diff options
93 files changed, 840 insertions, 476 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 79b400c97059..00836f6452f0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16313,6 +16313,7 @@ M: Pekka Enberg <penberg@kernel.org> M: David Rientjes <rientjes@google.com> M: Joonsoo Kim <iamjoonsoo.kim@lge.com> M: Andrew Morton <akpm@linux-foundation.org> +M: Vlastimil Babka <vbabka@suse.cz> L: linux-mm@kvack.org S: Maintained F: include/linux/sl?b*.h diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 05e17351e4f3..f39568b28ec1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -174,8 +174,6 @@ config ARM64 select HAVE_NMI select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS - select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS - select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 015ddffaf6ca..b56a4b2bc248 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -17,7 +17,7 @@ #include <asm/lse.h> #define ATOMIC_OP(op) \ -static inline void arch_##op(int i, atomic_t *v) \ +static __always_inline void arch_##op(int i, atomic_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, op) \ -static inline int arch_##op##name(int i, atomic_t *v) \ +static __always_inline int arch_##op##name(int i, atomic_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return) #undef ATOMIC_FETCH_OPS #define ATOMIC64_OP(op) \ -static inline void arch_##op(long i, atomic64_t *v) \ +static __always_inline void arch_##op(long i, atomic64_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, op) \ -static inline long arch_##op##name(long i, atomic64_t *v) \ +static __always_inline long arch_##op##name(long i, atomic64_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return) #undef ATOMIC64_FETCH_OP #undef ATOMIC64_FETCH_OPS -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) +static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v) { return __lse_ll_sc_body(atomic64_dec_if_positive, v); } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 69ad25fbeae4..ca2cd75d3286 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -94,8 +94,7 @@ #endif /* CONFIG_ARM64_FORCE_52BIT */ extern phys_addr_t arm64_dma_phys_limit; -extern phys_addr_t arm64_dma32_phys_limit; -#define ARCH_LOW_ADDRESS_LIMIT ((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1) +#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1) struct debug_info { #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f42fd9e33981..301784463587 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,7 +75,7 @@ int main(void) DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); - DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); + DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); BLANK(); #ifdef CONFIG_COMPAT DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0)); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index a338f40e64d3..b3e4f9a088b1 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -35,7 +35,7 @@ */ .macro ftrace_regs_entry, allregs=0 /* Make room for pt_regs, plus a callee frame */ - sub sp, sp, #(S_FRAME_SIZE + 16) + sub sp, sp, #(PT_REGS_SIZE + 16) /* Save function arguments (and x9 for simplicity) */ stp x0, x1, [sp, #S_X0] @@ -61,15 +61,15 @@ .endif /* Save the callsite's SP and LR */ - add x10, sp, #(S_FRAME_SIZE + 16) + add x10, sp, #(PT_REGS_SIZE + 16) stp x9, x10, [sp, #S_LR] /* Save the PC after the ftrace callsite */ str x30, [sp, #S_PC] /* Create a frame record for the callsite above pt_regs */ - stp x29, x9, [sp, #S_FRAME_SIZE] - add x29, sp, #S_FRAME_SIZE + stp x29, x9, [sp, #PT_REGS_SIZE] + add x29, sp, #PT_REGS_SIZE /* Create our frame record within pt_regs. */ stp x29, x30, [sp, #S_STACKFRAME] @@ -120,7 +120,7 @@ ftrace_common_return: ldr x9, [sp, #S_PC] /* Restore the callsite's SP */ - add sp, sp, #S_FRAME_SIZE + 16 + add sp, sp, #PT_REGS_SIZE + 16 ret x9 SYM_CODE_END(ftrace_common) @@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller) ldr x0, [sp, #S_PC] sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) add x1, sp, #S_LR // parent_ip (callsite's LR) - ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP) bl prepare_ftrace_return b ftrace_common_return SYM_CODE_END(ftrace_graph_caller) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a8c3e7aaca74..c9bae73f2621 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -75,7 +75,7 @@ alternative_else_nop_endif .endif #endif - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK /* * Test whether the SP has overflowed, without corrupting a GPR. @@ -96,7 +96,7 @@ alternative_else_nop_endif * userspace, and can clobber EL0 registers to free up GPRs. */ - /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */ + /* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */ msr tpidr_el0, x0 /* Recover the original x0 value and stash it in tpidrro_el0 */ @@ -253,7 +253,7 @@ alternative_else_nop_endif scs_load tsk, x20 .else - add x21, sp, #S_FRAME_SIZE + add x21, sp, #PT_REGS_SIZE get_current_task tsk .endif /* \el == 0 */ mrs x22, elr_el1 @@ -377,7 +377,7 @@ alternative_else_nop_endif ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] ldr