diff --git a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt index 23e3abc3fdef0c..c88919480d373e 100644 --- a/Documentation/devicetree/bindings/input/atmel,maxtouch.txt +++ b/Documentation/devicetree/bindings/input/atmel,maxtouch.txt @@ -4,6 +4,13 @@ Required properties: - compatible: atmel,maxtouch + The following compatibles have been used in various products but are + deprecated: + atmel,qt602240_ts + atmel,atmel_mxt_ts + atmel,atmel_mxt_tp + atmel,mXT224 + - reg: The I2C address of the device - interrupts: The sink for the touchpad's IRQ output diff --git a/Documentation/i2c/dev-interface b/Documentation/i2c/dev-interface index d04e6e4964ee7f..fbed645ccd7563 100644 --- a/Documentation/i2c/dev-interface +++ b/Documentation/i2c/dev-interface @@ -9,8 +9,8 @@ i2c adapters present on your system at a given time. i2cdetect is part of the i2c-tools package. I2C device files are character device files with major device number 89 -and a minor device number corresponding to the number assigned as -explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ..., +and a minor device number corresponding to the number assigned as +explained above. They should be called "i2c-%d" (i2c-0, i2c-1, ..., i2c-10, ...). All 256 minor device numbers are reserved for i2c. @@ -23,11 +23,6 @@ First, you need to include these two headers: #include #include -(Please note that there are two files named "i2c-dev.h" out there. One is -distributed with the Linux kernel and the other one is included in the -source tree of i2c-tools. They used to be different in content but since 2012 -they're identical. You should use "linux/i2c-dev.h"). - Now, you have to decide which adapter you want to access. You should inspect /sys/class/i2c-dev/ or run "i2cdetect -l" to decide this. Adapter numbers are assigned somewhat dynamically, so you can not @@ -38,7 +33,7 @@ Next thing, open the device file, as follows: int file; int adapter_nr = 2; /* probably dynamically determined */ char filename[20]; - + snprintf(filename, 19, "/dev/i2c-%d", adapter_nr); file = open(filename, O_RDWR); if (file < 0) { @@ -72,8 +67,10 @@ the device supports them. Both are illustrated below. /* res contains the read word */ } - /* Using I2C Write, equivalent of - i2c_smbus_write_word_data(file, reg, 0x6543) */ + /* + * Using I2C Write, equivalent of + * i2c_smbus_write_word_data(file, reg, 0x6543) + */ buf[0] = reg; buf[1] = 0x43; buf[2] = 0x65; @@ -140,14 +137,14 @@ ioctl(file, I2C_RDWR, struct i2c_rdwr_ioctl_data *msgset) set in each message, overriding the values set with the above ioctl's. ioctl(file, I2C_SMBUS, struct i2c_smbus_ioctl_data *args) - Not meant to be called directly; instead, use the access functions - below. + If possible, use the provided i2c_smbus_* methods described below instead + of issuing direct ioctls. You can do plain i2c transactions by using read(2) and write(2) calls. You do not need to pass the address byte; instead, set it through ioctl I2C_SLAVE before you try to access the device. -You can do SMBus level transactions (see documentation file smbus-protocol +You can do SMBus level transactions (see documentation file smbus-protocol for details) through the following functions: __s32 i2c_smbus_write_quick(int file, __u8 value); __s32 i2c_smbus_read_byte(int file); @@ -158,7 +155,7 @@ for details) through the following functions: __s32 i2c_smbus_write_word_data(int file, __u8 command, __u16 value); __s32 i2c_smbus_process_call(int file, __u8 command, __u16 value); __s32 i2c_smbus_read_block_data(int file, __u8 command, __u8 *values); - __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length, + __s32 i2c_smbus_write_block_data(int file, __u8 command, __u8 length, __u8 *values); All these transactions return -1 on failure; you can read errno to see what happened. The 'write' transactions return 0 on success; the @@ -166,10 +163,9 @@ what happened. The 'write' transactions return 0 on success; the returns the number of values read. The block buffers need not be longer than 32 bytes. -The above functions are all inline functions, that resolve to calls to -the i2c_smbus_access function, that on its turn calls a specific ioctl -with the data in a specific format. Read the source code if you -want to know what happens behind the screens. +The above functions are made available by linking against the libi2c library, +which is provided by the i2c-tools project. See: +https://git.kernel.org/pub/scm/utils/i2c-tools/i2c-tools.git/. Implementation details diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst index e45f0786f3f9ef..67d9c38e95eb54 100644 --- a/Documentation/trace/ftrace.rst +++ b/Documentation/trace/ftrace.rst @@ -461,9 +461,17 @@ of ftrace. Here is a list of some of the key files: and ticks at the same rate as the hardware clocksource. boot: - Same as mono. Used to be a separate clock which accounted - for the time spent in suspend while CLOCK_MONOTONIC did - not. + This is the boot clock (CLOCK_BOOTTIME) and is based on the + fast monotonic clock, but also accounts for time spent in + suspend. Since the clock access is designed for use in + tracing in the suspend path, some side effects are possible + if clock is accessed after the suspend time is accounted before + the fast mono clock is updated. In this case, the clock update + appears to happen slightly sooner than it normally would have. + Also on 32-bit systems, it's possible that the 64-bit boot offset + sees a partial update. These effects are rare and post + processing should be able to handle them. See comments in the + ktime_get_boot_fast_ns() function for more information. To set a clock, simply echo the clock name into this file:: diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 1c7958b57fe9fd..758bf403a169da 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1960,6 +1960,9 @@ ARM 32-bit VFP control registers have the following id bit patterns: ARM 64-bit FP registers have the following id bit patterns: 0x4030 0000 0012 0 +ARM firmware pseudo-registers have the following bit pattern: + 0x4030 0000 0014 + arm64 registers are mapped using the lower 32 bits. The upper 16 of that is the register group type, or coprocessor number: @@ -1976,6 +1979,9 @@ arm64 CCSIDR registers are demultiplexed by CSSELR value: arm64 system registers have the following id bit patterns: 0x6030 0000 0013 +arm64 firmware pseudo-registers have the following bit pattern: + 0x6030 0000 0014 + MIPS registers are mapped using the lower 32 bits. The upper 16 of that is the register group type: @@ -2510,7 +2516,8 @@ Possible features: and execute guest code when KVM_RUN is called. - KVM_ARM_VCPU_EL1_32BIT: Starts the CPU in a 32bit mode. Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only). - - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 for the CPU. + - KVM_ARM_VCPU_PSCI_0_2: Emulate PSCI v0.2 (or a future revision + backward compatible with v0.2) for the CPU. Depends on KVM_CAP_ARM_PSCI_0_2. - KVM_ARM_VCPU_PMU_V3: Emulate PMUv3 for the CPU. Depends on KVM_CAP_ARM_PMU_V3. diff --git a/Documentation/virtual/kvm/arm/psci.txt b/Documentation/virtual/kvm/arm/psci.txt new file mode 100644 index 00000000000000..aafdab887b047b --- /dev/null +++ b/Documentation/virtual/kvm/arm/psci.txt @@ -0,0 +1,30 @@ +KVM implements the PSCI (Power State Coordination Interface) +specification in order to provide services such as CPU on/off, reset +and power-off to the guest. + +The PSCI specification is regularly updated to provide new features, +and KVM implements these updates if they make sense from a virtualization +point of view. + +This means that a guest booted on two different versions of KVM can +observe two different "firmware" revisions. This could cause issues if +a given guest is tied to a particular PSCI revision (unlikely), or if +a migration causes a different PSCI version to be exposed out of the +blue to an unsuspecting guest. + +In order to remedy this situation, KVM exposes a set of "firmware +pseudo-registers" that can be manipulated using the GET/SET_ONE_REG +interface. These registers can be saved/restored by userspace, and set +to a convenient value if required. + +The following register is defined: + +* KVM_REG_ARM_PSCI_VERSION: + + - Only valid if the vcpu has the KVM_ARM_VCPU_PSCI_0_2 feature set + (and thus has already been initialized) + - Returns the current PSCI version on GET_ONE_REG (defaulting to the + highest PSCI version implemented by KVM and compatible with v0.2) + - Allows any PSCI version implemented by KVM and compatible with + v0.2 to be set with SET_ONE_REG + - Affects the whole VM (even if the register view is per-vcpu) diff --git a/MAINTAINERS b/MAINTAINERS index 3e41e12a88a4d5..eab763f17aab8d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -564,8 +564,9 @@ S: Maintained F: drivers/media/dvb-frontends/af9033* AFFS FILE SYSTEM +M: David Sterba L: linux-fsdevel@vger.kernel.org -S: Orphan +S: Odd Fixes F: Documentation/filesystems/affs.txt F: fs/affs/ @@ -7744,7 +7745,7 @@ F: arch/x86/include/asm/svm.h F: arch/x86/kvm/svm.c KERNEL VIRTUAL MACHINE FOR ARM (KVM/arm) -M: Christoffer Dall +M: Christoffer Dall M: Marc Zyngier L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu @@ -7758,7 +7759,7 @@ F: virt/kvm/arm/ F: include/kvm/arm_* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) -M: Christoffer Dall +M: Christoffer Dall M: Marc Zyngier L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.cs.columbia.edu @@ -13852,7 +13853,6 @@ S: Supported F: drivers/iommu/tegra* TEGRA KBC DRIVER -M: Rakesh Iyer M: Laxman Dewangan S: Supported F: drivers/input/keyboard/tegra-kbc.c diff --git a/Makefile b/Makefile index 83b6c541565ac4..619a85ad716b43 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Fearless Coyote # *DOCUMENTATION* diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index c6a749568dd6c4..c7c28c885a1946 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -77,6 +77,9 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; int max_vcpus; + + /* Mandated version of PSCI */ + u32 psci_version; }; #define KVM_NR_MEM_OBJS 40 diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h index 2ba95d6fe852d7..caae4843cb7001 100644 --- a/arch/arm/include/uapi/asm/kvm.h +++ b/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/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 1e0784ebbfd6db..a18f33edc471a9 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include @@ -176,6 +177,7 @@ static unsigned long num_core_regs(void) unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) { return num_core_regs() + kvm_arm_num_coproc_regs(vcpu) + + kvm_arm_get_fw_num_regs(vcpu) + NUM_TIMER_REGS; } @@ -196,6 +198,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) uindices++; } + ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); + if (ret) + return ret; + uindices += kvm_arm_get_fw_num_regs(vcpu); + ret = copy_timer_indices(vcpu, uindices); if (ret) return ret; @@ -214,6 +221,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return get_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_get_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return get_timer_reg(vcpu, reg); @@ -230,6 +240,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return set_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_set_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return set_timer_reg(vcpu, reg); diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index ab46bc70add636..469de8acd06f5f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -75,6 +75,9 @@ struct kvm_arch { /* Interrupt controller */ struct vgic_dist vgic; + + /* Mandated version of PSCI */ + u32 psci_version; }; #define KVM_NR_MEM_OBJS 40 diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index 9abbf30446545a..04b3256f8e6d5f 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/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/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 959e50d2588c0f..56a0260ceb11a9 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -205,7 +206,7 @@ static int get_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu) { return num_core_regs() + kvm_arm_num_sys_reg_descs(vcpu) - + NUM_TIMER_REGS; + + kvm_arm_get_fw_num_regs(vcpu) + NUM_TIMER_REGS; } /** @@ -225,6 +226,11 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) uindices++; } + ret = kvm_arm_copy_fw_reg_indices(vcpu, uindices); + if (ret) + return ret; + uindices += kvm_arm_get_fw_num_regs(vcpu); + ret = copy_timer_indices(vcpu, uindices); if (ret) return ret; @@ -243,6 +249,9 @@ int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return get_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_get_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return get_timer_reg(vcpu, reg); @@ -259,6 +268,9 @@ int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_CORE) return set_core_reg(vcpu, reg); + if ((reg->id & KVM_REG_ARM_COPROC_MASK) == KVM_REG_ARM_FW) + return kvm_arm_set_fw_reg(vcpu, reg); + if (is_timer_reg(reg->id)) return set_timer_reg(vcpu, reg); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 806b0b126a644d..6e3b969391fdbb 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -996,14 +996,12 @@ static u64 read_id_reg(struct sys_reg_desc const *r, bool raz) if (id == SYS_ID_AA64PFR0_EL1) { if (val & (0xfUL << ID_AA64PFR0_SVE_SHIFT)) - pr_err_once("kvm [%i]: SVE unsupported for guests, suppressing\n", - task_pid_nr(current)); + kvm_debug("SVE unsupported for guests, suppressing\n"); val &= ~(0xfUL << ID_AA64PFR0_SVE_SHIFT); } else if (id == SYS_ID_AA64MMFR1_EL1) { if (val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT)) - pr_err_once("kvm [%i]: LORegions unsupported for guests, suppressing\n", - task_pid_nr(current)); + kvm_debug("LORegions unsupported for guests, suppressing\n"); val &= ~(0xfUL << ID_AA64MMFR1_LOR_SHIFT); } diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h index 9e8621d94ee9c0..e17262ad125e7e 100644 --- a/arch/hexagon/include/asm/io.h +++ b/arch/hexagon/include/asm/io.h @@ -216,6 +216,12 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, memcpy((void *) dst, src, count); } +static inline void memset_io(volatile void __iomem *addr, int value, + size_t size) +{ + memset((void __force *)addr, value, size); +} + #define PCI_IO_ADDR (volatile void __iomem *) /* diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c index 617506d1a55966..7cd0a225926965 100644 --- a/arch/hexagon/lib/checksum.c +++ b/arch/hexagon/lib/checksum.c @@ -199,3 +199,4 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum) memcpy(dst, src, len); return csum_partial(dst, len, sum); } +EXPORT_SYMBOL(csum_partial_copy_nocheck); diff --git a/arch/powerpc/include/asm/powernv.h b/arch/powerpc/include/asm/powernv.h index d1c2d2e658cf4d..2f3ff7a278815a 100644 --- a/arch/powerpc/include/asm/powernv.h +++ b/arch/powerpc/include/asm/powernv.h @@ -15,7 +15,7 @@ extern void powernv_set_nmmu_ptcr(unsigned long ptcr); extern struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, unsigned long flags, - struct npu_context *(*cb)(struct npu_context *, void *), + void (*cb)(struct npu_context *, void *), void *priv); extern void pnv_npu2_destroy_context(struct npu_context *context, struct pci_dev *gpdev); diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c index fe6fc63251fec7..38c5b4764bfed0 100644 --- a/arch/powerpc/kernel/mce_power.c +++ b/arch/powerpc/kernel/mce_power.c @@ -441,7 +441,6 @@ static int mce_handle_ierror(struct pt_regs *regs, if (pfn != ULONG_MAX) { *phys_addr = (pfn << PAGE_SHIFT); - handled = 1; } } } @@ -532,9 +531,7 @@ static int mce_handle_derror(struct pt_regs *regs, * kernel/exception-64s.h */ if (get_paca()->in_mce < MAX_MCE_DEPTH) - if (!mce_find_instr_ea_and_pfn(regs, addr, - phys_addr)) - handled = 1; + mce_find_instr_ea_and_pfn(regs, addr, phys_addr); } found = 1; } @@ -572,7 +569,7 @@ static long mce_handle_error(struct pt_regs *regs, const struct mce_ierror_table itable[]) { struct mce_error_info mce_err = { 0 }; - uint64_t addr, phys_addr; + uint64_t addr, phys_addr = ULONG_MAX; uint64_t srr1 = regs->msr; long handled; diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e16ec7b3b427ea..9ca7148b5881a0 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -566,10 +566,35 @@ void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) #endif #ifdef CONFIG_NMI_IPI -static void stop_this_cpu(struct pt_regs *regs) -#else +static void nmi_stop_this_cpu(struct pt_regs *regs) +{ + /* + * This is a special case because it never returns, so the NMI IPI + * handling would never mark it as done, which makes any later + * smp_send_nmi_ipi() call spin forever. Mark it done now. + * + * IRQs are already hard disabled by the smp_handle_nmi_ipi. + */ + nmi_ipi_lock(); + nmi_ipi_busy_count--; + nmi_ipi_unlock(); + + /* Remove this CPU */ + set_cpu_online(smp_processor_id(), false); + + spin_begin(); + while (1) + spin_cpu_relax(); +} + +void smp_send_stop(void) +{ + smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, nmi_stop_this_cpu, 1000000); +} + +#else /* CONFIG_NMI_IPI */ + static void stop_this_cpu(void *dummy) -#endif { /* Remove this CPU */ set_cpu_online(smp_processor_id(), false); @@ -582,12 +607,22 @@ static void stop_this_cpu(void *dummy) void smp_send_stop(void) { -#ifdef CONFIG_NMI_IPI - smp_send_nmi_ipi(NMI_IPI_ALL_OTHERS, stop_this_cpu, 1000000); -#else + static bool stopped = false; + + /* + * Prevent waiting on csd lock from a previous smp_send_stop. + * This is racy, but in general callers try to do the right + * thing and only fire off one smp_send_stop (e.g., see + * kernel/panic.c) + */ + if (stopped) + return; + + stopped = true; + smp_call_function(stop_this_cpu, NULL, 0); -#endif } +#endif /* CONFIG_NMI_IPI */ struct thread_info *current_set[NR_CPUS]; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 6038e2e7aee03c..876d4f294fdd89 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -305,6 +305,13 @@ void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu) kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_FP_UNAVAIL); } +#ifdef CONFIG_ALTIVEC +void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu) +{ + kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_UNAVAIL); +} +#endif + void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu) { kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DECREMENTER); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 737f8a4632ccc6..c3c39b02b2ba7b 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -133,6 +133,7 @@ int __meminit arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap * start, start + size, rc); return -EFAULT; } + flush_inval_dcache_range(start, start + size); return __add_pages(nid, start_pfn, nr_pages, altmap, want_memblock); } @@ -159,6 +160,7 @@ int __meminit arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap /* Remove htab bolted mappings for this section of memory */ start = (unsigned long)__va(start); + flush_inval_dcache_range(start, start + size); ret = remove_section_mapping(start, start + size); /* Ensure all vmalloc mappings are flushed in case they also diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index de470caf07848e..fc222a0c2ac46b 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -82,19 +82,6 @@ static const struct file_operations memtrace_fops = { .open = simple_open, }; -static void flush_memory_region(u64 base, u64 size) -{ - unsigned long line_size = ppc64_caches.l1d.size; - u64 end = base + size; - u64 addr; - - base = round_down(base, line_size); - end = round_up(end, line_size); - - for (addr = base; addr < end; addr += line_size) - asm volatile("dcbf 0,%0" : "=r" (addr) :: "memory"); -} - static int check_memblock_online(struct memory_block *mem, void *arg) { if (mem->state != MEM_ONLINE) @@ -132,10 +119,6 @@ static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages) walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE, change_memblock_state); - /* RCU grace period? */ - flush_memory_region((u64)__va(start_pfn << PAGE_SHIFT), - nr_pages << PAGE_SHIFT); - lock_device_hotplug(); remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT); unlock_device_hotplug(); diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index 69a4f9e8bd554f..525e966dce3418 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -33,6 +33,19 @@ #define npu_to_phb(x) container_of(x, struct pnv_phb, npu) +/* + * spinlock to protect initialisation of an npu_context for a particular + * mm_struct. + */ +static DEFINE_SPINLOCK(npu_context_lock); + +/* + * When an address shootdown range exceeds this threshold we invalidate the + * entire TLB on the GPU for the given PID rather than each specific address in + * the range. + */ +#define ATSD_THRESHOLD (2*1024*1024) + /* * Other types of TCE cache invalidation are not functional in the * hardware. @@ -401,7 +414,7 @@ struct npu_context { bool nmmu_flush; /* Callback to stop translation requests on a given GPU */ - struct npu_context *(*release_cb)(struct npu_context *, void *); + void (*release_cb)(struct npu_context *context, void *priv); /* * Private pointer passed to the above callback for usage by @@ -671,11 +684,19 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, struct npu_context *npu_context = mn_to_npu_context(mn); unsigned long address; - for (address = start; address < end; address += PAGE_SIZE) - mmio_invalidate(npu_context, 1, address, false); + if (end - start > ATSD_THRESHOLD) { + /* + * Just invalidate the entire PID if the address range is too + * large. + */ + mmio_invalidate(npu_context, 0, 0, true); + } else { + for (address = start; address < end; address += PAGE_SIZE) + mmio_invalidate(npu_context, 1, address, false); - /* Do the flush only on the final addess == end */ - mmio_invalidate(npu_context, 1, address, true); + /* Do the flush only on the final addess == end */ + mmio_invalidate(npu_context, 1, address, true); + } } static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { @@ -696,11 +717,12 @@ static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { * Returns an error if there no contexts are currently available or a * npu_context which should be passed to pnv_npu2_handle_fault(). * - * mmap_sem must be held in write mode. + * mmap_sem must be held in write mode and must not be called from interrupt + * context. */ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, unsigned long flags, - struct npu_context *(*cb)(struct npu_context *, void *), + void (*cb)(struct npu_context *, void *), void *priv) { int rc; @@ -743,7 +765,9 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, /* * Setup the NPU context table for a particular GPU. These need to be * per-GPU as we need the tables to filter ATSDs when there are no - * active contexts on a particular GPU. + * active contexts on a particular GPU. It is safe for these to be + * called concurrently with destroy as the OPAL call takes appropriate + * locks and refcounts on init/destroy. */ rc = opal_npu_init_context(nphb->opal_id, mm->context.id, flags, PCI_DEVID(gpdev->bus->number, gpdev->devfn)); @@ -754,8 +778,29 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, * We store the npu pci device so we can more easily get at the * associated npus. */ + spin_lock(&npu_context_lock); npu_context = mm->context.npu_context; + if (npu_context) { + if (npu_context->release_cb != cb || + npu_context->priv != priv) { + spin_unlock(&npu_context_lock); + opal_npu_destroy_context(nphb->opal_id, mm->context.id, + PCI_DEVID(gpdev->bus->number, + gpdev->devfn)); + return ERR_PTR(-EINVAL); + } + + WARN_ON(!kref_get_unless_zero(&npu_context->kref)); + } + spin_unlock(&npu_context_lock); + if (!npu_context) { + /* + * We can set up these fields without holding the + * npu_context_lock as the npu_context hasn't been returned to + * the caller meaning it can't be destroyed. Parallel allocation + * is protected against by mmap_sem. + */ rc = -ENOMEM; npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL); if (npu_context) { @@ -774,8 +819,6 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev, } mm->context.npu_context = npu_context; - } else { - WARN_ON(!kref_get_unless_zero(&npu_context->kref)); } npu_context->release_cb = cb; @@ -814,15 +857,16 @@ static void pnv_npu2_release_context(struct kref *kref) mm_context_remove_copro(npu_context->mm); npu_context->mm->context.npu_context = NULL; - mmu_notifier_unregister(&npu_context->mn, - npu_context->mm); - - kfree(npu_context); } +/* + * Destroy a context on the given GPU. May free the npu_context if it is no + * longer active on any GPUs. Must not be called from interrupt context. + */ void pnv_npu2_destroy_context(struct npu_context *npu_context, struct pci_dev *gpdev) { + int removed; struct pnv_phb *nphb; struct npu *npu; struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0); @@ -844,7 +888,21 @@ void pnv_npu2_destroy_context(struct npu_context *npu_context, WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL); opal_npu_destroy_context(nphb->opal_id, npu_context->mm->context.id, PCI_DEVID(gpdev->bus->number, gpdev->devfn)); - kref_put(&npu_context->kref, pnv_npu2_release_context); + spin_lock(&npu_context_lock); + removed = kref_put(&npu_context->kref, pnv_npu2_release_context); + spin_unlock(&npu_context_lock); + + /* + * We need to do this outside of pnv_npu2_release_context so that it is + * outside the spinlock as mmu_notifier_destroy uses SRCU. + */ + if (removed) { + mmu_notifier_unregister(&npu_context->mn, + npu_context->mm); + + kfree(npu_context); + } + } EXPORT_SYMBOL(pnv_npu2_destroy_context); diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c index f8868864f373ed..aa2a5139462ea5 100644 --- a/arch/powerpc/platforms/powernv/opal-rtc.c +++ b/arch/powerpc/platforms/powernv/opal-rtc.c @@ -48,10 +48,12 @@ unsigned long __init opal_get_boot_time(void) while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); - if (rc == OPAL_BUSY_EVENT) + if (rc == OPAL_BUSY_EVENT) { + mdelay(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); - else if (rc == OPAL_BUSY) - mdelay(10); + } else if (rc == OPAL_BUSY) { + mdelay(OPAL_BUSY_DELAY_MS); + } } if (rc != OPAL_SUCCESS) return 0; diff --git a/arch/sparc/include/uapi/asm/oradax.h b/arch/sparc/include/uapi/asm/oradax.h index 722951908b0a45..4f6676fe4bcc89 100644 --- a/arch/sparc/include/uapi/asm/oradax.h +++ b/arch/sparc/include/uapi/asm/oradax.h @@ -3,7 +3,7 @@ * * This program is free software: you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, either version 3 of the License, or + * the Free Software Foundation, either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, diff --git a/arch/sparc/kernel/vio.c b/arch/sparc/kernel/vio.c index 1a0fa10cb6b721..32bae68e34c1b6 100644 --- a/arch/sparc/kernel/vio.c +++ b/arch/sparc/kernel/vio.c @@ -403,7 +403,7 @@ static struct vio_dev *vio_create_one(struct mdesc_handle *hp, u64 mp, if (err) { printk(KERN_ERR "VIO: Could not register device %s, err=%d\n", dev_name(&vdev->dev), err); - kfree(vdev); + put_device(&vdev->dev); return NULL; } if (vdev->dp) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 00fcf81f2c569b..c07f492b871a8b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -52,6 +52,7 @@ config X86 select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER + select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV if X86_64 @@ -273,6 +274,9 @@ config ARCH_HAS_CPU_RELAX config ARCH_HAS_CACHE_LINE_SIZE def_bool y +config ARCH_HAS_FILTER_PGPROT + def_bool y + config HAVE_SETUP_PER_CPU_AREA def_bool y diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 9af927e59d4974..9de7f1e1dede7f 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -84,13 +84,13 @@ ENTRY(entry_SYSENTER_compat) pushq %rdx /* pt_regs->dx */ pushq %rcx /* pt_regs->cx */ pushq $-ENOSYS /* pt_regs->ax */ - pushq $0 /* pt_regs->r8 = 0 */ + pushq %r8 /* pt_regs->r8 */ xorl %r8d, %r8d /* nospec r8 */ - pushq $0 /* pt_regs->r9 = 0 */ + pushq %r9 /* pt_regs->r9 */ xorl %r9d, %r9d /* nospec r9 */ - pushq $0 /* pt_regs->r10 = 0 */ + pushq %r10 /* pt_regs->r10 */ xorl %r10d, %r10d /* nospec r10 */ - pushq $0 /* pt_regs->r11 = 0 */ + pushq %r11 /* pt_regs->r11 */ xorl %r11d, %r11d /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ xorl %ebx, %ebx /* nospec rbx */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 607bf565a90c97..707b2a96e516b5 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3339,7 +3339,8 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; - flip_smm_bit(&x86_pmu.attr_freeze_on_smi); + if (x86_pmu.version > 1) + flip_smm_bit(&x86_pmu.attr_freeze_on_smi); if (!cpuc->shared_regs) return; @@ -3502,6 +3503,8 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_dying = intel_pmu_cpu_dying, }; +static struct attribute *intel_pmu_attrs[]; + static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, @@ -3533,6 +3536,8 @@ static __initconst const struct x86_pmu intel_pmu = { .format_attrs = intel_arch3_formats_attr, .events_sysfs_show = intel_event_sysfs_show, + .attrs = intel_pmu_attrs, + .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, @@ -3911,8 +3916,6 @@ __init int intel_pmu_init(void) x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); - - x86_pmu.attrs = intel_pmu_attrs; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index d554c11e01ff46..578793e97431da 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/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/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 404c5fdff859de..548d90bbf919e8 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -34,11 +34,6 @@ * (0x80 is the syscall vector, 0x30-0x3f are for ISA) */ #define FIRST_EXTERNAL_VECTOR 0x20 -/* - * We start allocating at 0x21 to spread out vectors evenly between - * priority levels. (0x80 is the syscall vector) - */ -#define VECTOR_OFFSET_START 1 /* * Reserve the lowest usable vector (and hence lowest priority) 0x20 for @@ -119,8 +114,6 @@ #define FIRST_SYSTEM_VECTOR NR_VECTORS #endif -#define FPU_IRQ 13 - /* * Size the maximum number of interrupts. * diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h index b885a961a150f0..a34897aef2c295 100644 --- a/arch/x86/include/asm/jailhouse_para.h +++ b/arch/x86/include/asm/jailhouse_para.