diff options
142 files changed, 1154 insertions, 924 deletions
diff --git a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml index b2a1e42c56fa..71de5631ebae 100644 --- a/Documentation/devicetree/bindings/iio/st,st-sensors.yaml +++ b/Documentation/devicetree/bindings/iio/st,st-sensors.yaml @@ -152,47 +152,6 @@ allOf: maxItems: 1 st,drdy-int-pin: false - - if: - properties: - compatible: - enum: - # Two intertial interrupts i.e. accelerometer/gyro interrupts - - st,h3lis331dl-accel - - st,l3g4200d-gyro - - st,l3g4is-gyro - - st,l3gd20-gyro - - st,l3gd20h-gyro - - st,lis2de12 - - st,lis2dw12 - - st,lis2hh12 - - st,lis2dh12-accel - - st,lis331dl-accel - - st,lis331dlh-accel - - st,lis3de - - st,lis3dh-accel - - st,lis3dhh - - st,lis3mdl-magn - - st,lng2dm-accel - - st,lps331ap-press - - st,lsm303agr-accel - - st,lsm303dlh-accel - - st,lsm303dlhc-accel - - st,lsm303dlm-accel - - st,lsm330-accel - - st,lsm330-gyro - - st,lsm330d-accel - - st,lsm330d-gyro - - st,lsm330dl-accel - - st,lsm330dl-gyro - - st,lsm330dlc-accel - - st,lsm330dlc-gyro - - st,lsm9ds0-gyro - - st,lsm9ds1-magn - then: - properties: - interrupts: - maxItems: 2 - required: - compatible - reg diff --git a/Documentation/i2c/index.rst b/Documentation/i2c/index.rst index 8b76217e370a..6270f1fd7d4e 100644 --- a/Documentation/i2c/index.rst +++ b/Documentation/i2c/index.rst @@ -17,6 +17,7 @@ Introduction busses/index i2c-topology muxes/i2c-mux-gpio + i2c-sysfs Writing device drivers ====================== diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index 35eca377543d..88fa495abbac 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -25,10 +25,10 @@ On x86: - vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock -- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock is - taken inside kvm->arch.mmu_lock, and cannot be taken without already - holding kvm->arch.mmu_lock (typically with ``read_lock``, otherwise - there's no need to take kvm->arch.tdp_mmu_pages_lock at all). +- kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and + kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and + cannot be taken without already holding kvm->arch.mmu_lock (typically with + ``read_lock`` for the TDP MMU, thus the need for additional spinlocks). Everything else is a leaf: no other lock is taken inside the critical sections. @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 14 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Opossums on Parade # *DOCUMENTATION* diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e9a2b8f27792..0ca72f5cda41 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -94,10 +94,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, kvm->arch.return_nisv_io_abort_to_user = true; break; case KVM_CAP_ARM_MTE: - if (!system_supports_mte() || kvm->created_vcpus) - return -EINVAL; - r = 0; - kvm->arch.mte_enabled = true; + mutex_lock(&kvm->lock); + if (!system_supports_mte() || kvm->created_vcpus) { + r = -EINVAL; + } else { + r = 0; + kvm->arch.mte_enabled = true; + } + mutex_unlock(&kvm->lock); break; default: r = -EINVAL; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index d938ce95d3bd..a6ce991b1467 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -193,7 +193,7 @@ static bool range_is_memory(u64 start, u64 end) { struct kvm_mem_range r1, r2; - if (!find_mem_range(start, &r1) || !find_mem_range(end, &r2)) + if (!find_mem_range(start, &r1) || !find_mem_range(end - 1, &r2)) return false; if (r1.start != r2.start) return false; diff --git a/arch/powerpc/include/asm/interrupt.h b/arch/powerpc/include/asm/interrupt.h index d4bdf7d274ac..6b800d3e2681 100644 --- a/arch/powerpc/include/asm/interrupt.h +++ b/arch/powerpc/include/asm/interrupt.h @@ -583,6 +583,9 @@ DECLARE_INTERRUPT_HANDLER_NMI(hmi_exception_realmode); DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException); +/* irq.c */ +DECLARE_INTERRUPT_HANDLER_ASYNC(do_IRQ); + void __noreturn unrecoverable_exception(struct pt_regs *regs); void replay_system_reset(void); diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h index 4982f3711fc3..2b3278534bc1 100644 --- a/arch/powerpc/include/asm/irq.h +++ b/arch/powerpc/include/asm/irq.h @@ -52,7 +52,7 @@ extern void *mcheckirq_ctx[NR_CPUS]; extern void *hardirq_ctx[NR_CPUS]; extern void *softirq_ctx[NR_CPUS]; -extern void do_IRQ(struct pt_regs *regs); +void __do_IRQ(struct pt_regs *regs); extern void __init init_IRQ(void); extern void __do_irq(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 3e5d470a6155..14422e851494 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -70,6 +70,22 @@ struct pt_regs unsigned long __pad[4]; /* Maintain 16 byte interrupt stack alignment */ }; #endif +#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) + struct { /* Must be a multiple of 16 bytes */ + unsigned long mas0; + unsigned long mas1; + unsigned long mas2; + unsigned long mas3; + unsigned long mas6; + unsigned long mas7; + unsigned long srr0; + unsigned long srr1; + unsigned long csrr0; + unsigned long csrr1; + unsigned long dsrr0; + unsigned long dsrr1; + }; +#endif }; #endif diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index a47eefa09bcb..5bee245d832b 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -309,24 +309,21 @@ int main(void) STACK_PT_REGS_OFFSET(STACK_REGS_IAMR, iamr); #endif -#if defined(CONFIG_PPC32) -#if defined(CONFIG_BOOKE) || defined(CONFIG_40x) - DEFINE(EXC_LVL_SIZE, STACK_EXC_LVL_FRAME_SIZE); - DEFINE(MAS0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0)); +#if defined(CONFIG_PPC32) && defined(CONFIG_BOOKE) + STACK_PT_REGS_OFFSET(MAS0, mas0); /* we overload MMUCR for 44x on MAS0 since they are mutually exclusive */ - DEFINE(MMUCR, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas0)); - DEFINE(MAS1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas1)); - DEFINE(MAS2, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas2)); - DEFINE(MAS3, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas3)); - DEFINE(MAS6, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas6)); - DEFINE(MAS7, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, mas7)); - DEFINE(_SRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr0)); - DEFINE(_SRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, srr1)); - DEFINE(_CSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr0)); - DEFINE(_CSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, csrr1)); - DEFINE(_DSRR0, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr0)); - DEFINE(_DSRR1, STACK_INT_FRAME_SIZE+offsetof(struct exception_regs, dsrr1)); -#endif + STACK_PT_REGS_OFFSET(MMUCR, mas0); + STACK_PT_REGS_OFFSET(MAS1, mas1); + STACK_PT_REGS_OFFSET(MAS2, mas2); + STACK_PT_REGS_OFFSET(MAS3, mas3); + STACK_PT_REGS_OFFSET(MAS6, mas6); + STACK_PT_REGS_OFFSET(MAS7, mas7); + STACK_PT_REGS_OFFSET(_SRR0, srr0); + STACK_PT_REGS_OFFSET(_SRR1, srr1); + STACK_PT_REGS_OFFSET(_CSRR0, csrr0); + STACK_PT_REGS_OFFSET(_CSRR1, csrr1); + STACK_PT_REGS_OFFSET(_DSRR0, dsrr0); + STACK_PT_REGS_OFFSET(_DSRR1, dsrr1); #endif /* About the CPU features table */ diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 764edd860ed4..68e5c0a7e99d 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -300,7 +300,7 @@ ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_HPTE_TABLE) EXCEPTION_PROLOG_1 EXCEPTION_PROLOG_2 INTERRUPT_DATA_STORAGE DataAccess handle_dar_dsisr=1 prepare_transfer_to_handler - lwz r5, _DSISR(r11) + lwz r5, _DSISR(r1) andis. r0, r5, DSISR_DABRMATCH@h bne- 1f bl do_page_fault diff --git a/arch/powerpc/kernel/head_booke.h b/arch/powerpc/kernel/head_booke.h index 87b806e8eded..e5503420b6c6 100644 --- a/arch/powerpc/kernel/head_booke.h +++ b/arch/powerpc/kernel/head_booke.h @@ -168,20 +168,18 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) /* only on e500mc */ #define DBG_STACK_BASE dbgirq_ctx -#define EXC_LVL_FRAME_OVERHEAD (THREAD_SIZE - INT_FRAME_SIZE - EXC_LVL_SIZE) - #ifdef CONFIG_SMP #define BOOKE_LOAD_EXC_LEVEL_STACK(level) \ mfspr r8,SPRN_PIR; \ slwi r8,r8,2; \ addis r8,r8,level##_STACK_BASE@ha; \ lwz r8,level##_STACK_BASE@l(r8); \ - addi r8,r8,EXC_LVL_FRAME_OVERHEAD; + addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE; #else #define BOOKE_LOAD_EXC_LEVEL_STACK(level) \ lis r8,level##_STACK_BASE@ha; \ lwz r8,level##_STACK_BASE@l(r8); \ - addi r8,r8,EXC_LVL_FRAME_OVERHEAD; + addi r8,r8,THREAD_SIZE - INT_FRAME_SIZE; #endif /* @@ -208,7 +206,7 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_EMB_HV) mtmsr r11; \ mfspr r11,SPRN_SPRG_THREAD; /* if from user, start at top of */\ lwz r11, TASK_STACK - THREAD(r11); /* this thread's kernel stack */\ - addi r11,r11,EXC_LVL_FRAME_OVERHEAD; /* allocate stack frame */\ + addi r11,r11,THREAD_SIZE - INT_FRAME_SIZE; /* allocate stack frame */\ beq 1f; \ /* COMING FROM USER MODE */ \ stw r9,_CCR(r11); /* save CR */\ @@ -516,24 +514,5 @@ label: bl kernel_fp_unavailable_exception; \ b interrupt_return -#else /* __ASSEMBLY__ */ -struct exception_regs { - unsigned long mas0; - unsigned long mas1; - unsigned long mas2; - unsigned long mas3; - unsigned long mas6; - unsigned long mas7; - unsigned long srr0; - unsigned long srr1; - unsigned long csrr0; - unsigned long csrr1; - unsigned long dsrr0; - unsigned long dsrr1; -}; - -/* ensure this structure is always sized to a multiple of the stack alignment */ -#define STACK_EXC_LVL_FRAME_SIZE ALIGN(sizeof (struct exception_regs), 16) - #endif /* __ASSEMBLY__ */ #endif /* __HEAD_BOOKE_H__ */ diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 91e63eac4e8f..551b653228c4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -750,7 +750,7 @@ void __do_irq(struct pt_regs *regs) trace_irq_exit(regs); } -DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) +void __do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); void *cursp, *irqsp, *sirqsp; @@ -774,6 +774,11 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) set_irq_regs(old_regs); } +DEFINE_INTERRUPT_HANDLER_ASYNC(do_IRQ) +{ + __do_IRQ(regs); +} + static void *__init alloc_vm_stack(void) { return __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, THREADINFO_GFP, diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index cbc28d1a2e1b..7a7cd6bda53e 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -292,7 +292,8 @@ int kprobe_handler(struct pt_regs *regs) if (user_mode(regs)) return 0; - if (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR)) + if (!IS_ENABLED(CONFIG_BOOKE) && + (!(regs->msr & MSR_IR) || !(regs->msr & MSR_DR))) return 0; /* diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 5ff0e55d0db1..defecb3b1b15 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -1167,7 +1167,7 @@ static int __init topology_init(void) * CPU. For instance, the boot cpu might never be valid * for hotplugging. */ - if (smp_ops->cpu_offline_self) + if (smp_ops && smp_ops->cpu_offline_self) c->hotpluggable = 1; #endif diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index e45ce427bffb..c487ba5a6e11 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -586,7 +586,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) #if defined(CONFIG_PPC32) && defined(CONFIG_PPC_PMAC) if (atomic_read(&ppc_n_lost_interrupts) != 0) - do_IRQ(regs); + __do_IRQ(regs); #endif old_regs = set_irq_regs(regs); diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index dfbce527c98e..d56254f05e17 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -1104,7 +1104,7 @@ DEFINE_INTERRUPT_HANDLER(RunModeException) _exception(SIGTRAP, regs, TRAP_UNK, 0); } -DEFINE_INTERRUPT_HANDLER(single_step_exception) +static void __single_step_exception(struct pt_regs *regs) { clear_single_step(regs); clear_br_trace(regs); @@ -1121,6 +1121,11 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception) _exception(SIGTRAP, regs, TRAP_TRACE, regs->nip); } +DEFINE_INTERRUPT_HANDLER(single_step_exception) +{ + __single_step_exception(regs); +} + /* * After we have successfully emulated an instruction, we have to * check if the instruction was being single-stepped, and if so, @@ -1130,7 +1135,7 @@ DEFINE_INTERRUPT_HANDLER(single_step_exception) static void emulate_single_step(struct pt_regs *regs) { if (single_stepping(regs)) - single_step_exception(regs); + __single_step_exception(regs); } static inline int __parse_fpscr(unsigned long fpscr) diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 6b0886668465..0dfaa6ab44cc 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -539,9 +539,10 @@ static void init_cpu_char_feature_flags(struct h_cpu_char_result *result) * H_CPU_BEHAV_FAVOUR_SECURITY_H could be set only if * H_CPU_BEHAV_FAVOUR_SECURITY is. */ - if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) + if (!(result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY)) { security_ftr_clear(SEC_FTR_FAVOUR_SECURITY); - else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H) + pseries_security_flavor = 0; + } else if (result->behaviour & H_CPU_BEHAV_FAVOUR_SECURITY_H) pseries_security_flavor = 1; else pseries_security_flavor = 2; diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index dbdbbc2f1dc5..943fd30095af 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -67,6 +67,7 @@ static struct irq_domain *xive_irq_domain; static struct xive_ipi_desc { unsigned int irq; char name[16]; + atomic_t started; } *xive_ipis; /* @@ -1120,7 +1121,7 @@ static const struct irq_domain_ops xive_ipi_irq_domain_ops = { .alloc = xive_ipi_irq_domain_alloc, }; -static int __init xive_request_ipi(void) +static int __init xive_init_ipis(void) { struct fwnode_handle *fwnode; struct irq_domain *ipi_domain; @@ -1144,10 +1145,6 @@ static int __init xive_request_ipi(void) struct xive_ipi_desc *xid = &xive_ipis[node]; struct xive_ipi_alloc_info info = { node }; - /* Skip nodes without CPUs */ - if (cpumask_empty(cpumask_of_node(node))) - continue; - /* * Map one IPI interrupt per node for all cpus of that node. * Since the HW interrupt number doesn't have any meaning, @@ -1159,11 +1156,6 @@ static int __init xive_request_ipi(void) xid->irq = ret; snprintf(xid->name, sizeof(xid->name), "IPI-%d", node); - - ret = request_irq(xid->irq, xive_muxed_ipi_action, - IRQF_PERCPU | IRQF_NO_THREAD, xid->name, NULL); - - WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret); } return ret; @@ -1178,6 +1170,22 @@ out: return ret; } +static int __init xive_request_ipi(unsigned int cpu) +{ + struct xive_ipi_desc *xid = &xive_ipis[early_cpu_to_node(cpu)]; + int ret; + + if (atomic_inc_return(&xid->started) > 1) + return 0; + + ret = request_irq(xid->irq, xive_muxed_ipi_action, + IRQF_PERCPU | IRQF_NO_THREAD, + xid->name, NULL); + + WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret); + return ret; +} + static int xive_setup_cpu_ipi(unsigned int cpu) { unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu); @@ -1192,6 +1200,9 @@ static int xive_setup_cpu_ipi(unsigned int cpu) if (xc->hw_ipi != XIVE_BAD_IRQ) return 0; + /* Register the IPI */ + xive_request_ipi(cpu); + /* Grab an IPI from the backend, this will populate xc->hw_ipi */ if (xive_ops->get_ipi(cpu, xc)) return -EIO; @@ -1231,6 +1242,8 @@ static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc) if (xc->hw_ipi == XIVE_BAD_IRQ) return; + /* TODO: clear IPI mapping */ + /* Mask the IPI */ xive_do_source_set_mask(&xc->ipi_data, true); @@ -1253,7 +1266,7 @@ void __init xive_smp_probe(void) smp_ops->cause_ipi = xive_cause_ipi; /* Register the IPI */ - xive_request_ipi(); + xive_init_ipis(); /* Allocate and setup IPI for the boot CPU */ xive_setup_cpu_ipi(smp_processor_id()); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index d3081e4d9600..3397ddac1a30 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -11,7 +11,7 @@ endif CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,) ifdef CONFIG_KEXEC -AFLAGS_kexec_relocate.o := -mcmodel=medany -mno-relax +AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) endif extra-y += head.o diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 88134cc288d9..7cb4f391d106 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -197,7 +197,7 @@ static void __init setup_bootmem(void) * if end of dram is equal to maximum addressable memory. For 64-bit * kernel, this problem can't happen here as the end of the virtual * address space is occupied by the kernel mapping then this check must - * be done in create_kernel_page_table. + * be done as soon as the kernel mapping base address is determined. */ max_mapped_addr = __pa(~(ulong)0); if (max_mapped_addr == (phys_ram_end - 1)) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 974cbfb1eefe..af6ce8d4c86a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1038,6 +1038,13 @@ struct kvm_arch { struct list_head lpage_disallowed_mmu_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; + /* + * Protects marking pages unsync during page faults, as TDP MMU page + * faults only take mmu_lock for read. For simplicity, the unsync + * pages lock is always taken when marking pages unsync regardless of + * whether mmu_lock is held for read or write. + */ + spinlock_t mmu_unsync_pages_lock; struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index e322676039f4..b00dbc5fac2b 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -184,6 +184,8 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define V_IGN_TPR_SHIFT 20 #define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) +#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK) + #define V_INTR_MASKING_SHIFT 24 #define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index d5c691a3208b..39224e035e47 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1986,7 +1986,8 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct irq_chip ioapic_ir_chip __read_mostly = { @@ -1999,7 +2000,8 @@ static struct irq_chip ioapic_ir_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static inline void init_IO_APIC_traps(void) diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 44ebe25e7703..dbacb9ec8843 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -58,11 +58,13 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * The quirk bit is not set in this case. * - The new vector is the same as the old vector * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) + * - The interrupt is not yet started up * - The new destination CPU is the same as the old destination CPU */ if (!irqd_msi_nomask_quirk(irqd) || cfg->vector == old_cfg.vector || old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || + !irqd_is_started(irqd) || cfg->dest_apicid == old_cfg.dest_apicid) { irq_msi_update_msg(irqd, cfg); return ret; @@ -150,7 +152,8 @@ static struct irq_chip pci_msi_controller = { .