lr, [sp, #S_LR] - add sp, sp, #S_FRAME_SIZE // restore sp + add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 @@ -580,12 +580,12 @@ __bad_stack: /* * Store the original GPRs to the new stack. The orginal SP (minus - * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry. + * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry. */ - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE kernel_entry 1 mrs x0, tpidr_el0 - add x0, x0, #S_FRAME_SIZE + add x0, x0, #PT_REGS_SIZE str x0, [sp, #S_SP] /* Stash the regs for handle_bad_stack */ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 38bb07eff872..3605f77ad4df 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -23,8 +23,6 @@ #include <linux/platform_device.h> #include <linux/sched_clock.h> #include <linux/smp.h> -#include <linux/nmi.h> -#include <linux/cpufreq.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = { static int __init armv8_pmu_driver_init(void) { - int ret; - if (acpi_disabled) - ret = platform_driver_register(&armv8_pmu_driver); + return platform_driver_register(&armv8_pmu_driver); else - ret = arm_pmu_acpi_probe(armv8_pmuv3_init); - - /* - * Try to re-initialize lockup detector after PMU init in - * case PMU events are triggered via NMIs. - */ - if (ret == 0 && arm_pmu_irq_is_nmi()) - lockup_detector_init(); - - return ret; + return arm_pmu_acpi_probe(armv8_pmuv3_init); } device_initcall(armv8_pmu_driver_init) @@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time_zero = 1; userpg->cap_user_time_short = 1; } - -#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF -/* - * Safe maximum CPU frequency in case a particular platform doesn't implement - * cpufreq driver. Although, architecture doesn't put any restrictions on - * maximum frequency but 5 GHz seems to be safe maximum given the available - * Arm CPUs in the market which are clocked much less than 5 GHz. On the other - * hand, we can't make it much higher as it would lead to a large hard-lockup - * detection timeout on parts which are running slower (eg. 1GHz on - * Developerbox) and doesn't possess a cpufreq driver. - */ -#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz -u64 hw_nmi_get_sample_period(int watchdog_thresh) -{ - unsigned int cpu = smp_processor_id(); - unsigned long max_cpu_freq; - - max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL; - if (!max_cpu_freq) - max_cpu_freq = SAFE_MAX_CPU_FREQ; - - return (u64)max_cpu_freq * watchdog_thresh; -} -#endif diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 890ca72c5a51..288a84e253cc 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -25,7 +25,7 @@ stp x24, x25, [sp, #S_X24] stp x26, x27, [sp, #S_X26] stp x28, x29, [sp, #S_X28] - add x0, sp, #S_FRAME_SIZE + add x0, sp, #PT_REGS_SIZE stp lr, x0, [sp, #S_LR] /* * Construct a useful saved PSTATE @@ -62,7 +62,7 @@ .endm SYM_CODE_START(kretprobe_trampoline) - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE save_all_base_regs @@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline) restore_all_base_regs - add sp, sp, #S_FRAME_SIZE + add sp, sp, #PT_REGS_SIZE ret SYM_CODE_END(kretprobe_trampoline) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index f71d6ce4673f..6237486ff6bb 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { - /* - * The assembly code enters us with IRQs off, but it hasn't - * informed the tracing code of that for efficiency reasons. - * Update the trace code with the current status. - */ - trace_hardirqs_off(); - do { if (thread_flags & _TIF_NEED_RESCHED) { /* Unmask Debug and SError for the next task */ diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index f61e9d8cc55a..c2877c332f2d 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -9,6 +9,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> +#include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { - /* - * We're off to userspace, where interrupts are - * always enabled after we restore the flags from - * the SPSR. - */ - trace_hardirqs_on(); + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) return; - } local_daif_restore(DAIF_PROCCTX); } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 7deddf56f7c3..709d98fea90c 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* - * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of - * memory as some devices, namely the Raspberry Pi 4, have peripherals with - * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 - * bit addressable memory area. + * If the corresponding config options are enabled, we create both ZONE_DMA + * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory + * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). + * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, + * otherwise it is empty. */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, + crash_base = memblock_find_in_range(0, arm64_dma_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; unsigned int __maybe_unused acpi_zone_dma_bits; unsigned int __maybe_unused dt_zone_dma_bits; + phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); @@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = dma32_phys_limit; #endif + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max; free_area_init(max_zone_pfns); @@ -394,16 +399,9 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma32_phys_limit = max_zone_phys(32); - else - arm64_dma32_phys_limit = PHYS_MASK + 1; - reserve_elfcorehdr(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - - dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -439,6 +437,11 @@ void __init bootmem_init(void) zone_sizes_init(min, max); /* + * Reserve the CMA area after arm64_dma_phys_limit was initialised. + */ + dma_contiguous_reserve(arm64_dma_phys_limit); + + /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ @@ -455,7 +458,7 @@ void __init bootmem_init(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c61c641674e6..e3946b06e840 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> +#include <asm/unaligned.h> /* * These two variables specify the free mem region @@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start) dtb_size = fdt_totalsize((void *)&__appended_dtb); /* last four bytes is always image size in little endian */ - image_size = le32_to_cpup((void *)&__image_end - 4); + image_size = get_unaligned_le32((void *)&__image_end - 4); /* copy dtb to where the booted kernel will expect it */ memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index bd47e15d02c7..be5d4afcd30f 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void) static int __init octeon_irq_init_ciu( struct device_node *ciu_node, struct device_node *parent) { - unsigned int i, r; + int i, r; struct irq_chip *chip; struct irq_chip *chip_edge; struct irq_chip *chip_mbox; diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 6ee3f7218c67..c4441416e96b 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 6dd103d3cebb..7b2a23f48c1a 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 47aeb3350a76..0e365b7c742d 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset) static inline __init unsigned long rotate_xor(unsigned long hash, const void *area, size_t size) { - size_t i; - unsigned long *ptr = (unsigned long *)area; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + size_t diff, i; + + diff = (void *)ptr - area; + if (unlikely(size < diff + sizeof(hash))) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); for (i = 0; i < size / sizeof(hash); i++) { /* Rotate by odd number of bits and XOR. */ diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 81671aa365b3..77c635c2c90d 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); } +#ifdef __powerpc64__ + static __always_inline int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); } -#ifdef CONFIG_VDSO32 +#else #define BUILD_VDSO32 1 static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) { return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 8e0b1298bf19..4ab426b8b0e0 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -187,6 +187,12 @@ SECTIONS .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT + + /* + *.init.text might be RO so we must ensure this section ends on + * a page boundary. + */ + . = ALIGN(PAGE_SIZE); _einittext = .; #ifdef CONFIG_PPC64 *(.tramp.ftrace.init); @@ -200,6 +206,8 @@ SECTIONS EXIT_TEXT } + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(16) . = ALIGN(8); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 81b76d44725d..e9e2c1f0a690 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -137,7 +137,7 @@ config PA_BITS config PAGE_OFFSET hex - default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB + default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB default 0x80000000 if 64BIT && !MMU default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB @@ -247,10 +247,12 @@ config MODULE_SECTIONS choice prompt "Maximum Physical Memory" - default MAXPHYSMEM_2GB if 32BIT + default MAXPHYSMEM_1GB if 32BIT default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY + config MAXPHYSMEM_1GB + bool "1GiB" config MAXPHYSMEM_2GB bool "2GiB" config MAXPHYSMEM_128GB diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 4a2729f5ca3f..24d75a146e02 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -88,7 +88,9 @@ phy-mode = "gmii"; phy-handle = <&phy0>; phy0: ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0771"; reg = <0>; + reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>; }; }; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index d222d353d86d..8c3d1e451703 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 41a72861987c..251e1db088fa 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -99,7 +99,6 @@ | _PAGE_DIRTY) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 8454f746bbfd..1453a2f563bc 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -10,7 +10,7 @@ #include <linux/types.h> -#ifndef GENERIC_TIME_VSYSCALL +#ifndef CONFIG_GENERIC_TIME_VSYSCALL struct vdso_data { }; #endif diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index de59dd457b41..d86781357044 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf) static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); struct cacheinfo *this_leaf; int index; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 