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL2.0 */ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Jailhouse paravirt detection diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5f49b4ff0c2484..f1633de5a67592 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -601,6 +601,11 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) #define canon_pgprot(p) __pgprot(massage_pgprot(p)) +static inline pgprot_t arch_filter_pgprot(pgprot_t prot) +{ + return canon_pgprot(prot); +} + static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, enum page_cache_mode pcm, enum page_cache_mode new_pcm) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index d5c21a38247570..adb47552e6bb70 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -105,14 +105,14 @@ extern unsigned int ptrs_per_p4d; #define LDT_PGD_ENTRY (pgtable_l5_enabled ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) -#define __VMALLOC_BASE_L4 0xffffc90000000000 -#define __VMALLOC_BASE_L5 0xffa0000000000000 +#define __VMALLOC_BASE_L4 0xffffc90000000000UL +#define __VMALLOC_BASE_L5 0xffa0000000000000UL #define VMALLOC_SIZE_TB_L4 32UL #define VMALLOC_SIZE_TB_L5 12800UL -#define __VMEMMAP_BASE_L4 0xffffea0000000000 -#define __VMEMMAP_BASE_L5 0xffd4000000000000 +#define __VMEMMAP_BASE_L4 0xffffea0000000000UL +#define __VMEMMAP_BASE_L5 0xffd4000000000000UL #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT # define VMALLOC_START vmalloc_base diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h index 809134c644a677..90ab9a795b4932 100644 --- a/arch/x86/include/uapi/asm/msgbuf.h +++ b/arch/x86/include/uapi/asm/msgbuf.h @@ -1 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_X64_MSGBUF_H +#define __ASM_X64_MSGBUF_H + +#if !defined(__x86_64__) || !defined(__ILP32__) #include +#else +/* + * The msqid64_ds structure for x86 architecture with x32 ABI. + * + * On x86-32 and x86-64 we can just use the generic definition, but + * x32 uses the same binary layout as x86_64, which is differnet + * from other 32-bit architectures. + */ + +struct msqid64_ds { + struct ipc64_perm msg_perm; + __kernel_time_t msg_stime; /* last msgsnd time */ + __kernel_time_t msg_rtime; /* last msgrcv time */ + __kernel_time_t msg_ctime; /* last change time */ + __kernel_ulong_t msg_cbytes; /* current number of bytes on queue */ + __kernel_ulong_t msg_qnum; /* number of messages in queue */ + __kernel_ulong_t msg_qbytes; /* max number of bytes on queue */ + __kernel_pid_t msg_lspid; /* pid of last msgsnd */ + __kernel_pid_t msg_lrpid; /* last receive pid */ + __kernel_ulong_t __unused4; + __kernel_ulong_t __unused5; +}; + +#endif + +#endif /* __ASM_GENERIC_MSGBUF_H */ diff --git a/arch/x86/include/uapi/asm/shmbuf.h b/arch/x86/include/uapi/asm/shmbuf.h index 83c05fc2de385c..644421f3823bee 100644 --- a/arch/x86/include/uapi/asm/shmbuf.h +++ b/arch/x86/include/uapi/asm/shmbuf.h @@ -1 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __ASM_X86_SHMBUF_H +#define __ASM_X86_SHMBUF_H + +#if !defined(__x86_64__) || !defined(__ILP32__) #include +#else +/* + * The shmid64_ds structure for x86 architecture with x32 ABI. + * + * On x86-32 and x86-64 we can just use the generic definition, but + * x32 uses the same binary layout as x86_64, which is differnet + * from other 32-bit architectures. + */ + +struct shmid64_ds { + struct ipc64_perm shm_perm; /* operation perms */ + size_t shm_segsz; /* size of segment (bytes) */ + __kernel_time_t shm_atime; /* last attach time */ + __kernel_time_t shm_dtime; /* last detach time */ + __kernel_time_t shm_ctime; /* last change time */ + __kernel_pid_t shm_cpid; /* pid of creator */ + __kernel_pid_t shm_lpid; /* pid of last operator */ + __kernel_ulong_t shm_nattch; /* no. of current attaches */ + __kernel_ulong_t __unused4; + __kernel_ulong_t __unused5; +}; + +struct shminfo64 { + __kernel_ulong_t shmmax; + __kernel_ulong_t shmmin; + __kernel_ulong_t shmmni; + __kernel_ulong_t shmseg; + __kernel_ulong_t shmall; + __kernel_ulong_t __unused1; + __kernel_ulong_t __unused2; + __kernel_ulong_t __unused3; + __kernel_ulong_t __unused4; +}; + +#endif + +#endif /* __ASM_X86_SHMBUF_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index b9693b80fc219c..60d1897041da89 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -835,6 +835,9 @@ static const struct _tlb_table intel_tlb_table[] = { { 0x5d, TLB_DATA_4K_4M, 256, " TLB_DATA 4 KByte and 4 MByte pages" }, { 0x61, TLB_INST_4K, 48, " TLB_INST 4 KByte pages, full associative" }, { 0x63, TLB_DATA_1G, 4, " TLB_DATA 1 GByte pages, 4-way set associative" }, + { 0x6b, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 8-way associative" }, + { 0x6c, TLB_DATA_2M_4M, 128, " TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" }, + { 0x6d, TLB_DATA_1G, 16, " TLB_DATA 1 GByte pages, fully associative" }, { 0x76, TLB_INST_2M_4M, 8, " TLB_INST 2-MByte or 4-MByte pages, fully associative" }, { 0xb0, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 4-way set associative" }, { 0xb1, TLB_INST_2M_4M, 4, " TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" }, diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 10c4fc2c91f8ed..77e20130152881 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -564,14 +564,12 @@ static int __reload_late(void *info) apply_microcode_local(&err); spin_unlock(&update_lock); + /* siblings return UCODE_OK because their engine got updated already */ if (err > UCODE_NFOUND) { pr_warn("Error reloading microcode on CPU %d\n", cpu); - return -1; - /* siblings return UCODE_OK because their engine got updated already */ + ret = -1; } else if (err == UCODE_UPDATED || err == UCODE_OK) { ret = 1; - } else { - return ret; } /* diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 32b8e5724f966a..1c2cfa0644aa97 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -485,7 +485,6 @@ static void show_saved_mc(void) */ static void save_mc_for_early(u8 *mc, unsigned int size) { -#ifdef CONFIG_HOTPLUG_CPU /* Synchronization during CPU hotplug. */ static DEFINE_MUTEX(x86_cpu_microcode_mutex); @@ -495,7 +494,6 @@ static void save_mc_for_early(u8 *mc, unsigned int size) show_saved_mc(); mutex_unlock(&x86_cpu_microcode_mutex); -#endif } static bool load_builtin_intel_microcode(struct cpio_data *cp) diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index fa183a131edc7b..a15fe0e92cf994 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL2.0 +// SPDX-License-Identifier: GPL-2.0 /* * Jailhouse paravirt_ops implementation * diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 6285697b6e565c..5c623dfe39d159 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -50,6 +50,7 @@ #include #include #include +#include #include #include @@ -534,6 +535,11 @@ static void __init reserve_crashkernel(void) high = true; } + if (xen_pv_domain()) { + pr_info("Ignoring crashkernel for a Xen PV domain\n"); + return; + } + /* 0 means: find the address automatically */ if (crash_base <= 0) { /* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 45175b81dd5b37..0f1cbb042f49b8 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1571,6 +1571,8 @@ static inline void mwait_play_dead(void) void *mwait_ptr; int i; + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return; if (!this_cpu_has(X86_FEATURE_MWAIT)) return; if (!this_cpu_has(X86_FEATURE_CLFLUSH)) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index aa66ccd6ed6cc5..c7668806163fd5 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -4544,12 +4544,6 @@ static void vmx_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa) __vmx_flush_tlb(vcpu, to_vmx(vcpu)->vpid, invalidate_gpa); } -static void vmx_flush_tlb_ept_only(struct kvm_vcpu *vcpu) -{ - if (enable_ept) - vmx_flush_tlb(vcpu, true); -} - static void vmx_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { ulong cr0_guest_owned_bits = vcpu->arch.cr0_guest_owned_bits; @@ -9278,7 +9272,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) } else { sec_exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; sec_exec_control |= SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } vmcs_write32(SECONDARY_VM_EXEC_CONTROL, sec_exec_control); @@ -9306,7 +9300,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu, hpa_t hpa) !nested_cpu_has2(get_vmcs12(&vmx->vcpu), SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { vmcs_write64(APIC_ACCESS_ADDR, hpa); - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } } @@ -11220,7 +11214,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, } } else if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } /* @@ -12073,7 +12067,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, } else if (!nested_cpu_has_ept(vmcs12) && nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { - vmx_flush_tlb_ept_only(vcpu); + vmx_flush_tlb(vcpu, true); } /* This is needed for same reason as it was needed in prepare_vmcs02 */ diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7d35ce672989dd..c9492f7649020e 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -302,13 +302,6 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) __rem; \ }) -#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) - static inline bool kvm_mwait_in_guest(struct kvm *kvm) { return kvm->arch.mwait_in_guest; diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 0f3d50f4c48c5b..3bded76e8d5c56 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -93,6 +93,18 @@ void arch_report_meminfo(struct seq_file *m) static inline void split_page_count(int level) { } #endif +static inline int +within(unsigned long addr, unsigned long start, unsigned long end) +{ + return addr >= start && addr < end; +} + +static inline int +within_inclusive(unsigned long addr, unsigned long start, unsigned long end) +{ + return addr >= start && addr <= end; +} + #ifdef CONFIG_X86_64 static inline unsigned long highmap_start_pfn(void) @@ -106,20 +118,25 @@ static inline unsigned long highmap_end_pfn(void) return __pa_symbol(roundup(_brk_end, PMD_SIZE) - 1) >> PAGE_SHIFT; } -#endif - -static inline int -within(unsigned long addr, unsigned long start, unsigned long end) +static bool __cpa_pfn_in_highmap(unsigned long pfn) { - return addr >= start && addr < end; + /* + * Kernel text has an alias mapping at a high address, known + * here as "highmap". + */ + return within_inclusive(pfn, highmap_start_pfn(), highmap_end_pfn()); } -static inline int -within_inclusive(unsigned long addr, unsigned long start, unsigned long end) +#else + +static bool __cpa_pfn_in_highmap(unsigned long pfn) { - return addr >= start && addr <= end; + /* There is no highmap on 32-bit */ + return false; } +#endif + /* * Flushing functions */ @@ -172,7 +189,7 @@ static void __cpa_flush_all(void *arg) static void cpa_flush_all(unsigned long cache) { - BUG_ON(irqs_disabled()); + BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); on_each_cpu(__cpa_flush_all, (void *) cache, 1); } @@ -236,7 +253,7 @@ static void cpa_flush_array(unsigned long *start, int numpages, int cache, unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */ #endif - BUG_ON(irqs_disabled()); + BUG_ON(irqs_disabled() && !early_boot_irqs_disabled); on_each_cpu(__cpa_flush_all, (void *) do_wbinvd, 1); @@ -1183,6 +1200,10 @@ static int __cpa_process_fault(struct cpa_data *cpa, unsigned long vaddr, cpa->numpages = 1; cpa->pfn = __pa(vaddr) >> PAGE_SHIFT; return 0; + + } else if (__cpa_pfn_in_highmap(cpa->pfn)) { + /* Faults in the highmap are OK, so do not warn: */ + return -EFAULT; } else { WARN(1, KERN_WARNING "CPA: called for zero pte. " "vaddr = %lx cpa->vaddr = %lx\n", vaddr, @@ -1335,8 +1356,7 @@ static int cpa_process_alias(struct cpa_data *cpa) * to touch the high mapped kernel as well: */ if (!within(vaddr, (unsigned long)_text, _brk_end) && - within_inclusive(cpa->pfn, highmap_start_pfn(), - highmap_end_pfn())) { + __cpa_pfn_in_highmap(cpa->pfn)) { unsigned long temp_cpa_vaddr = (cpa->pfn << PAGE_SHIFT) + __START_KERNEL_map - phys_base; alias_cpa = *cpa; diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index f1fd52f449e00c..4d418e70587802 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -421,6 +421,16 @@ static inline bool pti_kernel_image_global_ok(void) if (boot_cpu_has(X86_FEATURE_K8)) return false; + /* + * RANDSTRUCT derives its hardening benefits from the + * attacker's lack of knowledge about the layout of kernel + * data structures. Keep the kernel image non-global in + * cases where RANDSTRUCT is in use to help keep the layout a + * secret. + */ + if (IS_ENABLED(CONFIG_GCC_PLUGIN_RANDSTRUCT)) + return false; + return true; } @@ -430,12 +440,24 @@ static inline bool pti_kernel_image_global_ok(void) */ void pti_clone_kernel_text(void) { + /* + * rodata is part of the kernel image and is normally + * readable on the filesystem or on the web. But, do not + * clone the areas past rodata, they might contain secrets. + */ unsigned long start = PFN_ALIGN(_text); - unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE); + unsigned long end = (unsigned long)__end_rodata_hpage_align; if (!pti_kernel_image_global_ok()) return; + pr_debug("mapping partial kernel image into user address space\n"); + + /* + * Note that this will undo _some_ of the work that + * pti_set_kernel_image_nonglobal() did to clear the + * global bit. + */ pti_clone_pmds(start, end, _PAGE_RW); } @@ -458,8 +480,6 @@ void pti_set_kernel_image_nonglobal(void) if (pti_kernel_image_global_ok()) return; - pr_debug("set kernel image non-global\n"); - set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT); } diff --git a/crypto/api.c b/crypto/api.c index 1d5290c6710831..0ee632bba06461 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -204,9 +204,14 @@ static struct crypto_alg *crypto_alg_lookup(const char *name, u32 type, down_read(&crypto_alg_sem); alg = __crypto_alg_lookup(name, type | test, mask | test); - if (!alg && test) - alg = __crypto_alg_lookup(name, type, mask) ? - ERR_PTR(-ELIBBAD) : NULL; + if (!alg && test) { + alg = __crypto_alg_lookup(name, type, mask); + if (alg && !crypto_is_larval(alg)) { + /* Test failed */ + crypto_mod_put(alg); + alg = ERR_PTR(-ELIBBAD); + } + } up_read(&crypto_alg_sem); return alg; diff --git a/crypto/drbg.c b/crypto/drbg.c index 4faa2781c964e2..466a112a444682 100644 --- a/crypto/drbg.c +++ b/crypto/drbg.c @@ -1134,8 +1134,10 @@ static inline void drbg_dealloc_state(struct drbg_state *drbg) if (!drbg) return; kzfree(drbg->Vbuf); + drbg->Vbuf = NULL; drbg->V = NULL; kzfree(drbg->Cbuf); + drbg->Cbuf = NULL; drbg->C = NULL; kzfree(drbg->scratchpadbuf); drbg->scratchpadbuf = NULL; diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 0591874856d3c8..54edaec1e60837 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -679,6 +679,16 @@ void gpstate_timer_handler(struct timer_list *t) if (!spin_trylock(&gpstates->gpstate_lock)) return; + /* + * If the timer has migrated to the different cpu then bring + * it back to one of the policy->cpus + */ + if (!cpumask_test_cpu(raw_smp_processor_id(), policy->cpus)) { + gpstates->timer.expires = jiffies + msecs_to_jiffies(1); + add_timer_on(&gpstates->timer, cpumask_first(policy->cpus)); + spin_unlock(&gpstates->gpstate_lock); + return; + } /* * If PMCR was last updated was using fast_swtich then @@ -718,10 +728,8 @@ void gpstate_timer_handler(struct timer_list *t) if (gpstate_idx != gpstates->last_lpstate_idx) queue_gpstate_timer(gpstates); + set_pstate(&freq_data); spin_unlock(&gpstates->gpstate_lock); - - /* Timer may get migrated to a different cpu on cpu hot unplug */ - smp_call_function_any(policy->cpus, set_pstate, &freq_data, 1); } /* diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index c4865b08d7fb9e..8d21b9825d7176 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -707,7 +707,6 @@ config I2C_MPC config I2C_MT65XX tristate "MediaTek I2C adapter" depends on ARCH_MEDIATEK || COMPILE_TEST - depends on HAS_DMA help This selects the MediaTek(R) Integrated Inter Circuit bus driver for MT65xx and MT81xx. @@ -885,7 +884,6 @@ config I2C_SH7760 config I2C_SH_MOBILE tristate "SuperH Mobile I2C Controller" - depends on HAS_DMA depends on ARCH_SHMOBILE || ARCH_RENESAS || COMPILE_TEST help If you say yes to this option, support will be included for the @@ -1098,7 +1096,6 @@ config I2C_XLP9XX config I2C_RCAR tristate "Renesas R-Car I2C Controller" - depends on HAS_DMA depends on ARCH_RENESAS || COMPILE_TEST select I2C_SLAVE help diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c index 25fcc3c1e32bf3..4053259bccb8d7 100644 --- a/drivers/i2c/busses/i2c-sprd.c +++ b/drivers/i2c/busses/i2c-sprd.c @@ -86,6 +86,7 @@ struct sprd_i2c { u32 count; int irq; int err; + bool is_suspended; }; static void sprd_i2c_set_count(struct sprd_i2c *i2c_dev, u32 count) @@ -283,6 +284,9 @@ static int sprd_i2c_master_xfer(struct i2c_adapter *i2c_adap, struct sprd_i2c *i2c_dev = i2c_adap->algo_data; int im, ret; + if (i2c_dev->is_suspended) + return -EBUSY; + ret = pm_runtime_get_sync(i2c_dev->dev); if (ret < 0) return ret; @@ -364,13 +368,12 @@ static irqreturn_t sprd_i2c_isr_thread(int irq, void *dev_id) struct sprd_i2c *i2c_dev = dev_id; struct i2c_msg *msg = i2c_dev->msg; bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK); - u32 i2c_count = readl(i2c_dev->base + I2C_COUNT); u32 i2c_tran; if (msg->flags & I2C_M_RD) i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD; else - i2c_tran = i2c_count; + i2c_tran = i2c_dev->count; /* * If we got one ACK from slave when writing data, and we did not @@ -408,14 +411,13 @@ static irqreturn_t sprd_i2c_isr(int irq, void *dev_id) { struct sprd_i2c *i2c_dev = dev_id; struct i2c_msg *msg = i2c_dev->msg; - u32 i2c_count = readl(i2c_dev->base + I2C_COUNT); bool ack = !