diff options
92 files changed, 680 insertions, 419 deletions
diff --git a/Documentation/devicetree/bindings/spi/spi-mux.yaml b/Documentation/devicetree/bindings/spi/spi-mux.yaml index d09c6355e22d..51c7622dc20b 100644 --- a/Documentation/devicetree/bindings/spi/spi-mux.yaml +++ b/Documentation/devicetree/bindings/spi/spi-mux.yaml @@ -72,7 +72,7 @@ examples: mux-controls = <&mux>; - spi-flash@0 { + flash@0 { compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <40000000>; diff --git a/Documentation/powerpc/syscall64-abi.rst b/Documentation/powerpc/syscall64-abi.rst index dabee3729e5a..56490c4c0c07 100644 --- a/Documentation/powerpc/syscall64-abi.rst +++ b/Documentation/powerpc/syscall64-abi.rst @@ -109,6 +109,16 @@ auxiliary vector. scv 0 syscalls will always behave as PPC_FEATURE2_HTM_NOSC. +ptrace +------ +When ptracing system calls (PTRACE_SYSCALL), the pt_regs.trap value contains +the system call type that can be used to distinguish between sc and scv 0 +system calls, and the different register conventions can be accounted for. + +If the value of (pt_regs.trap & 0xfff0) is 0xc00 then the system call was +performed with the sc instruction, if it is 0x3000 then the system call was +performed with the scv 0 instruction. + vsyscall ======== diff --git a/MAINTAINERS b/MAINTAINERS index def1640cc294..04babfa8fc76 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14735,7 +14735,6 @@ W: https://wireless.wiki.kernel.org/en/users/Drivers/p54 F: drivers/net/wireless/intersil/prism54/ PROC FILESYSTEM -R: Alexey Dobriyan <adobriyan@gmail.com> L: linux-kernel@vger.kernel.org L: linux-fsdevel@vger.kernel.org S: Maintained @@ -17305,6 +17304,12 @@ L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-stm32* +ST STM32 SPI DRIVER +M: Alain Volmat <alain.volmat@foss.st.com> +L: linux-spi@vger.kernel.org +S: Maintained +F: drivers/spi/spi-stm32.c + ST STPDDC60 DRIVER M: Daniel Nilsson <daniel.nilsson@flex.com> L: linux-hwmon@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc2 +EXTRAVERSION = -rc3 NAME = Frozen Wasteland # *DOCUMENTATION* diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c index ec0d9b094744..bddfc7cd5d40 100644 --- a/arch/arm/mach-pxa/pxa_cplds_irqs.c +++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c @@ -121,8 +121,13 @@ static int cplds_probe(struct platform_device *pdev) return fpga->irq; base_irq = platform_get_irq(pdev, 1); - if (base_irq < 0) + if (base_irq < 0) { base_irq = 0; + } else { + ret = devm_irq_alloc_descs(&pdev->dev, base_irq, base_irq, CPLDS_NB_IRQ, 0); + if (ret < 0) + return ret; + } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); fpga->base = devm_ioremap_resource(&pdev->dev, res); diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h index 9c9ab2746168..b476a685f066 100644 --- a/arch/powerpc/include/asm/ptrace.h +++ b/arch/powerpc/include/asm/ptrace.h @@ -19,6 +19,7 @@ #ifndef _ASM_POWERPC_PTRACE_H #define _ASM_POWERPC_PTRACE_H +#include <linux/err.h> #include <uapi/asm/ptrace.h> #include <asm/asm-const.h> @@ -152,25 +153,6 @@ extern unsigned long profile_pc(struct pt_regs *regs); long do_syscall_trace_enter(struct pt_regs *regs); void do_syscall_trace_leave(struct pt_regs *regs); -#define kernel_stack_pointer(regs) ((regs)->gpr[1]) -static inline int is_syscall_success(struct pt_regs *regs) -{ - return !(regs->ccr & 0x10000000); -} - -static inline long regs_return_value(struct pt_regs *regs) -{ - if (is_syscall_success(regs)) - return regs->gpr[3]; - else - return -regs->gpr[3]; -} - -static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) -{ - regs->gpr[3] = rc; -} - #ifdef __powerpc64__ #define user_mode(regs) ((((regs)->msr) >> MSR_PR_LG) & 0x1) #else @@ -235,6 +217,31 @@ static __always_inline void set_trap_norestart(struct pt_regs *regs) regs->trap |= 0x1; } +#define kernel_stack_pointer(regs) ((regs)->gpr[1]) +static inline int is_syscall_success(struct pt_regs *regs) +{ + if (trap_is_scv(regs)) + return !IS_ERR_VALUE((unsigned long)regs->gpr[3]); + else + return !(regs->ccr & 0x10000000); +} + +static inline long regs_return_value(struct pt_regs *regs) +{ + if (trap_is_scv(regs)) + return regs->gpr[3]; + + if (is_syscall_success(regs)) + return regs->gpr[3]; + else + return -regs->gpr[3]; +} + +static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +{ + regs->gpr[3] = rc; +} + #define arch_has_single_step() (1) #define arch_has_block_step() (true) #define ARCH_HAS_USER_SINGLE_STEP_REPORT diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h index fd1b518eed17..ba0f88f3a30d 100644 --- a/arch/powerpc/include/asm/syscall.h +++ b/arch/powerpc/include/asm/syscall.h @@ -41,11 +41,17 @@ static inline void syscall_rollback(struct task_struct *task, static inline long syscall_get_error(struct task_struct *task, struct pt_regs *regs) { - /* - * If the system call failed, - * regs->gpr[3] contains a positive ERRORCODE. - */ - return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0; + if (trap_is_scv(regs)) { + unsigned long error = regs->gpr[3]; + + return IS_ERR_VALUE(error) ? error : 0; + } else { + /* + * If the system call failed, + * regs->gpr[3] contains a positive ERRORCODE. + */ + return (regs->ccr & 0x10000000UL) ? -regs->gpr[3] : 0; + } } static inline long syscall_get_return_value(struct task_struct *task, @@ -58,18 +64,22 @@ static inline void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs, int error, long val) { - /* - * In the general case it's not obvious that we must deal with CCR - * here, as the syscall exit path will also do that for us. However - * there are some places, eg. the signal code, which check ccr to - * decide if the value in r3 is actually an error. - */ - if (error) { - regs->ccr |= 0x10000000L; - regs->gpr[3] = error; + if (trap_is_scv(regs)) { + regs->gpr[3] = (long) error ?: val; } else { - regs->ccr &= ~0x10000000L; - regs->gpr[3] = val; + /* + * In the general case it's not obvious that we must deal with + * CCR here, as the syscall exit path will also do that for us. + * However there are some places, eg. the signal code, which + * check ccr to decide if the value in r3 is actually an error. + */ + if (error) { + regs->ccr |= 0x10000000L; + regs->gpr[3] = error; + } else { + regs->ccr &= ~0x10000000L; + regs->gpr[3] = val; + } } } diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index b779d25761cf..e42b85e4f1aa 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -369,11 +369,11 @@ void __init early_setup(unsigned long dt_ptr) apply_feature_fixups(); setup_feature_keys(); - early_ioremap_setup(); - /* Initialize the hash table or TLB handling */ early_init_mmu(); + early_ioremap_setup(); + /* * After firmware and early platform setup code has set things up, * we note the SPR values for configurable control/performance diff --git a/arch/x86/Makefile b/arch/x86/Makefile index c77c5d8a7b3e..307529417021 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -178,11 +178,6 @@ ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,) endif -ifdef CONFIG_LTO_CLANG -KBUILD_LDFLAGS += -plugin-opt=-code-model=kernel \ - -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8) -endif - # Workaround for a gcc prelease that unfortunately was shipped in a suse release KBUILD_CFLAGS += -Wno-sign-compare # @@ -202,7 +197,12 @@ ifdef CONFIG_RETPOLINE endif endif -KBUILD_LDFLAGS := -m elf_$(UTS_MACHINE) +KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE) + +ifdef CONFIG_LTO_CLANG +KBUILD_LDFLAGS += -plugin-opt=-code-model=kernel \ + -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8) +endif ifdef CONFIG_X86_NEED_RELOCS LDFLAGS_vmlinux := --emit-relocs --discard-none diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 8e509325c2c3..8f71dd72ef95 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -396,10 +396,12 @@ int x86_reserve_hardware(void) if (!atomic_inc_not_zero(&pmc_refcount)) { mutex_lock(&pmc_reserve_mutex); if (atomic_read(&pmc_refcount) == 0) { - if (!reserve_pmc_hardware()) + if (!reserve_pmc_hardware()) { err = -EBUSY; - else + } else { reserve_ds_buffers(); + reserve_lbr_buffers(); + } } if (!err) atomic_inc(&pmc_refcount); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2521d03de5e0..e28892270c58 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6253,7 +6253,7 @@ __init int intel_pmu_init(void) * Check all LBT MSR here. * Disable LBR access if any LBR MSRs can not be accessed. */ - if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL)) + if (x86_pmu.lbr_tos && !check_msr(x86_pmu.lbr_tos, 0x3UL)) x86_pmu.lbr_nr = 0; for (i = 0; i < x86_pmu.lbr_nr; i++) { if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) && diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 76dbab6ac9fb..4409d2cccfda 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -658,7 +658,6 @@ static inline bool branch_user_callstack(unsigned br_sel) void intel_pmu_lbr_add(struct perf_event *event) { - struct kmem_cache *kmem_cache = event->pmu->task_ctx_cache; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (!x86_pmu.lbr_nr) @@ -696,11 +695,6 @@ void intel_pmu_lbr_add(struct perf_event *event) perf_sched_cb_inc(event->ctx->pmu); if (!cpuc->lbr_users++ && !event->total_time_running) intel_pmu_lbr_reset(); - - if (static_cpu_has(X86_FEATURE_ARCH_LBR) && - kmem_cache && !cpuc->lbr_xsave && - (cpuc->lbr_users != cpuc->lbr_pebs_users)) - cpuc->lbr_xsave = kmem_cache_alloc(kmem_cache, GFP_KERNEL); } void release_lbr_buffers(void) @@ -722,6 +716,26 @@ void release_lbr_buffers(void) } } +void reserve_lbr_buffers(void) +{ + struct kmem_cache *kmem_cache; + struct cpu_hw_events *cpuc; + int cpu; + + if (!static_cpu_has(X86_FEATURE_ARCH_LBR)) + return; + + for_each_possible_cpu(cpu) { + cpuc = per_cpu_ptr(&cpu_hw_events, cpu); + kmem_cache = x86_get_pmu(cpu)->task_ctx_cache; + if (!kmem_cache || cpuc->lbr_xsave) + continue; + + cpuc->lbr_xsave = kmem_cache_alloc_node(kmem_cache, GFP_KERNEL, + cpu_to_node(cpu)); + } +} + void intel_pmu_lbr_del(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 27fa85e7d4fd..ad87cb36f7c8 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1244,6 +1244,8 @@ void reserve_ds_buffers(void); void release_lbr_buffers(void); +void reserve_lbr_buffers(void); + extern struct event_constraint bts_constraint; extern struct event_constraint vlbr_constraint; @@ -1393,6 +1395,10 @@ static inline void release_lbr_buffers(void) { } +static inline void reserve_lbr_buffers(void) +{ +} + static inline int intel_pmu_init(void) { return 0; diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 6ec8b3bfd76e..9f90f460a28c 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -63,6 +63,7 @@ static bool sev_es_negotiate_protocol(void) static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb) { + ghcb->save.sw_exit_code = 0; memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 9578c82832aa..651b81cd648e 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -203,8 +203,18 @@ static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state) if (unlikely(data->ghcb_active)) { /* GHCB is already in use - save its contents */ - if (unlikely(data->backup_ghcb_active)) - return NULL; + if (unlikely(data->backup_ghcb_active)) { + /* + * Backup-GHCB is also already in use. There is no way + * to continue here so just kill the machine. To make + * panic() work, mark GHCBs inactive so that messages + * can be printed out. + */ + data->ghcb_active = false; + data->backup_ghcb_active = false; + + panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use"); + } /* Mark backup_ghcb active before writing to it */ data->backup_ghcb_active = true; @@ -221,24 +231,6 @@ static __always_inline struct ghcb *sev_es_get_ghcb(struct ghcb_state *state) return ghcb; } -static __always_inline void sev_es_put_ghcb(struct ghcb_state *state) -{ - struct sev_es_runtime_data *data; - struct ghcb *ghcb; - - data = this_cpu_read(runtime_data); - ghcb = &data->ghcb_page; - - if (state->ghcb) { - /* Restore GHCB from Backup */ - *ghcb = *state->ghcb; - data->backup_ghcb_active = false; - state->ghcb = NULL; - } else { - data->ghcb_active = false; - } -} - /* Needed in vc_early_forward_exception */ void do_early_exception(struct pt_regs *regs, int trapnr); @@ -323,31 +315,44 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; - /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ - if (!user_mode(ctxt->regs) && !access_ok(target, size)) { - memcpy(dst, buf, size); - return ES_OK; - } - + /* + * This function uses __put_user() independent of whether kernel or user + * memory is accessed. This works fine because __put_user() does no + * sanity checks of the pointer being accessed. All that it does is + * to report when the access failed. + * + * Also, this function runs in atomic context, so __put_user() is not + * allowed to sleep. The page-fault handler detects that it is running + * in atomic context and will not try to take mmap_sem and handle the + * fault, so additional pagefault_enable()/disable() calls are not + * needed. + * + * The access can't be done via copy_to_user() here because + * vc_write_mem() must not use string instructions to access unsafe + * memory. The reason is that MOVS is emulated by the #VC handler by + * splitting the move up into a read and a write and taking a nested #VC + * exception on whatever of them is the MMIO access. Using string + * instructions here would cause infinite nesting. + */ switch (size) { case 1: memcpy(&d1, buf, 1); - if (put_user(d1, target)) + if (__put_user(d1, target)) goto fault; break; case 2: memcpy(&d2, buf, 2); - if (put_user(d2, target)) + if (__put_user(d2, target)) goto fault; break; case 4: memcpy(&d4, buf, 4); - if (put_user(d4, target)) + if (__put_user(d4, target)) goto fault; break; case 8: memcpy(&d8, buf, 8); - if (put_user(d8, target)) + if (__put_user(d8, target)) goto fault; break; default: @@ -378,30 +383,43 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; - /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ - if (!user_mode(ctxt->regs) && !access_ok(s, size)) { - memcpy(buf, src, size); - return ES_OK; - } - + /* + * This function uses __get_user() independent of whether kernel or user + * memory is accessed. This works fine because __get_user() does no + * sanity checks of the pointer being accessed. All that it does is + * to report when the access failed. + * + * Also, this function runs in atomic context, so __get_user() is not + * allowed to sleep. The page-fault handler detects that it is running + * in atomic context and will not try to take mmap_sem and handle the + * fault, so additional pagefault_enable()/disable() calls are not + * needed. + * + * The access can't be done via copy_from_user() here because + * vc_read_mem() must not use string instructions to access unsafe + * memory. The reason is that MOVS is emulated by the #VC handler by + * splitting the move up into a read and a write and taking a nested #VC + * exception on whatever of them is the MMIO access. Using string + * instructions here would cause infinite nesting. + */ switch (size) { case 1: - if (get_user(d1, s)) + if (__get_user(d1, s)) goto fault; memcpy(buf, &d1, 1); break; case 2: - if (get_user(d2, s)) + if (__get_user(d2, s)) goto fault; memcpy(buf, &d2, 2); break; case 4: - if (get_user(d4, s)) + if (__get_user(d4, s)) goto fault; memcpy(buf, &d4, 4); break; case 8: - if (get_user(d8, s)) + if (__get_user(d8, s)) goto fault; memcpy(buf, &d8, 8); break; @@ -461,6 +479,29 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt /* Include code shared with pre-decompression boot stage */ #include "sev-shared.c" +static __always_inline void sev_es_put_ghcb(struct ghcb_state *state) +{ + struct sev_es_runtime_data *data; + struct ghcb *ghcb; + + data = this_cpu_read(runtime_data); + ghcb = &data->ghcb_page; + + if (state->ghcb) { + /* Restore GHCB from Backup */ + *ghcb = *state->ghcb; + data->backup_ghcb_active = false; + state->ghcb = NULL; + } else { + /* + * Invalidate the GHCB so a VMGEXIT instruction issued + * from userspace won't appear to be valid. + */ + vc_ghcb_invalidate(ghcb); + data->ghcb_active = false; + } +} + void noinstr __sev_es_nmi_complete(void) { struct ghcb_state state; @@ -1255,6 +1296,10 @@ static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt) case X86_TRAP_UD: exc_invalid_op(ctxt->regs); break; + case X86_TRAP_PF: + write_cr2(ctxt->fi.cr2); + exc_page_fault(ctxt->regs, error_code); + break; case X86_TRAP_AC: exc_alignment_check(ctxt->regs, error_code); break; @@ -1284,7 +1329,6 @@ static __always_inline bool on_vc_fallback_stack(struct pt_regs *regs) */ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) { - struct sev_es_runtime_data *data = this_cpu_read(runtime_data); irqentry_state_t irq_state; struct ghcb_state state; struct es_em_ctxt ctxt; @@ -1310,16 +1354,6 @@ DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication) */ ghcb = sev_es_get_ghcb(&state); - if (!ghcb) { - /* - * Mark GHCBs inactive so that panic() is able to print the - * message. - */ - data->ghcb_active = false; - data->backup_ghcb_active = false; - - panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use"); - } vc_ghcb_invalidate(ghcb); result = vc_init_em_ctxt(&ctxt, regs, error_code); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 17503fed2017..e87699aa2dc8 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1273,16 +1273,16 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Get mfn list */ xen_build_dynamic_phys_to_machine(); + /* Work out if we support NX */ + get_cpu_cap(&boot_cpu_data); + x86_configure_nx(); + /* * Set up kernel GDT and segment registers, mainly so that * -fstack-protector code can be executed. */ xen_setup_gdt(0); - /* Work out if we support NX */ - get_cpu_cap(&boot_cpu_data); - x86_configure_nx(); - /* Determine virtual and physical address sizes */ get_cpu_address_sizes(&boot_cpu_data); diff --git a/block/genhd.c b/block/genhd.c index 39ca97b0edc6..9f8cb7beaad1 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -29,8 +29,6 @@ static struct kobject *block_depr; -DECLARE_RWSEM(bdev_lookup_sem); - /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) static DEFINE_IDA(ext_devt_ida); @@ -609,13 +607,8 @@ void del_gendisk(struct gendisk *disk) blk_integrity_del(disk); disk_del_events(disk); - /* - * Block lookups of the disk until all bdevs are unhashed and the - * disk is marked as dead (GENHD_FL_UP cleared). - */ - down_write(&bdev_lookup_sem); - mutex_lock(&disk->part0->bd_mutex); + disk->flags &= ~GENHD_FL_UP; blk_drop_partitions(disk); mutex_unlock(&disk->part0->bd_mutex); @@ -629,8 +622,6 @@ void del_gendisk(struct gendisk *disk) remove_inode_hash(disk->part0->bd_inode); set_capacity(disk, 0); - disk->flags &= ~GENHD_FL_UP; - up_write(&bdev_lookup_sem); if (!(disk->flags & GENHD_FL_HIDDEN)) { sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi"); diff --git a/drivers/gpio/gpio-cadence.c b/drivers/gpio/gpio-cadence.c index a4d3239d2594..4ab3fcd9b9ba 100644 --- a/drivers/gpio/gpio-cadence.c +++ b/drivers/gpio/gpio-cadence.c @@ -278,6 +278,7 @@ static const struct of_device_id cdns_of_ids[] = { { .compatible = "cdns,gpio-r1p02" }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, cdns_of_ids); static struct platform_driver cdns_gpio_driver = { .driver = { diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index 1bd9e44df718..05974b760796 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -444,16 +444,6 @@ static int tegra186_irq_set_wake(struct irq_data *data, unsigned int on) return 0; } -static int tegra186_irq_set_affinity(struct irq_data *data, - const struct cpumask *dest, - bool force) -{ - if (data->parent_data) - return irq_chip_set_affinity_parent(data, dest, force); - - return -EINVAL; -} - static void tegra186_gpio_irq(struct irq_desc *desc) { struct tegra_gpio *gpio = irq_desc_get_handler_data(desc); @@ -700,7 +690,6 @@ static int tegra186_gpio_probe(struct platform_device *pdev) gpio->intc.irq_unmask = tegra186_irq_unmask; gpio->intc.irq_set_type = tegra186_irq_set_type; gpio->intc.irq_set_wake = tegra186_irq_set_wake; - gpio->intc.irq_set_affinity = tegra186_irq_set_affinity; irq = &gpio->gpio.irq; irq->chip = &gpio->intc; diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c index b411d3156e0b..136557e7dd3c 100644 --- a/drivers/gpio/gpio-xilinx.c +++ b/drivers/gpio/gpio-xilinx.c @@ -542,7 +542,7 @@ static void xgpio_irqhandler(struct irq_desc *desc) } /** - * xgpio_of_probe - Probe method for the GPIO device. + * xgpio_probe - Probe method for the GPIO device. * @pdev: pointer to the platform device * * Return: diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig index b90e825df7e1..62543a4eccc0 100644 --- a/drivers/irqchip/Kconfig +++ b/drivers/irqchip/Kconfig @@ -596,7 +596,7 @@ config IRQ_IDT3243X config APPLE_AIC bool "Apple Interrupt Controller (AIC)" depends on ARM64 - default ARCH_APPLE + depends on ARCH_APPLE || COMPILE_TEST help Support for the Apple Interrupt Controller found on Apple Silicon SoCs, such as the M1. diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c index 91adf771f185..090bc3f4f7d8 100644 --- a/drivers/irqchip/irq-mvebu-icu.c +++ b/drivers/irqchip/irq-mvebu-icu.c @@ -359,10 +359,8 @@ static int mvebu_icu_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); icu->base = devm_ioremap_resource(&pdev->dev, res); - if (IS_ERR(icu->base)) { - dev_err(&pdev->dev, "Failed to map icu base address.