3_1_vco_freq_10khz; + uint32_t bootup_fclk_10khz; + uint32_t bootup_waflclk_10khz; + uint32_t reserved[3]; +}; + /* *************************************************************************** Data Table smc_dpm_info structure @@ -1283,7 +1401,6 @@ struct atom_smc_dpm_info_v4_1 uint32_t boardreserved[10]; }; - /* *************************************************************************** Data Table asic_profiling_info structure @@ -1864,6 +1981,55 @@ enum atom_smu9_syspll0_clock_id SMU9_SYSPLL0_DISPCLK_ID = 11, // DISPCLK }; +enum atom_smu11_syspll_id { + SMU11_SYSPLL0_ID = 0, + SMU11_SYSPLL1_0_ID = 1, + SMU11_SYSPLL1_1_ID = 2, + SMU11_SYSPLL1_2_ID = 3, + SMU11_SYSPLL2_ID = 4, + SMU11_SYSPLL3_0_ID = 5, + SMU11_SYSPLL3_1_ID = 6, +}; + + +enum atom_smu11_syspll0_clock_id { + SMU11_SYSPLL0_SOCCLK_ID = 0, // SOCCLK + SMU11_SYSPLL0_MP0CLK_ID = 1, // MP0CLK + SMU11_SYSPLL0_DCLK_ID = 2, // DCLK + SMU11_SYSPLL0_VCLK_ID = 3, // VCLK + SMU11_SYSPLL0_ECLK_ID = 4, // ECLK + SMU11_SYSPLL0_DCEFCLK_ID = 5, // DCEFCLK +}; + + +enum atom_smu11_syspll1_0_clock_id { + SMU11_SYSPLL1_0_UCLKA_ID = 0, // UCLK_a +}; + +enum atom_smu11_syspll1_1_clock_id { + SMU11_SYSPLL1_0_UCLKB_ID = 0, // UCLK_b +}; + +enum atom_smu11_syspll1_2_clock_id { + SMU11_SYSPLL1_0_FCLK_ID = 0, // FCLK +}; + +enum atom_smu11_syspll2_clock_id { + SMU11_SYSPLL2_GFXCLK_ID = 0, // GFXCLK +}; + +enum atom_smu11_syspll3_0_clock_id { + SMU11_SYSPLL3_0_WAFCLK_ID = 0, // WAFCLK + SMU11_SYSPLL3_0_DISPCLK_ID = 1, // DISPCLK + SMU11_SYSPLL3_0_DPREFCLK_ID = 2, // DPREFCLK +}; + +enum atom_smu11_syspll3_1_clock_id { + SMU11_SYSPLL3_1_MP1CLK_ID = 0, // MP1CLK + SMU11_SYSPLL3_1_SMNCLK_ID = 1, // SMNCLK + SMU11_SYSPLL3_1_LCLK_ID = 2, // LCLK +}; + struct atom_get_smu_clock_info_output_parameters_v3_1 { union { diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index 26fbeafc3c96..18b5b2ff47fe 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -79,12 +79,13 @@ #define PCIE_BUS_CLK 10000 #define TCLK (PCIE_BUS_CLK / 10) -static const struct profile_mode_setting smu7_profiling[5] = +static const struct profile_mode_setting smu7_profiling[6] = {{1, 0, 100, 30, 1, 0, 100, 10}, {1, 10, 0, 30, 0, 0, 0, 0}, {0, 0, 0, 0, 1, 10, 16, 31}, {1, 0, 11, 50, 1, 0, 100, 10}, {1, 0, 5, 30, 0, 0, 0, 0}, + {0, 0, 0, 0, 0, 0, 0, 0}, }; /** Values for the CG_THERMAL_CTRL::DPM_EVENT_SRC field. */ @@ -4864,6 +4865,17 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf) len = sizeof(smu7_profiling) / sizeof(struct profile_mode_setting); for (i = 0; i < len; i++) { + if (i == hwmgr->power_profile_mode) { + size += sprintf(buf + size, "%3d %14s %s: %8d %16d %16d %16d %16d %16d\n", + i, profile_name[i], "*", + data->current_profile_setting.sclk_up_hyst, + data->current_profile_setting.sclk_down_hyst, + data->current_profile_setting.sclk_activity, + data->current_profile_setting.mclk_up_hyst, + data->current_profile_setting.mclk_down_hyst, + data->current_profile_setting.mclk_activity); + continue; + } if (smu7_profiling[i].bupdate_sclk) size += sprintf(buf + size, "%3d %16s: %8d %16d %16d ", i, profile_name[i], smu7_profiling[i].sclk_up_hyst, @@ -4883,24 +4895,6 @@ static int smu7_get_power_profile_mode(struct pp_hwmgr *hwmgr, char *buf) "-", "-", "-"); } - size += sprintf(buf + size, "%3d %16s: %8d %16d %16d %16d %16d %16d\n", - i, profile_name[i], - data->custom_profile_setting.sclk_up_hyst, - data->custom_profile_setting.sclk_down_hyst, - data->custom_profile_setting.sclk_activity, - data->custom_profile_setting.mclk_up_hyst, - data->custom_profile_setting.mclk_down_hyst, - data->custom_profile_setting.mclk_activity); - - size += sprintf(buf + size, "%3s %16s: %8d %16d %16d %16d %16d %16d\n", - "*", "CURRENT", - data->current_profile_setting.sclk_up_hyst, - data->current_profile_setting.sclk_down_hyst, - data->current_profile_setting.sclk_activity, - data->current_profile_setting.mclk_up_hyst, - data->current_profile_setting.mclk_down_hyst, - data->current_profile_setting.mclk_activity); - return size; } @@ -4939,16 +4933,16 @@ static int smu7_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint if (size < 8) return -EINVAL; - data->custom_profile_setting.bupdate_sclk = input[0]; - data->custom_profile_setting.sclk_up_hyst = input[1]; - data->custom_profile_setting.sclk_down_hyst = input[2]; - data->custom_profile_setting.sclk_activity = input[3]; - data->custom_profile_setting.bupdate_mclk = input[4]; - data->custom_profile_setting.mclk_up_hyst = input[5]; - data->custom_profile_setting.mclk_down_hyst = input[6]; - data->custom_profile_setting.mclk_activity = input[7]; - if (!smum_update_dpm_settings(hwmgr, &data->custom_profile_setting)) { - memcpy(&data->current_profile_setting, &data->custom_profile_setting, sizeof(struct profile_mode_setting)); + tmp.bupdate_sclk = input[0]; + tmp.sclk_up_hyst = input[1]; + tmp.sclk_down_hyst = input[2]; + tmp.sclk_activity = input[3]; + tmp.bupdate_mclk = input[4]; + tmp.mclk_up_hyst = input[5]; + tmp.mclk_down_hyst = input[6]; + tmp.mclk_activity = input[7]; + if (!smum_update_dpm_settings(hwmgr, &tmp)) { + memcpy(&data->current_profile_setting, &tmp, sizeof(struct profile_mode_setting)); hwmgr->power_profile_mode = mode; } break; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h index f40179c9ca97..b8d0bb378595 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h @@ -325,7 +325,6 @@ struct smu7_hwmgr { uint16_t mem_latency_high; uint16_t mem_latency_low; uint32_t vr_config; - struct profile_mode_setting custom_profile_setting; struct profile_mode_setting current_profile_setting; }; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c index 03bc7453f3b1..d9e92e306535 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c @@ -852,12 +852,10 @@ int smu7_set_power_limit(struct pp_hwmgr *hwmgr, uint32_t n) { struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); - n = (n & 0xff) << 8; - if (data->power_containment_features & POWERCONTAINMENT_FEATURE_PkgPwrLimit) return smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_PkgPwrSetLimit, n); + PPSMC_MSG_PkgPwrSetLimit, n<<8); return 0; } diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig index 3aa65bdecb0e..684ac626ac53 100644 --- a/drivers/gpu/drm/bridge/Kconfig +++ b/drivers/gpu/drm/bridge/Kconfig @@ -74,6 +74,7 @@ config DRM_SIL_SII8620 tristate "Silicon Image SII8620 HDMI/MHL bridge" depends on OF && RC_CORE select DRM_KMS_HELPER + imply EXTCON help Silicon Image SII8620 HDMI/MHL bridge chip driver. diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 7d25c42f22db..c825c76edc1d 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -155,6 +155,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) state->connectors[i].state); state->connectors[i].ptr = NULL; state->connectors[i].state = NULL; + state->connectors[i].old_state = NULL; + state->connectors[i].new_state = NULL; drm_connector_put(connector); } @@ -169,6 +171,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) state->crtcs[i].ptr = NULL; state->crtcs[i].state = NULL; + state->crtcs[i].old_state = NULL; + state->crtcs[i].new_state = NULL; } for (i = 0; i < config->num_total_plane; i++) { @@ -181,6 +185,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) state->planes[i].state); state->planes[i].ptr = NULL; state->planes[i].state = NULL; + state->planes[i].old_state = NULL; + state->planes[i].new_state = NULL; } for (i = 0; i < state->num_private_objs; i++) { @@ -190,6 +196,8 @@ void drm_atomic_state_default_clear(struct drm_atomic_state *state) state->private_objs[i].state); state->private_objs[i].ptr = NULL; state->private_objs[i].state = NULL; + state->private_objs[i].old_state = NULL; + state->private_objs[i].new_state = NULL; } state->num_private_objs = 0; diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c index a1b9338736e3..c2c21d839727 100644 --- a/drivers/gpu/drm/drm_drv.c +++ b/drivers/gpu/drm/drm_drv.c @@ -716,7 +716,7 @@ static void remove_compat_control_link(struct drm_device *dev) if (!minor) return; - name = kasprintf(GFP_KERNEL, "controlD%d", minor->index); + name = kasprintf(GFP_KERNEL, "controlD%d", minor->index + 64); if (!name) return; diff --git a/drivers/gpu/drm/drm_dumb_buffers.c b/drivers/gpu/drm/drm_dumb_buffers.c index 39ac15ce4702..9e2ae02f31e0 100644 --- a/drivers/gpu/drm/drm_dumb_buffers.c +++ b/drivers/gpu/drm/drm_dumb_buffers.c @@ -65,12 +65,13 @@ int drm_mode_create_dumb_ioctl(struct drm_device *dev, return -EINVAL; /* overflow checks for 32bit size calculations */ - /* NOTE: DIV_ROUND_UP() can overflow */ + if (args->bpp > U32_MAX - 8) + return -EINVAL; cpp = DIV_ROUND_UP(args->bpp, 8); - if (!cpp || cpp > 0xffffffffU / args->width) + if (cpp > U32_MAX / args->width) return -EINVAL; stride = cpp * args->width; - if (args->height > 0xffffffffU / stride) + if (args->height > U32_MAX / stride) return -EINVAL; /* test for wrap-around */ diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c index e394799979a6..6d9b9453707c 100644 --- a/drivers/gpu/drm/drm_file.c +++ b/drivers/gpu/drm/drm_file.c @@ -212,6 +212,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor) return -ENOMEM; filp->private_data = priv; + filp->f_mode |= FMODE_UNSIGNED_OFFSET; priv->filp = filp; priv->pid = get_pid(task_pid(current)); priv->minor = minor; diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index abd84cbcf1c2..09c4bc0b1859 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -954,8 +954,6 @@ static int hdmi_create_connector(struct drm_encoder *encoder) drm_mode_connector_attach_encoder(connector, encoder); if (hdata->bridge) { - encoder->bridge = hdata->bridge; - hdata->bridge->encoder = encoder; ret = drm_bridge_attach(encoder, hdata->bridge, NULL); if (ret) DRM_ERROR("Failed to attach bridge\n"); diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index 257299ec95c4..272c79f5f5bf 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -473,7 +473,7 @@ static void vp_video_buffer(struct mixer_context *ctx, chroma_addr[1] = chroma_addr[0] + 0x40; } else { luma_addr[1] = luma_addr[0] + fb->pitches[0]; - chroma_addr[1] = chroma_addr[0] + fb->pitches[0]; + chroma_addr[1] = chroma_addr[0] + fb->pitches[1]; } } else { luma_addr[1] = 0; @@ -482,6 +482,7 @@ static void vp_video_buffer(struct mixer_context *ctx, spin_lock_irqsave(&ctx->reg_slock, flags); + vp_reg_write(ctx, VP_SHADOW_UPDATE, 1); /* interlace or progressive scan mode */ val = (test_bit(MXR_BIT_INTERLACE, &ctx->flags) ? ~0 : 0); vp_reg_writemask(ctx, VP_MODE, val, VP_MODE_LINE_SKIP); @@ -495,21 +496,23 @@ static void vp_video_buffer(struct mixer_context *ctx, vp_reg_write(ctx, VP_IMG_SIZE_Y, VP_IMG_HSIZE(fb->pitches[0]) | VP_IMG_VSIZE(fb->height)); /* chroma plane for NV12/NV21 is half the height of the luma plane */ - vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[0]) | + vp_reg_write(ctx, VP_IMG_SIZE_C, VP_IMG_HSIZE(fb->pitches[1]) | VP_IMG_VSIZE(fb->height / 2)); vp_reg_write(ctx, VP_SRC_WIDTH, state->src.w); - vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h); vp_reg_write(ctx, VP_SRC_H_POSITION, VP_SRC_H_POSITION_VAL(state->src.x)); - vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y); - vp_reg_write(ctx, VP_DST_WIDTH, state->crtc.w); vp_reg_write(ctx, VP_DST_H_POSITION, state->crtc.x); + if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) { + vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h / 2); + vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y / 2); vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h / 2); vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y / 2); } else { + vp_reg_write(ctx, VP_SRC_HEIGHT, state->src.h); + vp_reg_write(ctx, VP_SRC_V_POSITION, state->src.y); vp_reg_write(ctx, VP_DST_HEIGHT, state->crtc.h); vp_reg_write(ctx, VP_DST_V_POSITION, state->crtc.y); } @@ -699,6 +702,15 @@ static irqreturn_t mixer_irq_handler(int irq, void *arg) /* interlace scan need to check shadow register */ if (test_bit(MXR_BIT_INTERLACE, &ctx->flags)) { + if (test_bit(MXR_BIT_VP_ENABLED, &ctx->flags) && + vp_reg_read(ctx, VP_SHADOW_UPDATE)) + goto out; + + base = mixer_reg_read(ctx, MXR_CFG); + shadow = mixer_reg_read(ctx, MXR_CFG_S); + if (base != shadow) + goto out; + base = mixer_reg_read(ctx, MXR_GRAPHIC_BASE(0)); shadow = mixer_reg_read(ctx, MXR_GRAPHIC_BASE_S(0)); if (base != shadow) diff --git a/drivers/gpu/drm/exynos/regs-mixer.h b/drivers/gpu/drm/exynos/regs-mixer.h index c311f571bdf9..189cfa2470a8 100644 --- a/drivers/gpu/drm/exynos/regs-mixer.h +++ b/drivers/gpu/drm/exynos/regs-mixer.h @@ -47,6 +47,7 @@ #define MXR_MO 0x0304 #define MXR_RESOLUTION 0x0310 +#define MXR_CFG_S 0x2004 #define MXR_GRAPHIC0_BASE_S 0x2024 #define MXR_GRAPHIC1_BASE_S 0x2044 diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c index d596a8302ca3..854bd51b9478 100644 --- a/drivers/gpu/drm/i915/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/i915_gem_userptr.c @@ -778,6 +778,9 @@ i915_gem_userptr_ioctl(struct drm_device *dev, I915_USERPTR_UNSYNCHRONIZED)) return -EINVAL; + if (!args->user_size) + return -EINVAL; + if (offset_in_page(args->user_ptr | args->user_size)) return -EINVAL; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e6a8c0ee7df1..8a69a9275e28 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7326,6 +7326,9 @@ enum { #define SLICE_ECO_CHICKEN0 _MMIO(0x7308) #define PIXEL_MASK_CAMMING_DISABLE (1 << 14) +#define GEN9_WM_CHICKEN3 _MMIO(0x5588) +#define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9) + /* WaCatErrorRejectionIssue */ #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG _MMIO(0x9030) #define GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB (1<<11) diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 32d24c69da3c..704ddb4d3ca7 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -2302,9 +2302,44 @@ static int bdw_modeset_calc_cdclk(struct drm_atomic_state *state) return 0; } +static int skl_dpll0_vco(struct intel_atomic_state *intel_state) +{ + struct drm_i915_private *dev_priv = to_i915(intel_state->base.dev); + struct intel_crtc *crtc; + struct intel_crtc_state *crtc_state; + int vco, i; + + vco = intel_state->cdclk.logical.vco; + if (!vco) + vco = dev_priv->skl_preferred_vco_freq; + + for_each_new_intel_crtc_in_state(intel_state, crtc, crtc_state, i) { + if (!crtc_state->base.enable) + continue; + + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_EDP)) + continue; + + /* + * DPLL0 VCO may need to be adjusted to get the correct + * clock for eDP. This will affect cdclk as well. + */ + switch (crtc_state->port_clock / 2) { + case 108000: + case 216000: + vco = 8640000; + break; + default: + vco = 8100000; + break; + } + } + + return vco; +} + static int skl_modeset_calc_cdclk(struct drm_atomic_state *state) { - struct drm_i915_private *dev_priv = to_i915(state->dev); struct intel_atomic_state *intel_state = to_intel_atomic_state(state); int min_cdclk, cdclk, vco; @@ -2312,9 +2347,7 @@ static int skl_modeset_calc_cdclk(struct drm_atomic_state *state) if (min_cdclk < 0) return min_cdclk; - vco = intel_state->cdclk.logical.vco; - if (!vco) - vco = dev_priv->skl_preferred_vco_freq; + vco = skl_dpll0_vco(intel_state); /* * FIXME should also account for plane ratio diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3b48fd2561fe..56004ffbd8bb 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15178,6 +15178,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev) memset(&crtc->base.mode, 0, sizeof(crtc->base.mode)); if (crtc_state->base.active) { intel_mode_from_pipe_config(&crtc->base.mode, crtc_state); + crtc->base.mode.hdisplay = crtc_state->pipe_src_w; + crtc->base.mode.vdisplay = crtc_state->pipe_src_h; intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode, crtc_state); WARN_ON(drm_atomic_set_mode_for_crtc(crtc->base.state, &crtc->base.mode)); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 9a4a51e79fa1..b7b4cfdeb974 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -1881,26 +1881,6 @@ found: reduce_m_n); } - /* - * DPLL0 VCO may need to be adjusted to get the correct - * clock for eDP. This will affect cdclk as well. - */ - if (intel_dp_is_edp(intel_dp) && IS_GEN9_BC(dev_priv)) { - int vco; - - switch (pipe_config->port_clock / 2) { - case 108000: - case 216000: - vco = 8640000; - break; - default: - vco = 8100000; - break; - } - - to_intel_atomic_state(pipe_config->base.state)->cdclk.logical.vco = vco; - } - if (!HAS_DDI(dev_priv)) intel_dp_set_clock(encoder, pipe_config); diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 4ba139c27fba..f7c25828d3bb 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -1149,6 +1149,10 @@ static int gen9_init_workarounds(struct intel_engine_cs *engine) WA_SET_FIELD_MASKED(GEN8_CS_CHICKEN1, GEN9_PREEMPT_GPGPU_LEVEL_MASK, GEN9_PREEMPT_GPGPU_COMMAND_LEVEL); + /* WaClearHIZ_WM_CHICKEN3:bxt,glk */ + if (IS_GEN9_LP(dev_priv)) + WA_SET_BIT_MASKED(GEN9_WM_CHICKEN3, GEN9_FACTOR_IN_CLR_VAL_HIZ); + /* WaVFEStateAfterPipeControlwithMediaStateClear:skl,bxt,glk,cfl */ ret = wa_ring_whitelist_reg(engine, GEN9_CTX_PREEMPT_REG); if (ret) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index e3a5f673ff67..8704f7f8d072 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -884,6 +884,7 @@ static void execlists_submission_tasklet(unsigned long data) head = execlists->csb_head; tail = READ_ONCE(buf[write_idx]); + rmb(); /* Hopefully paired with a wmb() in HW */ } GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n", engine->name, diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index d35d2d50f595..8691c86f579c 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -326,7 +326,8 @@ static void intel_enable_lvds(struct intel_encoder *encoder, I915_WRITE(PP_CONTROL(0), I915_READ(PP_CONTROL(0)) | PANEL_POWER_ON); POSTING_READ(lvds_encoder->reg); - if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 1000)) + + if (intel_wait_for_register(dev_priv, PP_STATUS(0), PP_ON, PP_ON, 5000)) DRM_ERROR("timed out waiting for panel to power on\n"); intel_panel_enable_backlight(pipe_config, conn_state); diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 6f402c4f2bdd..ab61c038f42c 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -214,7 +214,6 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align, INIT_LIST_HEAD(&nvbo->entry); INIT_LIST_HEAD(&nvbo->vma_list); nvbo->bo.bdev = &drm->ttm.bdev; - nvbo->cli = cli; /* This is confusing, and doesn't actually mean we want an uncached * mapping, but is what NOUVEAU_GEM_DOMAIN_COHERENT gets translated diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h index be8e00b49cde..73c48440d4d7 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.h +++ b/drivers/gpu/drm/nouveau/nouveau_bo.h @@ -26,8 +26,6 @@ struct nouveau_bo { struct list_head vma_list; - struct nouveau_cli *cli; - unsigned contig:1; unsigned page:5; unsigned kind:8; diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c index dff51a0ee028..8c093ca4222e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_ttm.c +++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c @@ -63,7 +63,7 @@ nouveau_vram_manager_new(struct ttm_mem_type_manager *man, struct ttm_mem_reg *reg) { struct nouveau_bo *nvbo = nouveau_bo(bo); - struct nouveau_drm *drm = nvbo->cli->drm; + struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_mem *mem; int ret; @@ -103,7 +103,7 @@ nouveau_gart_manager_new(struct ttm_mem_type_manager *man, struct ttm_mem_reg *reg) { struct nouveau_bo *nvbo = nouveau_bo(bo); - struct nouveau_drm *drm = nvbo->cli->drm; + struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_mem *mem; int ret; @@ -131,7 +131,7 @@ nv04_gart_manager_new(struct ttm_mem_type_manager *man, struct ttm_mem_reg *reg) { struct nouveau_bo *nvbo = nouveau_bo(bo); - struct nouveau_drm *drm = nvbo->cli->drm; + struct nouveau_drm *drm = nouveau_bdev(bo->bdev); struct nouveau_mem *mem; int ret; diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 8bd739cfd00d..2b3ccd850750 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -3264,10 +3264,11 @@ nv50_mstm_destroy_connector(struct drm_dp_mst_topology_mgr *mgr, drm_connector_unregister(&mstc->connector); - drm_modeset_lock_all(drm->dev); drm_fb_helper_remove_one_connector(&drm->fbcon->helper, &mstc->connector); + + drm_modeset_lock(&drm->dev->mode_config.connection_mutex, NULL); mstc->port = NULL; - drm_modeset_unlock_all(drm->dev); + drm_modeset_unlock(&drm->dev->mode_config.connection_mutex); drm_connector_unreference(&mstc->connector); } @@ -3277,9 +3278,7 @@ nv50_mstm_register_connector(struct drm_connector *connector) { struct nouveau_drm *drm = nouveau_drm(connector->dev); - drm_modeset_lock_all(drm->dev); drm_fb_helper_add_one_connector(&drm->fbcon->helper, connector); - drm_modeset_unlock_all(drm->dev); drm_connector_register(connector); } diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c index 5e2e65e88847..7f3ac6b13b56 100644 --- a/drivers/gpu/drm/omapdrm/dss/dispc.c +++ b/drivers/gpu/drm/omapdrm/dss/dispc.c @@ -828,6 +828,12 @@ static void dispc_ovl_set_scale_coef(struct dispc_device *dispc, h_coef = dispc_ovl_get_scale_coef(fir_hinc, true); v_coef = dispc_ovl_get_scale_coef(fir_vinc, five_taps); + if (!h_coef || !v_coef) { + dev_err(&dispc->pdev->dev, "%s: failed to find scale coefs\n", + __func__); + return; + } + for (i = 0; i < 8; i++) { u32 h, hv; @@ -2342,7 +2348,7 @@ static int dispc_ovl_calc_scaling_24xx(struct dispc_device *dispc, } if (in_width > maxsinglelinewidth) { - DSSERR("Cannot scale max input width exceeded"); + DSSERR("Cannot scale max input width exceeded\n"); return -EINVAL; } return 0; @@ -2424,13 +2430,13 @@ again: } if (in_width > (maxsinglelinewidth * 2)) { - DSSERR("Cannot setup scaling"); - DSSERR("width exceeds maximum width possible"); + DSSERR("Cannot setup scaling\n"); + DSSERR("width exceeds maximum width possible\n"); return -EINVAL; } if (in_width > maxsinglelinewidth && *five_taps) { - DSSERR("cannot setup scaling with five taps"); + DSSERR("cannot setup scaling with five taps\n"); return -EINVAL; } return 0; @@ -2472,7 +2478,7 @@ static int dispc_ovl_calc_scaling_44xx(struct dispc_device *dispc, in_width > maxsinglelinewidth && ++*decim_x); if (in_width > maxsinglelinewidth) { - DSSERR("Cannot scale width exceeds max line width"); + DSSERR("Cannot scale width exceeds max line width\n"); return -EINVAL; } @@ -2490,7 +2496,7 @@ static int dispc_ovl_calc_scaling_44xx(struct dispc_device *dispc, * bandwidth. Despite what theory says this appears to * be true also for 16-bit color formats. */ - DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)", *decim_x); + DSSERR("Not enough bandwidth, too much downscaling (x-decimation factor %d > 4)\n", *decim_x); return -EINVAL; } @@ -4633,7 +4639,7 @@ static int dispc_errata_i734_wa_init(struct dispc_device *dispc) i734_buf.size, &i734_buf.paddr, GFP_KERNEL); if (!i734_buf.vaddr) { - dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed", + dev_err(&dispc->pdev->dev, "%s: dma_alloc_writecombine failed\n", __func__); return -ENOMEM; } diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4.c b/drivers/gpu/drm/omapdrm/dss/hdmi4.c index 97c88861d67a..5879f45f6fc9 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi4.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi4.c @@ -679,7 +679,7 @@ static int hdmi_audio_config(struct device *dev, struct omap_dss_audio *dss_audio) { struct omap_hdmi *hd = dev_get_drvdata(dev); - int ret; + int ret = 0; mutex_lock(&hd->lock); diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c index 35ed2add6189..813ba42f2753 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c @@ -922,8 +922,13 @@ int hdmi4_core_init(struct platform_device *pdev, struct hdmi_core_data *core) { const struct hdmi4_features *features; struct resource *res; + const struct soc_device_attribute *soc; - features = soc_device_match(hdmi4_soc_devices)->data; + soc = soc_device_match(hdmi4_soc_devices); + if (!soc) + return -ENODEV; + + features = soc->data; core->cts_swmode = features->cts_swmode; core->audio_use_mclk = features->audio_use_mclk; diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi5.c b/drivers/gpu/drm/omapdrm/dss/hdmi5.c index d28da9ac3e90..ae1a001d1b83 100644 --- a/drivers/gpu/drm/omapdrm/dss/hdmi5.c +++ b/drivers/gpu/drm/omapdrm/dss/hdmi5.c @@ -671,7 +671,7 @@ static int hdmi_audio_config(struct device *dev, struct omap_dss_audio *dss_audio) { struct omap_hdmi *hd = dev_get_drvdata(dev); - int ret; + int ret = 0; mutex_lock(&hd->lock); diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c index a0d7b1d905e8..5cde26ac937b 100644 --- a/drivers/gpu/drm/omapdrm/omap_connector.c +++ b/drivers/gpu/drm/omapdrm/omap_connector.c @@ -121,6 +121,9 @@ static int omap_connector_get_modes(struct drm_connector *connector) if (dssdrv->read_edid) { void *edid = kzalloc(MAX_EDID, GFP_KERNEL); + if (!edid) + return 0; + if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) && drm_edid_is_valid(edid)) { drm_mode_connector_update_edid_property( @@ -139,6 +142,9 @@ static int omap_connector_get_modes(struct drm_connector *connector) struct drm_display_mode *mode = drm_mode_create(dev); struct videomode vm = {0}; + if (!mode) + return 0; + dssdrv->get_timings(dssdev, &vm); drm_display_mode_from_videomode(&vm, mode); @@ -200,6 +206,10 @@ static int omap_connector_mode_valid(struct drm_connector *connector, if (!r) { /* check if vrefresh is still valid */ new_mode = drm_mode_duplicate(dev, mode); + + if (!new_mode) + return MODE_BAD; + new_mode->clock = vm.pixelclock / 1000; new_mode->vrefresh = 0; if (mode->vrefresh == drm_mode_vrefresh(new_mode)) diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c index f9fa1c90b35c..401c02e9e6b2 100644 --- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c +++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c @@ -401,12 +401,16 @@ int tiler_unpin(struct tiler_block *block) struct tiler_block *tiler_reserve_2d(enum tiler_fmt fmt, u16 w, u16 h, u16 align) { - struct tiler_block *block = kzalloc(sizeof(*block), GFP_KERNEL); + struct tiler_block *block; u32 min_align = 128; int ret; unsigned long flags; u32 slot_bytes; + block = kzalloc(sizeof(*block), GFP_KERNEL); + if (!block) + return ERR_PTR(-ENOMEM); + BUG_ON(!validfmt(fmt)); /* convert width/height to slots */ diff --git a/drivers/gpu/drm/omapdrm/tcm-sita.c b/drivers/gpu/drm/omapdrm/tcm-sita.c index d7f7bc9f061a..817be3c41863 100644 --- a/drivers/gpu/drm/omapdrm/tcm-sita.c +++ b/drivers/gpu/drm/omapdrm/tcm-sita.c @@ -90,7 +90,7 @@ static int l2r_t2b(u16 w, u16 h, u16 a, s16 offset, { int i; unsigned long index; - bool area_free; + bool area_free = false; unsigned long slots_per_band = PAGE_SIZE / slot_bytes; unsigned long bit_offset = (offset > 0) ? offset / slot_bytes : 0; unsigned long curr_bit = bit_offset; diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c index f0481b7b60c5..06c94e3a5f15 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c @@ -910,7 +910,8 @@ static int ttm_get_pages(struct page **pages, unsigned npages, int flags, while (npages >= HPAGE_PMD_NR) { gfp_t huge_flags = gfp_flags; - huge_flags |= GFP_TRANSHUGE; + huge_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY | + __GFP_KSWAPD_RECLAIM; huge_flags &= ~__GFP_MOVABLE; huge_flags &= ~__GFP_COMP; p = alloc_pages(huge_flags, HPAGE_PMD_ORDER); @@ -1027,11 +1028,15 @@ int ttm_page_alloc_init(struct ttm_mem_global *glob, unsigned max_pages) GFP_USER | GFP_DMA32, "uc dma", 0); ttm_page_pool_init_locked(&_manager->wc_pool_huge, - GFP_TRANSHUGE & ~(__GFP_MOVABLE | __GFP_COMP), + (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY | + __GFP_KSWAPD_RECLAIM) & + ~(__GFP_MOVABLE | __GFP_COMP), "wc huge", order); ttm_page_pool_init_locked(&_manager->uc_pool_huge, - GFP_TRANSHUGE & ~(__GFP_MOVABLE | __GFP_COMP) + (GFP_TRANSHUGE_LIGHT | __GFP_NORETRY | + __GFP_KSWAPD_RECLAIM) & + ~(__GFP_MOVABLE | __GFP_COMP) , "uc huge", order); _manager->options.max_size = max_pages; diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c index 8a25d1974385..f63d99c302e4 100644 --- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c +++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c @@ -910,7 +910,8 @@ static gfp_t ttm_dma_pool_gfp_flags(struct ttm_dma_tt *ttm_dma, bool huge) gfp_flags |= __GFP_ZERO; if (huge) { - gfp_flags |= GFP_TRANSHUGE; + gfp_flags |= GFP_TRANSHUGE_LIGHT | __GFP_NORETRY | + __GFP_KSWAPD_RECLAIM; gfp_flags &= ~__GFP_MOVABLE; gfp_flags &= ~__GFP_COMP; } diff --git a/drivers/gpu/drm/vc4/vc4_dpi.c b/drivers/gpu/drm/vc4/vc4_dpi.c index 72c9dbd81d7f..f185812970da 100644 --- a/drivers/gpu/drm/vc4/vc4_dpi.c +++ b/drivers/gpu/drm/vc4/vc4_dpi.c @@ -96,7 +96,6 @@ struct vc4_dpi { struct platform_device *pdev; struct drm_encoder *encoder; - struct drm_connector *connector; void __iomem *regs; @@ -164,14 +163,31 @@ static void vc4_dpi_encoder_disable(struct drm_encoder *encoder) static void vc4_dpi_encoder_enable(struct drm_encoder *encoder) { + struct drm_device *dev = encoder->dev; struct drm_display_mode *mode = &encoder->crtc->mode; struct vc4_dpi_encoder *vc4_encoder = to_vc4_dpi_encoder(encoder); struct vc4_dpi *dpi = vc4_encoder->dpi; + struct drm_connector_list_iter conn_iter; + struct drm_connector *connector = NULL, *connector_scan; u32 dpi_c = DPI_ENABLE | DPI_OUTPUT_ENABLE_MODE; int ret; - if (dpi->connector->display_info.num_bus_formats) { - u32 bus_format = dpi->connector->display_info.bus_formats[0]; + /* Look up the connector attached to DPI so we can get the + * bus_format. Ideally the bridge would tell us the + * bus_format we want, but it doesn't yet, so assume that it's + * uniform throughout the bridge chain. + */ + drm_connector_list_iter_begin(dev, &conn_iter); + drm_for_each_connector_iter(connector_scan, &conn_iter) { + if (connector_scan->encoder == encoder) { + connector = connector_scan; + break; + } + } + drm_connector_list_iter_end(&conn_iter); + + if (connector && connector->display_info.num_bus_formats) { + u32 bus_format = connector->display_info.bus_formats[0]; switch (bus_format) { case MEDIA_BUS_FMT_RGB888_1X24: @@ -199,6 +215,9 @@ static void vc4_dpi_encoder_enable(struct drm_encoder *encoder) DRM_ERROR("Unknown media bus format %d\n", bus_format); break; } + } else { + /* Default to 24bit if no connector found. */ + dpi_c |= VC4_SET_FIELD(DPI_FORMAT_24BIT_888_RGB, DPI_FORMAT); } if (mode->flags & DRM_MODE_FLAG_NHSYNC) diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 94b99c90425a..7c95ed5c5cac 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -130,6 +130,7 @@ static void vc4_close(struct drm_device *dev, struct drm_file *file) struct vc4_file *vc4file = file->driver_priv; vc4_perfmon_close_file(vc4file); + kfree(vc4file); } static const struct vm_operations_struct vc4_vm_ops = { diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index ce39390be389..13dcaad06798 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -503,7 +503,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane, * the scl fields here. */ if (num_planes == 1) { - scl0 = vc4_get_scl_field(state, 1); + scl0 = vc4_get_scl_field(state, 0); scl1 = scl0; } else { scl0 = vc4_get_scl_field(state, 1); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 648f8127f65a..3d667e903beb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -482,6 +482,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane, return ret; } + vps->dmabuf_size = size; + /* * TTM already thinks the buffer is pinned, but make sure the * pin_count is upped. diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 60252fd796f6..0000434a1fbd 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -462,10 +462,11 @@ config HID_LENOVO select NEW_LEDS select LEDS_CLASS ---help--- - Support for Lenovo devices that are not fully compliant with HID standard. + Support for IBM/Lenovo devices that are not fully compliant with HID standard. - Say Y if you want support for the non-compliant features of the Lenovo - Thinkpad standalone keyboards, e.g: + Say Y if you want support for horizontal scrolling of the IBM/Lenovo + Scrollpoint mice or the non-compliant features of the Lenovo Thinkpad + standalone keyboards, e.g: - ThinkPad USB Keyboard with TrackPoint (supports extra LEDs and trackpoint configuration) - ThinkPad Compact Bluetooth Keyboard with TrackPoint (supports Fn keys) diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 0b5cc910f62e..46f5ecd11bf7 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -552,6 +552,13 @@ #define USB_VENDOR_ID_HUION 0x256c #define USB_DEVICE_ID_HUION_TABLET 0x006e +#define USB_VENDOR_ID_IBM 0x04b3 +#define USB_DEVICE_ID_IBM_SCROLLPOINT_III 0x3100 +#define USB_DEVICE_ID_IBM_SCROLLPOINT_PRO 0x3103 +#define USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL 0x3105 +#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL 0x3108 +#define USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO 0x3109 + #define USB_VENDOR_ID_IDEACOM 0x1cb6 #define USB_DEVICE_ID_IDEACOM_IDC6650 0x6650 #define USB_DEVICE_ID_IDEACOM_IDC6651 0x6651 @@ -684,6 +691,7 @@ #define USB_DEVICE_ID_LENOVO_TPKBD 0x6009 #define USB_DEVICE_ID_LENOVO_CUSBKBD 0x6047 #define USB_DEVICE_ID_LENOVO_CBTKBD 0x6048 +#define USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL 0x6049 #define USB_DEVICE_ID_LENOVO_TPPRODOCK 0x6067 #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 @@ -964,6 +972,7 @@ #define USB_DEVICE_ID_SIS817_TOUCH 0x0817 #define USB_DEVICE_ID_SIS_TS 0x1013 #define USB_DEVICE_ID_SIS1030_TOUCH 0x1030 +#define USB_DEVICE_ID_SIS10FB_TOUCH 0x10fb #define USB_VENDOR_ID_SKYCABLE 0x1223 #define USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER 0x3F07 diff --git a/drivers/hid/hid-lenovo.c b/drivers/hid/hid-lenovo.c index 1ac4ff4d57a6..643b6eb54442 100644 --- a/drivers/hid/hid-lenovo.c +++ b/drivers/hid/hid-lenovo.c @@ -6,6 +6,17 @@ * * Copyright (c) 2012 Bernhard Seibold * Copyright (c) 2014 Jamie Lentin <jm@lentin.co.uk> + * + * Linux IBM/Lenovo Scrollpoint mouse driver: + * - IBM Scrollpoint III + * - IBM Scrollpoint Pro + * - IBM Scrollpoint Optical + * - IBM Scrollpoint Optical 800dpi + * - IBM Scrollpoint Optical 800dpi Pro + * - Lenovo Scrollpoint Optical + * + * Copyright (c) 2012 Peter De Wachter <pdewacht@gmail.com> + * Copyright (c) 2018 Peter Ganzhorn <peter.ganzhorn@gmail.com> */ /* @@ -160,6 +171,17 @@ static int lenovo_input_mapping_cptkbd(struct hid_device *hdev, return 0; } +static int lenovo_input_mapping_scrollpoint(struct hid_device *hdev, + struct hid_input *hi, struct hid_field *field, + struct hid_usage *usage, unsigned long **bit, int *max) +{ + if (usage->hid == HID_GD_Z) { + hid_map_usage(hi, usage, bit, max, EV_REL, REL_HWHEEL); + return 1; + } + return 0; +} + static int lenovo_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) @@ -172,6 +194,14 @@ static int lenovo_input_mapping(struct hid_device *hdev, case USB_DEVICE_ID_LENOVO_CBTKBD: return lenovo_input_mapping_cptkbd(hdev, hi, field, usage, bit, max); + case USB_DEVICE_ID_IBM_SCROLLPOINT_III: + case USB_DEVICE_ID_IBM_SCROLLPOINT_PRO: + case USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL: + case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL: + case USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO: + case USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL: + return lenovo_input_mapping_scrollpoint(hdev, hi, field, + usage, bit, max); default: return 0; } @@ -883,6 +913,12 @@ static const struct hid_device_id lenovo_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CUSBKBD) }, { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_CBTKBD) }, { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_TPPRODOCK) }, + { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_III) }, + { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_PRO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_OPTICAL) }, + { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL) }, + { HID_USB_DEVICE(USB_VENDOR_ID_IBM, USB_DEVICE_ID_IBM_SCROLLPOINT_800DPI_OPTICAL_PRO) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_SCROLLPOINT_OPTICAL) }, { } }; diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 963328674e93..cc33622253aa 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -174,6 +174,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, { I2C_VENDOR_ID_RAYD, I2C_PRODUCT_ID_RAYD_3118, I2C_HID_QUIRK_RESEND_REPORT_DESCR }, + { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH, + I2C_HID_QUIRK_RESEND_REPORT_DESCR }, { 0, 0 } }; diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index 157b44aacdff..acc2536c8094 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -77,21 +77,21 @@ static void process_recv(struct ishtp_cl *hid_ishtp_cl, void *recv_buf, struct ishtp_cl_data *client_data = hid_ishtp_cl->client_data; int curr_hid_dev = client_data->cur_hid_dev; - if (data_len < sizeof(struct hostif_msg_hdr)) { - dev_err(&client_data->cl_device->dev, - "[hid-ish]: error, received %u which is less than data header %u\n", - (unsigned int)data_len, - (unsigned int)sizeof(struct hostif_msg_hdr)); - ++client_data->bad_recv_cnt; - ish_hw_reset(hid_ishtp_cl->dev); - return; - } - payload = recv_buf + sizeof(struct hostif_msg_hdr); total_len = data_len; cur_pos = 0; do { + if (cur_pos + sizeof(struct hostif_msg) > total_len) { + dev_err(&client_data->cl_device->dev, + "[hid-ish]: error, received %u which is less than data header %u\n", + (unsigned int)data_len, + (unsigned int)sizeof(struct hostif_msg_hdr)); + ++client_data->bad_recv_cnt; + ish_hw_reset(hid_ishtp_cl->dev); + break; + } + recv_msg = (struct hostif_msg *)(recv_buf + cur_pos); payload_len = recv_msg->hdr.size; @@ -412,9 +412,7 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id, { struct ishtp_hid_data *hid_data = hid->driver_data; struct ishtp_cl_data *client_data = hid_data->client_data; - static unsigned char buf[10]; - unsigned int len; - struct hostif_msg_to_sensor *msg = (struct hostif_msg_to_sensor *)buf; + struct hostif_msg_to_sensor msg = {}; int rv; int i; @@ -426,14 +424,11 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id, return; } - len = sizeof(struct hostif_msg_to_sensor); - - memset(msg, 0, sizeof(struct hostif_msg_to_sensor)); - msg->hdr.command = (report_type == HID_FEATURE_REPORT) ? + msg.hdr.command = (report_type == HID_FEATURE_REPORT) ? HOSTIF_GET_FEATURE_REPORT : HOSTIF_GET_INPUT_REPORT; for (i = 0; i < client_data->num_hid_devices; ++i) { if (hid == client_data->hid_sensor_hubs[i]) { - msg->hdr.device_id = + msg.hdr.device_id = client_data->hid_devices[i].dev_id; break; } @@ -442,8 +437,9 @@ void hid_ishtp_get_report(struct hid_device *hid, int report_id, if (i == client_data->num_hid_devices) return; - msg->report_id = report_id; - rv = ishtp_cl_send(client_data->hid_ishtp_cl, buf, len); + msg.report_id = report_id; + rv = ishtp_cl_send(client_data->hid_ishtp_cl, (uint8_t *)&msg, + sizeof(msg)); if (rv) hid_ishtp_trace(client_data, "%s hid %p send failed\n", __func__, hid); diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index f272cdd9bd55..2623a567ffba 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -418,7 +418,7 @@ static struct ishtp_cl_device *ishtp_bus_add_device(struct ishtp_device *dev, list_del(&device->device_link); spin_unlock_irqrestore(&dev->device_list_lock, flags); dev_err(dev->devc, "Failed to register ISHTP client device\n"); - kfree(device); + put_device(&device->dev); return NULL; } diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index b54ef1ffcbec..ee7a37eb159a 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -1213,8 +1213,10 @@ static int __wacom_devm_sysfs_create_group(struct wacom *wacom, devres->root = root; error = sysfs_create_group(devres->root, group); - if (error) + if (error) { + devres_free(devres); return error; + } devres_add(&wacom->hdev->dev, devres); diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig index f249a4428458..6ec307c93ece 100644 --- a/drivers/hwmon/Kconfig +++ b/drivers/hwmon/Kconfig @@ -272,7 +272,7 @@ config SENSORS_K8TEMP config SENSORS_K10TEMP tristate "AMD Family 10h+ temperature sensor" - depends on X86 && PCI + depends on X86 && PCI && AMD_NB help If you say yes here you get support for the temperature sensor(s) inside your CPU. Supported are later revisions of diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c index d2cc55e21374..3b73dee6fdc6 100644 --- a/drivers/hwmon/k10temp.c +++ b/drivers/hwmon/k10temp.c @@ -23,6 +23,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/pci.h> +#include <asm/amd_nb.h> #include <asm/processor.h> MODULE_DESCRIPTION("AMD Family 10h+ CPU core temperature monitor"); @@ -40,8 +41,8 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); #define PCI_DEVICE_ID_AMD_17H_DF_F3 0x1463 #endif -#ifndef PCI_DEVICE_ID_AMD_17H_RR_NB -#define PCI_DEVICE_ID_AMD_17H_RR_NB 0x15d0 +#ifndef PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F3 0x15eb #endif /* CPUID function 0x80000001, ebx */ @@ -63,10 +64,12 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); #define NB_CAP_HTC 0x00000400 /* - * For F15h M60h, functionality of REG_REPORTED_TEMPERATURE - * has been moved to D0F0xBC_xD820_0CA4 [Reported Temperature - * Control] + * For F15h M60h and M70h, REG_HARDWARE_THERMAL_CONTROL + * and REG_REPORTED_TEMPERATURE have been moved to + * D0F0xBC_xD820_0C64 [Hardware Temperature Control] + * D0F0xBC_xD820_0CA4 [Reported Temperature Control] */ +#define F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET 0xd8200c64 #define F15H_M60H_REPORTED_TEMP_CTRL_OFFSET 0xd8200ca4 /* F17h M01h Access througn SMN */ @@ -74,6 +77,7 @@ static DEFINE_MUTEX(nb_smu_ind_mutex); struct k10temp_data { struct pci_dev *pdev; + void (*read_htcreg)(struct pci_dev *pdev, u32 *regval); void (*read_tempreg)(struct pci_dev *pdev, u32 *regval); int temp_offset; u32 temp_adjust_mask; @@ -98,6 +102,11 @@ static const struct tctl_offset tctl_offset_table[] = { { 0x17, "AMD Ryzen Threadripper 1910", 10000 }, }; +static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval) +{ + pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, regval); +} + static void read_tempreg_pci(struct pci_dev *pdev, u32 *regval) { pci_read_config_dword(pdev, REG_REPORTED_TEMPERATURE, regval); @@ -114,6 +123,12 @@ static void amd_nb_index_read(struct pci_dev *pdev, unsigned int devfn, mutex_unlock(&nb_smu_ind_mutex); } +static void read_htcreg_nb_f15(struct pci_dev *pdev, u32 *regval) +{ + amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8, + F15H_M60H_HARDWARE_TEMP_CTRL_OFFSET, regval); +} + static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval) { amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0xb8, @@ -122,8 +137,8 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval) static void read_tempreg_nb_f17(struct pci_dev *pdev, u32 *regval) { - amd_nb_index_read(pdev, PCI_DEVFN(0, 0), 0x60, - F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval); + amd_smn_read(amd_pci_dev_to_node_id(pdev), + F17H_M01H_REPORTED_TEMP_CTRL_OFFSET, regval); } static ssize_t temp1_input_show(struct device *dev, @@ -160,8 +175,7 @@ static ssize_t show_temp_crit(struct device *dev, u32 regval; int value; - pci_read_config_dword(data->pdev, - REG_HARDWARE_THERMAL_CONTROL, ®val); + data->read_htcreg(data->pdev, ®val); value = ((regval >> 16) & 0x7f) * 500 + 52000; if (show_hyst) value -= ((regval >> 24) & 0xf) * 500; @@ -181,13 +195,18 @@ static umode_t k10temp_is_visible(struct kobject *kobj, struct pci_dev *pdev = data->pdev; if (index >= 2) { - u32 reg_caps, reg_htc; + u32 reg; + + if (!data->read_htcreg) + return 0; pci_read_config_dword(pdev, REG_NORTHBRIDGE_CAPABILITIES, - ®_caps); - pci_read_config_dword(pdev, REG_HARDWARE_THERMAL_CONTROL, - ®_htc); - if (!