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_set_affinity = msi_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, @@ -219,7 +222,8 @@ static struct irq_chip pci_msi_ir_controller = { .irq_mask = pci_msi_mask_irq, .irq_ack = irq_chip_ack_parent, .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static struct msi_domain_info pci_msi_ir_domain_info = { @@ -273,7 +277,8 @@ static struct irq_chip dmar_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = dmar_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP, }; static int dmar_msi_init(struct irq_domain *domain, diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index f07c10b87a87..57e4bb695ff9 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -285,15 +285,14 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) return chunks >>= shift; } -static int __mon_event_count(u32 rmid, struct rmid_read *rr) +static u64 __mon_event_count(u32 rmid, struct rmid_read *rr) { struct mbm_state *m; u64 chunks, tval; tval = __rmid_read(rmid, rr->evtid); if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) { - rr->val = tval; - return -EINVAL; + return tval; } switch (rr->evtid) { case QOS_L3_OCCUP_EVENT_ID: @@ -305,12 +304,6 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) case QOS_L3_MBM_LOCAL_EVENT_ID: m = &rr->d->mbm_local[rmid]; break; - default: - /* - * Code would never reach here because - * an invalid event id would fail the __rmid_read. - */ - return -EINVAL; } if (rr->first) { @@ -361,23 +354,29 @@ void mon_event_count(void *info) struct rdtgroup *rdtgrp, *entry; struct rmid_read *rr = info; struct list_head *head; + u64 ret_val; rdtgrp = rr->rgrp; - if (__mon_event_count(rdtgrp->mon.rmid, rr)) - return; + ret_val = __mon_event_count(rdtgrp->mon.rmid, rr); /* - * For Ctrl groups read data from child monitor groups. + * For Ctrl groups read data from child monitor groups and + * add them together. Count events which are read successfully. + * Discard the rmid_read's reporting errors. */ head = &rdtgrp->mon.crdtgrp_list; if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { - if (__mon_event_count(entry->mon.rmid, rr)) - return; + if (__mon_event_count(entry->mon.rmid, rr) == 0) + ret_val = 0; } } + + /* Report error if none of rmid_reads are successful */ + if (ret_val) + rr->val = ret_val; } /* diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 08651a4e6aa0..42fc41dd0e1f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -508,7 +508,7 @@ static struct irq_chip hpet_msi_controller __ro_after_init = { .irq_set_affinity = msi_domain_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_write_msi_msg = hpet_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_AFFINITY_PRE_STARTUP, }; static int hpet_msi_init(struct irq_domain *domain, diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 739be5da3bca..fe03bd978761 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -208,30 +208,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_mmu_after_set_cpuid(vcpu); } -static int is_efer_nx(void) -{ - return host_efer & EFER_NX; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_cpuid_entry2 *e, *entry; - - entry = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && cpuid_entry_has(entry, X86_FEATURE_NX) && !is_efer_nx()) { - cpuid_entry_clear(entry, X86_FEATURE_NX); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -302,7 +278,6 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); kvm_update_cpuid_runtime(vcpu); kvm_vcpu_after_set_cpuid(vcpu); @@ -401,7 +376,6 @@ static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) void kvm_set_cpu_caps(void) { - unsigned int f_nx = is_efer_nx() ? F(NX) : 0; #ifdef CONFIG_X86_64 unsigned int f_gbpages = F(GBPAGES); unsigned int f_lm = F(LM); @@ -515,7 +489,7 @@ void kvm_set_cpu_caps(void) F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) ); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 0b38f944c6b6..41d2a53c5dea 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1933,7 +1933,7 @@ ret_success: void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *entry; - struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + struct kvm_vcpu_hv *hv_vcpu; entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c4f4fa23320e..47b765270239 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2535,6 +2535,7 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) { struct kvm_mmu_page *sp; + bool locked = false; /* * Force write-protection if the page is being tracked. Note, the page @@ -2557,9 +2558,34 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync) if (sp->unsync) continue; + /* + * TDP MMU page faults require an additional spinlock as they + * run with mmu_lock held for read, not write, and the unsync + * logic is not thread safe. Take the spinklock regardless of + * the MMU type to avoid extra conditionals/parameters, there's + * no meaningful penalty if mmu_lock is held for write. + */ + if (!locked) { + locked = true; + spin_lock(&vcpu->kvm->arch.mmu_unsync_pages_lock); + + /* + * Recheck after taking the spinlock, a different vCPU + * may have since marked the page unsync. A false + * positive on the unprotected check above is not + * possible as clearing sp->unsync _must_ hold mmu_lock + * for write, i.e. unsync cannot transition from 0->1 + * while this CPU holds mmu_lock for read (or write). + */ + if (READ_ONCE(sp->unsync)) + continue; + } + WARN_ON(sp->role.level != PG_LEVEL_4K); kvm_unsync_page(vcpu, sp); } + if (locked) + spin_unlock(&vcpu->kvm->arch.mmu_unsync_pages_lock); /* * We need to ensure that the marking of unsync pages is visible @@ -5537,6 +5563,8 @@ void kvm_mmu_init_vm(struct kvm *kvm) { struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker; + spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); + if (!kvm_mmu_init_tdp_mmu(kvm)) /* * No smp_load/store wrappers needed here as we are in diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 0853370bd811..d80cb122b5f3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -43,6 +43,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) if (!kvm->arch.tdp_mmu_enabled) return; + WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* @@ -81,8 +82,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, bool shared) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); - kvm_lockdep_assert_mmu_lock_held(kvm, shared); if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) @@ -94,7 +93,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, list_del_rcu(&root->link); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); - zap_gfn_range(kvm, root, 0, max_gfn, false, false, shared); + zap_gfn_range(kvm, root, 0, -1ull, false, false, shared); call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } @@ -724,13 +723,29 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, bool can_yield, bool flush, bool shared) { + gfn_t max_gfn_host = 1ULL << (shadow_phys_bits - PAGE_SHIFT); + bool zap_all = (start == 0 && end >= max_gfn_host); struct tdp_iter iter; + /* + * No need to try to step down in the iterator when zapping all SPTEs, + * zapping the top-level non-leaf SPTEs will recurse on their children. + */ + int min_level = zap_all ? root->role.level : PG_LEVEL_4K; + + /* + * Bound the walk at host.MAXPHYADDR, guest accesses beyond that will + * hit a #PF(RSVD) and never get to an EPT Violation/Misconfig / #NPF, + * and so KVM will never install a SPTE for such addresses. + */ + end = min(end, max_gfn_host); + kvm_lockdep_assert_mmu_lock_held(kvm, shared); rcu_read_lock(); - tdp_root_for_each_pte(iter, root, start, end) { + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, start, end) { retry: if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, shared)) { @@ -744,9 +759,10 @@ retry: /* * If this is a non-last-level SPTE that covers a larger range * than should be zapped, continue, and zap the mappings at a - * lower level. + * lower level, except when zapping all SPTEs. */ - if ((iter.gfn < start || + if (!zap_all && + (iter.gfn < start || iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) && !is_last_spte(iter.old_spte, iter.level)) continue; @@ -794,12 +810,11 @@ bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start, void kvm_tdp_mmu_zap_all(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); bool flush = false; int i; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, max_gfn, + flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, 0, -1ull, flush, false); if (flush) @@ -838,7 +853,6 @@ static struct kvm_mmu_page *next_invalidated_root(struct kvm *kvm, */ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) { - gfn_t max_gfn = 1ULL << (shadow_phys_bits - PAGE_SHIFT); struct kvm_mmu_page *next_root; struct kvm_mmu_page *root; bool flush = false; @@ -854,8 +868,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) rcu_read_unlock(); - flush = zap_gfn_range(kvm, root, 0, max_gfn, true, flush, - true); + flush = zap_gfn_range(kvm, root, 0, -1ull, true, flush, true); /* * Put the reference acquired in diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 61738ff8ef33..e5515477c30a 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -158,6 +158,9 @@ void recalc_intercepts(struct vcpu_svm *svm) /* If SMI is not intercepted, ignore guest SMI intercept as well */ if (!intercept_smi) vmcb_clr_intercept(c, INTERCEPT_SMI); + + vmcb_set_intercept(c, INTERCEPT_VMLOAD); + vmcb_set_intercept(c, INTERCEPT_VMSAVE); } static void copy_vmcb_control_area(struct vmcb_control_area *dst, @@ -503,7 +506,11 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) { - const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK; + const u32 int_ctl_vmcb01_bits = + V_INTR_MASKING_MASK | V_GIF_MASK | V_GIF_ENABLE_MASK; + + const u32 int_ctl_vmcb12_bits = V_TPR_MASK | V_IRQ_INJECTION_BITS_MASK; + struct kvm_vcpu *vcpu = &svm->vcpu; /* @@ -535,8 +542,8 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm) vcpu->arch.l1_tsc_offset + svm->nested.ctl.tsc_offset; svm->vmcb->control.int_ctl = - (svm->nested.ctl.int_ctl & ~mask) | - (svm->vmcb01.ptr->control.int_ctl & mask); + (svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) | + (svm->vmcb01.ptr->control.int_ctl & int_ctl_vmcb01_bits); svm->vmcb->control.virt_ext = svm->nested.ctl.virt_ext; svm->vmcb->control.int_vector = svm->nested.ctl.int_vector; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e8ccab50ebf6..69639f9624f5 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1589,17 +1589,18 @@ static void svm_set_vintr(struct vcpu_svm *svm) static void svm_clear_vintr(struct vcpu_svm *svm) { - const u32 mask = V_TPR_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK | V_INTR_MASKING_MASK; svm_clr_intercept(svm, INTERCEPT_VINTR); /* Drop int_ctl fields related to VINTR injection. */ - svm->vmcb->control.int_ctl &= mask; + svm->vmcb->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK; if (is_guest_mode(&svm->vcpu)) { - svm->vmcb01.ptr->control.int_ctl &= mask; + svm->vmcb01.ptr->control.int_ctl &= ~V_IRQ_INJECTION_BITS_MASK; WARN_ON((svm->vmcb->control.int_ctl & V_TPR_MASK) != (svm->nested.ctl.int_ctl & V_TPR_MASK)); - svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & ~mask; + + svm->vmcb->control.int_ctl |= svm->nested.ctl.int_ctl & + V_IRQ_INJECTION_BITS_MASK; } vmcb_mark_dirty(svm->vmcb, VMCB_INTR); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 1a52134b0c42..b3f77d18eb5a 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -330,6 +330,31 @@ void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu) vcpu_put(vcpu); } +#define EPTP_PA_MASK GENMASK_ULL(51, 12) + +static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) +{ + return VALID_PAGE(root_hpa) && + ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); +} + +static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, + gpa_t addr) +{ + uint i; + struct kvm_mmu_root_info *cached_root; + + WARN_ON_ONCE(!mmu_is_nested(vcpu)); + + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + cached_root = &vcpu->arch.mmu->prev_roots[i]; + + if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, + eptp)) + vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa); + } +} + static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) { @@ -342,10 +367,22 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, vm_exit_reason = EXIT_REASON_PML_FULL; vmx->nested.pml_full = false; exit_qualification &= INTR_INFO_UNBLOCK_NMI; - } else if (fault->error_code & PFERR_RSVD_MASK) - vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; - else - vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + } else { + if (fault->error_code & PFERR_RSVD_MASK) + vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; + else + vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + + /* + * Although the caller (kvm_inject_emulated_page_fault) would + * have already synced the faulting address in the shadow EPT + * tables for the current EPTP12, we also need to sync it for + * any other cached EPTP02s based on the same EP4TA, since the + * TLB associates mappings to the EP4TA rather than the full EPTP. + */ + nested_ept_invalidate_addr(vcpu, vmcs12->ept_pointer, + fault->address); + } nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification); vmcs12->guest_physical_address = fault->address; @@ -5325,14 +5362,6 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return nested_vmx_succeed(vcpu); } -#define EPTP_PA_MASK GENMASK_ULL(51, 12) - -static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) -{ - return VALID_PAGE(root_hpa) && - ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK)); -} - /* Emulate the INVEPT instruction */ static int handle_invept(struct kvm_vcpu *vcpu) { @@ -5826,7 +5855,8 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, if (is_nmi(intr_info)) return true; else if (is_page_fault(intr_info)) - return vcpu->arch.apf.host_apf_flags || !enable_ept; + return vcpu->arch.apf.host_apf_flags || + vmx_need_pf_intercept(vcpu); else if (is_debug(intr_info) && vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index db88ed4f2121..17a1cb4b059d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -522,7 +522,7 @@ static inline struct vmcs *alloc_vmcs(bool shadow) static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) { - return vmx->secondary_exec_control & + return secondary_exec_controls_get(vmx) & SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE; } diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk index fd1ab80be0de..a4cf678cf5c8 100644 --- a/arch/x86/tools/chkobjdump.awk +++ b/arch/x86/tools/chkobjdump.awk @@ -10,6 +10,7 @@ BEGIN { /^GNU objdump/ { verstr = "" + gsub(/\(.*\)/, ""); for (i = 3; i <= NF; i++) if (match($(i), "^[0-9]")) { verstr = $(i); diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 64053d67a97b..2f2158e05a91 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -9,12 +9,6 @@ config MQ_IOSCHED_DEADLINE help MQ version of the deadline IO scheduler. -config MQ_IOSCHED_DEADLINE_CGROUP - tristate - default y - depends on MQ_IOSCHED_DEADLINE - depends on BLK_CGROUP - config MQ_IOSCHED_KYBER tristate "Kyber I/O scheduler" default y diff --git a/block/Makefile b/block/Makefile index bfbe4e13ca1e..1e1afa10f869 100644 --- a/block/Makefile +++ b/block/Makefile @@ -22,8 +22,6 @@ obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o -mq-deadline-y += mq-deadline-main.o -mq-deadline-$(CONFIG_MQ_IOSCHED_DEADLINE_CGROUP)+= mq-deadline-cgroup.o obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o obj-$(CONFIG_IOSCHED_BFQ) += bfq.o diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 5fac3757e6e0..0e56557cacf2 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -3061,19 +3061,19 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf, if (v < CGROUP_WEIGHT_MIN || v > CGROUP_WEIGHT_MAX) return -EINVAL; - spin_lock(&blkcg->lock); + spin_lock_irq(&blkcg->lock); iocc->dfl_weight = v * WEIGHT_ONE; hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { struct ioc_gq *iocg = blkg_to_iocg(blkg); if (iocg) { - spin_lock_irq(&iocg->ioc->lock); + spin_lock(&iocg->ioc->lock); ioc_now(iocg->ioc, &now); weight_updated(iocg, &now); - spin_unlock_irq(&iocg->ioc->lock); + spin_unlock(&iocg->ioc->lock); } } - spin_unlock(&blkcg->lock); + spin_unlock_irq(&blkcg->lock); return nbytes; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 2c4ac51e54eb..2fe396385a4a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2994,10 +2994,12 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared) int i; queue_for_each_hw_ctx(q, hctx, i) { - if (shared) + if (shared) { hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; - else + } else { + blk_mq_tag_idle(hctx); hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; + } } } diff --git a/block/mq-deadline-cgroup.c b/block/mq-deadline-cgroup.c deleted file mode 100644 index 3b4bfddec39f..000000000000 --- a/block/mq-deadline-cgroup.c +++ /dev/null @@ -1,126 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <linux/blk-cgroup.h> -#include <linux/ioprio.h> - -#include "mq-deadline-cgroup.h" - -static struct blkcg_policy dd_blkcg_policy; - -static struct blkcg_policy_data *dd_cpd_alloc(gfp_t gfp) -{ - struct dd_blkcg *pd; - - pd = kzalloc(sizeof(*pd), gfp); - if (!pd) - return NULL; - pd->stats = alloc_percpu_gfp(typeof(*pd->stats), - GFP_KERNEL | __GFP_ZERO); - if (!pd->stats) { - kfree(pd); - return NULL; - } - return &pd->cpd; -} - -static void dd_cpd_free(struct blkcg_policy_data *cpd) -{ - struct dd_blkcg *dd_blkcg = container_of(cpd, typeof(*dd_blkcg), cpd); - - free_percpu(dd_blkcg->stats); - kfree(dd_blkcg); -} - -static struct dd_blkcg *dd_blkcg_from_pd(struct blkg_policy_data *pd) -{ - return container_of(blkcg_to_cpd(pd->blkg->blkcg, &dd_blkcg_policy), - struct dd_blkcg, cpd); -} - -/* - * Convert an association between a block cgroup and a request queue into a - * pointer to the mq-deadline information associated with a (blkcg, queue) pair. - */ -struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) -{ - struct blkg_policy_data *pd; - - pd = blkg_to_pd(bio->bi_blkg, &dd_blkcg_policy); - if (!pd) - return NULL; - - return dd_blkcg_from_pd(pd); -} - -static size_t dd_pd_stat(struct blkg_policy_data *pd, char *buf, size_t size) -{ - static const char *const prio_class_name[] = { - [IOPRIO_CLASS_NONE] = "NONE", - [IOPRIO_CLASS_RT] = "RT", - [IOPRIO_CLASS_BE] = "BE", - [IOPRIO_CLASS_IDLE] = "IDLE", - }; - struct dd_blkcg *blkcg = dd_blkcg_from_pd(pd); - int res = 0; - u8 prio; - - for (prio = 0; prio < ARRAY_SIZE(blkcg->stats->stats); prio++) - res += scnprintf(buf + res, size - res, - " [%s] dispatched=%u inserted=%u merged=%u", - prio_class_name[prio], - ddcg_sum(blkcg, dispatched, prio) + - ddcg_sum(blkcg, merged, prio) - - ddcg_sum(blkcg, completed, prio), - ddcg_sum(blkcg, inserted, prio) - - ddcg_sum(blkcg, completed, prio), - ddcg_sum(blkcg, merged, prio)); - - return res; -} - -static struct blkg_policy_data *dd_pd_alloc(gfp_t gfp, struct request_queue *q, - struct blkcg *blkcg) -{ - struct dd_blkg *pd; - - pd = kzalloc(sizeof(*pd), gfp); - if (!pd) - return NULL; - return &pd->pd; -} - -static void dd_pd_free(struct blkg_policy_data *pd) -{ - struct dd_blkg *dd_blkg = container_of(pd, typeof(*dd_blkg), pd); - - kfree(dd_blkg); -} - -static struct blkcg_policy dd_blkcg_policy = { - .cpd_alloc_fn = dd_cpd_alloc, - .cpd_free_fn = dd_cpd_free, - - .pd_alloc_fn = dd_pd_alloc, - .pd_free_fn = dd_pd_free, - .pd_stat_fn = dd_pd_stat, -}; - -int dd_activate_policy(struct request_queue *q) -{ - return blkcg_activate_policy(q, &dd_blkcg_policy); -} - -void dd_deactivate_policy(struct request_queue *q) -{ - blkcg_deactivate_policy(q, &dd_blkcg_policy); -} - -int __init dd_blkcg_init(void) -{ - return blkcg_policy_register(&dd_blkcg_policy); -} - -void __exit dd_blkcg_exit(void) -{ - blkcg_policy_unregister(&dd_blkcg_policy); -} diff --git a/block/mq-deadline-cgroup.h b/block/mq-deadline-cgroup.h deleted file mode 100644 index 0143fd74f3ce..000000000000 --- a/block/mq-deadline-cgroup.h +++ /dev/null @@ -1,114 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -#if !defined(_MQ_DEADLINE_CGROUP_H_) -#define _MQ_DEADLINE_CGROUP_H_ - -#include <linux/blk-cgroup.h> - -struct request_queue; - -/** - * struct io_stats_per_prio - I/O statistics per I/O priority class. - * @inserted: Number of inserted requests. - * @merged: Number of merged requests. - * @dispatched: Number of dispatched requests. - * @completed: Number of I/O completions. - */ -struct io_stats_per_prio { - local_t inserted; - local_t merged; - local_t dispatched; - local_t completed; -}; - -/* I/O statistics per I/O cgroup per I/O priority class (IOPRIO_CLASS_*). */ -struct blkcg_io_stats { - struct io_stats_per_prio stats[4]; -}; - -/** - * struct dd_blkcg - Per cgroup data. - * @cpd: blkcg_policy_data structure. - * @stats: I/O statistics. - */ -struct dd_blkcg { - struct blkcg_policy_data cpd; /* must be the first member */ - struct blkcg_io_stats __percpu *stats; -}; - -/* - * Count one event of type 'event_type' and with I/O priority class - * 'prio_class'. - */ -#define ddcg_count(ddcg, event_type, prio_class) do { \ -if (ddcg) { \ - struct blkcg_io_stats *io_stats = get_cpu_ptr((ddcg)->stats); \ - \ - BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ - BUILD_BUG_ON(!