(readl(i2c_dev->base + I2C_STATUS) & I2C_RX_ACK); u32 i2c_tran; if (msg->flags & I2C_M_RD) i2c_tran = i2c_dev->count >= I2C_FIFO_FULL_THLD; else - i2c_tran = i2c_count; + i2c_tran = i2c_dev->count; /* * If we did not get one ACK from slave when writing data, then we @@ -586,11 +588,23 @@ static int sprd_i2c_remove(struct platform_device *pdev) static int __maybe_unused sprd_i2c_suspend_noirq(struct device *pdev) { + struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev); + + i2c_lock_adapter(&i2c_dev->adap); + i2c_dev->is_suspended = true; + i2c_unlock_adapter(&i2c_dev->adap); + return pm_runtime_force_suspend(pdev); } static int __maybe_unused sprd_i2c_resume_noirq(struct device *pdev) { + struct sprd_i2c *i2c_dev = dev_get_drvdata(pdev); + + i2c_lock_adapter(&i2c_dev->adap); + i2c_dev->is_suspended = false; + i2c_unlock_adapter(&i2c_dev->adap); + return pm_runtime_force_resume(pdev); } diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index 036a03f0d0a686..1667b6e7674f4a 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -280,7 +280,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, */ if (msgs[i].flags & I2C_M_RECV_LEN) { if (!(msgs[i].flags & I2C_M_RD) || - msgs[i].buf[0] < 1 || + msgs[i].len < 1 || msgs[i].buf[0] < 1 || msgs[i].len < msgs[i].buf[0] + I2C_SMBUS_BLOCK_MAX) { res = -EINVAL; diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 46115a39209821..c81c79d01d9307 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -31,6 +31,7 @@ enum evdev_clock_type { EV_CLK_REAL = 0, EV_CLK_MONO, + EV_CLK_BOOT, EV_CLK_MAX }; @@ -197,10 +198,12 @@ static int evdev_set_clk_type(struct evdev_client *client, unsigned int clkid) case CLOCK_REALTIME: clk_type = EV_CLK_REAL; break; - case CLOCK_BOOTTIME: case CLOCK_MONOTONIC: clk_type = EV_CLK_MONO; break; + case CLOCK_BOOTTIME: + clk_type = EV_CLK_BOOT; + break; default: return -EINVAL; } @@ -311,6 +314,8 @@ static void evdev_events(struct input_handle *handle, ev_time[EV_CLK_MONO] = ktime_get(); ev_time[EV_CLK_REAL] = ktime_mono_to_real(ev_time[EV_CLK_MONO]); + ev_time[EV_CLK_BOOT] = ktime_mono_to_any(ev_time[EV_CLK_MONO], + TK_OFFS_BOOT); rcu_read_lock(); diff --git a/drivers/input/input-leds.c b/drivers/input/input-leds.c index 766bf26601163c..5f04b2d946350d 100644 --- a/drivers/input/input-leds.c +++ b/drivers/input/input-leds.c @@ -88,6 +88,7 @@ static int input_leds_connect(struct input_handler *handler, const struct input_device_id *id) { struct input_leds *leds; + struct input_led *led; unsigned int num_leds; unsigned int led_code; int led_no; @@ -119,14 +120,13 @@ static int input_leds_connect(struct input_handler *handler, led_no = 0; for_each_set_bit(led_code, dev->ledbit, LED_CNT) { - struct input_led *led = &leds->leds[led_no]; + if (!input_led_info[led_code].name) + continue; + led = &leds->leds[led_no]; led->handle = &leds->handle; led->code = led_code; - if (!input_led_info[led_code].name) - continue; - led->cdev.name = kasprintf(GFP_KERNEL, "%s::%s", dev_name(&dev->dev), input_led_info[led_code].name); diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 0a67f235ba88a7..38f9501acdf04c 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -583,7 +583,7 @@ static void alps_process_trackstick_packet_v3(struct psmouse *psmouse) x = (s8)(((packet[0] & 0x20) << 2) | (packet[1] & 0x7f)); y = (s8)(((packet[0] & 0x10) << 3) | (packet[2] & 0x7f)); - z = packet[4] & 0x7c; + z = packet[4] & 0x7f; /* * The x and y values tend to be quite large, and when used diff --git a/drivers/input/rmi4/rmi_spi.c b/drivers/input/rmi4/rmi_spi.c index 76edbf2c1bced8..082defc329a8e2 100644 --- a/drivers/input/rmi4/rmi_spi.c +++ b/drivers/input/rmi4/rmi_spi.c @@ -147,8 +147,11 @@ static int rmi_spi_xfer(struct rmi_spi_xport *rmi_spi, if (len > RMI_SPI_XFER_SIZE_LIMIT) return -EINVAL; - if (rmi_spi->xfer_buf_size < len) - rmi_spi_manage_pools(rmi_spi, len); + if (rmi_spi->xfer_buf_size < len) { + ret = rmi_spi_manage_pools(rmi_spi, len); + if (ret < 0) + return ret; + } if (addr == 0) /* diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig index 4f15496fec8b56..3e613afa10b4ba 100644 --- a/drivers/input/touchscreen/Kconfig +++ b/drivers/input/touchscreen/Kconfig @@ -362,7 +362,7 @@ config TOUCHSCREEN_HIDEEP If unsure, say N. - To compile this driver as a moudle, choose M here : the + To compile this driver as a module, choose M here : the module will be called hideep_ts. config TOUCHSCREEN_ILI210X diff --git a/drivers/input/touchscreen/atmel_mxt_ts.c b/drivers/input/touchscreen/atmel_mxt_ts.c index 5d9699fe1b55aa..09194721aed2dc 100644 --- a/drivers/input/touchscreen/atmel_mxt_ts.c +++ b/drivers/input/touchscreen/atmel_mxt_ts.c @@ -280,7 +280,8 @@ struct mxt_data { struct input_dev *input_dev; char phys[64]; /* device physical location */ struct mxt_object *object_table; - struct mxt_info info; + struct mxt_info *info; + void *raw_info_block; unsigned int irq; unsigned int max_x; unsigned int max_y; @@ -460,12 +461,13 @@ static int mxt_lookup_bootloader_address(struct mxt_data *data, bool retry) { u8 appmode = data->client->addr; u8 bootloader; + u8 family_id = data->info ? data->info->family_id : 0; switch (appmode) { case 0x4a: case 0x4b: /* Chips after 1664S use different scheme */ - if (retry || data->info.family_id >= 0xa2) { + if (retry || family_id >= 0xa2) { bootloader = appmode - 0x24; break; } @@ -692,7 +694,7 @@ mxt_get_object(struct mxt_data *data, u8 type) struct mxt_object *object; int i; - for (i = 0; i < data->info.object_num; i++) { + for (i = 0; i < data->info->object_num; i++) { object = data->object_table + i; if (object->type == type) return object; @@ -1462,12 +1464,12 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg) data_pos += offset; } - if (cfg_info.family_id != data->info.family_id) { + if (cfg_info.family_id != data->info->family_id) { dev_err(dev, "Family ID mismatch!\n"); return -EINVAL; } - if (cfg_info.variant_id != data->info.variant_id) { + if (cfg_info.variant_id != data->info->variant_id) { dev_err(dev, "Variant ID mismatch!\n"); return -EINVAL; } @@ -1512,7 +1514,7 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg) /* Malloc memory to store configuration */ cfg_start_ofs = MXT_OBJECT_START + - data->info.object_num * sizeof(struct mxt_object) + + data->info->object_num * sizeof(struct mxt_object) + MXT_INFO_CHECKSUM_SIZE; config_mem_size = data->mem_size - cfg_start_ofs; config_mem = kzalloc(config_mem_size, GFP_KERNEL); @@ -1563,20 +1565,6 @@ static int mxt_update_cfg(struct mxt_data *data, const struct firmware *cfg) return ret; } -static int mxt_get_info(struct mxt_data *data) -{ - struct i2c_client *client = data->client; - struct mxt_info *info = &data->info; - int error; - - /* Read 7-byte info block starting at address 0 */ - error = __mxt_read_reg(client, 0, sizeof(*info), info); - if (error) - return error; - - return 0; -} - static void mxt_free_input_device(struct mxt_data *data) { if (data->input_dev) { @@ -1591,9 +1579,10 @@ static void mxt_free_object_table(struct mxt_data *data) video_unregister_device(&data->dbg.vdev); v4l2_device_unregister(&data->dbg.v4l2); #endif - - kfree(data->object_table); data->object_table = NULL; + data->info = NULL; + kfree(data->raw_info_block); + data->raw_info_block = NULL; kfree(data->msg_buf); data->msg_buf = NULL; data->T5_address = 0; @@ -1609,34 +1598,18 @@ static void mxt_free_object_table(struct mxt_data *data) data->max_reportid = 0; } -static int mxt_get_object_table(struct mxt_data *data) +static int mxt_parse_object_table(struct mxt_data *data, + struct mxt_object *object_table) { struct i2c_client *client = data->client; - size_t table_size; - struct mxt_object *object_table; - int error; int i; u8 reportid; u16 end_address; - table_size = data->info.object_num * sizeof(struct mxt_object); - object_table = kzalloc(table_size, GFP_KERNEL); - if (!object_table) { - dev_err(&data->client->dev, "Failed to allocate memory\n"); - return -ENOMEM; - } - - error = __mxt_read_reg(client, MXT_OBJECT_START, table_size, - object_table); - if (error) { - kfree(object_table); - return error; - } - /* Valid Report IDs start counting from 1 */ reportid = 1; data->mem_size = 0; - for (i = 0; i < data->info.object_num; i++) { + for (i = 0; i < data->info->object_num; i++) { struct mxt_object *object = object_table + i; u8 min_id, max_id; @@ -1660,8 +1633,8 @@ static int mxt_get_object_table(struct mxt_data *data) switch (object->type) { case MXT_GEN_MESSAGE_T5: - if (data->info.family_id == 0x80 && - data->info.version < 0x20) { + if (data->info->family_id == 0x80 && + data->info->version < 0x20) { /* * On mXT224 firmware versions prior to V2.0 * read and discard unused CRC byte otherwise @@ -1716,24 +1689,102 @@ static int mxt_get_object_table(struct mxt_data *data) /* If T44 exists, T5 position has to be directly after */ if (data->T44_address && (data->T5_address != data->T44_address + 1)) { dev_err(&client->dev, "Invalid T44 position\n"); - error = -EINVAL; - goto free_object_table; + return -EINVAL; } data->msg_buf = kcalloc(data->max_reportid, data->T5_msg_size, GFP_KERNEL); - if (!data->msg_buf) { - dev_err(&client->dev, "Failed to allocate message buffer\n"); + if (!data->msg_buf) + return -ENOMEM; + + return 0; +} + +static int mxt_read_info_block(struct mxt_data *data) +{ + struct i2c_client *client = data->client; + int error; + size_t size; + void *id_buf, *buf; + uint8_t num_objects; + u32 calculated_crc; + u8 *crc_ptr; + + /* If info block already allocated, free it */ + if (data->raw_info_block) + mxt_free_object_table(data); + + /* Read 7-byte ID information block starting at address 0 */ + size = sizeof(struct mxt_info); + id_buf = kzalloc(size, GFP_KERNEL); + if (!id_buf) + return -ENOMEM; + + error = __mxt_read_reg(client, 0, size, id_buf); + if (error) + goto err_free_mem; + + /* Resize buffer to give space for rest of info block */ + num_objects = ((struct mxt_info *)id_buf)->object_num; + size += (num_objects * sizeof(struct mxt_object)) + + MXT_INFO_CHECKSUM_SIZE; + + buf = krealloc(id_buf, size, GFP_KERNEL); + if (!buf) { error = -ENOMEM; - goto free_object_table; + goto err_free_mem; + } + id_buf = buf; + + /* Read rest of info block */ + error = __mxt_read_reg(client, MXT_OBJECT_START, + size - MXT_OBJECT_START, + id_buf + MXT_OBJECT_START); + if (error) + goto err_free_mem; + + /* Extract & calculate checksum */ + crc_ptr = id_buf + size - MXT_INFO_CHECKSUM_SIZE; + data->info_crc = crc_ptr[0] | (crc_ptr[1] << 8) | (crc_ptr[2] << 16); + + calculated_crc = mxt_calculate_crc(id_buf, 0, + size - MXT_INFO_CHECKSUM_SIZE); + + /* + * CRC mismatch can be caused by data corruption due to I2C comms + * issue or else device is not using Object Based Protocol (eg i2c-hid) + */ + if ((data->info_crc == 0) || (data->info_crc != calculated_crc)) { + dev_err(&client->dev, + "Info Block CRC error calculated=0x%06X read=0x%06X\n", + calculated_crc, data->info_crc); + error = -EIO; + goto err_free_mem; + } + + data->raw_info_block = id_buf; + data->info = (struct mxt_info *)id_buf; + + dev_info(&client->dev, + "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n", + data->info->family_id, data->info->variant_id, + data->info->version >> 4, data->info->version & 0xf, + data->info->build, data->info->object_num); + + /* Parse object table information */ + error = mxt_parse_object_table(data, id_buf + MXT_OBJECT_START); + if (error) { + dev_err(&client->dev, "Error %d parsing object table\n", error); + mxt_free_object_table(data); + goto err_free_mem; } - data->object_table = object_table; + data->object_table = (struct mxt_object *)(id_buf + MXT_OBJECT_START); return 0; -free_object_table: - mxt_free_object_table(data); +err_free_mem: + kfree(id_buf); return error; } @@ -2046,7 +2097,7 @@ static int mxt_initialize(struct mxt_data *data) int error; while (1) { - error = mxt_get_info(data); + error = mxt_read_info_block(data); if (!error) break; @@ -2077,16 +2128,9 @@ static int mxt_initialize(struct mxt_data *data) msleep(MXT_FW_RESET_TIME); } - /* Get object table information */ - error = mxt_get_object_table(data); - if (error) { - dev_err(&client->dev, "Error %d reading object table\n", error); - return error; - } - error = mxt_acquire_irq(data); if (error) - goto err_free_object_table; + return error; error = request_firmware_nowait(THIS_MODULE, true, MXT_CFG_NAME, &client->dev, GFP_KERNEL, data, @@ -2094,14 +2138,10 @@ static int mxt_initialize(struct mxt_data *data) if (error) { dev_err(&client->dev, "Failed to invoke firmware loader: %d\n", error); - goto err_free_object_table; + return error; } return 0; - -err_free_object_table: - mxt_free_object_table(data); - return error; } static int mxt_set_t7_power_cfg(struct mxt_data *data, u8 sleep) @@ -2162,7 +2202,7 @@ static int mxt_init_t7_power_cfg(struct mxt_data *data) static u16 mxt_get_debug_value(struct mxt_data *data, unsigned int x, unsigned int y) { - struct mxt_info *info = &data->info; + struct mxt_info *info = data->info; struct mxt_dbg *dbg = &data->dbg; unsigned int ofs, page; unsigned int col = 0; @@ -2490,7 +2530,7 @@ static const struct video_device mxt_video_device = { static void mxt_debug_init(struct mxt_data *data) { - struct mxt_info *info = &data->info; + struct mxt_info *info = data->info; struct mxt_dbg *dbg = &data->dbg; struct mxt_object *object; int error; @@ -2576,7 +2616,6 @@ static int mxt_configure_objects(struct mxt_data *data, const struct firmware *cfg) { struct device *dev = &data->client->dev; - struct mxt_info *info = &data->info; int error; error = mxt_init_t7_power_cfg(data); @@ -2601,11 +2640,6 @@ static int mxt_configure_objects(struct mxt_data *data, mxt_debug_init(data); - dev_info(dev, - "Family: %u Variant: %u Firmware V%u.%u.%02X Objects: %u\n", - info->family_id, info->variant_id, info->version >> 4, - info->version & 0xf, info->build, info->object_num); - return 0; } @@ -2614,7 +2648,7 @@ static ssize_t mxt_fw_version_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mxt_data *data = dev_get_drvdata(dev); - struct mxt_info *info = &data->info; + struct mxt_info *info = data->info; return scnprintf(buf, PAGE_SIZE, "%u.%u.%02X\n", info->version >> 4, info->version & 0xf, info->build); } @@ -2624,7 +2658,7 @@ static ssize_t mxt_hw_version_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mxt_data *data = dev_get_drvdata(dev); - struct mxt_info *info = &data->info; + struct mxt_info *info = data->info; return scnprintf(buf, PAGE_SIZE, "%u.