(reg_caps & NB_CAP_HTC) || !(reg_htc & HTC_ENABLE)) + ®); + if (!(reg & NB_CAP_HTC)) + return 0; + + data->read_htcreg(data->pdev, ®); + if (!(reg & HTC_ENABLE)) return 0; } return attr->mode; @@ -268,11 +287,13 @@ static int k10temp_probe(struct pci_dev *pdev, if (boot_cpu_data.x86 == 0x15 && (boot_cpu_data.x86_model == 0x60 || boot_cpu_data.x86_model == 0x70)) { + data->read_htcreg = read_htcreg_nb_f15; data->read_tempreg = read_tempreg_nb_f15; } else if (boot_cpu_data.x86 == 0x17) { data->temp_adjust_mask = 0x80000; data->read_tempreg = read_tempreg_nb_f17; } else { + data->read_htcreg = read_htcreg_pci; data->read_tempreg = read_tempreg_pci; } @@ -302,7 +323,7 @@ static const struct pci_device_id k10temp_id_table[] = { { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, - { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_RR_NB) }, + { PCI_VDEVICE(AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, {} }; MODULE_DEVICE_TABLE(pci, k10temp_id_table); diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index fd36c39ddf4e..0cdba29ae0a9 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -209,7 +209,10 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev) i2c_dw_disable_int(dev); /* Enable the adapter */ - __i2c_dw_enable_and_wait(dev, true); + __i2c_dw_enable(dev, true); + + /* Dummy read to avoid the register getting stuck on Bay Trail */ + dw_readl(dev, DW_IC_ENABLE_STATUS); /* Clear and enable interrupts */ dw_readl(dev, DW_IC_CLR_INTR); diff --git a/drivers/i2c/busses/i2c-pmcmsp.c b/drivers/i2c/busses/i2c-pmcmsp.c index 2aa0e83174c5..dae8ac618a52 100644 --- a/drivers/i2c/busses/i2c-pmcmsp.c +++ b/drivers/i2c/busses/i2c-pmcmsp.c @@ -564,10 +564,10 @@ static int pmcmsptwi_master_xfer(struct i2c_adapter *adap, * TODO: We could potentially loop and retry in the case * of MSP_TWI_XFER_TIMEOUT. */ - return -1; + return -EIO; } - return 0; + return num; } static u32 pmcmsptwi_i2c_func(struct i2c_adapter *adapter) diff --git a/drivers/i2c/busses/i2c-viperboard.c b/drivers/i2c/busses/i2c-viperboard.c index e4be86b3de9a..7235c7302bb7 100644 --- a/drivers/i2c/busses/i2c-viperboard.c +++ b/drivers/i2c/busses/i2c-viperboard.c @@ -337,7 +337,7 @@ static int vprbrd_i2c_xfer(struct i2c_adapter *i2c, struct i2c_msg *msgs, } mutex_unlock(&vb->lock); } - return 0; + return num; error: mutex_unlock(&vb->lock); return error; diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index a9126b3cda61..7c3b4740b94b 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -445,10 +445,17 @@ static int acpi_gsb_i2c_read_bytes(struct i2c_client *client, msgs[1].buf = buffer; ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); - if (ret < 0) - dev_err(&client->adapter->dev, "i2c read failed\n"); - else + if (ret < 0) { + /* Getting a NACK is unfortunately normal with some DSTDs */ + if (ret == -EREMOTEIO) + dev_dbg(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n", + data_len, client->addr, cmd, ret); + else + dev_err(&client->adapter->dev, "i2c read %d bytes from client@%#x starting at reg %#x failed, error: %d\n", + data_len, client->addr, cmd, ret); + } else { memcpy(data, buffer, data_len); + } kfree(buffer); return ret; diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 4e63c6f6c04d..d030ce3025a6 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -250,7 +250,9 @@ void bch_debug_exit(void) int __init bch_debug_init(struct kobject *kobj) { - bcache_debug = debugfs_create_dir("bcache", NULL); + if (!IS_ENABLED(CONFIG_DEBUG_FS)) + return 0; + bcache_debug = debugfs_create_dir("bcache", NULL); return IS_ERR_OR_NULL(bcache_debug); } diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 12aa9ca21d8c..dc385b70e4c3 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1681,8 +1681,9 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign if (block_size <= KMALLOC_MAX_SIZE && (block_size < PAGE_SIZE || !is_power_of_2(block_size))) { - snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", c->block_size); - c->slab_cache = kmem_cache_create(slab_name, c->block_size, ARCH_KMALLOC_MINALIGN, + unsigned align = min(1U << __ffs(block_size), (unsigned)PAGE_SIZE); + snprintf(slab_name, sizeof slab_name, "dm_bufio_cache-%u", block_size); + c->slab_cache = kmem_cache_create(slab_name, block_size, align, SLAB_RECLAIM_ACCOUNT, NULL); if (!c->slab_cache) { r = -ENOMEM; diff --git a/drivers/md/dm-cache-background-tracker.c b/drivers/md/dm-cache-background-tracker.c index 1d0af0a21fc7..84814e819e4c 100644 --- a/drivers/md/dm-cache-background-tracker.c +++ b/drivers/md/dm-cache-background-tracker.c @@ -166,7 +166,7 @@ static bool max_work_reached(struct background_tracker *b) atomic_read(&b->pending_demotes) >= b->max_work; } -struct bt_work *alloc_work(struct background_tracker *b) +static struct bt_work *alloc_work(struct background_tracker *b) { if (max_work_reached(b)) return NULL; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 77d9fe58dae2..514fb4aec5d1 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -2440,7 +2440,7 @@ static void dm_integrity_free_journal_scatterlist(struct dm_integrity_c *ic, str unsigned i; for (i = 0; i < ic->journal_sections; i++) kvfree(sl[i]); - kfree(sl); + kvfree(sl); } static struct scatterlist **dm_integrity_alloc_journal_scatterlist(struct dm_integrity_c *ic, struct page_list *pl) diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c index 580c49cc8079..5903e492bb34 100644 --- a/drivers/md/dm-raid1.c +++ b/drivers/md/dm-raid1.c @@ -23,6 +23,8 @@ #define MAX_RECOVERY 1 /* Maximum number of regions recovered in parallel. */ +#define MAX_NR_MIRRORS (DM_KCOPYD_MAX_REGIONS + 1) + #define DM_RAID1_HANDLE_ERRORS 0x01 #define DM_RAID1_KEEP_LOG 0x02 #define errors_handled(p) ((p)->features & DM_RAID1_HANDLE_ERRORS) @@ -255,7 +257,7 @@ static int mirror_flush(struct dm_target *ti) unsigned long error_bits; unsigned int i; - struct dm_io_region io[ms->nr_mirrors]; + struct dm_io_region io[MAX_NR_MIRRORS]; struct mirror *m; struct dm_io_request io_req = { .bi_op = REQ_OP_WRITE, @@ -651,7 +653,7 @@ static void write_callback(unsigned long error, void *context) static void do_write(struct mirror_set *ms, struct bio *bio) { unsigned int i; - struct dm_io_region io[ms->nr_mirrors], *dest = io; + struct dm_io_region io[MAX_NR_MIRRORS], *dest = io; struct mirror *m; struct dm_io_request io_req = { .bi_op = REQ_OP_WRITE, @@ -1083,7 +1085,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv) argc -= args_used; if (!argc || sscanf(argv[0], "%u%c", &nr_mirrors, &dummy) != 1 || - nr_mirrors < 2 || nr_mirrors > DM_KCOPYD_MAX_REGIONS + 1) { + nr_mirrors < 2 || nr_mirrors > MAX_NR_MIRRORS) { ti->error = "Invalid number of mirrors"; dm_dirty_log_destroy(dl); return -EINVAL; @@ -1404,7 +1406,7 @@ static void mirror_status(struct dm_target *ti, status_type_t type, int num_feature_args = 0; struct mirror_set *ms = (struct mirror_set *) ti->private; struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh); - char buffer[ms->nr_mirrors + 1]; + char buffer[MAX_NR_MIRRORS + 1]; switch (type) { case STATUSTYPE_INFO: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4ea404dbcf0b..0a7b0107ca78 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1020,7 +1020,8 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len) EXPORT_SYMBOL_GPL(dm_set_target_max_io_len); static struct dm_target *dm_dax_get_live_target(struct mapped_device *md, - sector_t sector, int *srcu_idx) + sector_t sector, int *srcu_idx) + __acquires(md->io_barrier) { struct dm_table *map; struct dm_target *ti; @@ -1037,7 +1038,7 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md, } static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, - long nr_pages, void **kaddr, pfn_t *pfn) + long nr_pages, void **kaddr, pfn_t *pfn) { struct mapped_device *md = dax_get_private(dax_dev); sector_t sector = pgoff * PAGE_SECTORS; @@ -1065,7 +1066,7 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, } static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) + void *addr, size_t bytes, struct iov_iter *i) { struct mapped_device *md = dax_get_private(dax_dev); sector_t sector = pgoff * PAGE_SECTORS; diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index a4c9c8297a6d..918d4fb742d1 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -717,6 +717,7 @@ struct cxl { bool perst_select_user; bool perst_same_image; bool psl_timebase_synced; + bool tunneled_ops_supported; /* * number of contexts mapped on to this card. Possible values are: diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index 83f1d08058fc..4d6736f9d463 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1742,6 +1742,15 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev) /* Required for devices using CAPP DMA mode, harmless for others */ pci_set_master(dev); + adapter->tunneled_ops_supported = false; + + if (cxl_is_power9()) { + if (pnv_pci_set_tunnel_bar(dev, 0x00020000E0000000ull, 1)) + dev_info(&dev->dev, "Tunneled operations unsupported\n"); + else + adapter->tunneled_ops_supported = true; + } + if ((rc = pnv_phb_to_cxl_mode(dev, adapter->native->sl_ops->capi_mode))) goto err; @@ -1768,6 +1777,9 @@ static void cxl_deconfigure_adapter(struct cxl *adapter) { struct pci_dev *pdev = to_pci_dev(adapter->dev.parent); + if (cxl_is_power9()) + pnv_pci_set_tunnel_bar(pdev, 0x00020000E0000000ull, 0); + cxl_native_release_psl_err_irq(adapter); cxl_unmap_adapter_regs(adapter); diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c index 95285b7f636f..4b5a4c5d3c01 100644 --- a/drivers/misc/cxl/sysfs.c +++ b/drivers/misc/cxl/sysfs.c @@ -78,6 +78,15 @@ static ssize_t psl_timebase_synced_show(struct device *device, return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_timebase_synced); } +static ssize_t tunneled_ops_supported_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl *adapter = to_cxl_adapter(device); + + return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->tunneled_ops_supported); +} + static ssize_t reset_adapter_store(struct device *device, struct device_attribute *attr, const char *buf, size_t count) @@ -183,6 +192,7 @@ static struct device_attribute adapter_attrs[] = { __ATTR_RO(base_image), __ATTR_RO(image_loaded), __ATTR_RO(psl_timebase_synced), + __ATTR_RO(tunneled_ops_supported), __ATTR_RW(load_image_on_perst), __ATTR_RW(perst_reloads_same_image), __ATTR(reset, S_IWUSR, NULL, reset_adapter_store), diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c index 0c125f207aea..33053b0d1fdf 100644 --- a/drivers/misc/eeprom/at24.c +++ b/drivers/misc/eeprom/at24.c @@ -518,7 +518,7 @@ static int at24_get_pdata(struct device *dev, struct at24_platform_data *pdata) if (of_node && of_match_device(at24_of_match, dev)) cdata = of_device_get_match_data(dev); else if (id) - cdata = (void *)&id->driver_data; + cdata = (void *)id->driver_data; else cdata = acpi_device_get_match_data(dev); diff --git a/drivers/mtd/nand/onenand/omap2.c b/drivers/mtd/nand/onenand/omap2.c index 9c159f0dd9a6..321137158ff3 100644 --- a/drivers/mtd/nand/onenand/omap2.c +++ b/drivers/mtd/nand/onenand/omap2.c @@ -375,56 +375,42 @@ static int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area, { struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd); struct onenand_chip *this = mtd->priv; - dma_addr_t dma_src, dma_dst; - int bram_offset; + struct device *dev = &c->pdev->dev; void *buf = (void *)buffer; + dma_addr_t dma_src, dma_dst; + int bram_offset, err; size_t xtra; - int ret; bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset; - if (bram_offset & 3 || (size_t)buf & 3 || count < 384) - goto out_copy; - - /* panic_write() may be in an interrupt context */ - if (in_interrupt() || oops_in_progress) + /* + * If the buffer address is not DMA-able, len is not long enough to make + * DMA transfers profitable or panic_write() may be in an interrupt + * context fallback to PIO mode. + */ + if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 || + count < 384 || in_interrupt() || oops_in_progress ) goto out_copy; - if (buf >= high_memory) { - struct page *p1; - - if (((size_t)buf & PAGE_MASK) != - ((size_t)(buf + count - 1) & PAGE_MASK)) - goto out_copy; - p1 = vmalloc_to_page(buf); - if (!p1) - goto out_copy; - buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK); - } - xtra = count & 3; if (xtra) { count -= xtra; memcpy(buf + count, this->base + bram_offset + count, xtra); } + dma_dst = dma_map_single(dev, buf, count, DMA_FROM_DEVICE); dma_src = c->phys_base + bram_offset; - dma_dst = dma_map_single(&c->pdev->dev, buf, count, DMA_FROM_DEVICE); - if (dma_mapping_error(&c->pdev->dev, dma_dst)) { - dev_err(&c->pdev->dev, - "Couldn't DMA map a %d byte buffer\n", - count); - goto out_copy; - } - ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count); - dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE); - - if (ret) { - dev_err(&c->pdev->dev, "timeout waiting for DMA\n"); + if (dma_mapping_error(dev, dma_dst)) { + dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count); goto out_copy; } - return 0; + err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count); + dma_unmap_single(dev, dma_dst, count, DMA_FROM_DEVICE); + if (!err) + return 0; + + dev_err(dev, "timeout waiting for DMA\n"); out_copy: memcpy(buf, this->base + bram_offset, count); @@ -437,49 +423,34 @@ static int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area, { struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd); struct onenand_chip *this = mtd->priv; - dma_addr_t dma_src, dma_dst; - int bram_offset; + struct device *dev = &c->pdev->dev; void *buf = (void *)buffer; - int ret; + dma_addr_t dma_src, dma_dst; + int bram_offset, err; bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset; - if (bram_offset & 3 || (size_t)buf & 3 || count < 384) - goto out_copy; - - /* panic_write() may be in an interrupt context */ - if (in_interrupt() || oops_in_progress) + /* + * If the buffer address is not DMA-able, len is not long enough to make + * DMA transfers profitable or panic_write() may be in an interrupt + * context fallback to PIO mode. + */ + if (!virt_addr_valid(buf) || bram_offset & 3 || (size_t)buf & 3 || + count < 384 || in_interrupt() || oops_in_progress ) goto out_copy; - if (buf >= high_memory) { - struct page *p1; - - if (((size_t)buf & PAGE_MASK) != - ((size_t)(buf + count - 1) & PAGE_MASK)) - goto out_copy; - p1 = vmalloc_to_page(buf); - if (!p1) - goto out_copy; - buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK); - } - - dma_src = dma_map_single(&c->pdev->dev, buf, count, DMA_TO_DEVICE); + dma_src = dma_map_single(dev, buf, count, DMA_TO_DEVICE); dma_dst = c->phys_base + bram_offset; - if (dma_mapping_error(&c->pdev->dev, dma_src)) { - dev_err(&c->pdev->dev, - "Couldn't DMA map a %d byte buffer\n", - count); - return -1; - } - - ret = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count); - dma_unmap_single(&c->pdev->dev, dma_src, count, DMA_TO_DEVICE); - - if (ret) { - dev_err(&c->pdev->dev, "timeout waiting for DMA\n"); + if (dma_mapping_error(dev, dma_src)) { + dev_err(dev, "Couldn't DMA map a %d byte buffer\n", count); goto out_copy; } - return 0; + err = omap2_onenand_dma_transfer(c, dma_src, dma_dst, count); + dma_unmap_page(dev, dma_src, count, DMA_TO_DEVICE); + if (!err) + return 0; + + dev_err(dev, "timeout waiting for DMA\n"); out_copy: memcpy(this->base + bram_offset, buf, count); diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 1d779a35ac8e..ebb1d141b900 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -1074,7 +1074,7 @@ static int marvell_nfc_hw_ecc_hmg_do_write_page(struct nand_chip *chip, return ret; ret = marvell_nfc_wait_op(chip, - chip->data_interface.timings.sdr.tPROG_max); + PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max)); return ret; } @@ -1194,11 +1194,13 @@ static void marvell_nfc_hw_ecc_bch_read_chunk(struct nand_chip *chip, int chunk, NDCB0_CMD2(NAND_CMD_READSTART); /* - * Trigger the naked read operation only on the last chunk. - * Otherwise, use monolithic read. + * Trigger the monolithic read on the first chunk, then naked read on + * intermediate chunks and finally a last naked read on the last chunk. */ - if (lt->nchunks == 1 || (chunk < lt->nchunks - 1)) + if (chunk == 0) nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_MONOLITHIC_RW); + else if (chunk < lt->nchunks - 1) + nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_NAKED_RW); else nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_LAST_NAKED_RW); @@ -1408,6 +1410,7 @@ marvell_nfc_hw_ecc_bch_write_chunk(struct nand_chip *chip, int chunk, struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip); struct marvell_nfc *nfc = to_marvell_nfc(chip->controller); const struct marvell_hw_ecc_layout *lt = to_marvell_nand(chip)->layout; + u32 xtype; int ret; struct marvell_nfc_op nfc_op = { .ndcb[0] = NDCB0_CMD_TYPE(TYPE_WRITE) | NDCB0_LEN_OVRD, @@ -1423,7 +1426,12 @@ marvell_nfc_hw_ecc_bch_write_chunk(struct nand_chip *chip, int chunk, * last naked write. */ if (chunk == 0) { - nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(XTYPE_WRITE_DISPATCH) | + if (lt->nchunks == 1) + xtype = XTYPE_MONOLITHIC_RW; + else + xtype = XTYPE_WRITE_DISPATCH; + + nfc_op.ndcb[0] |= NDCB0_CMD_XTYPE(xtype) | NDCB0_ADDR_CYC(marvell_nand->addr_cyc) | NDCB0_CMD1(NAND_CMD_SEQIN); nfc_op.ndcb[1] |= NDCB1_ADDRS_PAGE(page); @@ -1494,7 +1502,7 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct mtd_info *mtd, } ret = marvell_nfc_wait_op(chip, - chip->data_interface.timings.sdr.tPROG_max); + PSEC_TO_MSEC(chip->data_interface.timings.sdr.tPROG_max)); marvell_nfc_disable_hw_ecc(chip); diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 72f3a89da513..f28c3a555861 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -706,12 +706,17 @@ static void nand_wait_status_ready(struct mtd_info *mtd, unsigned long timeo) */ int nand_soft_waitrdy(struct nand_chip *chip, unsigned long timeout_ms) { + const struct nand_sdr_timings *timings; u8 status = 0; int ret; if (!chip->exec_op) return -ENOTSUPP; + /* Wait tWB before polling the STATUS reg. */ + timings = nand_get_sdr_timings(&chip->data_interface); + ndelay(PSEC_TO_NSEC(timings->tWB_max)); + ret = nand_status_op(chip, NULL); if (ret) return ret; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 1ed9529e7bd1..5eb0df2e5464 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -450,7 +450,7 @@ static void rlb_update_client(struct rlb_client_info *client_info) { int i; - if (!client_info->slave) + if (!client_info->slave || !is_valid_ether_addr(client_info->mac_dst)) return; for (i = 0; i < RLB_ARP_BURST_SIZE; i++) { @@ -943,6 +943,10 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[], skb->priority = TC_PRIO_CONTROL; skb->dev = slave->dev; + netdev_dbg(slave->bond->dev, + "Send learning packet: dev %s mac %pM vlan %d\n", + slave->dev->name, mac_addr, vid); + if (vid) __vlan_hwaccel_put_tag(skb, vlan_proto, vid); @@ -965,14 +969,13 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data) u8 *mac_addr = data->mac_addr; struct bond_vlan_tag *tags; - if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) { - if (strict_match && - ether_addr_equal_64bits(mac_addr, - upper->dev_addr)) { + if (is_vlan_dev(upper) && + bond->nest_level == vlan_get_encap_level(upper) - 1) { + if (upper->addr_assign_type == NET_ADDR_STOLEN) { alb_send_lp_vid(slave, mac_addr, vlan_dev_vlan_proto(upper), vlan_dev_vlan_id(upper)); - } else if (!strict_match) { + } else { alb_send_lp_vid(slave, upper->dev_addr, vlan_dev_vlan_proto(upper), vlan_dev_vlan_id(upper)); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 718e4914e3a0..1f1e97b26f95 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1738,6 +1738,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, if (bond_mode_uses_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); + bond->nest_level = dev_get_nest_level(bond_dev); + netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n", slave_dev->name, bond_is_active_slave(new_slave) ? "an active" : "a backup", diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c index b1779566c5bb..3c71f1cb205f 100644 --- a/drivers/net/can/dev.c +++ b/drivers/net/can/dev.c @@ -605,7 +605,7 @@ void can_bus_off(struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); - netdev_dbg(dev, "bus-off\n"); + netdev_info(dev, "bus-off\n"); netif_carrier_off(dev); diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 634c51e6b8ae..d53a45bf2a72 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -200,6 +200,7 @@ #define FLEXCAN_QUIRK_DISABLE_MECR BIT(4) /* Disable Memory error detection */ #define FLEXCAN_QUIRK_USE_OFF_TIMESTAMP BIT(5) /* Use timestamp based offloading */ #define FLEXCAN_QUIRK_BROKEN_PERR_STATE BIT(6) /* No interrupt for error passive */ +#define FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN BIT(7) /* default to BE register access */ /* Structure of the message buffer */ struct flexcan_mb { @@ -288,6 +289,12 @@ struct flexcan_priv { static const struct flexcan_devtype_data fsl_p1010_devtype_data = { .quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE | + FLEXCAN_QUIRK_BROKEN_PERR_STATE | + FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN, +}; + +static const struct flexcan_devtype_data fsl_imx25_devtype_data = { + .quirks = FLEXCAN_QUIRK_BROKEN_WERR_STATE | FLEXCAN_QUIRK_BROKEN_PERR_STATE, }; @@ -1251,9 +1258,9 @@ static void unregister_flexcandev(struct net_device *dev) static const struct of_device_id flexcan_of_match[] = { { .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, }, { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, }, - { .compatible = "fsl,imx53-flexcan", .data = &fsl_p1010_devtype_data, }, - { .compatible = "fsl,imx35-flexcan", .data = &fsl_p1010_devtype_data, }, - { .compatible = "fsl,imx25-flexcan", .data = &fsl_p1010_devtype_data, }, + { .compatible = "fsl,imx53-flexcan", .data = &fsl_imx25_devtype_data, }, + { .compatible = "fsl,imx35-flexcan", .data = &fsl_imx25_devtype_data, }, + { .compatible = "fsl,imx25-flexcan", .data = &fsl_imx25_devtype_data, }, { .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, }, { .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, }, { .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, }, @@ -1337,18 +1344,13 @@ static int flexcan_probe(struct platform_device *pdev) priv = netdev_priv(dev); - if (of_property_read_bool(pdev->dev.of_node, "big-endian")) { + if (of_property_read_bool(pdev->dev.of_node, "big-endian") || + devtype_data->quirks & FLEXCAN_QUIRK_DEFAULT_BIG_ENDIAN) { priv->read = flexcan_read_be; priv->write = flexcan_write_be; } else { - if (of_device_is_compatible(pdev->dev.of_node, - "fsl,p1010-flexcan")) { - priv->read = flexcan_read_be; - priv->write = flexcan_write_be; - } else { - priv->read = flexcan_read_le; - priv->write = flexcan_write_le; - } + priv->read = flexcan_read_le; + priv->write = flexcan_write_le; } priv->can.clock.freq = clock_freq; diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index 5590c559a8ca..53e320c92a8b 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -91,6 +91,7 @@ #define HI3110_STAT_BUSOFF BIT(2) #define HI3110_STAT_ERRP BIT(3) #define HI3110_STAT_ERRW BIT(4) +#define HI3110_STAT_TXMTY BIT(7) #define HI3110_BTR0_SJW_SHIFT 6 #define HI3110_BTR0_BRP_SHIFT 0 @@ -427,8 +428,10 @@ static int hi3110_get_berr_counter(const struct net_device *net, struct hi3110_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; + mutex_lock(&priv->hi3110_lock); bec->txerr = hi3110_read(spi, HI3110_READ_TEC); bec->rxerr = hi3110_read(spi, HI3110_READ_REC); + mutex_unlock(&priv->hi3110_lock); return 0; } @@ -735,10 +738,7 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id) } } - if (intf == 0) - break; - - if (intf & HI3110_INT_TXCPLT) { + if (priv->tx_len && statf & HI3110_STAT_TXMTY) { net->stats.tx_packets++; net->stats.tx_bytes += priv->tx_len - 1; can_led_event(net, CAN_LED_EVENT_TX); @@ -748,6 +748,9 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id) } netif_wake_queue(net); } + + if (intf == 0) + break; } mutex_unlock(&priv->hi3110_lock); return IRQ_HANDLED; diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c index 63587b8e6825..daed57d3d209 100644 --- a/drivers/net/can/usb/kvaser_usb.c +++ b/drivers/net/can/usb/kvaser_usb.c @@ -1179,7 +1179,7 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev, skb = alloc_can_skb(priv->netdev, &cf); if (!skb) { - stats->tx_dropped++; + stats->rx_dropped++; return; } diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 3d2091099f7f..5b4374f21d76 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3370,6 +3370,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 5, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3391,6 +3392,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 0, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3410,6 +3412,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 8, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3431,6 +3434,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 5, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3452,6 +3456,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 0, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3472,6 +3477,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 11, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x10, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 3750, @@ -3493,6 +3499,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 5, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3514,6 +3521,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 0, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3535,6 +3543,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 5, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3557,6 +3566,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3578,6 +3588,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 5, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3600,6 +3611,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3621,6 +3633,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 0, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3641,6 +3654,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .tag_protocol = DSA_TAG_PROTO_DSA, @@ -3663,6 +3677,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 3750, @@ -3684,6 +3699,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 11, .max_vid = 8191, .port_base_addr = 0x0, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 3750, @@ -3707,6 +3723,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3730,6 +3747,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 3750, @@ -3753,6 +3771,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3776,6 +3795,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3798,6 +3818,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 11, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x10, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 3750, @@ -3820,6 +3841,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 5, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3841,6 +3863,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_internal_phys = 5, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3863,6 +3886,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 15, .max_vid = 4095, .port_base_addr = 0x10, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 15000, @@ -3885,6 +3909,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 3750, @@ -3907,6 +3932,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = { .num_gpio = 16, .max_vid = 8191, .port_base_addr = 0x0, + .phy_base_addr = 0x0, .global1_addr = 0x1b, .global2_addr = 0x1c, .age_time_coeff = 3750, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 80490f66bc06..12b7f4649b25 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -114,6 +114,7 @@ struct mv88e6xxx_info { unsigned int num_gpio; unsigned int max_vid; unsigned int port_base_addr; + unsigned int phy_base_addr; unsigned int global1_addr; unsigned int global2_addr; unsigned int age_time_coeff; diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 0ce627fded48..8d22d66d84b7 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -1118,7 +1118,7 @@ int mv88e6xxx_g2_irq_mdio_setup(struct mv88e6xxx_chip *chip, err = irq; goto out; } - bus->irq[chip->info->port_base_addr + phy] = irq; + bus->irq[chip->info->phy_base_addr + phy] = irq; } return 0; out: diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 32f6d2e24d66..1a1a6380c128 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -95,6 +95,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self) /*rss rings */ cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF); cfg->vecs = min(cfg->vecs, num_online_cpus()); + cfg->vecs = min(cfg->vecs, self->irqvecs); /* cfg->vecs should be power of 2 for RSS */ if (cfg->vecs >= 8U) cfg->vecs = 8U; @@ -246,6 +247,8 @@ void aq_nic_ndev_init(struct aq_nic_s *self) self->ndev->hw_features |= aq_hw_caps->hw_features; self->ndev->features = aq_hw_caps->hw_features; + self->ndev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM | + NETIF_F_RXHASH | NETIF_F_SG | NETIF_F_LRO; self->ndev->priv_flags = aq_hw_caps->hw_priv_flags; self->ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index 219b550d1665..faa533a0ec47 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -80,6 +80,7 @@ struct aq_nic_s { struct pci_dev *pdev; unsigned int msix_entry_mask; + u32 irqvecs; }; static inline struct device *aq_nic_get_dev(struct aq_nic_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index ecc6306f940f..a50e08bb4748 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -267,16 +267,16 @@ static int aq_pci_probe(struct pci_dev *pdev, numvecs = min(numvecs, num_online_cpus()); /*enable interrupts */ #if !AQ_CFG_FORCE_LEGACY_INT - err = pci_alloc_irq_vectors(self->pdev, numvecs, numvecs, - PCI_IRQ_MSIX); - - if (err < 0) { - err = pci_alloc_irq_vectors(self->pdev, 1, 1, - PCI_IRQ_MSI | PCI_IRQ_LEGACY); - if (err < 0) - goto err_hwinit; + numvecs = pci_alloc_irq_vectors(self->pdev, 1, numvecs, + PCI_IRQ_MSIX | PCI_IRQ_MSI | + PCI_IRQ_LEGACY); + + if (numvecs < 0) { + err = numvecs; + goto err_hwinit; } #endif + self->irqvecs = numvecs; /* net device init */ aq_nic_cfg_start(self); @@ -298,9 +298,9 @@ err_free_aq_hw: kfree(self->aq_hw); err_ioremap: free_netdev(ndev); -err_pci_func: - pci_release_regions(pdev); err_ndev: + pci_release_regions(pdev); +err_pci_func: pci_disable_device(pdev); return err; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 08bbb639be1a..9f59b1270a7c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -8733,14 +8733,15 @@ static void tg3_free_consistent(struct tg3 *tp) tg3_mem_rx_release(tp); tg3_mem_tx_release(tp); - /* Protect tg3_get_stats64() from reading freed tp->hw_stats. */ - tg3_full_lock(tp, 0); + /* tp->hw_stats can be referenced safely: + * 1. under rtnl_lock + * 2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set. + */ if (tp->hw_stats) { dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats), tp->hw_stats, tp->stats_mapping); tp->hw_stats = NULL; } - tg3_full_unlock(tp); } /* @@ -14178,7 +14179,7 @@ static void tg3_get_stats64(struct net_device *dev, struct tg3 *tp = netdev_priv(dev); spin_lock_bh(&tp->lock); - if (!tp->hw_stats) { + if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) { *stats = tp->net_stats_prev; spin_unlock_bh(&tp->lock); return; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 24d2865b8806..005283c7cdfe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3433,8 +3433,8 @@ static int adap_config_hma(struct adapter *adapter) sgl = adapter->hma.sgt->sgl; node = dev_to_node(adapter->pdev_dev); for_each_sg(sgl, iter, sgt->orig_nents, i) { - newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL, - page_order); + newpage = alloc_pages_node(node, __GFP_NOWARN | GFP_KERNEL | + __GFP_ZERO, page_order); if (!newpage) { dev_err(adapter->pdev_dev, "Not enough memory for HMA page allocation\n"); @@ -5474,6 +5474,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } spin_lock_init(&adapter->mbox_lock); INIT_LIST_HEAD(&adapter->mlist.list); + adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS; pci_set_drvdata(pdev, adapter); if (func != ent->driver_data) { @@ -5508,8 +5509,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto out_free_adapter; } - adapter->mbox_log->size = T4_OS_LOG_MBOX_CMDS; - /* PCI device has been enabled */ adapter->flags |= DEV_ENABLED; memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map)); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 5909a4407e38..7c511f144ed6 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -1014,10 +1014,10 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, desc = ICE_CTL_Q_DESC(cq->rq, ntc); desc_idx = ntc; + cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval); flags = le16_to_cpu(desc->flags); if (flags & ICE_AQ_FLAG_ERR) { ret_code = ICE_ERR_AQ_ERROR; - cq->rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval); ice_debug(hw, ICE_DBG_AQ_MSG, "Control Receive Queue Event received with error 0x%x\n", cq->rq_last_status); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 68af127987bc..cead23e3db0c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -943,8 +943,8 @@ err2: kfree(ipsec->ip_tbl); kfree(ipsec->rx_tbl); kfree(ipsec->tx_tbl); + kfree(ipsec); err1: - kfree(adapter->ipsec); netdev_err(adapter->netdev, "Unable to allocate memory for SA tables"); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 3123267dfba9..9592f3e3e42e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -3427,6 +3427,9 @@ static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) hw->phy.sfp_setup_needed = false; } + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + return status; + /* Reset PHY */ if (!hw->phy.reset_disable && hw->phy.ops.reset) hw->phy.ops.reset(hw); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index e3d04f226d57..850f8af95e49 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -4137,7 +4137,7 @@ out_drop: return NETDEV_TX_OK; } -static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbevf_ring *tx_ring; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a30a2e95d13f..f11b45001cad 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1027,6 +1027,22 @@ static int mlx4_en_set_coalesce(struct net_device *dev, if (!coal->tx_max_coalesced_frames_irq) return -EINVAL; + if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) { + netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n", + __func__, MLX4_EN_MAX_COAL_TIME); + return -ERANGE; + } + + if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS || + coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) { + netdev_info(dev, "%s: maximum coalesced frames supported is %d\n", + __func__, MLX4_EN_MAX_COAL_PKTS); + return -ERANGE; + } + priv->rx_frames = (coal->rx_max_coalesced_frames == MLX4_EN_AUTO_CONF) ? MLX4_EN_RX_COAL_TARGET : diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index e0adac4a9a19..9670b33fc9b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3324,12 +3324,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, MAX_TX_RINGS, GFP_KERNEL); if (!priv->tx_ring[t]) { err = -ENOMEM; - goto err_free_tx; + goto out; } priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS, GFP_KERNEL); if (!priv->tx_cq[t]) { - kfree(priv->tx_ring[t]); err = -ENOMEM; goto out; } @@ -3582,11 +3581,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, return 0; -err_free_tx: - while (t--) { - kfree(priv->tx_ring[t]); - kfree(priv->tx_cq[t]); - } out: mlx4_en_destroy_netdev(dev); return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index f7c81133594f..ace6545f82e6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -132,6 +132,9 @@ #define MLX4_EN_TX_COAL_PKTS 16 #define MLX4_EN_TX_COAL_TIME 0x10 +#define MLX4_EN_MAX_COAL_PKTS U16_MAX +#define MLX4_EN_MAX_COAL_TIME U16_MAX + #define MLX4_EN_RX_RATE_LOW 400000 #define MLX4_EN_RX_COAL_TIME_LOW 0 #define MLX4_EN_RX_RATE_HIGH 450000 @@ -552,8 +555,8 @@ struct mlx4_en_priv { u16 rx_usecs_low; u32 pkt_rate_high; u16 rx_usecs_high; - u16 sample_interval; - u16 adaptive_rx_coal; + u32 sample_interval; + u32 adaptive_rx_coal; u32 msg_enable; u32 loopback_ok; u32 validate_loopback; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3c534fc43400..b94276db3ce9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1261,6 +1261,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, f->mask); addr_type = key->addr_type; + /* the HW doesn't support frag first/later */ + if (mask->flags & FLOW_DIS_FIRST_FRAG) + return -EOPNOTSUPP; + if (mask->flags & FLOW_DIS_IS_FRAGMENT) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index c1c94974e16b..1814f803bd2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -34,6 +34,9 @@ #include <linux/module.h> #include <linux/mlx5/driver.h> #include <linux/mlx5/cmd.h> +#ifdef CONFIG_RFS_ACCEL +#include <linux/cpu_rmap.h> +#endif #include "mlx5_core.h" #include "fpga/core.h" #include "eswitch.h" @@ -923,3 +926,28 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, MLX5_SET(query_eq_in, in, eq_number, eq->eqn); return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } + +/* This function should only be called after mlx5_cmd_force_teardown_hca */ +void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) +{ + struct mlx5_eq_table *table = &dev->priv.eq_table; + struct mlx5_eq *eq; + +#ifdef CONFIG_RFS_ACCEL + if (dev->rmap) { + free_irq_cpu_rmap(dev->rmap); + dev->rmap = NULL; + } +#endif + list_for_each_entry(eq, &table->comp_eqs_list, list) + free_irq(eq->irqn, eq); + + free_irq(table->pages_eq.irqn, &table->pages_eq); + free_irq(table->async_eq.irqn, &table->async_eq); + free_irq(table->cmd_eq.irqn, &table->cmd_eq); +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING + if (MLX5_CAP_GEN(dev, pg)) + free_irq(table->pfault_eq.irqn, &table->pfault_eq); +#endif + pci_free_irq_vectors(dev->pdev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 332bc56306bf..1352d13eedb3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2175,26 +2175,35 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, memset(vf_stats, 0, sizeof(*vf_stats)); vf_stats->rx_packets = MLX5_GET_CTR(out, received_eth_unicast.packets) + + MLX5_GET_CTR(out, received_ib_unicast.packets) + MLX5_GET_CTR(out, received_eth_multicast.packets) + + MLX5_GET_CTR(out, received_ib_multicast.packets) + MLX5_GET_CTR(out, received_eth_broadcast.packets); vf_stats->rx_bytes = MLX5_GET_CTR(out, received_eth_unicast.octets) + + MLX5_GET_CTR(out, received_ib_unicast.octets) + MLX5_GET_CTR(out, received_eth_multicast.octets) + + MLX5_GET_CTR(out, received_ib_multicast.octets) + MLX5_GET_CTR(out, received_eth_broadcast.octets); vf_stats->tx_packets = MLX5_GET_CTR(out, transmitted_eth_unicast.packets) + + MLX5_GET_CTR(out, transmitted_ib_unicast.packets) + MLX5_GET_CTR(out, transmitted_eth_multicast.packets) + + MLX5_GET_CTR(out, transmitted_ib_multicast.packets) + MLX5_GET_CTR(out, transmitted_eth_broadcast.packets); vf_stats->tx_bytes = MLX5_GET_CTR(out, transmitted_eth_unicast.octets) + + MLX5_GET_CTR(out, transmitted_ib_unicast.octets) + MLX5_GET_CTR(out, transmitted_eth_multicast.octets) + + MLX5_GET_CTR(out, transmitted_ib_multicast.octets) + MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); vf_stats->multicast = - MLX5_GET_CTR(out, received_eth_multicast.packets); + MLX5_GET_CTR(out, received_eth_multicast.packets) + + MLX5_GET_CTR(out, received_ib_multicast.packets); vf_stats->broadcast = MLX5_GET_CTR(out, received_eth_broadcast.packets); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 63a8ea31601c..e2c465b0b3f8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1587,6 +1587,14 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) mlx5_enter_error_state(dev, true); + /* Some platforms requiring freeing the IRQ's in the shutdown + * flow. If they aren't freed they can't be allocated after + * kexec. There is no need to cleanup the mlx5_core software + * contexts. + */ + mlx5_irq_clear_affinity_hints(dev); + mlx5_core_eq_free_irqs(dev); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 7d001fe6e631..023882d9a22e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -128,6 +128,8 @@ int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u32 *out, int outlen); int mlx5_start_eqs(struct mlx5_core_dev *dev); void mlx5_stop_eqs(struct mlx5_core_dev *dev); +/* This function should only be called after mlx5_cmd_force_teardown_hca */ +void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev); struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn); u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq); void mlx5_cq_tasklet_cb(unsigned long data); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 93ea56620a24..e13ac3b8dff7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1100,11 +1100,11 @@ err_emad_init: err_alloc_lag_mapping: mlxsw_ports_fini(mlxsw_core); err_ports_init: - mlxsw_bus->fini(bus_priv); -err_bus_init: if (!reload) devlink_resources_unregister(devlink, NULL); err_register_resources: + mlxsw_bus->fini(bus_priv); +err_bus_init: if (!reload) devlink_free(devlink); err_devlink_alloc: diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index a997e34bcec2..84e3b9f5abb1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -52,8 +52,6 @@ #define NFP_FLOWER_ALLOWED_VER 0x0001000000010000UL -#define NFP_FLOWER_FRAME_HEADROOM 158 - static const char *nfp_flower_extra_cap(struct nfp_app *app, struct nfp_net *nn) { return "FLOWER"; @@ -559,22 +557,6 @@ static void nfp_flower_clean(struct nfp_app *app) app->priv = NULL; } -static int -nfp_flower_check_mtu(struct nfp_app *app, struct net_device *netdev, - int new_mtu) -{ - /* The flower fw reserves NFP_FLOWER_FRAME_HEADROOM bytes of the - * supported max MTU to allow for appending tunnel headers. To prevent - * unexpected behaviour this needs to be accounted for. - */ - if (new_mtu > netdev->max_mtu - NFP_FLOWER_FRAME_HEADROOM) { - nfp_err(app->cpp, "New MTU (%d) is not valid\n", new_mtu); - return -EINVAL; - } - - return 0; -} - static bool nfp_flower_check_ack(struct nfp_flower_priv *app_priv) { bool ret; @@ -656,7 +638,6 @@ const struct nfp_app_type app_flower = { .init = nfp_flower_init, .clean = nfp_flower_clean, - .check_mtu = nfp_flower_check_mtu, .repr_change_mtu = nfp_flower_repr_change_mtu, .vnic_alloc = nfp_flower_vnic_alloc, diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 27364b7572fc..b092894dd128 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1170,7 +1170,7 @@ static void *nixge_get_nvmem_address(struct device *dev) cell = nvmem_cell_get(dev, "address"); if (IS_ERR(cell)) - return cell; + return NULL; mac = nvmem_cell_read(cell, &cell_size); nvmem_cell_put(cell); @@ -1183,7 +1183,7 @@ static int nixge_probe(struct platform_device *pdev) struct nixge_priv *priv; struct net_device *ndev; struct resource *dmares; - const char *mac_addr; + const u8 *mac_addr; int err; ndev = alloc_etherdev(sizeof(*priv)); @@ -1202,10 +1202,12 @@ static int nixge_probe(struct platform_device *pdev) ndev->max_mtu = NIXGE_JUMBO_MTU; mac_addr = nixge_get_nvmem_address(&pdev->dev); - if (mac_addr && is_valid_ether_addr(mac_addr)) + if (mac_addr && is_valid_ether_addr(mac_addr)) { ether_addr_copy(ndev->dev_addr, mac_addr); - else + kfree(mac_addr); + } else { eth_hw_addr_random(ndev); + } priv = netdev_priv(ndev); priv->ndev = ndev; diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index e874504e8b28..8667799d0069 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -115,8 +115,7 @@ int qed_l2_alloc(struct qed_hwfn *p_hwfn) void qed_l2_setup(struct qed_hwfn *p_hwfn) { - if (p_hwfn->hw_info.personality != QED_PCI_ETH && - p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE) + if (!QED_IS_L2_PERSONALITY(p_hwfn)) return; mutex_init(&p_hwfn->p_l2_info->lock); @@ -126,8 +125,7 @@ void qed_l2_free(struct qed_hwfn *p_hwfn) { u32 i; - if (p_hwfn->hw_info.personality != QED_PCI_ETH && - p_hwfn->hw_info.personality != QED_PCI_ETH_ROCE) + if (!QED_IS_L2_PERSONALITY(p_hwfn)) return; if (!p_hwfn->p_l2_info) diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 9854aa9139af..7870ae2a6f7e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -680,7 +680,7 @@ static int qed_nic_stop(struct qed_dev *cdev) tasklet_disable(p_hwfn->sp_dpc); p_hwfn->b_sp_dpc_enabled = false; DP_VERBOSE(cdev, NETIF_MSG_IFDOWN, - "Disabled sp taskelt [hwfn %d] at %p\n", + "Disabled sp tasklet [hwfn %d] at %p\n", i, p_hwfn->sp_dpc); } } diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index 50b142fad6b8..1900bf7e67d1 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -238,7 +238,7 @@ qede_rdma_get_free_event_node(struct qede_dev *edev) } if (!found) { - event_node = kzalloc(sizeof(*event_node), GFP_KERNEL); + event_node = kzalloc(sizeof(*event_node), GFP_ATOMIC); if (!event_node) { DP_NOTICE(edev, "qedr: Could not allocate memory for rdma work\n"); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 604ae78381ae..c7aac1fc99e8 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4981,6 +4981,9 @@ static void rtl_pll_power_down(struct rtl8169_private *tp) static void rtl_pll_power_up(struct rtl8169_private *tp) { rtl_generic_op(tp, tp->pll_power_ops.up); + + /* give MAC/PHY some time to resume */ + msleep(20); } static void rtl_init_pll_power_ops(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index f081de4f38d7..88c12474a0c3 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3443,7 +3443,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, len = (val & RCR_ENTRY_L2_LEN) >> RCR_ENTRY_L2_LEN_SHIFT; - len -= ETH_FCS_LEN; + append_size = len + ETH_HLEN + ETH_FCS_LEN; addr = (val & RCR_ENTRY_PKT_BUF_ADDR) << RCR_ENTRY_PKT_BUF_ADDR_SHIFT; @@ -3453,7 +3453,6 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, RCR_ENTRY_PKTBUFSZ_SHIFT]; off = addr & ~PAGE_MASK; - append_size = rcr_size; if (num_rcr == 1) { int ptype; @@ -3466,7 +3465,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, else skb_checksum_none_assert(skb); } else if (!(val & RCR_ENTRY_MULTI)) - append_size = len - skb->len; + append_size = append_size - skb->len; niu_rx_skb_append(skb, page, off, append_size, rcr_size); if ((page->index + rp->rbr_block_size) - rcr_size == addr) { diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index ecc84954c511..da07ccdf84bf 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1840,7 +1840,8 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto rx_handler_failed; } - ret = netdev_upper_dev_link(vf_netdev, ndev, NULL); + ret = netdev_master_upper_dev_link(vf_netdev, ndev, + NULL, NULL, NULL); if (ret != 0) { netdev_err(vf_netdev, "can not set master device %s (err = %d)\n", diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 6b127be781d9..e7ca5b5f39ed 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1288,7 +1288,7 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, rndis_device->link_state ? "down" : "up"); if (net_device->nvsp_version < NVSP_PROTOCOL_VERSION_5) - return net_device; + goto out; rndis_filter_query_link_speed(rndis_device, net_device); diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 9fb9b565a002..4f684cbcdc57 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -1045,7 +1045,7 @@ static int atusb_probe(struct usb_interface *interface, atusb->tx_dr.bRequest = ATUSB_TX; atusb->tx_dr.wValue = cpu_to_le16(0); - atusb->tx_urb = usb_alloc_urb(0, GFP_ATOMIC); + atusb->tx_urb = usb_alloc_urb(0, GFP_KERNEL); if (!atusb->tx_urb) goto fail; diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 55a22c761808..de0d7f28a181 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -1267,7 +1267,7 @@ mcr20a_probe(struct spi_device *spi) ret = mcr20a_get_platform_data(spi, pdata); if (ret < 0) { dev_crit(&spi->dev, "mcr20a_get_platform_data failed.\n"); - return ret; + goto free_pdata; } /* init reset gpio */ @@ -1275,7 +1275,7 @@ mcr20a_probe(struct spi_device *spi) ret = devm_gpio_request_one(&spi->dev, pdata->rst_gpio, GPIOF_OUT_INIT_HIGH, "reset"); if (ret) - return ret; + goto free_pdata; } /* reset mcr20a */ @@ -1291,7 +1291,8 @@ mcr20a_probe(struct spi_device *spi) hw = ieee802154_alloc_hw(sizeof(*lp), &mcr20a_hw_ops); if (!hw) { dev_crit(&spi->dev, "ieee802154_alloc_hw failed\n"); - return -ENOMEM; + ret = -ENOMEM; + goto free_pdata; } /* init mcr20a local data */ @@ -1308,8 +1309,10 @@ mcr20a_probe(struct spi_device *spi) /* init buf */ lp->buf = devm_kzalloc(&spi->dev, SPI_COMMAND_BUFFER, GFP_KERNEL); - if (!lp->buf) - return -ENOMEM; + if (!lp->buf) { + ret = -ENOMEM; + goto free_dev; + } mcr20a_setup_tx_spi_messages(lp); mcr20a_setup_rx_spi_messages(lp); @@ -1366,6 +1369,8 @@ mcr20a_probe(struct spi_device *spi) free_dev: ieee802154_free_hw(lp->hw); +free_pdata: + kfree(pdata); return ret; } diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 3bb6b66dc7bf..f9c25912eb98 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -720,6 +720,15 @@ static struct phy_driver broadcom_drivers[] = { .get_strings = bcm_phy_get_strings, .get_stats = bcm53xx_phy_get_stats, .probe = bcm53xx_phy_probe, +}, { + .phy_id = PHY_ID_BCM89610, + .phy_id_mask = 0xfffffff0, + .name = "Broadcom BCM89610", + .features = PHY_GBIT_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = bcm54xx_config_init, + .ack_interrupt = bcm_phy_ack_intr, + .config_intr = bcm_phy_config_intr, } }; module_phy_driver(broadcom_drivers); @@ -741,6 +750,7 @@ static struct mdio_device_id __maybe_unused broadcom_tbl[] = { { PHY_ID_BCMAC131, 0xfffffff0 }, { PHY_ID_BCM5241, 0xfffffff0 }, { PHY_ID_BCM5395, 0xfffffff0 }, + { PHY_ID_BCM89610, 0xfffffff0 }, { } }; diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index 0381da78d228..fd6c23f69c2f 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -125,7 +125,7 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, if (id->base.br_nominal) { if (id->base.br_nominal != 255) { br_nom = id->base.br_nominal * 100; - br_min = br_nom + id->base.br_nominal * id->ext.br_min; + br_min = br_nom - id->base.br_nominal * id->ext.br_min; br_max = br_nom + id->base.br_nominal * id->ext.br_max; } else if (id->ext.br_max) { br_nom = 250 * id->ext.br_max; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 96d26cfae90b..4a017a0d71ea 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3236,6 +3236,7 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) GENL_SET_ERR_MSG(info,"MAC is no valid source addr"); NL_SET_BAD_ATTR(info->extack, info->attrs[HWSIM_ATTR_PERM_ADDR]); + kfree(hwname); return -EINVAL; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index a3771c5729f5..99b857e5a7a9 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -99,6 +99,7 @@ static struct class *nvme_subsys_class; static void nvme_ns_remove(struct nvme_ns *ns); static int nvme_revalidate_disk(struct gendisk *disk); +static void nvme_put_subsystem(struct nvme_subsystem *subsys); int nvme_reset_ctrl(struct nvme_ctrl *ctrl) { @@ -117,7 +118,8 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) ret = nvme_reset_ctrl(ctrl); if (!ret) { flush_work(&ctrl->reset_work); - if (ctrl->state != NVME_CTRL_LIVE) + if (ctrl->state != NVME_CTRL_LIVE && + ctrl->state != NVME_CTRL_ADMIN_ONLY) ret = -ENETRESET; } @@ -350,6 +352,7 @@ static void nvme_free_ns_head(struct kref *ref) ida_simple_remove(&head->subsys->ns_ida, head->instance); list_del_init(&head->entry); cleanup_srcu_struct(&head->srcu); + nvme_put_subsystem(head->subsys); kfree(head); } @@ -2861,6 +2864,9 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl, goto out_cleanup_srcu; list_add_tail(&head->entry, &ctrl->subsys->nsheads); + + kref_get(&ctrl->subsys->ref); + return head; out_cleanup_srcu: cleanup_srcu_struct(&head->srcu); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 7ded7a51c430..17d2f7cf3fed 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -84,6 +84,11 @@ enum nvme_quirks { * Supports the LighNVM command set if indicated in vs[1]. */ NVME_QUIRK_LIGHTNVM = (1 << 6), + + /* + * Set MEDIUM priority on SQ creation + */ + NVME_QUIRK_MEDIUM_PRIO_SQ = (1 << 7), }; /* diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fbc71fac6f1e..17a0190bd88f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1093,10 +1093,19 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid, static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid, struct nvme_queue *nvmeq) { + struct nvme_ctrl *ctrl = &dev->ctrl; struct nvme_command c; int flags = NVME_QUEUE_PHYS_CONTIG; /* + * Some drives have a bug that auto-enables WRRU if MEDIUM isn't + * set. Since URGENT priority is zeroes, it makes all queues + * URGENT. + */ + if (ctrl->quirks & NVME_QUIRK_MEDIUM_PRIO_SQ) + flags |= NVME_SQ_PRIO_MEDIUM; + + /* * Note: we (ab)use the fact that the prp fields survive if no data * is attached to the request. */ @@ -2701,7 +2710,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_STRIPE_SIZE | NVME_QUIRK_DEALLOCATE_ZEROES, }, { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */ - .driver_data = NVME_QUIRK_NO_DEEPEST_PS }, + .driver_data = NVME_QUIRK_NO_DEEPEST_PS | + NVME_QUIRK_MEDIUM_PRIO_SQ }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ .driver_data = NVME_QUIRK_IDENTIFY_CNS, }, { PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */ diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index b35fe88f1851..7baa53e5b1d7 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -102,12 +102,28 @@ static DEFINE_IDR(ovcs_idr); static BLOCKING_NOTIFIER_HEAD(overlay_notify_chain); +/** + * of_overlay_notifier_register() - Register notifier for overlay operations + * @nb: Notifier block to register + * + * Register for notification on overlay operations on device tree nodes. The + * reported actions definied by @of_reconfig_change. The notifier callback + * furthermore receives a pointer to the affected device tree node. + * + * Note that a notifier callback is not supposed to store pointers to a device + * tree node or its content beyond @OF_OVERLAY_POST_REMOVE corresponding to the + * respective node it received. + */ int of_overlay_notifier_register(struct notifier_block *nb) { return blocking_notifier_chain_register(&overlay_notify_chain, nb); } EXPORT_SYMBOL_GPL(of_overlay_notifier_register); +/** + * of_overlay_notifier_register() - Unregister notifier for overlay operations + * @nb: Notifier block to unregister + */ int of_overlay_notifier_unregister(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&overlay_notify_chain, nb); @@ -671,17 +687,13 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs) of_node_put(ovcs->fragments[i].overlay); } kfree(ovcs->fragments); - /* - * TODO - * - * would like to: kfree(ovcs->overlay_tree); - * but can not since drivers may have pointers into this data - * - * would like to: kfree(ovcs->fdt); - * but can not since drivers may have pointers into this data + * There should be no live pointers into ovcs->overlay_tree and + * ovcs->fdt due to the policy that overlay notifiers are not allowed + * to retain pointers into the overlay devicetree. */ - + kfree(ovcs->overlay_tree); + kfree(ovcs->fdt); kfree(ovcs); } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index a04197ce767d..dbfe7c4f3776 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1910,7 +1910,7 @@ void pci_pme_active(struct pci_dev *dev, bool enable) EXPORT_SYMBOL(pci_pme_active); /** - * pci_enable_wake - enable PCI device as wakeup event source + * __pci_enable_wake - enable PCI device as wakeup event source * @dev: PCI device affected * @state: PCI state from which device will issue wakeup events * @enable: True to enable event generation; false to disable @@ -1928,7 +1928,7 @@ EXPORT_SYMBOL(pci_pme_active); * Error code depending on the platform is returned if both the platform and * the native mechanism fail to enable the generation of wake-up events */ -int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) +static int __pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) { int ret = 0; @@ -1969,6 +1969,23 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, bool enable) return ret; } + +/** + * pci_enable_wake - change wakeup settings for a PCI device + * @pci_dev: Target device + * @state: PCI state from which device will issue wakeup events + * @enable: Whether or not to enable event generation + * + * If @enable is set, check device_may_wakeup() for the device before calling + * __pci_enable_wake() for it. + */ +int pci_enable_wake(struct pci_dev *pci_dev, pci_power_t state, bool enable) +{ + if (enable && !device_may_wakeup(&pci_dev->dev)) + return -EINVAL; + + return __pci_enable_wake(pci_dev, state, enable); +} EXPORT_SYMBOL(pci_enable_wake); /** @@ -1981,9 +1998,9 @@ EXPORT_SYMBOL(pci_enable_wake); * should not be called twice in a row to enable wake-up due to PCI PM vs ACPI * ordering constraints. * - * This function only returns error code if the device is not capable of - * generating PME# from both D3_hot and D3_cold, and the platform is unable to - * enable wake-up power for it. + * This function only returns error code if the device is not allowed to wake + * up the system from sleep or it is not capable of generating PME# from both + * D3_hot and D3_cold and the platform is unable to enable wake-up power for it. */ int pci_wake_from_d3(struct pci_dev *dev, bool enable) { @@ -2114,7 +2131,7 @@ int pci_finish_runtime_suspend(struct pci_dev *dev) dev->runtime_d3cold = target_state == PCI_D3cold; - pci_enable_wake(dev, target_state, pci_dev_run_wake(dev)); + __pci_enable_wake(dev, target_state, pci_dev_run_wake(dev)); error = pci_set_power_state(dev, target_state); @@ -2138,16 +2155,16 @@ bool pci_dev_run_wake(struct pci_dev *dev) { struct pci_bus *bus = dev->bus; - if (device_can_wakeup(&dev->dev)) - return true; - if (!dev->pme_support) return false; /* PME-capable in principle, but not from the target power state */ - if (!pci_pme_capable(dev, pci_target_state(dev, false))) + if (!pci_pme_capable(dev, pci_target_state(dev, true))) return false; + if (device_can_wakeup(&dev->dev)) + return true; + while (bus->parent) { struct pci_dev *bridge = bus->self; diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index b1ae1618fefe..fee9225ca559 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1622,22 +1622,30 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq) if (!need_valid_mask) { irq_base = devm_irq_alloc_descs(pctrl->dev, -1, 0, - chip->ngpio, NUMA_NO_NODE); + community->npins, NUMA_NO_NODE); if (irq_base < 0) { dev_err(pctrl->dev, "Failed to allocate IRQ numbers\n"); return irq_base; } - } else { - irq_base = 0; } - ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, irq_base, + ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0, handle_bad_irq, IRQ_TYPE_NONE); if (ret) { dev_err(pctrl->dev, "failed to add IRQ chip\n"); return ret; } + if (!need_valid_mask) { + for (i = 0; i < community->ngpio_ranges; i++) { + range = &community->gpio_ranges[i]; + + irq_domain_associate_many(chip->irq.domain, irq_base, + range->base, range->npins); + irq_base += range->npins; + } + } + gpiochip_set_chained_irqchip(chip, &chv_gpio_irqchip, irq, chv_gpio_irq_handler); return 0; diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c index 8870a4100164..fee3435a6f15 100644 --- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c +++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c @@ -36,6 +36,27 @@ .npins = ((e) - (s) + 1), \ } +#define SPTH_GPP(r, s, e, g) \ + { \ + .reg_num = (r), \ + .base = (s), \ + .size = ((e) - (s) + 1), \ + .gpio_base = (g), \ + } + +#define SPTH_COMMUNITY(b, s, e, g) \ + { \ + .barno = (b), \ + .padown_offset = SPT_PAD_OWN, \ + .padcfglock_offset = SPT_PADCFGLOCK, \ + .hostown_offset = SPT_HOSTSW_OWN, \ + .ie_offset = SPT_GPI_IE, \ + .pin_base = (s), \ + .npins = ((e) - (s) + 1), \ + .gpps = (g), \ + .ngpps = ARRAY_SIZE(g), \ + } + /* Sunrisepoint-LP */ static const struct pinctrl_pin_desc sptlp_pins[] = { /* GPP_A */ @@ -531,10 +552,28 @@ static const struct intel_function spth_functions[] = { FUNCTION("i2c2", spth_i2c2_groups), }; +static const struct intel_padgroup spth_community0_gpps[] = { + SPTH_GPP(0, 0, 23, 0), /* GPP_A */ + SPTH_GPP(1, 24, 47, 24), /* GPP_B */ +}; + +static const struct intel_padgroup spth_community1_gpps[] = { + SPTH_GPP(0, 48, 71, 48), /* GPP_C */ + SPTH_GPP(1, 72, 95, 72), /* GPP_D */ + SPTH_GPP(2, 96, 108, 96), /* GPP_E */ + SPTH_GPP(3, 109, 132, 120), /* GPP_F */ + SPTH_GPP(4, 133, 156, 144), /* GPP_G */ + SPTH_GPP(5, 157, 180, 168), /* GPP_H */ +}; + +static const struct intel_padgroup spth_community3_gpps[] = { + SPTH_GPP(0, 181, 191, 192), /* GPP_I */ +}; + static const struct intel_community spth_communities[] = { - SPT_COMMUNITY(0, 0, 47), - SPT_COMMUNITY(1, 48, 180), - SPT_COMMUNITY(2, 181, 191), + SPTH_COMMUNITY(0, 0, 47, spth_community0_gpps), + SPTH_COMMUNITY(1, 48, 180, spth_community1_gpps), + SPTH_COMMUNITY(2, 181, 191, spth_community3_gpps), }; static const struct intel_pinctrl_soc_data spth_soc_data = { diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c index 4b91ff74779b..99a6ceac8e53 100644 --- a/drivers/pinctrl/meson/pinctrl-meson-axg.c +++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c @@ -898,7 +898,7 @@ static struct meson_bank meson_axg_periphs_banks[] = { static struct meson_bank meson_axg_aobus_banks[] = { /* name first last irq pullen pull dir out in */ - BANK("AO", GPIOAO_0, GPIOAO_9, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0), + BANK("AO", GPIOAO_0, GPIOAO_13, 0, 13, 0, 16, 0, 0, 0, 0, 0, 16, 1, 0), }; static struct meson_pmx_bank meson_axg_periphs_pmx_banks[] = { diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index bc309c5327ff..566644bb496a 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -168,8 +168,8 @@ config DELL_WMI depends on DMI depends on INPUT depends on ACPI_VIDEO || ACPI_VIDEO = n + depends on DELL_SMBIOS select DELL_WMI_DESCRIPTOR - select DELL_SMBIOS select INPUT_SPARSEKMAP ---help--- Say Y here if you want to support WMI-based hotkeys on Dell laptops. diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c index 439991d71b14..4c14ce428e92 100644 --- a/drivers/s390/cio/qdio_setup.c +++ b/drivers/s390/cio/qdio_setup.c @@ -141,7 +141,7 @@ static int __qdio_allocate_qs(struct qdio_q **irq_ptr_qs, int nr_queues) int i; for (i = 0; i < nr_queues; i++) { - q = kmem_cache_alloc(qdio_q_cache, GFP_KERNEL); + q = kmem_cache_zalloc(qdio_q_cache, GFP_KERNEL); if (!q) return -ENOMEM; @@ -456,7 +456,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data) { struct ciw *ciw; struct qdio_irq *irq_ptr = init_data->cdev->private->qdio_data; - int rc; memset(&irq_ptr->qib, 0, sizeof(irq_ptr->qib)); memset(&irq_ptr->siga_flag, 0, sizeof(irq_ptr->siga_flag)); @@ -493,16 +492,14 @@ int qdio_setup_irq(struct qdio_initialize *init_data) ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_EQUEUE); if (!ciw) { DBF_ERROR("%4x NO EQ", irq_ptr->schid.sch_no); - rc = -EINVAL; - goto out_err; + return -EINVAL; } irq_ptr->equeue = *ciw; ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_AQUEUE); if (!ciw) { DBF_ERROR("%4x NO AQ", irq_ptr->schid.sch_no); - rc = -EINVAL; - goto out_err; + return -EINVAL; } irq_ptr->aqueue = *ciw; @@ -512,9 +509,6 @@ int qdio_setup_irq(struct qdio_initialize *init_data) init_data->cdev->handler = qdio_int_handler; spin_unlock_irq(get_ccwdev_lock(irq_ptr->cdev)); return 0; -out_err: - qdio_release_memory(irq_ptr); - return rc; } void qdio_print_subchannel_info(struct qdio_irq *irq_ptr, diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index 2c7550797ec2..dce92b2a895d 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -715,6 +715,10 @@ void cp_free(struct channel_program *cp) * and stores the result to ccwchain list. @cp must have been * initialized by a previous call with cp_init(). Otherwise, undefined * behavior occurs. + * For each chain composing the channel program: + * - On entry ch_len holds the count of CCWs to be translated. + * - On exit ch_len is adjusted to the count of successfully translated CCWs. + * This allows cp_free to find in ch_len the count of CCWs to free in a chain. * * The S/390 CCW Translation APIS (prefixed by 'cp_') are introduced * as helpers to do ccw chain translation inside the kernel. Basically @@ -749,11 +753,18 @@ int cp_prefetch(struct channel_program *cp) for (idx = 0; idx < len; idx++) { ret = ccwchain_fetch_one(chain, idx, cp); if (ret) - return ret; + goto out_err; } } return 0; +out_err: + /* Only cleanup the chain elements that were actually translated. */ + chain->ch_len = idx; + list_for_each_entry_continue(chain, &cp->ccwchain_list, next) { + chain->ch_len = 0; + } + return ret; } /** diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index 0156c9623c35..d62ddd63f4fe 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -724,6 +724,8 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, int wait; unsigned long flags = 0; unsigned long mflags = 0; + struct aac_hba_cmd_req *hbacmd = (struct aac_hba_cmd_req *) + fibptr->hw_fib_va; fibptr->flags = (FIB_CONTEXT_FLAG | FIB_CONTEXT_FLAG_NATIVE_HBA); if (callback) { @@ -734,11 +736,9 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, wait = 1; - if (command == HBA_IU_TYPE_SCSI_CMD_REQ) { - struct aac_hba_cmd_req *hbacmd = - (struct aac_hba_cmd_req *)fibptr->hw_fib_va; + hbacmd->iu_type = command; - hbacmd->iu_type = command; + if (command == HBA_IU_TYPE_SCSI_CMD_REQ) { /* bit1 of request_id must be 0 */ hbacmd->request_id = cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1); diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index c374e3b5c678..777e5f1e52d1 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -609,7 +609,7 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter, break; case BTSTAT_ABORTQUEUE: - cmd->result = (DID_ABORT << 16); + cmd->result = (DID_BUS_BUSY << 16); break; case BTSTAT_SCSIPARITY: diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 1596d35498c5..6573152ce893 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -490,7 +490,7 @@ static int bcm_qspi_bspi_set_mode(struct bcm_qspi *qspi, static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi) { - if (!has_bspi(qspi) || (qspi->bspi_enabled)) + if (!has_bspi(qspi)) return; qspi->bspi_enabled = 1; @@ -505,7 +505,7 @@ static void bcm_qspi_enable_bspi(struct bcm_qspi *qspi) static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi) { - if (!has_bspi(qspi) || (!qspi->bspi_enabled)) + if (!has_bspi(qspi)) return; qspi->bspi_enabled = 0; @@ -519,16 +519,19 @@ static void bcm_qspi_disable_bspi(struct bcm_qspi *qspi) static void bcm_qspi_chip_select(struct bcm_qspi *qspi, int cs) { - u32 data = 0; + u32 rd = 0; + u32 wr = 0; - if (qspi->curr_cs == cs) - return; if (qspi->base[CHIP_SELECT]) { - data = bcm_qspi_read(qspi, CHIP_SELECT, 0); - data = (data & ~0xff) | (1 << cs); - bcm_qspi_write(qspi, CHIP_SELECT, 0, data); + rd = bcm_qspi_read(qspi, CHIP_SELECT, 0); + wr = (rd & ~0xff) | (1 << cs); + if (rd == wr) + return; + bcm_qspi_write(qspi, CHIP_SELECT, 0, wr); usleep_range(10, 20); } + + dev_dbg(&qspi->pdev->dev, "using cs:%d\n", cs); qspi->curr_cs = cs; } @@ -755,8 +758,13 @@ static int write_to_hw(struct bcm_qspi *qspi, struct spi_device *spi) dev_dbg(&qspi->pdev->dev, "WR %04x\n", val); } mspi_cdram = MSPI_CDRAM_CONT_BIT; - mspi_cdram |= (~(1 << spi->chip_select) & - MSPI_CDRAM_PCS); + + if (has_bspi(qspi)) + mspi_cdram &= ~1; + else + mspi_cdram |= (~(1 << spi->chip_select) & + MSPI_CDRAM_PCS); + mspi_cdram |= ((tp.trans->bits_per_word <= 8) ? 0 : MSPI_CDRAM_BITSE_BIT); diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c index 1431cb98fe40..3094d818cf06 100644 --- a/drivers/spi/spi-bcm2835aux.c +++ b/drivers/spi/spi-bcm2835aux.c @@ -184,6 +184,11 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id) struct bcm2835aux_spi *bs = spi_master_get_devdata(master); irqreturn_t ret = IRQ_NONE; + /* IRQ may be shared, so return if our interrupts are disabled */ + if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) & + (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE))) + return ret; + /* check if we have data to read */ while (bs->rx_len && (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) & diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c index 5c9516ae4942..4a001634023e 100644 --- a/drivers/spi/spi-cadence.c +++ b/drivers/spi/spi-cadence.c @@ -313,6 +313,14 @@ static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi) while ((trans_cnt < CDNS_SPI_FIFO_DEPTH) && (xspi->tx_bytes > 0)) { + + /* When xspi in busy condition, bytes may send failed, + * then spi control did't work thoroughly, add one byte delay + */ + if (cdns_spi_read(xspi, CDNS_SPI_ISR) & + CDNS_SPI_IXR_TXFULL) + usleep_range(10, 20); + if (xspi->txbuf) cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++); else diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 6f57592a7f95..a056ee88a960 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -1701,7 +1701,7 @@ static struct platform_driver spi_imx_driver = { }; module_platform_driver(spi_imx_driver); -MODULE_DESCRIPTION("SPI Master Controller driver"); +MODULE_DESCRIPTION("SPI Controller driver"); MODULE_AUTHOR("Sascha Hauer, Pengutronix"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:" DRIVER_NAME); diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h index 513ec6c6e25b..0ae7defd3492 100644 --- a/drivers/spi/spi-pxa2xx.h +++ b/drivers/spi/spi-pxa2xx.h @@ -38,7 +38,7 @@ struct driver_data { /* SSP register addresses */ void __iomem *ioaddr; - u32 ssdr_physical; + phys_addr_t ssdr_physical; /* SSP masks*/ u32 dma_cr1; diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c index ae086aab57d5..8171eedbfc90 100644 --- a/drivers/spi/spi-sh-msiof.c +++ b/drivers/spi/spi-sh-msiof.c @@ -283,6 +283,7 @@ static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p, } k = min_t(int, k, ARRAY_SIZE(sh_msiof_spi_div_table) - 1); + brps = min_t(int, brps, 32); scr = sh_msiof_spi_div_table[k].brdv | SCR_BRPS(brps); sh_msiof_write(p, TSCR, scr); diff --git a/drivers/thermal/int340x_thermal/int3403_thermal.c b/drivers/thermal/int340x_thermal/int3403_thermal.c index 8a7f24dd9315..0c19fcd56a0d 100644 --- a/drivers/thermal/int340x_thermal/int3403_thermal.c +++ b/drivers/thermal/int340x_thermal/int3403_thermal.c @@ -194,6 +194,7 @@ static int int3403_cdev_add(struct int3403_priv *priv) return -EFAULT; } + priv->priv = obj; obj->max_state = p->package.count - 1; obj->cdev = thermal_cooling_device_register(acpi_device_bid(priv->adev), @@ -201,8 +202,6 @@ static int int3403_cdev_add(struct int3403_priv *priv) if (IS_ERR(obj->cdev)) result = PTR_ERR(obj->cdev); - priv->priv = obj; - kfree(buf.pointer); /* TODO: add ACPI notification support */ diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c index ed805c7c5ace..ac83f721db24 100644 --- a/drivers/thermal/samsung/exynos_tmu.c +++ b/drivers/thermal/samsung/exynos_tmu.c @@ -185,6 +185,7 @@ * @regulator: pointer to the TMU regulator structure. * @reg_conf: pointer to structure to register with core thermal. * @ntrip: number of supported trip points. + * @enabled: current status of TMU device * @tmu_initialize: SoC specific TMU initialization method * @tmu_control: SoC specific TMU control method * @tmu_read: SoC specific TMU temperature read method @@ -205,6 +206,7 @@ struct exynos_tmu_data { struct regulator *regulator; struct thermal_zone_device *tzd; unsigned int ntrip; + bool enabled; int (*tmu_initialize)(struct platform_device *pdev); void (*tmu_control)(struct platform_device *pdev, bool on); @@ -398,6 +400,7 @@ static void exynos_tmu_control(struct platform_device *pdev, bool on) mutex_lock(&data->lock); clk_enable(data->clk); data->tmu_control(pdev, on); + data->enabled = on; clk_disable(data->clk); mutex_unlock(&data->lock); } @@ -889,19 +892,24 @@ static void exynos7_tmu_control(struct platform_device *pdev, bool on) static int exynos_get_temp(void *p, int *temp) { struct exynos_tmu_data *data = p; + int value, ret = 0; - if (!data || !data->tmu_read) + if (!data || !data->tmu_read || !data->enabled) return -EINVAL; mutex_lock(&data->lock); clk_enable(data->clk); - *temp = code_to_temp(data, data->tmu_read(data)) * MCELSIUS; + value = data->tmu_read(data); + if (value < 0) + ret = value; + else + *temp = code_to_temp(data, value) * MCELSIUS; clk_disable(data->clk); mutex_unlock(&data->lock); - return 0; + return ret; } #ifdef CONFIG_THERMAL_EMULATION diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 72ebbc908e19..32cd52ca8318 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -354,7 +354,7 @@ int xhci_find_slot_id_by_port(struct usb_hcd *hcd, struct xhci_hcd *xhci, slot_id = 0; for (i = 0; i < MAX_HC_SLOTS; i++) { - if (!xhci->devs[i]) + if (!xhci->devs[i] || !xhci->devs[i]->udev) continue; speed = xhci->devs[i]->udev->speed; if (((speed >= USB_SPEED_SUPER) == (hcd->speed >= HCD_USB3)) diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index e7f99d55922a..15a42cee0a9c 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2524,8 +2524,11 @@ static int musb_bus_suspend(struct usb_hcd *hcd) { struct musb *musb = hcd_to_musb(hcd); u8 devctl; + int ret; - musb_port_suspend(musb, true); + ret = musb_port_suspend(musb, true); + if (ret) + return ret; if (!is_host_active(musb)) return 0; diff --git a/drivers/usb/musb/musb_host.h b/drivers/usb/musb/musb_host.h index 72392bbcd0a4..2999845632ce 100644 --- a/drivers/usb/musb/musb_host.h +++ b/drivers/usb/musb/musb_host.h @@ -67,7 +67,7 @@ extern void musb_host_rx(struct musb *, u8); extern void musb_root_disconnect(struct musb *musb); extern void musb_host_resume_root_hub(struct musb *musb); extern void musb_host_poke_root_hub(struct musb *musb); -extern void musb_port_suspend(struct musb *musb, bool do_suspend); +extern int musb_port_suspend(struct musb *musb, bool do_suspend); extern void musb_port_reset(struct musb *musb, bool do_reset); extern void musb_host_finish_resume(struct work_struct *work); #else @@ -99,7 +99,10 @@ static inline void musb_root_disconnect(struct musb *musb) {} static inline void musb_host_resume_root_hub(struct musb *musb) {} static inline void musb_host_poll_rh_status(struct musb *musb) {} static inline void musb_host_poke_root_hub(struct musb *musb) {} -static inline void musb_port_suspend(struct musb *musb, bool do_suspend) {} +static inline int musb_port_suspend(struct musb *musb, bool do_suspend) +{ + return 0; +} static inline void musb_port_reset(struct musb *musb, bool do_reset) {} static inline void musb_host_finish_resume(struct work_struct *work) {} #endif diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c index 5165d2b07ade..2f8dd9826e94 100644 --- a/drivers/usb/musb/musb_virthub.c +++ b/drivers/usb/musb/musb_virthub.c @@ -48,14 +48,14 @@ void musb_host_finish_resume(struct work_struct *work) spin_unlock_irqrestore(&musb->lock, flags); } -void musb_port_suspend(struct musb *musb, bool do_suspend) +int musb_port_suspend(struct musb *musb, bool do_suspend) { struct usb_otg *otg = musb->xceiv->otg; u8 power; void __iomem *mbase = musb->mregs; if (!is_host_active(musb)) - return; + return 0; /* NOTE: this doesn't necessarily put PHY into low power mode, * turning off its clock; that's a function of PHY integration and @@ -66,16 +66,20 @@ void musb_port_suspend(struct musb *musb, bool do_suspend) if (do_suspend) { int retries = 10000; - power &= ~MUSB_POWER_RESUME; - power |= MUSB_POWER_SUSPENDM; - musb_writeb(mbase, MUSB_POWER, power); + if (power & MUSB_POWER_RESUME) + return -EBUSY; - /* Needed for OPT A tests */ - power = musb_readb(mbase, MUSB_POWER); - while (power & MUSB_POWER_SUSPENDM) { + if (!(power & MUSB_POWER_SUSPENDM)) { + power |= MUSB_POWER_SUSPENDM; + musb_writeb(mbase, MUSB_POWER, power); + + /* Needed for OPT A tests */ power = musb_readb(mbase, MUSB_POWER); - if (retries-- < 1) - break; + while (power & MUSB_POWER_SUSPENDM) { + power = musb_readb(mbase, MUSB_POWER); + if (retries-- < 1) + break; + } } musb_dbg(musb, "Root port suspended, power %02x", power); @@ -111,6 +115,7 @@ void musb_port_suspend(struct musb *musb, bool do_suspend) schedule_delayed_work(&musb->finish_resume_work, msecs_to_jiffies(USB_RESUME_TIMEOUT)); } + return 0; } void musb_port_reset(struct musb *musb, bool do_reset) diff --git a/drivers/usb/usbip/stub.h b/drivers/usb/usbip/stub.h index 14a72357800a..35618ceb2791 100644 --- a/drivers/usb/usbip/stub.h +++ b/drivers/usb/usbip/stub.h @@ -73,6 +73,7 @@ struct bus_id_priv { struct stub_device *sdev; struct usb_device *udev; char shutdown_busid; + spinlock_t busid_lock; }; /* stub_priv is allocated from stub_priv_cache */ @@ -83,6 +84,7 @@ extern struct usb_device_driver stub_driver; /* stub_main.c */ struct bus_id_priv *get_busid_priv(const char *busid); +void put_busid_priv(struct bus_id_priv *bid); int del_match_busid(char *busid); void stub_device_cleanup_urbs(struct stub_device *sdev); diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index dd8ef36ab10e..c0d6ff1baa72 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -300,9 +300,9 @@ static int stub_probe(struct usb_device *udev) struct stub_device *sdev = NULL; const char *udev_busid = dev_name(&udev->dev); struct bus_id_priv *busid_priv; - int rc; + int rc = 0; - dev_dbg(&udev->dev, "Enter\n"); + dev_dbg(&udev->dev, "Enter probe\n"); /* check we should claim or not by busid_table */ busid_priv = get_busid_priv(udev_busid); @@ -317,13 +317,15 @@ static int stub_probe(struct usb_device *udev) * other matched drivers by the driver core. * See driver_probe_device() in driver/base/dd.c */ - return -ENODEV; + rc = -ENODEV; + goto call_put_busid_priv; } if (udev->descriptor.bDeviceClass == USB_CLASS_HUB) { dev_dbg(&udev->dev, "%s is a usb hub device... skip!\n", udev_busid); - return -ENODEV; + rc = -ENODEV; + goto call_put_busid_priv; } if (!strcmp(udev->bus->bus_name, "vhci_hcd")) { @@ -331,13 +333,16 @@ static int stub_probe(struct usb_device *udev) "%s is attached on vhci_hcd... skip!