__same_type((prio_class), u8)); \ - local_inc(&io_stats->stats[(prio_class)].event_type); \ - put_cpu_ptr(io_stats); \ -} \ -} while (0) - -/* - * Returns the total number of ddcg_count(ddcg, event_type, prio_class) calls - * across all CPUs. No locking or barriers since it is fine if the returned - * sum is slightly outdated. - */ -#define ddcg_sum(ddcg, event_type, prio) ({ \ - unsigned int cpu; \ - u32 sum = 0; \ - \ - BUILD_BUG_ON(!__same_type((ddcg), struct dd_blkcg *)); \ - BUILD_BUG_ON(!__same_type((prio), u8)); \ - for_each_present_cpu(cpu) \ - sum += local_read(&per_cpu_ptr((ddcg)->stats, cpu)-> \ - stats[(prio)].event_type); \ - sum; \ -}) - -#ifdef CONFIG_BLK_CGROUP - -/** - * struct dd_blkg - Per (cgroup, request queue) data. - * @pd: blkg_policy_data structure. - */ -struct dd_blkg { - struct blkg_policy_data pd; /* must be the first member */ -}; - -struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio); -int dd_activate_policy(struct request_queue *q); -void dd_deactivate_policy(struct request_queue *q); -int __init dd_blkcg_init(void); -void __exit dd_blkcg_exit(void); - -#else /* CONFIG_BLK_CGROUP */ - -static inline struct dd_blkcg *dd_blkcg_from_bio(struct bio *bio) -{ - return NULL; -} - -static inline int dd_activate_policy(struct request_queue *q) -{ - return 0; -} - -static inline void dd_deactivate_policy(struct request_queue *q) -{ -} - -static inline int dd_blkcg_init(void) -{ - return 0; -} - -static inline void dd_blkcg_exit(void) -{ -} - -#endif /* CONFIG_BLK_CGROUP */ - -#endif /* _MQ_DEADLINE_CGROUP_H_ */ diff --git a/block/mq-deadline-main.c b/block/mq-deadline.c index 6f612e6dc82b..a09761cbdf12 100644 --- a/block/mq-deadline-main.c +++ b/block/mq-deadline.c @@ -25,7 +25,6 @@ #include "blk-mq-debugfs.h" #include "blk-mq-tag.h" #include "blk-mq-sched.h" -#include "mq-deadline-cgroup.h" /* * See Documentation/block/deadline-iosched.rst @@ -57,6 +56,14 @@ enum dd_prio { enum { DD_PRIO_COUNT = 3 }; +/* I/O statistics per I/O priority. */ +struct io_stats_per_prio { + local_t inserted; + local_t merged; + local_t dispatched; + local_t completed; +}; + /* I/O statistics for all I/O priorities (enum dd_prio). */ struct io_stats { struct io_stats_per_prio stats[DD_PRIO_COUNT]; @@ -79,9 +86,6 @@ struct deadline_data { * run time data */ - /* Request queue that owns this data structure. */ - struct request_queue *queue; - struct dd_per_prio per_prio[DD_PRIO_COUNT]; /* Data direction of latest dispatched request. */ @@ -234,10 +238,8 @@ static void dd_merged_requests(struct request_queue *q, struct request *req, struct deadline_data *dd = q->elevator->elevator_data; const u8 ioprio_class = dd_rq_ioclass(next); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; - struct dd_blkcg *blkcg = next->elv.priv[0]; dd_count(dd, merged, prio); - ddcg_count(blkcg, merged, ioprio_class); /* * if next expires before rq, assign its expire time to rq @@ -375,7 +377,6 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd, { struct request *rq, *next_rq; enum dd_data_dir data_dir; - struct dd_blkcg *blkcg; enum dd_prio prio; u8 ioprio_class; @@ -474,8 +475,6 @@ done: ioprio_class = dd_rq_ioclass(rq); prio = ioprio_class_to_prio[ioprio_class]; dd_count(dd, dispatched, prio); - blkcg = rq->elv.priv[0]; - ddcg_count(blkcg, dispatched, ioprio_class); /* * If the request needs its target zone locked, do it. */ @@ -569,8 +568,6 @@ static void dd_exit_sched(struct elevator_queue *e) struct deadline_data *dd = e->elevator_data; enum dd_prio prio; - dd_deactivate_policy(dd->queue); - for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; @@ -584,7 +581,7 @@ static void dd_exit_sched(struct elevator_queue *e) } /* - * Initialize elevator private data (deadline_data) and associate with blkcg. + * initialize elevator private data (deadline_data). */ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) { @@ -593,12 +590,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) enum dd_prio prio; int ret = -ENOMEM; - /* - * Initialization would be very tricky if the queue is not frozen, - * hence the warning statement below. - */ - WARN_ON_ONCE(!percpu_ref_is_zero(&q->q_usage_counter)); - eq = elevator_alloc(q, e); if (!eq) return ret; @@ -614,8 +605,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) if (!dd->stats) goto free_dd; - dd->queue = q; - for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; @@ -635,17 +624,9 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e) spin_lock_init(&dd->lock); spin_lock_init(&dd->zone_lock); - ret = dd_activate_policy(q); - if (ret) - goto free_stats; - - ret = 0; q->elevator = eq; return 0; -free_stats: - free_percpu(dd->stats); - free_dd: kfree(dd); @@ -718,7 +699,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); struct dd_per_prio *per_prio; enum dd_prio prio; - struct dd_blkcg *blkcg; LIST_HEAD(free); lockdep_assert_held(&dd->lock); @@ -729,18 +709,8 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, */ blk_req_zone_write_unlock(rq); - /* - * If a block cgroup has been associated with the submitter and if an - * I/O priority has been set in the associated block cgroup, use the - * lowest of the cgroup priority and the request priority for the - * request. If no priority has been set in the request, use the cgroup - * priority. - */ prio = ioprio_class_to_prio[ioprio_class]; dd_count(dd, inserted, prio); - blkcg = dd_blkcg_from_bio(rq->bio); - ddcg_count(blkcg, inserted, ioprio_class); - rq->elv.priv[0] = blkcg; if (blk_mq_sched_try_insert_merge(q, rq, &free)) { blk_mq_free_requests(&free); @@ -789,10 +759,12 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, spin_unlock(&dd->lock); } -/* Callback from inside blk_mq_rq_ctx_init(). */ +/* + * Nothing to do here. This is defined only to ensure that .finish_request + * method is called upon request completion. + */ static void dd_prepare_request(struct request *rq) { - rq->elv.priv[0] = NULL; } /* @@ -815,13 +787,11 @@ static void dd_finish_request(struct request *rq) { struct request_queue *q = rq->q; struct deadline_data *dd = q->elevator->elevator_data; - struct dd_blkcg *blkcg = rq->elv.priv[0]; const u8 ioprio_class = dd_rq_ioclass(rq); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; struct dd_per_prio *per_prio = &dd->per_prio[prio]; dd_count(dd, completed, prio); - ddcg_count(blkcg, completed, ioprio_class); if (blk_queue_is_zoned(q)) { unsigned long flags; @@ -1144,26 +1114,11 @@ MODULE_ALIAS("mq-deadline-iosched"); static int __init deadline_init(void) { - int ret; - - ret = elv_register(&mq_deadline); - if (ret) - goto out; - ret = dd_blkcg_init(); - if (ret) - goto unreg; - -out: - return ret; - -unreg: - elv_unregister(&mq_deadline); - goto out; + return elv_register(&mq_deadline); } static void __exit deadline_exit(void) { - dd_blkcg_exit(); elv_unregister(&mq_deadline); } diff --git a/crypto/Kconfig b/crypto/Kconfig index ca3b02dcbbfa..64b772c5d1c9 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -1768,7 +1768,7 @@ config CRYPTO_DRBG_HMAC bool default y select CRYPTO_HMAC - select CRYPTO_SHA256 + select CRYPTO_SHA512 config CRYPTO_DRBG_HASH bool "Enable Hash DRBG" diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 23d9a09d7060..a3ef6cce644c 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3021,6 +3021,9 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev; struct nd_mapping_desc *mapping; + /* range index 0 == unmapped in SPA or invalid-SPA */ + if (memdev->range_index == 0 || spa->range_index == 0) + continue; if (memdev->range_index != spa->range_index) continue; if (count >= ND_MAX_MAPPINGS) { diff --git a/drivers/base/core.c b/drivers/base/core.c index f6360490a4a3..6c0ef9d55a34 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2837,6 +2837,7 @@ void device_initialize(struct device *dev) device_pm_init(dev); set_dev_node(dev, -1); #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spin_lock_init(&dev->msi_lock); INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index c38317979f74..19f5d5a8b16a 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -818,6 +818,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); + /* don't abort one completed request */ + if (blk_mq_request_completed(req)) + return true; + mutex_lock(&cmd->lock); cmd->status = BLK_STS_IOERR; mutex_unlock(&cmd->lock); @@ -2004,15 +2008,19 @@ static void nbd_disconnect_and_put(struct nbd_device *nbd) { mutex_lock(&nbd->config_lock); nbd_disconnect(nbd); - nbd_clear_sock(nbd); - mutex_unlock(&nbd->config_lock); + sock_shutdown(nbd); /* * Make sure recv thread has finished, so it does not drop the last * config ref and try to destroy the workqueue from inside the work - * queue. + * queue. And this also ensure that we can safely call nbd_clear_que() + * to cancel the inflight I/Os. */ if (nbd->recv_workq) flush_workqueue(nbd->recv_workq); + nbd_clear_que(nbd); + nbd->task_setup = NULL; + mutex_unlock(&nbd->config_lock); + if (test_and_clear_bit(NBD_RT_HAS_CONFIG_REF, &nbd->config->runtime_flags)) nbd_config_put(nbd); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 4b49df2dfd23..afb37aac09e8 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -692,6 +692,28 @@ static const struct blk_mq_ops virtio_mq_ops = { static unsigned int virtblk_queue_depth; module_param_named(queue_depth, virtblk_queue_depth, uint, 0444); +static int virtblk_validate(struct virtio_device *vdev) +{ + u32 blk_size; + + if (!vdev->config->get) { + dev_err(&vdev->dev, "%s failure: config access disabled\n", + __func__); + return -EINVAL; + } + + if (!virtio_has_feature(vdev, VIRTIO_BLK_F_BLK_SIZE)) + return 0; + + blk_size = virtio_cread32(vdev, + offsetof(struct virtio_blk_config, blk_size)); + + if (blk_size < SECTOR_SIZE || blk_size > PAGE_SIZE) + __virtio_clear_bit(vdev, VIRTIO_BLK_F_BLK_SIZE); + + return 0; +} + static int virtblk_probe(struct virtio_device *vdev) { struct virtio_blk *vblk; @@ -703,12 +725,6 @@ static int virtblk_probe(struct virtio_device *vdev) u8 physical_block_exp, alignment_offset; unsigned int queue_depth; - if (!vdev->config->get) { - dev_err(&vdev->dev, "%s failure: config access disabled\n", - __func__); - return -EINVAL; - } - err = ida_simple_get(&vd_index_ida, 0, minor_to_index(1 << MINORBITS), GFP_KERNEL); if (err < 0) @@ -823,6 +839,14 @@ static int virtblk_probe(struct virtio_device *vdev) else blk_size = queue_logical_block_size(q); + if (unlikely(blk_size < SECTOR_SIZE || blk_size > PAGE_SIZE)) { + dev_err(&vdev->dev, + "block size is changed unexpectedly, now is %u\n", + blk_size); + err = -EINVAL; + goto err_cleanup_disk; + } + /* Use topology information if available */ err = virtio_cread_feature(vdev, VIRTIO_BLK_F_TOPOLOGY, struct virtio_blk_config, physical_block_exp, @@ -881,6 +905,8 @@ static int virtblk_probe(struct virtio_device *vdev) device_add_disk(&vdev->dev, vblk->disk, virtblk_attr_groups); return 0; +err_cleanup_disk: + blk_cleanup_disk(vblk->disk); out_free_tags: blk_mq_free_tag_set(&vblk->tag_set); out_free_vq: @@ -983,6 +1009,7 @@ static struct virtio_driver virtio_blk = { .driver.name = KBUILD_MODNAME, .driver.owner = THIS_MODULE, .id_table = id_table, + .validate = virtblk_validate, .probe = virtblk_probe, .remove = virtblk_remove, .config_changed = virtblk_config_changed, diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 5fa6ae9dbc8b..44736cbd446e 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -313,7 +313,7 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, return -ENXIO; if (nr_pages < 0) - return nr_pages; + return -EINVAL; avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 7bf0a7acae5e..2363fee9211c 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -35,15 +35,48 @@ efi_status_t check_platform_features(void) } /* - * Although relocatable kernels can fix up the misalignment with respect to - * MIN_KIMG_ALIGN, the resulting virtual text addresses are subtly out of - * sync with those recorded in the vmlinux when kaslr is disabled but the - * image required relocation anyway. Therefore retain 2M alignment unless - * KASLR is in use. + * Distro versions of GRUB may ignore the BSS allocation entirely (i.e., fail + * to provide space, and fail to zero it). Check for this condition by double + * checking that the first and the last byte of the image are covered by the + * same EFI memory map entry. */ -static u64 min_kimg_align(void) +static bool check_image_region(u64 base, u64 size) { - return efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; + unsigned long map_size, desc_size, buff_size; + efi_memory_desc_t *memory_map; + struct efi_boot_memmap map; + efi_status_t status; + bool ret = false; + int map_offset; + + map.map = &memory_map; + map.map_size = &map_size; + map.desc_size = &desc_size; + map.desc_ver = NULL; + map.key_ptr = NULL; + map.buff_size = &buff_size; + + status = efi_get_memory_map(&map); + if (status != EFI_SUCCESS) + return false; + + for (map_offset = 0; map_offset < map_size; map_offset += desc_size) { + efi_memory_desc_t *md = (void *)memory_map + map_offset; + u64 end = md->phys_addr + md->num_pages * EFI_PAGE_SIZE; + + /* + * Find the region that covers base, and return whether + * it covers base+size bytes. + */ + if (base >= md->phys_addr && base < end) { + ret = (base + size) <= end; + break; + } + } + + efi_bs_call(free_pool, memory_map); + + return ret; } efi_status_t handle_kernel_image(unsigned long *image_addr, @@ -56,6 +89,16 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, unsigned long kernel_size, kernel_memsize = 0; u32 phys_seed = 0; + /* + * Although relocatable kernels can fix up the misalignment with + * respect to MIN_KIMG_ALIGN, the resulting virtual text addresses are + * subtly out of sync with those recorded in the vmlinux when kaslr is + * disabled but the image required relocation anyway. Therefore retain + * 2M alignment if KASLR was explicitly disabled, even if it was not + * going to be activated to begin with. + */ + u64 min_kimg_align = efi_nokaslr ? MIN_KIMG_ALIGN : EFI_KIMG_ALIGN; + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { if (!efi_nokaslr) { status = efi_get_random_bytes(sizeof(phys_seed), @@ -76,6 +119,10 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, if (image->image_base != _text) efi_err("FIRMWARE BUG: efi_loaded_image_t::image_base has bogus value\n"); + if (!IS_ALIGNED((u64)_text, EFI_KIMG_ALIGN)) + efi_err("FIRMWARE BUG: kernel image not aligned on %ldk boundary\n", + EFI_KIMG_ALIGN >> 10); + kernel_size = _edata - _text; kernel_memsize = kernel_size + (_end - _edata); *reserve_size = kernel_memsize; @@ -85,14 +132,18 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, * If KASLR is enabled, and we have some randomness available, * locate the kernel at a randomized offset in physical memory. */ - status = efi_random_alloc(*reserve_size, min_kimg_align(), + status = efi_random_alloc(*reserve_size, min_kimg_align, reserve_addr, phys_seed); + if (status != EFI_SUCCESS) + efi_warn("efi_random_alloc() failed: 0x%lx\n", status); } else { status = EFI_OUT_OF_RESOURCES; } if (status != EFI_SUCCESS) { - if (IS_ALIGNED((u64)_text, min_kimg_align())) { + if (!check_image_region((u64)_text, kernel_memsize)) { + efi_err("FIRMWARE BUG: Image BSS overlaps adjacent EFI memory region\n"); + } else if (IS_ALIGNED((u64)_text, min_kimg_align)) { /* * Just execute from wherever we were loaded by the * UEFI PE/COFF loader if the alignment is suitable. @@ -103,7 +154,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, } status = efi_allocate_pages_aligned(*reserve_size, reserve_addr, - ULONG_MAX, min_kimg_align()); + ULONG_MAX, min_kimg_align); if (status != EFI_SUCCESS) { efi_err("Failed to relocate kernel\n"); diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c index a408df474d83..724155b9e10d 100644 --- a/drivers/firmware/efi/libstub/randomalloc.c +++ b/drivers/firmware/efi/libstub/randomalloc.c @@ -30,6 +30,8 @@ static unsigned long get_entry_num_slots(efi_memory_desc_t *md, region_end = min(md->phys_addr + md->num_pages * EFI_PAGE_SIZE - 1, (u64)ULONG_MAX); + if (region_end < size) + return 0; first_slot = round_up(md->phys_addr, align); last_slot = round_down(region_end - size + 1, align); diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index cceaf69279a9..6304d1dd2dd6 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -1224,14 +1224,14 @@ static int bcm_iproc_i2c_unreg_slave(struct i2c_client *slave) disable_irq(iproc_i2c->irq); + tasklet_kill(&iproc_i2c->slave_rx_tasklet); + /* disable all slave interrupts */ tmp = iproc_i2c_rd_reg(iproc_i2c, IE_OFFSET); tmp &= ~(IE_S_ALL_INTERRUPT_MASK << IE_S_ALL_INTERRUPT_SHIFT); iproc_i2c_wr_reg(iproc_i2c, IE_OFFSET, tmp); - tasklet_kill(&iproc_i2c->slave_rx_tasklet); - /* Erase the slave address programmed */ tmp = iproc_i2c_rd_reg(iproc_i2c, S_CFG_SMBUS_ADDR_OFFSET); tmp &= ~BIT(S_CFG_EN_NIC_SMB_ADDR3_SHIFT); diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index cb64fe649390..77f576e51652 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -141,7 +141,7 @@ static ssize_t i2cdev_read(struct file *file, char __user *buf, size_t count, if (count > 8192) count = 8192; - tmp = kmalloc(count, GFP_KERNEL); + tmp = kzalloc(count, GFP_KERNEL); if (tmp == NULL) return -ENOMEM; @@ -150,7 +150,8 @@ static ssize_t i2cdev_read(struct file *file, char __user *buf, size_t count, ret = i2c_master_recv(client, tmp, count); if (ret >= 0) - ret = copy_to_user(buf, tmp, count) ? -EFAULT : ret; + if (copy_to_user(buf, tmp, ret)) + ret = -EFAULT; kfree(tmp); return ret; } diff --git a/drivers/iio/accel/Kconfig b/drivers/iio/accel/Kconfig index 0e56ace61103..8d8b1ba42ff8 100644 --- a/drivers/iio/accel/Kconfig +++ b/drivers/iio/accel/Kconfig @@ -231,6 +231,7 @@ config DMARD10 config FXLS8962AF tristate + depends on I2C || !I2C # cannot be built-in for modular I2C config FXLS8962AF_I2C tristate "NXP FXLS8962AF/FXLS8964AF Accelerometer I2C Driver" @@ -247,6 +248,7 @@ config FXLS8962AF_I2C config FXLS8962AF_SPI tristate "NXP FXLS8962AF/FXLS8964AF Accelerometer SPI Driver" depends on SPI + depends on I2C || !I2C select FXLS8962AF select REGMAP_SPI help diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 078d87865fde..0019f1ea7df2 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -637,7 +637,7 @@ static int fxls8962af_i2c_raw_read_errata3(struct fxls8962af_data *data, return ret; } - return ret; + return 0; } static int fxls8962af_fifo_transfer(struct fxls8962af_data *data, diff --git a/drivers/iio/adc/palmas_gpadc.c b/drivers/iio/adc/palmas_gpadc.c index 6ef09609be9f..f9c8385c72d3 100644 --- a/drivers/iio/adc/palmas_gpadc.c +++ b/drivers/iio/adc/palmas_gpadc.c @@ -664,8 +664,8 @@ static int palmas_adc_wakeup_configure(struct palmas_gpadc *adc) adc_period = adc->auto_conversion_period; for (i = 0; i < 16; ++i) { - if (((1000 * (1 << i)) / 32) < adc_period) - continue; + if (((1000 * (1 << i)) / 32) >= adc_period) + break; } if (i > 0) i--; diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c index 2383eacada87..a2b83f0bd526 100644 --- a/drivers/iio/adc/ti-ads7950.c +++ b/drivers/iio/adc/ti-ads7950.c @@ -568,7 +568,6 @@ static int ti_ads7950_probe(struct spi_device *spi) st->ring_xfer.tx_buf = &st->tx_buf[0]; st->ring_xfer.rx_buf = &st->rx_buf[0]; /* len will be set later */ - st->ring_xfer.cs_change = true; spi_message_add_tail(&st->ring_xfer, &st->ring_msg); diff --git a/drivers/iio/humidity/hdc100x.c b/drivers/iio/humidity/hdc100x.c index 2a957f19048e..9e0fce917ce4 100644 --- a/drivers/iio/humidity/hdc100x.c +++ b/drivers/iio/humidity/hdc100x.c @@ -25,6 +25,8 @@ #include <linux/iio/trigger_consumer.h> #include <linux/iio/triggered_buffer.h> +#include <linux/time.h> + #define HDC100X_REG_TEMP 0x00 #define HDC100X_REG_HUMIDITY 0x01 @@ -166,7 +168,7 @@ static int hdc100x_get_measurement(struct hdc100x_data *data, struct iio_chan_spec const *chan) { struct i2c_client *client = data->client; - int delay = data->adc_int_us[chan->address]; + int delay = data->adc_int_us[chan->address] + 1*USEC_PER_MSEC; int ret; __be16 val; @@ -316,7 +318,7 @@ static irqreturn_t hdc100x_trigger_handler(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct hdc100x_data *data = iio_priv(indio_dev); struct i2c_client *client = data->client; - int delay = data->adc_int_us[0] + data->adc_int_us[1]; + int delay = data->adc_int_us[0] + data->adc_int_us[1] + 2*USEC_PER_MSEC; int ret; /* dual read starts at temp register */ diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index a5b421f42287..b9a06ca29bee 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -411,12 +411,11 @@ int __adis_initial_startup(struct adis *adis) int ret; /* check if the device has rst pin low */ - gpio = devm_gpiod_get_optional(&adis->spi->dev, "reset", GPIOD_ASIS); + gpio = devm_gpiod_get_optional(&adis->spi->dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(gpio)) return PTR_ERR(gpio); if (gpio) { - gpiod_set_value_cansleep(gpio, 1); msleep(10); /* bring device out of reset */ gpiod_set_value_cansleep(gpio, 0); diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c index 3097e93787f7..a761134fd3be 100644 --- a/drivers/mtd/chips/cfi_cmdset_0002.c +++ b/drivers/mtd/chips/cfi_cmdset_0002.c @@ -119,7 +119,7 @@ static int cfi_use_status_reg(struct cfi_private *cfi) struct cfi_pri_amdstd *extp = cfi->cmdset_priv; u8 poll_mask = CFI_POLL_STATUS_REG | CFI_POLL_DQ; - return extp->MinorVersion >= '5' && + return extp && extp->MinorVersion >= '5' && (extp->SoftwareFeatures & poll_mask) == CFI_POLL_STATUS_REG; } diff --git a/drivers/mtd/devices/mchp48l640.c b/drivers/mtd/devices/mchp48l640.c index efc2003bd13a..99400d0fb8c1 100644 --- a/drivers/mtd/devices/mchp48l640.c +++ b/drivers/mtd/devices/mchp48l640.c @@ -229,7 +229,7 @@ static int mchp48l640_write(struct mtd_info *mtd, loff_t to, size_t len, woff += ws; } - return ret; + return 0; } static int mchp48l640_read_page(struct mtd_info *mtd, loff_t from, size_t len, @@ -255,6 +255,7 @@ static int mchp48l640_read_page(struct mtd_info *mtd, loff_t from, size_t len, if (!ret) *retlen += len; + kfree(cmd); return ret; fail: @@ -286,7 +287,7 @@ static int mchp48l640_read(struct mtd_info *mtd, loff_t from, size_t len, woff += ws; } - return ret; + return 0; }; static const struct mchp48_caps mchp48l640_caps = { diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 6ce4bc57f919..44bea3f65060 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -419,6 +419,7 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) if (tr->discard) { blk_queue_flag_set(QUEUE_FLAG_DISCARD, new->rq); blk_queue_max_discard_sectors(new->rq, UINT_MAX); + new->rq->limits.discard_granularity = tr->blksize; } gd->queue = new->rq; @@ -525,14 +526,10 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) if (!blktrans_notifier.list.next) register_mtd_user(&blktrans_notifier); - - mutex_lock(&mtd_table_mutex); - ret = register_blkdev(tr->major, tr->name); if (ret < 0) { printk(KERN_WARNING "Unable to register %s block device on major %d: %d\n", tr->name, tr->major, ret); - mutex_unlock(&mtd_table_mutex); return ret; } @@ -542,12 +539,12 @@ int register_mtd_blktrans(struct mtd_blktrans_ops *tr) tr->blkshift = ffs(tr->blksize) - 1; INIT_LIST_HEAD(&tr->devs); - list_add(&tr->list, &blktrans_majors); + mutex_lock(&mtd_table_mutex); + list_add(&tr->list, &blktrans_majors); mtd_for_each_device(mtd) if (mtd->type != MTD_ABSENT) tr->add_mtd(tr, mtd); - mutex_unlock(&mtd_table_mutex); return 0; } @@ -564,8 +561,8 @@ int deregister_mtd_blktrans(struct mtd_blktrans_ops *tr) list_for_each_entry_safe(dev, next, &tr->devs, list) tr->remove_dev(dev); - unregister_blkdev(tr->major, tr->name); mutex_unlock(&mtd_table_mutex); + unregister_blkdev(tr->major, tr->name); BUG_ON(!list_empty(&tr->devs)); return 0; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index b5ccd3037788..c8fd7f758938 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -806,7 +806,9 @@ static ssize_t mtd_otp_size(struct mtd_info *mtd, bool is_user) err: kfree(info); - return ret; + + /* ENODATA means there is no OTP region. */ + return ret == -ENODATA ? 0 : ret; } static struct nvmem_device *mtd_otp_nvmem_register(struct mtd_info *mtd, diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 57a583149cc0..3d6c6e880520 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5228,12 +5228,18 @@ static bool of_get_nand_on_flash_bbt(struct device_node *np) static int of_get_nand_secure_regions(struct nand_chip *chip) { struct device_node *dn = nand_get_flash_node(chip); + struct property *prop; int nr_elem, i, j; - nr_elem = of_property_count_elems_of_size(dn, "secure-regions", sizeof(u64)); - if (!nr_elem) + /* Only proceed if the "secure-regions" property is present in DT */ + prop = of_find_property(dn, "secure-regions", NULL); + if (!prop) return 0; + nr_elem = of_property_count_elems_of_size(dn, "secure-regions", sizeof(u64)); + if (nr_elem <= 0) + return nr_elem; + chip->nr_secure_regions = nr_elem / 2; chip->secure_regions = kcalloc(chip->nr_secure_regions, sizeof(*chip->secure_regions), GFP_KERNEL); diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 2403b71b601e..745478213ff2 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -2527,7 +2527,7 @@ static void deactivate_labels(void *region) static int init_active_labels(struct nd_region *nd_region) { - int i; + int i, rc = 0; for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; @@ -2546,13 +2546,14 @@ static int init_active_labels(struct nd_region *nd_region) else if (test_bit(NDD_LABELING, &nvdimm->flags)) /* fail, labels needed to disambiguate dpa */; else - return 0; + continue; dev_err(&nd_region->dev, "%s: is %s, failing probe\n", dev_name(&nd_mapping->nvdimm->dev), test_bit(NDD_LOCKED, &nvdimm->flags) ? "locked" : "disabled"); - return -ENXIO; + rc = -ENXIO; + goto out; } nd_mapping->ndd = ndd; atomic_inc(&nvdimm->busy); @@ -2586,13 +2587,17 @@ static int init_active_labels(struct nd_region *nd_region) break; } - if (i < nd_region->ndr_mappings) { + if (i < nd_region->ndr_mappings) + rc = -ENOMEM; + +out: + if (rc) { deactivate_labels(nd_region); - return -ENOMEM; + return rc; } return devm_add_action_or_reset(&nd_region->dev, deactivate_labels, - nd_region); + nd_region); } int nd_region_register_namespaces(struct nd_region *nd_region, int *err) diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 9232255c8515..e5e75331b415 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -143,24 +143,25 @@ static inline __attribute_const__ u32 msi_mask(unsigned x) * reliably as devices without an INTx disable bit will then generate a * level IRQ which will never be cleared. */ -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - u32 mask_bits = desc->masked; + raw_spinlock_t *lock = &desc->dev->msi_lock; + unsigned long flags; if (pci_msi_ignore_mask || !desc->msi_attrib.maskbit) - return 0; + return; - mask_bits &= ~mask; - mask_bits |= flag; + raw_spin_lock_irqsave(lock, flags); + desc->masked &= ~mask; + desc->masked |= flag; pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos, - mask_bits); - - return mask_bits; + desc->masked); + raw_spin_unlock_irqrestore(lock, flags); } static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) { - desc->masked = __pci_msi_desc_mask_irq(desc, mask, flag); + __pci_msi_desc_mask_irq(desc, mask, flag); } static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) @@ -289,13 +290,31 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) /* Don't touch the hardware now */ } else if (entry->msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); + bool unmasked = !(entry->masked & PCI_MSIX_ENTRY_CTRL_MASKBIT); if (!base) goto skip; + /* + * The specification mandates that the entry is masked + * when the message is modified: + * + * "If software changes the Address or Data value of an + * entry while the entry is unmasked, the result is + * undefined." + */ + if (unmasked) + __pci_msix_desc_mask_irq(entry, PCI_MSIX_ENTRY_CTRL_MASKBIT); + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); writel(msg->data, base + PCI_MSIX_ENTRY_DATA); + + if (unmasked) + __pci_msix_desc_mask_irq(entry, 0); + + /* Ensure that the writes are visible in the device */ + readl(base + PCI_MSIX_ENTRY_DATA); } else { int pos = dev->msi_cap; u16 msgctl; @@ -316,6 +335,8 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) pci_write_config_word(dev, pos + PCI_MSI_DATA_32, msg->data); } + /* Ensure that the writes are visible in the device */ + pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); } skip: @@ -636,21 +657,21 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, /* Configure MSI capability structure */ ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } ret = msi_verify_entries(dev); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } ret = populate_msi_sysfs(dev); if (ret) { - msi_mask_irq(entry, mask, ~mask); + msi_mask_irq(entry, mask, 0); free_msi_irqs(dev); return ret; } @@ -691,6 +712,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, { struct irq_affinity_desc *curmsk, *masks = NULL; struct msi_desc *entry; + void __iomem *addr; int ret, i; int vec_count = pci_msix_vec_count(dev); @@ -711,6 +733,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.is_msix = 1; entry->msi_attrib.is_64 = 1; + if (entries) entry->msi_attrib.entry_nr = entries[i].entry; else @@ -722,6 +745,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.default_irq = dev->irq; entry->mask_base = base; + addr = pci_msix_desc_addr(entry); + if (addr) + entry->masked = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + list_add_tail(&entry->list, dev_to_msi_list(&dev->dev)); if (masks) curmsk++; @@ -732,26 +759,25 @@ out: return ret; } -static void msix_program_entries(struct pci_dev *dev, - struct msix_entry *entries) +static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries) { struct msi_desc *entry; - int i = 0; - void __iomem *desc_addr; for_each_pci_msi_entry(entry, dev) { - if (entries) - entries[i++].vector = entry->irq; + if (entries) { + entries->vector = entry->irq; + entries++; + } + } +} - desc_addr = pci_msix_desc_addr(entry); - if (desc_addr) - entry->masked = readl(desc_addr + - PCI_MSIX_ENTRY_VECTOR_CTRL); - else - entry->masked = 0; +static void msix_mask_all(void __iomem *base, int tsize) +{ + u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT; + int i; - msix_mask_irq(entry, 1); - } + for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE) + writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); } /** @@ -768,22 +794,33 @@ static void msix_program_entries(struct pci_dev *dev, static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd) { - int ret; - u16 control; void __iomem *base; + int ret, tsize; + u16 control; - /* Ensure MSI-X is disabled while it is set up */ - pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + /* + * Some devices require MSI-X to be enabled before the MSI-X + * registers can be accessed. Mask all the vectors to prevent + * interrupts coming in before they're fully set up. + */ + pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_MASKALL | + PCI_MSIX_FLAGS_ENABLE); pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control); /* Request & Map MSI-X table region */ - base = msix_map_region(dev, msix_table_size(control)); - if (!base) - return -ENOMEM; + tsize = msix_table_size(control); + base = msix_map_region(dev, tsize); + if (!base) { + ret = -ENOMEM; + goto out_disable; + } + + /* Ensure that all table entries are masked. */ + msix_mask_all(base, tsize); ret = msix_setup_entries(dev, base, entries, nvec, affd); if (ret) - return ret; + goto out_disable; ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); if (ret) @@ -794,15 +831,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, if (ret) goto out_free; - /* - * Some devices require MSI-X to be enabled before we can touch the - * MSI-X registers. We need to mask all the vectors to prevent - * interrupts coming in before they're fully set up. - */ - pci_msix_clear_and_set_ctrl(dev, 0, - PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE); - - msix_program_entries(dev, entries); + msix_update_entries(dev, entries); ret = populate_msi_sysfs(dev); if (ret) @@ -836,6 +865,9 @@ out_avail: out_free: free_msi_irqs(dev); +out_disable: + pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); + return ret; } @@ -930,8 +962,7 @@ static void pci_msi_shutdown(struct pci_dev *dev) /* Return the device with MSI unmasked as initial states */ mask = msi_mask(desc->msi_attrib.multi_cap); - /* Keep cached state to be restored */ - __pci_msi_desc_mask_irq(desc, mask, ~mask); + msi_mask_irq(desc, mask, 0); /* Restore dev->irq to its default pin-assertion IRQ */ dev->irq = desc->msi_attrib.default_irq; @@ -1016,10 +1047,8 @@ static void pci_msix_shutdown(struct pci_dev *dev) } /* Return the device with MSI-X masked as initial states */ - for_each_pci_msi_entry(entry, dev) { - /* Keep cached states to be restored */ + for_each_pci_msi_entry(entry, dev) __pci_msix_desc_mask_irq(entry, 1); - } pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0); pci_intx_for_msi(dev, 1); diff --git a/drivers/pinctrl/intel/pinctrl-tigerlake.c b/drivers/pinctrl/intel/pinctrl-tigerlake.c index 3e4ef2b87526..0bcd19597e4a 100644 --- a/drivers/pinctrl/intel/pinctrl-tigerlake.c +++ b/drivers/pinctrl/intel/pinctrl-tigerlake.c @@ -701,32 +701,32 @@ static const struct pinctrl_pin_desc tglh_pins[] = { static const struct intel_padgroup tglh_community0_gpps[] = { TGL_GPP(0, 0, 24, 0), /* GPP_A */ - TGL_GPP(1, 25, 44, 128), /* GPP_R */ - TGL_GPP(2, 45, 70, 32), /* GPP_B */ - TGL_GPP(3, 71, 78, INTEL_GPIO_BASE_NOMAP), /* vGPIO_0 */ + TGL_GPP(1, 25, 44, 32), /* GPP_R */ + TGL_GPP(2, 45, 70, 64), /* GPP_B */ + TGL_GPP(3, 71, 78, 96), /* vGPIO_0 */ }; static const struct intel_padgroup tglh_community1_gpps[] = { - TGL_GPP(0, 79, 104, 96), /* GPP_D */ - TGL_GPP(1, 105, 128, 64), /* GPP_C */ - TGL_GPP(2, 129, 136, 160), /* GPP_S */ - TGL_GPP(3, 137, 153, 192), /* GPP_G */ - TGL_GPP(4, 154, 180, 224), /* vGPIO */ + TGL_GPP(0, 79, 104, 128), /* GPP_D */ + TGL_GPP(1, 105, 128, 160), /* GPP_C */ + TGL_GPP(2, 129, 136, 192), /* GPP_S */ + TGL_GPP(3, 137, 153, 224), /* GPP_G */ + TGL_GPP(4, 154, 180, 256), /* vGPIO */ }; static const struct intel_padgroup tglh_community3_gpps[] = { - TGL_GPP(0, 181, 193, 256), /* GPP_E */ - TGL_GPP(1, 194, 217, 288), /* GPP_F */ + TGL_GPP(0, 181, 193, 288), /* GPP_E */ + TGL_GPP(1, 194, 217, 320), /* GPP_F */ }; static const struct intel_padgroup tglh_community4_gpps[] = { - TGL_GPP(0, 218, 241, 320), /* GPP_H */ + TGL_GPP(0, 218, 241, 352), /* GPP_H */ TGL_GPP(1, 242, 251, 384), /* GPP_J */ - TGL_GPP(2, 252, 266, 352), /* GPP_K */ + TGL_GPP(2, 252, 266, 416), /* GPP_K */ }; static const struct intel_padgroup tglh_community5_gpps[] = { - TGL_GPP(0, 267, 281, 416), /* GPP_I */ + TGL_GPP(0, 267, 281, 448), /* GPP_I */ TGL_GPP(1, 282, 290, INTEL_GPIO_BASE_NOMAP), /* JTAG */ }; diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index 5b3b048725cc..45ebdeba985a 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -925,12 +925,10 @@ int mtk_pinconf_adv_pull_set(struct