\n"); + if (IS_ERR(icu->base)) return PTR_ERR(icu->base); - } /* * Legacy bindings: ICU is one node with one MSI parent: force manually diff --git a/drivers/irqchip/irq-mvebu-sei.c b/drivers/irqchip/irq-mvebu-sei.c index 18832ccc8ff8..3a7b7a7f20ca 100644 --- a/drivers/irqchip/irq-mvebu-sei.c +++ b/drivers/irqchip/irq-mvebu-sei.c @@ -384,10 +384,8 @@ static int mvebu_sei_probe(struct platform_device *pdev) sei->res = platform_get_resource(pdev, IORESOURCE_MEM, 0); sei->base = devm_ioremap_resource(sei->dev, sei->res); - if (IS_ERR(sei->base)) { - dev_err(sei->dev, "Failed to remap SEI resource\n"); + if (IS_ERR(sei->base)) return PTR_ERR(sei->base); - } /* Retrieve the SEI capabilities with the interrupt ranges */ sei->caps = of_device_get_match_data(&pdev->dev); diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index b9db90c4aa56..4704f2ee5797 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -892,10 +892,8 @@ static int stm32_exti_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, 0); host_data->base = devm_ioremap_resource(dev, res); - if (IS_ERR(host_data->base)) { - dev_err(dev, "Unable to map registers\n"); + if (IS_ERR(host_data->base)) return PTR_ERR(host_data->base); - } for (i = 0; i < drv_data->bank_nr; i++) stm32_exti_chip_init(host_data, i, np); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index d9ab9e7871d0..256e87721a01 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2461,6 +2461,18 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved) static void __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues) { + int q; + + /* + * if aborting io, the queues are no longer good, mark them + * all as not live. + */ + if (ctrl->ctrl.queue_count > 1) { + for (q = 1; q < ctrl->ctrl.queue_count; q++) + clear_bit(NVME_FC_Q_LIVE, &ctrl->queues[q].flags); + } + clear_bit(NVME_FC_Q_LIVE, &ctrl->queues[0].flags); + /* * If io queues are present, stop them and terminate all outstanding * ios on them. As FC allocates FC exchange for each io, the diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 0222e23f5936..34f4b3402f7c 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -943,7 +943,6 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) if (ret <= 0) return ret; - nvme_tcp_advance_req(req, ret); if (queue->data_digest) nvme_tcp_ddgst_update(queue->snd_hash, page, offset, ret); @@ -960,6 +959,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) } return 1; } + nvme_tcp_advance_req(req, ret); } return -EAGAIN; } @@ -1140,7 +1140,8 @@ static void nvme_tcp_io_work(struct work_struct *w) pending = true; else if (unlikely(result < 0)) break; - } + } else + pending = !llist_empty(&queue->req_list); result = nvme_tcp_try_recv(queue); if (result > 0) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 25cc2ee8de3f..1853db38b682 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1372,7 +1372,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, goto out_free_changed_ns_list; if (subsys->cntlid_min > subsys->cntlid_max) - goto out_free_changed_ns_list; + goto out_free_sqs; ret = ida_simple_get(&cntlid_ida, subsys->cntlid_min, subsys->cntlid_max, diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 74b3b150e1a5..cb30cb942e1d 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -590,8 +590,10 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev, ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops, 0 /* no quirks, we're perfect! */); - if (ret) + if (ret) { + kfree(ctrl); goto out; + } if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) WARN_ON_ONCE(1); diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 8b161ec4943b..f4481fe48bf0 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -65,7 +65,7 @@ config SPI_ALTERA This is the driver for the Altera SPI Controller. config SPI_ALTERA_CORE - tristate "Altera SPI Controller core code" + tristate "Altera SPI Controller core code" if COMPILE_TEST select REGMAP help "The core code for the Altera SPI Controller" diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 028736687488..fb45e6af6638 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -1375,11 +1375,13 @@ poll_mode: ret = spi_register_controller(ctlr); if (ret != 0) { dev_err(&pdev->dev, "Problem registering DSPI ctlr\n"); - goto out_free_irq; + goto out_release_dma; } return ret; +out_release_dma: + dspi_release_dma(dspi); out_free_irq: if (dspi->irq) free_irq(dspi->irq, dspi); diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c index 297c512069a5..5d27ee482237 100644 --- a/drivers/spi/spi-sc18is602.c +++ b/drivers/spi/spi-sc18is602.c @@ -174,7 +174,7 @@ static int sc18is602_setup_transfer(struct sc18is602 *hw, u32 hz, u8 mode) static int sc18is602_check_transfer(struct spi_device *spi, struct spi_transfer *t, int tlen) { - if (t && t->len + tlen > SC18IS602_BUFSIZ) + if (t && t->len + tlen > SC18IS602_BUFSIZ + 1) return -EINVAL; return 0; @@ -219,6 +219,11 @@ static int sc18is602_transfer_one(struct spi_master *master, return status; } +static size_t sc18is602_max_transfer_size(struct spi_device *spi) +{ + return SC18IS602_BUFSIZ; +} + static int sc18is602_setup(struct spi_device *spi) { struct sc18is602 *hw = spi_master_get_devdata(spi->master); @@ -293,6 +298,8 @@ static int sc18is602_probe(struct i2c_client *client, master->bits_per_word_mask = SPI_BPW_MASK(8); master->setup = sc18is602_setup; master->transfer_one_message = sc18is602_transfer_one; + master->max_transfer_size = sc18is602_max_transfer_size; + master->max_message_size = sc18is602_max_transfer_size; master->dev.of_node = np; master->min_speed_hz = hw->freq / 128; master->max_speed_hz = hw->freq / 4; diff --git a/drivers/spi/spi-sprd.c b/drivers/spi/spi-sprd.c index b41a75749b49..28e70db9bbba 100644 --- a/drivers/spi/spi-sprd.c +++ b/drivers/spi/spi-sprd.c @@ -1068,6 +1068,7 @@ static const struct of_device_id sprd_spi_of_match[] = { { .compatible = "sprd,sc9860-spi", }, { /* sentinel */ } }; +MODULE_DEVICE_TABLE(of, sprd_spi_of_match); static struct platform_driver sprd_spi_driver = { .driver = { diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index 5d8a5ee62fa2..5a3d81c31d04 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -367,7 +367,7 @@ static int zynq_qspi_config_op(struct zynq_qspi *xqspi, struct spi_device *spi) } /** - * zynq_qspi_setup - Configure the QSPI controller + * zynq_qspi_setup_op - Configure the QSPI controller * @spi: Pointer to the spi_device structure * * Sets the operational mode of QSPI controller for the next QSPI transfer, baud @@ -528,18 +528,17 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem, struct zynq_qspi *xqspi = spi_controller_get_devdata(mem->spi->master); int err = 0, i; u8 *tmpbuf; - u8 opcode = op->cmd.opcode; dev_dbg(xqspi->dev, "cmd:%#x mode:%d.%d.%d.%d\n", - opcode, op->cmd.buswidth, op->addr.buswidth, + op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth, op->dummy.buswidth, op->data.buswidth); zynq_qspi_chipselect(mem->spi, true); zynq_qspi_config_op(xqspi, mem->spi); - if (op->cmd.nbytes) { + if (op->cmd.opcode) { reinit_completion(&xqspi->data_completion); - xqspi->txbuf = &opcode; + xqspi->txbuf = (u8 *)&op->cmd.opcode; xqspi->rxbuf = NULL; xqspi->tx_bytes = op->cmd.nbytes; xqspi->rx_bytes = op->cmd.nbytes; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ba425b9c7700..e353b7a9e54e 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -47,10 +47,6 @@ static void spidev_release(struct device *dev) { struct spi_device *spi = to_spi_device(dev); - /* spi controllers may cleanup for released devices */ - if (spi->controller->cleanup) - spi->controller->cleanup(spi); - spi_controller_put(spi->controller); kfree(spi->driver_override); kfree(spi); @@ -558,6 +554,12 @@ static int spi_dev_check(struct device *dev, void *data) return 0; } +static void spi_cleanup(struct spi_device *spi) +{ + if (spi->controller->cleanup) + spi->controller->cleanup(spi); +} + /** * spi_add_device - Add spi_device allocated with spi_alloc_device * @spi: spi_device to register @@ -622,11 +624,13 @@ int spi_add_device(struct spi_device *spi) /* Device may be bound to an active driver when this returns */ status = device_add(&spi->dev); - if (status < 0) + if (status < 0) { dev_err(dev, "can't add %s, status %d\n", dev_name(&spi->dev), status); - else + spi_cleanup(spi); + } else { dev_dbg(dev, "registered child %s\n", dev_name(&spi->dev)); + } done: mutex_unlock(&spi_add_lock); @@ -717,7 +721,9 @@ void spi_unregister_device(struct spi_device *spi) if (ACPI_COMPANION(&spi->dev)) acpi_device_clear_enumerated(ACPI_COMPANION(&spi->dev)); device_remove_software_node(&spi->dev); - device_unregister(&spi->dev); + device_del(&spi->dev); + spi_cleanup(spi); + put_device(&spi->dev); } EXPORT_SYMBOL_GPL(spi_unregister_device); @@ -814,15 +820,29 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force) if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio)) { if (!(spi->mode & SPI_NO_CS)) { - if (spi->cs_gpiod) - /* polarity handled by gpiolib */ - gpiod_set_value_cansleep(spi->cs_gpiod, activate); - else + if (spi->cs_gpiod) { + /* + * Historically ACPI has no means of the GPIO polarity and + * thus the SPISerialBus() resource defines it on the per-chip + * basis. In order to avoid a chain of negations, the GPIO + * polarity is considered being Active High. Even for the cases + * when _DSD() is involved (in the updated versions of ACPI) + * the GPIO CS polarity must be defined Active High to avoid + * ambiguity. That's why we use enable, that takes SPI_CS_HIGH + * into account. + */ + if (has_acpi_companion(&spi->dev)) + gpiod_set_value_cansleep(spi->cs_gpiod, !enable); + else + /* Polarity handled by GPIO library */ + gpiod_set_value_cansleep(spi->cs_gpiod, activate); + } else { /* * invert the enable line, as active low is * default for SPI. */ gpio_set_value_cansleep(spi->cs_gpio, !enable); + } } /* Some SPI masters need both GPIO CS & slave_select */ if ((spi->controller->flags & SPI_MASTER_GPIO_SS) && @@ -3451,9 +3471,12 @@ int spi_set_cs_timing(struct spi_device *spi, struct spi_delay *setup, if (spi->controller->set_cs_timing && !(spi->cs_gpiod || gpio_is_valid(spi->cs_gpio))) { + mutex_lock(&spi->controller->io_mutex); + if (spi->controller->auto_runtime_pm) { status = pm_runtime_get_sync(parent); if (status < 0) { + mutex_unlock(&spi->controller->io_mutex); pm_runtime_put_noidle(parent); dev_err(&spi->controller->dev, "Failed to power device: %d\n", status); @@ -3464,11 +3487,13 @@ int spi_set_cs_timing(struct spi_device *spi, struct spi_delay *setup, hold, inactive); pm_runtime_mark_last_busy(parent); pm_runtime_put_autosuspend(parent); - return status; } else { - return spi->controller->set_cs_timing(spi, setup, hold, + status = spi->controller->set_cs_timing(spi, setup, hold, inactive); } + + mutex_unlock(&spi->controller->io_mutex); + return status; } if ((setup && setup->unit == SPI_DELAY_UNIT_SCK) || diff --git a/drivers/xen/xen-pciback/vpci.c b/drivers/xen/xen-pciback/vpci.c index 4162d0e7e00d..cc7450f2b2a9 100644 --- a/drivers/xen/xen-pciback/vpci.c +++ b/drivers/xen/xen-pciback/vpci.c @@ -70,7 +70,7 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, struct pci_dev *dev, int devid, publish_pci_dev_cb publish_cb) { - int err = 0, slot, func = -1; + int err = 0, slot, func = PCI_FUNC(dev->devfn); struct pci_dev_entry *t, *dev_entry; struct vpci_dev_data *vpci_dev = pdev->pci_dev_data; @@ -95,22 +95,25 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, /* * Keep multi-function devices together on the virtual PCI bus, except - * virtual functions. + * that we want to keep virtual functions at func 0 on their own. They + * aren't multi-function devices and hence their presence at func 0 + * may cause guests to not scan the other functions. */ - if (!dev->is_virtfn) { + if (!dev->is_virtfn || func) { for (slot = 0; slot < PCI_SLOT_MAX; slot++) { if (list_empty(&vpci_dev->dev_list[slot])) continue; t = list_entry(list_first(&vpci_dev->dev_list[slot]), struct pci_dev_entry, list); + if (t->dev->is_virtfn && !PCI_FUNC(t->dev->devfn)) + continue; if (match_slot(dev, t->dev)) { dev_info(&dev->dev, "vpci: assign to virtual slot %d func %d\n", - slot, PCI_FUNC(dev->devfn)); + slot, func); list_add_tail(&dev_entry->list, &vpci_dev->dev_list[slot]); - func = PCI_FUNC(dev->devfn); goto unlock; } } @@ -123,7 +126,6 @@ static int __xen_pcibk_add_pci_dev(struct xen_pcibk_device *pdev, slot); list_add_tail(&dev_entry->list, &vpci_dev->dev_list[slot]); - func = dev->is_virtfn ? 