\n", udev_busid); - return -ENODEV; + rc = -ENODEV; + goto call_put_busid_priv; } /* ok, this is my device */ sdev = stub_device_alloc(udev); - if (!sdev) - return -ENOMEM; + if (!sdev) { + rc = -ENOMEM; + goto call_put_busid_priv; + } dev_info(&udev->dev, "usbip-host: register new device (bus %u dev %u)\n", @@ -369,7 +374,9 @@ static int stub_probe(struct usb_device *udev) } busid_priv->status = STUB_BUSID_ALLOC; - return 0; + rc = 0; + goto call_put_busid_priv; + err_files: usb_hub_release_port(udev->parent, udev->portnum, (struct usb_dev_state *) udev); @@ -379,6 +386,9 @@ err_port: busid_priv->sdev = NULL; stub_device_free(sdev); + +call_put_busid_priv: + put_busid_priv(busid_priv); return rc; } @@ -404,7 +414,7 @@ static void stub_disconnect(struct usb_device *udev) struct bus_id_priv *busid_priv; int rc; - dev_dbg(&udev->dev, "Enter\n"); + dev_dbg(&udev->dev, "Enter disconnect\n"); busid_priv = get_busid_priv(udev_busid); if (!busid_priv) { @@ -417,7 +427,7 @@ static void stub_disconnect(struct usb_device *udev) /* get stub_device */ if (!sdev) { dev_err(&udev->dev, "could not get device"); - return; + goto call_put_busid_priv; } dev_set_drvdata(&udev->dev, NULL); @@ -432,12 +442,12 @@ static void stub_disconnect(struct usb_device *udev) (struct usb_dev_state *) udev); if (rc) { dev_dbg(&udev->dev, "unable to release port\n"); - return; + goto call_put_busid_priv; } /* If usb reset is called from event handler */ if (usbip_in_eh(current)) - return; + goto call_put_busid_priv; /* shutdown the current connection */ shutdown_busid(busid_priv); @@ -448,12 +458,11 @@ static void stub_disconnect(struct usb_device *udev) busid_priv->sdev = NULL; stub_device_free(sdev); - if (busid_priv->status == STUB_BUSID_ALLOC) { + if (busid_priv->status == STUB_BUSID_ALLOC) busid_priv->status = STUB_BUSID_ADDED; - } else { - busid_priv->status = STUB_BUSID_OTHER; - del_match_busid((char *)udev_busid); - } + +call_put_busid_priv: + put_busid_priv(busid_priv); } #ifdef CONFIG_PM diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c index d41d0cdeec0f..bf8a5feb0ee9 100644 --- a/drivers/usb/usbip/stub_main.c +++ b/drivers/usb/usbip/stub_main.c @@ -14,6 +14,7 @@ #define DRIVER_DESC "USB/IP Host Driver" struct kmem_cache *stub_priv_cache; + /* * busid_tables defines matching busids that usbip can grab. A user can change * dynamically what device is locally used and what device is exported to a @@ -25,6 +26,8 @@ static spinlock_t busid_table_lock; static void init_busid_table(void) { + int i; + /* * This also sets the bus_table[i].status to * STUB_BUSID_OTHER, which is 0. @@ -32,6 +35,9 @@ static void init_busid_table(void) memset(busid_table, 0, sizeof(busid_table)); spin_lock_init(&busid_table_lock); + + for (i = 0; i < MAX_BUSID; i++) + spin_lock_init(&busid_table[i].busid_lock); } /* @@ -43,15 +49,20 @@ static int get_busid_idx(const char *busid) int i; int idx = -1; - for (i = 0; i < MAX_BUSID; i++) + for (i = 0; i < MAX_BUSID; i++) { + spin_lock(&busid_table[i].busid_lock); if (busid_table[i].name[0]) if (!strncmp(busid_table[i].name, busid, BUSID_SIZE)) { idx = i; + spin_unlock(&busid_table[i].busid_lock); break; } + spin_unlock(&busid_table[i].busid_lock); + } return idx; } +/* Returns holding busid_lock. Should call put_busid_priv() to unlock */ struct bus_id_priv *get_busid_priv(const char *busid) { int idx; @@ -59,13 +70,22 @@ struct bus_id_priv *get_busid_priv(const char *busid) spin_lock(&busid_table_lock); idx = get_busid_idx(busid); - if (idx >= 0) + if (idx >= 0) { bid = &(busid_table[idx]); + /* get busid_lock before returning */ + spin_lock(&bid->busid_lock); + } spin_unlock(&busid_table_lock); return bid; } +void put_busid_priv(struct bus_id_priv *bid) +{ + if (bid) + spin_unlock(&bid->busid_lock); +} + static int add_match_busid(char *busid) { int i; @@ -78,15 +98,19 @@ static int add_match_busid(char *busid) goto out; } - for (i = 0; i < MAX_BUSID; i++) + for (i = 0; i < MAX_BUSID; i++) { + spin_lock(&busid_table[i].busid_lock); if (!busid_table[i].name[0]) { strlcpy(busid_table[i].name, busid, BUSID_SIZE); if ((busid_table[i].status != STUB_BUSID_ALLOC) && (busid_table[i].status != STUB_BUSID_REMOV)) busid_table[i].status = STUB_BUSID_ADDED; ret = 0; + spin_unlock(&busid_table[i].busid_lock); break; } + spin_unlock(&busid_table[i].busid_lock); + } out: spin_unlock(&busid_table_lock); @@ -107,6 +131,8 @@ int del_match_busid(char *busid) /* found */ ret = 0; + spin_lock(&busid_table[idx].busid_lock); + if (busid_table[idx].status == STUB_BUSID_OTHER) memset(busid_table[idx].name, 0, BUSID_SIZE); @@ -114,6 +140,7 @@ int del_match_busid(char *busid) (busid_table[idx].status != STUB_BUSID_ADDED)) busid_table[idx].status = STUB_BUSID_REMOV; + spin_unlock(&busid_table[idx].busid_lock); out: spin_unlock(&busid_table_lock); @@ -126,9 +153,12 @@ static ssize_t match_busid_show(struct device_driver *drv, char *buf) char *out = buf; spin_lock(&busid_table_lock); - for (i = 0; i < MAX_BUSID; i++) + for (i = 0; i < MAX_BUSID; i++) { + spin_lock(&busid_table[i].busid_lock); if (busid_table[i].name[0]) out += sprintf(out, "%s ", busid_table[i].name); + spin_unlock(&busid_table[i].busid_lock); + } spin_unlock(&busid_table_lock); out += sprintf(out, "\n"); @@ -169,6 +199,51 @@ static ssize_t match_busid_store(struct device_driver *dev, const char *buf, } static DRIVER_ATTR_RW(match_busid); +static int do_rebind(char *busid, struct bus_id_priv *busid_priv) +{ + int ret; + + /* device_attach() callers should hold parent lock for USB */ + if (busid_priv->udev->dev.parent) + device_lock(busid_priv->udev->dev.parent); + ret = device_attach(&busid_priv->udev->dev); + if (busid_priv->udev->dev.parent) + device_unlock(busid_priv->udev->dev.parent); + if (ret < 0) { + dev_err(&busid_priv->udev->dev, "rebind failed\n"); + return ret; + } + return 0; +} + +static void stub_device_rebind(void) +{ +#if IS_MODULE(CONFIG_USBIP_HOST) + struct bus_id_priv *busid_priv; + int i; + + /* update status to STUB_BUSID_OTHER so probe ignores the device */ + spin_lock(&busid_table_lock); + for (i = 0; i < MAX_BUSID; i++) { + if (busid_table[i].name[0] && + busid_table[i].shutdown_busid) { + busid_priv = &(busid_table[i]); + busid_priv->status = STUB_BUSID_OTHER; + } + } + spin_unlock(&busid_table_lock); + + /* now run rebind - no need to hold locks. driver files are removed */ + for (i = 0; i < MAX_BUSID; i++) { + if (busid_table[i].name[0] && + busid_table[i].shutdown_busid) { + busid_priv = &(busid_table[i]); + do_rebind(busid_table[i].name, busid_priv); + } + } +#endif +} + static ssize_t rebind_store(struct device_driver *dev, const char *buf, size_t count) { @@ -186,16 +261,17 @@ static ssize_t rebind_store(struct device_driver *dev, const char *buf, if (!bid) return -ENODEV; - /* device_attach() callers should hold parent lock for USB */ - if (bid->udev->dev.parent) - device_lock(bid->udev->dev.parent); - ret = device_attach(&bid->udev->dev); - if (bid->udev->dev.parent) - device_unlock(bid->udev->dev.parent); - if (ret < 0) { - dev_err(&bid->udev->dev, "rebind failed\n"); + /* mark the device for deletion so probe ignores it during rescan */ + bid->status = STUB_BUSID_OTHER; + /* release the busid lock */ + put_busid_priv(bid); + + ret = do_rebind((char *) buf, bid); + if (ret < 0) return ret; - } + + /* delete device from busid_table */ + del_match_busid((char *) buf); return count; } @@ -317,6 +393,9 @@ static void __exit usbip_host_exit(void) */ usb_deregister_device_driver(&stub_driver); + /* initiate scan to attach devices */ + stub_device_rebind(); + kmem_cache_destroy(stub_priv_cache); } diff --git a/fs/afs/addr_list.c b/fs/afs/addr_list.c index 3bedfed608a2..7587fb665ff1 100644 --- a/fs/afs/addr_list.c +++ b/fs/afs/addr_list.c @@ -121,7 +121,7 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, p = text; do { struct sockaddr_rxrpc *srx = &alist->addrs[alist->nr_addrs]; - char tdelim = delim; + const char *q, *stop; if (*p == delim) { p++; @@ -130,28 +130,33 @@ struct afs_addr_list *afs_parse_text_addrs(const char *text, size_t len, if (*p == '[') { p++; - tdelim = ']'; + q = memchr(p, ']', end - p); + } else { + for (q = p; q < end; q++) + if (*q == '+' || *q == delim) + break; } - if (in4_pton(p, end - p, + if (in4_pton(p, q - p, (u8 *)&srx->transport.sin6.sin6_addr.s6_addr32[3], - tdelim, &p)) { + -1, &stop)) { srx->transport.sin6.sin6_addr.s6_addr32[0] = 0; srx->transport.sin6.sin6_addr.s6_addr32[1] = 0; srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); - } else if (in6_pton(p, end - p, + } else if (in6_pton(p, q - p, srx->transport.sin6.sin6_addr.s6_addr, - tdelim, &p)) { + -1, &stop)) { /* Nothing to do */ } else { goto bad_address; } - if (tdelim == ']') { - if (p == end || *p != ']') - goto bad_address; + if (stop != q) + goto bad_address; + + p = q; + if (q < end && *q == ']') p++; - } if (p < end) { if (*p == '+') { diff --git a/fs/afs/callback.c b/fs/afs/callback.c index abd9a84f4e88..571437dcb252 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -23,36 +23,55 @@ /* * Set up an interest-in-callbacks record for a volume on a server and * register it with the server. - * - Called with volume->server_sem held. + * - Called with vnode->io_lock held. */ int afs_register_server_cb_interest(struct afs_vnode *vnode, - struct afs_server_entry *entry) + struct afs_server_list *slist, + unsigned int index) { - struct afs_cb_interest *cbi = entry->cb_interest, *vcbi, *new, *x; + struct afs_server_entry *entry = &slist->servers[index]; + struct afs_cb_interest *cbi, *vcbi, *new, *old; struct afs_server *server = entry->server; again: + if (vnode->cb_interest && + likely(vnode->cb_interest == entry->cb_interest)) + return 0; + + read_lock(&slist->lock); + cbi = afs_get_cb_interest(entry->cb_interest); + read_unlock(&slist->lock); + vcbi = vnode->cb_interest; if (vcbi) { - if (vcbi == cbi) + if (vcbi == cbi) { + afs_put_cb_interest(afs_v2net(vnode), cbi); return 0; + } + /* Use a new interest in the server list for the same server + * rather than an old one that's still attached to a vnode. + */ if (cbi && vcbi->server == cbi->server) { write_seqlock(&vnode->cb_lock); - vnode->cb_interest = afs_get_cb_interest(cbi); + old = vnode->cb_interest; + vnode->cb_interest = cbi; write_sequnlock(&vnode->cb_lock); - afs_put_cb_interest(afs_v2net(vnode), cbi); + afs_put_cb_interest(afs_v2net(vnode), old); return 0; } + /* Re-use the one attached to the vnode. */ if (!cbi && vcbi->server == server) { - afs_get_cb_interest(vcbi); - x = cmpxchg(&entry->cb_interest, cbi, vcbi); - if (x != cbi) { - cbi = x; - afs_put_cb_interest(afs_v2net(vnode), vcbi); + write_lock(&slist->lock); + if (entry->cb_interest) { + write_unlock(&slist->lock); + afs_put_cb_interest(afs_v2net(vnode), cbi); goto again; } + + entry->cb_interest = cbi; + write_unlock(&slist->lock); return 0; } } @@ -72,13 +91,16 @@ again: list_add_tail(&new->cb_link, &server->cb_interests); write_unlock(&server->cb_break_lock); - x = cmpxchg(&entry->cb_interest, cbi, new); - if (x == cbi) { + write_lock(&slist->lock); + if (!entry->cb_interest) { + entry->cb_interest = afs_get_cb_interest(new); cbi = new; + new = NULL; } else { - cbi = x; - afs_put_cb_interest(afs_v2net(vnode), new); + cbi = afs_get_cb_interest(entry->cb_interest); } + write_unlock(&slist->lock); + afs_put_cb_interest(afs_v2net(vnode), new); } ASSERT(cbi); @@ -88,11 +110,14 @@ again: */ write_seqlock(&vnode->cb_lock); - vnode->cb_interest = afs_get_cb_interest(cbi); + old = vnode->cb_interest; + vnode->cb_interest = cbi; vnode->cb_s_break = cbi->server->cb_s_break; + vnode->cb_v_break = vnode->volume->cb_v_break; clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags); write_sequnlock(&vnode->cb_lock); + afs_put_cb_interest(afs_v2net(vnode), old); return 0; } @@ -171,13 +196,24 @@ static void afs_break_one_callback(struct afs_server *server, if (cbi->vid != fid->vid) continue; - data.volume = NULL; - data.fid = *fid; - inode = ilookup5_nowait(cbi->sb, fid->vnode, afs_iget5_test, &data); - if (inode) { - vnode = AFS_FS_I(inode); - afs_break_callback(vnode); - iput(inode); + if (fid->vnode == 0 && fid->unique == 0) { + /* The callback break applies to an entire volume. */ + struct afs_super_info *as = AFS_FS_S(cbi->sb); + struct afs_volume *volume = as->volume; + + write_lock(&volume->cb_break_lock); + volume->cb_v_break++; + write_unlock(&volume->cb_break_lock); + } else { + data.volume = NULL; + data.fid = *fid; + inode = ilookup5_nowait(cbi->sb, fid->vnode, + afs_iget5_test, &data); + if (inode) { + vnode = AFS_FS_I(inode); + afs_break_callback(vnode); + iput(inode); + } } } @@ -195,6 +231,8 @@ void afs_break_callbacks(struct afs_server *server, size_t count, ASSERT(server != NULL); ASSERTCMP(count, <=, AFSCBMAX); + /* TODO: Sort the callback break list by volume ID */ + for (; count > 0; callbacks++, count--) { _debug("- Fid { vl=%08x n=%u u=%u } CB { v=%u x=%u t=%u }", callbacks->fid.vid, diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 357de908df3a..c332c95a6940 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -133,21 +133,10 @@ bool afs_cm_incoming_call(struct afs_call *call) } /* - * clean up a cache manager call + * Clean up a cache manager call. */ static void afs_cm_destructor(struct afs_call *call) { - _enter(""); - - /* Break the callbacks here so that we do it after the final ACK is - * received. The step number here must match the final number in - * afs_deliver_cb_callback(). - */ - if (call->unmarshall == 5) { - ASSERT(call->cm_server && call->count && call->request); - afs_break_callbacks(call->cm_server, call->count, call->request); - } - kfree(call->buffer); call->buffer = NULL; } @@ -161,14 +150,14 @@ static void SRXAFSCB_CallBack(struct work_struct *work) _enter(""); - /* be sure to send the reply *before* attempting to spam the AFS server - * with FSFetchStatus requests on the vnodes with broken callbacks lest - * the AFS server get into a vicious cycle of trying to break further - * callbacks because it hadn't received completion of the CBCallBack op - * yet */ - afs_send_empty_reply(call); + /* We need to break the callbacks before sending the reply as the + * server holds up change visibility till it receives our reply so as + * to maintain cache coherency. + */ + if (call->cm_server) + afs_break_callbacks(call->cm_server, call->count, call->request); - afs_break_callbacks(call->cm_server, call->count, call->request); + afs_send_empty_reply(call); afs_put_call(call); _leave(""); } @@ -180,7 +169,6 @@ static int afs_deliver_cb_callback(struct afs_call *call) { struct afs_callback_break *cb; struct sockaddr_rxrpc srx; - struct afs_server *server; __be32 *bp; int ret, loop; @@ -267,15 +255,6 @@ static int afs_deliver_cb_callback(struct afs_call *call) call->offset = 0; call->unmarshall++; - - /* Record that the message was unmarshalled successfully so - * that the call destructor can know do the callback breaking - * work, even if the final ACK isn't received. - * - * If the step number changes, then afs_cm_destructor() must be - * updated also. - */ - call->unmarshall++; case 5: break; } @@ -286,10 +265,9 @@ static int afs_deliver_cb_callback(struct afs_call *call) /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); - server = afs_find_server(call->net, &srx); - if (!server) - return -ENOTCONN; - call->cm_server = server; + call->cm_server = afs_find_server(call->net, &srx); + if (!call->cm_server) + trace_afs_cm_no_server(call, &srx); return afs_queue_call_work(call); } @@ -303,7 +281,8 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) _enter("{%p}", call->cm_server); - afs_init_callback_state(call->cm_server); + if (call->cm_server) + afs_init_callback_state(call->cm_server); afs_send_empty_reply(call); afs_put_call(call); _leave(""); @@ -315,7 +294,6 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work) static int afs_deliver_cb_init_call_back_state(struct afs_call *call) { struct sockaddr_rxrpc srx; - struct afs_server *server; int ret; _enter(""); @@ -328,10 +306,9 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - server = afs_find_server(call->net, &srx); - if (!server) - return -ENOTCONN; - call->cm_server = server; + call->cm_server = afs_find_server(call->net, &srx); + if (!call->cm_server) + trace_afs_cm_no_server(call, &srx); return afs_queue_call_work(call); } @@ -341,8 +318,6 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call) */ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) { - struct sockaddr_rxrpc srx; - struct afs_server *server; struct afs_uuid *r; unsigned loop; __be32 *b; @@ -398,11 +373,11 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call) /* we'll need the file server record as that tells us which set of * vnodes to operate upon */ - rxrpc_kernel_get_peer(call->net->socket, call->rxcall, &srx); - server = afs_find_server(call->net, &srx); - if (!server) - return -ENOTCONN; - call->cm_server = server; + rcu_read_lock(); + call->cm_server = afs_find_server_by_uuid(call->net, call->request); + rcu_read_unlock(); + if (!call->cm_server) + trace_afs_cm_no_server_u(call, call->request); return afs_queue_call_work(call); } diff --git a/fs/afs/dir.c b/fs/afs/dir.c index 5889f70d4d27..7d623008157f 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -180,6 +180,7 @@ static int afs_dir_open(struct inode *inode, struct file *file) * get reclaimed during the iteration. */ static struct afs_read *afs_read_dir(struct afs_vnode *dvnode, struct key *key) + __acquires(&dvnode->validate_lock) { struct afs_read *req; loff_t i_size; @@ -261,18 +262,21 @@ retry: /* If we're going to reload, we need to lock all the pages to prevent * races. */ - if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { - ret = -ERESTARTSYS; - for (i = 0; i < req->nr_pages; i++) - if (lock_page_killable(req->pages[i]) < 0) - goto error_unlock; + ret = -ERESTARTSYS; + if (down_read_killable(&dvnode->validate_lock) < 0) + goto error; - if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) - goto success; + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) + goto success; + + up_read(&dvnode->validate_lock); + if (down_write_killable(&dvnode->validate_lock) < 0) + goto error; + if (!test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { ret = afs_fetch_data(dvnode, key, req); if (ret < 0) - goto error_unlock_all; + goto error_unlock; task_io_account_read(PAGE_SIZE * req->nr_pages); @@ -284,33 +288,26 @@ retry: for (i = 0; i < req->nr_pages; i++) if (!afs_dir_check_page(dvnode, req->pages[i], req->actual_len)) - goto error_unlock_all; + goto error_unlock; // TODO: Trim excess pages set_bit(AFS_VNODE_DIR_VALID, &dvnode->flags); } + downgrade_write(&dvnode->validate_lock); success: - i = req->nr_pages; - while (i > 0) - unlock_page(req->pages[--i]); return req; -error_unlock_all: - i = req->nr_pages; error_unlock: - while (i > 0) - unlock_page(req->pages[--i]); + up_write(&dvnode->validate_lock); error: afs_put_read(req); _leave(" = %d", ret); return ERR_PTR(ret); content_has_grown: - i = req->nr_pages; - while (i > 0) - unlock_page(req->pages[--i]); + up_write(&dvnode->validate_lock); afs_put_read(req); goto retry; } @@ -473,6 +470,7 @@ static int afs_dir_iterate(struct inode *dir, struct dir_context *ctx, } out: + up_read(&dvnode->validate_lock); afs_put_read(req); _leave(" = %d", ret); return ret; @@ -1143,7 +1141,7 @@ static int afs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = dvnode->cb_break + dvnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(dvnode); afs_fs_create(&fc, dentry->d_name.name, mode, data_version, &newfid, &newstatus, &newcb); } @@ -1213,7 +1211,7 @@ static int afs_rmdir(struct inode *dir, struct dentry *dentry) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = dvnode->cb_break + dvnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(dvnode); afs_fs_remove(&fc, dentry->d_name.name, true, data_version); } @@ -1316,7 +1314,7 @@ static int afs_unlink(struct inode *dir, struct dentry *dentry) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = dvnode->cb_break + dvnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(dvnode); afs_fs_remove(&fc, dentry->d_name.name, false, data_version); } @@ -1373,7 +1371,7 @@ static int afs_create(struct inode *dir, struct dentry *dentry, umode_t mode, ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = dvnode->cb_break + dvnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(dvnode); afs_fs_create(&fc, dentry->d_name.name, mode, data_version, &newfid, &newstatus, &newcb); } @@ -1443,8 +1441,8 @@ static int afs_link(struct dentry *from, struct inode *dir, } while (afs_select_fileserver(&fc)) { - fc.cb_break = dvnode->cb_break + dvnode->cb_s_break; - fc.cb_break_2 = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(dvnode); + fc.cb_break_2 = afs_calc_vnode_cb_break(vnode); afs_fs_link(&fc, vnode, dentry->d_name.name, data_version); } @@ -1512,7 +1510,7 @@ static int afs_symlink(struct inode *dir, struct dentry *dentry, ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, dvnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = dvnode->cb_break + dvnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(dvnode); afs_fs_symlink(&fc, dentry->d_name.name, content, data_version, &newfid, &newstatus); @@ -1588,8 +1586,8 @@ static int afs_rename(struct inode *old_dir, struct dentry *old_dentry, } } while (afs_select_fileserver(&fc)) { - fc.cb_break = orig_dvnode->cb_break + orig_dvnode->cb_s_break; - fc.cb_break_2 = new_dvnode->cb_break + new_dvnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(orig_dvnode); + fc.cb_break_2 = afs_calc_vnode_cb_break(new_dvnode); afs_fs_rename(&fc, old_dentry->d_name.name, new_dvnode, new_dentry->d_name.name, orig_data_version, new_data_version); diff --git a/fs/afs/file.c b/fs/afs/file.c index c24c08016dd9..7d4f26198573 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -238,7 +238,7 @@ int afs_fetch_data(struct afs_vnode *vnode, struct key *key, struct afs_read *de ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, vnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_fetch_data(&fc, desc); } diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 7a0e017070ec..dc62d15a964b 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -86,7 +86,7 @@ static int afs_set_lock(struct afs_vnode *vnode, struct key *key, ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, vnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_set_lock(&fc, type); } @@ -117,7 +117,7 @@ static int afs_extend_lock(struct afs_vnode *vnode, struct key *key) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, vnode, key)) { while (afs_select_current_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_extend_lock(&fc); } @@ -148,7 +148,7 @@ static int afs_release_lock(struct afs_vnode *vnode, struct key *key) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, vnode, key)) { while (afs_select_current_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_release_lock(&fc); } diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index efacdb7c1dee..b273e1d60478 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -134,6 +134,7 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, struct afs_read *read_req) { const struct afs_xdr_AFSFetchStatus *xdr = (const void *)*_bp; + bool inline_error = (call->operation_ID == afs_FS_InlineBulkStatus); u64 data_version, size; u32 type, abort_code; u8 flags = 0; @@ -142,13 +143,32 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, if (vnode) write_seqlock(&vnode->cb_lock); + abort_code = ntohl(xdr->abort_code); + if (xdr->if_version != htonl(AFS_FSTATUS_VERSION)) { + if (xdr->if_version == htonl(0) && + abort_code != 0 && + inline_error) { + /* The OpenAFS fileserver has a bug in FS.InlineBulkStatus + * whereby it doesn't set the interface version in the error + * case. + */ + status->abort_code = abort_code; + ret = 0; + goto out; + } + pr_warn("Unknown AFSFetchStatus version %u\n", ntohl(xdr->if_version)); goto bad; } + if (abort_code != 0 && inline_error) { + status->abort_code = abort_code; + ret = 0; + goto out; + } + type = ntohl(xdr->type); - abort_code = ntohl(xdr->abort_code); switch (type) { case AFS_FTYPE_FILE: case AFS_FTYPE_DIR: @@ -165,13 +185,6 @@ static int xdr_decode_AFSFetchStatus(struct afs_call *call, } status->type = type; break; - case AFS_FTYPE_INVALID: - if (abort_code != 0) { - status->abort_code = abort_code; - ret = 0; - goto out; - } - /* Fall through */ default: goto bad; } @@ -248,7 +261,7 @@ static void xdr_decode_AFSCallBack(struct afs_call *call, write_seqlock(&vnode->cb_lock); - if (call->cb_break == (vnode->cb_break + cbi->server->cb_s_break)) { + if (call->cb_break == afs_cb_break_sum(vnode, cbi)) { vnode->cb_version = ntohl(*bp++); cb_expiry = ntohl(*bp++); vnode->cb_type = ntohl(*bp++); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 06194cfe9724..479b7fdda124 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -108,7 +108,7 @@ int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool new_inode) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, vnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_fetch_file_status(&fc, NULL, new_inode); } @@ -393,15 +393,18 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) read_seqlock_excl(&vnode->cb_lock); if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) { - if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break) { + if (vnode->cb_s_break != vnode->cb_interest->server->cb_s_break || + vnode->cb_v_break != vnode->volume->cb_v_break) { vnode->cb_s_break = vnode->cb_interest->server->cb_s_break; + 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; + valid = true; } else if (!test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) && vnode->cb_expires_at - 10 > now) { - valid = true; + valid = true; } } else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) { valid = true; @@ -415,7 +418,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) if (valid) goto valid; - mutex_lock(&vnode->validate_lock); + down_write(&vnode->validate_lock); /* if the promise has expired, we need to check the server again to get * a new promise - note that if the (parent) directory's metadata was @@ -444,13 +447,13 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) * different */ if (test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) afs_zap_data(vnode); - mutex_unlock(&vnode->validate_lock); + up_write(&vnode->validate_lock); valid: _leave(" = 0"); return 0; error_unlock: - mutex_unlock(&vnode->validate_lock); + up_write(&vnode->validate_lock); _leave(" = %d", ret); return ret; } @@ -574,7 +577,7 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, vnode, key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_setattr(&fc, attr); } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index f8086ec95e24..e3f8a46663db 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -396,6 +396,7 @@ struct afs_server { #define AFS_SERVER_FL_PROBED 5 /* The fileserver has been probed */ #define AFS_SERVER_FL_PROBING 6 /* Fileserver is being probed */ #define AFS_SERVER_FL_NO_IBULK 7 /* Fileserver doesn't support FS.InlineBulkStatus */ +#define AFS_SERVER_FL_MAY_HAVE_CB 8 /* May have callbacks on this fileserver */ atomic_t usage; u32 addr_version; /* Address list version */ @@ -433,6 +434,7 @@ struct afs_server_list { unsigned short index; /* Server currently in use */ unsigned short vnovol_mask; /* Servers to be skipped due to VNOVOL */ unsigned int seq; /* Set to ->servers_seq when installed */ + rwlock_t lock; struct afs_server_entry servers[]; }; @@ -459,6 +461,9 @@ struct afs_volume { rwlock_t servers_lock; /* Lock for ->servers */ unsigned int servers_seq; /* Incremented each time ->servers changes */ + unsigned cb_v_break; /* Break-everything counter. */ + rwlock_t cb_break_lock; + afs_voltype_t type; /* type of volume */ short error; char type_force; /* force volume type (suppress R/O -> R/W) */ @@ -494,7 +499,7 @@ struct afs_vnode { #endif struct afs_permits __rcu *permit_cache; /* cache of permits so far obtained */ struct mutex io_lock; /* Lock for serialising I/O on this mutex */ - struct mutex validate_lock; /* lock for validating this vnode */ + struct rw_semaphore validate_lock; /* lock for validating this vnode */ spinlock_t wb_lock; /* lock for wb_keys */ spinlock_t lock; /* waitqueue/flags lock */ unsigned long flags; @@ -519,6 +524,7 @@ struct afs_vnode { /* outstanding callback notification on this file */ struct afs_cb_interest *cb_interest; /* Server on which this resides */ unsigned int cb_s_break; /* Mass break counter on ->server */ + unsigned int cb_v_break; /* Mass break counter on ->volume */ unsigned int cb_break; /* Break counter on vnode */ seqlock_t cb_lock; /* Lock for ->cb_interest, ->status, ->cb_*break */ @@ -648,16 +654,29 @@ extern void afs_init_callback_state(struct afs_server *); extern void afs_break_callback(struct afs_vnode *); extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*); -extern int afs_register_server_cb_interest(struct afs_vnode *, struct afs_server_entry *); +extern int afs_register_server_cb_interest(struct afs_vnode *, + struct afs_server_list *, unsigned int); extern void afs_put_cb_interest(struct afs_net *, struct afs_cb_interest *); extern void afs_clear_callback_interests(struct afs_net *, struct afs_server_list *); static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest *cbi) { - refcount_inc(&cbi->usage); + if (cbi) + refcount_inc(&cbi->usage); return cbi; } +static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode) +{ + return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break; +} + +static inline unsigned int afs_cb_break_sum(struct afs_vnode *vnode, + struct afs_cb_interest *cbi) +{ + return vnode->cb_break + cbi->server->cb_s_break + vnode->volume->cb_v_break; +} + /* * cell.c */ diff --git a/fs/afs/rotate.c b/fs/afs/rotate.c index ac0feac9d746..e065bc0768e6 100644 --- a/fs/afs/rotate.c +++ b/fs/afs/rotate.c @@ -179,7 +179,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) */ if (fc->flags & AFS_FS_CURSOR_VNOVOL) { fc->ac.error = -EREMOTEIO; - goto failed; + goto next_server; } write_lock(&vnode->volume->servers_lock); @@ -201,7 +201,7 @@ bool afs_select_fileserver(struct afs_fs_cursor *fc) */ if (vnode->volume->servers == fc->server_list) { fc->ac.error = -EREMOTEIO; - goto failed; + goto next_server; } /* Try again */ @@ -350,8 +350,8 @@ use_server: * break request before we've finished decoding the reply and * installing the vnode. */ - fc->ac.error = afs_register_server_cb_interest( - vnode, &fc->server_list->servers[fc->index]); + fc->ac.error = afs_register_server_cb_interest(vnode, fc->server_list, + fc->index); if (fc->ac.error < 0) goto failed; @@ -369,8 +369,16 @@ use_server: if (!test_bit(AFS_SERVER_FL_PROBED, &server->flags)) { fc->ac.alist = afs_get_addrlist(alist); - if (!afs_probe_fileserver(fc)) - goto failed; + if (!afs_probe_fileserver(fc)) { + switch (fc->ac.error) { + case -ENOMEM: + case -ERESTARTSYS: + case -EINTR: + goto failed; + default: + goto next_server; + } + } } if (!fc->ac.alist) diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 5c6263972ec9..08735948f15d 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -41,6 +41,7 @@ int afs_open_socket(struct afs_net *net) { struct sockaddr_rxrpc srx; struct socket *socket; + unsigned int min_level; int ret; _enter(""); @@ -60,6 +61,12 @@ int afs_open_socket(struct afs_net *net) srx.transport.sin6.sin6_family = AF_INET6; srx.transport.sin6.sin6_port = htons(AFS_CM_PORT); + min_level = RXRPC_SECURITY_ENCRYPT; + ret = kernel_setsockopt(socket, SOL_RXRPC, RXRPC_MIN_SECURITY_LEVEL, + (void *)&min_level, sizeof(min_level)); + if (ret < 0) + goto error_2; + ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx)); if (ret == -EADDRINUSE) { srx.transport.sin6.sin6_port = 0; @@ -482,8 +489,12 @@ static void afs_deliver_to_call(struct afs_call *call) state = READ_ONCE(call->state); switch (ret) { case 0: - if (state == AFS_CALL_CL_PROC_REPLY) + if (state == AFS_CALL_CL_PROC_REPLY) { + if (call->cbi) + set_bit(AFS_SERVER_FL_MAY_HAVE_CB, + &call->cbi->server->flags); goto call_complete; + } ASSERTCMP(state, >, AFS_CALL_CL_PROC_REPLY); goto done; case -EINPROGRESS: @@ -493,11 +504,6 @@ static void afs_deliver_to_call(struct afs_call *call) case -ECONNABORTED: ASSERTCMP(state, ==, AFS_CALL_COMPLETE); goto done; - case -ENOTCONN: - abort_code = RX_CALL_DEAD; - rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, ret, "KNC"); - goto local_abort; case -ENOTSUPP: abort_code = RXGEN_OPCODE; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, diff --git a/fs/afs/security.c b/fs/afs/security.c index cea2fff313dc..1992b0ffa543 100644 --- a/fs/afs/security.c +++ b/fs/afs/security.c @@ -147,8 +147,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, break; } - if (cb_break != (vnode->cb_break + - vnode->cb_interest->server->cb_s_break)) { + if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) { changed = true; break; } @@ -178,7 +177,7 @@ void afs_cache_permit(struct afs_vnode *vnode, struct key *key, } } - if (cb_break != (vnode->cb_break + vnode->cb_interest->server->cb_s_break)) + if (cb_break != afs_cb_break_sum(vnode, vnode->cb_interest)) goto someone_else_changed_it; /* We need a ref on any permits list we want to copy as we'll have to @@ -257,7 +256,7 @@ found: spin_lock(&vnode->lock); zap = rcu_access_pointer(vnode->permit_cache); - if (cb_break == (vnode->cb_break + vnode->cb_interest->server->cb_s_break) && + if (cb_break == afs_cb_break_sum(vnode, vnode->cb_interest) && zap == permits) rcu_assign_pointer(vnode->permit_cache, replacement); else diff --git a/fs/afs/server.c b/fs/afs/server.c index 629c74986cff..3af4625e2f8c 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -67,12 +67,6 @@ struct afs_server *afs_find_server(struct afs_net *net, sizeof(struct in6_addr)); if (diff == 0) goto found; - if (diff < 0) { - // TODO: Sort the list - //if (i == alist->nr_ipv4) - // goto not_found; - break; - } } } } else { @@ -87,17 +81,10 @@ struct afs_server *afs_find_server(struct afs_net *net, (u32 __force)b->sin6_addr.s6_addr32[3]); if (diff == 0) goto found; - if (diff < 0) { - // TODO: Sort the list - //if (i == 0) - // goto not_found; - break; - } } } } - //not_found: server = NULL; found: if (server && !atomic_inc_not_zero(&server->usage)) @@ -395,14 +382,16 @@ static void afs_destroy_server(struct afs_net *net, struct afs_server *server) struct afs_addr_list *alist = rcu_access_pointer(server->addresses); struct afs_addr_cursor ac = { .alist = alist, - .addr = &alist->addrs[0], .start = alist->index, - .index = alist->index, + .index = 0, + .addr = &alist->addrs[alist->index], .error = 0, }; _enter("%p", server); - afs_fs_give_up_all_callbacks(net, server, &ac, NULL); + if (test_bit(AFS_SERVER_FL_MAY_HAVE_CB, &server->flags)) + afs_fs_give_up_all_callbacks(net, server, &ac, NULL); + call_rcu(&server->rcu, afs_server_rcu); afs_dec_servers_outstanding(net); } diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c index 0f8dc4c8f07c..8a5760aa5832 100644 --- a/fs/afs/server_list.c +++ b/fs/afs/server_list.c @@ -49,6 +49,7 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, goto error; refcount_set(&slist->usage, 1); + rwlock_init(&slist->lock); /* Make sure a records exists for each server in the list. */ for (i = 0; i < vldb->nr_servers; i++) { @@ -64,9 +65,11 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell, goto error_2; } - /* Insertion-sort by server pointer */ + /* Insertion-sort by UUID */ for (j = 0; j < slist->nr_servers; j++) - if (slist->servers[j].server >= server) + if (memcmp(&slist->servers[j].server->uuid, + &server->uuid, + sizeof(server->uuid)) >= 0) break; if (j < slist->nr_servers) { if (slist->servers[j].server == server) { diff --git a/fs/afs/super.c b/fs/afs/super.c index 65081ec3c36e..9e5d7966621c 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -590,7 +590,7 @@ static void afs_i_init_once(void *_vnode) memset(vnode, 0, sizeof(*vnode)); inode_init_once(&vnode->vfs_inode); mutex_init(&vnode->io_lock); - mutex_init(&vnode->validate_lock); + init_rwsem(&vnode->validate_lock); spin_lock_init(&vnode->wb_lock); spin_lock_init(&vnode->lock); INIT_LIST_HEAD(&vnode->wb_keys); @@ -688,7 +688,7 @@ static int afs_statfs(struct dentry *dentry, struct kstatfs *buf) if (afs_begin_vnode_operation(&fc, vnode, key)) { fc.flags |= AFS_FS_CURSOR_NO_VSLEEP; while (afs_select_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_get_volume_status(&fc, &vs); } diff --git a/fs/afs/write.c b/fs/afs/write.c index c164698dc304..8b39e6ebb40b 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -351,7 +351,7 @@ found_key: ret = -ERESTARTSYS; if (afs_begin_vnode_operation(&fc, vnode, wbk->key)) { while (afs_select_fileserver(&fc)) { - fc.cb_break = vnode->cb_break + vnode->cb_s_break; + fc.cb_break = afs_calc_vnode_cb_break(vnode); afs_fs_store_data(&fc, mapping, first, last, offset, to); } diff --git a/fs/ceph/file.c b/fs/ceph/file.c index f85040d73e3d..cf0e45b10121 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -70,69 +70,104 @@ static __le32 ceph_flags_sys2wire(u32 flags) */ /* - * Calculate the length sum of direct io vectors that can - * be combined into one page vector. + * How many pages to get in one call to iov_iter_get_pages(). This + * determines the size of the on-stack array used as a buffer. */ -static size_t dio_get_pagev_size(const struct iov_iter *it) +#define ITER_GET_BVECS_PAGES 64 + +static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize, + struct bio_vec *bvecs) { - const struct iovec *iov = it->iov; - const struct iovec *iovend = iov + it->nr_segs; - size_t size; - - size = iov->iov_len - it->iov_offset; - /* - * An iov can be page vectored when both the current tail - * and the next base are page aligned. - */ - while (PAGE_ALIGNED((iov->iov_base + iov->iov_len)) && - (++iov < iovend && PAGE_ALIGNED((iov->iov_base)))) { - size += iov->iov_len; - } - dout("dio_get_pagevlen len = %zu\n", size); - return size; + size_t size = 0; + int bvec_idx = 0; + + if (maxsize > iov_iter_count(iter)) + maxsize = iov_iter_count(iter); + + while (size < maxsize) { + struct page *pages[ITER_GET_BVECS_PAGES]; + ssize_t bytes; + size_t start; + int idx = 0; + + bytes = iov_iter_get_pages(iter, pages, maxsize - size, + ITER_GET_BVECS_PAGES, &start); + if (bytes < 0) + return size ?: bytes; + + iov_iter_advance(iter, bytes); + size += bytes; + + for ( ; bytes; idx++, bvec_idx++) { + struct bio_vec bv = { + .bv_page = pages[idx], + .bv_len = min_t(int, bytes, PAGE_SIZE - start), + .bv_offset = start, + }; + + bvecs[bvec_idx] = bv; + bytes -= bv.bv_len; + start = 0; + } + } + + return size; } /* - * Allocate a page vector based on (@it, @nbytes). - * The return value is the tuple describing a page vector, - * that is (@pages, @page_align, @num_pages). + * iov_iter_get_pages() only considers one iov_iter segment, no matter + * what maxsize or maxpages are given. For ITER_BVEC that is a single + * page. + * + * Attempt to get up to @maxsize bytes worth of pages from @iter. + * Return the number of bytes in the created bio_vec array, or an error. */ -static struct page ** -dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes, - size_t *page_align, int *num_pages) +static ssize_t iter_get_bvecs_alloc(struct iov_iter *iter, size_t maxsize, + struct bio_vec **bvecs, int *num_bvecs) { - struct iov_iter tmp_it = *it; - size_t align; - struct page **pages; - int ret = 0, idx, npages; + struct bio_vec *bv; + size_t orig_count = iov_iter_count(iter); + ssize_t bytes; + int npages; - align = (unsigned long)(it->iov->iov_base + it->iov_offset) & - (PAGE_SIZE - 1); - npages = calc_pages_for(align, nbytes); - pages = kvmalloc(sizeof(*pages) * npages, GFP_KERNEL); - if (!pages) - return ERR_PTR(-ENOMEM); + iov_iter_truncate(iter, maxsize); + npages = iov_iter_npages(iter, INT_MAX); + iov_iter_reexpand(iter, orig_count); - for (idx = 0; idx < npages; ) { - size_t start; - ret = iov_iter_get_pages(&tmp_it, pages + idx, nbytes, - npages - idx, &start); - if (ret < 0) - goto fail; + /* + * __iter_get_bvecs() may populate only part of the array -- zero it + * out. + */ + bv = kvmalloc_array(npages, sizeof(*bv), GFP_KERNEL | __GFP_ZERO); + if (!bv) + return -ENOMEM; - iov_iter_advance(&tmp_it, ret); - nbytes -= ret; - idx += (ret + start + PAGE_SIZE - 1) / PAGE_SIZE; + bytes = __iter_get_bvecs(iter, maxsize, bv); + if (bytes < 0) { + /* + * No pages were pinned -- just free the array. + */ + kvfree(bv); + return bytes; } - BUG_ON(nbytes != 0); - *num_pages = npages; - *page_align = align; - dout("dio_get_pages_alloc: got %d pages align %zu\n", npages, align); - return pages; -fail: - ceph_put_page_vector(pages, idx, false); - return ERR_PTR(ret); + *bvecs = bv; + *num_bvecs = npages; + return bytes; +} + +static void put_bvecs(struct bio_vec *bvecs, int num_bvecs, bool should_dirty) +{ + int i; + + for (i = 0; i < num_bvecs; i++) { + if (bvecs[i].bv_page) { + if (should_dirty) + set_page_dirty_lock(bvecs[i].bv_page); + put_page(bvecs[i].bv_page); + } + } + kvfree(bvecs); } /* @@ -746,11 +781,12 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) struct inode *inode = req->r_inode; struct ceph_aio_request *aio_req = req->r_priv; struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0); - int num_pages = calc_pages_for((u64)osd_data->alignment, - osd_data->length); - dout("ceph_aio_complete_req %p rc %d bytes %llu\n", - inode, rc, osd_data->length); + BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS); + BUG_ON(!osd_data->num_bvecs); + + dout("ceph_aio_complete_req %p rc %d bytes %u\n", + inode, rc, osd_data->bvec_pos.iter.bi_size); if (rc == -EOLDSNAPC) { struct ceph_aio_work *aio_work; @@ -768,9 +804,10 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) } else if (!aio_req->write) { if (rc == -ENOENT) rc = 0; - if (rc >= 0 && osd_data->length > rc) { - int zoff = osd_data->alignment + rc; - int zlen = osd_data->length - rc; + if (rc >= 0 && osd_data->bvec_pos.iter.bi_size > rc) { + struct iov_iter i; + int zlen = osd_data->bvec_pos.iter.bi_size - rc; + /* * If read is satisfied by single OSD request, * it can pass EOF. Otherwise read is within @@ -785,13 +822,16 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) aio_req->total_len = rc + zlen; } - if (zlen > 