524d918f3601..744f3209c48d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -124,15 +124,15 @@ skip_context_tracking: REG_L a1, (a1) jr a1 1: -#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on -#endif /* * Exceptions run with interrupts enabled or disabled depending on the * state of SR_PIE in m/sstatus. */ andi t0, s1, SR_PIE beqz t0, 1f +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_on +#endif csrs CSR_STATUS, SR_IE 1: @@ -155,6 +155,15 @@ skip_context_tracking: tail do_trap_unknown handle_syscall: +#ifdef CONFIG_RISCV_M_MODE + /* + * When running is M-Mode (no MMU config), MPIE does not get set. + * As a result, we need to force enable interrupts here because + * handle_exception did not do set SR_IE as it always sees SR_PIE + * being cleared. + */ + csrs CSR_STATUS, SR_IE +#endif #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING) /* Recover a0 - a7 for system calls */ REG_L a0, PT_A0(sp) @@ -186,14 +195,7 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - blt a7, t1, 1f + bgeu a7, t0, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 1d85e9bf783c..3fa3f26dde85 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -127,7 +127,9 @@ static void __init init_resources(void) { struct memblock_region *region = NULL; struct resource *res = NULL; - int ret = 0; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int ret = 0, i = 0; code_res.start = __pa_symbol(_text); code_res.end = __pa_symbol(_etext) - 1; @@ -145,16 +147,17 @@ static void __init init_resources(void) bss_res.end = __pa_symbol(__bss_stop) - 1; bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); + if (!mem_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); /* * Start by adding the reserved regions, if they overlap * with /memory regions, insert_resource later on will take * care of it. */ for_each_reserved_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; res->name = "Reserved"; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; @@ -171,8 +174,10 @@ static void __init init_resources(void) * Ignore any other reserved regions within * system memory. */ - if (memblock_is_memory(res->start)) + if (memblock_is_memory(res->start)) { + memblock_free((phys_addr_t) res, sizeof(struct resource)); continue; + } ret = add_resource(&iomem_resource, res); if (ret < 0) @@ -181,10 +186,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -205,9 +207,9 @@ static void __init init_resources(void) return; error: - memblock_free((phys_addr_t) res, sizeof(struct resource)); /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); + memblock_free((phys_addr_t) mem_res, mem_res_sz); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 48b870a685b3..df5d2da7c40b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register unsigned long sp_in_global __asm__("sp"); +register const unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER @@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp = sp_in_global; fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = sp_in_global; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 4d3a1048ad8b..8a5cf99c0776 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -24,6 +25,8 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 678204231700..3f1d35e7c98a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,7 +12,7 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else #include <asm/vdso.h> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index bf5379135e39..7cd4993f4ff2 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -157,9 +157,10 @@ disable: void __init setup_bootmem(void) { phys_addr_t mem_start = 0; - phys_addr_t start, end = 0; + phys_addr_t start, dram_end, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); + phys_addr_t max_mapped_addr = __pa(~(ulong)0); u64 i; /* Find the memory region containing the kernel */ @@ -181,7 +182,18 @@ void __init setup_bootmem(void) /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + dram_end = memblock_end_of_DRAM(); + + /* + * memblock allocator is not aware of the fact that last 4K bytes of + * the addressable memory can not be mapped because of IS_ERR_VALUE + * macro. Make sure that last 4k bytes are not usable by memblock + * if end of dram is equal to maximum addressable memory. + */ + if (max_mapped_addr == (dram_end - 1)) + memblock_set_current_limit(max_mapped_addr - 4096); + + max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 12ddd1f6bf70..a8a2ffd9114a 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -93,8 +93,8 @@ void __init kasan_init(void) VMALLOC_END)); for_each_mem_range(i, &_start, &_end) { - void *start = (void *)_start; - void *end = (void *)_end; + void *start = (void *)__va(_start); + void *end = (void *)__va(_end); if (start >= end) break; diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c index 7f70e5a7de10..97a77ea8d3c9 100644 --- a/drivers/infiniband/core/cma_configfs.c +++ b/drivers/infiniband/core/cma_configfs.c @@ -131,8 +131,10 @@ static ssize_t default_roce_mode_store(struct config_item *item, return ret; gid_type = ib_cache_gid_parse_type_str(buf); - if (gid_type < 0) + if (gid_type < 0) { + cma_configfs_params_put(cma_dev); return -EINVAL; + } ret = cma_set_default_gid_type(cma_dev, group->port_num, gid_type); diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c index e0a41c867002..ff1551b3cf61 100644 --- a/drivers/infiniband/core/restrack.c +++ b/drivers/infiniband/core/restrack.c @@ -254,6 +254,7 @@ void rdma_restrack_add(struct rdma_restrack_entry *res) } else { ret = xa_alloc_cyclic(&rt->xa, &res->id, res, xa_limit_32b, &rt->next_id, GFP_KERNEL); + ret = (ret < 0) ? ret : 0; } out: diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index 7dab9a27a145..da2512c30ffd 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -95,8 +95,6 @@ struct ucma_context { u64 uid; struct list_head list; - /* sync between removal event and id destroy, protected by file mut */ - int destroying; struct work_struct close_work; }; @@ -122,7 +120,7 @@ static DEFINE_XARRAY_ALLOC(ctx_table); static DEFINE_XARRAY_ALLOC(multicast_table); static const struct file_operations ucma_fops; -static int __destroy_id(struct ucma_context *ctx); +static int ucma_destroy_private_ctx(struct ucma_context *ctx); static inline struct ucma_context *_ucma_find_context(int id, struct ucma_file *file) @@ -179,19 +177,14 @@ static void ucma_close_id(struct work_struct *work) /* once all inflight tasks are finished, we close all underlying * resources. The context is still alive till its explicit destryoing - * by its creator. + * by its creator. This puts back the xarray's reference. */ ucma_put_ctx(ctx); wait_for_completion(&ctx->comp); /* No new events will be generated after destroying the id. */ rdma_destroy_id(ctx->cm_id); - /* - * At this point ctx->ref is zero so the only place the ctx can be is in - * a uevent or in __destroy_id(). Since the former doesn't touch - * ctx->cm_id and the latter sync cancels this, there is no races with - * this store. - */ + /* Reading the cm_id without holding a positive ref is not allowed */ ctx->cm_id = NULL; } @@ -204,7 +197,6 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) return NULL; INIT_WORK(&ctx->close_work, ucma_close_id); - refcount_set(&ctx->ref, 1); init_completion(&ctx->comp); /* So list_del() will work if we don't do ucma_finish_ctx() */ INIT_LIST_HEAD(&ctx->list); @@ -218,6 +210,13 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file) return ctx; } +static void ucma_set_ctx_cm_id(struct ucma_context *ctx, + struct rdma_cm_id *cm_id) +{ + refcount_set(&ctx->ref, 1); + ctx->cm_id = cm_id; +} + static void ucma_finish_ctx(struct ucma_context *ctx) { lockdep_assert_held(&ctx->file->mut); @@ -303,7 +302,7 @@ static int ucma_connect_event_handler(struct rdma_cm_id *cm_id, ctx = ucma_alloc_ctx(listen_ctx->file); if (!ctx) goto err_backlog; - ctx->cm_id = cm_id; + ucma_set_ctx_cm_id(ctx, cm_id); uevent = ucma_create_uevent(listen_ctx, event); if (!uevent) @@ -321,8 +320,7 @@ static int ucma_connect_event_handler(struct rdma_cm_id *cm_id, return 0; err_alloc: - xa_erase(&ctx_table, ctx->id); - kfree(ctx); + ucma_destroy_private_ctx(ctx); err_backlog: atomic_inc(&listen_ctx->backlog); /* Returning error causes the new ID to be destroyed */ @@ -356,8 +354,12 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id, wake_up_interruptible(&ctx->file->poll_wait); } - if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL && !ctx->destroying) - queue_work(system_unbound_wq, &ctx->close_work); + if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) { + xa_lock(&ctx_table); + if (xa_load(&ctx_table, ctx->id) == ctx) + queue_work(system_unbound_wq, &ctx->close_work); + xa_unlock(&ctx_table); + } return 0; } @@ -461,13 +463,12 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf, ret = PTR_ERR(cm_id); goto err1; } - ctx->cm_id = cm_id; + ucma_set_ctx_cm_id(ctx, cm_id); resp.id = ctx->id; if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) { - xa_erase(&ctx_table, ctx->id); - __destroy_id(ctx); + ucma_destroy_private_ctx(ctx); return -EFAULT; } @@ -477,8 +478,7 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf, return 0; err1: - xa_erase(&ctx_table, ctx->id); - kfree(ctx); + ucma_destroy_private_ctx(ctx); return ret; } @@ -516,68 +516,73 @@ static void ucma_cleanup_mc_events(struct ucma_multicast *mc) rdma_unlock_handler(mc->ctx->cm_id); } -/* - * ucma_free_ctx is called after the underlying rdma CM-ID is destroyed. At - * this point, no new events will be reported from the hardware. However, we - * still need to cleanup the UCMA context for this ID. Specifically, there - * might be events that have not yet been consumed by the user space software. - * mutex. After that we release them as needed. - */ -static int ucma_free_ctx(struct ucma_context *ctx) +static int ucma_cleanup_ctx_events(struct ucma_context *ctx) { int events_reported; struct ucma_event *uevent, *tmp; LIST_HEAD(list); - ucma_cleanup_multicast(ctx); - - /* Cleanup events not yet reported to the user. */ + /* Cleanup events not yet reported to the user.