0 : PCI_FUNC(dev->devfn); goto unlock; } } diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 5188f02e75fb..c09c7ebd6968 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -359,7 +359,8 @@ out: return err; } -static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev) +static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev, + enum xenbus_state state) { int err = 0; int num_devs; @@ -373,9 +374,7 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev) dev_dbg(&pdev->xdev->dev, "Reconfiguring device ...\n"); mutex_lock(&pdev->dev_lock); - /* Make sure we only reconfigure once */ - if (xenbus_read_driver_state(pdev->xdev->nodename) != - XenbusStateReconfiguring) + if (xenbus_read_driver_state(pdev->xdev->nodename) != state) goto out; err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, "num_devs", "%d", @@ -500,6 +499,10 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev) } } + if (state != XenbusStateReconfiguring) + /* Make sure we only reconfigure once. */ + goto out; + err = xenbus_switch_state(pdev->xdev, XenbusStateReconfigured); if (err) { xenbus_dev_fatal(pdev->xdev, err, @@ -525,7 +528,7 @@ static void xen_pcibk_frontend_changed(struct xenbus_device *xdev, break; case XenbusStateReconfiguring: - xen_pcibk_reconfigure(pdev); + xen_pcibk_reconfigure(pdev, XenbusStateReconfiguring); break; case XenbusStateConnected: @@ -664,6 +667,15 @@ static void xen_pcibk_be_watch(struct xenbus_watch *watch, xen_pcibk_setup_backend(pdev); break; + case XenbusStateInitialised: + /* + * We typically move to Initialised when the first device was + * added. Hence subsequent devices getting added may need + * reconfiguring. + */ + xen_pcibk_reconfigure(pdev, XenbusStateInitialised); + break; + default: break; } diff --git a/fs/block_dev.c b/fs/block_dev.c index b8abccd03e5d..6cc4d4cfe0c2 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1244,6 +1244,9 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate) lockdep_assert_held(&bdev->bd_mutex); + if (!(disk->flags & GENHD_FL_UP)) + return -ENXIO; + rescan: if (bdev->bd_part_count) return -EBUSY; @@ -1298,6 +1301,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) struct gendisk *disk = bdev->bd_disk; int ret = 0; + if (!(disk->flags & GENHD_FL_UP)) + return -ENXIO; + if (!bdev->bd_openers) { if (!bdev_is_partition(bdev)) { ret = 0; @@ -1332,8 +1338,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode) whole->bd_part_count++; mutex_unlock(&whole->bd_mutex); - if (!(disk->flags & GENHD_FL_UP) || - !bdev_nr_sectors(bdev)) { + if (!bdev_nr_sectors(bdev)) { __blkdev_put(whole, mode, 1); bdput(whole); return -ENXIO; @@ -1364,16 +1369,12 @@ struct block_device *blkdev_get_no_open(dev_t dev) struct block_device *bdev; struct gendisk *disk; - down_read(&bdev_lookup_sem); bdev = bdget(dev); if (!bdev) { - up_read(&bdev_lookup_sem); blk_request_module(dev); - down_read(&bdev_lookup_sem); - bdev = bdget(dev); if (!bdev) - goto unlock; + return NULL; } disk = bdev->bd_disk; @@ -1383,14 +1384,11 @@ struct block_device *blkdev_get_no_open(dev_t dev) goto put_disk; if (!try_module_get(bdev->bd_disk->fops->owner)) goto put_disk; - up_read(&bdev_lookup_sem); return bdev; put_disk: put_disk(disk); bdput: bdput(bdev); -unlock: - up_read(&bdev_lookup_sem); return NULL; } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 2bea01d23a5b..d17ac301032e 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -28,6 +28,7 @@ #include "compression.h" #include "extent_io.h" #include "extent_map.h" +#include "zoned.h" static const char* const btrfs_compress_types[] = { "", "zlib", "lzo", "zstd" }; @@ -349,6 +350,7 @@ static void end_compressed_bio_write(struct bio *bio) */ inode = cb->inode; cb->compressed_pages[0]->mapping = cb->inode->i_mapping; + btrfs_record_physical_zoned(inode, cb->start, bio); btrfs_writepage_endio_finish_ordered(cb->compressed_pages[0], cb->start, cb->start + cb->len - 1, bio->bi_status == BLK_STS_OK); @@ -401,6 +403,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, u64 first_byte = disk_start; blk_status_t ret; int skip_sum = inode->flags & BTRFS_INODE_NODATASUM; + const bool use_append = btrfs_use_zone_append(inode, disk_start); + const unsigned int bio_op = use_append ? REQ_OP_ZONE_APPEND : REQ_OP_WRITE; WARN_ON(!PAGE_ALIGNED(start)); cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS); @@ -418,10 +422,31 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, cb->nr_pages = nr_pages; bio = btrfs_bio_alloc(first_byte); - bio->bi_opf = REQ_OP_WRITE | write_flags; + bio->bi_opf = bio_op | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; + if (use_append) { + struct extent_map *em; + struct map_lookup *map; + struct block_device *bdev; + + em = btrfs_get_chunk_map(fs_info, disk_start, PAGE_SIZE); + if (IS_ERR(em)) { + kfree(cb); + bio_put(bio); + return BLK_STS_NOTSUPP; + } + + map = em->map_lookup; + /* We only support single profile for now */ + ASSERT(map->num_stripes == 1); + bdev = map->stripes[0].dev->bdev; + + bio_set_dev(bio, bdev); + free_extent_map(em); + } + if (blkcg_css) { bio->bi_opf |= REQ_CGROUP_PUNT; kthread_associate_blkcg(blkcg_css); @@ -432,6 +457,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bytes_left = compressed_len; for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) { int submit = 0; + int len; page = compressed_pages[pg_index]; page->mapping = inode->vfs_inode.i_mapping; @@ -439,9 +465,13 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, submit = btrfs_bio_fits_in_stripe(page, PAGE_SIZE, bio, 0); + if (pg_index == 0 && use_append) + len = bio_add_zone_append_page(bio, page, PAGE_SIZE, 0); + else + len = bio_add_page(bio, page, PAGE_SIZE, 0); + page->mapping = NULL; - if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) < - PAGE_SIZE) { + if (submit || len < PAGE_SIZE) { /* * inc the count before we submit the bio so * we know the end IO handler won't happen before @@ -465,11 +495,15 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, } bio = btrfs_bio_alloc(first_byte); - bio->bi_opf = REQ_OP_WRITE | write_flags; + bio->bi_opf = bio_op | write_flags; bio->bi_private = cb; bio->bi_end_io = end_compressed_bio_write; if (blkcg_css) bio->bi_opf |= REQ_CGROUP_PUNT; + /* + * Use bio_add_page() to ensure the bio has at least one + * page. + */ bio_add_page(bio, page, PAGE_SIZE, 0); } if (bytes_left < PAGE_SIZE) { diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 83b9c64ba76e..dee2dafbc872 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3753,7 +3753,7 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode, /* Note that em_end from extent_map_end() is exclusive */ iosize = min(em_end, end + 1) - cur; - if (btrfs_use_zone_append(inode, em)) + if (btrfs_use_zone_append(inode, em->block_start)) opf = REQ_OP_ZONE_APPEND; free_extent_map(em); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c6164ae16e2a..33f14573f2ec 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7786,7 +7786,7 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, iomap->bdev = fs_info->fs_devices->latest_bdev; iomap->length = len; - if (write && btrfs_use_zone_append(BTRFS_I(inode), em)) + if (write && btrfs_use_zone_append(BTRFS_I(inode), em->block_start)) iomap->flags |= IOMAP_F_ZONE_APPEND; free_extent_map(em); diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index 3928ecc40d7b..d434dc78dadf 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -282,6 +282,11 @@ copy_inline_extent: out: if (!ret && !trans) { /* + * Release path before starting a new transaction so we don't + * hold locks that would confuse lockdep. + */ + btrfs_release_path(path); + /* * No transaction here means we copied the inline extent into a * page of the destination inode. * diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 14ec61048483..326be57f2828 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1858,8 +1858,6 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans, ret = btrfs_update_inode(trans, root, BTRFS_I(inode)); } else if (ret == -EEXIST) { ret = 0; - } else { - BUG(); /* Logic Error */ } iput(inode); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 304ce64c70a4..1bb8ee97aae0 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1278,7 +1278,7 @@ void btrfs_free_redirty_list(struct btrfs_transaction *trans) spin_unlock(&trans->releasing_ebs_lock); } -bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) +bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_block_group *cache; @@ -1293,7 +1293,7 @@ bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) if (!is_data_inode(&inode->vfs_inode)) return false; - cache = btrfs_lookup_block_group(fs_info, em->block_start); + cache = btrfs_lookup_block_group(fs_info, start); ASSERT(cache); if (!cache) return false; diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 5e41a74a9cb2..e55d32595c2c 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -53,7 +53,7 @@ void btrfs_calc_zone_unusable(struct btrfs_block_group *cache); void btrfs_redirty_list_add(struct btrfs_transaction *trans, struct extent_buffer *eb); void btrfs_free_redirty_list(struct btrfs_transaction *trans); -bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em); +bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start); void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, struct bio *bio); void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered); @@ -152,8 +152,7 @@ static inline void btrfs_redirty_list_add(struct btrfs_transaction *trans, struct extent_buffer *eb) { } static inline void btrfs_free_redirty_list(struct btrfs_transaction *trans) { } -static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, - struct extent_map *em) +static inline bool btrfs_use_zone_append(struct btrfs_inode *inode, u64 start) { return false; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d7ea9c5fe0f8..2ffcb29d5c8f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -133,7 +133,7 @@ struct workqueue_struct *cifsiod_wq; struct workqueue_struct *decrypt_wq; struct workqueue_struct *fileinfo_put_wq; struct workqueue_struct *cifsoplockd_wq; -struct workqueue_struct *deferredclose_wq; +struct workqueue_struct *deferredclose_wq; __u32 cifs_lock_secret; /* diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index d88b4b523dcc..8488d7024462 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1257,8 +1257,7 @@ struct cifsFileInfo { struct work_struct oplock_break; /* work for oplock breaks */ struct work_struct