0) - ceph_zero_page_vector_range(zoff, zlen, - osd_data->pages); + iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs, + osd_data->num_bvecs, + osd_data->bvec_pos.iter.bi_size); + iov_iter_advance(&i, rc); + iov_iter_zero(zlen, &i); } } - ceph_put_page_vector(osd_data->pages, num_pages, aio_req->should_dirty); + put_bvecs(osd_data->bvec_pos.bvecs, osd_data->num_bvecs, + aio_req->should_dirty); ceph_osdc_put_request(req); if (rc < 0) @@ -879,7 +919,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_vino vino; struct ceph_osd_request *req; - struct page **pages; + struct bio_vec *bvecs; struct ceph_aio_request *aio_req = NULL; int num_pages = 0; int flags; @@ -914,10 +954,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, } while (iov_iter_count(iter) > 0) { - u64 size = dio_get_pagev_size(iter); - size_t start = 0; + u64 size = iov_iter_count(iter); ssize_t len; + if (write) + size = min_t(u64, size, fsc->mount_options->wsize); + else + size = min_t(u64, size, fsc->mount_options->rsize); + vino = ceph_vino(inode); req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout, vino, pos, &size, 0, @@ -933,18 +977,14 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, break; } - if (write) - size = min_t(u64, size, fsc->mount_options->wsize); - else - size = min_t(u64, size, fsc->mount_options->rsize); - - len = size; - pages = dio_get_pages_alloc(iter, len, &start, &num_pages); - if (IS_ERR(pages)) { + len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages); + if (len < 0) { ceph_osdc_put_request(req); - ret = PTR_ERR(pages); + ret = len; break; } + if (len != size) + osd_req_op_extent_update(req, 0, len); /* * To simplify error handling, allow AIO when IO within i_size @@ -977,8 +1017,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, req->r_mtime = mtime; } - osd_req_op_extent_osd_data_pages(req, 0, pages, len, start, - false, false); + osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len); if (aio_req) { aio_req->total_len += len; @@ -991,7 +1030,6 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, list_add_tail(&req->r_unsafe_item, &aio_req->osd_reqs); pos += len; - iov_iter_advance(iter, len); continue; } @@ -1004,25 +1042,26 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, if (ret == -ENOENT) ret = 0; if (ret >= 0 && ret < len && pos + ret < size) { + struct iov_iter i; int zlen = min_t(size_t, len - ret, size - pos - ret); - ceph_zero_page_vector_range(start + ret, zlen, - pages); + + iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages, + len); + iov_iter_advance(&i, ret); + iov_iter_zero(zlen, &i); ret += zlen; } if (ret >= 0) len = ret; } - ceph_put_page_vector(pages, num_pages, should_dirty); - + put_bvecs(bvecs, num_pages, should_dirty); ceph_osdc_put_request(req); if (ret < 0) break; pos += len; - iov_iter_advance(iter, len); - if (!write && pos >= size) break; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index f715609b13f3..5a5a0158cc8f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1047,6 +1047,18 @@ out: return rc; } +/* + * Directory operations under CIFS/SMB2/SMB3 are synchronous, so fsync() + * is a dummy operation. + */ +static int cifs_dir_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + cifs_dbg(FYI, "Sync directory - name: %pD datasync: 0x%x\n", + file, datasync); + + return 0; +} + static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off, struct file *dst_file, loff_t destoff, size_t len, unsigned int flags) @@ -1181,6 +1193,7 @@ const struct file_operations cifs_dir_ops = { .copy_file_range = cifs_copy_file_range, .clone_file_range = cifs_clone_file_range, .llseek = generic_file_llseek, + .fsync = cifs_dir_fsync, }; static void diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index a5aa158d535a..7a10a5d0731f 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1977,14 +1977,6 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, goto cifs_parse_mount_err; } -#ifdef CONFIG_CIFS_SMB_DIRECT - if (vol->rdma && vol->sign) { - cifs_dbg(VFS, "Currently SMB direct doesn't support signing." - " This is being fixed\n"); - goto cifs_parse_mount_err; - } -#endif - #ifndef CONFIG_KEYS /* Muliuser mounts require CONFIG_KEYS support */ if (vol->multiuser) { diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index b76b85881dcc..9c6d95ffca97 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -589,9 +589,15 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + /* + * If ea_name is NULL (listxattr) and there are no EAs, return 0 as it's + * not an error. Otherwise, the specified ea_name was not found. + */ if (!rc) rc = move_smb2_ea_to_cifs(ea_data, buf_size, smb2_data, SMB2_MAX_EA_BUF, ea_name); + else if (!ea_name && rc == -ENODATA) + rc = 0; kfree(smb2_data); return rc; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 60db51bae0e3..0f48741a0130 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -730,19 +730,14 @@ neg_exit: int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) { - int rc = 0; - struct validate_negotiate_info_req vneg_inbuf; + int rc; + struct validate_negotiate_info_req *pneg_inbuf; struct validate_negotiate_info_rsp *pneg_rsp = NULL; u32 rsplen; u32 inbuflen; /* max of 4 dialects */ cifs_dbg(FYI, "validate negotiate\n"); -#ifdef CONFIG_CIFS_SMB_DIRECT - if (tcon->ses->server->rdma) - return 0; -#endif - /* In SMB3.11 preauth integrity supersedes validate negotiate */ if (tcon->ses->server->dialect == SMB311_PROT_ID) return 0; @@ -765,63 +760,69 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) if (tcon->ses->session_flags & SMB2_SESSION_FLAG_IS_NULL) cifs_dbg(VFS, "Unexpected null user (anonymous) auth flag sent by server\n"); - vneg_inbuf.Capabilities = + pneg_inbuf = kmalloc(sizeof(*pneg_inbuf), GFP_NOFS); + if (!pneg_inbuf) + return -ENOMEM; + + pneg_inbuf->Capabilities = cpu_to_le32(tcon->ses->server->vals->req_capabilities); - memcpy(vneg_inbuf.Guid, tcon->ses->server->client_guid, + memcpy(pneg_inbuf->Guid, tcon->ses->server->client_guid, SMB2_CLIENT_GUID_SIZE); if (tcon->ses->sign) - vneg_inbuf.SecurityMode = + pneg_inbuf->SecurityMode = cpu_to_le16(SMB2_NEGOTIATE_SIGNING_REQUIRED); else if (global_secflags & CIFSSEC_MAY_SIGN) - vneg_inbuf.SecurityMode = + pneg_inbuf->SecurityMode = cpu_to_le16(SMB2_NEGOTIATE_SIGNING_ENABLED); else - vneg_inbuf.SecurityMode = 0; + pneg_inbuf->SecurityMode = 0; if (strcmp(tcon->ses->server->vals->version_string, SMB3ANY_VERSION_STRING) == 0) { - vneg_inbuf.Dialects[0] = cpu_to_le16(SMB30_PROT_ID); - vneg_inbuf.Dialects[1] = cpu_to_le16(SMB302_PROT_ID); - vneg_inbuf.DialectCount = cpu_to_le16(2); + pneg_inbuf->Dialects[0] = cpu_to_le16(SMB30_PROT_ID); + pneg_inbuf->Dialects[1] = cpu_to_le16(SMB302_PROT_ID); + pneg_inbuf->DialectCount = cpu_to_le16(2); /* structure is big enough for 3 dialects, sending only 2 */ - inbuflen = sizeof(struct validate_negotiate_info_req) - 2; + inbuflen = sizeof(*pneg_inbuf) - + sizeof(pneg_inbuf->Dialects[0]); } else if (strcmp(tcon->ses->server->vals->version_string, SMBDEFAULT_VERSION_STRING) == 0) { - vneg_inbuf.Dialects[0] = cpu_to_le16(SMB21_PROT_ID); - vneg_inbuf.Dialects[1] = cpu_to_le16(SMB30_PROT_ID); - vneg_inbuf.Dialects[2] = cpu_to_le16(SMB302_PROT_ID); - vneg_inbuf.DialectCount = cpu_to_le16(3); + pneg_inbuf->Dialects[0] = cpu_to_le16(SMB21_PROT_ID); + pneg_inbuf->Dialects[1] = cpu_to_le16(SMB30_PROT_ID); + pneg_inbuf->Dialects[2] = cpu_to_le16(SMB302_PROT_ID); + pneg_inbuf->DialectCount = cpu_to_le16(3); /* structure is big enough for 3 dialects */ - inbuflen = sizeof(struct validate_negotiate_info_req); + inbuflen = sizeof(*pneg_inbuf); } else { /* otherwise specific dialect was requested */ - vneg_inbuf.Dialects[0] = + pneg_inbuf->Dialects[0] = cpu_to_le16(tcon->ses->server->vals->protocol_id); - vneg_inbuf.DialectCount = cpu_to_le16(1); + pneg_inbuf->DialectCount = cpu_to_le16(1); /* structure is big enough for 3 dialects, sending only 1 */ - inbuflen = sizeof(struct validate_negotiate_info_req) - 4; + inbuflen = sizeof(*pneg_inbuf) - + sizeof(pneg_inbuf->Dialects[0]) * 2; } rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID, FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */, - (char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req), - (char **)&pneg_rsp, &rsplen); + (char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen); if (rc != 0) { cifs_dbg(VFS, "validate protocol negotiate failed: %d\n", rc); - return -EIO; + rc = -EIO; + goto out_free_inbuf; } - if (rsplen != sizeof(struct validate_negotiate_info_rsp)) { + rc = -EIO; + if (rsplen != sizeof(*pneg_rsp)) { cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n", rsplen); /* relax check since Mac returns max bufsize allowed on ioctl */ - if ((rsplen > CIFSMaxBufSize) - || (rsplen < sizeof(struct validate_negotiate_info_rsp))) - goto err_rsp_free; + if (rsplen > CIFSMaxBufSize || rsplen < sizeof(*pneg_rsp)) + goto out_free_rsp; } /* check validate negotiate info response matches what we got earlier */ @@ -838,15 +839,17 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon) goto vneg_out; /* validate negotiate successful */ + rc = 0; cifs_dbg(FYI, "validate negotiate info successful\n"); - kfree(pneg_rsp); - return 0; + goto out_free_rsp; vneg_out: cifs_dbg(VFS, "protocol revalidation - security settings mismatch\n"); -err_rsp_free: +out_free_rsp: kfree(pneg_rsp); - return -EIO; +out_free_inbuf: + kfree(pneg_inbuf); + return rc; } enum securityEnum diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index 513c357c734b..a6c0f54c48c3 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -588,6 +588,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent) return 0; out_put_hidden_dir: + cancel_delayed_work_sync(&sbi->sync_work); iput(sbi->hidden_dir); out_put_root: dput(sb->s_root); diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 01c6b3894406..7869622af22a 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4250,10 +4250,11 @@ out: static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry, bool preserve) { - int error; + int error, had_lock; struct inode *inode = d_inode(old_dentry); struct buffer_head *old_bh = NULL; struct inode *new_orphan_inode = NULL; + struct ocfs2_lock_holder oh; if (!ocfs2_refcount_tree(OCFS2_SB(inode->i_sb))) return -EOPNOTSUPP; @@ -4295,6 +4296,14 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, goto out; } + had_lock = ocfs2_inode_lock_tracker(new_orphan_inode, NULL, 1, + &oh); + if (had_lock < 0) { + error = had_lock; + mlog_errno(error); + goto out; + } + /* If the security isn't preserved, we need to re-initialize them. */ if (!preserve) { error = ocfs2_init_security_and_acl(dir, new_orphan_inode, @@ -4302,14 +4311,15 @@ static int ocfs2_reflink(struct dentry *old_dentry, struct inode *dir, if (error) mlog_errno(error); } -out: if (!error) { error = ocfs2_mv_orphaned_inode_to_new(dir, new_orphan_inode, new_dentry); if (error) mlog_errno(error); } + ocfs2_inode_unlock_tracker(new_orphan_inode, 1, &oh, had_lock); +out: if (new_orphan_inode) { /* * We need to open_unlock the inode no matter whether we diff --git a/fs/proc/base.c b/fs/proc/base.c index 1b2ede6abcdf..1a76d751cf3c 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -261,7 +261,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, * Inherently racy -- command line shares address space * with code and data. */ - rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0); + rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON); if (rv <= 0) goto out_free_page; @@ -279,7 +279,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, int nr_read; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -325,7 +325,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, bool final; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -946,7 +946,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); - retval = access_remote_vm(mm, (env_start + src), page, this_len, 0); + retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON); if (retval <= 0) { ret = retval; diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index d1e82761de81..e64ecb9f2720 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -209,25 +209,34 @@ kclist_add_private(unsigned long pfn, unsigned long nr_pages, void *arg) { struct list_head *head = (struct list_head *)arg; struct kcore_list *ent; + struct page *p; + + if (!pfn_valid(pfn)) + return 1; + + p = pfn_to_page(pfn); + if (!memmap_valid_within(pfn, p, page_zone(p))) + return 1; ent = kmalloc(sizeof(*ent), GFP_KERNEL); if (!ent) return -ENOMEM; - ent->addr = (unsigned long)__va((pfn << PAGE_SHIFT)); + ent->addr = (unsigned long)page_to_virt(p); ent->size = nr_pages << PAGE_SHIFT; - /* Sanity check: Can happen in 32bit arch...maybe */ - if (ent->addr < (unsigned long) __va(0)) + if (!virt_addr_valid(ent->addr)) goto free_out; /* cut not-mapped area. ....from ppc-32 code. */ if (ULONG_MAX - ent->addr < ent->size) ent->size = ULONG_MAX - ent->addr; - /* cut when vmalloc() area is higher than direct-map area */ - if (VMALLOC_START > (unsigned long)__va(0)) { - if (ent->addr > VMALLOC_START) - goto free_out; + /* + * We've already checked virt_addr_valid so we know this address + * is a valid pointer, therefore we can check against it to determine + * if we need to trim + */ + if (VMALLOC_START > ent->addr) { if (VMALLOC_START - ent->addr < ent->size) ent->size = VMALLOC_START - ent->addr; } diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index e7efe12a81bd..cfdd2484cc42 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -28,7 +28,7 @@ #include <linux/irqchip/arm-gic-v4.h> -#define VGIC_V3_MAX_CPUS 255 +#define VGIC_V3_MAX_CPUS 512 #define VGIC_V2_MAX_CPUS 8 #define VGIC_NR_IRQS_LEGACY 256 #define VGIC_NR_SGIS 16 @@ -201,6 +201,14 @@ struct vgic_its { struct vgic_state_iter; +struct vgic_redist_region { + u32 index; + gpa_t base; + u32 count; /* number of redistributors or 0 if single region */ + u32 free_index; /* index of the next free redistributor */ + struct list_head list; +}; + struct vgic_dist { bool in_kernel; bool ready; @@ -220,10 +228,7 @@ struct vgic_dist { /* either a GICv2 CPU interface */ gpa_t vgic_cpu_base; /* or a number of GICv3 redistributor regions */ - struct { - gpa_t vgic_redist_base; - gpa_t vgic_redist_free_offset; - }; + struct list_head rd_regions; }; /* distributor enabled */ @@ -311,6 +316,7 @@ struct vgic_cpu { */ struct vgic_io_device rd_iodev; struct vgic_io_device sgi_iodev; + struct vgic_redist_region *rdreg; /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; @@ -332,7 +338,6 @@ void kvm_vgic_early_init(struct kvm *kvm); int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu); int kvm_vgic_create(struct kvm *kvm, u32 type); void kvm_vgic_destroy(struct kvm *kvm); -void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu); void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_vgic_map_resources(struct kvm *kvm); int kvm_vgic_hyp_init(void); diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index d3339dd48b1a..b324e01ccf2d 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -25,6 +25,7 @@ #define PHY_ID_BCM54612E 0x03625e60 #define PHY_ID_BCM54616S 0x03625d10 #define PHY_ID_BCM57780 0x03625d90 +#define PHY_ID_BCM89610 0x03625cd0 #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7260 0xae025190 diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 528ccc943cee..96bb32285989 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -77,7 +77,10 @@ struct ceph_osd_data { u32 bio_length; }; #endif /* CONFIG_BLOCK */ - struct ceph_bvec_iter bvec_pos; + struct { + struct ceph_bvec_iter bvec_pos; + u32 num_bvecs; + }; }; }; @@ -412,6 +415,10 @@ void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, struct ceph_bio_iter *bio_pos, u32 bio_length); #endif /* CONFIG_BLOCK */ +void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req, + unsigned int which, + struct bio_vec *bvecs, u32 num_bvecs, + u32 bytes); void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bvec_iter *bvec_pos); @@ -426,7 +433,8 @@ extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *, bool own_pages); void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, - struct bio_vec *bvecs, u32 bytes); + struct bio_vec *bvecs, u32 num_bvecs, + u32 bytes); extern void osd_req_op_cls_response_data_pages(struct ceph_osd_request *, unsigned int which, struct page **pages, u64 length, diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c1961761311d..2803264c512f 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -62,6 +62,7 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); +void kthread_park_complete(struct task_struct *k); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6930c63126c7..b81769a5a2b7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -730,6 +730,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu); void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); + +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); long kvm_arch_dev_ioctl(struct file *filp, @@ -1045,13 +1048,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING -#ifdef CONFIG_S390 -#define KVM_MAX_IRQ_ROUTES 4096 //FIXME: we can have more than that... -#elif defined(CONFIG_ARM64) -#define KVM_MAX_IRQ_ROUTES 4096 -#else -#define KVM_MAX_IRQ_ROUTES 1024 -#endif +#define KVM_MAX_IRQ_ROUTES 4096 /* might need extension/rework in the future */ bool kvm_arch_can_set_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, @@ -1276,4 +1273,13 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end); +#ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE +int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); +#else +static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) +{ + return 0; +} +#endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */ + #endif diff --git a/include/linux/mm.h b/include/linux/mm.h index 1ac1f06a4be6..c6fa9a255dbf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2466,6 +2466,13 @@ static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } +static inline vm_fault_t vmf_error(int err) +{ + if (err == -ENOMEM) + return VM_FAULT_OOM; + return VM_FAULT_SIGBUS; +} + struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags, unsigned int *page_mask); @@ -2493,6 +2500,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ +#define FOLL_ANON 0x8000 /* don't do file mappings */ static inline int vm_fault_to_errno(int vm_fault, int foll_flags) { diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h index b5b43f94f311..01b990e4b228 100644 --- a/include/linux/mtd/map.h +++ b/include/linux/mtd/map.h @@ -312,7 +312,7 @@ void map_destroy(struct mtd_info *mtd); ({ \ int i, ret = 1; \ for (i = 0; i < map_words(map); i++) { \ - if (((val1).x[i] & (val2).x[i]) != (val2).x[i]) { \ + if (((val1).x[i] & (val2).x[i]) != (val3).x[i]) { \ ret = 0; \ break; \ } \ diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 5dad59b31244..17c919436f48 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -867,12 +867,18 @@ struct nand_op_instr { * tBERS (during an erase) which all of them are u64 values that cannot be * divided by usual kernel macros and must be handled with the special * DIV_ROUND_UP_ULL() macro. + * + * Cast to type of dividend is needed here to guarantee that the result won't + * be an unsigned long long when the dividend is an unsigned long (or smaller), + * which is what the compiler does when it sees ternary operator with 2 + * different return types (picks the largest type to make sure there's no + * loss). */ -#define __DIVIDE(dividend, divisor) ({ \ - sizeof(dividend) == sizeof(u32) ? \ - DIV_ROUND_UP(dividend, divisor) : \ - DIV_ROUND_UP_ULL(dividend, divisor); \ - }) +#define __DIVIDE(dividend, divisor) ({ \ + (__typeof__(dividend))(sizeof(dividend) <= sizeof(unsigned long) ? \ + DIV_ROUND_UP(dividend, divisor) : \ + DIV_ROUND_UP_ULL(dividend, divisor)); \ + }) #define PSEC_TO_NSEC(x) __DIVIDE(x, 1000) #define PSEC_TO_MSEC(x) __DIVIDE(x, 1000000000) diff --git a/include/linux/oom.h b/include/linux/oom.h index 5bad038ac012..6adac113e96d 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -95,6 +95,8 @@ static inline int check_stable_address_space(struct mm_struct *mm) return 0; } +void __oom_reap_task_mm(struct mm_struct *mm); + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h index 6bfd2b581f75..af8a61be2d8d 100644 --- a/include/linux/rbtree_augmented.h +++ b/include/linux/rbtree_augmented.h @@ -26,6 +26,7 @@ #include <linux/compiler.h> #include <linux/rbtree.h> +#include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for diff --git a/include/linux/rbtree_latch.h b/include/linux/rbtree_latch.h index ece43e882b56..7d012faa509a 100644 --- a/include/linux/rbtree_latch.h +++ b/include/linux/rbtree_latch.h @@ -35,6 +35,7 @@ #include <linux/rbtree.h> #include <linux/seqlock.h> +#include <linux/rcupdate.h> struct latch_tree_node { struct rb_node node[2]; diff --git a/include/linux/sched.h b/include/linux/sched.h index b3d697f3b573..ff289ae6b787 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -112,17 +112,36 @@ struct task_group; #ifdef CONFIG_DEBUG_ATOMIC_SLEEP +/* + * Special states are those that do not use the normal wait-loop pattern. See + * the comment with set_special_state(). + */ +#define is_special_task_state(state) \ + ((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD)) + #define __set_current_state(state_value) \ do { \ + WARN_ON_ONCE(is_special_task_state(state_value));\ current->task_state_change = _THIS_IP_; \ current->state = (state_value); \ } while (0) + #define set_current_state(state_value) \ do { \ + WARN_ON_ONCE(is_special_task_state(state_value));\ current->task_state_change = _THIS_IP_; \ smp_store_mb(current->state, (state_value)); \ } while (0) +#define set_special_state(state_value) \ + do { \ + unsigned long flags; /* may shadow */ \ + WARN_ON_ONCE(!is_special_task_state(state_value)); \ + raw_spin_lock_irqsave(¤t->pi_lock, flags); \ + current->task_state_change = _THIS_IP_; \ + current->state = (state_value); \ + raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ + } while (0) #else /* * set_current_state() includes a barrier so that the write of current->state @@ -144,8 +163,8 @@ struct task_group; * * The above is typically ordered against the wakeup, which does: * - * need_sleep = false; - * wake_up_state(p, TASK_UNINTERRUPTIBLE); + * need_sleep = false; + * wake_up_state(p, TASK_UNINTERRUPTIBLE); * * Where wake_up_state() (and all other wakeup primitives) imply enough * barriers to order the store of the variable against wakeup. @@ -154,12 +173,33 @@ struct task_group; * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING). * - * This is obviously fine, since they both store the exact same value. + * However, with slightly different timing the wakeup TASK_RUNNING store can + * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not + * a problem either because that will result in one extra go around the loop + * and our @cond test will save the day. * * Also see the comments of try_to_wake_up(). */ -#define __set_current_state(state_value) do { current->state = (state_value); } while (0) -#define set_current_state(state_value) smp_store_mb(current->state, (state_value)) +#define __set_current_state(state_value) \ + current->state = (state_value) + +#define set_current_state(state_value) \ + smp_store_mb(current->state, (state_value)) + +/* + * set_special_state() should be used for those states when the blocking task + * can not use the regular condition based wait-loop. In that case we must + * serialize against wakeups such that any possible in-flight TASK_RUNNING stores + * will not collide with our state change. + */ +#define set_special_state(state_value) \ + do { \ + unsigned long flags; /* may shadow */ \ + raw_spin_lock_irqsave(¤t->pi_lock, flags); \ + current->state = (state_value); \ + raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ + } while (0) + #endif /* Task command name length: */ @@ -1578,6 +1618,12 @@ static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag) clear_ti_thread_flag(task_thread_info(tsk), flag); } +static inline void update_tsk_thread_flag(struct task_struct *tsk, int flag, + bool value) +{ + update_ti_thread_flag(task_thread_info(tsk), flag, value); +} + static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag) { return test_and_set_ti_thread_flag(task_thread_info(tsk), flag); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index a7ce74c74e49..113d1ad1ced7 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -280,7 +280,7 @@ static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) - __set_current_state(TASK_STOPPED); + set_special_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); schedule(); diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index cf2862bd134a..8d8821b3689a 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -60,6 +60,15 @@ static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) clear_bit(flag, (unsigned long *)&ti->flags); } +static inline void update_ti_thread_flag(struct thread_info *ti, int flag, + bool value) +{ + if (value) + set_ti_thread_flag(ti, flag); + else + clear_ti_thread_flag(ti, flag); +} + static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); @@ -79,6 +88,8 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) +#define update_thread_flag(flag, value) \ + update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ diff --git a/include/net/bonding.h b/include/net/bonding.h index f801fc940b29..b52235158836 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -198,6 +198,7 @@ struct bonding { struct slave __rcu *primary_slave; struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ bool force_primary; + u32 nest_level; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index 9a074776f70b..d1fcf2442a42 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -251,7 +251,7 @@ extern struct flow_dissector flow_keys_buf_dissector; * This structure is used to hold a digest of the full flow keys. This is a * larger "hash" of a flow to allow definitively matching specific flows where * the 32 bit skb->hash is not large enough. The size is limited to 16 bytes so - * that it can by used in CB of skb (see sch_choke for an example). + * that it can be used in CB of skb (see sch_choke for an example). */ #define FLOW_KEYS_DIGEST_LEN 16 struct flow_keys_digest { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index d2279b2d61aa..b2f3a0c018e7 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2080,7 +2080,7 @@ struct ieee80211_txq { * virtual interface might not be given air time for the transmission of * the frame, as it is not synced with the AP/P2P GO yet, and thus the * deauthentication frame might not be transmitted. - > + * * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't * support QoS NDP for AP probing - that's most likely a driver bug. * diff --git a/include/net/xfrm.h b/include/net/xfrm.h index a872379b69da..45e75c36b738 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -375,6 +375,7 @@ struct xfrm_input_afinfo { int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); +void xfrm_flush_gc(void); void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index f0820554caa9..d0a341bc4540 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -575,6 +575,48 @@ TRACE_EVENT(afs_protocol_error, __entry->call, __entry->error, __entry->where) ); +TRACE_EVENT(afs_cm_no_server, + TP_PROTO(struct afs_call *call, struct sockaddr_rxrpc *srx), + + TP_ARGS(call, srx), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(unsigned int, op_id ) + __field_struct(struct sockaddr_rxrpc, srx ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->op_id = call->operation_ID; + memcpy(&__entry->srx, srx, sizeof(__entry->srx)); + ), + + TP_printk("c=%08x op=%u %pISpc", + __entry->call, __entry->op_id, &__entry->srx.transport) + ); + +TRACE_EVENT(afs_cm_no_server_u, + TP_PROTO(struct afs_call *call, const uuid_t *uuid), + + TP_ARGS(call, uuid), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(unsigned int, op_id ) + __field_struct(uuid_t, uuid ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->op_id = call->operation_ID; + memcpy(&__entry->uuid, uuid, sizeof(__entry->uuid)); + ), + + TP_printk("c=%08x op=%u %pU", + __entry->call, __entry->op_id, &__entry->uuid) + ); + #endif /* _TRACE_AFS_H */ /* This part must be outside protection */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 9e96c2fe2793..077e664ac9a2 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -15,6 +15,7 @@ #define _TRACE_RXRPC_H #include <linux/tracepoint.h> +#include <linux/errqueue.h> /* * Define enums for tracing information. @@ -210,6 +211,20 @@ enum rxrpc_congest_change { rxrpc_cong_saw_nack, }; +enum rxrpc_tx_fail_trace { + rxrpc_tx_fail_call_abort, + rxrpc_tx_fail_call_ack, + rxrpc_tx_fail_call_data_frag, + rxrpc_tx_fail_call_data_nofrag, + rxrpc_tx_fail_call_final_resend, + rxrpc_tx_fail_conn_abort, + rxrpc_tx_fail_conn_challenge, + rxrpc_tx_fail_conn_response, + rxrpc_tx_fail_reject, + rxrpc_tx_fail_version_keepalive, + rxrpc_tx_fail_version_reply, +}; + #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ /* @@ -437,6 +452,19 @@ enum rxrpc_congest_change { EM(RXRPC_CALL_LOCAL_ERROR, "LocalError") \ E_(RXRPC_CALL_NETWORK_ERROR, "NetError") +#define rxrpc_tx_fail_traces \ + EM(rxrpc_tx_fail_call_abort, "CallAbort") \ + EM(rxrpc_tx_fail_call_ack, "CallAck") \ + EM(rxrpc_tx_fail_call_data_frag, "CallDataFrag") \ + EM(rxrpc_tx_fail_call_data_nofrag, "CallDataNofrag") \ + EM(rxrpc_tx_fail_call_final_resend, "CallFinalResend") \ + EM(rxrpc_tx_fail_conn_abort, "ConnAbort") \ + EM(rxrpc_tx_fail_conn_challenge, "ConnChall") \ + EM(rxrpc_tx_fail_conn_response, "ConnResp") \ + EM(rxrpc_tx_fail_reject, "Reject") \ + EM(rxrpc_tx_fail_version_keepalive, "VerKeepalive") \ + E_(rxrpc_tx_fail_version_reply, "VerReply") + /* * Export enum symbols via userspace. */ @@ -460,6 +488,7 @@ rxrpc_propose_ack_traces; rxrpc_propose_ack_outcomes; rxrpc_congest_modes; rxrpc_congest_changes; +rxrpc_tx_fail_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -1374,6 +1403,62 @@ TRACE_EVENT(rxrpc_resend, __entry->anno) ); +TRACE_EVENT(rxrpc_rx_icmp, + TP_PROTO(struct rxrpc_peer *peer, struct sock_extended_err *ee, + struct sockaddr_rxrpc *srx), + + TP_ARGS(peer, ee, srx), + + TP_STRUCT__entry( + __field(unsigned int, peer ) + __field_struct(struct sock_extended_err, ee ) + __field_struct(struct sockaddr_rxrpc, srx ) + ), + + TP_fast_assign( + __entry->peer = peer->debug_id; + memcpy(&__entry->ee, ee, sizeof(__entry->ee)); + memcpy(&__entry->srx, srx, sizeof(__entry->srx)); + ), + + TP_printk("P=%08x o=%u t=%u c=%u i=%u d=%u e=%d %pISp", + __entry->peer, + __entry->ee.ee_origin, + __entry->ee.ee_type, + __entry->ee.ee_code, + __entry->ee.ee_info, + __entry->ee.ee_data, + __entry->ee.ee_errno, + &__entry->srx.transport) + ); + +TRACE_EVENT(rxrpc_tx_fail, + TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, int ret, + enum rxrpc_tx_fail_trace what), + + TP_ARGS(debug_id, serial, ret, what), + + TP_STRUCT__entry( + __field(unsigned int, debug_id ) + __field(rxrpc_serial_t, serial ) + __field(int, ret ) + __field(enum rxrpc_tx_fail_trace, what ) + ), + + TP_fast_assign( + __entry->debug_id = debug_id; + __entry->serial = serial; + __entry->ret = ret; + __entry->what = what; + ), + + TP_printk("c=%08x r=%x ret=%d %s", + __entry->debug_id, + __entry->serial, + __entry->ret, + __print_symbolic(__entry->what, rxrpc_tx_fail_traces)) + ); + #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index 335d87242439..bbb08a3ef5cc 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -224,6 +224,8 @@ TRACE_EVENT(rpc_stats_latency, TP_ARGS(task, backlog, rtt, execute), TP_STRUCT__entry( + __field(unsigned int, task_id) + __field(unsigned int, client_id) __field(u32, xid) __field(int, version) __string(progname, task->tk_client->cl_program->name) @@ -231,13 +233,11 @@ TRACE_EVENT(rpc_stats_latency, __field(unsigned long, backlog) __field(unsigned long, rtt) __field(unsigned long, execute) - __string(addr, - task->tk_xprt->address_strings[RPC_DISPLAY_ADDR]) - __string(port, - task->tk_xprt->address_strings[RPC_DISPLAY_PORT]) ), TP_fast_assign( + __entry->client_id = task->tk_client->cl_clid; + __entry->task_id = task->tk_pid; __entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid); __entry->version = task->tk_client->cl_vers; __assign_str(progname, task->tk_client->cl_program->name) @@ -245,14 +245,10 @@ TRACE_EVENT(rpc_stats_latency, __entry->backlog = ktime_to_us(backlog); __entry->rtt = ktime_to_us(rtt); __entry->execute = ktime_to_us(execute); - __assign_str(addr, - task->tk_xprt->address_strings[RPC_DISPLAY_ADDR]); - __assign_str(port, - task->tk_xprt->address_strings[RPC_DISPLAY_PORT]); ), - TP_printk("peer=[%s]:%s xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu", - __get_str(addr), __get_str(port), __entry->xid, + TP_printk("task:%u@%d xid=0x%08x %sv%d %s backlog=%lu rtt=%lu execute=%lu", + __entry->task_id, __entry->client_id, __entry->xid, __get_str(progname), __entry->version, __get_str(procname), __entry->backlog, __entry->rtt, __entry->execute) ); diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index 7dd8f34c37df..fdcf88bcf0ea 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -352,22 +352,6 @@ DECLARE_EVENT_CLASS(xen_mmu_pgd, DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_pin); DEFINE_XEN_MMU_PGD_EVENT(xen_mmu_pgd_unpin); -TRACE_EVENT(xen_mmu_flush_tlb_all, - TP_PROTO(int x), - TP_ARGS(x), - TP_STRUCT__entry(__array(char, x, 0)), - TP_fast_assign((void)x), - TP_printk("%s", "") - ); - -TRACE_EVENT(xen_mmu_flush_tlb, - TP_PROTO(int x), - TP_ARGS(x), - TP_STRUCT__entry(__array(char, x, 0)), - TP_fast_assign((void)x), - TP_printk("%s", "") - ); - TRACE_EVENT(xen_mmu_flush_tlb_one_user, TP_PROTO(unsigned long addr), TP_ARGS(addr), diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b02c41e53d56..b252ceb3965c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -948,6 +948,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_BPB 152 #define KVM_CAP_GET_MSR_FEATURES 153 #define KVM_CAP_HYPERV_EVENTFD 154 +#define KVM_CAP_HYPERV_TLBFLUSH 155 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 15daf5e2638d..9c3630146cec 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2698,6 +2698,8 @@ enum nl80211_attrs { #define NL80211_ATTR_KEYS NL80211_ATTR_KEYS #define NL80211_ATTR_FEATURE_FLAGS NL80211_ATTR_FEATURE_FLAGS +#define NL80211_WIPHY_NAME_MAXLEN 128 + #define NL80211_MAX_SUPP_RATES 32 #define NL80211_MAX_SUPP_HT_RATES 77 #define NL80211_MAX_SUPP_REG_RULES 64 diff --git a/init/main.c b/init/main.c index b795aa341a3a..fd37315835b4 100644 --- a/init/main.c +++ b/init/main.c @@ -423,7 +423,7 @@ static noinline void __ref rest_init(void) /* * Enable might_sleep() and smp_processor_id() checks. - * They cannot be enabled earlier because with CONFIG_PRREMPT=y + * They cannot be enabled earlier because with CONFIG_PREEMPT=y * kernel_thread() would trigger might_sleep() splats. With * CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled * already, but it's stuck on the kthreadd_done completion. @@ -1034,6 +1034,13 @@ __setup("rodata=", set_debug_rodata); static void mark_readonly(void) { if (rodata_enabled) { + /* + * load_module() results in W+X mappings, which are cleaned up + * with call_rcu_sched(). Let's make sure that queued work is + * flushed so that we don't hit false positives looking for + * insecure pages which are W+X. + */ + rcu_barrier_sched(); mark_rodata_ro(); rodata_test(); } else diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ebfe9f29dae8..016ef9025827 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -26,6 +26,7 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> +#include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -102,12 +103,14 @@ const struct bpf_map_ops bpf_map_offload_ops = { static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) { const struct bpf_map_ops *ops; + u32 type = attr->map_type; struct bpf_map *map; int err; - if (attr->map_type >= ARRAY_SIZE(bpf_map_types)) + if (type >= ARRAY_SIZE(bpf_map_types)) return ERR_PTR(-EINVAL); - ops = bpf_map_types[attr->map_type]; + type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types)); + ops = bpf_map_types[type]; if (!ops) return ERR_PTR(-EINVAL); @@ -122,7 +125,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) if (IS_ERR(map)) return map; map->ops = ops; - map->map_type = attr->map_type; + map->map_type = type; return map; } @@ -871,11 +874,17 @@ static const struct bpf_prog_ops * const bpf_prog_types[] = { static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { - if (type >= ARRAY_SIZE(bpf_prog_types) || !bpf_prog_types[type]) + const struct bpf_prog_ops *ops; + + if (type >= ARRAY_SIZE(bpf_prog_types)) + return -EINVAL; + type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types)); + ops = bpf_prog_types[type]; + if (!ops) return -EINVAL; if (!bpf_prog_is_dev_bound(prog->aux)) - prog->aux->ops = bpf_prog_types[type]; + prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; diff --git a/kernel/compat.c b/kernel/compat.c index 6d21894806b4..92d8c98c0f57 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -34,6 +34,7 @@ int compat_get_timex(struct timex *txc, const struct compat_timex __user *utp) { struct compat_timex tx32; + memset(txc, 0, sizeof(struct timex)); if (copy_from_user(&tx32, utp, sizeof(struct compat_timex))) return -EFAULT; diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 6c6b3c48db71..1d8ca9ea9979 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/circ_buf.h> #include <linux/poll.h> +#include <linux/nospec.h> #include "internal.h" @@ -867,8 +868,10 @@ perf_mmap_to_page(struct ring_buffer *rb, unsigned long pgoff) return NULL; /* AUX space */ - if (pgoff >= rb->aux_pgoff) - return virt_to_page(rb->aux_pages[pgoff - rb->aux_pgoff]); + if (pgoff >= rb->aux_pgoff) { + int aux_pgoff = array_index_nospec(pgoff - rb->aux_pgoff, rb->aux_nr_pages); + return virt_to_page(rb->aux_pages[aux_pgoff]); + } } return __perf_mmap_to_page(rb, pgoff); diff --git a/kernel/kthread.c b/kernel/kthread.c index cd50e99202b0..2017a39ab490 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -55,7 +55,6 @@ enum KTHREAD_BITS { KTHREAD_IS_PER_CPU = 0, KTHREAD_SHOULD_STOP, KTHREAD_SHOULD_PARK, - KTHREAD_IS_PARKED, }; static inline void set_kthread_struct(void *kthread) @@ -177,14 +176,12 @@ void *kthread_probe_data(struct task_struct *task) static void __kthread_parkme(struct kthread *self) { - __set_current_state(TASK_PARKED); - while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) { - if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags)) - complete(&self->parked); + for (;;) { + set_current_state(TASK_PARKED); + if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags)) + break; schedule(); - __set_current_state(TASK_PARKED); } - clear_bit(KTHREAD_IS_PARKED, &self->flags); __set_current_state(TASK_RUNNING); } @@ -194,6 +191,11 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); +void kthread_park_complete(struct task_struct *k) +{ + complete(&to_kthread(k)->parked); +} + static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ @@ -450,22 +452,15 @@ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = to_kthread(k); - clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); /* - * We clear the IS_PARKED bit here as we don't wait - * until the task has left the park code. So if we'd - * park before that happens we'd see the IS_PARKED bit - * which might be about to be cleared. + * Newly created kthread was parked when the CPU was offline. + * The binding was lost and we need to set it again. */ - if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) { - /* - * Newly created kthread was parked when the CPU was offline. - * The binding was lost and we need to set it again. - */ - if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) - __kthread_bind(k, kthread->cpu, TASK_PARKED); - wake_up_state(k, TASK_PARKED); - } + if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) + __kthread_bind(k, kthread->cpu, TASK_PARKED); + + clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + wake_up_state(k, TASK_PARKED); } EXPORT_SYMBOL_GPL(kthread_unpark); @@ -488,12 +483,13 @@ int kthread_park(struct task_struct *k) if (WARN_ON(k->flags & PF_EXITING)) return -ENOSYS; - if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) { - set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); - if (k != current) { - wake_up_process(k); - wait_for_completion(&kthread->parked); - } + if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags))) + return -EBUSY; + + set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + if (k != current) { + wake_up_process(k); + wait_for_completion(&kthread->parked); } return 0; diff --git a/kernel/module.c b/kernel/module.c index ce8066b88178..c9bea7f2b43e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3517,6 +3517,11 @@ static noinline int do_init_module(struct module *mod) * walking this with preempt disabled. In all the failure paths, we * call synchronize_sched(), but we don't want to slow down the success * path, so use actual RCU