*/ mutex_lock(&ctx->file->mut); list_for_each_entry_safe(uevent, tmp, &ctx->file->event_list, list) { - if (uevent->ctx == ctx || uevent->conn_req_ctx == ctx) + if (uevent->ctx != ctx) + continue; + + if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST && + xa_cmpxchg(&ctx_table, uevent->conn_req_ctx->id, + uevent->conn_req_ctx, XA_ZERO_ENTRY, + GFP_KERNEL) == uevent->conn_req_ctx) { list_move_tail(&uevent->list, &list); + continue; + } + list_del(&uevent->list); + kfree(uevent); } list_del(&ctx->list); events_reported = ctx->events_reported; mutex_unlock(&ctx->file->mut); /* - * If this was a listening ID then any connections spawned from it - * that have not been delivered to userspace are cleaned up too. - * Must be done outside any locks. + * If this was a listening ID then any connections spawned from it that + * have not been delivered to userspace are cleaned up too. Must be done + * outside any locks. */ list_for_each_entry_safe(uevent, tmp, &list, list) { - list_del(&uevent->list); - if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST && - uevent->conn_req_ctx != ctx) - __destroy_id(uevent->conn_req_ctx); + ucma_destroy_private_ctx(uevent->conn_req_ctx); kfree(uevent); } - - mutex_destroy(&ctx->mutex); - kfree(ctx); return events_reported; } -static int __destroy_id(struct ucma_context *ctx) +/* + * When this is called the xarray must have a XA_ZERO_ENTRY in the ctx->id (ie + * the ctx is not public to the user). This either because: + * - ucma_finish_ctx() hasn't been called + * - xa_cmpxchg() succeed to remove the entry (only one thread can succeed) + */ +static int ucma_destroy_private_ctx(struct ucma_context *ctx) { + int events_reported; + /* - * If the refcount is already 0 then ucma_close_id() has already - * destroyed the cm_id, otherwise holding the refcount keeps cm_id - * valid. Prevent queue_work() from being called. + * Destroy the underlying cm_id. New work queuing is prevented now by + * the removal from the xarray. Once the work is cancled ref will either + * be 0 because the work ran to completion and consumed the ref from the + * xarray, or it will be positive because we still have the ref from the + * xarray. This can also be 0 in cases where cm_id was never set */ - if (refcount_inc_not_zero(&ctx->ref)) { - rdma_lock_handler(ctx->cm_id); - ctx->destroying = 1; - rdma_unlock_handler(ctx->cm_id); - ucma_put_ctx(ctx); - } - cancel_work_sync(&ctx->close_work); - /* At this point it's guaranteed that there is no inflight closing task */ - if (ctx->cm_id) + if (refcount_read(&ctx->ref)) ucma_close_id(&ctx->close_work); - return ucma_free_ctx(ctx); + + events_reported = ucma_cleanup_ctx_events(ctx); + ucma_cleanup_multicast(ctx); + + WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, XA_ZERO_ENTRY, NULL, + GFP_KERNEL) != NULL); + mutex_destroy(&ctx->mutex); + kfree(ctx); + return events_reported; } static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf, @@ -596,14 +601,17 @@ static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf, xa_lock(&ctx_table); ctx = _ucma_find_context(cmd.id, file); - if (!IS_ERR(ctx)) - __xa_erase(&ctx_table, ctx->id); + if (!IS_ERR(ctx)) { + if (__xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY, + GFP_KERNEL) != ctx) + ctx = ERR_PTR(-ENOENT); + } xa_unlock(&ctx_table); if (IS_ERR(ctx)) return PTR_ERR(ctx); - resp.events_reported = __destroy_id(ctx); + resp.events_reported = ucma_destroy_private_ctx(ctx); if (copy_to_user(u64_to_user_ptr(cmd.response), &resp, sizeof(resp))) ret = -EFAULT; @@ -1777,15 +1785,16 @@ static int ucma_close(struct inode *inode, struct file *filp) * prevented by this being a FD release function. The list_add_tail() in * ucma_connect_event_handler() can run concurrently, however it only * adds to the list *after* a listening ID. By only reading the first of - * the list, and relying on __destroy_id() to block + * the list, and relying on ucma_destroy_private_ctx() to block * ucma_connect_event_handler(), no additional locking is needed. */ while (!list_empty(&file->ctx_list)) { struct ucma_context *ctx = list_first_entry( &file->ctx_list, struct ucma_context, list); - xa_erase(&ctx_table, ctx->id); - __destroy_id(ctx); + WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY, + GFP_KERNEL) != ctx); + ucma_destroy_private_ctx(ctx); } kfree(file); return 0; diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 7ca4112e3e8f..917338db7ac1 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -135,7 +135,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem, */ if (mask) pgsz_bitmap &= GENMASK(count_trailing_zeros(mask), 0); - return rounddown_pow_of_two(pgsz_bitmap); + return pgsz_bitmap ? rounddown_pow_of_two(pgsz_bitmap) : 0; } EXPORT_SYMBOL(ib_umem_find_best_pgsz); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 3bae9ba0ead8..d26f3f3e0462 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -3956,7 +3956,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev) err = set_has_smi_cap(dev); if (err) - return err; + goto err_mp; if (!mlx5_core_mp_enabled(mdev)) { for (i = 1; i <= dev->num_ports; i++) { @@ -4319,7 +4319,7 @@ static int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev) err = mlx5_alloc_bfreg(dev->mdev, &dev->fp_bfreg, false, true); if (err) - mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg); + mlx5_free_bfreg(dev->mdev, &dev->bfreg); return err; } diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index bc98bd950d99..3acb5c10b155 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -434,9 +434,9 @@ static void ocrdma_dealloc_ucontext_pd(struct ocrdma_ucontext *uctx) pr_err("%s(%d) Freeing in use pdid=0x%x.