mtk_pinctrl *hw, err = hw->soc->bias_set(hw, desc, pullup); if (err) return err; - } else if (hw->soc->bias_set_combo) { - err = hw->soc->bias_set_combo(hw, desc, pullup, arg); - if (err) - return err; } else { - return -ENOTSUPP; + err = mtk_pinconf_bias_set_rev1(hw, desc, pullup); + if (err) + err = mtk_pinconf_bias_set(hw, desc, pullup); } } diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index a76be6cc26ee..5b764740b829 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -444,8 +444,7 @@ static int amd_gpio_irq_set_wake(struct irq_data *d, unsigned int on) unsigned long flags; struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct amd_gpio *gpio_dev = gpiochip_get_data(gc); - u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) | - BIT(WAKE_CNTRL_OFF_S4); + u32 wake_mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3); raw_spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c index f831526d06ff..49e32684dbb2 100644 --- a/drivers/pinctrl/pinctrl-k210.c +++ b/drivers/pinctrl/pinctrl-k210.c @@ -950,23 +950,37 @@ static int k210_fpioa_probe(struct platform_device *pdev) return ret; pdata->pclk = devm_clk_get_optional(dev, "pclk"); - if (!IS_ERR(pdata->pclk)) - clk_prepare_enable(pdata->pclk); + if (!IS_ERR(pdata->pclk)) { + ret = clk_prepare_enable(pdata->pclk); + if (ret) + goto disable_clk; + } pdata->sysctl_map = syscon_regmap_lookup_by_phandle_args(np, "canaan,k210-sysctl-power", 1, &pdata->power_offset); - if (IS_ERR(pdata->sysctl_map)) - return PTR_ERR(pdata->sysctl_map); + if (IS_ERR(pdata->sysctl_map)) { + ret = PTR_ERR(pdata->sysctl_map); + goto disable_pclk; + } k210_fpioa_init_ties(pdata); pdata->pctl = pinctrl_register(&k210_pinctrl_desc, dev, (void *)pdata); - if (IS_ERR(pdata->pctl)) - return PTR_ERR(pdata->pctl); + if (IS_ERR(pdata->pctl)) { + ret = PTR_ERR(pdata->pctl); + goto disable_pclk; + } return 0; + +disable_pclk: + clk_disable_unprepare(pdata->pclk); +disable_clk: + clk_disable_unprepare(pdata->clk); + + return ret; } static const struct of_device_id k210_fpioa_dt_ids[] = { diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index 2f51b4f99393..cad4e60df618 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -13,7 +13,7 @@ config PINCTRL_MSM config PINCTRL_APQ8064 tristate "Qualcomm APQ8064 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -21,7 +21,7 @@ config PINCTRL_APQ8064 config PINCTRL_APQ8084 tristate "Qualcomm APQ8084 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -29,7 +29,7 @@ config PINCTRL_APQ8084 config PINCTRL_IPQ4019 tristate "Qualcomm IPQ4019 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -37,7 +37,7 @@ config PINCTRL_IPQ4019 config PINCTRL_IPQ8064 tristate "Qualcomm IPQ8064 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -45,7 +45,7 @@ config PINCTRL_IPQ8064 config PINCTRL_IPQ8074 tristate "Qualcomm Technologies, Inc. IPQ8074 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for @@ -55,7 +55,7 @@ config PINCTRL_IPQ8074 config PINCTRL_IPQ6018 tristate "Qualcomm Technologies, Inc. IPQ6018 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for @@ -65,7 +65,7 @@ config PINCTRL_IPQ6018 config PINCTRL_MSM8226 tristate "Qualcomm 8226 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -74,7 +74,7 @@ config PINCTRL_MSM8226 config PINCTRL_MSM8660 tristate "Qualcomm 8660 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -82,7 +82,7 @@ config PINCTRL_MSM8660 config PINCTRL_MSM8960 tristate "Qualcomm 8960 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -90,7 +90,7 @@ config PINCTRL_MSM8960 config PINCTRL_MDM9615 tristate "Qualcomm 9615 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -98,7 +98,7 @@ config PINCTRL_MDM9615 config PINCTRL_MSM8X74 tristate "Qualcomm 8x74 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -106,7 +106,7 @@ config PINCTRL_MSM8X74 config PINCTRL_MSM8916 tristate "Qualcomm 8916 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -114,7 +114,7 @@ config PINCTRL_MSM8916 config PINCTRL_MSM8953 tristate "Qualcomm 8953 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -124,7 +124,7 @@ config PINCTRL_MSM8953 config PINCTRL_MSM8976 tristate "Qualcomm 8976 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -134,7 +134,7 @@ config PINCTRL_MSM8976 config PINCTRL_MSM8994 tristate "Qualcomm 8994 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -143,7 +143,7 @@ config PINCTRL_MSM8994 config PINCTRL_MSM8996 tristate "Qualcomm MSM8996 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -151,7 +151,7 @@ config PINCTRL_MSM8996 config PINCTRL_MSM8998 tristate "Qualcomm MSM8998 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -159,7 +159,7 @@ config PINCTRL_MSM8998 config PINCTRL_QCS404 tristate "Qualcomm QCS404 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -167,7 +167,7 @@ config PINCTRL_QCS404 config PINCTRL_QDF2XXX tristate "Qualcomm Technologies QDF2xxx pin controller driver" - depends on GPIOLIB && ACPI + depends on ACPI depends on PINCTRL_MSM help This is the GPIO driver for the TLMM block found on the @@ -175,7 +175,7 @@ config PINCTRL_QDF2XXX config PINCTRL_QCOM_SPMI_PMIC tristate "Qualcomm SPMI PMIC pin controller driver" - depends on GPIOLIB && OF && SPMI + depends on OF && SPMI select REGMAP_SPMI select PINMUX select PINCONF @@ -190,7 +190,7 @@ config PINCTRL_QCOM_SPMI_PMIC config PINCTRL_QCOM_SSBI_PMIC tristate "Qualcomm SSBI PMIC pin controller driver" - depends on GPIOLIB && OF + depends on OF select PINMUX select PINCONF select GENERIC_PINCONF @@ -204,7 +204,7 @@ config PINCTRL_QCOM_SSBI_PMIC config PINCTRL_SC7180 tristate "Qualcomm Technologies Inc SC7180 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -213,7 +213,7 @@ config PINCTRL_SC7180 config PINCTRL_SC7280 tristate "Qualcomm Technologies Inc SC7280 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -222,7 +222,7 @@ config PINCTRL_SC7280 config PINCTRL_SC8180X tristate "Qualcomm Technologies Inc SC8180x pin controller driver" - depends on GPIOLIB && (OF || ACPI) + depends on (OF || ACPI) depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -231,7 +231,7 @@ config PINCTRL_SC8180X config PINCTRL_SDM660 tristate "Qualcomm Technologies Inc SDM660 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -240,7 +240,7 @@ config PINCTRL_SDM660 config PINCTRL_SDM845 tristate "Qualcomm Technologies Inc SDM845 pin controller driver" - depends on GPIOLIB && (OF || ACPI) + depends on (OF || ACPI) depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -249,7 +249,7 @@ config PINCTRL_SDM845 config PINCTRL_SDX55 tristate "Qualcomm Technologies Inc SDX55 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -258,7 +258,7 @@ config PINCTRL_SDX55 config PINCTRL_SM6125 tristate "Qualcomm Technologies Inc SM6125 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -267,7 +267,7 @@ config PINCTRL_SM6125 config PINCTRL_SM8150 tristate "Qualcomm Technologies Inc SM8150 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -276,7 +276,7 @@ config PINCTRL_SM8150 config PINCTRL_SM8250 tristate "Qualcomm Technologies Inc SM8250 pin controller driver" - depends on GPIOLIB && OF + depends on OF depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the @@ -285,8 +285,7 @@ config PINCTRL_SM8250 config PINCTRL_SM8350 tristate "Qualcomm Technologies Inc SM8350 pin controller driver" - depends on GPIOLIB && OF - select PINCTRL_MSM + depends on PINCTRL_MSM help This is the pinctrl, pinmux, pinconf and gpiolib driver for the Qualcomm Technologies Inc TLMM block found on the Qualcomm diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index dc8d39ae045b..9c7679c06dca 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -1219,10 +1219,12 @@ static int sunxi_pinctrl_build_state(struct platform_device *pdev) } /* - * We suppose that we won't have any more functions than pins, - * we'll reallocate that later anyway + * Find an upper bound for the maximum number of functions: in + * the worst case we have gpio_in, gpio_out, irq and up to four + * special functions per pin, plus one entry for the sentinel. + * We'll reallocate that later anyway. */ - pctl->functions = kcalloc(pctl->ngroups, + pctl->functions = kcalloc(4 * pctl->ngroups + 4, sizeof(*pctl->functions), GFP_KERNEL); if (!pctl->functions) diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 0cb927f0f301..a81dc4b191b7 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -41,6 +41,10 @@ static int wapf = -1; module_param(wapf, uint, 0444); MODULE_PARM_DESC(wapf, "WAPF value"); +static int tablet_mode_sw = -1; +module_param(tablet_mode_sw, uint, 0444); +MODULE_PARM_DESC(tablet_mode_sw, "Tablet mode detect: -1:auto 0:disable 1:kbd-dock 2:lid-flip"); + static struct quirk_entry *quirks; static bool asus_q500a_i8042_filter(unsigned char data, unsigned char str, @@ -458,6 +462,15 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_use_lid_flip_devid, }, + { + .callback = dmi_matched, + .ident = "ASUS TP200s / E205SA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "E205SA"), + }, + .driver_data = &quirk_asus_use_lid_flip_devid, + }, {}, }; @@ -477,6 +490,21 @@ static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver) else wapf = quirks->wapf; + switch (tablet_mode_sw) { + case 0: + quirks->use_kbd_dock_devid = false; + quirks->use_lid_flip_devid = false; + break; + case 1: + quirks->use_kbd_dock_devid = true; + quirks->use_lid_flip_devid = false; + break; + case 2: + quirks->use_kbd_dock_devid = false; + quirks->use_lid_flip_devid = true; + break; + } + if (quirks->i8042_filter) { ret = i8042_install_filter(quirks->i8042_filter); if (ret) { diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index fbb224a82e34..7f3a03f937f6 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -140,6 +140,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) }} static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"), @@ -147,6 +148,7 @@ static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("Z390 I AORUS PRO WIFI-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 AORUS ELITE"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 GAMING X"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 I AORUS PRO WIFI"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("X570 UD"), { } diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 5983e05b648f..e29523a1b530 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -13193,6 +13193,8 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) if (!phba) return -ENOMEM; + INIT_LIST_HEAD(&phba->poll_list); + /* Perform generic PCI device enabling operation */ error = lpfc_enable_pci_dev(phba); if (error) @@ -13327,7 +13329,6 @@ lpfc_pci_probe_one_s4(struct pci_dev *pdev, const struct pci_device_id *pid) /* Enable RAS FW log support */ lpfc_sli4_ras_setup(phba); - INIT_LIST_HEAD(&phba->poll_list); timer_setup(&phba->cpuhp_poll_timer, lpfc_sli4_poll_hbtimer, 0); cpuhp_state_add_instance_nocalls(lpfc_cpuhp_state, &phba->cpuhp); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 19b1c0cf5f2a..cf4a3a2c22ad 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7851,7 +7851,7 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc) return r; } - rc = _base_static_config_pages(ioc); + r = _base_static_config_pages(ioc); if (r) return r; diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 328bb961c281..37506b3fe5a9 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1199,14 +1199,24 @@ static void storvsc_on_io_completion(struct storvsc_device *stor_device, vstor_packet->vm_srb.sense_info_length); if (vstor_packet->vm_srb.scsi_status != 0 || - vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS) - storvsc_log(device, STORVSC_LOGGING_ERROR, + vstor_packet->vm_srb.srb_status != SRB_STATUS_SUCCESS) { + + /* + * Log TEST_UNIT_READY errors only as warnings. Hyper-V can + * return errors when detecting devices using TEST_UNIT_READY, + * and logging these as errors produces unhelpful noise. + */ + int loglevel = (stor_pkt->vm_srb.cdb[0] == TEST_UNIT_READY) ? + STORVSC_LOGGING_WARN : STORVSC_LOGGING_ERROR; + + storvsc_log(device, loglevel, "tag#%d cmd 0x%x status: scsi 0x%x srb 0x%x hv 0x%x\n", request->cmd->request->tag, stor_pkt->vm_srb.cdb[0], vstor_packet->vm_srb.scsi_status, vstor_packet->vm_srb.srb_status, vstor_packet->status); + } if (vstor_packet->vm_srb.scsi_status == SAM_STAT_CHECK_CONDITION && (vstor_packet->vm_srb.srb_status & SRB_STATUS_AUTOSENSE_VALID)) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index b8d4b2d327b2..84fe57ef5a49 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1741,13 +1741,9 @@ static void dwc3_gadget_ep_cleanup_cancelled_requests(struct dwc3_ep *dep) { struct dwc3_request *req; struct dwc3_request *tmp; - struct list_head local; struct dwc3 *dwc = dep->dwc; -restart: - list_replace_init(&dep->cancelled_list, &local); - - list_for_each_entry_safe(req, tmp, &local, list) { + list_for_each_entry_safe(req, tmp, &dep->cancelled_list, list) { dwc3_gadget_ep_skip_trbs(dep, req); switch (req->status) { case DWC3_REQUEST_STATUS_DISCONNECTED: @@ -1765,9 +1761,6 @@ restart: break; } } - - if (!list_empty(&dep->cancelled_list)) - goto restart; } static int dwc3_gadget_ep_dequeue(struct usb_ep *ep, @@ -2976,12 +2969,8 @@ static void dwc3_gadget_ep_cleanup_completed_requests(struct dwc3_ep *dep, { struct dwc3_request *req; struct dwc3_request *tmp; - struct list_head local; -restart: - list_replace_init(&dep->started_list, &local); - - list_for_each_entry_safe(req, tmp, &local, list) { + list_for_each_entry_safe(req, tmp, &dep->started_list, list) { int ret; ret = dwc3_gadget_ep_cleanup_completed_request(dep, event, @@ -2989,9 +2978,6 @@ restart: if (ret) break; } - - if (!list_empty(&dep->started_list)) - goto restart; } static bool dwc3_gadget_ep_should_continue(struct dwc3_ep *dep) diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 21b78f1cd521..351c6cfb24c3 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -493,9 +493,9 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa, dev, &ifc_vdpa_ops, NULL); - if (adapter == NULL) { + if (IS_ERR(adapter)) { IFCVF_ERR(pdev, "Failed to allocate vDPA structure"); - return -ENOMEM; + return PTR_ERR(adapter); } pci_set_master(pdev); diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index dcee6039e966..e59135fa867e 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -512,11 +512,6 @@ out: mutex_unlock(&mr->mkey_mtx); } -static bool map_empty(struct vhost_iotlb *iotlb) -{ - return !vhost_iotlb_itree_first(iotlb, 0, U64_MAX); -} - int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, bool *change_map) { @@ -524,10 +519,6 @@ int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *io int err = 0; *change_map = false; - if (map_empty(iotlb)) { - mlx5_vdpa_destroy_mr(mvdev); - return 0; - } mutex_lock(&mr->mkey_mtx); if (mr->initialized) { mlx5_vdpa_info(mvdev, "memory map update\n"); diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 379a19144a25..3cc12fcab08d 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -752,12 +752,12 @@ static int get_queue_type(struct mlx5_vdpa_net *ndev) type_mask = MLX5_CAP_DEV_VDPA_EMULATION(ndev->mvdev.mdev, virtio_queue_type); /* prefer split queue */ - if (type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED) - return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED; + if (type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT) + return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT; - WARN_ON(!(type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT)); + WARN_ON(!(type_mask & MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED)); - return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT; + return MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED; } static bool vq_is_tx(u16 idx) @@ -2029,6 +2029,12 @@ static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) return -ENOSPC; mdev = mgtdev->madev->mdev; + if (!(MLX5_CAP_DEV_VDPA_EMULATION(mdev, virtio_queue_type) & + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT)) { + dev_warn(mdev->device, "missing support for split virtqueues\n"); + return -EOPNOTSUPP; + } + /* we save one virtqueue for control virtqueue should we require it */ max_vqs = MLX5_CAP_DEV_VDPA_EMULATION(mdev, max_num_virtio_queues); max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 14e024de5cbf..c621cf7feec0 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -251,8 +251,10 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr) vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, dev_attr->name); - if (!vdpasim) + if (IS_ERR(vdpasim)) { + ret = PTR_ERR(vdpasim); goto err_alloc; + } vdpasim->dev_attr = *dev_attr; INIT_WORK(&vdpasim->work, dev_attr->work_fn); diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index 7b4a6396c553..fe0527329857 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -436,9 +436,9 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id) vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, dev, &vp_vdpa_ops, NULL); - if (vp_vdpa == NULL) { + if (IS_ERR(vp_vdpa)) { dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n"); - return -ENOMEM; + return PTR_ERR(vp_vdpa); } mdev = &vp_vdpa->mdev; diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 210ab35a7ebf..9479f7f79217 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -614,7 +614,8 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, long pinned; int ret = 0; - if (msg->iova < v->range.first || + if (msg->iova < v->range.first || !msg->size || + msg->iova > U64_MAX - msg->size + 1 || msg->iova + msg->size - 1 > v->range.last) return -EINVAL; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index b9e853e6094d..59edb5a1ffe2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -735,10 +735,16 @@ static bool log_access_ok(void __user *log_base, u64 addr, unsigned long sz) (sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8); } +/* Make sure 64 bit math will not overflow. */ static bool vhost_overflow(u64 uaddr, u64 size) { - /* Make sure 64 bit math will not overflow. */ - return uaddr > ULONG_MAX || size > ULONG_MAX || uaddr > ULONG_MAX - size; + if (uaddr > ULONG_MAX || size > ULONG_MAX) + return true; + + if (!size) + return false; + + return uaddr > ULONG_MAX - size + 1; } /* Caller should have vq mutex and device mutex. */ diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c index 4af8fa259d65..14e2043d7685 100644 --- a/drivers/vhost/vringh.c +++ b/drivers/vhost/vringh.c @@ -359,7 +359,7 @@ __vringh_iov(struct vringh *vrh, u16 i, iov = wiov; else { iov = riov; - if (unlikely(wiov && wiov->i)) { + if (unlikely(wiov && wiov->used)) { vringh_bad("Readable desc %p after writable", &descs[i]); err = -EINVAL; diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 4b15c00c0a0a..49984d2cba24 