here. + * Note that module_alloc() on most architectures creates W+X page + * mappings which won't be cleaned up until do_free_init() runs. Any + * code such as mark_rodata_ro() which depends on those mappings to + * be cleaned up needs to sync with the queued work - ie + * rcu_barrier_sched() */ call_rcu_sched(&freeinit->rcu, do_free_init); mutex_unlock(&module_mutex); diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 6be6c575b6cd..2d4ff5353ded 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -2,6 +2,7 @@ /* * Auto-group scheduling implementation: */ +#include <linux/nospec.h> #include "sched.h" unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1; @@ -209,7 +210,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) static unsigned long next = INITIAL_JIFFIES; struct autogroup *ag; unsigned long shares; - int err; + int err, idx; if (nice < MIN_NICE || nice > MAX_NICE) return -EINVAL; @@ -227,7 +228,9 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) next = HZ / 10 + jiffies; ag = autogroup_task_get(p); - shares = scale_load(sched_prio_to_weight[nice + 20]); + + idx = array_index_nospec(nice + 20, 40); + shares = scale_load(sched_prio_to_weight[idx]); down_write(&ag->lock); err = sched_group_set_shares(ag->tg, shares); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5e10aaeebfcc..092f7c4de903 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7,6 +7,9 @@ */ #include "sched.h" +#include <linux/kthread.h> +#include <linux/nospec.h> + #include <asm/switch_to.h> #include <asm/tlb.h> @@ -2718,20 +2721,28 @@ static struct rq *finish_task_switch(struct task_struct *prev) membarrier_mm_sync_core_before_usermode(mm); mmdrop(mm); } - if (unlikely(prev_state == TASK_DEAD)) { - if (prev->sched_class->task_dead) - prev->sched_class->task_dead(prev); + if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) { + switch (prev_state) { + case TASK_DEAD: + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); + + /* Task is done with its stack. */ + put_task_stack(prev); - /* Task is done with its stack. */ - put_task_stack(prev); + put_task_struct(prev); + break; - put_task_struct(prev); + case TASK_PARKED: + kthread_park_complete(prev); + break; + } } tick_nohz_task_switch(); @@ -3498,23 +3509,8 @@ static void __sched notrace __schedule(bool preempt) void __noreturn do_task_dead(void) { - /* - * The setting of TASK_RUNNING by try_to_wake_up() may be delayed - * when the following two conditions become true. - * - There is race condition of mmap_sem (It is acquired by - * exit_mm()), and - * - SMI occurs before setting TASK_RUNINNG. - * (or hypervisor of virtual machine switches to other guest) - * As a result, we may become TASK_RUNNING after becoming TASK_DEAD - * - * To avoid it, we have to wait for releasing tsk->pi_lock which - * is held by try_to_wake_up() - */ - raw_spin_lock_irq(¤t->pi_lock); - raw_spin_unlock_irq(¤t->pi_lock); - /* Causes final put_task_struct in finish_task_switch(): */ - __set_current_state(TASK_DEAD); + set_special_state(TASK_DEAD); /* Tell freezer to ignore us: */ current->flags |= PF_NOFREEZE; @@ -6928,11 +6924,15 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 nice) { unsigned long weight; + int idx; if (nice < MIN_NICE || nice > MAX_NICE) return -ERANGE; - weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO]; + idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO; + idx = array_index_nospec(idx, 40); + weight = sched_prio_to_weight[idx]; + return sched_group_set_shares(css_tg(css), scale_load(weight)); } #endif diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index d2c6083304b4..e13df951aca7 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -305,7 +305,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, * Do not reduce the frequency if the CPU has not been idle * recently, as the reduction is likely to be premature then. */ - if (busy && next_f < sg_policy->next_freq) { + if (busy && next_f < sg_policy->next_freq && + sg_policy->next_freq != UINT_MAX) { next_f = sg_policy->next_freq; /* Reset cached freq as next_freq has changed */ @@ -396,19 +397,6 @@ static void sugov_irq_work(struct irq_work *irq_work) sg_policy = container_of(irq_work, struct sugov_policy, irq_work); - /* - * For RT tasks, the schedutil governor shoots the frequency to maximum. - * Special care must be taken to ensure that this kthread doesn't result - * in the same behavior. - * - * This is (mostly) guaranteed by the work_in_progress flag. The flag is - * updated only at the end of the sugov_work() function and before that - * the schedutil governor rejects all other frequency scaling requests. - * - * There is a very rare case though, where the RT thread yields right - * after the work_in_progress flag is cleared. The effects of that are - * neglected for now. - */ kthread_queue_work(&sg_policy->worker, &sg_policy->work); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 54dc31e7ab9b..79f574dba096 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1854,7 +1854,6 @@ static int task_numa_migrate(struct task_struct *p) static void numa_migrate_preferred(struct task_struct *p) { unsigned long interval = HZ; - unsigned long numa_migrate_retry; /* This task has no NUMA fault statistics yet */ if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) @@ -1862,18 +1861,7 @@ static void numa_migrate_preferred(struct task_struct *p) /* Periodically retry migrating the task to the preferred node */ interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16); - numa_migrate_retry = jiffies + interval; - - /* - * Check that the new retry threshold is after the current one. If - * the retry is in the future, it implies that wake_affine has - * temporarily asked NUMA balancing to backoff from placement. - */ - if (numa_migrate_retry > p->numa_migrate_retry) - return; - - /* Safe to try placing the task on the preferred node */ - p->numa_migrate_retry = numa_migrate_retry; + p->numa_migrate_retry = jiffies + interval; /* Success if task is already running on preferred CPU */ if (task_node(p) == p->numa_preferred_nid) @@ -5922,48 +5910,6 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits; } -#ifdef CONFIG_NUMA_BALANCING -static void -update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target) -{ - unsigned long interval; - - if (!static_branch_likely(&sched_numa_balancing)) - return; - - /* If balancing has no preference then continue gathering data */ - if (p->numa_preferred_nid == -1) - return; - - /* - * If the wakeup is not affecting locality then it is neutral from - * the perspective of NUMA balacing so continue gathering data. - */ - if (cpu_to_node(prev_cpu) == cpu_to_node(target)) - return; - - /* - * Temporarily prevent NUMA balancing trying to place waker/wakee after - * wakee has been moved by wake_affine. This will potentially allow - * related tasks to converge and update their data placement. The - * 4 * numa_scan_period is to allow the two-pass filter to migrate - * hot data to the wakers node. - */ - interval = max(sysctl_numa_balancing_scan_delay, - p->numa_scan_period << 2); - p->numa_migrate_retry = jiffies + msecs_to_jiffies(interval); - - interval = max(sysctl_numa_balancing_scan_delay, - current->numa_scan_period << 2); - current->numa_migrate_retry = jiffies + msecs_to_jiffies(interval); -} -#else -static void -update_wa_numa_placement(struct task_struct *p, int prev_cpu, int target) -{ -} -#endif - static int wake_affine(struct sched_domain *sd, struct task_struct *p, int this_cpu, int prev_cpu, int sync) { @@ -5979,7 +5925,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, if (target == nr_cpumask_bits) return prev_cpu; - update_wa_numa_placement(p, prev_cpu, target); schedstat_inc(sd->ttwu_move_affine); schedstat_inc(p->se.statistics.nr_wakeups_affine); return target; @@ -9847,6 +9792,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) if (curr_cost > this_rq->max_idle_balance_cost) this_rq->max_idle_balance_cost = curr_cost; +out: /* * While browsing the domains, we released the rq lock, a task could * have been enqueued in the meantime. Since we're not going idle, @@ -9855,7 +9801,6 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) if (this_rq->cfs.h_nr_running && !pulled_task) pulled_task = 1; -out: /* Move the next balance forward */ if (time_after(this_rq->next_balance, next_balance)) this_rq->next_balance = next_balance; diff --git a/kernel/signal.c b/kernel/signal.c index d4ccea599692..9c33163a6165 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1961,14 +1961,27 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) return; } + set_special_state(TASK_TRACED); + /* * We're committing to trapping. TRACED should be visible before * TRAPPING is cleared; otherwise, the tracer might fail do_wait(). * Also, transition to TRACED and updates to ->jobctl should be * atomic with respect to siglock and should be done after the arch * hook as siglock is released and regrabbed across it. + * + * TRACER TRACEE + * + * ptrace_attach() + * [L] wait_on_bit(JOBCTL_TRAPPING) [S] set_special_state(TRACED) + * do_wait() + * set_current_state() smp_wmb(); + * ptrace_do_wait() + * wait_task_stopped() + * task_stopped_code() + * [L] task_is_traced() [S] task_clear_jobctl_trapping(); */ - set_current_state(TASK_TRACED); + smp_wmb(); current->last_siginfo = info; current->exit_code = exit_code; @@ -2176,7 +2189,7 @@ static bool do_signal_stop(int signr) if (task_participate_group_stop(current)) notify = CLD_STOPPED; - __set_current_state(TASK_STOPPED); + set_special_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); /* diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index b7591261652d..64c0291b579c 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -21,6 +21,7 @@ #include <linux/smpboot.h> #include <linux/atomic.h> #include <linux/nmi.h> +#include <linux/sched/wake_q.h> /* * Structure to determine completion condition and record errors. May @@ -65,27 +66,31 @@ static void cpu_stop_signal_done(struct cpu_stop_done *done) } static void __cpu_stop_queue_work(struct cpu_stopper *stopper, - struct cpu_stop_work *work) + struct cpu_stop_work *work, + struct wake_q_head *wakeq) { list_add_tail(&work->list, &stopper->works); - wake_up_process(stopper->thread); + wake_q_add(wakeq, stopper->thread); } /* queue @work to @stopper. if offline, @work is completed immediately */ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + DEFINE_WAKE_Q(wakeq); unsigned long flags; bool enabled; spin_lock_irqsave(&stopper->lock, flags); enabled = stopper->enabled; if (enabled) - __cpu_stop_queue_work(stopper, work); + __cpu_stop_queue_work(stopper, work, &wakeq); else if (work->done) cpu_stop_signal_done(work->done); spin_unlock_irqrestore(&stopper->lock, flags); + wake_up_q(&wakeq); + return enabled; } @@ -229,6 +234,7 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, { struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1); struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2); + DEFINE_WAKE_Q(wakeq); int err; retry: spin_lock_irq(&stopper1->lock); @@ -252,8 +258,8 @@ retry: goto unlock; err = 0; - __cpu_stop_queue_work(stopper1, work1); - __cpu_stop_queue_work(stopper2, work2); + __cpu_stop_queue_work(stopper1, work1, &wakeq); + __cpu_stop_queue_work(stopper2, work2, &wakeq); unlock: spin_unlock(&stopper2->lock); spin_unlock_irq(&stopper1->lock); @@ -263,6 +269,9 @@ unlock: cpu_relax(); goto retry; } + + wake_up_q(&wakeq); + return err; } /** diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 1f951b3df60c..7d306b74230f 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -762,6 +762,9 @@ static int regex_match_full(char *str, struct regex *r, int len) static int regex_match_front(char *str, struct regex *r, int len) { + if (len < r->len) + return 0; + if (strncmp(str, r->pattern, r->len) == 0) return 1; return 0; diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index 5985a25e6cbc..5367ffa5c18f 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -132,7 +132,12 @@ static int __init find_bit_test(void) test_find_next_bit(bitmap, BITMAP_LEN); test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); - test_find_first_bit(bitmap, BITMAP_LEN); + + /* + * test_find_first_bit() may take some time, so + * traverse only part of bitmap to avoid soft lockup. + */ + test_find_first_bit(bitmap, BITMAP_LEN / 10); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); pr_err("\nStart testing find_bit() with sparse bitmap\n"); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index da9e10c827df..43e0cbedc3a0 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1612,11 +1612,9 @@ static void set_iter_tags(struct radix_tree_iter *iter, static void __rcu **skip_siblings(struct radix_tree_node **nodep, void __rcu **slot, struct radix_tree_iter *iter) { - void *sib = node_to_entry(slot - 1); - while (iter->index < iter->next_index) { *nodep = rcu_dereference_raw(*slot); - if (*nodep && *nodep != sib) + if (*nodep && !is_sibling_entry(iter->node, *nodep)) return slot; slot++; iter->index = __radix_tree_iter_add(iter, 1); @@ -1631,7 +1629,7 @@ void __rcu **__radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; - struct radix_tree_node *node = rcu_dereference_raw(*slot); + struct radix_tree_node *node; slot = skip_siblings(&node, slot, iter); diff --git a/lib/swiotlb.c b/lib/swiotlb.c index 12fbaa445637..cc640588f145 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -714,7 +714,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, phys_addr = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start), - 0, size, DMA_FROM_DEVICE, 0); + 0, size, DMA_FROM_DEVICE, attrs); if (phys_addr == SWIOTLB_MAP_ERROR) goto out_warn; diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index de16f7869fb1..6cd7d0740005 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -331,23 +331,32 @@ static void noinline __init test_mem_optimisations(void) unsigned int start, nbits; for (start = 0; start < 1024; start += 8) { - memset(bmap1, 0x5a, sizeof(bmap1)); - memset(bmap2, 0x5a, sizeof(bmap2)); for (nbits = 0; nbits < 1024 - start; nbits += 8) { + memset(bmap1, 0x5a, sizeof(bmap1)); + memset(bmap2, 0x5a, sizeof(bmap2)); + bitmap_set(bmap1, start, nbits); __bitmap_set(bmap2, start, nbits); - if (!bitmap_equal(bmap1, bmap2, 1024)) + if (!bitmap_equal(bmap1, bmap2, 1024)) { printk("set not equal %d %d\n", start, nbits); - if (!__bitmap_equal(bmap1, bmap2, 1024)) + failed_tests++; + } + if (!__bitmap_equal(bmap1, bmap2, 1024)) { printk("set not __equal %d %d\n", start, nbits); + failed_tests++; + } bitmap_clear(bmap1, start, nbits); __bitmap_clear(bmap2, start, nbits); - if (!bitmap_equal(bmap1, bmap2, 1024)) + if (!bitmap_equal(bmap1, bmap2, 1024)) { printk("clear not equal %d %d\n", start, nbits); - if (!__bitmap_equal(bmap1, bmap2, 1024)) + failed_tests++; + } + if (!__bitmap_equal(bmap1, bmap2, 1024)) { printk("clear not __equal %d %d\n", start, nbits); + failed_tests++; + } } } } diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 30c0cb8cc9bc..23920c5ff728 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -1669,19 +1669,22 @@ char *pointer_string(char *buf, char *end, const void *ptr, return number(buf, end, (unsigned long int)ptr, spec); } -static bool have_filled_random_ptr_key __read_mostly; +static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); static siphash_key_t ptr_key __read_mostly; -static void fill_random_ptr_key(struct random_ready_callback *unused) +static void enable_ptr_key_workfn(struct work_struct *work) { get_random_bytes(&ptr_key, sizeof(ptr_key)); - /* - * have_filled_random_ptr_key==true is dependent on get_random_bytes(). - * ptr_to_id() needs to see have_filled_random_ptr_key==true - * after get_random_bytes() returns. - */ - smp_mb(); - WRITE_ONCE(have_filled_random_ptr_key, true); + /* Needs to run from preemptible context */ + static_branch_disable(¬_filled_random_ptr_key); +} + +static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); + +static void fill_random_ptr_key(struct random_ready_callback *unused) +{ + /* This may be in an interrupt handler. */ + queue_work(system_unbound_wq, &enable_ptr_key_work); } static struct random_ready_callback random_ready = { @@ -1695,7 +1698,8 @@ static int __init initialize_ptr_random(void) if (!ret) { return 0; } else if (ret == -EALREADY) { - fill_random_ptr_key(&random_ready); + /* This is in preemptible context */ + enable_ptr_key_workfn(&enable_ptr_key_work); return 0; } @@ -1709,7 +1713,7 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec) unsigned long hashval; const int default_width = 2 * sizeof(ptr); - if (unlikely(!have_filled_random_ptr_key)) { + if (static_branch_unlikely(¬_filled_random_ptr_key)) { spec.field_width = default_width; /* string length must be less than default_width */ return string(buf, end, "(ptrval)", spec); diff --git a/mm/Kconfig b/mm/Kconfig index d5004d82a1d6..e14c01513bfd 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -636,6 +636,7 @@ config DEFERRED_STRUCT_PAGE_INIT default n depends on NO_BOOTMEM depends on !FLATMEM + depends on !NEED_PER_CPU_KM help Ordinarily all struct pages are initialised during early boot in a single thread. On very large machines this can take a considerable @@ -544,6 +544,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; + if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma)) + return -EFAULT; + if (write) { if (!(vm_flags & VM_WRITE)) { if (!(gup_flags & FOLL_FORCE)) diff --git a/mm/migrate.c b/mm/migrate.c index 568433023831..8c0af0f7cab1 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -528,14 +528,12 @@ int migrate_page_move_mapping(struct address_space *mapping, int i; int index = page_index(page); - for (i = 0; i < HPAGE_PMD_NR; i++) { + for (i = 1; i < HPAGE_PMD_NR; i++) { pslot = radix_tree_lookup_slot(&mapping->i_pages, index + i); radix_tree_replace_slot(&mapping->i_pages, pslot, newpage + i); } - } else { - radix_tree_replace_slot(&mapping->i_pages, pslot, newpage); } /* diff --git a/mm/mmap.c b/mm/mmap.c index 9d5968d1e8e3..78e14facdb6e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1324,6 +1324,35 @@ static inline int mlock_future_check(struct mm_struct *mm, return 0; } +static inline u64 file_mmap_size_max(struct file *file, struct inode *inode) +{ + if (S_ISREG(inode->i_mode)) + return inode->i_sb->s_maxbytes; + + if (S_ISBLK(inode->i_mode)) + return MAX_LFS_FILESIZE; + + /* Special "we do even unsigned file positions" case */ + if (file->f_mode & FMODE_UNSIGNED_OFFSET) + return 0; + + /* Yes, random drivers might want more. But I'm tired of buggy drivers */ + return ULONG_MAX; +} + +static inline bool file_mmap_ok(struct file *file, struct inode *inode, + unsigned long pgoff, unsigned long len) +{ + u64 maxsize = file_mmap_size_max(file, inode); + + if (maxsize && len > maxsize) + return false; + maxsize -= len; + if (pgoff > maxsize >> PAGE_SHIFT) + return false; + return true; +} + /* * The caller must hold down_write(¤t->mm->mmap_sem). */ @@ -1409,6 +1438,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr, struct inode *inode = file_inode(file); unsigned long flags_mask; + if (!file_mmap_ok(file, inode, pgoff, len)) + return -EOVERFLOW; + flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags; switch (flags & MAP_TYPE) { @@ -3024,6 +3056,32 @@ void exit_mmap(struct mm_struct *mm) /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); + if (unlikely(mm_is_oom_victim(mm))) { + /* + * Manually reap the mm to free as much memory as possible. + * Then, as the oom reaper does, set MMF_OOM_SKIP to disregard + * this mm from further consideration. Taking mm->mmap_sem for + * write after setting MMF_OOM_SKIP will guarantee that the oom + * reaper will not run on this mm again after mmap_sem is + * dropped. + * + * Nothing can be holding mm->mmap_sem here and the above call + * to mmu_notifier_release(mm) ensures mmu notifier callbacks in + * __oom_reap_task_mm() will not block. + * + * This needs to be done before calling munlock_vma_pages_all(), + * which clears VM_LOCKED, otherwise the oom reaper cannot + * reliably test it. + */ + mutex_lock(&oom_lock); + __oom_reap_task_mm(mm); + mutex_unlock(&oom_lock); + + set_bit(MMF_OOM_SKIP, &mm->flags); + down_write(&mm->mmap_sem); + up_write(&mm->mmap_sem); + } + if (mm->locked_vm) { vma = mm->mmap; while (vma) { @@ -3045,24 +3103,6 @@ void exit_mmap(struct mm_struct *mm) /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - - if (unlikely(mm_is_oom_victim(mm))) { - /* - * Wait for oom_reap_task() to stop working on this - * mm. Because MMF_OOM_SKIP is already set before - * calling down_read(), oom_reap_task() will not run - * on this "mm" post up_write(). - * - * mm_is_oom_victim() cannot be set from under us - * either because victim->mm is already set to NULL - * under task_lock before calling mmput and oom_mm is - * set not NULL by the OOM killer only if victim->mm - * is found not NULL while holding the task_lock. - */ - set_bit(MMF_OOM_SKIP, &mm->flags); - down_write(&mm->mmap_sem); - up_write(&mm->mmap_sem); - } free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index ff992fa8760a..8ba6cb88cf58 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -469,7 +469,6 @@ bool process_shares_mm(struct task_struct *p, struct mm_struct *mm) return false; } - #ifdef CONFIG_MMU /* * OOM Reaper kernel thread which tries to reap the memory used by the OOM @@ -480,16 +479,54 @@ static DECLARE_WAIT_QUEUE_HEAD(oom_reaper_wait); static struct task_struct *oom_reaper_list; static DEFINE_SPINLOCK(oom_reaper_lock); -static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) +void __oom_reap_task_mm(struct mm_struct *mm) { - struct mmu_gather tlb; struct vm_area_struct *vma; + + /* + * Tell all users of get_user/copy_from_user etc... that the content + * is no longer stable. No barriers really needed because unmapping + * should imply barriers already and the reader would hit a page fault + * if it stumbled over a reaped memory. + */ + set_bit(MMF_UNSTABLE, &mm->flags); + + for (vma = mm->mmap ; vma; vma = vma->vm_next) { + if (!can_madv_dontneed_vma(vma)) + continue; + + /* + * Only anonymous pages have a good chance to be dropped + * without additional steps which we cannot afford as we + * are OOM already. + * + * We do not even care about fs backed pages because all + * which are reclaimable have already been reclaimed and + * we do not want to block exit_mmap by keeping mm ref + * count elevated without a good reason. + */ + if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { + const unsigned long start = vma->vm_start; + const unsigned long end = vma->vm_end; + struct mmu_gather tlb; + + tlb_gather_mmu(&tlb, mm, start, end); + mmu_notifier_invalidate_range_start(mm, start, end); + unmap_page_range(&tlb, vma, start, end, NULL); + mmu_notifier_invalidate_range_end(mm, start, end); + tlb_finish_mmu(&tlb, start, end); + } + } +} + +static bool oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) +{ bool ret = true; /* * We have to make sure to not race with the victim exit path * and cause premature new oom victim selection: - * __oom_reap_task_mm exit_mm + * oom_reap_task_mm exit_mm * mmget_not_zero * mmput * atomic_dec_and_test @@ -534,39 +571,8 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm) trace_start_task_reaping(tsk->pid); - /* - * Tell all users of get_user/copy_from_user etc... that the content - * is no longer stable. No barriers really needed because unmapping - * should imply barriers already and the reader would hit a page fault - * if it stumbled over a reaped memory. - */ - set_bit(MMF_UNSTABLE, &mm->flags); - - for (vma = mm->mmap ; vma; vma = vma->vm_next) { - if (!can_madv_dontneed_vma(vma)) - continue; + __oom_reap_task_mm(mm); - /* - * Only anonymous pages have a good chance to be dropped - * without additional steps which we cannot afford as we - * are OOM already. - * - * We do not even care about fs backed pages because all - * which are reclaimable have already been reclaimed and - * we do not want to block exit_mmap by keeping mm ref - * count elevated without a good reason. - */ - if (vma_is_anonymous(vma) || !(vma->vm_flags & VM_SHARED)) { - const unsigned long start = vma->vm_start; - const unsigned long end = vma->vm_end; - - tlb_gather_mmu(&tlb, mm, start, end); - mmu_notifier_invalidate_range_start(mm, start, end); - unmap_page_range(&tlb, vma, start, end, NULL); - mmu_notifier_invalidate_range_end(mm, start, end); - tlb_finish_mmu(&tlb, start, end); - } - } pr_info("oom_reaper: reaped process %d (%s), now anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(tsk), tsk->comm, K(get_mm_counter(mm, MM_ANONPAGES)), @@ -587,14 +593,13 @@ static void oom_reap_task(struct task_struct *tsk) struct mm_struct *mm = tsk->signal->oom_mm; /* Retry the down_read_trylock(mmap_sem) a few times */ - while (attempts++ < MAX_OOM_REAP_RETRIES && !__oom_reap_task_mm(tsk, mm)) + while (attempts++ < MAX_OOM_REAP_RETRIES && !oom_reap_task_mm(tsk, mm)) schedule_timeout_idle(HZ/10); if (attempts <= MAX_OOM_REAP_RETRIES || test_bit(MMF_OOM_SKIP, &mm->flags)) goto done; - pr_info("oom_reaper: unable to reap pid:%d (%s)\n", task_pid_nr(tsk), tsk->comm); debug_show_all_locks(); diff --git a/mm/sparse.c b/mm/sparse.c index 62eef264a7bd..73dc2fcc0eab 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -629,7 +629,7 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn) unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - unsigned long section_nr = pfn_to_section_nr(start_pfn); + unsigned long section_nr = pfn_to_section_nr(pfn); struct mem_section *ms; /* diff --git a/mm/vmstat.c b/mm/vmstat.c index 536332e988b8..a2b9518980ce 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", - "nr_indirectly_reclaimable", + "", /* nr_indirectly_reclaimable */ /* enum writeback_stat_item counters */ "nr_dirty_threshold", @@ -1740,6 +1740,10 @@ static int vmstat_show(struct seq_file *m, void *arg) unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; + /* Skip hidden vmstat items. */ + if (*vmstat_text[off] == '\0') + return 0; + seq_puts(m, vmstat_text[off]); seq_put_decimal_ull(m, " ", *l); seq_putc(m, '\n'); diff --git a/mm/z3fold.c b/mm/z3fold.c index c0bca6153b95..4b366d181f35 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -144,7 +144,8 @@ enum z3fold_page_flags { PAGE_HEADLESS = 0, MIDDLE_CHUNK_MAPPED, NEEDS_COMPACTING, - PAGE_STALE + PAGE_STALE, + UNDER_RECLAIM }; /***************** @@ -173,6 +174,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page, clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); clear_bit(PAGE_STALE, &page->private); + clear_bit(UNDER_RECLAIM, &page->private); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); @@ -756,6 +758,10 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } + if (test_bit(UNDER_RECLAIM, &page->private)) { + z3fold_page_unlock(zhdr); + return; + } if (test_and_set_bit(NEEDS_COMPACTING, &page->private)) { z3fold_page_unlock(zhdr); return; @@ -840,6 +846,8 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); zhdr->cpu = -1; + set_bit(UNDER_RECLAIM, &page->private); + break; } list_del_init(&page->lru); @@ -887,25 +895,35 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) goto next; } next: - spin_lock(&pool->lock); if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { - spin_unlock(&pool->lock); free_z3fold_page(page); return 0; } - } else if (kref_put(&zhdr->refcount, release_z3fold_page)) { - atomic64_dec(&pool->pages_nr); + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); + spin_unlock(&pool->lock); + } else { + z3fold_page_lock(zhdr); + clear_bit(UNDER_RECLAIM, &page->private); + if (kref_put(&zhdr->refcount, + release_z3fold_page_locked)) { + atomic64_dec(&pool->pages_nr); + return 0; + } + /* + * if we are here, the page is still not completely + * free. Take the global pool lock then to be able + * to add it back to the lru list + */ + spin_lock(&pool->lock); + list_add(&page->lru, &pool->lru); spin_unlock(&pool->lock); - return 0; + z3fold_page_unlock(zhdr); } - /* - * Add to the beginning of LRU. - * Pool lock has to be kept here to ensure the page has - * not already been released - */ - list_add(&page->lru, &pool->lru); + /* We started off locked to we need to lock the pool back */ + spin_lock(&pool->lock); } spin_unlock(&pool->lock); return -EAGAIN; diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 38aa6345bdfa..b718db2085b2 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -16,7 +16,7 @@ #include <linux/module.h> /** - * p9_release_req_pages - Release pages after the transaction. + * p9_release_pages - Release pages after the transaction. */ void p9_release_pages(struct page **pages, int nr_pages) { diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 0cfba919d167..848969fe7979 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -1092,8 +1092,8 @@ static struct p9_trans_module p9_fd_trans = { }; /** - * p9_poll_proc - poll worker thread - * @a: thread state and arguments + * p9_poll_workfn - poll worker thread + * @work: work queue * * polls all v9fs transports for new events and queues the appropriate * work to the work queue diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 6d8e3031978f..3d414acb7015 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -68,8 +68,6 @@ * @pd: Protection Domain pointer * @qp: Queue Pair pointer * @cq: Completion Queue pointer - * @dm_mr: DMA Memory Region pointer - * @lkey: The local access only memory region key * @timeout: Number of uSecs to wait for connection management events * @privport: Whether a privileged port may be used * @port: The port to use @@ -632,7 +630,7 @@ static int p9_rdma_bind_privport(struct p9_trans_rdma *rdma) } /** - * trans_create_rdma - Transport method for creating atransport instance + * rdma_create_trans - Transport method for creating a transport instance * @client: client instance * @addr: IP address string * @args: Mount options string diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 3aa5a93ad107..4d0372263e5d 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -60,7 +60,6 @@ static atomic_t vp_pinned = ATOMIC_INIT(0); /** * struct virtio_chan - per-instance transport information - * @initialized: whether the channel is initialized * @inuse: whether the channel is in use * @lock: protects multiple elements within this structure * @client: client instance @@ -385,8 +384,8 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, * @uidata: user bffer that should be ued for zero copy read * @uodata: user buffer that shoud be user for zero copy write * @inlen: read buffer size - * @olen: write buffer size - * @hdrlen: reader header size, This is the size of response protocol data + * @outlen: write buffer size + * @in_hdr_len: reader header size, This is the size of response protocol data * */ static int diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 086a4abdfa7c..0f19960390a6 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -485,7 +485,7 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev, static int xen_9pfs_front_resume(struct xenbus_device *dev) { - dev_warn(&dev->dev, "suspsend/resume unsupported\n"); + dev_warn(&dev->dev, "suspend/resume unsupported\n"); return 0; } diff --git a/net/atm/lec.c b/net/atm/lec.c index 01d5d20a6eb1..3138a869b5c0 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -41,6 +41,9 @@ static unsigned char bridge_ula_lec[] = { 0x01, 0x80, 0xc2, 0x00, 0x00 }; #include <linux/module.h> #include <linux/init.h> +/* Hardening for Spectre-v1 */ +#include <linux/nospec.h> + #include "lec.h" #include "lec_arpc.h" #include "resources.h" @@ -687,8 +690,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg) bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc)); if (bytes_left != 0) pr_info("copy from user failed for %d bytes\n", bytes_left); - if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF || - !dev_lec[ioc_data.dev_num]) + if (ioc_data.dev_num < 0 || ioc_data.dev_num >= MAX_LEC_ITF) + return -EINVAL; + ioc_data.dev_num = array_index_nospec(ioc_data.dev_num, MAX_LEC_ITF); + if (!dev_lec[ioc_data.dev_num]) return -EINVAL; vpriv = kmalloc(sizeof(struct lec_vcc_priv), GFP_KERNEL); if (!vpriv) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index ea2a6c9fb7ce..d2667e5dddc3 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -157,10 +157,12 @@ static void ceph_osd_data_bio_init(struct ceph_osd_data *osd_data, #endif /* CONFIG_BLOCK */ static void ceph_osd_data_bvecs_init(struct ceph_osd_data *osd_data, - struct ceph_bvec_iter *bvec_pos) + struct ceph_bvec_iter *bvec_pos, + u32 num_bvecs) { osd_data->type = CEPH_OSD_DATA_TYPE_BVECS; osd_data->bvec_pos = *bvec_pos; + osd_data->num_bvecs = num_bvecs; } #define osd_req_op_data(oreq, whch, typ, fld) \ @@ -237,6 +239,22 @@ void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req, EXPORT_SYMBOL(osd_req_op_extent_osd_data_bio); #endif /* CONFIG_BLOCK */ +void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req, + unsigned int which, + struct bio_vec *bvecs, u32 num_bvecs, + u32 bytes) +{ + struct ceph_osd_data *osd_data; + struct ceph_bvec_iter it = { + .bvecs = bvecs, + .iter = { .bi_size = bytes }, + }; + + osd_data = osd_req_op_data(osd_req, which, extent, osd_data); + ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); +} +EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvecs); + void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, unsigned int which, struct ceph_bvec_iter *bvec_pos) @@ -244,7 +262,7 @@ void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req, struct ceph_osd_data *osd_data; osd_data = osd_req_op_data(osd_req, which, extent, osd_data); - ceph_osd_data_bvecs_init(osd_data, bvec_pos); + ceph_osd_data_bvecs_init(osd_data, bvec_pos, 0); } EXPORT_SYMBOL(osd_req_op_extent_osd_data_bvec_pos); @@ -287,7 +305,8 @@ EXPORT_SYMBOL(osd_req_op_cls_request_data_pages); void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, unsigned int which, - struct bio_vec *bvecs, u32 bytes) + struct bio_vec *bvecs, u32 num_bvecs, + u32 bytes) { struct ceph_osd_data *osd_data; struct ceph_bvec_iter it = { @@ -296,7 +315,7 @@ void osd_req_op_cls_request_data_bvecs(struct ceph_osd_request *osd_req, }; osd_data = osd_req_op_data(osd_req, which, cls, request_data); - ceph_osd_data_bvecs_init(osd_data, &it); + ceph_osd_data_bvecs_init(osd_data, &it, num_bvecs); osd_req->r_ops[which].cls.indata_len += bytes; osd_req->r_ops[which].indata_len += bytes; } diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h index b8d95cb71c25..44a7e16bf3b5 100644 --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -20,8 +20,8 @@ typedef unsigned __bitwise lowpan_rx_result; struct frag_lowpan_compare_key { u16 tag; u16 d_size; - const struct ieee802154_addr src; - const struct ieee802154_addr dst; + struct ieee802154_addr src; + struct ieee802154_addr dst; }; /* Equivalent of ipv4 struct ipq diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 1790b65944b3..2cc224106b69 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -75,14 +75,14 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb, { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); - struct frag_lowpan_compare_key key = { - .tag = cb->d_tag, - .d_size = cb->d_size, - .src = *src, - .dst = *dst, - }; + struct frag_lowpan_compare_key key = {}; struct inet_frag_queue *q; + key.tag = cb->d_tag; + key.d_size = cb->d_size; + key.src = *src; + key.dst = *dst; + q = inet_frag_find(&ieee802154_lowpan->frags, &key); if (!q) return NULL; @@ -372,7 +372,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); - struct ieee802154_hdr hdr; + struct ieee802154_hdr hdr = {}; int err; if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05e47d777009..56a010622f70 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); @@ -842,6 +844,7 @@ back_from_confirm: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1412a7baf0b9..29268efad247 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1375,6 +1375,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; + fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 24b5c59b1c53..b61a770884fa 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -401,9 +401,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } @@ -952,8 +952,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; connected = 0; } @@ -1074,6 +1076,7 @@ do_append_data: out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 6794ddf0547c..11e4e80cf7e9 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -34,16 +34,15 @@ config IPV6_ROUTE_INFO bool "IPv6: Route Information (RFC 4191) support" depends on IPV6_ROUTER_PREF ---help--- - This is experimental support of Route Information. + Support of Route Information. If unsure, say N. config IPV6_OPTIMISTIC_DAD bool "IPv6: Enable RFC 4429 Optimistic DAD" ---help--- - This is experimental support for optimistic Duplicate - Address Detection. It allows for autoconfigured addresses - to be used more quickly. + Support for optimistic Duplicate Address Detection. It allows for + autoconfigured addresses to be used more quickly. If unsure, say N. @@ -280,7 +279,7 @@ config IPV6_MROUTE depends on IPV6 select IP_MROUTE_COMMON ---help--- - Experimental support for IPv6 multicast forwarding. + Support for IPv6 multicast forwarding. If unsure, say N. config IPV6_MROUTE_MULTIPLE_TABLES diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index c214ffec02f0..ca957dd93a29 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -669,7 +669,7 @@ static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) else mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr); - dev->mtu = max_t(int, mtu, IPV6_MIN_MTU); + dev->mtu = max_t(int, mtu, IPV4_MIN_MTU); } /** @@ -881,7 +881,7 @@ static void vti6_dev_setup(struct net_device *dev) dev->priv_destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; - dev->min_mtu = IPV6_MIN_MTU; + dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 4ec76a87aeb8..ea0730028e5d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -148,9 +148,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score++; } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f85f0d7480ac..4a46df8441c9 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -341,6 +341,9 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; + xfrm_state_flush(net, IPSEC_PROTO_ANY, false); + xfrm_flush_gc(); + for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 7e2e7188e7f4..e62e52e8f141 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -437,6 +437,24 @@ static int verify_address_len(const void *p) return 0; } +static inline int sadb_key_len(const struct sadb_key *key) +{ + int key_bytes = DIV_ROUND_UP(key->sadb_key_bits, 8); + + return DIV_ROUND_UP(sizeof(struct sadb_key) + key_bytes, + sizeof(uint64_t)); +} + +static int verify_key_len(const void *p) +{ + const struct sadb_key *key = p; + + if (sadb_key_len(key) > key->sadb_key_len) + return -EINVAL; + + return 0; +} + static inline int pfkey_sec_ctx_len(const struct sadb_x_sec_ctx *sec_ctx) { return DIV_ROUND_UP(sizeof(struct sadb_x_sec_ctx) + @@ -533,16 +551,25 @@ static int parse_exthdrs(struct sk_buff *skb, const struct sadb_msg *hdr, void * return -EINVAL; if (ext_hdrs[ext_type-1] != NULL) return -EINVAL; - if (ext_type == SADB_EXT_ADDRESS_SRC || - ext_type == SADB_EXT_ADDRESS_DST || - ext_type == SADB_EXT_ADDRESS_PROXY || - ext_type == SADB_X_EXT_NAT_T_OA) { + switch (ext_type) { + case SADB_EXT_ADDRESS_SRC: + case SADB_EXT_ADDRESS_DST: + case SADB_EXT_ADDRESS_PROXY: + case SADB_X_EXT_NAT_T_OA: if (verify_address_len(p)) return -EINVAL; - } - if (ext_type == SADB_X_EXT_SEC_CTX) { + break; + case SADB_X_EXT_SEC_CTX: if (verify_sec_ctx_len(p)) return -EINVAL; + break; + case SADB_EXT_KEY_AUTH: + case SADB_EXT_KEY_ENCRYPT: + if (verify_key_len(p)) + return -EINVAL; + break; + default: + break; } ext_hdrs[ext_type-1] = (void *) p; } @@ -1104,14 +1131,12 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (key != NULL && sa->sadb_sa_auth != SADB_X_AALG_NULL && - ((key->sadb_key_bits+7) / 8 == 0 || - (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t))) + key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); key = ext_hdrs[SADB_EXT_KEY_ENCRYPT-1]; if (key != NULL && sa->sadb_sa_encrypt != SADB_EALG_NULL && - ((key->sadb_key_bits+7) / 8 == 0 || - (key->sadb_key_bits+7) / 8 > key->sadb_key_len * sizeof(uint64_t))) + key->sadb_key_bits == 0) return ERR_PTR(-EINVAL); x = xfrm_state_alloc(net); diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index cb80ebb38311..1beeea9549fa 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -930,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (size > llc->dev->mtu) size = llc->dev->mtu; copied = size - hdrlen; + rc = -EINVAL; + if (copied < 0) + goto release; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 595c662a61e8..ac4295296514 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -8,6 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -970,6 +971,9 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, sta->ampdu_mlme.addba_req_num[tid] = 0; + tid_tx->timeout = + le16_to_cpu(mgmt->u.action.u.addba_resp.timeout); + if (tid_tx->timeout) { mod_timer(&tid_tx->session_timer, TU_TO_EXP_TIME(tid_tx->timeout)); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 69449db7e283..233068756502 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -36,6 +36,7 @@ #define IEEE80211_AUTH_TIMEOUT (HZ / 5) #define IEEE80211_AUTH_TIMEOUT_LONG (HZ / 2) #define IEEE80211_AUTH_TIMEOUT_SHORT (HZ / 10) +#define IEEE80211_AUTH_TIMEOUT_SAE (HZ * 2) #define IEEE80211_AUTH_MAX_TRIES 3 #define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5) #define IEEE80211_ASSOC_TIMEOUT (HZ / 5) @@ -1787,7 +1788,7 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local, params[ac].acm = acm; params[ac].uapsd = uapsd; - if (params->cw_min == 0 || + if (params[ac].cw_min == 0 || params[ac].cw_min > params[ac].cw_max) { sdata_info(sdata, "AP has invalid WMM params (CWmin/max=%d/%d for ACI %d), using defaults\n", @@ -3814,16 +3815,19 @@ static int ieee80211_auth(struct ieee80211_sub_if_data *sdata) tx_flags); if (tx_flags == 0) { - auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; - auth_data->timeout_started = true; - run_again(sdata, auth_data->timeout); + if (auth_data->algorithm == WLAN_AUTH_SAE) + auth_data->timeout = jiffies + + IEEE80211_AUTH_TIMEOUT_SAE; + else + auth_data->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; } else { auth_data->timeout = round_jiffies_up(jiffies + IEEE80211_AUTH_TIMEOUT_LONG); - auth_data->timeout_started = true; - run_again(sdata, auth_data->timeout); } + auth_data->timeout_started = true; + run_again(sdata, auth_data->timeout); + return 0; } @@ -3894,8 +3898,15 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) ifmgd->status_received = false; if (ifmgd->auth_data && ieee80211_is_auth(fc)) { if (status_acked) { - ifmgd->auth_data->timeout = - jiffies + IEEE80211_AUTH_TIMEOUT_SHORT; + if (ifmgd->auth_data->algorithm == + WLAN_AUTH_SAE) + ifmgd->auth_data->timeout = + jiffies + + IEEE80211_AUTH_TIMEOUT_SAE; + else + ifmgd->auth_data->timeout = + jiffies + + IEEE80211_AUTH_TIMEOUT_SHORT; run_again(sdata, ifmgd->auth_data->timeout); } else { ifmgd->auth_data->timeout = jiffies - 1; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 535de3161a78..05a265cd573d 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4,6 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1135,7 +1136,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, } /* reset session timer */ - if (reset_agg_timer && tid_tx->timeout) + if (reset_agg_timer) tid_tx->last_tx = jiffies; return queued; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 55342c4d5cec..2e2dd88fc79f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2606,13 +2606,13 @@ static int netlink_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, - "sk Eth Pid Groups " - "Rmem Wmem Dump Locks Drops Inode\n"); + "sk Eth Pid Groups " + "Rmem Wmem Dump Locks Drops Inode\n"); } else { struct sock *s = v; struct netlink_sock *nlk = nlk_sk(s); - seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n", + seq_printf(seq, "%pK %-3d %-10u %08x %-8d %-8d %-5d %-8d %-8d %-8lu\n", s, s->sk_protocol, nlk->portid, diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index d7da99a0b0b8..9696ef96b719 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -57,6 +57,8 @@ int nsh_pop(struct sk_buff *skb) return -ENOMEM; nh = (struct nshhdr *)(skb->data); length = nsh_hdr_len(nh); + if (length < NSH_BASE_HDR_LEN) + return -EINVAL; inner_proto = tun_p_to_eth_p(nh->np); if (!pskb_may_pull(skb, length)) return -ENOMEM; @@ -90,6 +92,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) goto out; nsh_len = nsh_hdr_len(nsh_hdr(skb)); + if (nsh_len < NSH_BASE_HDR_LEN) + goto out; if (unlikely(!pskb_may_pull(skb, nsh_len))) goto out; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7322aa1e382e..492ab0c36f7c 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1712,13 +1712,10 @@ static void nlattr_set(struct nlattr *attr, u8 val, /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) { - if (tbl[nla_type(nla)].next) - tbl = tbl[nla_type(nla)].next; - nlattr_set(nla, val, tbl); - } else { + if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) + nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl); + else memset(nla_data(nla), val, nla_len(nla)); - } if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 41bd496531d4..00192a996be0 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -137,13 +137,18 @@ static int rfkill_gpio_probe(struct platform_device *pdev) ret = rfkill_register(rfkill->rfkill_dev); if (ret < 0) - return ret; + goto err_destroy; platform_set_drvdata(pdev, rfkill); dev_info(&pdev->dev, "%s device registered.