%u\n", info->family_id, info->variant_id); } @@ -2663,7 +2697,7 @@ static ssize_t mxt_object_show(struct device *dev, return -ENOMEM; error = 0; - for (i = 0; i < data->info.object_num; i++) { + for (i = 0; i < data->info->object_num; i++) { object = data->object_table + i; if (!mxt_object_readable(object->type)) @@ -3034,6 +3068,15 @@ static const struct dmi_system_id mxt_dmi_table[] = { }, .driver_data = samus_platform_data, }, + { + /* Samsung Chromebook Pro */ + .ident = "Samsung Chromebook Pro", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Google"), + DMI_MATCH(DMI_PRODUCT_NAME, "Caroline"), + }, + .driver_data = samus_platform_data, + }, { /* Other Google Chromebooks */ .ident = "Chromebook", @@ -3254,6 +3297,11 @@ static SIMPLE_DEV_PM_OPS(mxt_pm_ops, mxt_suspend, mxt_resume); static const struct of_device_id mxt_of_match[] = { { .compatible = "atmel,maxtouch", }, + /* Compatibles listed below are deprecated */ + { .compatible = "atmel,qt602240_ts", }, + { .compatible = "atmel,atmel_mxt_ts", }, + { .compatible = "atmel,atmel_mxt_tp", }, + { .compatible = "atmel,mXT224", }, {}, }; MODULE_DEVICE_TABLE(of, mxt_of_match); diff --git a/drivers/rtc/rtc-opal.c b/drivers/rtc/rtc-opal.c index 304e891e35fcb0..60f2250fd96bec 100644 --- a/drivers/rtc/rtc-opal.c +++ b/drivers/rtc/rtc-opal.c @@ -57,7 +57,7 @@ static void tm_to_opal(struct rtc_time *tm, u32 *y_m_d, u64 *h_m_s_ms) static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm) { - long rc = OPAL_BUSY; + s64 rc = OPAL_BUSY; int retries = 10; u32 y_m_d; u64 h_m_s_ms; @@ -66,13 +66,17 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm) while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms); - if (rc == OPAL_BUSY_EVENT) + if (rc == OPAL_BUSY_EVENT) { + msleep(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); - else if (retries-- && (rc == OPAL_HARDWARE - || rc == OPAL_INTERNAL_ERROR)) - msleep(10); - else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT) - break; + } else if (rc == OPAL_BUSY) { + msleep(OPAL_BUSY_DELAY_MS); + } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) { + if (retries--) { + msleep(10); /* Wait 10ms before retry */ + rc = OPAL_BUSY; /* go around again */ + } + } } if (rc != OPAL_SUCCESS) @@ -87,21 +91,26 @@ static int opal_get_rtc_time(struct device *dev, struct rtc_time *tm) static int opal_set_rtc_time(struct device *dev, struct rtc_time *tm) { - long rc = OPAL_BUSY; + s64 rc = OPAL_BUSY; int retries = 10; u32 y_m_d = 0; u64 h_m_s_ms = 0; tm_to_opal(tm, &y_m_d, &h_m_s_ms); + while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) { rc = opal_rtc_write(y_m_d, h_m_s_ms); - if (rc == OPAL_BUSY_EVENT) + if (rc == OPAL_BUSY_EVENT) { + msleep(OPAL_BUSY_DELAY_MS); opal_poll_events(NULL); - else if (retries-- && (rc == OPAL_HARDWARE - || rc == OPAL_INTERNAL_ERROR)) - msleep(10); - else if (rc != OPAL_BUSY && rc != OPAL_BUSY_EVENT) - break; + } else if (rc == OPAL_BUSY) { + msleep(OPAL_BUSY_DELAY_MS); + } else if (rc == OPAL_HARDWARE || rc == OPAL_INTERNAL_ERROR) { + if (retries--) { + msleep(10); /* Wait 10ms before retry */ + rc = OPAL_BUSY; /* go around again */ + } + } } return rc == OPAL_SUCCESS ? 0 : -EIO; diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c index c44d7c7ffc920e..1754f55e2facfb 100644 --- a/drivers/sbus/char/oradax.c +++ b/drivers/sbus/char/oradax.c @@ -3,7 +3,7 @@ * * This program is free software: you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by - * the Free Software Foundation, either version 3 of the License, or + * the Free Software Foundation, either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, diff --git a/drivers/scsi/isci/port_config.c b/drivers/scsi/isci/port_config.c index edb7be786c6501..9e8de1462593aa 100644 --- a/drivers/scsi/isci/port_config.c +++ b/drivers/scsi/isci/port_config.c @@ -291,7 +291,7 @@ sci_mpc_agent_validate_phy_configuration(struct isci_host *ihost, * Note: We have not moved the current phy_index so we will actually * compare the startting phy with itself. * This is expected and required to add the phy to the port. */ - while (phy_index < SCI_MAX_PHYS) { + for (; phy_index < SCI_MAX_PHYS; phy_index++) { if ((phy_mask & (1 << phy_index)) == 0) continue; sci_phy_get_sas_address(&ihost->phys[phy_index], @@ -311,7 +311,6 @@ sci_mpc_agent_validate_phy_configuration(struct isci_host *ihost, &ihost->phys[phy_index]); assigned_phy_mask |= (1 << phy_index); - phy_index++; } } diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 8c51d628b52edf..a2ec0bc9e9fac0 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1722,11 +1722,14 @@ static int storvsc_probe(struct hv_device *device, max_targets = STORVSC_MAX_TARGETS; max_channels = STORVSC_MAX_CHANNELS; /* - * On Windows8 and above, we support sub-channels for storage. + * On Windows8 and above, we support sub-channels for storage + * on SCSI and FC controllers. * The number of sub-channels offerred is based on the number of * VCPUs in the guest. */ - max_sub_channels = (num_cpus / storvsc_vcpus_per_sub_channel); + if (!dev_is_ide) + max_sub_channels = + (num_cpus - 1) / storvsc_vcpus_per_sub_channel; } scsi_driver.can_queue = (max_outstanding_req_per_channel * diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 07c814c42648fa..60429011292a2c 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -427,8 +427,8 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd) { struct se_device *dev = cmd->se_dev; struct scatterlist *sg = &cmd->t_data_sg[0]; - unsigned char *buf, zero = 0x00, *p = &zero; - int rc, ret; + unsigned char *buf, *not_zero; + int ret; buf = kmap(sg_page(sg)) + sg->offset; if (!buf) @@ -437,10 +437,10 @@ iblock_execute_zero_out(struct block_device *bdev, struct se_cmd *cmd) * Fall back to block_execute_write_same() slow-path if * incoming WRITE_SAME payload does not contain zeros. */ - rc = memcmp(buf, p, cmd->data_length); + not_zero = memchr_inv(buf, 0x00, cmd->data_length); kunmap(sg_page(sg)); - if (rc) + if (not_zero) return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; ret = blkdev_issue_zeroout(bdev, diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 6d3e40d7029c47..1529a088383d04 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -455,6 +455,9 @@ cifs_enable_signing(struct TCP_Server_Info *server, bool mnt_sign_required) server->sign = true; } + if (cifs_rdma_enabled(server) && server->sign) + cifs_dbg(VFS, "Signing is enabled, and RDMA read/write will be disabled"); + return 0; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index e8830f076a7f16..a5aa158d535a70 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2959,6 +2959,22 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) } } + if (volume_info->seal) { + if (ses->server->vals->protocol_id == 0) { + cifs_dbg(VFS, + "SMB3 or later required for encryption\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } else if (tcon->ses->server->capabilities & + SMB2_GLOBAL_CAP_ENCRYPTION) + tcon->seal = true; + else { + cifs_dbg(VFS, "Encryption is not supported on share\n"); + rc = -EOPNOTSUPP; + goto out_fail; + } + } + /* * BB Do we need to wrap session_mutex around this TCon call and Unix * SetFS as we do on SessSetup and reconnect? @@ -3007,22 +3023,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info) tcon->use_resilient = true; } - if (volume_info->seal) { - if (ses->server->vals->protocol_id == 0) { - cifs_dbg(VFS, - "SMB3 or later required for encryption\n"); - rc = -EOPNOTSUPP; - goto out_fail; - } else if (tcon->ses->server->capabilities & - SMB2_GLOBAL_CAP_ENCRYPTION) - tcon->seal = true; - else { - cifs_dbg(VFS, "Encryption is not supported on share\n"); - rc = -EOPNOTSUPP; - goto out_fail; - } - } - /* * We can have only one retry value for a connection to a share so for * resources mounted more than once to the same server share the last diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 38ebf3f357d292..b76b85881dcc66 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -252,9 +252,14 @@ smb2_negotiate_wsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) wsize = volume_info->wsize ? volume_info->wsize : CIFS_DEFAULT_IOSIZE; wsize = min_t(unsigned int, wsize, server->max_write); #ifdef CONFIG_CIFS_SMB_DIRECT - if (server->rdma) - wsize = min_t(unsigned int, + if (server->rdma) { + if (server->sign) + wsize = min_t(unsigned int, + wsize, server->smbd_conn->max_fragmented_send_size); + else + wsize = min_t(unsigned int, wsize, server->smbd_conn->max_readwrite_size); + } #endif if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU)) wsize = min_t(unsigned int, wsize, SMB2_MAX_BUFFER_SIZE); @@ -272,9 +277,14 @@ smb2_negotiate_rsize(struct cifs_tcon *tcon, struct smb_vol *volume_info) rsize = volume_info->rsize ? volume_info->rsize : CIFS_DEFAULT_IOSIZE; rsize = min_t(unsigned int, rsize, server->max_read); #ifdef CONFIG_CIFS_SMB_DIRECT - if (server->rdma) - rsize = min_t(unsigned int, + if (server->rdma) { + if (server->sign) + rsize = min_t(unsigned int, + rsize, server->smbd_conn->max_fragmented_recv_size); + else + rsize = min_t(unsigned int, rsize, server->smbd_conn->max_readwrite_size); + } #endif if (!(server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU)) diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 0f044c4a2dc9b5..60db51bae0e3a8 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -383,10 +383,10 @@ static void build_encrypt_ctxt(struct smb2_encryption_neg_context *pneg_ctxt) { pneg_ctxt->ContextType = SMB2_ENCRYPTION_CAPABILITIES; - pneg_ctxt->DataLength = cpu_to_le16(6); - pneg_ctxt->CipherCount = cpu_to_le16(2); - pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM; - pneg_ctxt->Ciphers[1] = SMB2_ENCRYPTION_AES128_CCM; + pneg_ctxt->DataLength = cpu_to_le16(4); /* Cipher Count + le16 cipher */ + pneg_ctxt->CipherCount = cpu_to_le16(1); +/* pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_GCM;*/ /* not supported yet */ + pneg_ctxt->Ciphers[0] = SMB2_ENCRYPTION_AES128_CCM; } static void @@ -444,6 +444,7 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server, return -EINVAL; } server->cipher_type = ctxt->Ciphers[0]; + server->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION; return 0; } @@ -2590,7 +2591,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len, * If we want to do a RDMA write, fill in and append * smbd_buffer_descriptor_v1 to the end of read request */ - if (server->rdma && rdata && + if (server->rdma && rdata && !server->sign && rdata->bytes >= server->smbd_conn->rdma_readwrite_threshold) { struct smbd_buffer_descriptor_v1 *v1; @@ -2968,7 +2969,7 @@ smb2_async_writev(struct cifs_writedata *wdata, * If we want to do a server RDMA read, fill in and append * smbd_buffer_descriptor_v1 to the end of write request */ - if (server->rdma && wdata->bytes >= + if (server->rdma && !server->sign && wdata->bytes >= server->smbd_conn->rdma_readwrite_threshold) { struct smbd_buffer_descriptor_v1 *v1; diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 6093e5142b2bc3..d28f358022c507 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -297,7 +297,7 @@ struct smb2_encryption_neg_context { __le16 DataLength; __le32 Reserved; __le16 CipherCount; /* AES-128-GCM and AES-128-CCM */ - __le16 Ciphers[2]; /* Ciphers[0] since only one used now */ + __le16 Ciphers[1]; /* Ciphers[0] since only one used now */ } __packed; struct smb2_negotiate_rsp { diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 87817ddcc096d4..c62f7c95683c51 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -2086,7 +2086,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) int start, i, j; int max_iov_size = info->max_send_size - sizeof(struct smbd_data_transfer); - struct kvec iov[SMBDIRECT_MAX_SGE]; + struct kvec *iov; int rc; info->smbd_send_pending++; @@ -2096,32 +2096,20 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) } /* - * This usually means a configuration error - * We use RDMA read/write for packet size > rdma_readwrite_threshold - * as long as it's properly configured we should never get into this - * situation - */ - if (rqst->rq_nvec + rqst->rq_npages > SMBDIRECT_MAX_SGE) { - log_write(ERR, "maximum send segment %x exceeding %x\n", - rqst->rq_nvec + rqst->rq_npages, SMBDIRECT_MAX_SGE); - rc = -EINVAL; - goto done; - } - - /* - * Remove the RFC1002 length defined in MS-SMB2 section 2.1 - * It is used only for TCP transport + * Skip the RFC1002 length defined in MS-SMB2 section 2.1 + * It is used only for TCP transport in the iov[0] * In future we may want to add a transport layer under protocol * layer so this will only be issued to TCP transport */ - iov[0].iov_base = (char *)rqst->rq_iov[0].iov_base + 4; - iov[0].iov_len = rqst->rq_iov[0].iov_len - 4; - buflen += iov[0].iov_len; + + if (rqst->rq_iov[0].iov_len != 4) { + log_write(ERR, "expected the pdu length in 1st iov, but got %zu\n", rqst->rq_iov[0].iov_len); + return -EINVAL; + } + iov = &rqst->rq_iov[1]; /* total up iov array first */ - for (i = 1; i < rqst->rq_nvec; i++) { - iov[i].iov_base = rqst->rq_iov[i].iov_base; - iov[i].iov_len = rqst->rq_iov[i].iov_len; + for (i = 0; i < rqst->rq_nvec-1; i++) { buflen += iov[i].iov_len; } @@ -2198,14 +2186,14 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) goto done; } i++; - if (i == rqst->rq_nvec) + if (i == rqst->rq_nvec-1) break; } start = i; buflen = 0; } else { i++; - if (i == rqst->rq_nvec) { + if (i == rqst->rq_nvec-1) { /* send out all remaining vecs */ remaining_data_length -= buflen; log_write(INFO, diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 8f6f25918229d9..927226a2122f4d 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -753,7 +753,7 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, goto out; #ifdef CONFIG_CIFS_SMB311 - if (ses->status == CifsNew) + if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) smb311_update_preauth_hash(ses, rqst->rq_iov+1, rqst->rq_nvec-1); #endif @@ -798,7 +798,7 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses, *resp_buf_type = CIFS_SMALL_BUFFER; #ifdef CONFIG_CIFS_SMB311 - if (ses->status == CifsNew) { + if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) { struct kvec iov = { .iov_base = buf + 4, .iov_len = get_rfc1002_length(buf) @@ -834,8 +834,11 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses, if (n_vec + 1 > CIFS_MAX_IOV_SIZE) { new_iov = kmalloc(sizeof(struct kvec) * (n_vec + 1), GFP_KERNEL); - if (!new_iov) + if (!new_iov) { + /* otherwise cifs_send_recv below sets resp_buf_type */ + *resp_buf_type = CIFS_NO_BUFFER; return -ENOMEM; + } } else new_iov = s_iov; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index a33d8fb1bf2a7f..508b905d744d75 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -321,6 +321,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; + ext4_grpblk_t max_bit = EXT4_CLUSTERS_PER_GROUP(sb); ext4_fsblk_t blk; ext4_fsblk_t group_first_block; @@ -338,7 +339,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, /* check whether block bitmap block number is set */ blk = ext4_block_bitmap(sb, desc); offset = blk - group_first_block; - if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize || + if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit || !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data)) /* bad block bitmap */ return blk; @@ -346,7 +347,7 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, /* check whether the inode bitmap block number is set */ blk = ext4_inode_bitmap(sb, desc); offset = blk - group_first_block; - if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize || + if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit || !ext4_test_bit(EXT4_B2C(sbi, offset), bh->b_data)) /* bad block bitmap */ return blk; @@ -354,8 +355,8 @@ static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, /* check whether the inode table block number is set */ blk = ext4_inode_table(sb, desc); offset = blk - group_first_block; - if (offset < 0 || EXT4_B2C(sbi, offset) >= sb->s_blocksize || - EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= sb->s_blocksize) + if (offset < 0 || EXT4_B2C(sbi, offset) >= max_bit || + EXT4_B2C(sbi, offset + sbi->s_itb_per_group) >= max_bit) return blk; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, EXT4_B2C(sbi, offset + sbi->s_itb_per_group), diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0a7315961bac6e..c969275ce3ee74 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5329,8 +5329,9 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, stop = le32_to_cpu(extent->ee_block); /* - * In case of left shift, Don't start shifting extents until we make - * sure the hole is big enough to accommodate the shift. + * For left shifts, make sure the hole on the left is big enough to + * accommodate the shift. For right shifts, make sure the last extent + * won't be shifted beyond EXT_MAX_BLOCKS. */ if (SHIFT == SHIFT_LEFT) { path = ext4_find_extent(inode, start - 1, &path, @@ -5350,9 +5351,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle, if ((start == ex_start && shift > ex_start) || (shift > start - ex_end)) { - ext4_ext_drop_refs(path); - kfree(path); - return -EINVAL; + ret = -EINVAL; + goto out; + } + } else { + if (shift > EXT_MAX_BLOCKS - + (stop + ext4_ext_get_actual_len(extent))) { + ret = -EINVAL; + goto out; } } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 185f7e61f4cfe0..eb104e8476f040 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5886,5 +5886,6 @@ static void __exit ext4_exit_fs(void) MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others"); MODULE_DESCRIPTION("Fourth Extended Filesystem"); MODULE_LICENSE("GPL"); +MODULE_SOFTDEP("pre: crc32c"); module_init(ext4_init_fs) module_exit(ext4_exit_fs) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index ac311037d7a59b..8aa453784402bb 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -532,6 +532,7 @@ int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, */ ret = start_this_handle(journal, handle, GFP_NOFS); if (ret < 0) { + handle->h_journal = journal; jbd2_journal_free_reserved(handle); return ret; } diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c index ce4a34a2751d6e..35a124400d60a1 100644 --- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -511,7 +511,14 @@ xfs_attr_shortform_addname(xfs_da_args_t *args) if (args->flags & ATTR_CREATE) return retval; retval = xfs_attr_shortform_remove(args); - ASSERT(retval == 0); + if (retval) + return retval; + /* + * Since we have removed the old attr, clear ATTR_REPLACE so + * that the leaf format add routine won't trip over the attr + * not being around. + */ + args->flags &= ~ATTR_REPLACE; } if (args->namelen >= XFS_ATTR_SF_ENTSIZE_MAX || diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 6a7c2f03ea11a1..040eeda8426ff7 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -725,12 +725,16 @@ xfs_bmap_extents_to_btree( *logflagsp = 0; if ((error = xfs_alloc_vextent(&args))) { xfs_iroot_realloc(ip, -1, whichfork); + ASSERT(ifp->if_broot == NULL); + XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return error; } if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) { xfs_iroot_realloc(ip, -1, whichfork); + ASSERT(ifp->if_broot == NULL); + XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS); xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); return -ENOSPC; } diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index ef68b1de006a7e..1201107eabc632 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -466,6 +466,8 @@ xfs_dinode_verify( return __this_address; if (di_size > XFS_DFORK_DSIZE(dip, mp)) return __this_address; + if (dip->di_nextents) + return __this_address; /* fall through */ case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: @@ -484,12 +486,31 @@ xfs_dinode_verify( if (XFS_DFORK_Q(dip)) { switch (dip->di_aformat) { case XFS_DINODE_FMT_LOCAL: + if (dip->di_anextents) + return __this_address; + /* fall through */ case XFS_DINODE_FMT_EXTENTS: case XFS_DINODE_FMT_BTREE: break; default: return __this_address; } + } else { + /* + * If there is no fork offset, this may be a freshly-made inode + * in a new disk cluster, in which case di_aformat is zeroed. + * Otherwise, such an inode must be in EXTENTS format; this goes + * for freed inodes as well. + */ + switch (dip->di_aformat) { + case 0: + case XFS_DINODE_FMT_EXTENTS: + break; + default: + return __this_address; + } + if (dip->di_anextents) + return __this_address; } /* only version 3 or greater inodes are extensively verified here */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 299aee4b7b0b35..eed073cc477834 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -778,22 +778,26 @@ xfs_file_fallocate( if (error) goto out_unlock; } else if (mode & FALLOC_FL_INSERT_RANGE) { - unsigned int blksize_mask = i_blocksize(inode) - 1; + unsigned int blksize_mask = i_blocksize(inode) - 1; + loff_t isize = i_size_read(inode); - new_size = i_size_read(inode) + len; if (offset & blksize_mask || len & blksize_mask) { error = -EINVAL; goto out_unlock; } - /* check the new inode size does not wrap through zero */ - if (new_size > inode->i_sb->s_maxbytes) { + /* + * New inode size must not exceed ->s_maxbytes, accounting for + * possible signed overflow. + */ + if (inode->i_sb->s_maxbytes - isize < len) { error = -EFBIG; goto out_unlock; } + new_size = isize + len; /* Offset should be less than i_size */ - if (offset >= i_size_read(inode)) { + if (offset >= isize) { error = -EINVAL; goto out_unlock; } diff --git a/include/kvm/arm_psci.h b/include/kvm/arm_psci.h index e518e4e3dfb50a..4b1548129fa2b3 100644 --- a/include/kvm/arm_psci.h +++ b/include/kvm/arm_psci.h @@ -37,10 +37,15 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm) * Our PSCI implementation stays the same across versions from * v0.2 onward, only adding the few mandatory functions (such * as FEATURES with 1.0) that are required by newer - * revisions. It is thus safe to return the latest. + * revisions. It is thus safe to return the latest, unless + * userspace has instructed us otherwise. */ - if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) + if (test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features)) { + if (vcpu->kvm->arch.psci_version) + return vcpu->kvm->arch.psci_version; + return KVM_ARM_PSCI_LATEST; + } return KVM_ARM_PSCI_0_1; } @@ -48,4 +53,11 @@ static inline int kvm_psci_version(struct kvm_vcpu *vcpu, struct kvm *kvm) int kvm_hvc_call_handler(struct kvm_vcpu *vcpu); +struct kvm_one_reg; + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu); +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); + #endif /* __KVM_ARM_PSCI_H__ */ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index a2656c3ebe81ca..3892e9c8b2deb7 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -161,9 +161,11 @@ struct hrtimer_clock_base { enum hrtimer_base_type { HRTIMER_BASE_MONOTONIC, HRTIMER_BASE_REALTIME, + HRTIMER_BASE_BOOTTIME, HRTIMER_BASE_TAI, HRTIMER_BASE_MONOTONIC_SOFT, HRTIMER_BASE_REALTIME_SOFT, + HRTIMER_BASE_BOOTTIME_SOFT, HRTIMER_BASE_TAI_SOFT, HRTIMER_MAX_CLOCK_BASES, }; diff --git a/include/linux/stringhash.h b/include/linux/stringhash.h index e8f0f852968f13..c0c5c5b73dc0b0 100644 --- a/include/linux/stringhash.h +++ b/include/linux/stringhash.h @@ -50,9 +50,9 @@ partial_name_hash(unsigned long c, unsigned long prevhash) * losing bits). This also has the property (wanted by the dcache) * that the msbits make a good hash table index. */ -static inline unsigned long end_name_hash(unsigned long hash) +static inline unsigned int end_name_hash(unsigned long hash) { - return __hash_32((unsigned int)hash); + return hash_long(hash, 32); } /* diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index 4b3dca173e8959..7acb953298a731 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -52,7 +52,6 @@ struct tk_read_base { * @offs_real: Offset clock monotonic -> clock realtime * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai - * @time_suspended: Accumulated suspend time * @tai_offset: The current UTC to TAI offset in seconds * @clock_was_set_seq: The sequence number of clock was set events * @cs_was_changed_seq: The sequence number of clocksource change events @@ -95,7 +94,6 @@ struct timekeeper { ktime_t offs_real; ktime_t offs_boot; ktime_t offs_tai; - ktime_t time_suspended; s32 tai_offset; unsigned int clock_was_set_seq; u8 cs_was_changed_seq; diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 9737fbec7019bd..588a0e4b1ab933 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -33,25 +33,20 @@ extern void ktime_get_ts64(struct timespec64 *ts); extern time64_t ktime_get_seconds(void); extern time64_t __ktime_get_real_seconds(void); extern time64_t ktime_get_real_seconds(void); -extern void ktime_get_active_ts64(struct timespec64 *ts); extern int __getnstimeofday64(struct timespec64 *tv); extern void getnstimeofday64(struct timespec64 *tv); extern void getboottime64(struct timespec64 *ts); -#define ktime_get_real_ts64(ts) getnstimeofday64(ts) - -/* Clock BOOTTIME compatibility wrappers */ -static inline void get_monotonic_boottime64(struct timespec64 *ts) -{ - ktime_get_ts64(ts); -} +#define ktime_get_real_ts64(ts) getnstimeofday64(ts) /* * ktime_t based interfaces */ + enum tk_offsets { TK_OFFS_REAL, + TK_OFFS_BOOT, TK_OFFS_TAI, TK_OFFS_MAX, }; @@ -62,10 +57,6 @@ extern ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs); extern ktime_t ktime_get_raw(void); extern u32 ktime_get_resolution_ns(void); -/* Clock BOOTTIME compatibility wrappers */ -static inline ktime_t ktime_get_boottime(void) { return ktime_get(); } -static inline u64 ktime_get_boot_ns(void) { return ktime_get(); } - /** * ktime_get_real - get the real (wall-) time in ktime_t format */ @@ -74,6 +65,17 @@ static inline ktime_t ktime_get_real(void) return ktime_get_with_offset(TK_OFFS_REAL); } +/** + * ktime_get_boottime - Returns monotonic time since boot in ktime_t format + * + * This is similar to CLOCK_MONTONIC/ktime_get, but also includes the + * time spent in suspend. + */ +static inline ktime_t ktime_get_boottime(void) +{ + return ktime_get_with_offset(TK_OFFS_BOOT); +} + /** * ktime_get_clocktai - Returns the TAI time of day in ktime_t format */ @@ -100,6 +102,11 @@ static inline u64 ktime_get_real_ns(void) return ktime_to_ns(ktime_get_real()); } +static inline u64 ktime_get_boot_ns(void) +{ + return ktime_to_ns(ktime_get_boottime()); +} + static inline u64 ktime_get_tai_ns(void) { return ktime_to_ns(ktime_get_clocktai()); @@ -112,11 +119,17 @@ static inline u64 ktime_get_raw_ns(void) extern u64 ktime_get_mono_fast_ns(void); extern u64 ktime_get_raw_fast_ns(void); +extern u64 ktime_get_boot_fast_ns(void); extern u64 ktime_get_real_fast_ns(void); /* * timespec64 interfaces utilizing the ktime based ones */ +static inline void get_monotonic_boottime64(struct timespec64 *ts) +{ + *ts = ktime_to_timespec64(ktime_get_boottime()); +} + static inline void timekeeping_clocktai64(struct timespec64 *ts) { *ts = ktime_to_timespec64(ktime_get_clocktai()); diff --git a/include/trace/events/initcall.h b/include/trace/events/initcall.h index 8d6cf10d27c92c..eb903c3f195f59 100644 --- a/include/trace/events/initcall.h +++ b/include/trace/events/initcall.h @@ -31,7 +31,11 @@ TRACE_EVENT(initcall_start, TP_ARGS(func), TP_STRUCT__entry( - __field(initcall_t, func) + /* + * Use field_struct to avoid is_signed_type() + * comparison of a function pointer + */ + __field_struct(initcall_t, func) ), TP_fast_assign( @@ -48,8 +52,12 @@ TRACE_EVENT(initcall_finish, TP_ARGS(func, ret), TP_STRUCT__entry( - __field(initcall_t, func) - __field(int, ret) + /* + * Use field_struct to avoid is_signed_type() + * comparison of a function pointer + */ + __field_struct(initcall_t, func) + __field(int, ret) ), TP_fast_assign( diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 1065006c9bf589..b02c41e53d5616 100644 --- a/include/uapi/linux/kvm.h +++ b/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/include/uapi/linux/time.h b/include/uapi/linux/time.h index 16a296612ba4b0..4c0338ea308a67 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -73,7 +73,6 @@ struct __kernel_old_timeval { */ #define CLOCK_SGI_CYCLE 10 #define CLOCK_TAI 11 -#define CLOCK_MONOTONIC_ACTIVE 12 #define MAX_CLOCKS 16 #define CLOCKS_MASK (CLOCK_REALTIME | CLOCK_MONOTONIC) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index ce6848e46e9451..1725b902983fcd 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -491,7 +491,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) if (!uprobe) return NULL; - uprobe->inode = igrab(inode); + uprobe->inode = inode; uprobe->offset = offset; init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); @@ -502,7 +502,6 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) if (cur_uprobe) { kfree(uprobe); uprobe = cur_uprobe; - iput(inode); } return uprobe; @@ -701,7 +700,6 @@ static void delete_uprobe(struct uprobe *uprobe) rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock(&uprobes_treelock); RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ - iput(uprobe->inode); put_uprobe(uprobe); } @@ -873,7 +871,8 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @uc for the @uprobe - * unregisters. + * unregisters. Caller of uprobe_register() is required to keep @inode + * (and the containing mount) referenced. * * Return errno if it cannot successully install probes * else return 0 (success) diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index eda1210ce50f88..14e858753d7689 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -90,6 +90,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, @@ -105,6 +110,11 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, + { + .index = HRTIMER_BASE_BOOTTIME_SOFT, + .clockid = CLOCK_BOOTTIME, + .get_time = &ktime_get_boottime, + }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, @@ -119,7 +129,7 @@ static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, - [CLOCK_BOOTTIME] = HRTIMER_BASE_MONOTONIC, + [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, [CLOCK_TAI] = HRTIMER_BASE_TAI, }; @@ -571,12 +581,14 @@ __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, - offs_real, offs_tai); + offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; + base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index e0dbae98db9d9b..69a937c3cd8126 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -83,8 +83,6 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp) case CLOCK_BOOTTIME: get_monotonic_boottime64(tp); break; - case CLOCK_MONOTONIC_ACTIVE: - ktime_get_active_ts64(tp); default: return -EINVAL; } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index b6899b5060bd84..10b7186d063830 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -252,16 +252,15 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 * return 0; } -static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) +static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp) { - timekeeping_clocktai64(tp); + get_monotonic_boottime64(tp); return 0; } -static int posix_get_monotonic_active(clockid_t which_clock, - struct timespec64 *tp) +static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp) { - ktime_get_active_ts64(tp); + timekeeping_clocktai64(tp); return 0; } @@ -1317,9 +1316,19 @@ static const struct k_clock clock_tai = { .timer_arm = common_hrtimer_arm, }; -static const struct k_clock clock_monotonic_active = { +static const struct k_clock clock_boottime = { .clock_getres = posix_get_hrtimer_res, - .clock_get = posix_get_monotonic_active, + .clock_get = posix_get_boottime, + .nsleep = common_nsleep, + .timer_create = common_timer_create, + .timer_set = common_timer_set, + .timer_get = common_timer_get, + .timer_del = common_timer_del, + .timer_rearm = common_hrtimer_rearm, + .timer_forward = common_hrtimer_forward, + .timer_remaining = common_hrtimer_remaining, + .timer_try_to_cancel = common_hrtimer_try_to_cancel, + .timer_arm = common_hrtimer_arm, }; static const struct k_clock * const posix_clocks[] = { @@ -1330,11 +1339,10 @@ static const struct k_clock * const posix_clocks[] = { [CLOCK_MONOTONIC_RAW] = &clock_monotonic_raw, [CLOCK_REALTIME_COARSE] = &clock_realtime_coarse, [CLOCK_MONOTONIC_COARSE] = &clock_monotonic_coarse, - [CLOCK_BOOTTIME] = &clock_monotonic, + [CLOCK_BOOTTIME] = &clock_boottime, [CLOCK_REALTIME_ALARM] = &alarm_clock, [CLOCK_BOOTTIME_ALARM] = &alarm_clock, [CLOCK_TAI] = &clock_tai, - [CLOCK_MONOTONIC_ACTIVE] = &clock_monotonic_active, }; static const struct k_clock *clockid_to_kclock(const clockid_t id) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 099572ca4a8f23..49edc1c4f3e645 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -419,19 +419,6 @@ void tick_suspend_local(void) clockevents_shutdown(td->evtdev); } -static void tick_forward_next_period(void) -{ - ktime_t delta, now = ktime_get(); - u64 n; - - delta = ktime_sub(now, tick_next_period); - n = ktime_divns(delta, tick_period); - tick_next_period += n * tick_period; - if (tick_next_period < now) - tick_next_period += tick_period; - tick_sched_forward_next_period(); -} - /** * tick_resume_local - Resume the local tick device * @@ -444,8 +431,6 @@ void tick_resume_local(void) struct tick_device *td = this_cpu_ptr(&tick_cpu_device); bool broadcast = tick_resume_check_broadcast(); - tick_forward_next_period(); - clockevents_tick_resume(td->evtdev); if (!broadcast) { if (td->mode == TICKDEV_MODE_PERIODIC) diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 21efab7485ca51..e277284c2831c9 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -141,12 +141,6 @@ static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } #endif /* !