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -355,6 +355,7 @@ int register_virtio_device(struct virtio_device *dev) virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE); INIT_LIST_HEAD(&dev->vqs); + spin_lock_init(&dev->vqs_list_lock); /* * device_add() causes the bus infrastructure to look for a matching diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 222d630c41fc..b35bb2d57f62 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -576,6 +576,13 @@ static void virtio_pci_remove(struct pci_dev *pci_dev) struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev); struct device *dev = get_device(&vp_dev->vdev.dev); + /* + * Device is marked broken on surprise removal so that virtio upper + * layers can abort any ongoing operation. + */ + if (!pci_device_is_present(pci_dev)) + virtio_break_device(&vp_dev->vdev); + pci_disable_sriov(pci_dev); unregister_virtio_device(&vp_dev->vdev); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 89bfe46a8a7f..dd95dfd85e98 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -11,6 +11,7 @@ #include <linux/module.h> #include <linux/hrtimer.h> #include <linux/dma-mapping.h> +#include <linux/spinlock.h> #include <xen/xen.h> #ifdef DEBUG @@ -1755,7 +1756,9 @@ static struct virtqueue *vring_create_virtqueue_packed( cpu_to_le16(vq->packed.event_flags_shadow); } + spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); + spin_unlock(&vdev->vqs_list_lock); return &vq->vq; err_desc_extra: @@ -2229,7 +2232,9 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, memset(vq->split.desc_state, 0, vring.num * sizeof(struct vring_desc_state_split)); + spin_lock(&vdev->vqs_list_lock); list_add_tail(&vq->vq.list, &vdev->vqs); + spin_unlock(&vdev->vqs_list_lock); return &vq->vq; err_extra: @@ -2291,6 +2296,10 @@ void vring_del_virtqueue(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); + spin_lock(&vq->vq.vdev->vqs_list_lock); + list_del(&_vq->list); + spin_unlock(&vq->vq.vdev->vqs_list_lock); + if (vq->we_own_ring) { if (vq->packed_ring) { vring_free_queue(vq->vq.vdev, @@ -2321,7 +2330,6 @@ void vring_del_virtqueue(struct virtqueue *_vq) kfree(vq->split.desc_state); kfree(vq->split.desc_extra); } - list_del(&_vq->list); kfree(vq); } EXPORT_SYMBOL_GPL(vring_del_virtqueue); @@ -2373,7 +2381,7 @@ bool virtqueue_is_broken(struct virtqueue *_vq) { struct vring_virtqueue *vq = to_vvq(_vq); - return vq->broken; + return READ_ONCE(vq->broken); } EXPORT_SYMBOL_GPL(virtqueue_is_broken); @@ -2385,10 +2393,14 @@ void virtio_break_device(struct virtio_device *dev) { struct virtqueue *_vq; + spin_lock(&dev->vqs_list_lock); list_for_each_entry(_vq, &dev->vqs, list) { struct vring_virtqueue *vq = to_vvq(_vq); - vq->broken = true; + + /* Pairs with READ_ONCE() in virtqueue_is_broken(). */ + WRITE_ONCE(vq->broken, true); } + spin_unlock(&dev->vqs_list_lock); } EXPORT_SYMBOL_GPL(virtio_break_device); diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index e1a141135992..72eaef2caeb1 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -151,6 +151,9 @@ virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index, if (!name) return NULL; + if (index >= vdpa->nvqs) + return ERR_PTR(-ENOENT); + /* Queue shouldn't already be set up. */ if (ops->get_vq_ready(vdpa, index)) return ERR_PTR(-ENOENT); diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index d7e361fb0548..a78704ae3618 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -198,12 +198,12 @@ static void disable_dynirq(struct irq_data *data); static DEFINE_PER_CPU(unsigned int, irq_epoch); -static void clear_evtchn_to_irq_row(unsigned row) +static void clear_evtchn_to_irq_row(int *evtchn_row) { unsigned col; for (col = 0; col < EVTCHN_PER_ROW; col++) - WRITE_ONCE(evtchn_to_irq[row][col], -1); + WRITE_ONCE(evtchn_row[col], -1); } static void clear_evtchn_to_irq_all(void) @@ -213,7 +213,7 @@ static void clear_evtchn_to_irq_all(void) for (row = 0; row < EVTCHN_ROW(xen_evtchn_max_channels()); row++) { if (evtchn_to_irq[row] == NULL) continue; - clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_to_irq[row]); } } @@ -221,6 +221,7 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) { unsigned row; unsigned col; + int *evtchn_row; if (evtchn >= xen_evtchn_max_channels()) return -EINVAL; @@ -233,11 +234,18 @@ static int set_evtchn_to_irq(evtchn_port_t evtchn, unsigned int irq) if (irq == -1) return 0; - evtchn_to_irq[row] = (int *)get_zeroed_page(GFP_KERNEL); - if (evtchn_to_irq[row] == NULL) + evtchn_row = (int *) __get_free_pages(GFP_KERNEL, 0); + if (evtchn_row == NULL) return -ENOMEM; - clear_evtchn_to_irq_row(row); + clear_evtchn_to_irq_row(evtchn_row); + + /* + * We've prepared an empty row for the mapping. If a different + * thread was faster inserting it, we can drop ours. + */ + if (cmpxchg(&evtchn_to_irq[row], NULL, evtchn_row) != NULL) + free_page((unsigned long) evtchn_row); } WRITE_ONCE(evtchn_to_irq[row][col], irq); @@ -1009,7 +1017,7 @@ static void __unbind_from_irq(unsigned int irq) int xen_bind_pirq_gsi_to_irq(unsigned gsi, unsigned pirq, int shareable, char *name) { - int irq = -1; + int irq; struct physdev_irq irq_op; int ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0117d867ecf8..06f9f167222b 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9226,8 +9226,14 @@ static int btrfs_rename_exchange(struct inode *old_dir, bool dest_log_pinned = false; bool need_abort = false; - /* we only allow rename subvolume link between subvolumes */ - if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) + /* + * For non-subvolumes allow exchange only within one subvolume, in the + * same inode namespace. Two subvolumes (represented as directory) can + * be exchanged as they're a logical link and have a fixed inode number. + */ + if (root != dest && + (old_ino != BTRFS_FIRST_FREE_OBJECTID || + new_ino != BTRFS_FIRST_FREE_OBJECTID)) return -EXDEV; /* close the race window with snapshot create/destroy ioctl */ diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index c0bfc2f01030..c6a9542ca281 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1611,6 +1611,11 @@ struct dfs_info3_param { int ttl; }; +struct file_list { + struct list_head list; + struct cifsFileInfo *cfile; +}; + /* * common struct for holding inode info when searching for or updating an * inode with new info diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 79402ca0ddfa..5f8a302ffcb2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -100,7 +100,7 @@ build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page, if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0; - s = dentry_path_raw(direntry, page, PAGE_SIZE); + s = dentry_path_raw(direntry, page, PATH_MAX); if (IS_ERR(s)) return s; if (!s[1]) // for root we want "", not "/" diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0a72840a88f1..bb98fbdd22a9 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4848,34 +4848,33 @@ void cifs_oplock_break(struct work_struct *work) oplock_break_ack: /* - * releasing stale oplock after recent reconnect of smb session using - * a now incorrect file handle is not a data integrity issue but do - * not bother sending an oplock release if session to server still is - * disconnected since oplock already released by the server - */ - if (!cfile->oplock_break_cancelled) { - rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid, - cinode); - cifs_dbg(FYI, "Oplock release rc = %d\n", rc); - } - /* * When oplock break is received and there are no active * file handles but cached, then schedule deferred close immediately. * So, new open will not use cached handle. */ spin_lock(&CIFS_I(inode)->deferred_lock); is_deferred = cifs_is_deferred_close(cfile, &dclose); + spin_unlock(&CIFS_I(inode)->deferred_lock); if (is_deferred && cfile->deferred_close_scheduled && delayed_work_pending(&cfile->deferred)) { - /* - * If there is no pending work, mod_delayed_work queues new work. - * So, Increase the ref count to avoid use-after-free. - */ - if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) - cifsFileInfo_get(cfile); + if (cancel_delayed_work(&cfile->deferred)) { + _cifsFileInfo_put(cfile, false, false); + goto oplock_break_done; + } } - spin_unlock(&CIFS_I(inode)->deferred_lock); + /* + * releasing stale oplock after recent reconnect of smb session using + * a now incorrect file handle is not a data integrity issue but do + * not bother sending an oplock release if session to server still is + * disconnected since oplock already released by the server + */ + if (!cfile->oplock_break_cancelled) { + rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid, + cinode); + cifs_dbg(FYI, "Oplock release rc = %d\n", rc); + } +oplock_break_done: _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); cifs_done_oplock_break(cinode); } diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index b96b253e7635..65f8a70cece3 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1625,7 +1625,7 @@ int cifs_unlink(struct inode *dir, struct dentry *dentry) goto unlink_out; } - cifs_close_all_deferred_files(tcon); + cifs_close_deferred_file(CIFS_I(inode)); if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability))) { rc = CIFSPOSIXDelFile(xid, tcon, full_path, @@ -2084,6 +2084,7 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, FILE_UNIX_BASIC_INFO *info_buf_target; unsigned int xid; int rc, tmprc; + int retry_count = 0; if (flags & ~RENAME_NOREPLACE) return -EINVAL; @@ -2113,10 +2114,24 @@ cifs_rename2(struct user_namespace *mnt_userns, struct inode *source_dir, goto cifs_rename_exit; } - cifs_close_all_deferred_files(tcon); + cifs_close_deferred_file(CIFS_I(d_inode(source_dentry))); + if (d_inode(target_dentry) != NULL) + cifs_close_deferred_file(CIFS_I(d_inode(target_dentry))); + rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, to_name); + if (rc == -EACCES) { + while (retry_count < 3) { + cifs_close_all_deferred_files(tcon); + rc = cifs_do_rename(xid, source_dentry, from_name, target_dentry, + to_name); + if (rc != -EACCES) + break; + retry_count++; + } + } + /* * No-replace is the natural behavior for CIFS, so skip unlink hacks. */ diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 844abeb2b48f..9469f1cf0b46 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -723,13 +723,31 @@ void cifs_close_deferred_file(struct cifsInodeInfo *cifs_inode) { struct cifsFileInfo *cfile = NULL; - struct cifs_deferred_close *dclose; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; + + if (cifs_inode == NULL) + return; + INIT_LIST_HEAD(&file_head); + spin_lock(&cifs_inode->open_file_lock); list_for_each_entry(cfile, &cifs_inode->openFileList, flist) { - spin_lock(&cifs_inode->deferred_lock); - if (cifs_is_deferred_close(cfile, &dclose)) - mod_delayed_work(deferredclose_wq, &cfile->deferred, 0); - spin_unlock(&cifs_inode->deferred_lock); + if (delayed_work_pending(&cfile->deferred)) { + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + continue; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } + } + } + spin_unlock(&cifs_inode->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); } } @@ -738,20 +756,30 @@ cifs_close_all_deferred_files(struct cifs_tcon *tcon) { struct cifsFileInfo *cfile; struct list_head *tmp; + struct file_list *tmp_list, *tmp_next_list; + struct list_head file_head; + INIT_LIST_HEAD(&file_head); spin_lock(&tcon->open_file_lock); list_for_each(tmp, &tcon->openFileList) { cfile = list_entry(tmp, struct cifsFileInfo, tlist); if (delayed_work_pending(&cfile->deferred)) { - /* - * If there is no pending work, mod_delayed_work queues new work. - * So, Increase the ref count to avoid use-after-free. - */ - if (!mod_delayed_work(deferredclose_wq, &cfile->deferred, 0)) - cifsFileInfo_get(cfile); + if (cancel_delayed_work(&cfile->deferred)) { + tmp_list = kmalloc(sizeof(struct file_list), GFP_ATOMIC); + if (tmp_list == NULL) + continue; + tmp_list->cfile = cfile; + list_add_tail(&tmp_list->list, &file_head); + } } } spin_unlock(&tcon->open_file_lock); + + list_for_each_entry_safe(tmp_list, tmp_next_list, &file_head, list) { + _cifsFileInfo_put(tmp_list->cfile, true, false); + list_del(&tmp_list->list); + kfree(tmp_list); + } } /* parses DFS refferal V3 structure diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 781d14e5f2af..b6d2e3591927 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2426,7 +2426,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len) memcpy(aclptr, &acl, sizeof(struct cifs_acl)); buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd); - *len = ptr - (__u8 *)buf; + *len = roundup(ptr - (__u8 *)buf, 8); return buf; } diff --git a/fs/configfs/file.c b/fs/configfs/file.c index 5a0be9985bae..0ad32150611e 100644 --- a/fs/configfs/file.c +++ b/fs/configfs/file.c @@ -177,28 +177,22 @@ out: return retval; } -/* Fill [buffer, buffer + pos) with data coming from @from. */ -static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos, +/* Fill @buffer with data coming from @from. */ +static int fill_write_buffer(struct configfs_buffer *buffer, struct iov_iter *from) { - loff_t to_copy; int copied; - u8 *to; if (!buffer->page) buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0); if (!buffer->page) return -ENOMEM; - to_copy = SIMPLE_ATTR_SIZE - 1 - pos; - if (to_copy <= 0) - return 0; - to = buffer->page + pos; - copied = copy_from_iter(to, to_copy, from); + copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from); buffer->needs_read_fill = 1; /* if buf is assumed to contain a string, terminate it by \0, * so e.g. sscanf() can scan the string easily */ - to[copied] = 0; + buffer->page[copied] = 0; return copied ? : -EFAULT; } @@ -227,10 +221,10 @@ static ssize_t configfs_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct configfs_buffer *buffer = file->private_data; - ssize_t len; + int len; mutex_lock(&buffer->mutex); - len = fill_write_buffer(buffer, iocb->ki_pos, from); + len = fill_write_buffer(buffer, from); if (len > 0) len = flush_write_buffer(file, buffer, len); if (len > 0) @@ -722,7 +722,7 @@ static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_d return rc; id = dax_read_lock(); - rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(PAGE_SIZE), &kaddr, NULL); + rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL); if (rc < 0) { dax_read_unlock(id); return rc; diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c index e55723744f58..9d58371d22c2 100644 --- a/fs/fuse/dax.c +++ b/fs/fuse/dax.c @@ -1235,8 +1235,6 @@ void fuse_dax_conn_free(struct fuse_conn *fc) static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd) { long nr_pages, nr_ranges; - void *kaddr; - pfn_t pfn; struct fuse_dax_mapping *range; int ret, id; size_t dax_size = -1; @@ -1248,8 +1246,8 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd) INIT_DELAYED_WORK(&fcd->free_work, fuse_dax_free_mem_worker); id = dax_read_lock(); - nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), &kaddr, - &pfn); + nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL, + NULL); dax_read_unlock(id); if (nr_pages < 0) { pr_debug("dax_direct_access() returned %ld\n", nr_pages); diff --git a/fs/io-wq.c b/fs/io-wq.c index 12fc19353bb0..7d2ed8c7dd31 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -129,7 +129,7 @@ struct io_cb_cancel_data { bool cancel_all; }; -static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index); +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index, bool first); static void io_wqe_dec_running(struct io_worker *worker); static bool io_worker_get(struct io_worker *worker) @@ -248,18 +248,20 @@ static void io_wqe_wake_worker(struct io_wqe *wqe, struct io_wqe_acct *acct) rcu_read_unlock(); if (!ret) { - bool do_create = false; + bool do_create = false, first = false; raw_spin_lock_irq(&wqe->lock); if (acct->nr_workers < acct->max_workers) { atomic_inc(&acct->nr_running); atomic_inc(&wqe->wq->worker_refs); + if (!acct->nr_workers) + first = true; acct->nr_workers++; do_create = true; } raw_spin_unlock_irq(&wqe->lock); if (do_create) - create_io_worker(wqe->wq, wqe, acct->index); + create_io_worker(wqe->wq, wqe, acct->index, first); } } @@ -282,16 +284,26 @@ static void create_worker_cb(struct callback_head *cb) struct io_wq *wq; struct io_wqe *wqe; struct io_wqe_acct *acct; + bool do_create = false, first = false; cwd = container_of(cb, struct create_worker_data, work); wqe = cwd->wqe; wq = wqe->wq; acct = &wqe->acct[cwd->index]; raw_spin_lock_irq(&wqe->lock); - if (acct->nr_workers < acct->max_workers) + if (acct->nr_workers < acct->max_workers) { + if (!acct->nr_workers) + first = true; acct->nr_workers++; + do_create = true; + } raw_spin_unlock_irq(&wqe->lock); - create_io_worker(wq, cwd->wqe, cwd->index); + if (do_create) { + create_io_worker(wq, wqe, cwd->index, first); + } else { + atomic_dec(&acct->nr_running); + io_worker_ref_put(wq); + } kfree(cwd); } @@ -629,7 +641,7 @@ void io_wq_worker_sleeping(struct task_struct *tsk) raw_spin_unlock_irq(&worker->wqe->lock); } -static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) +static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index, bool first) { struct io_wqe_acct *acct = &wqe->acct[index]; struct io_worker *worker; @@ -670,7 +682,7 @@ fail: worker->flags |= IO_WORKER_F_FREE; if (index == IO_WQ_ACCT_BOUND) worker->flags |= IO_WORKER_F_BOUND; - if ((acct->nr_workers == 1) && (worker->flags & IO_WORKER_F_BOUND)) + if (first && (worker->flags & IO_WORKER_F_BOUND)) worker->flags |= IO_WORKER_F_FIXED; raw_spin_unlock_irq(&wqe->lock); wake_up_new_task(tsk); diff --git a/fs/io_uring.c b/fs/io_uring.c index bf548af0426c..04c6d059ea94 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -78,6 +78,7 @@ #include <linux/task_work.h> #include <linux/pagemap.h> #include <linux/io_uring.h> +#include <linux/tracehook.