\n", rfkill->name); return 0; + +err_destroy: + rfkill_destroy(rfkill->rfkill_dev); + + return ret; } static int rfkill_gpio_remove(struct platform_device *pdev) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 9a2c8e7c000e..2b463047dd7b 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -313,7 +313,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, memset(&cp, 0, sizeof(cp)); cp.local = rx->local; cp.key = key; - cp.security_level = 0; + cp.security_level = rx->min_sec_level; cp.exclusive = false; cp.upgrade = upgrade; cp.service_id = srx->srx_service; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 90d7079e0aa9..19975d2ca9a2 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -476,6 +476,7 @@ enum rxrpc_call_flag { RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ + RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ }; /* diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index c717152070df..1350f1be8037 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -40,7 +40,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, } __attribute__((packed)) pkt; struct rxrpc_ackinfo ack_info; size_t len; - int ioc; + int ret, ioc; u32 serial, mtu, call_id, padding; _enter("%d", conn->debug_id); @@ -135,10 +135,13 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, break; } - kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len); conn->params.peer->last_tx_at = ktime_get_real(); + if (ret < 0) + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_call_final_resend); + _leave(""); - return; } /* @@ -236,6 +239,8 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_conn_abort); _debug("sendmsg failed: %d", ret); return -EAGAIN; } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 0410d2277ca2..b5fd6381313d 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -971,7 +971,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, if (timo) { unsigned long now = jiffies, expect_rx_by; - expect_rx_by = jiffies + timo; + expect_rx_by = now + timo; WRITE_ONCE(call->expect_rx_by, expect_rx_by); rxrpc_reduce_call_timer(call, expect_rx_by, now, rxrpc_timer_set_for_normal); diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 93b5d910b4a1..8325f1b86840 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -71,7 +71,8 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); if (ret < 0) - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(local->debug_id, 0, ret, + rxrpc_tx_fail_version_reply); _leave(""); } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 8b54e9531d52..b493e6b62740 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -134,22 +134,49 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) } } - /* we want to receive ICMP errors */ - opt = 1; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } + switch (local->srx.transport.family) { + case AF_INET: + /* we want to receive ICMP errors */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_RECVERR, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } - /* we want to set the don't fragment bit */ - opt = IP_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; + /* we want to set the don't fragment bit */ + opt = IP_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IP, IP_MTU_DISCOVER, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + break; + + case AF_INET6: + /* we want to receive ICMP errors */ + opt = 1; + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + + /* we want to set the don't fragment bit */ + opt = IPV6_PMTUDISC_DO; + ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, + (char *) &opt, sizeof(opt)); + if (ret < 0) { + _debug("setsockopt failed"); + goto error; + } + break; + + default: + BUG(); } /* set the socket up */ diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 7f1fc04775b3..f03de1c59ba3 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -210,6 +210,9 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (ping) call->ping_time = now; conn->params.peer->last_tx_at = ktime_get_real(); + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_ack); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -294,6 +297,10 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 1, sizeof(pkt)); conn->params.peer->last_tx_at = ktime_get_real(); + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_abort); + rxrpc_put_connection(conn); return ret; @@ -387,6 +394,9 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, conn->params.peer->last_tx_at = ktime_get_real(); up_read(&conn->params.local->defrag_sem); + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_data_nofrag); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -414,6 +424,17 @@ done: rxrpc_timer_set_for_lost_ack); } } + + if (sp->hdr.seq == 1 && + !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, + &call->flags)) { + unsigned long nowj = jiffies, expect_rx_by; + + expect_rx_by = nowj + call->next_rx_timo; + WRITE_ONCE(call->expect_rx_by, expect_rx_by); + rxrpc_reduce_call_timer(call, expect_rx_by, nowj, + rxrpc_timer_set_for_normal); + } } rxrpc_set_keepalive(call); @@ -465,6 +486,10 @@ send_fragmentable: #endif } + if (ret < 0) + trace_rxrpc_tx_fail(call->debug_id, serial, ret, + rxrpc_tx_fail_call_data_frag); + up_write(&conn->params.local->defrag_sem); goto done; } @@ -482,6 +507,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) struct kvec iov[2]; size_t size; __be32 code; + int ret; _enter("%d", local->debug_id); @@ -516,7 +542,10 @@ void rxrpc_reject_packets(struct rxrpc_local *local) whdr.flags ^= RXRPC_CLIENT_INITIATED; whdr.flags &= RXRPC_CLIENT_INITIATED; - kernel_sendmsg(local->socket, &msg, iov, 2, size); + ret = kernel_sendmsg(local->socket, &msg, iov, 2, size); + if (ret < 0) + trace_rxrpc_tx_fail(local->debug_id, 0, ret, + rxrpc_tx_fail_reject); } rxrpc_free_skb(skb, rxrpc_skb_rx_freed); @@ -567,7 +596,8 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len); if (ret < 0) - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(peer->debug_id, 0, ret, + rxrpc_tx_fail_version_keepalive); peer->last_tx_at = ktime_get_real(); _leave(""); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 78c2f95d1f22..0ed8b651cec2 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -28,39 +28,39 @@ static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); * Find the peer associated with an ICMP packet. */ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, - const struct sk_buff *skb) + const struct sk_buff *skb, + struct sockaddr_rxrpc *srx) { struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); - struct sockaddr_rxrpc srx; _enter(""); - memset(&srx, 0, sizeof(srx)); - srx.transport_type = local->srx.transport_type; - srx.transport_len = local->srx.transport_len; - srx.transport.family = local->srx.transport.family; + memset(srx, 0, sizeof(*srx)); + srx->transport_type = local->srx.transport_type; + srx->transport_len = local->srx.transport_len; + srx->transport.family = local->srx.transport.family; /* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice * versa? */ - switch (srx.transport.family) { + switch (srx->transport.family) { case AF_INET: - srx.transport.sin.sin_port = serr->port; + srx->transport.sin.sin_port = serr->port; switch (serr->ee.ee_origin) { case SO_EE_ORIGIN_ICMP: _net("Rx ICMP"); - memcpy(&srx.transport.sin.sin_addr, + memcpy(&srx->transport.sin.sin_addr, skb_network_header(skb) + serr->addr_offset, sizeof(struct in_addr)); break; case SO_EE_ORIGIN_ICMP6: _net("Rx ICMP6 on v4 sock"); - memcpy(&srx.transport.sin.sin_addr, + memcpy(&srx->transport.sin.sin_addr, skb_network_header(skb) + serr->addr_offset + 12, sizeof(struct in_addr)); break; default: - memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr, + memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr, sizeof(struct in_addr)); break; } @@ -68,25 +68,25 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, #ifdef CONFIG_AF_RXRPC_IPV6 case AF_INET6: - srx.transport.sin6.sin6_port = serr->port; + srx->transport.sin6.sin6_port = serr->port; switch (serr->ee.ee_origin) { case SO_EE_ORIGIN_ICMP6: _net("Rx ICMP6"); - memcpy(&srx.transport.sin6.sin6_addr, + memcpy(&srx->transport.sin6.sin6_addr, skb_network_header(skb) + serr->addr_offset, sizeof(struct in6_addr)); break; case SO_EE_ORIGIN_ICMP: _net("Rx ICMP on v6 sock"); - srx.transport.sin6.sin6_addr.s6_addr32[0] = 0; - srx.transport.sin6.sin6_addr.s6_addr32[1] = 0; - srx.transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); - memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12, + srx->transport.sin6.sin6_addr.s6_addr32[0] = 0; + srx->transport.sin6.sin6_addr.s6_addr32[1] = 0; + srx->transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff); + memcpy(srx->transport.sin6.sin6_addr.s6_addr + 12, skb_network_header(skb) + serr->addr_offset, sizeof(struct in_addr)); break; default: - memcpy(&srx.transport.sin6.sin6_addr, + memcpy(&srx->transport.sin6.sin6_addr, &ipv6_hdr(skb)->saddr, sizeof(struct in6_addr)); break; @@ -98,7 +98,7 @@ static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local, BUG(); } - return rxrpc_lookup_peer_rcu(local, &srx); + return rxrpc_lookup_peer_rcu(local, srx); } /* @@ -146,6 +146,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *se void rxrpc_error_report(struct sock *sk) { struct sock_exterr_skb *serr; + struct sockaddr_rxrpc srx; struct rxrpc_local *local = sk->sk_user_data; struct rxrpc_peer *peer; struct sk_buff *skb; @@ -166,7 +167,7 @@ void rxrpc_error_report(struct sock *sk) } rcu_read_lock(); - peer = rxrpc_lookup_peer_icmp_rcu(local, skb); + peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx); if (peer && !rxrpc_get_peer_maybe(peer)) peer = NULL; if (!peer) { @@ -176,6 +177,8 @@ void rxrpc_error_report(struct sock *sk) return; } + trace_rxrpc_rx_icmp(peer, &serr->ee, &srx); + if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP && serr->ee.ee_type == ICMP_DEST_UNREACH && serr->ee.ee_code == ICMP_FRAG_NEEDED)) { @@ -209,9 +212,6 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, ee = &serr->ee; - _net("Rx Error o=%d t=%d c=%d e=%d", - ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno); - err = ee->ee_errno; switch (ee->ee_origin) { diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 588fea0dd362..6c0ae27fff84 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -664,7 +664,8 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_conn_challenge); return -EAGAIN; } @@ -719,7 +720,8 @@ static int rxkad_send_response(struct rxrpc_connection *conn, ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len); if (ret < 0) { - _debug("sendmsg failed: %d", ret); + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_fail_conn_response); return -EAGAIN; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 206e802ccbdc..be01f9c5d963 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -223,6 +223,15 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, ret = rxrpc_send_data_packet(call, skb, false); if (ret < 0) { + switch (ret) { + case -ENETUNREACH: + case -EHOSTUNREACH: + case -ECONNREFUSED: + rxrpc_set_call_completion(call, + RXRPC_CALL_LOCAL_ERROR, + 0, ret); + goto out; + } _debug("need instant resend %d", ret); rxrpc_instant_resend(call, ix); } else { @@ -241,6 +250,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, rxrpc_timer_set_for_send); } +out: rxrpc_free_skb(skb, rxrpc_skb_tx_freed); _leave(""); } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index ddf69fc01bdf..6138d1d71900 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -121,7 +121,8 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, return 0; if (!flags) { - tcf_idr_release(*a, bind); + if (exists) + tcf_idr_release(*a, bind); return -EINVAL; } diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index bbcbdce732cc..ad050d7d4b46 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -131,8 +131,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (exists && bind) return 0; - if (!lflags) + if (!lflags) { + if (exists) + tcf_idr_release(*a, bind); return -EINVAL; + } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b66754f52a9f..963e4bf0aab8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -152,8 +152,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, NL_SET_ERR_MSG(extack, "TC classifier not found"); err = -ENOENT; } - goto errout; #endif + goto errout; } tp->classify = tp->ops->classify; tp->protocol = protocol; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 837806dd5799..a47179da24e6 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1024,8 +1024,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; - int state; + int first_time = 1; /* is this the first time through the loop */ int error = 0; + int state; /* The association should be held so we should be safe. */ ep = asoc->ep; @@ -1036,6 +1037,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type); + /* If the first chunk in the packet is AUTH, do special + * processing specified in Section 6.3 of SCTP-AUTH spec + */ + if (first_time && subtype.chunk == SCTP_CID_AUTH) { + struct sctp_chunkhdr *next_hdr; + + next_hdr = sctp_inq_peek(inqueue); + if (!next_hdr) + goto normal; + + /* If the next chunk is COOKIE-ECHO, skip the AUTH + * chunk while saving a pointer to it so we can do + * Authentication later (during cookie-echo + * processing). + */ + if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { + chunk->auth_chunk = skb_clone(chunk->skb, + GFP_ATOMIC); + chunk->auth = 1; + continue; + } + } + +normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has @@ -1074,6 +1099,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; + + if (first_time) + first_time = 0; } sctp_association_put(asoc); } diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5a4fb1dc8400..e62addb60434 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1152,7 +1152,7 @@ struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { - static const char error[] = "Association exceeded its max_retans count"; + static const char error[] = "Association exceeded its max_retrans count"; size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr); struct sctp_chunk *retval; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 28c070e187c2..c9ae3404b1bb 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -153,10 +153,7 @@ static enum sctp_disposition sctp_sf_violation_chunk( struct sctp_cmd_seq *commands); static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk); static enum sctp_disposition __sctp_sf_do_9_1_abort( @@ -626,6 +623,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, return SCTP_DISPOSITION_CONSUME; } +static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk, + const struct sctp_association *asoc) +{ + struct sctp_chunk auth; + + if (!chunk->auth_chunk) + return true; + + /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo + * is supposed to be authenticated and we have to do delayed + * authentication. We've just recreated the association using + * the information in the cookie and now it's much easier to + * do the authentication. + */ + + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + return false; + + /* set-up our fake chunk so that we can process it */ + auth.skb = chunk->auth_chunk; + auth.asoc = chunk->asoc; + auth.sctp_hdr = chunk->sctp_hdr; + auth.chunk_hdr = (struct sctp_chunkhdr *) + skb_push(chunk->auth_chunk, + sizeof(struct sctp_chunkhdr)); + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); + auth.transport = chunk->transport; + + return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR; +} + /* * Respond to a normal COOKIE ECHO chunk. * We are the side that is being asked for an association. @@ -763,37 +792,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, if (error) goto nomem_init; - /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo - * is supposed to be authenticated and we have to do delayed - * authentication. We've just recreated the association using - * the information in the cookie and now it's much easier to - * do the authentication. - */ - if (chunk->auth_chunk) { - struct sctp_chunk auth; - enum sctp_ierror ret; - - /* Make sure that we and the peer are AUTH capable */ - if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - - /* set-up our fake chunk so that we can process it */ - auth.skb = chunk->auth_chunk; - auth.asoc = chunk->asoc; - auth.sctp_hdr = chunk->sctp_hdr; - auth.chunk_hdr = (struct sctp_chunkhdr *) - skb_push(chunk->auth_chunk, - sizeof(struct sctp_chunkhdr)); - skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); - auth.transport = chunk->transport; - - ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - if (ret != SCTP_IERROR_NO_ERROR) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } repl = sctp_make_cookie_ack(new_asoc, chunk); @@ -1797,13 +1798,15 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) goto nomem; + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Make sure no new addresses are being added during the * restart. Though this is a pretty complicated attack * since you'd have to get inside the cookie. */ - if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) { + if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) return SCTP_DISPOSITION_CONSUME; - } /* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes * the peer has restarted (Action A), it MUST NOT setup a new @@ -1912,6 +1915,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_b( if (sctp_auth_asoc_init_active_key(new_asoc, GFP_ATOMIC)) goto nomem; + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -2009,6 +2015,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d( * a COOKIE ACK. */ + if (!sctp_auth_chunk_verify(net, chunk, asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Don't accidentally move back into established state. */ if (asoc->state < SCTP_STATE_ESTABLISHED) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, @@ -4171,10 +4180,7 @@ gen_shutdown: * The return value is the disposition of the chunk. */ static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk) { struct sctp_shared_key *sh_key = NULL; @@ -4275,7 +4281,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, commands); auth_hdr = (struct sctp_authhdr *)chunk->skb->data; - error = sctp_sf_authenticate(net, ep, asoc, type, chunk); + error = sctp_sf_authenticate(asoc, chunk); switch (error) { case SCTP_IERROR_AUTH_BAD_HMAC: /* Generate the ERROR chunk and discard the rest diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 84207ad33e8e..8cb7d9858270 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -715,7 +715,6 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, return event; fail_mark: - sctp_chunk_put(chunk); kfree_skb(skb); fail: return NULL; diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index 5cc68a824f45..f2f63959fddd 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -72,6 +72,7 @@ fmr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) if (IS_ERR(mr->fmr.fm_mr)) goto out_fmr_err; + INIT_LIST_HEAD(&mr->mr_list); return 0; out_fmr_err: @@ -102,10 +103,6 @@ fmr_op_release_mr(struct rpcrdma_mr *mr) LIST_HEAD(unmap_list); int rc; - /* Ensure MW is not on any rl_registered list */ - if (!list_empty(&mr->mr_list)) - list_del(&mr->mr_list); - kfree(mr->fmr.fm_physaddrs); kfree(mr->mr_sg); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index c5743a0960be..c59c5c788db0 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -110,6 +110,7 @@ frwr_op_init_mr(struct rpcrdma_ia *ia, struct rpcrdma_mr *mr) if (!mr->mr_sg) goto out_list_err; + INIT_LIST_HEAD(&mr->mr_list); sg_init_table(mr->mr_sg, depth); init_completion(&frwr->fr_linv_done); return 0; @@ -133,10 +134,6 @@ frwr_op_release_mr(struct rpcrdma_mr *mr) { int rc; - /* Ensure MR is not on any rl_registered list */ - if (!list_empty(&mr->mr_list)) - list_del(&mr->mr_list); - rc = ib_dereg_mr(mr->frwr.fr_mr); if (rc) pr_err("rpcrdma: final ib_dereg_mr for %p returned %i\n", @@ -195,7 +192,7 @@ frwr_op_recover_mr(struct rpcrdma_mr *mr) return; out_release: - pr_err("rpcrdma: FRWR reset failed %d, %p release\n", rc, mr); + pr_err("rpcrdma: FRWR reset failed %d, %p released\n", rc, mr); r_xprt->rx_stats.mrs_orphaned++; spin_lock(&r_xprt->rx_buf.rb_mrlock); @@ -476,7 +473,7 @@ frwr_op_reminv(struct rpcrdma_rep *rep, struct list_head *mrs) list_for_each_entry(mr, mrs, mr_list) if (mr->mr_handle == rep->rr_inv_rkey) { - list_del(&mr->mr_list); + list_del_init(&mr->mr_list); trace_xprtrdma_remoteinv(mr); mr->frwr.fr_state = FRWR_IS_INVALID; rpcrdma_mr_unmap_and_put(mr); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index fe5eaca2d197..c345d365af88 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1254,6 +1254,11 @@ rpcrdma_mrs_destroy(struct rpcrdma_buffer *buf) list_del(&mr->mr_all); spin_unlock(&buf->rb_mrlock); + + /* Ensure MW is not on any rl_registered list */ + if (!list_empty(&mr->mr_list)) + list_del(&mr->mr_list); + ia->ri_ops->ro_release_mr(mr); count++; spin_lock(&buf->rb_mrlock); diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 3d3b423fa9c1..cb41b12a3bf8 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -380,7 +380,7 @@ rpcrdma_mr_pop(struct list_head *list) struct rpcrdma_mr *mr; mr = list_first_entry(list, struct rpcrdma_mr, mr_list); - list_del(&mr->mr_list); + list_del_init(&mr->mr_list); return mr; } diff --git a/net/tipc/node.c b/net/tipc/node.c index baaf93f12cbd..f29549de9245 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1950,6 +1950,7 @@ out: int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); + struct nlattr *attrs[TIPC_NLA_LINK_MAX + 1]; struct tipc_nl_msg msg; char *name; int err; @@ -1957,9 +1958,19 @@ int tipc_nl_node_get_link(struct sk_buff *skb, struct genl_info *info) msg.portid = info->snd_portid; msg.seq = info->snd_seq; - if (!info->attrs[TIPC_NLA_LINK_NAME]) + if (!info->attrs[TIPC_NLA_LINK]) return -EINVAL; - name = nla_data(info->attrs[TIPC_NLA_LINK_NAME]); + + err = nla_parse_nested(attrs, TIPC_NLA_LINK_MAX, + info->attrs[TIPC_NLA_LINK], + tipc_nl_link_policy, info->extack); + if (err) + return err; + + if (!attrs[TIPC_NLA_LINK_NAME]) + return -EINVAL; + + name = nla_data(attrs[TIPC_NLA_LINK_NAME]); msg.skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!msg.skb) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 252a52ae0893..6be21575503a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1516,10 +1516,10 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) srcaddr->sock.family = AF_TIPC; srcaddr->sock.addrtype = TIPC_ADDR_ID; + srcaddr->sock.scope = 0; srcaddr->sock.addr.id.ref = msg_origport(hdr); srcaddr->sock.addr.id.node = msg_orignode(hdr); srcaddr->sock.addr.name.domain = 0; - srcaddr->sock.scope = 0; m->msg_namelen = sizeof(struct sockaddr_tipc); if (!msg_in_group(hdr)) @@ -1528,6 +1528,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb) /* Group message users may also want to know sending member's id */ srcaddr->member.family = AF_TIPC; srcaddr->member.addrtype = TIPC_ADDR_NAME; + srcaddr->member.scope = 0; srcaddr->member.addr.name.name.type = msg_nametype(hdr); srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member; srcaddr->member.addr.name.domain = 0; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index cc03e00785c7..20cd93be6236 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -135,6 +135,7 @@ retry: offset -= sg->offset; ctx->partially_sent_offset = offset; ctx->partially_sent_record = (void *)sg; + ctx->in_tcp_sendpages = false; return ret; } @@ -248,16 +249,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) struct tls_context *ctx = tls_get_ctx(sk); long timeo = sock_sndtimeo(sk, 0); void (*sk_proto_close)(struct sock *sk, long timeout); + bool free_ctx = false; lock_sock(sk); sk_proto_close = ctx->sk_proto_close; - if (ctx->conf == TLS_HW_RECORD) - goto skip_tx_cleanup; - - if (ctx->conf == TLS_BASE) { - kfree(ctx); - ctx = NULL; + if (ctx->conf == TLS_BASE || ctx->conf == TLS_HW_RECORD) { + free_ctx = true; goto skip_tx_cleanup; } @@ -294,7 +292,7 @@ skip_tx_cleanup: /* free ctx for TLS_HW_RECORD, used by tcp_set_state * for sk->sk_prot->unhash [tls_hw_unhash] */ - if (ctx && ctx->conf == TLS_HW_RECORD) + if (free_ctx) kfree(ctx); } diff --git a/net/wireless/core.c b/net/wireless/core.c index a6f3cac8c640..c0fd8a85e7f7 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -95,6 +95,9 @@ static int cfg80211_dev_check_name(struct cfg80211_registered_device *rdev, ASSERT_RTNL(); + if (strlen(newname) > NL80211_WIPHY_NAME_MAXLEN) + return -EINVAL; + /* prohibit calling the thing phy%d when %d is not its number */ sscanf(newname, PHY_NAME "%d%n", &wiphy_idx, &taken); if (taken == strlen(newname) && wiphy_idx != rdev->wiphy_idx) { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ff28f8feeb09..a052693c2e85 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -9214,6 +9214,7 @@ static int nl80211_connect(struct sk_buff *skb, struct genl_info *info) if (nla_get_flag(info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])) { if (!info->attrs[NL80211_ATTR_SOCKET_OWNER]) { + kzfree(connkeys); GENL_SET_ERR_MSG(info, "external auth requires connection ownership"); return -EINVAL; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 16c7e4ef5820..ac3e12c32aa3 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1026,6 +1026,7 @@ static int regdb_query_country(const struct fwdb_header *db, if (!tmp_rd) { kfree(regdom); + kfree(wmm_ptrs); return -ENOMEM; } regdom = tmp_rd; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f9d2f2233f09..6c177ae7a6d9 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2175,6 +2175,12 @@ struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) return afinfo; } +void xfrm_flush_gc(void) +{ + flush_work(&xfrm_state_gc_work); +} +EXPORT_SYMBOL(xfrm_flush_gc); + /* Temporarily located here until net/xfrm/xfrm_tunnel.c is created */ void xfrm_state_delete_tunnel(struct xfrm_state *x) { diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c index c07ba4da9e36..815eaf140ab5 100644 --- a/scripts/dtc/checks.c +++ b/scripts/dtc/checks.c @@ -787,10 +787,9 @@ static void check_pci_bridge(struct check *c, struct dt_info *dti, struct node * FAIL(c, dti, node, "incorrect #size-cells for PCI bridge"); prop = get_property(node, "bus-range"); - if (!prop) { - FAIL(c, dti, node, "missing bus-range for PCI bridge"); + if (!prop) return; - } + if (prop->val.len != (sizeof(cell_t) * 2)) { FAIL_PROP(c, dti, node, prop, "value must be 2 cells"); return; diff --git a/scripts/faddr2line b/scripts/faddr2line index 9e5735a4d3a5..1876a741087c 100755 --- a/scripts/faddr2line +++ b/scripts/faddr2line @@ -170,7 +170,10 @@ __faddr2line() { echo "$file_lines" | while read -r line do echo $line - eval $(echo $line | awk -F "[ :]" '{printf("n1=%d;n2=%d;f=%s",$NF-5, $NF+5, $(NF-1))}') + n=$(echo $line | sed 's/.*:\([0-9]\+\).*/\1/g') + n1=$[$n-5] + n2=$[$n+5] + f=$(echo $line | sed 's/.*at \(.\+\):.*/\1/g') awk 'NR>=strtonum("'$n1'") && NR<=strtonum("'$n2'") {printf("%d\t%s\n", NR, $0)}' $f done diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4cafe6a19167..be5817df0a9d 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4576,6 +4576,7 @@ static int selinux_socket_post_create(struct socket *sock, int family, static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen) { struct sock *sk = sock->sk; + struct sk_security_struct *sksec = sk->sk_security; u16 family; int err; @@ -4587,11 +4588,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in family = sk->sk_family; if (family == PF_INET || family == PF_INET6) { char *addrp; - struct sk_security_struct *sksec = sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; + u16 family_sa = address->sa_family; unsigned short snum; u32 sid, node_perm; @@ -4601,11 +4602,20 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in * need to check address->sa_family as it is possible to have * sk->sk_family = PF_INET6 with addr->sa_family = AF_INET. */ - switch (address->sa_family) { + switch (family_sa) { + case AF_UNSPEC: case AF_INET: if (addrlen < sizeof(struct sockaddr_in)) return -EINVAL; addr4 = (struct sockaddr_in *)address; + if (family_sa == AF_UNSPEC) { + /* see __inet_bind(), we only want to allow + * AF_UNSPEC if the address is INADDR_ANY + */ + if (addr4->sin_addr.s_addr != htonl(INADDR_ANY)) + goto err_af; + family_sa = AF_INET; + } snum = ntohs(addr4->sin_port); addrp = (char *)&addr4->sin_addr.s_addr; break; @@ -4617,15 +4627,14 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in addrp = (char *)&addr6->sin6_addr.s6_addr; break; default: - /* Note that SCTP services expect -EINVAL, whereas - * others expect -EAFNOSUPPORT. - */ - if (sksec->sclass == SECCLASS_SCTP_SOCKET) - return -EINVAL; - else - return -EAFNOSUPPORT; + goto err_af; } + ad.type = LSM_AUDIT_DATA_NET; + ad.u.net = &net; + ad.u.net->sport = htons(snum); + ad.u.net->family = family_sa; + if (snum) { int low, high; @@ -4637,10 +4646,6 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in snum, &sid); if (err) goto out; - ad.type = LSM_AUDIT_DATA_NET; - ad.u.net = &net; - ad.u.net->sport = htons(snum); - ad.u.net->family = family; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, @@ -4672,16 +4677,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in break; } - err = sel_netnode_sid(addrp, family, &sid); + err = sel_netnode_sid(addrp, family_sa, &sid); if (err) goto out; - ad.type = LSM_AUDIT_DATA_NET; - ad.u.net = &net; - ad.u.net->sport = htons(snum); - ad.u.net->family = family; - - if (address->sa_family == AF_INET) + if (family_sa == AF_INET) ad.u.net->v4info.saddr = addr4->sin_addr.s_addr; else ad.u.net->v6info.saddr = addr6->sin6_addr; @@ -4694,6 +4694,11 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in } out: return err; +err_af: + /* Note that SCTP services expect -EINVAL, others -EAFNOSUPPORT. */ + if (sksec->sclass == SECCLASS_SCTP_SOCKET) + return -EINVAL; + return -EAFNOSUPPORT; } /* This supports connect(2) and SCTP connect services such as sctp_connectx(3) @@ -4771,7 +4776,7 @@ static int selinux_socket_connect_helper(struct socket *sock, ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; ad.u.net->dport = htons(snum); - ad.u.net->family = sk->sk_family; + ad.u.net->family = address->sa_family; err = avc_has_perm(&selinux_state, sksec->sid, sid, sksec->sclass, perm, &ad); if (err) @@ -5272,6 +5277,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, while (walk_size < addrlen) { addr = addr_buf; switch (addr->sa_family) { + case AF_UNSPEC: case AF_INET: len = sizeof(struct sockaddr_in); break; @@ -5279,7 +5285,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, len = sizeof(struct sockaddr_in6); break; default: - return -EAFNOSUPPORT; + return -EINVAL; } err = -EINVAL; diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index a848836a5de0..507fd5210c1c 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -396,8 +396,7 @@ static int snd_ctl_elem_add_compat(struct snd_ctl_file *file, if (copy_from_user(&data->id, &data32->id, sizeof(data->id)) || copy_from_user(&data->type, &data32->type, 3 * sizeof(u32))) goto error; - if (get_user(data->owner, &data32->owner) || - get_user(data->type, &data32->type)) + if (get_user(data->owner, &data32->owner)) goto error; switch (data->type) { case SNDRV_CTL_ELEM_TYPE_BOOLEAN: diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index b0c8c79848a9..a0c93b9c9a28 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2210,6 +2210,8 @@ static struct snd_pci_quirk power_save_blacklist[] = { SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0), /* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */ SND_PCI_QUIRK(0x1043, 0x8733, "Asus Prime X370-Pro", 0), + /* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */ + SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0), /* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */ SND_PCI_QUIRK(0x17aa, 0x2227, "Lenovo X1 Carbon 3rd Gen", 0), {} diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 2dd34dd77447..01a6643fc7d4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2363,6 +2363,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530), diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 344d7b069d59..bb5ab7a7dfa5 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -967,6 +967,14 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval, } break; + case USB_ID(0x0d8c, 0x0103): + if (!strcmp(kctl->id.name, "PCM Playback Volume")) { + usb_audio_info(chip, + "set volume quirk for CM102-A+/102S+\n"); + cval->min = -256; + } + break; + case USB_ID(0x0471, 0x0101): case USB_ID(0x0471, 0x0104): case USB_ID(0x0471, 0x0105): diff --git a/sound/usb/stream.c b/sound/usb/stream.c index 956be9f7c72a..5ed334575fc7 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -576,7 +576,7 @@ static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip, if (protocol == UAC_VERSION_1) { attributes = csep->bmAttributes; - } else { + } else if (protocol == UAC_VERSION_2) { struct uac2_iso_endpoint_descriptor *csep2 = (struct uac2_iso_endpoint_descriptor *) csep; @@ -585,6 +585,13 @@ static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip, /* emulate the endpoint attributes of a v1 device */ if (csep2->bmControls & UAC2_CONTROL_PITCH) attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL; + } else { /* UAC_VERSION_3 */ + struct uac3_iso_endpoint_descriptor *csep3 = + (struct uac3_iso_endpoint_descriptor *) csep; + + /* emulate the endpoint attributes of a v1 device */ + if (le32_to_cpu(csep3->bmControls) & UAC2_CONTROL_PITCH) + attributes |= UAC_EP_CS_ATTR_PITCH_CONTROL; } return attributes; diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 2ba95d6fe852..caae4843cb70 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -195,6 +195,12 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_VFP_FPINST 0x1009 #define KVM_REG_ARM_VFP_FPINST2 0x100A +/* KVM-as-firmware specific pseudo-registers */ +#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW | ((r) & 0xffff)) +#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 9abbf3044654..04b3256f8e6d 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -206,6 +206,12 @@ struct kvm_arch_memory_slot { #define KVM_REG_ARM_TIMER_CNT ARM64_SYS_REG(3, 3, 14, 3, 2) #define KVM_REG_ARM_TIMER_CVAL ARM64_SYS_REG(3, 3, 14, 0, 2) +/* KVM-as-firmware specific pseudo-registers */ +#define KVM_REG_ARM_FW (0x0014 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW | ((r) & 0xffff)) +#define KVM_REG_ARM_PSCI_VERSION KVM_REG_ARM_FW_REG(0) + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index d554c11e01ff..578793e97431 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -320,6 +320,7 @@ #define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */ #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 */ /* 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/include/linux/spinlock.h b/tools/include/linux/spinlock.h index b21b586b9854..1738c0391da4 100644 --- a/tools/include/linux/spinlock.h +++ b/tools/include/linux/spinlock.h @@ -6,8 +6,9 @@ #include <stdbool.h> #define spinlock_t pthread_mutex_t -#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER; +#define DEFINE_SPINLOCK(x) pthread_mutex_t x = PTHREAD_MUTEX_INITIALIZER #define __SPIN_LOCK_UNLOCKED(x) (pthread_mutex_t)PTHREAD_MUTEX_INITIALIZER +#define spin_lock_init(x) pthread_mutex_init(x, NULL) #define spin_lock_irqsave(x, f) (void)f, pthread_mutex_lock(x) #define spin_unlock_irqrestore(x, f) (void)f, pthread_mutex_unlock(x) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 1065006c9bf5..b02c41e53d56 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -676,6 +676,13 @@ struct kvm_ioeventfd { __u8 pad[36]; }; +#define KVM_X86_DISABLE_EXITS_MWAIT (1 << 0) +#define KVM_X86_DISABLE_EXITS_HTL (1 << 1) +#define KVM_X86_DISABLE_EXITS_PAUSE (1 << 2) +#define KVM_X86_DISABLE_VALID_EXITS (KVM_X86_DISABLE_EXITS_MWAIT | \ + KVM_X86_DISABLE_EXITS_HTL | \ + KVM_X86_DISABLE_EXITS_PAUSE) + /* for KVM_ENABLE_CAP */ struct kvm_enable_cap { /* in */ diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index 944070e98a2c..63eb49082774 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -175,7 +175,7 @@ static const struct option options[] = { OPT_UINTEGER('s', "nr_secs" , &p0.nr_secs, "max number of seconds to run (default: 5 secs)"), OPT_UINTEGER('u', "usleep" , &p0.sleep_usecs, "usecs