(BROADCAST && ONESHOT) */ -#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) -extern void tick_sched_forward_next_period(void); -#else -static inline void tick_sched_forward_next_period(void) { } -#endif - /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 646645e981f942..da9455a6b42ba1 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -51,15 +51,6 @@ struct tick_sched *tick_get_tick_sched(int cpu) */ static ktime_t last_jiffies_update; -/* - * Called after resume. Make sure that jiffies are not fast forwarded due to - * clock monotonic being forwarded by the suspended time. - */ -void tick_sched_forward_next_period(void) -{ - last_jiffies_update = tick_next_period; -} - /* * Must be called with interrupts disabled ! */ @@ -804,12 +795,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) return; } - hrtimer_set_expires(&ts->sched_timer, tick); - - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); - else + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED); + } else { + hrtimer_set_expires(&ts->sched_timer, tick); tick_program_event(tick, 1); + } } static void tick_nohz_retain_tick(struct tick_sched *ts) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index dcf7f20fcd12f2..49cbceef5debc7 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -138,12 +138,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { - /* Update both bases so mono and raw stay coupled. */ - tk->tkr_mono.base += delta; - tk->tkr_raw.base += delta; - - /* Accumulate time spent in suspend */ - tk->time_suspended += delta; + tk->offs_boot = ktime_add(tk->offs_boot, delta); } /* @@ -473,6 +468,36 @@ u64 ktime_get_raw_fast_ns(void) } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); +/** + * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. + * + * To keep it NMI safe since we're accessing from tracing, we're not using a + * separate timekeeper with updates to monotonic clock and boot offset + * protected with seqlocks. This has the following minor side effects: + * + * (1) Its possible that a timestamp be taken after the boot offset is updated + * but before the timekeeper is updated. If this happens, the new boot offset + * is added to the old timekeeping making the clock appear to update slightly + * earlier: + * CPU 0 CPU 1 + * timekeeping_inject_sleeptime64() + * __timekeeping_inject_sleeptime(tk, delta); + * timestamp(); + * timekeeping_update(tk, TK_CLEAR_NTP...); + * + * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be + * partially updated. Since the tk->offs_boot update is a rare event, this + * should be a rare occurrence which postprocessing should be able to handle. + */ +u64 notrace ktime_get_boot_fast_ns(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + + return (ktime_get_mono_fast_ns() + ktime_to_ns(tk->offs_boot)); +} +EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); + + /* * See comment for __ktime_get_fast_ns() vs. timestamp ordering */ @@ -764,6 +789,7 @@ EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, + [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; @@ -860,39 +886,6 @@ void ktime_get_ts64(struct timespec64 *ts) } EXPORT_SYMBOL_GPL(ktime_get_ts64); -/** - * ktime_get_active_ts64 - Get the active non-suspended monotonic clock - * @ts: pointer to timespec variable - * - * The function calculates the monotonic clock from the realtime clock and - * the wall_to_monotonic offset, subtracts the accumulated suspend time and - * stores the result in normalized timespec64 format in the variable - * pointed to by @ts. - */ -void ktime_get_active_ts64(struct timespec64 *ts) -{ - struct timekeeper *tk = &tk_core.timekeeper; - struct timespec64 tomono, tsusp; - u64 nsec, nssusp; - unsigned int seq; - - WARN_ON(timekeeping_suspended); - - do { - seq = read_seqcount_begin(&tk_core.seq); - ts->tv_sec = tk->xtime_sec; - nsec = timekeeping_get_ns(&tk->tkr_mono); - tomono = tk->wall_to_monotonic; - nssusp = tk->time_suspended; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - ts->tv_sec += tomono.tv_sec; - ts->tv_nsec = 0; - timespec64_add_ns(ts, nsec + tomono.tv_nsec); - tsusp = ns_to_timespec64(nssusp); - *ts = timespec64_sub(*ts, tsusp); -} - /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * @@ -1593,6 +1586,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, return; } tk_xtime_add(tk, delta); + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } @@ -2125,7 +2119,7 @@ void update_wall_time(void) void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - ktime_t t = ktime_sub(tk->offs_real, tk->time_suspended); + ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } @@ -2188,6 +2182,7 @@ void do_timer(unsigned long ticks) * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset + * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the @@ -2197,7 +2192,7 @@ void do_timer(unsigned long ticks) * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, - ktime_t *offs_tai) + ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; @@ -2214,6 +2209,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 79b67f5e0343ca..7a9b4eb7a1d5bd 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -6,6 +6,7 @@ */ extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, + ktime_t *offs_boot, ktime_t *offs_tai); extern int timekeeping_valid_for_hres(void); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index dfbcf9ee144764..414d7210b2eca7 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1165,7 +1165,7 @@ static struct { { trace_clock, "perf", 1 }, { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, - { ktime_get_mono_fast_ns, "boot", 1 }, + { ktime_get_boot_fast_ns, "boot", 1 }, ARCH_TRACE_CLOCKS }; diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0d7b3ffbecc2a0..b9061ed59bbd9f 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2466,6 +2466,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, else if (strcmp(modifier, "usecs") == 0) *flags |= HIST_FIELD_FL_TIMESTAMP_USECS; else { + hist_err("Invalid field modifier: ", modifier); field = ERR_PTR(-EINVAL); goto out; } @@ -2481,6 +2482,7 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, else { field = trace_find_event_field(file->event_call, field_name); if (!field || !field->size) { + hist_err("Couldn't find field: ", field_name); field = ERR_PTR(-EINVAL); goto out; } @@ -4913,6 +4915,16 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field) seq_printf(m, "%s", field_name); } else if (hist_field->flags & HIST_FIELD_FL_TIMESTAMP) seq_puts(m, "common_timestamp"); + + if (hist_field->flags) { + if (!(hist_field->flags & HIST_FIELD_FL_VAR_REF) && + !(hist_field->flags & HIST_FIELD_FL_EXPR)) { + const char *flags = get_hist_field_flags(hist_field); + + if (flags) + seq_printf(m, ".%s", flags); + } + } } static int event_hist_trigger_print(struct seq_file *m, diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 34fd0e0ec51d2a..ac892878dbe60d 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -55,6 +55,7 @@ struct trace_uprobe { struct list_head list; struct trace_uprobe_filter filter; struct uprobe_consumer consumer; + struct path path; struct inode *inode; char *filename; unsigned long offset; @@ -289,7 +290,7 @@ static void free_trace_uprobe(struct trace_uprobe *tu) for (i = 0; i < tu->tp.nr_args; i++) traceprobe_free_probe_arg(&tu->tp.args[i]); - iput(tu->inode); + path_put(&tu->path); kfree(tu->tp.call.class->system); kfree(tu->tp.call.name); kfree(tu->filename); @@ -363,7 +364,6 @@ static int register_trace_uprobe(struct trace_uprobe *tu) static int create_trace_uprobe(int argc, char **argv) { struct trace_uprobe *tu; - struct inode *inode; char *arg, *event, *group, *filename; char buf[MAX_EVENT_NAME_LEN]; struct path path; @@ -371,7 +371,6 @@ static int create_trace_uprobe(int argc, char **argv) bool is_delete, is_return; int i, ret; - inode = NULL; ret = 0; is_delete = false; is_return = false; @@ -437,21 +436,16 @@ static int create_trace_uprobe(int argc, char **argv) } /* Find the last occurrence, in case the path contains ':' too. */ arg = strrchr(argv[1], ':'); - if (!arg) { - ret = -EINVAL; - goto fail_address_parse; - } + if (!arg) + return -EINVAL; *arg++ = '\0'; filename = argv[1]; ret = kern_path(filename, LOOKUP_FOLLOW, &path); if (ret) - goto fail_address_parse; - - inode = igrab(d_real_inode(path.dentry)); - path_put(&path); + return ret; - if (!inode || !S_ISREG(inode->i_mode)) { + if (!d_is_reg(path.dentry)) { ret = -EINVAL; goto fail_address_parse; } @@ -490,7 +484,7 @@ static int create_trace_uprobe(int argc, char **argv) goto fail_address_parse; } tu->offset = offset; - tu->inode = inode; + tu->path = path; tu->filename = kstrdup(filename, GFP_KERNEL); if (!tu->filename) { @@ -558,7 +552,7 @@ static int create_trace_uprobe(int argc, char **argv) return ret; fail_address_parse: - iput(inode); + path_put(&path); pr_info("Failed to parse address or file.\n"); @@ -922,6 +916,7 @@ probe_event_enable(struct trace_uprobe *tu, struct trace_event_file *file, goto err_flags; tu->consumer.filter = filter; + tu->inode = d_real_inode(tu->path.dentry); ret = uprobe_register(tu->inode, tu->offset, &tu->consumer); if (ret) goto err_buffer; @@ -967,6 +962,7 @@ probe_event_disable(struct trace_uprobe *tu, struct trace_event_file *file) WARN_ON(!uprobe_filter_is_empty(&tu->filter)); uprobe_unregister(tu->inode, tu->offset, &tu->consumer); + tu->inode = NULL; tu->tp.flags &= file ? ~TP_FLAG_TRACE : ~TP_FLAG_PROFILE; uprobe_buffer_disable(); @@ -1337,7 +1333,6 @@ struct trace_event_call * create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) { struct trace_uprobe *tu; - struct inode *inode; struct path path; int ret; @@ -1345,11 +1340,8 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) if (ret) return ERR_PTR(ret); - inode = igrab(d_inode(path.dentry)); - path_put(&path); - - if (!inode || !S_ISREG(inode->i_mode)) { - iput(inode); + if (!d_is_reg(path.dentry)) { + path_put(&path); return ERR_PTR(-EINVAL); } @@ -1364,11 +1356,12 @@ create_local_trace_uprobe(char *name, unsigned long offs, bool is_return) if (IS_ERR(tu)) { pr_info("Failed to allocate trace_uprobe.(%d)\n", (int)PTR_ERR(tu)); + path_put(&path); return ERR_CAST(tu); } tu->offset = offs; - tu->inode = inode; + tu->path = path; tu->filename = kstrdup(name, GFP_KERNEL); init_trace_event_call(tu, &tu->tp.call); diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 671b134573876d..1e37da2e0c25d1 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -207,7 +207,7 @@ static int tracepoint_add_func(struct tracepoint *tp, lockdep_is_held(&tracepoints_mutex)); old = func_add(&tp_funcs, func, prio); if (IS_ERR(old)) { - WARN_ON_ONCE(1); + WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM); return PTR_ERR(old); } @@ -239,7 +239,7 @@ static int tracepoint_remove_func(struct tracepoint *tp, lockdep_is_held(&tracepoints_mutex)); old = func_remove(&tp_funcs, func); if (IS_ERR(old)) { - WARN_ON_ONCE(1); + WARN_ON_ONCE(PTR_ERR(old) != -ENOMEM); return PTR_ERR(old); } diff --git a/lib/errseq.c b/lib/errseq.c index df782418b333ee..81f9e33aa7e72a 100644 --- a/lib/errseq.c +++ b/lib/errseq.c @@ -111,27 +111,22 @@ EXPORT_SYMBOL(errseq_set); * errseq_sample() - Grab current errseq_t value. * @eseq: Pointer to errseq_t to be sampled. * - * This function allows callers to sample an errseq_t value, marking it as - * "seen" if required. + * This function allows callers to initialise their errseq_t variable. + * If the error has been "seen", new callers will not see an old error. + * If there is an unseen error in @eseq, the caller of this function will + * see it the next time it checks for an error. * + * Context: Any context. * Return: The current errseq value. */ errseq_t errseq_sample(errseq_t *eseq) { errseq_t old = READ_ONCE(*eseq); - errseq_t new = old; - /* - * For the common case of no errors ever having been set, we can skip - * marking the SEEN bit. Once an error has been set, the value will - * never go back to zero. - */ - if (old != 0) { - new |= ERRSEQ_SEEN; - if (old != new) - cmpxchg(eseq, old, new); - } - return new; + /* If nobody has seen this error yet, then we can be the first. */ + if (!(old & ERRSEQ_SEEN)) + old = 0; + return old; } EXPORT_SYMBOL(errseq_sample); diff --git a/lib/swiotlb.c b/lib/swiotlb.c index fece57566d45b2..12fbaa4456375a 100644 --- a/lib/swiotlb.c +++ b/lib/swiotlb.c @@ -737,7 +737,7 @@ swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle, swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); out_warn: - if ((attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { + if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) { dev_warn(dev, "swiotlb: coherent allocation failed, size=%zu\n", size); diff --git a/mm/mmap.c b/mm/mmap.c index 188f195883b90b..9d5968d1e8e336 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -100,11 +100,20 @@ pgprot_t protection_map[16] __ro_after_init = { __S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111 }; +#ifndef CONFIG_ARCH_HAS_FILTER_PGPROT +static inline pgprot_t arch_filter_pgprot(pgprot_t prot) +{ + return prot; +} +#endif + pgprot_t vm_get_page_prot(unsigned long vm_flags) { - return __pgprot(pgprot_val(protection_map[vm_flags & + pgprot_t ret = __pgprot(pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) | pgprot_val(arch_vm_get_page_prot(vm_flags))); + + return arch_filter_pgprot(ret); } EXPORT_SYMBOL(vm_get_page_prot); diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index 8806ed5f380233..f8d2167cf3e7a2 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -28,29 +28,46 @@ OPTIONS ...:: Any command you can specify in a shell. +-i:: +--input=:: + Input file name. + -f:: --force:: Don't do ownership validation -t:: ---type=:: +--type=:: Select the memory operation type: load or store (default: load,store) -D:: ---dump-raw-samples=:: +--dump-raw-samples:: Dump the raw decoded samples on the screen in a format that is easy to parse with one sample per line. -x:: ---field-separator:: +--field-separator=:: Specify the field separator used when dump raw samples (-D option). By default, The separator is the space character. -C:: ---cpu-list:: - Restrict dump of raw samples to those provided via this option. Note that the same - option can be passed in record mode. It will be interpreted the same way as perf - record. +--cpu=:: + Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a + comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. Default + is to monitor all CPUS. +-U:: +--hide-unresolved:: + Only display entries resolved to a symbol. + +-p:: +--phys-data:: + Record/Report sample physical addresses + +RECORD OPTIONS +-------------- +-e:: +--event :: + Event selector. Use 'perf mem record -e list' to list available events. -K:: --all-kernel:: @@ -60,12 +77,12 @@ OPTIONS --all-user:: Configure all used events to run in user space. ---ldload:: - Specify desired latency for loads event. +-v:: +--verbose:: + Be more verbose (show counter open errors, etc) --p:: ---phys-data:: - Record/Report sample physical addresses +--ldlat :: + Specify desired latency for loads event. In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/arch/s390/util/auxtrace.c b/tools/perf/arch/s390/util/auxtrace.c index 6cb48e4cffd9a1..3afe8256eff275 100644 --- a/tools/perf/arch/s390/util/auxtrace.c +++ b/tools/perf/arch/s390/util/auxtrace.c @@ -87,6 +87,7 @@ struct auxtrace_record *auxtrace_record__init(struct perf_evlist *evlist, struct perf_evsel *pos; int diagnose = 0; + *err = 0; if (evlist->nr_entries == 0) return NULL; diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c index a4c30f1c70bec1..163b92f339980e 100644 --- a/tools/perf/arch/s390/util/header.c +++ b/tools/perf/arch/s390/util/header.c @@ -146,21 +146,3 @@ char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused) zfree(&buf); return buf; } - -/* - * Compare the cpuid string returned by get_cpuid() function - * with the name generated by the jevents file read from - * pmu-events/arch/s390/mapfile.csv. - * - * Parameter mapcpuid is the cpuid as stored in the - * pmu-events/arch/s390/mapfile.csv. This is just the type number. - * Parameter cpuid is the cpuid returned by function get_cpuid(). - */ -int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) -{ - char *cp = strchr(cpuid, ','); - - if (cp == NULL) - return -1; - return strncmp(cp + 1, mapcpuid, strlen(mapcpuid)); -} diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 147a27e8c937cd..f17dc601b0f39a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -172,6 +172,7 @@ static bool interval_count; static const char *output_name; static int output_fd; static int print_free_counters_hint; +static int print_mixed_hw_group_error; struct perf_stat { bool record; @@ -1126,6 +1127,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); } +static bool is_mixed_hw_group(struct perf_evsel *counter) +{ + struct perf_evlist *evlist = counter->evlist; + u32 pmu_type = counter->attr.type; + struct perf_evsel *pos; + + if (counter->nr_members < 2) + return false; + + evlist__for_each_entry(evlist, pos) { + /* software events can be part of any hardware group */ + if (pos->attr.type == PERF_TYPE_SOFTWARE) + continue; + if (pmu_type == PERF_TYPE_SOFTWARE) { + pmu_type = pos->attr.type; + continue; + } + if (pmu_type != pos->attr.type) + return true; + } + + return false; +} + static void printout(int id, int nr, struct perf_evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise, struct runtime_stat *st) @@ -1178,8 +1203,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED, csv_sep); - if (counter->supported) + if (counter->supported) { print_free_counters_hint = 1; + if (is_mixed_hw_group(counter)) + print_mixed_hw_group_error = 1; + } fprintf(stat_config.output, "%-*s%s", csv_output ? 