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -1499,7 +1500,8 @@ static bool __io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) all_flushed = list_empty(&ctx->cq_overflow_list); if (all_flushed) { clear_bit(0, &ctx->check_cq_overflow); - ctx->rings->sq_flags &= ~IORING_SQ_CQ_OVERFLOW; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_CQ_OVERFLOW); } if (posted) @@ -1578,7 +1580,9 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, } if (list_empty(&ctx->cq_overflow_list)) { set_bit(0, &ctx->check_cq_overflow); - ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_CQ_OVERFLOW); + } ocqe->cqe.user_data = user_data; ocqe->cqe.res = res; @@ -2222,9 +2226,9 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { - if (current->task_works) { + if (test_thread_flag(TIF_NOTIFY_SIGNAL) || current->task_works) { __set_current_state(TASK_RUNNING); - task_work_run(); + tracehook_notify_signal(); return true; } @@ -6803,14 +6807,16 @@ static inline void io_ring_set_wakeup_flag(struct io_ring_ctx *ctx) { /* Tell userspace we may need a wakeup call */ spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags |= IORING_SQ_NEED_WAKEUP; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags | IORING_SQ_NEED_WAKEUP); spin_unlock_irq(&ctx->completion_lock); } static inline void io_ring_clear_wakeup_flag(struct io_ring_ctx *ctx) { spin_lock_irq(&ctx->completion_lock); - ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP; + WRITE_ONCE(ctx->rings->sq_flags, + ctx->rings->sq_flags & ~IORING_SQ_NEED_WAKEUP); spin_unlock_irq(&ctx->completion_lock); } @@ -7132,16 +7138,6 @@ static void **io_alloc_page_table(size_t size) return table; } -static inline void io_rsrc_ref_lock(struct io_ring_ctx *ctx) -{ - spin_lock_bh(&ctx->rsrc_ref_lock); -} - -static inline void io_rsrc_ref_unlock(struct io_ring_ctx *ctx) -{ - spin_unlock_bh(&ctx->rsrc_ref_lock); -} - static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) { percpu_ref_exit(&ref_node->refs); @@ -7158,9 +7154,9 @@ static void io_rsrc_node_switch(struct io_ring_ctx *ctx, struct io_rsrc_node *rsrc_node = ctx->rsrc_node; rsrc_node->rsrc_data = data_to_kill; - io_rsrc_ref_lock(ctx); + spin_lock_irq(&ctx->rsrc_ref_lock); list_add_tail(&rsrc_node->node, &ctx->rsrc_ref_list); - io_rsrc_ref_unlock(ctx); + spin_unlock_irq(&ctx->rsrc_ref_lock); atomic_inc(&data_to_kill->refs); percpu_ref_kill(&rsrc_node->refs); @@ -7199,17 +7195,19 @@ static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ct /* kill initial ref, already quiesced if zero */ if (atomic_dec_and_test(&data->refs)) break; + mutex_unlock(&ctx->uring_lock); flush_delayed_work(&ctx->rsrc_put_work); ret = wait_for_completion_interruptible(&data->done); - if (!ret) + if (!ret) { + mutex_lock(&ctx->uring_lock); break; + } atomic_inc(&data->refs); /* wait for all works potentially completing data->done */ flush_delayed_work(&ctx->rsrc_put_work); reinit_completion(&data->done); - mutex_unlock(&ctx->uring_lock); ret = io_run_task_work_sig(); mutex_lock(&ctx->uring_lock); } while (ret >= 0); @@ -7668,9 +7666,10 @@ static void io_rsrc_node_ref_zero(struct percpu_ref *ref) { struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); struct io_ring_ctx *ctx = node->rsrc_data->ctx; + unsigned long flags; bool first_add = false; - io_rsrc_ref_lock(ctx); + spin_lock_irqsave(&ctx->rsrc_ref_lock, flags); node->done = true; while (!list_empty(&ctx->rsrc_ref_list)) { @@ -7682,7 +7681,7 @@ static void io_rsrc_node_ref_zero(struct percpu_ref *ref) list_del(&node->node); first_add |= llist_add(&node->llist, &ctx->rsrc_put_llist); } - io_rsrc_ref_unlock(ctx); + spin_unlock_irqrestore(&ctx->rsrc_ref_lock, flags); if (first_add) mod_delayed_work(system_wq, &ctx->rsrc_put_work, HZ); @@ -8653,13 +8652,10 @@ static void io_req_caches_free(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); } -static bool io_wait_rsrc_data(struct io_rsrc_data *data) +static void io_wait_rsrc_data(struct io_rsrc_data *data) { - if (!data) - return false; - if (!atomic_dec_and_test(&data->refs)) + if (data && !atomic_dec_and_test(&data->refs)) wait_for_completion(&data->done); - return true; } static void io_ring_ctx_free(struct io_ring_ctx *ctx) @@ -8671,10 +8667,14 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) ctx->mm_account = NULL; } + /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ + io_wait_rsrc_data(ctx->buf_data); + io_wait_rsrc_data(ctx->file_data); + mutex_lock(&ctx->uring_lock); - if (io_wait_rsrc_data(ctx->buf_data)) + if (ctx->buf_data) __io_sqe_buffers_unregister(ctx); - if (io_wait_rsrc_data(ctx->file_data)) + if (ctx->file_data) __io_sqe_files_unregister(ctx); if (ctx->rings) __io_cqring_overflow_flush(ctx, true); diff --git a/fs/pipe.c b/fs/pipe.c index 8e6ef62aeb1c..678dee2a8228 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -444,9 +444,6 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) #endif /* - * Epoll nonsensically wants a wakeup whether the pipe - * was already empty or not. - * * If it wasn't empty we try to merge new data into * the last buffer. * @@ -455,9 +452,9 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from) * spanning multiple pages. */ head = pipe->head; - was_empty = true; + was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); - if (chars && !pipe_empty(head, pipe->tail)) { + if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; @@ -590,8 +587,11 @@ out: * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs + * + * Epoll nonsensically wants a wakeup whether the pipe + * was already empty or not. */ - if (was_empty) { + if (was_empty || pipe->poll_usage) { wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } @@ -654,6 +654,9 @@ pipe_poll(struct file *filp, poll_table *wait) struct pipe_inode_info *pipe = filp->private_data; unsigned int head, tail; + /* Epoll has some historical nasty semantics, this enables them */ + pipe->poll_usage = 1; + /* * Reading pipe state only -- no need for acquiring the semaphore. * diff --git a/include/linux/device.h b/include/linux/device.h index 59940f1744c1..65d84b67b024 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -407,6 +407,7 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. + * @msi_lock: Lock to protect MSI mask cache and mask register * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. @@ -506,6 +507,7 @@ struct device { struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ + raw_spinlock_t msi_lock; struct list_head msi_list; #endif #ifdef CONFIG_DMA_OPS diff --git a/include/linux/irq.h b/include/linux/irq.h index 8e9a9ae471a6..c8293c817646 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -569,6 +569,7 @@ struct irq_chip { * IRQCHIP_SUPPORTS_NMI: Chip can deliver NMIs, only for root irqchips * IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND: Invokes __enable_irq()/__disable_irq() for wake irqs * in the suspend path if they are in disabled state + * IRQCHIP_AFFINITY_PRE_STARTUP: Default affinity update before startup */ enum { IRQCHIP_SET_TYPE_MASKED = (1 << 0), @@ -581,6 +582,7 @@ enum { IRQCHIP_SUPPORTS_LEVEL_MSI = (1 << 7), IRQCHIP_SUPPORTS_NMI = (1 << 8), IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND = (1 << 9), + IRQCHIP_AFFINITY_PRE_STARTUP = (1 << 10), }; #include <linux/irqdesc.h> diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h index 98b56b75c625..1a9c9d94cb59 100644 --- a/include/linux/mlx5/mlx5_ifc_vdpa.h +++ b/include/linux/mlx5/mlx5_ifc_vdpa.h @@ -11,13 +11,15 @@ enum { }; enum { - MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT = 0x1, // do I check this caps? - MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED = 0x2, + MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT = 0, + MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED = 1, }; enum { - MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT = 0, - MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED = 1, + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_SPLIT = + BIT(MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_SPLIT), + MLX5_VIRTIO_EMULATION_CAP_VIRTIO_QUEUE_TYPE_PACKED = + BIT(MLX5_VIRTIO_EMULATION_VIRTIO_QUEUE_TYPE_PACKED), }; struct mlx5_ifc_virtio_q_bits { diff --git a/include/linux/msi.h b/include/linux/msi.h index 6aff469e511d..e8bdcb83172b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -233,7 +233,7 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag); -u32 __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); +void __pci_msi_desc_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5d2705f1d01c..fc5642431b92 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -48,6 +48,7 @@ struct pipe_buffer { * @files: number of struct file referring this pipe (protected by ->i_lock) * @r_counter: reader counter * @w_counter: writer counter + * @poll_usage: is this pipe used for epoll, which has crazy wakeups? * @fasync_readers: reader side fasync * @fasync_writers: writer side fasync * @bufs: the circular array of pipe buffers @@ -70,6 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; + unsigned int poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 3357ac98878d..8cfe49d201dd 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -277,6 +277,17 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, const struct vdpa_config_ops *config, size_t size, const char *name); +/** + * vdpa_alloc_device - allocate and initilaize a vDPA device + * + * @dev_struct: the type of the parent structure + * @member: the name of struct vdpa_device within the @dev_struct + * @parent: the parent device + * @config: the bus operations that is supported by this device + * @name: name of the vdpa device + * + * Return allocated data structure or ERR_PTR upon error + */ #define vdpa_alloc_device(dev_struct, member, parent, config, name) \ container_of(__vdpa_alloc_device( \ parent, config, \ diff --git a/include/linux/virtio.h b/include/linux/virtio.h index b1894e0323fa..41edbc01ffa4 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -110,6 +110,7 @@ struct virtio_device { bool config_enabled; bool config_change_pending; spinlock_t config_lock; + spinlock_t vqs_list_lock; /* Protects VQs list access */ struct device dev; struct virtio_device_id id; const struct virtio_config_ops *config; diff --git a/include/linux/vringh.h b/include/linux/vringh.h index 84db7b8f912f..212892cf9822 100644 --- a/include/linux/vringh.h +++ b/include/linux/vringh.h @@ -14,6 +14,7 @@ #include <linux/virtio_byteorder.h> #include <linux/uio.h> #include <linux/slab.h> +#include <linux/spinlock.h> #if IS_REACHABLE(CONFIG_VHOST_IOTLB) #include <linux/dma-direction.h> #include <linux/vhost_iotlb.h> diff --git a/init/main.c b/init/main.c index f5b8246e8aa1..8d97aba78c3a 100644 --- a/init/main.c +++ b/init/main.c @@ -397,6 +397,12 @@ static int __init bootconfig_params(char *param, char *val, return 0; } +static int __init warn_bootconfig(char *str) +{ + /* The 'bootconfig' has been handled by bootconfig_params(). */ + return 0; +} + static void __init setup_boot_config(void) { static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata; @@ -475,9 +481,8 @@ static int __init warn_bootconfig(char *str) pr_warn("WARNING: 'bootconfig' found on the kernel command line but CONFIG_BOOT_CONFIG is not set.\n"); return 0; } -early_param("bootconfig", warn_bootconfig); - #endif +early_param("bootconfig", warn_bootconfig); /* Change NUL term back to "=", to make "param" the whole string. */ static void __init repair_env_string(char *param, char *val) diff --git a/kernel/cfi.c b/kernel/cfi.c index e17a56639766..9594cfd1cf2c 100644 --- a/kernel/cfi.c +++ b/kernel/cfi.c @@ -248,9 +248,9 @@ static inline cfi_check_fn find_shadow_check_fn(unsigned long ptr) { cfi_check_fn fn; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); fn = ptr_to_check_fn(rcu_dereference_sched(cfi_shadow), ptr); - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); return fn; } @@ -269,11 +269,11 @@ static inline cfi_check_fn find_module_check_fn(unsigned long ptr) cfi_check_fn fn = NULL; struct module *mod; - rcu_read_lock_sched(); + rcu_read_lock_sched_notrace(); mod = __module_address(ptr); if (mod) fn = mod->cfi_check; - rcu_read_unlock_sched(); + rcu_read_unlock_sched_notrace(); return fn; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index 7f04c7d8296e..a98bcfc4be7b 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -265,8 +265,11 @@ int irq_startup(struct irq_desc *desc, bool resend, bool force) } else { switch (__irq_startup_managed(desc, aff, force)) { case IRQ_STARTUP_NORMAL: + if (d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP) + irq_setup_affinity(desc); ret = __irq_startup(desc); - irq_setup_affinity(desc); + if (!(d->chip->flags & IRQCHIP_AFFINITY_PRE_STARTUP)) + irq_setup_affinity(desc); break; case IRQ_STARTUP_MANAGED: irq_do_set_affinity(d, aff, false); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index c41965e348b5..85df3ca03efe 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -476,11 +476,6 @@ skip_activate: return 0; cleanup: - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - if (irqd_is_activated(irq_data)) - irq_domain_deactivate_irq(irq_data); - } msi_domain_free_irqs(domain, dev); return ret; } @@ -505,7 +500,15 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) { + struct irq_data *irq_data; struct msi_desc *desc; + int i; + + for_each_msi_vector(desc, i, dev) { + irq_data = irq_domain_get_irq_data(domain, i); + if (irqd_is_activated(irq_data)) + irq_domain_deactivate_irq(irq_data); + } for_each_msi_entry(desc, dev) { /* diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c index d309d6fbf5bd..4d2a702d7aa9 100644 --- a/kernel/irq/timings.c +++ b/kernel/irq/timings.c @@ -453,6 +453,11 @@ static __always_inline void __irq_timings_store(int irq, struct irqt_stat *irqs, */ index = irq_timings_interval_index(interval); + if (index > PREDICTION_BUFFER_SIZE - 1) { + irqs->count = 0; + return; + } + /* * Store the index as an element of the pattern in another * circular array. diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index b5d9bb5202c6..ad0db322ed3b 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -343,7 +343,7 @@ static __always_inline bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter, enum rtmutex_chainwalk chwalk) { - if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEX)) + if (IS_ENABLED(CONFIG_DEBUG_RT_MUTEXES)) return waiter != NULL; return chwalk == RT_MUTEX_FULL_CHAINWALK; } diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index d567b1717c4c..3ee23f4d437f 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -219,6 +219,11 @@ config DYNAMIC_FTRACE_WITH_DIRECT_CALLS depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +config DYNAMIC_FTRACE_WITH_ARGS + def_bool y + depends on DYNAMIC_FTRACE + depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS + config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 33899a71fdc1..a1adb29ef5c1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2897,14 +2897,26 @@ int tracepoint_printk_sysctl(struct ctl_table *table, int write, void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) { + enum event_trigger_type tt = ETT_NONE; + struct trace_event_file *file = fbuffer->trace_file; + + if (__event_trigger_test_discard(file, fbuffer->buffer, fbuffer->event, + fbuffer->entry, &tt)) + goto discard; + if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); if (static_branch_unlikely(&trace_event_exports_enabled)) ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); - event_trigger_unlock_commit_regs(fbuffer->trace_file, fbuffer->buffer, - fbuffer->event, fbuffer->entry, - fbuffer->trace_ctx, fbuffer->regs); + + trace_buffer_unlock_commit_regs(file->tr, fbuffer->buffer, + fbuffer->event, fbuffer->trace_ctx, fbuffer->regs); + +discard: + if (tt) + event_triggers_post_call(file, tt); + } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index a180abf76d4e..4a0e693000c6 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1389,38 +1389,6 @@ event_trigger_unlock_commit(struct trace_event_file *file, event_triggers_post_call(file, tt); } -/** - * event_trigger_unlock_commit_regs - handle triggers and finish event commit - * @file: The file pointer associated with the event - * @buffer: The ring buffer that the event is being written to - * @event: The event meta data in the ring buffer - * @entry: The event itself - * @trace_ctx: The tracing context flags. - * - * This is a helper function to handle triggers that require data - * from the event itself. It also tests the event against filters and - * if the event is soft disabled and should be discarded. - * - * Same as event_trigger_unlock_commit() but calls - * trace_buffer_unlock_commit_regs() instead of trace_buffer_unlock_commit(). - */ -static inline void -event_trigger_unlock_commit_regs(struct trace_event_file *file, - struct trace_buffer *buffer, - struct ring_buffer_event *event, - void *entry, unsigned int trace_ctx, - struct pt_regs *regs) -{ - enum event_trigger_type tt = ETT_NONE; - - if (!__event_trigger_test_discard(file, buffer, event, entry, &tt)) - trace_buffer_unlock_commit_regs(file->tr, buffer, event, - trace_ctx, regs); - - if (tt) - event_triggers_post_call(file, tt); -} - #define FILTER_PRED_INVALID ((unsigned short)-1) #define FILTER_PRED_IS_RIGHT (1 << 15) #define FILTER_PRED_FOLD (1 << 15) diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 949ef09dc537..a48aa2a2875b 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3430,6 +3430,8 @@ trace_action_create_field_var(struct hist_trigger_data *hist_data, event = data->match_data.event; } + if (!event) + goto free; /* * At this point, we're looking at a field on another * event. Because we can't modify a hist trigger on diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index a7e3c24dee13..b61eefe5ccf5 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -253,6 +253,7 @@ static struct osnoise_data { */ static bool osnoise_busy; +#ifdef CONFIG_PREEMPT_RT /* * Print the osnoise header info. */ @@ -261,6 +262,35 @@ static void print_osnoise_headers(struct seq_file *s) if (osnoise_data.tainted) seq_puts(s, "# osnoise is tainted!\n"); + seq_puts(s, "# _-------=> irqs-off\n"); + seq_puts(s, "# / _------=> need-resched\n"); + seq_puts(s, "# | / _-----=> need-resched-lazy\n"); + seq_puts(s, "# || / _----=> hardirq/softirq\n"); + seq_puts(s, "# ||| / _---=> preempt-depth\n"); + seq_puts(s, "# |||| / _--=> preempt-lazy-depth\n"); + seq_puts(s, "# ||||| / _-=> migrate-disable\n"); + + seq_puts(s, "# |||||| / "); + seq_puts(s, " MAX\n"); + + seq_puts(s, "# ||||| / "); + seq_puts(s, " SINGLE Interference counters:\n"); + + seq_puts(s, "# ||||||| RUNTIME "); + seq_puts(s, " NOISE %% OF CPU NOISE +-----------------------------+\n"); + + seq_puts(s, "# TASK-PID CPU# ||||||| TIMESTAMP IN US "); + seq_puts(s, " IN US AVAILABLE IN US HW NMI IRQ SIRQ THREAD\n"); + + seq_puts(s, "# | | | ||||||| | | "); + seq_puts(s, " | | | | | | | |\n"); +} +#else /* CONFIG_PREEMPT_RT */ +static void print_osnoise_headers(struct seq_file *s) +{ + if (osnoise_data.tainted) + seq_puts(s, "# osnoise is tainted!