put; /* work for the final part of _put */ struct delayed_work deferred; - bool oplock_break_received; /* Flag to indicate oplock break */ - bool deferred_scheduled; + bool deferred_close_scheduled; /* Flag to indicate close is scheduled */ }; struct cifs_io_parms { @@ -1418,6 +1417,7 @@ struct cifsInodeInfo { struct inode vfs_inode; struct list_head deferred_closes; /* list of deferred closes */ spinlock_t deferred_lock; /* protection on deferred list */ + bool lease_granted; /* Flag to indicate whether lease or oplock is granted. */ }; static inline struct cifsInodeInfo * diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 6caad100c3f3..379a427f3c2f 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -323,8 +323,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file, cfile->dentry = dget(dentry); cfile->f_flags = file->f_flags; cfile->invalidHandle = false; - cfile->oplock_break_received = false; - cfile->deferred_scheduled = false; + cfile->deferred_close_scheduled = false; cfile->tlink = cifs_get_tlink(tlink); INIT_WORK(&cfile->oplock_break, cifs_oplock_break); INIT_WORK(&cfile->put, cifsFileInfo_put_work); @@ -574,21 +573,18 @@ int cifs_open(struct inode *inode, struct file *file) file->f_op = &cifs_file_direct_ops; } - spin_lock(&CIFS_I(inode)->deferred_lock); /* Get the cached handle as SMB2 close is deferred */ rc = cifs_get_readable_path(tcon, full_path, &cfile); if (rc == 0) { if (file->f_flags == cfile->f_flags) { file->private_data = cfile; + spin_lock(&CIFS_I(inode)->deferred_lock); cifs_del_deferred_close(cfile); spin_unlock(&CIFS_I(inode)->deferred_lock); goto out; } else { - spin_unlock(&CIFS_I(inode)->deferred_lock); _cifsFileInfo_put(cfile, true, false); } - } else { - spin_unlock(&CIFS_I(inode)->deferred_lock); } if (server->oplocks) @@ -878,12 +874,8 @@ void smb2_deferred_work_close(struct work_struct *work) struct cifsFileInfo, deferred.work); spin_lock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); - if (!cfile->deferred_scheduled) { - spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); - return; - } cifs_del_deferred_close(cfile); - cfile->deferred_scheduled = false; + cfile->deferred_close_scheduled = false; spin_unlock(&CIFS_I(d_inode(cfile->dentry))->deferred_lock); _cifsFileInfo_put(cfile, true, false); } @@ -900,19 +892,26 @@ int cifs_close(struct inode *inode, struct file *file) file->private_data = NULL; dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL); if ((cinode->oplock == CIFS_CACHE_RHW_FLG) && + cinode->lease_granted && dclose) { if (test_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) inode->i_ctime = inode->i_mtime = current_time(inode); spin_lock(&cinode->deferred_lock); cifs_add_deferred_close(cfile, dclose); - if (cfile->deferred_scheduled) { - mod_delayed_work(deferredclose_wq, - &cfile->deferred, cifs_sb->ctx->acregmax); + if (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, cifs_sb->ctx->acregmax)) + cifsFileInfo_get(cfile); } else { /* Deferred close for files */ queue_delayed_work(deferredclose_wq, &cfile->deferred, cifs_sb->ctx->acregmax); - cfile->deferred_scheduled = true; + cfile->deferred_close_scheduled = true; spin_unlock(&cinode->deferred_lock); return 0; } @@ -2020,8 +2019,7 @@ struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, if (fsuid_only && !uid_eq(open_file->uid, current_fsuid())) continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) { - if ((!open_file->invalidHandle) && - (!open_file->oplock_break_received)) { + if ((!open_file->invalidHandle)) { /* found a good file */ /* lock it so it will not be closed on us */ cifsFileInfo_get(open_file); @@ -4874,14 +4872,20 @@ oplock_break_ack: } /* * When oplock break is received and there are no active - * file handles but cached, then set the flag oplock_break_received. + * 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); - if (is_deferred && cfile->deferred_scheduled) { - cfile->oplock_break_received = true; - mod_delayed_work(deferredclose_wq, &cfile->deferred, 0); + 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); } spin_unlock(&CIFS_I(inode)->deferred_lock); _cifsFileInfo_put(cfile, false /* do not wait for ourself */, false); diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 5d21cd905315..92d4ab029c91 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -1145,7 +1145,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc, /* if iocharset not set then load_nls_default * is used by caller */ - cifs_dbg(FYI, "iocharset set to %s\n", ctx->iocharset); + cifs_dbg(FYI, "iocharset set to %s\n", ctx->iocharset); break; case Opt_netbiosname: memset(ctx->source_rfc1001_name, 0x20, diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 524dbdfb7184..7207a63819cb 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -672,6 +672,11 @@ cifs_add_pending_open(struct cifs_fid *fid, struct tcon_link *tlink, spin_unlock(&tlink_tcon(open->tlink)->open_file_lock); } +/* + * Critical section which runs after acquiring deferred_lock. + * As there is no reference count on cifs_deferred_close, pdclose + * should not be used outside deferred_lock. + */ bool cifs_is_deferred_close(struct cifsFileInfo *cfile, struct cifs_deferred_close **pdclose) { @@ -688,6 +693,9 @@ cifs_is_deferred_close(struct cifsFileInfo *cfile, struct cifs_deferred_close ** return false; } +/* + * Critical section which runs after acquiring deferred_lock. + */ void cifs_add_deferred_close(struct cifsFileInfo *cfile, struct cifs_deferred_close *dclose) { @@ -707,6 +715,9 @@ cifs_add_deferred_close(struct cifsFileInfo *cfile, struct cifs_deferred_close * list_add_tail(&dclose->dlist, &CIFS_I(d_inode(cfile->dentry))->deferred_closes); } +/* + * Critical section which runs after acquiring deferred_lock. + */ void cifs_del_deferred_close(struct cifsFileInfo *cfile) { @@ -738,15 +749,19 @@ void cifs_close_all_deferred_files(struct cifs_tcon *tcon) { struct cifsFileInfo *cfile; - struct cifsInodeInfo *cinode; struct list_head *tmp; spin_lock(&tcon->open_file_lock); list_for_each(tmp, &tcon->openFileList) { cfile = list_entry(tmp, struct cifsFileInfo, tlist); - cinode = CIFS_I(d_inode(cfile->dentry)); - if (delayed_work_pending(&cfile->deferred)) - mod_delayed_work(deferredclose_wq, &cfile->deferred, 0); + 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); + } } spin_unlock(&tcon->open_file_lock); } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index dd0eb665b680..21ef51d338e0 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1861,6 +1861,8 @@ smb2_copychunk_range(const unsigned int xid, cpu_to_le32(min_t(u32, len, tcon->max_bytes_chunk)); /* Request server copy to target from src identified by key */ + kfree(retbuf); + retbuf = NULL; rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE, true /* is_fsctl */, (char *)pcchunk, @@ -3981,6 +3983,7 @@ smb2_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int epoch, bool *purge_cache) { oplock &= 0xFF; + cinode->lease_granted = false; if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) return; if (oplock == SMB2_OPLOCK_LEVEL_BATCH) { @@ -4007,6 +4010,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, unsigned int new_oplock = 0; oplock &= 0xFF; + cinode->lease_granted = true; if (oplock == SMB2_OPLOCK_LEVEL_NOCHANGE) return; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index a8bf43184773..9f24eb88297a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3900,10 +3900,10 @@ smb2_new_read_req(void **buf, unsigned int *total_len, * Related requests use info from previous read request * in chain. */ - shdr->SessionId = 0xFFFFFFFF; + shdr->SessionId = 0xFFFFFFFFFFFFFFFF; shdr->TreeId = 0xFFFFFFFF; - req->PersistentFileId = 0xFFFFFFFF; - req->VolatileFileId = 0xFFFFFFFF; + req->PersistentFileId = 0xFFFFFFFFFFFFFFFF; + req->VolatileFileId = 0xFFFFFFFFFFFFFFFF; } } if (remaining_bytes > io_parms->length) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9d9e0097c1d3..55efd3dd04f6 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -529,7 +529,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, * the subpool and global reserve usage count can need * to be adjusted. */ - VM_BUG_ON(PagePrivate(page)); + VM_BUG_ON(HPageRestoreReserve(page)); remove_huge_page(page); freed++; if (!truncate_op) { diff --git a/fs/io_uring.c b/fs/io_uring.c index e481ac8a757a..5f82954004f6 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5019,10 +5019,10 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, * Can't handle multishot for double wait for now, turn it * into one-shot mode. */ - if (!(req->poll.events & EPOLLONESHOT)) - req->poll.events |= EPOLLONESHOT; + if (!(poll_one->events & EPOLLONESHOT)) + poll_one->events |= EPOLLONESHOT; /* double add on the same waitqueue head, ignore */ - if (poll->head == head) + if (poll_one->head == head) return; poll = kmalloc(sizeof(*poll), GFP_ATOMIC); if (!poll) { @@ -9035,15 +9035,15 @@ static void io_uring_del_task_file(unsigned long index) static void io_uring_clean_tctx(struct io_uring_task *tctx) { + struct io_wq *wq = tctx->io_wq; struct io_tctx_node *node; unsigned long index; + tctx->io_wq = NULL; xa_for_each(&tctx->xa, index, node) io_uring_del_task_file(index); - if (tctx->io_wq) { - io_wq_put_and_exit(tctx->io_wq); - tctx->io_wq = NULL; - } + if (wq) + io_wq_put_and_exit(wq); } static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index a83bdd0c47a8..bde2b4c64dbe 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -770,6 +770,8 @@ struct xfs_scrub_metadata { /* * ioctl commands that are used by Linux filesystems */ +#define XFS_IOC_GETXFLAGS FS_IOC_GETFLAGS +#define XFS_IOC_SETXFLAGS FS_IOC_SETFLAGS #define XFS_IOC_GETVERSION FS_IOC_GETVERSION /* @@ -780,6 +782,8 @@ struct xfs_scrub_metadata { #define XFS_IOC_ALLOCSP _IOW ('X', 10, struct xfs_flock64) #define XFS_IOC_FREESP _IOW ('X', 11, struct xfs_flock64) #define XFS_IOC_DIOINFO _IOR ('X', 30, struct dioattr) +#define XFS_IOC_FSGETXATTR FS_IOC_FSGETXATTR +#define XFS_IOC_FSSETXATTR FS_IOC_FSSETXATTR #define XFS_IOC_ALLOCSP64 _IOW ('X', 36, struct xfs_flock64) #define XFS_IOC_FREESP64 _IOW ('X', 37, struct xfs_flock64) #define XFS_IOC_GETBMAP _IOWR('X', 38, struct getbmap) diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c index aa874607618a..be38c960da85 100644 --- a/fs/xfs/scrub/common.c +++ b/fs/xfs/scrub/common.c @@ -74,7 +74,9 @@ __xchk_process_error( return true; case -EDEADLOCK: /* Used to restart an op with deadlock avoidance. */ - trace_xchk_deadlock_retry(sc->ip, sc->sm, *error); + trace_xchk_deadlock_retry( + sc->ip ? sc->ip : XFS_I(file_inode(sc->file)), + sc->sm, *error); break; case -EFSBADCRC: case -EFSCORRUPTED: diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index a5e9d7d34023..0936f3a96fe6 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -71,18 +71,24 @@ xfs_zero_extent( #ifdef CONFIG_XFS_RT int xfs_bmap_rtalloc( - struct xfs_bmalloca *ap) /* bmap alloc argument struct */ + struct xfs_bmalloca *ap) { - int error; /* error return value */ - xfs_mount_t *mp; /* mount point structure */ - xfs_extlen_t prod = 0; /* product factor for allocators */ - xfs_extlen_t mod = 0; /* product factor for allocators */ - xfs_extlen_t ralen = 0; /* realtime allocation length */ - xfs_extlen_t align; /* minimum allocation alignment */ - xfs_rtblock_t rtb; - - mp = ap->ip->i_mount; + struct xfs_mount *mp = ap->ip->i_mount; + xfs_fileoff_t orig_offset = ap->offset; + xfs_rtblock_t rtb; + xfs_extlen_t prod = 0; /* product factor for allocators */ + xfs_extlen_t mod = 0; /* product factor for allocators */ + xfs_extlen_t ralen = 0; /* realtime allocation length */ + xfs_extlen_t align; /* minimum allocation alignment */ + xfs_extlen_t orig_length = ap->length; + xfs_extlen_t minlen = mp->m_sb.sb_rextsize; + xfs_extlen_t raminlen; + bool rtlocked = false; + bool ignore_locality = false; + int error; + align = xfs_get_extsz_hint(ap->ip); +retry: prod = align / mp->m_sb.sb_rextsize; error = xfs_bmap_extsize_align(mp, &ap->got, &ap->prev, align, 1, ap->eof, 0, @@ -93,6 +99,15 @@ xfs_bmap_rtalloc( ASSERT(ap->length % mp->m_sb.sb_rextsize == 0); /* + * If we shifted the file offset downward to satisfy an extent size + * hint, increase minlen by that amount so that the allocator won't + * give us an allocation that's too short to cover at least one of the + * blocks that the caller asked for. + */ + if (ap->offset != orig_offset) + minlen += orig_offset - ap->offset; + + /* * If the offset & length are not perfectly aligned * then kill prod, it will just get us in trouble. */ @@ -116,10 +131,13 @@ xfs_bmap_rtalloc( /* * Lock out modifications to both the RT bitmap and summary inodes */ - xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP); - xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL); - xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM); - xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL); + if (!rtlocked) { + xfs_ilock(mp->m_rbmip, XFS_ILOCK_EXCL|XFS_ILOCK_RTBITMAP); + xfs_trans_ijoin(ap->tp, mp->m_rbmip, XFS_ILOCK_EXCL); + xfs_ilock(mp->m_rsumip, XFS_ILOCK_EXCL|XFS_ILOCK_RTSUM); + xfs_trans_ijoin(ap->tp, mp->m_rsumip, XFS_ILOCK_EXCL); + rtlocked = true; + } /* * If it's an allocation to an empty file at offset 0, @@ -141,33 +159,59 @@ xfs_bmap_rtalloc( /* * Realtime allocation, done through xfs_rtallocate_extent. */ - do_div(ap->blkno, mp->m_sb.sb_rextsize); + if (ignore_locality) + ap->blkno = 0; + else + do_div(ap->blkno, mp->m_sb.sb_rextsize); rtb = ap->blkno; ap->length = ralen; - error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length, - &ralen, ap->wasdel, prod, &rtb); + raminlen = max_t(xfs_extlen_t, 1, minlen / mp->m_sb.sb_rextsize); + error = xfs_rtallocate_extent(ap->tp, ap->blkno, raminlen, ap->length, + &ralen, ap->wasdel, prod, &rtb); if (error) return error; - ap->blkno = rtb; - if (ap->blkno != NULLFSBLOCK) { - ap->blkno *= mp->m_sb.sb_rextsize; - ralen *= mp->m_sb.sb_rextsize; - ap->length = ralen; - ap->ip->i_nblocks += ralen; + if (rtb != NULLRTBLOCK) { + ap->blkno = rtb * mp->m_sb.sb_rextsize; + ap->length = ralen * mp->m_sb.sb_rextsize; + ap->ip->i_nblocks += ap->length; xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE); if (ap->wasdel) - ap->ip->i_delayed_blks -= ralen; + ap->ip->i_delayed_blks -= ap->length; /* * Adjust the disk quota also. This was reserved * earlier. */ xfs_trans_mod_dquot_byino(ap->tp, ap->ip, ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT : - XFS_TRANS_DQ_RTBCOUNT, (long) ralen); - } else { - ap->length = 0; + XFS_TRANS_DQ_RTBCOUNT, ap->length); + return 0; } + + if (align > mp->m_sb.sb_rextsize) { + /* + * We previously enlarged the request length to try to satisfy + * an extent size hint. The allocator didn't return anything, + * so reset the parameters to the original values and try again + * without alignment criteria. + */ + ap->offset = orig_offset; + ap->length = orig_length; + minlen = align = mp->m_sb.sb_rextsize; + goto retry; + } + + if (!ignore_locality && ap->blkno != 0) { + /* + * If we can't allocate near a specific rt extent, try again + * without locality criteria. + */ + ignore_locality = true; + goto retry; + } + + ap->blkno = NULLFSBLOCK; + ap->length = 0; return 0; } #endif /* CONFIG_XFS_RT */ diff --git a/include/linux/bits.h b/include/linux/bits.h index 7f475d59a097..87d112650dfb 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -22,7 +22,7 @@ #include <linux/build_bug.h> #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __builtin_constant_p((l) > (h)), (l) > (h), 0))) + __is_constexpr((l) > (h)), (l) > (h), 0))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 559ee05f86b2..fb8f6d2cd104 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -232,7 +232,7 @@ struct css_set { struct list_head task_iters; /* - * On the default hierarhcy, ->subsys[ssid] may point to a css + * On the default hierarchy, ->subsys[ssid] may point to a css * attached to an ancestor instead of the cgroup this css_set is * associated with. The following node is anchored at * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to @@ -668,7 +668,7 @@ struct cgroup_subsys { */ bool threaded:1; - /* the following two fields are initialized automtically during boot */ + /* the following two fields are initialized automatically during boot */ int id; const char *name; @@ -757,7 +757,7 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer. * On boot, sock_cgroup_data records the cgroup that the sock was created * in so that cgroup2 matches can be made; however, once either net_prio or - * net_cls starts being used, the area is overriden to carry prioidx and/or + * net_cls starts being used, the area is overridden to carry prioidx and/or * classid. The two modes are distinguished by whether the lowest bit is * set. Clear bit indicates cgroup pointer while set bit prioidx and * classid. diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 4f2f79de083e..6bc9c76680b2 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -32,7 +32,7 @@ struct kernel_clone_args; #ifdef CONFIG_CGROUPS /* - * All weight knobs on the default hierarhcy should use the following min, + * All weight knobs on the default hierarchy should use the following min, * default and max values. The default value is the logarithmic center of * MIN and MAX and allows 100x to be expressed in both directions. */ diff --git a/include/linux/const.h b/include/linux/const.h index 81b8aae5a855..435ddd72d2c4 100644 --- a/include/linux/const.h +++ b/include/linux/const.h @@ -3,4 +3,12 @@ #include <vdso/const.h> +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de> + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + #endif /* _LINUX_CONST_H */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7e9660ea967d..6fc26f7bdf71 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -306,8 +306,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ -extern struct rw_semaphore bdev_lookup_sem; - dev_t blk_lookup_devt(const char *name, int partno); void blk_request_module(dev_t devt); #ifdef CONFIG_BLOCK diff --git a/include/linux/minmax.h b/include/linux/minmax.h index c0f57b0c64d9..5433c08fcc68 100644 --- a/include/linux/minmax.h +++ b/include/linux/minmax.h @@ -2,6 +2,8 @@ #ifndef _LINUX_MINMAX_H #define _LINUX_MINMAX_H +#include <linux/const.h> + /* * min()/max()/clamp() macros must accomplish three things: * @@ -17,14 +19,6 @@ #define __typecheck(x, y) \ (!!(sizeof((typeof(x) *)1 == (typeof(y) *)1))) -/* - * This returns a constant expression while determining if an argument is - * a constant expression, most importantly without evaluating the argument. - * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de> - */ -#define __is_constexpr(x) \ - (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) - #define __no_side_effects(x, y) \ (__is_constexpr(x) && __is_constexpr(y)) diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 360a3bc767ca..74239d65c7fd 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -644,8 +644,8 @@ struct spi_controller { int *cs_gpios; struct gpio_desc **cs_gpiods; bool use_gpio_descriptors; - u8 unused_native_cs; - u8 max_native_cs; + s8 unused_native_cs; + s8 max_native_cs; /* statistics */ struct spi_statistics statistics; diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 8031464ed4ae..4e4e61111500 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1004,12 +1004,14 @@ static inline void __pipelined_op(struct wake_q_head *wake_q, struct mqueue_inode_info *info, struct ext_wait_queue *this) { + struct task_struct *task; + list_del(&this->list); - get_task_struct(this->task); + task = get_task_struct(this->task); /* see MQ_BARRIER for purpose/pairing */ smp_store_release(&this->state, STATE_READY); - wake_q_add_safe(wake_q, this->task); + wake_q_add_safe(wake_q, task); } /* pipelined_send() - send a message directly to the task waiting in diff --git a/ipc/msg.c b/ipc/msg.c index acd1bc7af55a..6e6c8e0c9380 100644 --- a/ipc/msg.c +++ b/ipc/msg.c @@ -251,11 +251,13 @@ static void expunge_all(struct msg_queue *msq, int res, struct msg_receiver *msr, *t; list_for_each_entry_safe(msr, t, &msq->q_receivers, r_list) { - get_task_struct(msr->r_tsk); + struct task_struct *r_tsk; + + r_tsk = get_task_struct(msr->r_tsk); /* see MSG_BARRIER for purpose/pairing */ smp_store_release(&msr->r_msg, ERR_PTR(res)); - wake_q_add_safe(wake_q, msr->r_tsk); + wake_q_add_safe(wake_q, r_tsk); } } diff --git a/ipc/sem.c b/ipc/sem.c index e0ec239680cb..bf534c74293e 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -784,12 +784,14 @@ would_block: static inline void wake_up_sem_queue_prepare(struct sem_queue *q, int error, struct wake_q_head *wake_q) { - get_task_struct(q->sleeper); + struct task_struct *sleeper; + + sleeper = get_task_struct(q->sleeper); /* see SEM_BARRIER_2 for purpose/pairing */ smp_store_release(&q->status, error); - wake_q_add_safe(wake_q, q->sleeper); + wake_q_add_safe(wake_q, sleeper); } static void unlink_queue(struct sem_array *sma, struct sem_queue *q) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 391aa570369b..8190b6bfc978 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -1001,7 +1001,7 @@ static int check_cgroupfs_options(struct fs_context *fc) ctx->subsys_mask &= enabled; /* - * In absense of 'none', 'name=' or subsystem name options, + * In absence of 'none', 'name=' and subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e049edd66776..21ecc6ee6a6d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -468,7 +468,7 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, * @cgrp: the cgroup of interest * @ss: the subsystem of interest * - * Find and get @cgrp's css assocaited with @ss. If the css doesn't exist + * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, @@ -1633,7 +1633,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) /** * css_clear_dir - remove subsys files in a cgroup directory - * @css: taget css + * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { @@ -5350,7 +5350,7 @@ out_unlock: /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to - * initate destruction and put the css ref from kill_css(). + * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { @@ -5634,8 +5634,6 @@ int __init