0 : unit_width, @@ -1256,7 +1284,8 @@ static void uniquify_event_name(struct perf_evsel *counter) char *new_name; char *config; - if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name, + if (counter->uniquified_name || + !counter->pmu_name || !strncmp(counter->name, counter->pmu_name, strlen(counter->pmu_name))) return; @@ -1274,6 +1303,8 @@ static void uniquify_event_name(struct perf_evsel *counter) counter->name = new_name; } } + + counter->uniquified_name = true; } static void collect_all_aliases(struct perf_evsel *counter, @@ -1757,6 +1788,11 @@ static void print_footer(void) " echo 0 > /proc/sys/kernel/nmi_watchdog\n" " perf stat ...\n" " echo 1 > /proc/sys/kernel/nmi_watchdog\n"); + + if (print_mixed_hw_group_error) + fprintf(output, + "The events in group usually have to be from " + "the same PMU. Try reorganizing the group.\n"); } static void print_counters(struct timespec *ts, int argc, const char **argv) diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv index ca7682748a4b8d..78bcf7f8e2066e 100644 --- a/tools/perf/pmu-events/arch/s390/mapfile.csv +++ b/tools/perf/pmu-events/arch/s390/mapfile.csv @@ -1,6 +1,6 @@ Family-model,Version,Filename,EventType -209[78],1,cf_z10,core -281[78],1,cf_z196,core -282[78],1,cf_zec12,core -296[45],1,cf_z13,core -3906,3,cf_z14,core +^IBM.209[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z10,core +^IBM.281[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z196,core +^IBM.282[78].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_zec12,core +^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core +^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index f906b793196fc7..8a33ca4f9e1f7f 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -35,3 +35,6 @@ inherit=0 # sampling disabled sample_freq=0 sample_period=0 +freq=0 +write_backward=0 +sample_id_all=0 diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 1ecc1f0ff84a19..016882dbbc16bd 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -19,12 +19,10 @@ trace_libc_inet_pton_backtrace() { expected[1]=".*inet_pton[[:space:]]\($libc\)$" case "$(uname -m)" in s390x) - eventattr='call-graph=dwarf' + eventattr='call-graph=dwarf,max-stack=4' expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$" - expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$" + expected[3]="(__GI_)?getaddrinfo[[:space:]]\($libc|inlined\)$" expected[4]="main[[:space:]]\(.*/bin/ping.*\)$" - expected[5]="__libc_start_main[[:space:]]\($libc\)$" - expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$" ;; *) eventattr='max-stack=3' diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 3e87486c28fe9d..4cd2cf93f7263e 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -930,8 +930,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, * than leader in case leader 'leads' the sampling. */ if ((leader != evsel) && leader->sample_read) { - attr->sample_freq = 0; - attr->sample_period = 0; + attr->freq = 0; + attr->sample_freq = 0; + attr->sample_period = 0; + attr->write_backward = 0; + attr->sample_id_all = 0; } if (opts->no_samples) @@ -1922,7 +1925,8 @@ int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus, goto fallback_missing_features; } else if (!perf_missing_features.group_read && evsel->attr.inherit && - (evsel->attr.read_format & PERF_FORMAT_GROUP)) { + (evsel->attr.read_format & PERF_FORMAT_GROUP) && + perf_evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; pr_debug2("switching off group read\n"); goto fallback_missing_features; @@ -2754,8 +2758,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, (paranoid = perf_event_paranoid()) > 1) { const char *name = perf_evsel__name(evsel); char *new_name; + const char *sep = ":"; - if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0) + /* Is there already the separator in the name. */ + if (strchr(name, '/') || + strchr(name, ':')) + sep = ""; + + if (asprintf(&new_name, "%s%su", name, sep) < 0) return false; if (evsel->name) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index d3ee3af618ef52..92ec009a292d3e 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -115,6 +115,7 @@ struct perf_evsel { unsigned int sample_size; int id_pos; int is_pos; + bool uniquified_name; bool snapshot; bool supported; bool needs_swap; diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 2eca8478e24f0d..32d50492505d4b 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -1019,13 +1019,6 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type) return ret; } -static void map_groups__fixup_end(struct map_groups *mg) -{ - int i; - for (i = 0; i < MAP__NR_TYPES; ++i) - __map_groups__fixup_end(mg, i); -} - static char *get_kernel_version(const char *root_dir) { char version[PATH_MAX]; @@ -1233,6 +1226,7 @@ int machine__create_kernel_maps(struct machine *machine) { struct dso *kernel = machine__get_kernel(machine); const char *name = NULL; + struct map *map; u64 addr = 0; int ret; @@ -1259,13 +1253,25 @@ int machine__create_kernel_maps(struct machine *machine) machine__destroy_kernel_maps(machine); return -1; } - machine__set_kernel_mmap(machine, addr, 0); + + /* we have a real start address now, so re-order the kmaps */ + map = machine__kernel_map(machine); + + map__get(map); + map_groups__remove(&machine->kmaps, map); + + /* assume it's the last in the kmaps */ + machine__set_kernel_mmap(machine, addr, ~0ULL); + + map_groups__insert(&machine->kmaps, map); + map__put(map); } - /* - * Now that we have all the maps created, just set the ->end of them: - */ - map_groups__fixup_end(&machine->kmaps); + /* update end address of the kernel map using adjacent module address */ + map = map__next(machine__kernel_map(machine)); + if (map) + machine__set_kernel_mmap(machine, addr, map->start); + return 0; } diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 7afeb80cc39eed..d14464c42714b8 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 opt_event_config +PE_NAME '/' event_config '/' { struct list_head *list, *orig_terms, *terms; - if (parse_events_copy_term_list($2, &orig_terms)) + if (parse_events_copy_term_list($3, &orig_terms)) YYABORT; ALLOC_LIST(list); - if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) { + if (parse_events_add_pmu(_parse_state, list, $1, $3, false)) { struct perf_pmu *pmu = NULL; int ok = 0; char *pattern; @@ -262,7 +262,7 @@ PE_NAME opt_event_config if (!ok) YYABORT; } - parse_events_terms__delete($2); + parse_events_terms__delete($3); parse_events_terms__delete(orig_terms); $$ = list; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 61a5e502733815..d2fb597c9a8c78 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -539,9 +539,10 @@ static bool pmu_is_uncore(const char *name) /* * PMU CORE devices have different name other than cpu in sysfs on some - * platforms. looking for possible sysfs files to identify as core device. + * platforms. + * Looking for possible sysfs files to identify the arm core device. */ -static int is_pmu_core(const char *name) +static int is_arm_pmu_core(const char *name) { struct stat st; char path[PATH_MAX]; @@ -550,12 +551,6 @@ static int is_pmu_core(const char *name) if (!sysfs) return 0; - /* Look for cpu sysfs (x86 and others) */ - scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs); - if ((stat(path, &st) == 0) && - (strncmp(name, "cpu", strlen("cpu")) == 0)) - return 1; - /* Look for cpu sysfs (specific to arm) */ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus", sysfs, name); @@ -586,7 +581,7 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused) * cpuid string generated on this platform. * Otherwise return non-zero. */ -int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) +int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid) { regex_t re; regmatch_t pmatch[1]; @@ -668,6 +663,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) struct pmu_events_map *map; struct pmu_event *pe; const char *name = pmu->name; + const char *pname; map = perf_pmu__find_map(pmu); if (!map) @@ -686,11 +682,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) break; } - if (!is_pmu_core(name)) { - /* check for uncore devices */ - if (pe->pmu == NULL) - continue; - if (strncmp(pe->pmu, name, strlen(pe->pmu))) + if (!is_arm_pmu_core(name)) { + pname = pe->pmu ? pe->pmu : "cpu"; + if (strncmp(pname, name, strlen(pname))) continue; } diff --git a/tools/testing/selftests/x86/test_syscall_vdso.c b/tools/testing/selftests/x86/test_syscall_vdso.c index 40370354d4c11e..c9c3281077bca4 100644 --- a/tools/testing/selftests/x86/test_syscall_vdso.c +++ b/tools/testing/selftests/x86/test_syscall_vdso.c @@ -100,12 +100,19 @@ asm ( " shl $32, %r8\n" " orq $0x7f7f7f7f, %r8\n" " movq %r8, %r9\n" - " movq %r8, %r10\n" - " movq %r8, %r11\n" - " movq %r8, %r12\n" - " movq %r8, %r13\n" - " movq %r8, %r14\n" - " movq %r8, %r15\n" + " incq %r9\n" + " movq %r9, %r10\n" + " incq %r10\n" + " movq %r10, %r11\n" + " incq %r11\n" + " movq %r11, %r12\n" + " incq %r12\n" + " movq %r12, %r13\n" + " incq %r13\n" + " movq %r13, %r14\n" + " incq %r14\n" + " movq %r14, %r15\n" + " incq %r15\n" " ret\n" " .code32\n" " .popsection\n" @@ -128,12 +135,13 @@ int check_regs64(void) int err = 0; int num = 8; uint64_t *r64 = ®s64.r8; + uint64_t expected = 0x7f7f7f7f7f7f7f7fULL; if (!kernel_is_64bit) return 0; do { - if (*r64 == 0x7f7f7f7f7f7f7f7fULL) + if (*r64 == expected++) continue; /* register did not change */ if (syscall_addr != (long)&int80) { /* @@ -147,18 +155,17 @@ int check_regs64(void) continue; } } else { - /* INT80 syscall entrypoint can be used by + /* + * INT80 syscall entrypoint can be used by * 64-bit programs too, unlike SYSCALL/SYSENTER. * Therefore it must preserve R12+ * (they are callee-saved registers in 64-bit C ABI). * - * This was probably historically not intended, - * but R8..11 are clobbered (cleared to 0). - * IOW: they are the only registers which aren't - * preserved across INT80 syscall. + * Starting in Linux 4.17 (and any kernel that + * backports the change), R8..11 are preserved. + * Historically (and probably unintentionally), they + * were clobbered or zeroed. */ - if (*r64 == 0 && num <= 11) - continue; } printf("[FAIL]\tR%d has changed:%016llx\n", num, *r64); err++; diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index dba629c5f8acd1..a4c1b76240df2d 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu); static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); static u32 kvm_next_vmid; static unsigned int kvm_vmid_bits __read_mostly; -static DEFINE_SPINLOCK(kvm_vmid_lock); +static DEFINE_RWLOCK(kvm_vmid_lock); static bool vgic_present; @@ -473,11 +473,16 @@ static void update_vttbr(struct kvm *kvm) { phys_addr_t pgd_phys; u64 vmid; + bool new_gen; - if (!need_new_vmid_gen(kvm)) + read_lock(&kvm_vmid_lock); + new_gen = need_new_vmid_gen(kvm); + read_unlock(&kvm_vmid_lock); + + if (!new_gen) return; - spin_lock(&kvm_vmid_lock); + write_lock(&kvm_vmid_lock); /* * We need to re-check the vmid_gen here to ensure that if another vcpu @@ -485,7 +490,7 @@ static void update_vttbr(struct kvm *kvm) * use the same vmid. */ if (!need_new_vmid_gen(kvm)) { - spin_unlock(&kvm_vmid_lock); + write_unlock(&kvm_vmid_lock); return; } @@ -519,7 +524,7 @@ static void update_vttbr(struct kvm *kvm) vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits); kvm->arch.vttbr = kvm_phys_to_vttbr(pgd_phys) | vmid; - spin_unlock(&kvm_vmid_lock); + write_unlock(&kvm_vmid_lock); } static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 6919352cbf15e8..c4762bef13c6d3 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -427,3 +428,62 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) smccc_set_retval(vcpu, val, 0, 0, 0); return 1; } + +int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) +{ + return 1; /* PSCI version */ +} + +int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + if (put_user(KVM_REG_ARM_PSCI_VERSION, uindices)) + return -EFAULT; + + return 0; +} + +int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + if (reg->id == KVM_REG_ARM_PSCI_VERSION) { + void __user *uaddr = (void __user *)(long)reg->addr; + u64 val; + + val = kvm_psci_version(vcpu, vcpu->kvm); + if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; + } + + return -EINVAL; +} + +int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + if (reg->id == KVM_REG_ARM_PSCI_VERSION) { + void __user *uaddr = (void __user *)(long)reg->addr; + bool wants_02; + u64 val; + + if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + wants_02 = test_bit(KVM_ARM_VCPU_PSCI_0_2, vcpu->arch.features); + + switch (val) { + case KVM_ARM_PSCI_0_1: + if (wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + case KVM_ARM_PSCI_0_2: + case KVM_ARM_PSCI_1_0: + if (!wants_02) + return -EINVAL; + vcpu->kvm->arch.psci_version = val; + return 0; + } + } + + return -EINVAL; +} diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index bd125563b15b8d..702936cbe17301 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -600,6 +600,7 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) { struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB; + bool target_vcpu_needs_kick = false; spin_lock(&irq->irq_lock); @@ -670,11 +671,18 @@ static void vgic_prune_ap_list(struct kvm_vcpu *vcpu) list_del(&irq->ap_list); irq->vcpu = target_vcpu; list_add_tail(&irq->ap_list, &new_cpu->ap_list_head); + target_vcpu_needs_kick = true; } spin_unlock(&irq->irq_lock); spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock); spin_unlock_irqrestore(&vcpuA->arch.vgic_cpu.ap_list_lock, flags); + + if (target_vcpu_needs_kick) { + kvm_make_request(KVM_REQ_IRQ_PENDING, target_vcpu); + kvm_vcpu_kick(target_vcpu); + } + goto retry; }