\n"); + seq_puts(s, "# _-----=> irqs-off\n"); seq_puts(s, "# / _----=> need-resched\n"); seq_puts(s, "# | / _---=> hardirq/softirq\n"); @@ -279,6 +309,7 @@ static void print_osnoise_headers(struct seq_file *s) seq_puts(s, "# | | | |||| | | "); seq_puts(s, " | | | | | | | |\n"); } +#endif /* CONFIG_PREEMPT_RT */ /* * osnoise_taint - report an osnoise error. @@ -323,6 +354,24 @@ static void trace_osnoise_sample(struct osnoise_sample *sample) /* * Print the timerlat header info. */ +#ifdef CONFIG_PREEMPT_RT +static void print_timerlat_headers(struct seq_file *s) +{ + seq_puts(s, "# _-------=> irqs-off\n"); + seq_puts(s, "# / _------=> need-resched\n"); + seq_puts(s, "# | / _-----=> need-resched-lazy\n"); + seq_puts(s, "# || / _----=> hardirq/softirq\n"); + seq_puts(s, "# ||| / _---=> preempt-depth\n"); + seq_puts(s, "# |||| / _--=> preempt-lazy-depth\n"); + seq_puts(s, "# ||||| / _-=> migrate-disable\n"); + seq_puts(s, "# |||||| /\n"); + seq_puts(s, "# ||||||| ACTIVATION\n"); + seq_puts(s, "# TASK-PID CPU# ||||||| TIMESTAMP ID "); + seq_puts(s, " CONTEXT LATENCY\n"); + seq_puts(s, "# | | | ||||||| | | "); + seq_puts(s, " | |\n"); +} +#else /* CONFIG_PREEMPT_RT */ static void print_timerlat_headers(struct seq_file *s) { seq_puts(s, "# _-----=> irqs-off\n"); @@ -336,6 +385,7 @@ static void print_timerlat_headers(struct seq_file *s) seq_puts(s, "# | | | |||| | | "); seq_puts(s, " | |\n"); } +#endif /* CONFIG_PREEMPT_RT */ /* * Record an timerlat_sample into the tracer buffer. @@ -1025,9 +1075,13 @@ diff_osn_sample_stats(struct osnoise_variables *osn_var, struct osnoise_sample * /* * osnoise_stop_tracing - Stop tracing and the tracer. */ -static void osnoise_stop_tracing(void) +static __always_inline void osnoise_stop_tracing(void) { struct trace_array *tr = osnoise_trace; + + trace_array_printk_buf(tr->array_buffer.buffer, _THIS_IP_, + "stop tracing hit on cpu %d\n", smp_processor_id()); + tracer_tracing_off(tr); } diff --git a/lib/devmem_is_allowed.c b/lib/devmem_is_allowed.c index c0d67c541849..60be9e24bd57 100644 --- a/lib/devmem_is_allowed.c +++ b/lib/devmem_is_allowed.c @@ -19,7 +19,7 @@ */ int devmem_is_allowed(unsigned long pfn) { - if (iomem_is_exclusive(pfn << PAGE_SHIFT)) + if (iomem_is_exclusive(PFN_PHYS(pfn))) return 0; if (!page_is_ram(pfn)) return 1; @@ -1558,9 +1558,12 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start, gup_flags |= FOLL_WRITE; /* - * See check_vma_flags(): Will return -EFAULT on incompatible mappings - * or with insufficient permissions. + * We want to report -EINVAL instead of -EFAULT for any permission + * problems or incompatible mappings. */ + if (check_vma_flags(vma, gup_flags)) + return -EINVAL; + return __get_user_pages(mm, start, nr_pages, gup_flags, NULL, NULL, locked); } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 228a2fbe0657..73d46d16d575 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -290,7 +290,7 @@ static void hex_dump_object(struct seq_file *seq, warn_or_seq_printf(seq, " hex dump (first %zu bytes):\n", len); kasan_disable_current(); warn_or_seq_hex_dump(seq, DUMP_PREFIX_NONE, HEX_ROW_SIZE, - HEX_GROUP_SIZE, ptr, len, HEX_ASCII); + HEX_GROUP_SIZE, kasan_reset_tag((void *)ptr), len, HEX_ASCII); kasan_enable_current(); } @@ -1171,7 +1171,7 @@ static bool update_checksum(struct kmemleak_object *object) kasan_disable_current(); kcsan_disable_current(); - object->checksum = crc32(0, (void *)object->pointer, object->size); + object->checksum = crc32(0, kasan_reset_tag((void *)object->pointer), object->size); kasan_enable_current(); kcsan_enable_current(); @@ -1246,7 +1246,7 @@ static void scan_block(void *_start, void *_end, break; kasan_disable_current(); - pointer = *ptr; + pointer = *(unsigned long *)kasan_reset_tag((void *)ptr); kasan_enable_current(); untagged_ptr = (unsigned long)kasan_reset_tag((void *)pointer); diff --git a/mm/madvise.c b/mm/madvise.c index 6d3d348b17f4..5c065bc8b5f6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -862,10 +862,12 @@ static long madvise_populate(struct vm_area_struct *vma, switch (pages) { case -EINTR: return -EINTR; - case -EFAULT: /* Incompatible mappings / permissions. */ + case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; + case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ + return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index eb8e87c4833f..702a81dfe72d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3106,13 +3106,15 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, stock->cached_pgdat = pgdat; } else if (stock->cached_pgdat != pgdat) { /* Flush the existing cached vmstat data */ + struct pglist_data *oldpg = stock->cached_pgdat; + if (stock->nr_slab_reclaimable_b) { - mod_objcg_mlstate(objcg, pgdat, NR_SLAB_RECLAIMABLE_B, + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B, stock->nr_slab_reclaimable_b); stock->nr_slab_reclaimable_b = 0; } if (stock->nr_slab_unreclaimable_b) { - mod_objcg_mlstate(objcg, pgdat, NR_SLAB_UNRECLAIMABLE_B, + mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B, stock->nr_slab_unreclaimable_b); stock->nr_slab_unreclaimable_b = 0; } diff --git a/mm/slub.c b/mm/slub.c index af984e4990e8..f77d8cd79ef7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -576,8 +576,8 @@ static void print_section(char *level, char *text, u8 *addr, unsigned int length) { metadata_access_enable(); - print_hex_dump(level, kasan_reset_tag(text), DUMP_PREFIX_ADDRESS, - 16, 1, addr, length, 1); + print_hex_dump(level, text, DUMP_PREFIX_ADDRESS, + 16, 1, kasan_reset_tag((void *)addr), length, 1); metadata_access_disable(); } @@ -1400,12 +1400,13 @@ check_slabs: static int __init setup_slub_debug(char *str) { slab_flags_t flags; + slab_flags_t global_flags; char *saved_str; char *slab_list; bool global_slub_debug_changed = false; bool slab_list_specified = false; - slub_debug = DEBUG_DEFAULT_FLAGS; + global_flags = DEBUG_DEFAULT_FLAGS; if (*str++ != '=' || !*str) /* * No options specified. Switch on full debugging. @@ -1417,7 +1418,7 @@ static int __init setup_slub_debug(char *str) str = parse_slub_debug_flags(str, &flags, &slab_list, true); if (!slab_list) { - slub_debug = flags; + global_flags = flags; global_slub_debug_changed = true; } else { slab_list_specified = true; @@ -1426,16 +1427,18 @@ static int __init setup_slub_debug(char *str) /* * For backwards compatibility, a single list of flags with list of - * slabs means debugging is only enabled for those slabs, so the global - * slub_debug should be 0. We can extended that to multiple lists as + * slabs means debugging is only changed for those slabs, so the global + * slub_debug should be unchanged (0 or DEBUG_DEFAULT_FLAGS, depending + * on CONFIG_SLUB_DEBUG_ON). We can extended that to multiple lists as * long as there is no option specifying flags without a slab list. */ if (slab_list_specified) { if (!global_slub_debug_changed) - slub_debug = 0; + global_flags = slub_debug; slub_debug_string = saved_str; } out: + slub_debug = global_flags; if (slub_debug != 0 || slub_debug_string) static_branch_enable(&slub_debug_enabled); else @@ -3236,12 +3239,12 @@ struct detached_freelist { struct kmem_cache *s; }; -static inline void free_nonslab_page(struct page *page) +static inline void free_nonslab_page(struct page *page, void *object) { unsigned int order = compound_order(page); VM_BUG_ON_PAGE(!PageCompound(page), page); - kfree_hook(page_address(page)); + kfree_hook(object); mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order)); __free_pages(page, order); } @@ -3282,7 +3285,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size, if (!s) { /* Handle kalloc'ed objects */ if (unlikely(!PageSlab(page))) { - free_nonslab_page(page); + free_nonslab_page(page, object); p[size] = NULL; /* mark object processed */ return size; } @@ -4258,7 +4261,7 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { - free_nonslab_page(page); + free_nonslab_page(page, object); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); diff --git a/sound/firewire/oxfw/oxfw-stream.c b/sound/firewire/oxfw/oxfw-stream.c index 0ef242fdd3bc..fff18b5d4e05 100644 --- a/sound/firewire/oxfw/oxfw-stream.c +++ b/sound/firewire/oxfw/oxfw-stream.c @@ -153,7 +153,7 @@ static int init_stream(struct snd_oxfw *oxfw, struct amdtp_stream *stream) struct cmp_connection *conn; enum cmp_direction c_dir; enum amdtp_stream_direction s_dir; - unsigned int flags = CIP_UNAWARE_SYT; + unsigned int flags = 0; int err; if (!(oxfw->quirks & SND_OXFW_QUIRK_BLOCKING_TRANSMISSION)) @@ -161,6 +161,13 @@ static int init_stream(struct snd_oxfw *oxfw, struct amdtp_stream *stream) else flags |= CIP_BLOCKING; + // OXFW 970/971 has no function to generate playback timing according to the sequence + // of value in syt field, thus the packet should include NO_INFO value in the field. + // However, some models just ignore data blocks in packet with NO_INFO for audio data + // processing. + if (!(oxfw->quirks & SND_OXFW_QUIRK_IGNORE_NO_INFO_PACKET)) + flags |= CIP_UNAWARE_SYT; + if (stream == &oxfw->tx_stream) { conn = &oxfw->out_conn; c_dir = CMP_OUTPUT; diff --git a/sound/firewire/oxfw/oxfw.c b/sound/firewire/oxfw/oxfw.c index 84971d78d152..cb5b5e3a481b 100644 --- a/sound/firewire/oxfw/oxfw.c +++ b/sound/firewire/oxfw/oxfw.c @@ -159,8 +159,10 @@ static int detect_quirks(struct snd_oxfw *oxfw, const struct ieee1394_device_id return snd_oxfw_scs1x_add(oxfw); } - if (entry->vendor_id == OUI_APOGEE && entry->model_id == MODEL_DUET_FW) - oxfw->quirks |= SND_OXFW_QUIRK_BLOCKING_TRANSMISSION; + if (entry->vendor_id == OUI_APOGEE && entry->model_id == MODEL_DUET_FW) { + oxfw->quirks |= SND_OXFW_QUIRK_BLOCKING_TRANSMISSION | + SND_OXFW_QUIRK_IGNORE_NO_INFO_PACKET; + } /* * TASCAM FireOne has physical control and requires a pair of additional diff --git a/sound/firewire/oxfw/oxfw.h b/sound/firewire/oxfw/oxfw.h index ee47abcb0c90..c13034f6c2ca 100644 --- a/sound/firewire/oxfw/oxfw.h +++ b/sound/firewire/oxfw/oxfw.h @@ -42,6 +42,11 @@ enum snd_oxfw_quirk { SND_OXFW_QUIRK_BLOCKING_TRANSMISSION = 0x04, // Stanton SCS1.d and SCS1.m support unique transaction. SND_OXFW_QUIRK_SCS_TRANSACTION = 0x08, + // Apogee Duet FireWire ignores data blocks in packet with NO_INFO for audio data + // processing, while output level meter moves. Any value in syt field of packet takes + // the device to process audio data even if the value is invalid in a point of + // IEC 61883-1/6. + SND_OXFW_QUIRK_IGNORE_NO_INFO_PACKET = 0x10, }; /* This is an arbitrary number for convinience. */ diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c index e97d00585e8e..481d8f8d3396 100644 --- a/sound/pci/hda/hda_generic.c +++ b/sound/pci/hda/hda_generic.c @@ -3460,7 +3460,7 @@ static int cap_put_caller(struct snd_kcontrol *kcontrol, struct hda_gen_spec *spec = codec->spec; const struct hda_input_mux *imux; struct nid_path *path; - int i, adc_idx, err = 0; + int i, adc_idx, ret, err = 0; imux = &spec->input_mux; adc_idx = kcontrol->id.index; @@ -3470,9 +3470,13 @@ static int cap_put_caller(struct snd_kcontrol *kcontrol, if (!path || !path->ctls[type]) continue; kcontrol->private_value = path->ctls[type]; - err = func(kcontrol, ucontrol); - if (err < 0) + ret = func(kcontrol, ucontrol); + if (ret < 0) { + err = ret; break; + } + if (ret > 0) + err = 1; } mutex_unlock(&codec->control_mutex); if (err >= 0 && spec->cap_sync_hook) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 0322b289505e..0062c18b646a 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -883,10 +883,11 @@ static unsigned int azx_get_pos_skl(struct azx *chip, struct azx_dev *azx_dev) return azx_get_pos_posbuf(chip, azx_dev); } -static void azx_shutdown_chip(struct azx *chip) +static void __azx_shutdown_chip(struct azx *chip, bool skip_link_reset) { azx_stop_chip(chip); - azx_enter_link_reset(chip); + if (!skip_link_reset) + azx_enter_link_reset(chip); azx_clear_irq_pending(chip); display_power(chip, false); } @@ -895,6 +896,11 @@ static void azx_shutdown_chip(struct azx *chip) static DEFINE_MUTEX(card_list_lock); static LIST_HEAD(card_list); +static void azx_shutdown_chip(struct azx *chip) +{ + __azx_shutdown_chip(chip, false); +} + static void azx_add_card_list(struct azx *chip) { struct hda_intel *hda = container_of(chip, struct hda_intel, chip); @@ -2385,7 +2391,7 @@ static void azx_shutdown(struct pci_dev *pci) return; chip = card->private_data; if (chip && chip->running) - azx_shutdown_chip(chip); + __azx_shutdown_chip(chip, true); } /* PCI IDs */ diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a065260d0d20..96f32eaa24df 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8332,6 +8332,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0a2e, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a30, "Dell", ALC236_FIXUP_DELL_AIO_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0a58, "Dell", ALC255_FIXUP_DELL_HEADSET_MIC), + SND_PCI_QUIRK(0x1028, 0x0a61, "Dell XPS 15 9510", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index a5c1a2c4eae4..773a136161f1 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -1041,6 +1041,7 @@ static const struct hda_fixup via_fixups[] = { }; static const struct snd_pci_quirk vt2002p_fixups[] = { + SND_PCI_QUIRK(0x1043, 0x13f7, "Asus B23E", VIA_FIXUP_POWER_SAVE), SND_PCI_QUIRK(0x1043, 0x1487, "Asus G75", VIA_FIXUP_ASUS_G75), SND_PCI_QUIRK(0x1043, 0x8532, "Asus X202E", VIA_FIXUP_INTMIC_BOOST), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo", VIA_FIXUP_POWER_SAVE), diff --git a/tools/io_uring/io_uring-cp.c b/tools/io_uring/io_uring-cp.c index 81461813ec62..d9bd6f5f8f46 100644 --- a/tools/io_uring/io_uring-cp.c +++ b/tools/io_uring/io_uring-cp.c @@ -131,8 +131,7 @@ static int copy_file(struct io_uring *ring, off_t insize) writes = reads = offset = 0; while (insize || write_left) { - unsigned long had_reads; - int got_comp; + int had_reads, got_comp; /* * Queue up as many reads as we can @@ -174,8 +173,13 @@ static int copy_file(struct io_uring *ring, off_t insize) if (!got_comp) { ret = io_uring_wait_cqe(ring, &cqe); got_comp = 1; - } else + } else { ret = io_uring_peek_cqe(ring, &cqe); + if (ret == -EAGAIN) { + cqe = NULL; + ret = 0; + } + } if (ret < 0) { fprintf(stderr, "io_uring_peek_cqe: %s\n", strerror(-ret)); @@ -194,7 +198,7 @@ static int copy_file(struct io_uring *ring, off_t insize) fprintf(stderr, "cqe failed: %s\n", strerror(-cqe->res)); return 1; - } else if ((size_t) cqe->res != data->iov.iov_len) { + } else if (cqe->res != data->iov.iov_len) { /* Short read/write, adjust and requeue */ data->iov.iov_base += cqe->res; data->iov.iov_len -= cqe->res; @@ -221,6 +225,25 @@ static int copy_file(struct io_uring *ring, off_t insize) } } + /* wait out pending writes */ + while (writes) { + struct io_data *data; + + ret = io_uring_wait_cqe(ring, &cqe); + if (ret) { + fprintf(stderr, "wait_cqe=%d\n", ret); + return 1; + } + if (cqe->res < 0) { + fprintf(stderr, "write res=%d\n", cqe->res); + return 1; + } + data = io_uring_cqe_get_data(cqe); + free(data); + writes--; + io_uring_cqe_seen(ring, cqe); + } + return 0; } diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 54f367cbadae..b1bff5fb0f65 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -434,7 +434,7 @@ static int nd_intel_test_finish_query(struct nfit_test *t, dev_dbg(dev, "%s: transition out verify\n", __func__); fw->state = FW_STATE_UPDATED; fw->missed_activate = false; - /* fall through */ + fallthrough; case FW_STATE_UPDATED: nd_cmd->status = 0; /* bogus test version */ diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c index dee7a3d6c5a5..92bbc5a15c39 100644 --- a/tools/testing/selftests/sgx/sigstruct.c +++ b/tools/testing/selftests/sgx/sigstruct.c @@ -55,10 +55,27 @@ static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m, return true; } +static void reverse_bytes(void *data, int length) +{ + int i = 0; + int j = length - 1; + uint8_t temp; + uint8_t *ptr = data; + + while (i < j) { + temp = ptr[i]; + ptr[i] = ptr[j]; + ptr[j] = temp; + i++; + j--; + } +} + static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, uint8_t *q2) { struct q1q2_ctx ctx; + int len; if (!alloc_q1q2_ctx(s, m, &ctx)) { fprintf(stderr, "Not enough memory for Q1Q2 calculation\n"); @@ -89,8 +106,10 @@ static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1, goto out; } - BN_bn2bin(ctx.q1, q1); - BN_bn2bin(ctx.q2, q2); + len = BN_bn2bin(ctx.q1, q1); + reverse_bytes(q1, len); + len = BN_bn2bin(ctx.q2, q2); + reverse_bytes(q2, len); free_q1q2_ctx(&ctx); return true; @@ -152,22 +171,6 @@ static RSA *gen_sign_key(void) return key; } -static void reverse_bytes(void *data, int length) -{ - int i = 0; - int j = length - 1; - uint8_t temp; - uint8_t *ptr = data; - - while (i < j) { - temp = ptr[i]; - ptr[i] = ptr[j]; - ptr[j] = temp; - i++; - j--; - } -} - enum mrtags { MRECREATE = 0x0045544145524345, MREADD = 0x0000000044444145, @@ -367,8 +370,6 @@ bool encl_measure(struct encl *encl) /* BE -> LE */ reverse_bytes(sigstruct->signature, SGX_MODULUS_SIZE); reverse_bytes(sigstruct->modulus, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q1, SGX_MODULUS_SIZE); - reverse_bytes(sigstruct->q2, SGX_MODULUS_SIZE); EVP_MD_CTX_destroy(ctx); RSA_free(key); diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile index b587b9a7a124..0d7bbe49359d 100644 --- a/tools/virtio/Makefile +++ b/tools/virtio/Makefile @@ -4,7 +4,8 @@ test: virtio_test vringh_test virtio_test: virtio_ring.o virtio_test.o vringh_test: vringh_test.o vringh.o virtio_ring.o -CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h +CFLAGS += -g -O2 -Werror -Wno-maybe-uninitialized -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE -include ../../include/linux/kconfig.h +LDFLAGS += -lpthread vpath %.c ../../drivers/virtio ../../drivers/vhost mod: ${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V} diff --git a/tools/virtio/linux/spinlock.h b/tools/virtio/linux/spinlock.h new file mode 100644 index 000000000000..028e3cdcc5d3 --- /dev/null +++ b/tools/virtio/linux/spinlock.h @@ -0,0 +1,56 @@ +#ifndef SPINLOCK_H_STUB +#define SPINLOCK_H_STUB + +#include <pthread.h> + +typedef pthread_spinlock_t spinlock_t; + +static inline void spin_lock_init(spinlock_t *lock) +{ + int r = pthread_spin_init(lock, 0); + assert(!r); +} + +static inline void spin_lock(spinlock_t *lock) +{ + int ret = pthread_spin_lock(lock); + assert(!ret); +} + +static inline void spin_unlock(spinlock_t *lock) +{ + int ret = pthread_spin_unlock(lock); + assert(!ret); +} + +static inline void spin_lock_bh(spinlock_t *lock) +{ + spin_lock(lock); +} + +static inline void spin_unlock_bh(spinlock_t *lock) +{ + spin_unlock(lock); +} + +static inline void spin_lock_irq(spinlock_t *lock) +{ + spin_lock(lock); +} + +static inline void spin_unlock_irq(spinlock_t *lock) +{ + spin_unlock(lock); +} + +static inline void spin_lock_irqsave(spinlock_t *lock, unsigned long f) +{ + spin_lock(lock); +} + +static inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long f) +{ + spin_unlock(lock); +} + +#endif diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index 5d90254ddae4..363b98228301 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -3,6 +3,7 @@ #define LINUX_VIRTIO_H #include <linux/scatterlist.h> #include <linux/kernel.h> +#include <linux/spinlock.h> struct device { void *parent; @@ -12,6 +13,7 @@ struct virtio_device { struct device dev; u64 features; struct list_head vqs; + spinlock_t vqs_list_lock; }; struct virtqueue { |