cgroup_init_early(void) return 0; } -static u16 cgroup_disable_mask __initdata; - /** * cgroup_init - cgroup initialization * @@ -5694,12 +5692,8 @@ int __init cgroup_init(void) * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ - if (cgroup_disable_mask & (1 << ssid)) { - static_branch_disable(cgroup_subsys_enabled_key[ssid]); - printk(KERN_INFO "Disabling %s control group subsystem\n", - ss->name); + if (!cgroup_ssid_enabled(ssid)) continue; - } if (cgroup1_ssid_disabled(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", @@ -6058,7 +6052,7 @@ out_revert: * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* - * cgroup_can_fork() succeded and cleans up references we took to + * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, @@ -6214,7 +6208,10 @@ static int __init cgroup_disable(char *str) if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; - cgroup_disable_mask |= 1 << i; + + static_branch_disable(cgroup_subsys_enabled_key[i]); + pr_info("Disabling %s control group subsystem\n", + ss->name); } } return 1; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a945504c0ae7..adb5190c4429 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3376,7 +3376,7 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) } /** - * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed + * cpuset_nodemask_valid_mems_allowed - check nodemask vs. current mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c index ae042c347c64..3135406608c7 100644 --- a/kernel/cgroup/rdma.c +++ b/kernel/cgroup/rdma.c @@ -244,7 +244,7 @@ EXPORT_SYMBOL(rdmacg_uncharge); * This function follows charging resource in hierarchical way. * It will fail if the charge would cause the new value to exceed the * hierarchical limit. - * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. + * Returns 0 if the charge succeeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. * Returns pointer to rdmacg for this resource when charging is successful. * * Charger needs to account resources on two criteria. diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 3a3fd2993a65..cee265cb535c 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -75,7 +75,7 @@ void cgroup_rstat_updated(struct cgroup *cgrp, int cpu) * @root: root of the tree to traversal * @cpu: target cpu * - * Walks the udpated rstat_cpu tree on @cpu from @root. %NULL @pos starts + * Walks the updated rstat_cpu tree on @cpu from @root. %NULL @pos starts * the traversal and %NULL return indicates the end. During traversal, * each returned cgroup is unlinked from the tree. Must be called with the * matching cgroup_rstat_cpu_lock held. diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 48d736aa03b2..7641bd407239 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5736,7 +5736,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - trace_lock_acquired(lock, ip); + trace_lock_contended(lock, ip); if (unlikely(!lock_stat || !lockdep_enabled())) return; @@ -5754,7 +5754,7 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip) { unsigned long flags; - trace_lock_contended(lock, ip); + trace_lock_acquired(lock, ip); if (unlikely(!lock_stat || !lockdep_enabled())) return; diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index a7276aaf2abc..db9301591e3f 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -57,7 +57,7 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, task->blocked_on = waiter; } -void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, +void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct task_struct *task) { DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list)); @@ -65,7 +65,7 @@ void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter); task->blocked_on = NULL; - list_del_init(&waiter->list); + INIT_LIST_HEAD(&waiter->list); waiter->task = NULL; } diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h index 1edd3f45a4ec..53e631e1d76d 100644 --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -22,7 +22,7 @@ extern void debug_mutex_free_waiter(struct mutex_waiter *waiter); extern void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct task_struct *task); -extern void mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, +extern void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct task_struct *task); extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index cb6b112ce155..013e1b08a1bf 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -194,7 +194,7 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait * Add @waiter to a given location in the lock wait_list and set the * FLAG_WAITERS flag if it's the first waiter. */ -static void __sched +static void __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, struct list_head *list) { @@ -205,6 +205,16 @@ __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); } +static void +__mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter) +{ + list_del(&waiter->list); + if (likely(list_empty(&lock->wait_list))) + __mutex_clear_flag(lock, MUTEX_FLAGS); + + debug_mutex_remove_waiter(lock, waiter, current); +} + /* * Give up ownership to a specific task, when @task = NULL, this is equivalent * to a regular unlock. Sets PICKUP on a handoff, clears HANDOFF, preserves @@ -1061,9 +1071,7 @@ acquired: __ww_mutex_check_waiters(lock, ww_ctx); } - mutex_remove_waiter(lock, &waiter, current); - if (likely(list_empty(&lock->wait_list))) - __mutex_clear_flag(lock, MUTEX_FLAGS); + __mutex_remove_waiter(lock, &waiter); debug_mutex_free_waiter(&waiter); @@ -1080,7 +1088,7 @@ skip_wait: err: __set_current_state(TASK_RUNNING); - mutex_remove_waiter(lock, &waiter, current); + __mutex_remove_waiter(lock, &waiter); err_early_kill: spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 1c2287d3fa71..f0c710b1d192 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -10,12 +10,10 @@ * !CONFIG_DEBUG_MUTEXES case. Most of them are NOPs: */ -#define mutex_remove_waiter(lock, waiter, task) \ - __list_del((waiter)->list.prev, (waiter)->list.next) - #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) #define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) +#define debug_mutex_remove_waiter(lock, waiter, ti) do { } while (0) #define debug_mutex_unlock(lock) do { } while (0) #define debug_mutex_init(lock, name, key) do { } while (0) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 7c397907d0e9..92d3bcc5a5e0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -302,10 +302,10 @@ void touch_softlockup_watchdog_sync(void) __this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } -static int is_softlockup(unsigned long touch_ts, unsigned long period_ts) +static int is_softlockup(unsigned long touch_ts, + unsigned long period_ts, + unsigned long now) { - unsigned long now = get_timestamp(); - if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){ /* Warn about unreasonable delays. */ if (time_after(now, period_ts + get_softlockup_thresh())) @@ -353,8 +353,7 @@ static int softlockup_fn(void *data) /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { - unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); - unsigned long period_ts = __this_cpu_read(watchdog_report_ts); + unsigned long touch_ts, period_ts, now; struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; @@ -377,11 +376,22 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); /* + * Read the current timestamp first. It might become invalid anytime + * when a virtual machine is stopped by the host or when the watchog + * is touched from NMI. + */ + now = get_timestamp(); + /* * If a virtual machine is stopped by the host it can look to - * the watchdog like a soft lockup. Check to see if the host - * stopped the vm before we process the timestamps. + * the watchdog like a soft lockup. This function touches the watchdog. */ kvm_check_and_clear_guest_paused(); + /* + * The stored timestamp is comparable with @now only when not touched. + * It might get touched anytime from NMI. Make sure that is_softlockup() + * uses the same (valid) value. + */ + period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); /* Reset the interval when touched by known problematic code. */ if (period_ts == SOFTLOCKUP_DELAY_REPORT) { @@ -398,13 +408,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } - /* check for a softlockup - * This is done by making sure a high priority task is - * being scheduled. The task touches the watchdog to - * indicate it is getting cpu time. If it hasn't then - * this is a good indication some task is hogging the cpu - */ - duration = is_softlockup(touch_ts, period_ts); + /* Check for a softlockup. */ + touch_ts = __this_cpu_read(watchdog_touch_ts); + duration = is_softlockup(touch_ts, period_ts, now); if (unlikely(duration)) { /* * Prevent multiple soft-lockup reports if one cpu is already diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b19d759e55a5..50142fc08902 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -50,6 +50,7 @@ #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> +#include <linux/kvm_para.h> #include "workqueue_internal.h" @@ -5772,6 +5773,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; + unsigned long now = jiffies; struct worker_pool *pool; int pi; @@ -5786,6 +5788,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) if (list_empty(&pool->worklist)) continue; + /* + * If a virtual machine is stopped by the host it can look to + * the watchdog like a stall. + */ + kvm_check_and_clear_guest_paused(); + /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); @@ -5799,12 +5807,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) ts = touched; /* did we stall? */ - if (time_after(jiffies, ts + thresh)) { + if (time_after(now, ts + thresh)) { lockup_detected = true; pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", - jiffies_to_msecs(jiffies - pool_ts) / 1000); + jiffies_to_msecs(now - pool_ts) / 1000); } } diff --git a/lib/Makefile b/lib/Makefile index e11cfc18b6c0..2cc359ec1fdd 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -348,6 +348,7 @@ obj-$(CONFIG_OBJAGG) += objagg.o obj-$(CONFIG_PLDMFW) += pldmfw/ # KUnit tests +CFLAGS_bitfield_kunit.o := $(call cc-option,-Wframe-larger-than=10240) obj-$(CONFIG_BITFIELD_KUNIT) += bitfield_kunit.o obj-$(CONFIG_LIST_KUNIT_TEST) += list-test.o obj-$(CONFIG_LINEAR_RANGES_TEST) += test_linear_ranges.o @@ -1593,10 +1593,6 @@ struct page *get_dump_page(unsigned long addr) FOLL_FORCE | FOLL_DUMP | FOLL_GET); if (locked) mmap_read_unlock(mm); - - if (ret == 1 && is_page_poisoned(page)) - return NULL; - return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ diff --git a/mm/internal.h b/mm/internal.h index 54bd0dc2c23c..2f1182948aa6 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -96,26 +96,6 @@ static inline void set_page_refcounted(struct page *page) set_page_count(page, 1); } -/* - * When kernel touch the user page, the user page may be have been marked - * poison but still mapped in user space, if without this page, the kernel - * can guarantee the data integrity and operation success, the kernel is - * better to check the posion status and avoid touching it, be