to sleep per loop iteration"), - OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via writes (can be mixed with -W)"), + OPT_BOOLEAN('R', "data_reads" , &p0.data_reads, "access the data via reads (can be mixed with -W)"), OPT_BOOLEAN('W', "data_writes" , &p0.data_writes, "access the data via writes (can be mixed with -R)"), OPT_BOOLEAN('B', "data_backwards", &p0.data_backwards, "access the data backwards as well"), OPT_BOOLEAN('Z', "data_zero_memset", &p0.data_zero_memset,"access the data via glibc bzero only"), diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 93656f2fd53a..7e3cce3bcf3b 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -29,7 +29,6 @@ GenuineIntel-6-4D,v13,silvermont,core GenuineIntel-6-4C,v13,silvermont,core GenuineIntel-6-2A,v15,sandybridge,core GenuineIntel-6-2C,v2,westmereep-dp,core -GenuineIntel-6-2C,v2,westmereep-dp,core GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55,v1,skylakex,core diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index d14464c42714..7afeb80cc39e 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -224,15 +224,15 @@ event_def: event_pmu | event_bpf_file event_pmu: -PE_NAME '/' event_config '/' +PE_NAME opt_event_config { struct list_head *list, *orig_terms, *terms; - if (parse_events_copy_term_list($3, &orig_terms)) + if (parse_events_copy_term_list($2, &orig_terms)) YYABORT; ALLOC_LIST(list); - if (parse_events_add_pmu(_parse_state, list, $1, $3, false)) { + if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) { struct perf_pmu *pmu = NULL; int ok = 0; char *pattern; @@ -262,7 +262,7 @@ PE_NAME '/' event_config '/' if (!ok) YYABORT; } - parse_events_terms__delete($3); + parse_events_terms__delete($2); parse_events_terms__delete(orig_terms); $$ = list; } diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile index fa7ee369b3c9..db66f8a0d4be 100644 --- a/tools/testing/radix-tree/Makefile +++ b/tools/testing/radix-tree/Makefile @@ -17,7 +17,7 @@ ifeq ($(BUILD), 32) LDFLAGS += -m32 endif -targets: mapshift $(TARGETS) +targets: generated/map-shift.h $(TARGETS) main: $(OFILES) @@ -42,9 +42,7 @@ radix-tree.c: ../../../lib/radix-tree.c idr.c: ../../../lib/idr.c sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@ -.PHONY: mapshift - -mapshift: +generated/map-shift.h: @if ! grep -qws $(SHIFT) generated/map-shift.h; then \ echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \ generated/map-shift.h; \ diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 59245b3d587c..7bf405638b0b 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -16,6 +16,7 @@ #include <linux/radix-tree.h> #include <linux/slab.h> #include <linux/errno.h> +#include <pthread.h> #include "test.h" @@ -624,6 +625,67 @@ static void multiorder_account(void) item_kill_tree(&tree); } +bool stop_iteration = false; + +static void *creator_func(void *ptr) +{ + /* 'order' is set up to ensure we have sibling entries */ + unsigned int order = RADIX_TREE_MAP_SHIFT - 1; + struct radix_tree_root *tree = ptr; + int i; + + for (i = 0; i < 10000; i++) { + item_insert_order(tree, 0, order); + item_delete_rcu(tree, 0); + } + + stop_iteration = true; + return NULL; +} + +static void *iterator_func(void *ptr) +{ + struct radix_tree_root *tree = ptr; + struct radix_tree_iter iter; + struct item *item; + void **slot; + + while (!stop_iteration) { + rcu_read_lock(); + radix_tree_for_each_slot(slot, tree, &iter, 0) { + item = radix_tree_deref_slot(slot); + + if (!item) + continue; + if (radix_tree_deref_retry(item)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + + item_sanity(item, iter.index); + } + rcu_read_unlock(); + } + return NULL; +} + +static void multiorder_iteration_race(void) +{ + const int num_threads = sysconf(_SC_NPROCESSORS_ONLN); + pthread_t worker_thread[num_threads]; + RADIX_TREE(tree, GFP_KERNEL); + int i; + + pthread_create(&worker_thread[0], NULL, &creator_func, &tree); + for (i = 1; i < num_threads; i++) + pthread_create(&worker_thread[i], NULL, &iterator_func, &tree); + + for (i = 0; i < num_threads; i++) + pthread_join(worker_thread[i], NULL); + + item_kill_tree(&tree); +} + void multiorder_checks(void) { int i; @@ -644,6 +706,7 @@ void multiorder_checks(void) multiorder_join(); multiorder_split(); multiorder_account(); + multiorder_iteration_race(); radix_tree_cpu_dead(0); } diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index 5978ab1f403d..def6015570b2 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -75,6 +75,25 @@ int item_delete(struct radix_tree_root *root, unsigned long index) return 0; } +static void item_free_rcu(struct rcu_head *head) +{ + struct item *item = container_of(head, struct item, rcu_head); + + free(item); +} + +int item_delete_rcu(struct radix_tree_root *root, unsigned long index) +{ + struct item *item = radix_tree_delete(root, index); + + if (item) { + item_sanity(item, index); + call_rcu(&item->rcu_head, item_free_rcu); + return 1; + } + return 0; +} + void item_check_present(struct radix_tree_root *root, unsigned long index) { struct item *item; diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index d9c031dbeb1a..31f1d9b6f506 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -5,6 +5,7 @@ #include <linux/rcupdate.h> struct item { + struct rcu_head rcu_head; unsigned long index; unsigned int order; }; @@ -12,9 +13,11 @@ struct item { struct item *item_create(unsigned long index, unsigned int order); int __item_insert(struct radix_tree_root *root, struct item *item); int item_insert(struct radix_tree_root *root, unsigned long index); +void item_sanity(struct item *item, unsigned long index); int item_insert_order(struct radix_tree_root *root, unsigned long index, unsigned order); int item_delete(struct radix_tree_root *root, unsigned long index); +int item_delete_rcu(struct radix_tree_root *root, unsigned long index); struct item *item_lookup(struct radix_tree_root *root, unsigned long index); void item_check_present(struct radix_tree_root *root, unsigned long index); diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 2ddcc96ae456..d9d00319b07c 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -15,7 +15,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ -CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) +CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I.. # After inclusion, $(OUTPUT) is defined and # $(TEST_GEN_PROGS) starts with $(OUTPUT)/ diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index 7ab98e41324f..ac53730b30aa 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -19,6 +19,7 @@ #include <errno.h> #include <unistd.h> #include <fcntl.h> +#include "kselftest.h" ssize_t test_write(int fd, const void *buf, size_t count); ssize_t test_read(int fd, void *buf, size_t count); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 2cedfda181d4..37e2a787d2fc 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -50,8 +50,8 @@ int kvm_check_cap(long cap) int kvm_fd; kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i", - KVM_DEV_PATH, kvm_fd, errno); + if (kvm_fd < 0) + exit(KSFT_SKIP); ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap); TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n" @@ -91,8 +91,8 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm) vm->mode = mode; kvm_fd = open(KVM_DEV_PATH, perm); - TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i", - KVM_DEV_PATH, kvm_fd, errno); + if (kvm_fd < 0) + exit(KSFT_SKIP); /* Create VM. */ vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL); @@ -418,8 +418,8 @@ struct kvm_cpuid2 *kvm_get_supported_cpuid(void) cpuid = allocate_kvm_cpuid2(); kvm_fd = open(KVM_DEV_PATH, O_RDONLY); - TEST_ASSERT(kvm_fd >= 0, "open %s failed, rc: %i errno: %i", - KVM_DEV_PATH, kvm_fd, errno); + if (kvm_fd < 0) + exit(KSFT_SKIP); ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid); TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n", @@ -675,8 +675,8 @@ static int vcpu_mmap_sz(void) int dev_fd, ret; dev_fd = open(KVM_DEV_PATH, O_RDONLY); - TEST_ASSERT(dev_fd >= 0, "%s open %s failed, rc: %i errno: %i", - __func__, KVM_DEV_PATH, dev_fd, errno); + if (dev_fd < 0) + exit(KSFT_SKIP); ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL); TEST_ASSERT(ret >= sizeof(struct kvm_run), diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c index 428e9473f5e2..eae1ece3c31b 100644 --- a/tools/testing/selftests/kvm/sync_regs_test.c +++ b/tools/testing/selftests/kvm/sync_regs_test.c @@ -85,6 +85,9 @@ static void compare_vcpu_events(struct kvm_vcpu_events *left, { } +#define TEST_SYNC_FIELDS (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS) +#define INVALID_SYNC_FIELD 0x80000000 + int main(int argc, char *argv[]) { struct kvm_vm *vm; @@ -98,9 +101,14 @@ int main(int argc, char *argv[]) setbuf(stdout, NULL); cap = kvm_check_cap(KVM_CAP_SYNC_REGS); - TEST_ASSERT((unsigned long)cap == KVM_SYNC_X86_VALID_FIELDS, - "KVM_CAP_SYNC_REGS (0x%x) != KVM_SYNC_X86_VALID_FIELDS (0x%lx)\n", - cap, KVM_SYNC_X86_VALID_FIELDS); + if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) { + fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n"); + exit(KSFT_SKIP); + } + if ((cap & INVALID_SYNC_FIELD) != 0) { + fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n"); + exit(KSFT_SKIP); + } /* Create VM */ vm = vm_create_default(VCPU_ID, guest_code); @@ -108,7 +116,14 @@ int main(int argc, char *argv[]) run = vcpu_state(vm, VCPU_ID); /* Request reading invalid register set from VCPU. */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS << 1; + run->kvm_valid_regs = INVALID_SYNC_FIELD; + rv = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rv < 0 && errno == EINVAL, + "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", + rv); + vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; + + run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n", @@ -116,7 +131,14 @@ int main(int argc, char *argv[]) vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0; /* Request setting invalid register set into VCPU. */ - run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS << 1; + run->kvm_dirty_regs = INVALID_SYNC_FIELD; + rv = _vcpu_run(vm, VCPU_ID); + TEST_ASSERT(rv < 0 && errno == EINVAL, + "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", + rv); + vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0; + + run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(rv < 0 && errno == EINVAL, "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n", @@ -125,7 +147,7 @@ int main(int argc, char *argv[]) /* Request and verify all valid register sets. */ /* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_valid_regs = TEST_SYNC_FIELDS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "Unexpected exit reason: %u (%s),\n", @@ -146,7 +168,7 @@ int main(int argc, char *argv[]) run->s.regs.sregs.apic_base = 1 << 11; /* TODO run->s.regs.events.XYZ = ABC; */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, @@ -172,7 +194,7 @@ int main(int argc, char *argv[]) /* Clear kvm_dirty_regs bits, verify new s.regs values are * overwritten with existing guest values. */ - run->kvm_valid_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_valid_regs = TEST_SYNC_FIELDS; run->kvm_dirty_regs = 0; run->s.regs.regs.r11 = 0xDEADBEEF; rv = _vcpu_run(vm, VCPU_ID); @@ -211,7 +233,7 @@ int main(int argc, char *argv[]) * with kvm_sync_regs values. */ run->kvm_valid_regs = 0; - run->kvm_dirty_regs = KVM_SYNC_X86_VALID_FIELDS; + run->kvm_dirty_regs = TEST_SYNC_FIELDS; run->s.regs.regs.r11 = 0xBBBB; rv = _vcpu_run(vm, VCPU_ID); TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c index 8f7f62093add..aaa633263b2c 100644 --- a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c @@ -189,8 +189,8 @@ int main(int argc, char *argv[]) struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1); if (!(entry->ecx & CPUID_VMX)) { - printf("nested VMX not enabled, skipping test"); - return 0; + fprintf(stderr, "nested VMX not enabled, skipping test\n"); + exit(KSFT_SKIP); } vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code); diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index daf5effec3f0..3ff81a478dbe 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -6,7 +6,7 @@ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh -TEST_GEN_PROGS_EXTENDED := in_netns.sh +TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json index 5b012f4981d4..6f289a49e5ec 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json @@ -66,7 +66,7 @@ "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667", "expExitCode": "0", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c default-action pipe.*index 667 ref", + "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref", "matchCount": "1", "teardown": [ "$TC action flush action bpf", @@ -92,10 +92,15 @@ "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667", "expExitCode": "255", "verifyCmd": "$TC action get action bpf index 667", - "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9].*index 667 ref", + "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref", "matchCount": "0", "teardown": [ - "$TC action flush action bpf", + [ + "$TC action flush action bpf", + 0, + 1, + 255 + ], "rm -f _c.o" ] }, diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index cca7e065a075..72143cfaf6ec 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -54,3 +54,6 @@ config HAVE_KVM_IRQ_BYPASS config HAVE_KVM_VCPU_ASYNC_IOCTL bool + +config HAVE_KVM_VCPU_RUN_PID_CHANGE + bool diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index a4c1b76240df..126b98fbf9ba 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -16,6 +16,7 @@ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ +#include <linux/bug.h> #include <linux/cpu_pm.h> #include <linux/errno.h> #include <linux/err.h> @@ -41,6 +42,7 @@ #include <asm/mman.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> +#include <asm/cpufeature.h> #include <asm/virt.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> @@ -290,7 +292,6 @@ out: void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { - kvm_vgic_vcpu_early_init(vcpu); } void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) @@ -363,10 +364,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_vgic_load(vcpu); kvm_timer_vcpu_load(vcpu); kvm_vcpu_load_sysregs(vcpu); + kvm_arch_vcpu_load_fp(vcpu); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + kvm_arch_vcpu_put_fp(vcpu); kvm_vcpu_put_sysregs(vcpu); kvm_timer_vcpu_put(vcpu); kvm_vgic_put(vcpu); @@ -678,9 +681,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) */ preempt_disable(); - /* Flush FP/SIMD state that can't survive guest entry/exit */ - kvm_fpsimd_flush_cpu_state(); - kvm_pmu_flush_hwstate(vcpu); local_irq_disable(); @@ -778,6 +778,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (static_branch_unlikely(&userspace_irqchip_in_use)) kvm_timer_sync_hwstate(vcpu); + kvm_arch_vcpu_ctxsync_fp(vcpu); + /* * We may have taken a host interrupt in HYP mode (ie * while executing the guest). This interrupt is still @@ -1570,6 +1572,11 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (!kvm_arch_check_sve_has_vhe()) { + kvm_pr_unimpl("SVE system without VHE unsupported. Broken cpu?"); + return -ENODEV; + } + for_each_online_cpu(cpu) { smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); if (ret < 0) { diff --git a/virt/kvm/arm/vgic/vgic-debug.c b/virt/kvm/arm/vgic/vgic-debug.c index 10b38178cff2..4ffc0b5e6105 100644 --- a/virt/kvm/arm/vgic/vgic-debug.c +++ b/virt/kvm/arm/vgic/vgic-debug.c @@ -211,6 +211,7 @@ static int vgic_debug_show(struct seq_file *s, void *v) struct vgic_state_iter *iter = (struct vgic_state_iter *)v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; + unsigned long flags; if (iter->dist_id == 0) { print_dist_state(s, &kvm->arch.vgic); @@ -227,9 +228,9 @@ static int vgic_debug_show(struct seq_file *s, void *v) irq = &kvm->arch.vgic.spis[iter->intid - VGIC_NR_PRIVATE_IRQS]; } - spin_lock(&irq->irq_lock); + spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); - spin_unlock(&irq->irq_lock); + spin_unlock_irqrestore(&irq->irq_lock, flags); return 0; } diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index e07156c30323..2673efce65f3 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -44,7 +44,7 @@ * * CPU Interface: * - * - kvm_vgic_vcpu_early_init(): initialization of static data that + * - kvm_vgic_vcpu_init(): initialization of static data that * doesn't depend on any sizing information or emulation type. No * allocation is allowed there. */ @@ -67,46 +67,6 @@ void kvm_vgic_early_init(struct kvm *kvm) spin_lock_init(&dist->lpi_list_lock); } -/** - * kvm_vgic_vcpu_early_init() - Initialize static VGIC VCPU data structures - * @vcpu: The VCPU whose VGIC data structures whould be initialized - * - * Only do initialization, but do not actually enable the VGIC CPU interface - * yet. - */ -void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu) -{ - struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - int i; - - INIT_LIST_HEAD(&vgic_cpu->ap_list_head); - spin_lock_init(&vgic_cpu->ap_list_lock); - - /* - * Enable and configure all SGIs to be edge-triggered and - * configure all PPIs as level-triggered. - */ - for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { - struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; - - INIT_LIST_HEAD(&irq->ap_list); - spin_lock_init(&irq->irq_lock); - irq->intid = i; - irq->vcpu = NULL; - irq->target_vcpu = vcpu; - irq->targets = 1U << vcpu->vcpu_id; - kref_init(&irq->refcount); - if (vgic_irq_is_sgi(i)) { - /* SGIs */ - irq->enabled = 1; - irq->config = VGIC_CONFIG_EDGE; - } else { - /* PPIs */ - irq->config = VGIC_CONFIG_LEVEL; - } - } -} - /* CREATION */ /** @@ -167,8 +127,11 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) kvm->arch.vgic.vgic_model = type; kvm->arch.vgic.vgic_dist_base = VGIC_ADDR_UNDEF; - kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; - kvm->arch.vgic.vgic_redist_base = VGIC_ADDR_UNDEF; + + if (type == KVM_DEV_TYPE_ARM_VGIC_V2) + kvm->arch.vgic.vgic_cpu_base = VGIC_ADDR_UNDEF; + else + INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); out_unlock: for (; vcpu_lock_idx >= 0; vcpu_lock_idx--) { @@ -221,13 +184,50 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) } /** - * kvm_vgic_vcpu_init() - Register VCPU-specific KVM iodevs + * kvm_vgic_vcpu_init() - Initialize static VGIC VCPU data + * structures and register VCPU-specific KVM iodevs + * * @vcpu: pointer to the VCPU being created and initialized + * + * Only do initialization, but do not actually enable the + * VGIC CPU interface */ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) { - int ret = 0; + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_dist *dist = &vcpu->kvm->arch.vgic; + int ret = 0; + int i; + + vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; + vgic_cpu->sgi_iodev.base_addr = VGIC_ADDR_UNDEF; + + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); + spin_lock_init(&vgic_cpu->ap_list_lock); + + /* + * Enable and configure all SGIs to be edge-triggered and + * configure all PPIs as level-triggered. + */ + for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) { + struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; + + INIT_LIST_HEAD(&irq->ap_list); + spin_lock_init(&irq->irq_lock); + irq->intid = i; + irq->vcpu = NULL; + irq->target_vcpu = vcpu; + irq->targets = 1U << vcpu->vcpu_id; + kref_init(&irq->refcount); + if (vgic_irq_is_sgi(i)) { + /* SGIs */ + irq->enabled = 1; + irq->config = VGIC_CONFIG_EDGE; + } else { + /* PPIs */ + irq->config = VGIC_CONFIG_LEVEL; + } + } if (!irqchip_in_kernel(vcpu->kvm)) return 0; @@ -303,13 +303,23 @@ out: static void kvm_vgic_dist_destroy(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; + struct vgic_redist_region *rdreg, *next; dist->ready = false; dist->initialized = false; kfree(dist->spis); + dist->spis = NULL; dist->nr_spis = 0; + if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { + list_for_each_entry_safe(rdreg, next, &dist->rd_regions, list) { + list_del(&rdreg->list); + kfree(rdreg); + } + INIT_LIST_HEAD(&dist->rd_regions); + } + if (vgic_supports_direct_msis(kvm)) vgic_v4_teardown(kvm); } diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index a8f07243aa9f..4ed79c939fb4 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -52,6 +52,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq; + unsigned long flags; int ret; /* In this case there is no put, since we keep the reference. */ @@ -71,7 +72,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, irq->intid = intid; irq->target_vcpu = vcpu; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); /* * There could be a race with another vgic_add_lpi(), so we need to @@ -99,7 +100,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid, dist->lpi_list_count++; out_unlock: - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); /* * We "cache" the configuration table entries in our struct vgic_irq's. @@ -280,8 +281,8 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq, int ret; unsigned long flags; - ret = kvm_read_guest(kvm, propbase + irq->intid - GIC_LPI_OFFSET, - &prop, 1); + ret = kvm_read_guest_lock(kvm, propbase + irq->intid - GIC_LPI_OFFSET, + &prop, 1); if (ret) return ret; @@ -315,6 +316,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_irq *irq; + unsigned long flags; u32 *intids; int irq_count, i = 0; @@ -330,7 +332,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) if (!intids) return -ENOMEM; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (i == irq_count) break; @@ -339,7 +341,7 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) continue; intids[i++] = irq->intid; } - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); *intid_ptr = intids; return i; @@ -348,10 +350,11 @@ static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr) static int update_affinity(struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int ret = 0; + unsigned long flags; - spin_lock(&irq->irq_lock); + spin_lock_irqsave(&irq->irq_lock, flags); irq->target_vcpu = vcpu; - spin_unlock(&irq->irq_lock); + spin_unlock_irqrestore(&irq->irq_lock, flags); if (irq->hw) { struct its_vlpi_map map; @@ -441,8 +444,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) * this very same byte in the last iteration. Reuse that. */ if (byte_offset != last_byte_offset) { - ret = kvm_read_guest(vcpu->kvm, pendbase + byte_offset, - &pendmask, 1); + ret = kvm_read_guest_lock(vcpu->kvm, + pendbase + byte_offset, + &pendmask, 1); if (ret) { kfree(intids); return ret; @@ -786,7 +790,7 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id, return false; /* Each 1st level entry is represented by a 64-bit value. */ - if (kvm_read_guest(its->dev->kvm, + if (kvm_read_guest_lock(its->dev->kvm, BASER_ADDRESS(baser) + index * sizeof(indirect_ptr), &indirect_ptr, sizeof(indirect_ptr))) return false; @@ -1367,8 +1371,8 @@ static void vgic_its_process_commands(struct kvm *kvm, struct vgic_its *its) cbaser = CBASER_ADDRESS(its->cbaser); while (its->cwriter != its->creadr) { - int ret = kvm_read_guest(kvm, cbaser + its->creadr, - cmd_buf, ITS_CMD_SIZE); + int ret = kvm_read_guest_lock(kvm, cbaser + its->creadr, + cmd_buf, ITS_CMD_SIZE); /* * If kvm_read_guest() fails, this could be due to the guest * programming a bogus value in CBASER or something else going @@ -1893,7 +1897,7 @@ static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz, int next_offset; size_t byte_offset; - ret = kvm_read_guest(kvm, gpa, entry, esz); + ret = kvm_read_guest_lock(kvm, gpa, entry, esz); if (ret) return ret; @@ -2263,7 +2267,7 @@ static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz) int ret; BUG_ON(esz > sizeof(val)); - ret = kvm_read_guest(kvm, gpa, &val, esz); + ret = kvm_read_guest_lock(kvm, gpa, &val, esz); if (ret) return ret; val = le64_to_cpu(val); diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c index 10ae6f394b71..6ada2432e37c 100644 --- a/virt/kvm/arm/vgic/vgic-kvm-device.c +++ b/virt/kvm/arm/vgic/vgic-kvm-device.c @@ -66,6 +66,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) int r = 0; struct vgic_dist *vgic = &kvm->arch.vgic; phys_addr_t *addr_ptr, alignment; + u64 undef_value = VGIC_ADDR_UNDEF; mutex_lock(&kvm->lock); switch (type) { @@ -84,16 +85,61 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write) addr_ptr = &vgic->vgic_dist_base; alignment = SZ_64K; break; - case KVM_VGIC_V3_ADDR_TYPE_REDIST: + case KVM_VGIC_V3_ADDR_TYPE_REDIST: { + struct vgic_redist_region *rdreg; + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; if (write) { - r = vgic_v3_set_redist_base(kvm, *addr); + r = vgic_v3_set_redist_base(kvm, 0, *addr, 0); goto out; } - addr_ptr = &vgic->vgic_redist_base; + rdreg = list_first_entry(&vgic->rd_regions, + struct vgic_redist_region, list); + if (!rdreg) + addr_ptr = &undef_value; + else + addr_ptr = &rdreg->base; break; + } + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: + { + struct vgic_redist_region *rdreg; + u8 index; + + r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); + if (r) + break; + + index = *addr & KVM_VGIC_V3_RDIST_INDEX_MASK; + + if (write) { + gpa_t base = *addr & KVM_VGIC_V3_RDIST_BASE_MASK; + u32 count = (*addr & KVM_VGIC_V3_RDIST_COUNT_MASK) + >> KVM_VGIC_V3_RDIST_COUNT_SHIFT; + u8 flags = (*addr & KVM_VGIC_V3_RDIST_FLAGS_MASK) + >> KVM_VGIC_V3_RDIST_FLAGS_SHIFT; + + if (!count || flags) + r = -EINVAL; + else + r = vgic_v3_set_redist_base(kvm, index, + base, count); + goto out; + } + + rdreg = vgic_v3_rdist_region_from_index(kvm, index); + if (!rdreg) { + r = -ENOENT; + goto out; + } + + *addr = index; + *addr |= rdreg->base; + *addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; + goto out; + } default: r = -ENODEV; } @@ -665,6 +711,7 @@ static int vgic_v3_has_attr(struct kvm_device *dev, switch (attr->attr) { case KVM_VGIC_V3_ADDR_TYPE_DIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST: + case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: return 0; } break; diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index 671fe81f8e1d..287784095b5b 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -184,12 +184,17 @@ static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu); + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + struct vgic_redist_region *rdreg = vgic_cpu->rdreg; int target_vcpu_id = vcpu->vcpu_id; + gpa_t last_rdist_typer = rdreg->base + GICR_TYPER + + (rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE; u64 value; value = (u64)(mpidr & GENMASK(23, 0)) << 32; value |= ((target_vcpu_id & 0xffff) << 8); - if (target_vcpu_id == atomic_read(&vcpu->kvm->online_vcpus) - 1) + + if (addr == last_rdist_typer) value |= GICR_TYPER_LAST; if (vgic_has_its(vcpu->kvm)) value |= GICR_TYPER_PLPIS; @@ -580,24 +585,32 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; struct vgic_dist *vgic = &kvm->arch.vgic; + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev; struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev; + struct vgic_redist_region *rdreg; gpa_t rd_base, sgi_base; int ret; + if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) + return 0; + /* * We may be creating VCPUs before having set the base address for the * redistributor region, in which case we will come back to this * function for all VCPUs when the base address is set. Just return * without doing any work for now. */ - if (IS_VGIC_ADDR_UNDEF(vgic->vgic_redist_base)) + rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions); + if (!rdreg) return 0; if (!vgic_v3_check_base(kvm)) return -EINVAL; - rd_base = vgic->vgic_redist_base + vgic->vgic_redist_free_offset; + vgic_cpu->rdreg = rdreg; + + rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE; sgi_base = rd_base + SZ_64K; kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops); @@ -631,7 +644,7 @@ int vgic_register_redist_iodev(struct kvm_vcpu *vcpu) goto out; } - vgic->vgic_redist_free_offset += 2 * SZ_64K; + rdreg->free_index++; out: mutex_unlock(&kvm->slots_lock); return ret; @@ -670,23 +683,96 @@ static int vgic_register_all_redist_iodevs(struct kvm *kvm) return ret; } -int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr) +/** + * vgic_v3_insert_redist_region - Insert a new redistributor region + * + * Performs various checks before inserting the rdist region in the list. + * Those tests depend on whether the size of the rdist region is known + * (ie. count != 0). The list is sorted by rdist region index. + * + * @kvm: kvm handle + * @index: redist region index + * @base: base of the new rdist region + * @count: number of redistributors the region is made of (0 in the old style + * single region, whose size is induced from the number of vcpus) + * + * Return 0 on success, < 0 otherwise + */ +static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index, + gpa_t base, uint32_t count) { - struct vgic_dist *vgic = &kvm->arch.vgic; + struct vgic_dist *d = &kvm->arch.vgic; + struct vgic_redist_region *rdreg; + struct list_head *rd_regions = &d->rd_regions; + size_t size = count * KVM_VGIC_V3_REDIST_SIZE; int ret; - /* vgic_check_ioaddr makes sure we don't do this twice */ - ret = vgic_check_ioaddr(kvm, &vgic->vgic_redist_base, addr, SZ_64K); - if (ret) - return ret; + /* single rdist region already set ?*/ + if (!count && !list_empty(rd_regions)) + return -EINVAL; - vgic->vgic_redist_base = addr; - if (!vgic_v3_check_base(kvm)) { - vgic->vgic_redist_base = VGIC_ADDR_UNDEF; + /* cross the end of memory ? */ + if (base + size < base) return -EINVAL; + + if (list_empty(rd_regions)) { + if (index != 0) + return -EINVAL; + } else { + rdreg = list_last_entry(rd_regions, + struct vgic_redist_region, list); + if (index != rdreg->index + 1) + return -EINVAL; + + /* Cannot add an explicitly sized regions after legacy region */ + if (!rdreg->count) + return -EINVAL; } /* + * For legacy single-region redistributor regions (!count), + * check that the redistributor region does not overlap with the + * distributor's address space. + */ + if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && + vgic_dist_overlap(kvm, base, size)) + return -EINVAL; + + /* collision with any other rdist region? */ + if (vgic_v3_rdist_overlap(kvm, base, size)) + return -EINVAL; + + rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL); + if (!rdreg) + return -ENOMEM; + + rdreg->base = VGIC_ADDR_UNDEF; + + ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K); + if (ret) + goto free; + + rdreg->base = base; + rdreg->count = count; + rdreg->free_index = 0; + rdreg->index = index; + + list_add_tail(&rdreg->list, rd_regions); + return 0; +free: + kfree(rdreg); + return ret; +} + +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count) +{ + int ret; + + ret = vgic_v3_insert_redist_region(kvm, index, addr, count); + if (ret) + return ret; + + /* * Register iodevs for each existing VCPU. Adding more VCPUs * afterwards will register the iodevs when needed. */ diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index c7423f3768e5..ff7dc890941a 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -344,7 +344,7 @@ retry: bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; - ret = kvm_read_guest(kvm, ptr, &val, 1); + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; @@ -397,7 +397,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) ptr = pendbase + byte_offset; if (byte_offset != last_byte_offset) { - ret = kvm_read_guest(kvm, ptr, &val, 1); + ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; last_byte_offset = byte_offset; @@ -419,6 +419,29 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) return 0; } +/** + * vgic_v3_rdist_overlap - check if a region overlaps with any + * existing redistributor region + * + * @kvm: kvm handle + * @base: base of the region + * @size: size of region + * + * Return: true if there is an overlap + */ +bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) +{ + struct vgic_dist *d = &kvm->arch.vgic; + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, &d->rd_regions, list) { + if ((base + size > rdreg->base) && + (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) + return true; + } + return false; +} + /* * Check for overlapping regions and for regions crossing the end of memory * for base addresses which have already been set. @@ -426,41 +449,83 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) bool vgic_v3_check_base(struct kvm *kvm) { struct vgic_dist *d = &kvm->arch.vgic; - gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE; - - redist_size *= atomic_read(&kvm->online_vcpus); + struct vgic_redist_region *rdreg; if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) return false; - if (!IS_VGIC_ADDR_UNDEF(d->vgic_redist_base) && - d->vgic_redist_base + redist_size < d->vgic_redist_base) - return false; + list_for_each_entry(rdreg, &d->rd_regions, list) { + if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) < + rdreg->base) + return false; + } - /* Both base addresses must be set to check if they overlap */ - if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) || - IS_VGIC_ADDR_UNDEF(d->vgic_redist_base)) + if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) return true; - if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base) - return true; - if (d->vgic_redist_base + redist_size <= d->vgic_dist_base) - return true; + return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, + KVM_VGIC_V3_DIST_SIZE); +} - return false; +/** + * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one + * which has free space to put a new rdist region. + * + * @rd_regions: redistributor region list head + * + * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). + * Stride between redistributors is 0 and regions are filled in the index order. + * + * Return: the redist region handle, if any, that has space to map a new rdist + * region. + */ +struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) +{ + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, rd_regions, list) { + if (!vgic_v3_redist_region_full(rdreg)) + return rdreg; + } + return NULL; } +struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, + u32 index) +{ + struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; + struct vgic_redist_region *rdreg; + + list_for_each_entry(rdreg, rd_regions, list) { + if (rdreg->index == index) + return rdreg; + } + return NULL; +} + + int vgic_v3_map_resources(struct kvm *kvm) { - int ret = 0; struct vgic_dist *dist = &kvm->arch.vgic; + struct kvm_vcpu *vcpu; + int ret = 0; + int c; if (vgic_ready(kvm)) goto out; - if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || - IS_VGIC_ADDR_UNDEF(dist->vgic_redist_base)) { + kvm_for_each_vcpu(c, vcpu, kvm) { + struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + + if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { + kvm_debug("vcpu %d redistributor base not set\n", c); + ret = -ENXIO; + goto out; + } + } + + if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_err("Need to set vgic distributor addresses first\n"); ret = -ENXIO; goto out; diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index 97bfba8d9a59..33c8325c8f35 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -43,9 +43,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { * kvm->lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) - * vgic_cpu->ap_list_lock - * kvm->lpi_list_lock - * vgic_irq->irq_lock + * vgic_cpu->ap_list_lock must be taken with IRQs disabled + * kvm->lpi_list_lock must be taken with IRQs disabled + * vgic_irq->irq_lock must be taken with IRQs disabled + * + * As the ap_list_lock might be taken from the timer interrupt handler, + * we have to disable IRQs before taking this lock and everything lower + * than it. * * If you need to take multiple locks, always take the upper lock first, * then the lower ones, e.g. first take the its_lock, then the irq_lock. @@ -72,8 +76,9 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = NULL; + unsigned long flags; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) { if (irq->intid != intid) @@ -89,7 +94,7 @@ static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid) irq = NULL; out_unlock: - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return irq; } @@ -134,19 +139,20 @@ static void vgic_irq_release(struct kref *ref) void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { struct vgic_dist *dist = &kvm->arch.vgic; + unsigned long flags; if (irq->intid < VGIC_MIN_LPI) return; - spin_lock(&dist->lpi_list_lock); + spin_lock_irqsave(&dist->lpi_list_lock, flags); if (!kref_put(&irq->refcount, vgic_irq_release)) { - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); return; }; list_del(&irq->lpi_list); dist->lpi_list_count--; - spin_unlock(&dist->lpi_list_lock); + spin_unlock_irqrestore(&dist->lpi_list_lock, flags); kfree(irq); } diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 32c25d42c93f..6879cf48652a 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -96,6 +96,13 @@ /* we only support 64 kB translation table page size */ #define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16) +#define KVM_VGIC_V3_RDIST_INDEX_MASK GENMASK_ULL(11, 0) +#define KVM_VGIC_V3_RDIST_FLAGS_MASK GENMASK_ULL(15, 12) +#define KVM_VGIC_V3_RDIST_FLAGS_SHIFT 12 +#define KVM_VGIC_V3_RDIST_BASE_MASK GENMASK_ULL(51, 16) +#define KVM_VGIC_V3_RDIST_COUNT_MASK GENMASK_ULL(63, 52) +#define KVM_VGIC_V3_RDIST_COUNT_SHIFT 52 + /* Requires the irq_lock to be held by the caller. */ static inline bool irq_is_pending(struct vgic_irq *irq) { @@ -215,7 +222,7 @@ int vgic_v3_probe(const struct gic_kvm_info *info); int vgic_v3_map_resources(struct kvm *kvm); int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq); int vgic_v3_save_pending_tables(struct kvm *kvm); -int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr); +int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count); int vgic_register_redist_iodev(struct kvm_vcpu *vcpu); bool vgic_v3_check_base(struct kvm *kvm); @@ -265,6 +272,39 @@ static inline int vgic_v3_max_apr_idx(struct kvm_vcpu *vcpu) } } +static inline bool +vgic_v3_redist_region_full(struct vgic_redist_region *region) +{ + if (!region->count) + return false; + + return (region->free_index >= region->count); +} + +struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rdregs); + +static inline size_t +vgic_v3_rd_region_size(struct kvm *kvm, struct vgic_redist_region *rdreg) +{ + if (!rdreg->count) + return atomic_read(&kvm->online_vcpus) * KVM_VGIC_V3_REDIST_SIZE; + else + return rdreg->count * KVM_VGIC_V3_REDIST_SIZE; +} + +struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, + u32 index); + +bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size); + +static inline bool vgic_dist_overlap(struct kvm *kvm, gpa_t base, size_t size) +{ + struct vgic_dist *d = &kvm->arch.vgic; + + return (base + size > d->vgic_dist_base) && + (base < d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE); +} + int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its, u32 devid, u32 eventid, struct vgic_irq **irq); struct vgic_its *vgic_msi_to_its(struct kvm *kvm, struct kvm_msi *msi); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c7b2e927f699..c5f6a552e486 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -203,29 +203,47 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) return true; } -bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + unsigned long *vcpu_bitmap, cpumask_var_t tmp) { int i, cpu, me; - cpumask_var_t cpus; - bool called; struct kvm_vcpu *vcpu; - - zalloc_cpumask_var(&cpus, GFP_ATOMIC); + bool called; me = get_cpu(); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!test_bit(i, vcpu_bitmap)) + continue; + kvm_make_request(req, vcpu); cpu = vcpu->cpu; if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) continue; - if (cpus != NULL && cpu != -1 && cpu != me && + if (tmp != NULL && cpu != -1 && cpu != me && kvm_request_needs_ipi(vcpu, req)) - __cpumask_set_cpu(cpu, cpus); + __cpumask_set_cpu(cpu, tmp); } - called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); + + called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); put_cpu(); + + return called; +} + +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +{ + cpumask_var_t cpus; + bool called; + static unsigned long vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)] + = {[0 ... BITS_TO_LONGS(KVM_MAX_VCPUS)-1] = ULONG_MAX}; + + zalloc_cpumask_var(&cpus, GFP_ATOMIC); + + called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap, cpus); + free_cpumask_var(cpus); return called; } @@ -2550,8 +2568,13 @@ static long kvm_vcpu_ioctl(struct file *filp, oldpid = rcu_access_pointer(vcpu->pid); if (unlikely(oldpid != current->pids[PIDTYPE_PID].pid)) { /* The thread running this VCPU changed. */ - struct pid *newpid = get_task_pid(current, PIDTYPE_PID); + struct pid *newpid; + + r = kvm_arch_vcpu_run_pid_change(vcpu); + if (r) + break; + newpid = get_task_pid(current, PIDTYPE_PID); rcu_assign_pointer(vcpu->pid, newpid); if (oldpid) synchronize_rcu(); |