good not to - * panic, coredump for process fatal signal is a sample case matching this - * scenario. Or if kernel can't guarantee the data integrity, it's better - * not to call this function, let kernel touch the poison page and get to - * panic. - */ -static inline bool is_page_poisoned(struct page *page) -{ - if (PageHWPoison(page)) - return true; - else if (PageHuge(page) && PageHWPoison(compound_head(page))) - return true; - - return false; -} - extern unsigned long highest_memmap_pfn; /* diff --git a/mm/shuffle.h b/mm/shuffle.h index 71b784f0b7c3..cec62984f7d3 100644 --- a/mm/shuffle.h +++ b/mm/shuffle.h @@ -10,7 +10,7 @@ DECLARE_STATIC_KEY_FALSE(page_alloc_shuffle_key); extern void __shuffle_free_memory(pg_data_t *pgdat); extern bool shuffle_pick_tail(void); -static inline void shuffle_free_memory(pg_data_t *pgdat) +static inline void __meminit shuffle_free_memory(pg_data_t *pgdat) { if (!static_branch_unlikely(&page_alloc_shuffle_key)) return; @@ -18,7 +18,7 @@ static inline void shuffle_free_memory(pg_data_t *pgdat) } extern void __shuffle_zone(struct zone *z); -static inline void shuffle_zone(struct zone *z) +static inline void __meminit shuffle_zone(struct zone *z) { if (!static_branch_unlikely(&page_alloc_shuffle_key)) return; diff --git a/mm/slub.c b/mm/slub.c index 438fa8d4c970..3f96e099817a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -301,6 +301,7 @@ static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) if (!debug_pagealloc_enabled_static()) return get_freepointer(s, object); + object = kasan_reset_tag(object); freepointer_addr = (unsigned long)object + s->offset; copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p)); return freelist_ptr(s, p, freepointer_addr); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index e14b3820c6a8..63a73e164d55 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -360,38 +360,38 @@ out: * If a reservation for the page existed in the reservation * map of a private mapping, the map was modified to indicate * the reservation was consumed when the page was allocated. - * We clear the PagePrivate flag now so that the global + * We clear the HPageRestoreReserve flag now so that the global * reserve count will not be incremented in free_huge_page. * The reservation map will still indicate the reservation * was consumed and possibly prevent later page allocation. * This is better than leaking a global reservation. If no - * reservation existed, it is still safe to clear PagePrivate - * as no adjustments to reservation counts were made during - * allocation. + * reservation existed, it is still safe to clear + * HPageRestoreReserve as no adjustments to reservation counts + * were made during allocation. * * The reservation map for shared mappings indicates which * pages have reservations. When a huge page is allocated * for an address with a reservation, no change is made to - * the reserve map. In this case PagePrivate will be set - * to indicate that the global reservation count should be + * the reserve map. In this case HPageRestoreReserve will be + * set to indicate that the global reservation count should be * incremented when the page is freed. This is the desired * behavior. However, when a huge page is allocated for an * address without a reservation a reservation entry is added - * to the reservation map, and PagePrivate will not be set. - * When the page is freed, the global reserve count will NOT - * be incremented and it will appear as though we have leaked - * reserved page. In this case, set PagePrivate so that the - * global reserve count will be incremented to match the - * reservation map entry which was created. + * to the reservation map, and HPageRestoreReserve will not be + * set. When the page is freed, the global reserve count will + * NOT be incremented and it will appear as though we have + * leaked reserved page. In this case, set HPageRestoreReserve + * so that the global reserve count will be incremented to + * match the reservation map entry which was created. * * Note that vm_alloc_shared is based on the flags of the vma * for which the page was originally allocated. dst_vma could * be different or NULL on error. */ if (vm_alloc_shared) - SetPagePrivate(page); + SetHPageRestoreReserve(page); else - ClearPagePrivate(page); + ClearHPageRestoreReserve(page); put_page(page); } BUG_ON(copied < 0); diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc index f6d543725f1e..b2483149bbe5 100755 --- a/scripts/dummy-tools/gcc +++ b/scripts/dummy-tools/gcc @@ -76,7 +76,11 @@ fi if arg_contain -S "$@"; then # For scripts/gcc-x86-*-has-stack-protector.sh if arg_contain -fstack-protector "$@"; then - echo "%gs" + if arg_contain -mstack-protector-guard-reg=fs "$@"; then + echo "%fs" + else + echo "%gs" + fi exit 0 fi diff --git a/scripts/jobserver-exec b/scripts/jobserver-exec index 48d141e3ec56..8762887a970c 100755 --- a/scripts/jobserver-exec +++ b/scripts/jobserver-exec @@ -10,7 +10,7 @@ from __future__ import print_function import os, sys, errno import subprocess -# Extract and prepare jobserver file descriptors from envirnoment. +# Extract and prepare jobserver file descriptors from environment. claim = 0 jobs = b"" try: diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build index cd72016c3cfa..715092fc6a23 100644 --- a/tools/build/Makefile.build +++ b/tools/build/Makefile.build @@ -51,39 +51,39 @@ subdir-obj-y := build-file := $(dir)/Build -include $(build-file) -quiet_cmd_flex = FLEX $@ -quiet_cmd_bison = BISON $@ +quiet_cmd_flex = FLEX $@ +quiet_cmd_bison = BISON $@ # Create directory unless it exists -quiet_cmd_mkdir = MKDIR $(dir $@) +quiet_cmd_mkdir = MKDIR $(dir $@) cmd_mkdir = mkdir -p $(dir $@) rule_mkdir = $(if $(wildcard $(dir $@)),,@$(call echo-cmd,mkdir) $(cmd_mkdir)) # Compile command -quiet_cmd_cc_o_c = CC $@ +quiet_cmd_cc_o_c = CC $@ cmd_cc_o_c = $(CC) $(c_flags) -c -o $@ $< -quiet_cmd_host_cc_o_c = HOSTCC $@ +quiet_cmd_host_cc_o_c = HOSTCC $@ cmd_host_cc_o_c = $(HOSTCC) $(host_c_flags) -c -o $@ $< -quiet_cmd_cxx_o_c = CXX $@ +quiet_cmd_cxx_o_c = CXX $@ cmd_cxx_o_c = $(CXX) $(cxx_flags) -c -o $@ $< -quiet_cmd_cpp_i_c = CPP $@ +quiet_cmd_cpp_i_c = CPP $@ cmd_cpp_i_c = $(CC) $(c_flags) -E -o $@ $< -quiet_cmd_cc_s_c = AS $@ +quiet_cmd_cc_s_c = AS $@ cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $< -quiet_cmd_gen = GEN $@ +quiet_cmd_gen = GEN $@ # Link agregate command # If there's nothing to link, create empty $@ object. -quiet_cmd_ld_multi = LD $@ +quiet_cmd_ld_multi = LD $@ cmd_ld_multi = $(if $(strip $(obj-y)),\ $(LD) -r -o $@ $(filter $(obj-y),$^),rm -f $@; $(AR) rcs $@) -quiet_cmd_host_ld_multi = HOSTLD $@ +quiet_cmd_host_ld_multi = HOSTLD $@ cmd_host_ld_multi = $(if $(strip $(obj-y)),\ $(HOSTLD) -r -o $@ $(filter $(obj-y),$^),rm -f $@; $(HOSTAR) rcs $@) diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h index 7f475d59a097..87d112650dfb 100644 --- a/tools/include/linux/bits.h +++ b/tools/include/linux/bits.h @@ -22,7 +22,7 @@ #include <linux/build_bug.h> #define GENMASK_INPUT_CHECK(h, l) \ (BUILD_BUG_ON_ZERO(__builtin_choose_expr( \ - __builtin_constant_p((l) > (h)), (l) > (h), 0))) + __is_constexpr((l) > (h)), (l) > (h), 0))) #else /* * BUILD_BUG_ON_ZERO is not available in h files included from asm files, diff --git a/tools/include/linux/const.h b/tools/include/linux/const.h index 81b8aae5a855..435ddd72d2c4 100644 --- a/tools/include/linux/const.h +++ b/tools/include/linux/const.h @@ -3,4 +3,12 @@ #include <vdso/const.h> +/* + * This returns a constant expression while determining if an argument is + * a constant expression, most importantly without evaluating the argument. + * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de> + */ +#define __is_constexpr(x) \ + (sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8))) + #endif /* _LINUX_CONST_H */ diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include index f9271f3ea912..071312f5eb92 100644 --- a/tools/scripts/Makefile.include +++ b/tools/scripts/Makefile.include @@ -131,29 +131,29 @@ QUIET_SUBDIR1 = ifneq ($(silent),1) ifneq ($(V),1) - QUIET_CC = @echo ' CC '$@; - QUIET_CC_FPIC = @echo ' CC FPIC '$@; - QUIET_CLANG = @echo ' CLANG '$@; - QUIET_AR = @echo ' AR '$@; - QUIET_LINK = @echo ' LINK '$@; - QUIET_MKDIR = @echo ' MKDIR '$@; - QUIET_GEN = @echo ' GEN '$@; + QUIET_CC = @echo ' CC '$@; + QUIET_CC_FPIC = @echo ' CC FPIC '$@; + QUIET_CLANG = @echo ' CLANG '$@; + QUIET_AR = @echo ' AR '$@; + QUIET_LINK = @echo ' LINK '$@; + QUIET_MKDIR = @echo ' MKDIR '$@; + QUIET_GEN = @echo ' GEN '$@; QUIET_SUBDIR0 = +@subdir= QUIET_SUBDIR1 = ;$(NO_SUBDIR) \ - echo ' SUBDIR '$$subdir; \ + echo ' SUBDIR '$$subdir; \ $(MAKE) $(PRINT_DIR) -C $$subdir - QUIET_FLEX = @echo ' FLEX '$@; - QUIET_BISON = @echo ' BISON '$@; - QUIET_GENSKEL = @echo ' GEN-SKEL '$@; + QUIET_FLEX = @echo ' FLEX '$@; + QUIET_BISON = @echo ' BISON '$@; + QUIET_GENSKEL = @echo ' GENSKEL '$@; descend = \ - +@echo ' DESCEND '$(1); \ + +@echo ' DESCEND '$(1); \ mkdir -p $(OUTPUT)$(1) && \ $(MAKE) $(COMMAND_O) subdir=$(if $(subdir),$(subdir)/$(1),$(1)) $(PRINT_DIR) -C $(1) $(2) - QUIET_CLEAN = @printf ' CLEAN %s\n' $1; - QUIET_INSTALL = @printf ' INSTALL %s\n' $1; - QUIET_UNINST = @printf ' UNINST %s\n' $1; + QUIET_CLEAN = @printf ' CLEAN %s\n' $1; + QUIET_INSTALL = @printf ' INSTALL %s\n' $1; + QUIET_UNINST = @printf ' UNINST %s\n' $1; endif endif diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index cf69b2fcce59..dd61118df66e 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -28,8 +28,8 @@ $(OUTPUT)/execveat.denatured: $(OUTPUT)/execveat cp $< $@ chmod -x $@ $(OUTPUT)/load_address_4096: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000 -pie -static $< -o $@ $(OUTPUT)/load_address_2097152: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x200000 -pie -static $< -o $@ $(OUTPUT)/load_address_16777216: load_address.c - $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie $< -o $@ + $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=0x1000000 -pie -static $< -o $@ diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 98c3b647f54d..e3d5c77a8612 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1753,16 +1753,25 @@ TEST_F(TRACE_poke, getpid_runs_normally) # define SYSCALL_RET_SET(_regs, _val) \ do { \ typeof(_val) _result = (_val); \ - /* \ - * A syscall error is signaled by CR0 SO bit \ - * and the code is stored as a positive value. \ - */ \ - if (_result < 0) { \ - SYSCALL_RET(_regs) = -_result; \ - (_regs).ccr |= 0x10000000; \ - } else { \ + if ((_regs.trap & 0xfff0) == 0x3000) { \ + /* \ + * scv 0 system call uses -ve result \ + * for error, so no need to adjust. \ + */ \ SYSCALL_RET(_regs) = _result; \ - (_regs).ccr &= ~0x10000000; \ + } else { \ + /* \ + * A syscall error is signaled by the \ + * CR0 SO bit and the code is stored as \ + * a positive value. \ + */ \ + if (_result < 0) { \ + SYSCALL_RET(_regs) = -_result; \ + (_regs).ccr |= 0x10000000; \ + } else { \ + SYSCALL_RET(_regs) = _result; \ + (_regs).ccr &= ~0x10000000; \ + } \ } \ } while (0) # define SYSCALL_RET_SET_ON_PTRACE_EXIT |