\n", __func__, dev->id, pd->id); } - kfree(uctx->cntxt_pd); uctx->cntxt_pd = NULL; _ocrdma_dealloc_pd(dev, pd); + kfree(pd); } static struct ocrdma_pd *ocrdma_get_ucontext_pd(struct ocrdma_ucontext *uctx) diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c index 38a37770c016..3705c6b8b223 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c @@ -214,6 +214,7 @@ find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev, } usnic_uiom_free_dev_list(dev_list); + dev_list = NULL; } /* Try to find resources on an unused vf */ @@ -239,6 +240,8 @@ find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev, qp_grp_check: if (IS_ERR_OR_NULL(qp_grp)) { usnic_err("Failed to allocate qp_grp\n"); + if (usnic_ib_share_vf) + usnic_uiom_free_dev_list(dev_list); return ERR_PTR(qp_grp ? PTR_ERR(qp_grp) : -ENOMEM); } return qp_grp; diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index b7e2d9666614..9e44c09f6410 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -605,6 +605,7 @@ config DM_INTEGRITY select BLK_DEV_INTEGRITY select DM_BUFIO select CRYPTO + select CRYPTO_SKCIPHER select ASYNC_XOR help This device-mapper target emulates a block device that has @@ -622,6 +623,7 @@ config DM_ZONED tristate "Drive-managed zoned block device target support" depends on BLK_DEV_DM depends on BLK_DEV_ZONED + select CRC32 help This device-mapper target takes a host-managed or host-aware zoned block device and exposes most of its capacity as a regular block diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 9c1a86bde658..fce4cbf9529d 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1534,6 +1534,12 @@ sector_t dm_bufio_get_device_size(struct dm_bufio_client *c) } EXPORT_SYMBOL_GPL(dm_bufio_get_device_size); +struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c) +{ + return c->dm_io; +} +EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client); + sector_t dm_bufio_get_block_number(struct dm_buffer *b) { return b->block; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 53791138d78b..8c874710f0bc 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1454,13 +1454,16 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc, static void kcryptd_async_done(struct crypto_async_request *async_req, int error); -static void crypt_alloc_req_skcipher(struct crypt_config *cc, +static int crypt_alloc_req_skcipher(struct crypt_config *cc, struct convert_context *ctx) { unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1); - if (!ctx->r.req) - ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO); + if (!ctx->r.req) { + ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); + if (!ctx->r.req) + return -ENOMEM; + } skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]); @@ -1471,13 +1474,18 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc, skcipher_request_set_callback(ctx->r.req, CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req)); + + return 0; } -static void crypt_alloc_req_aead(struct crypt_config *cc, +static int crypt_alloc_req_aead(struct crypt_config *cc, struct convert_context *ctx) { - if (!ctx->r.req_aead) - ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO); + if (!ctx->r.req) { + ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO); + if (!ctx->r.req) + return -ENOMEM; + } aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]); @@ -1488,15 +1496,17 @@ static void crypt_alloc_req_aead(struct crypt_config *cc, aead_request_set_callback(ctx->r.req_aead, CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead)); + + return 0; } -static void crypt_alloc_req(struct crypt_config *cc, +static int crypt_alloc_req(struct crypt_config *cc, struct convert_context *ctx) { if (crypt_integrity_aead(cc)) - crypt_alloc_req_aead(cc, ctx); + return crypt_alloc_req_aead(cc, ctx); else - crypt_alloc_req_skcipher(cc, ctx); + return crypt_alloc_req_skcipher(cc, ctx); } static void crypt_free_req_skcipher(struct crypt_config *cc, @@ -1529,17 +1539,28 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_ * Encrypt / decrypt data from one bio to another one (can be the same one) */ static blk_status_t crypt_convert(struct crypt_config *cc, - struct convert_context *ctx, bool atomic) + struct convert_context *ctx, bool atomic, bool reset_pending) { unsigned int tag_offset = 0; unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT; int r; - atomic_set(&ctx->cc_pending, 1); + /* + * if reset_pending is set we are dealing with the bio for the first time, + * else we're continuing to work on the previous bio, so don't mess with + * the cc_pending counter + */ + if (reset_pending) + atomic_set(&ctx->cc_pending, 1); while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) { - crypt_alloc_req(cc, ctx); + r = crypt_alloc_req(cc, ctx); + if (r) { + complete(&ctx->restart); + return BLK_STS_DEV_RESOURCE; + } + atomic_inc(&ctx->cc_pending); if (crypt_integrity_aead(cc)) @@ -1553,7 +1574,25 @@ static blk_status_t crypt_convert(struct crypt_config *cc, * but the driver request queue is full, let's wait. */ case -EBUSY: - wait_for_completion(&ctx->restart); + if (in_interrupt()) { + if (try_wait_for_completion(&ctx->restart)) { + /* + * we don't have to block to wait for completion, + * so proceed + */ + } else { + /* + * we can't wait for completion without blocking + * exit and continue processing in a workqueue + */ + ctx->r.req = NULL; + ctx->cc_sector += sector_step; + tag_offset++; + return BLK_STS_DEV_RESOURCE; + } + } else { + wait_for_completion(&ctx->restart); + } reinit_completion(&ctx->restart); fallthrough; /* @@ -1691,6 +1730,12 @@ static void crypt_inc_pending(struct dm_crypt_io *io) atomic_inc(&io->io_pending); } +static void kcryptd_io_bio_endio(struct work_struct *work) +{ + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + bio_endio(io->base_bio); +} + /* * One of the bios was finished. Check for completion of * the whole request and correctly clean up the buffer. @@ -1713,7 +1758,23 @@ static void crypt_dec_pending(struct dm_crypt_io *io) kfree(io->integrity_metadata); base_bio->bi_status = error; - bio_endio(base_bio); + + /* + * If we are running this function from our tasklet, + * we can't call bio_endio() here, because it will call + * clone_endio() from dm.c, which in turn will + * free the current struct dm_crypt_io structure with + * our tasklet. In this case we need to delay bio_endio() + * execution to after the tasklet is done and dequeued. + */ + if (tasklet_trylock(&io->tasklet)) { + tasklet_unlock(&io->tasklet); + bio_endio(base_bio); + return; + } + + INIT_WORK(&io->work, kcryptd_io_bio_endio); + queue_work(cc->io_queue, &io->work); } /* @@ -1945,6 +2006,37 @@ static bool kcryptd_crypt_write_inline(struct crypt_config *cc, } } +static void kcryptd_crypt_write_continue(struct work_struct *work) +{ + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + struct crypt_config *cc = io->cc; + struct convert_context *ctx = &io->ctx; + int crypt_finished; + sector_t sector = io->sector; + blk_status_t r; + + wait_for_completion(&ctx->restart); + reinit_completion(&ctx->restart); + + r = crypt_convert(cc, &io->ctx, true, false); + if (r) + io->error = r; + crypt_finished = atomic_dec_and_test(&ctx->cc_pending); + if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) { + /* Wait for completion signaled by kcryptd_async_done() */ + wait_for_completion(&ctx->restart); + crypt_finished = 1; + } + + /* Encryption was already finished, submit io now */ + if (crypt_finished) { + kcryptd_crypt_write_io_submit(io, 0); + io->sector = sector; + } + + crypt_dec_pending(io); +} + static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; @@ -1973,7 +2065,17 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io) crypt_inc_pending(io); r = crypt_convert(cc, ctx, - test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags)); + test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true); + /* + * Crypto API backlogged the request, because its queue was full + * and we're in softirq context, so continue from a workqueue + * (TODO: is it actually possible to be in softirq in the write path?) + */ + if (r == BLK_STS_DEV_RESOURCE) { + INIT_WORK(&io->work, kcryptd_crypt_write_continue); + queue_work(cc->crypt_queue, &io->work); + return; + } if (r) io->error = r; crypt_finished = atomic_dec_and_test(&ctx->cc_pending); @@ -1998,6 +2100,25 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io) crypt_dec_pending(io); } +static void kcryptd_crypt_read_continue(struct work_struct *work) +{ + struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work); + struct crypt_config *cc = io->cc; + blk_status_t r; + + wait_for_completion(&io->ctx.restart); + reinit_completion(&io->ctx.restart); + + r = crypt_convert(cc, &io->ctx, true, false); + if (r) + io->error = r; + + if (atomic_dec_and_test(&io->ctx.cc_pending)) + kcryptd_crypt_read_done(io); + + crypt_dec_pending(io); +} + static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) { struct crypt_config *cc = io->cc; @@ -2009,7 +2130,16 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io) io->sector); r = crypt_convert(cc, &io->ctx, - test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)); + test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true); + /* + * Crypto API backlogged the request, because its queue was full + * and we're in softirq context, so continue from a workqueue + */ + if (r == BLK_STS_DEV_RESOURCE) { + INIT_WORK(&io->work, kcryptd_crypt_read_continue); + queue_work(cc->crypt_queue, &io->work); + return; + } if (r) io->error = r; @@ -2091,8 +2221,12 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io) if ((bio_data_dir(io->base_bio) == READ && test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) || (bio_data_dir(io->base_bio) == WRITE && test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))) { - if (in_irq()) { - /* Crypto API's "skcipher_walk_first() refuses to work in hard IRQ context */ + /* + * in_irq(): Crypto API's skcipher_walk_first() refuses to work in hard IRQ context. + * irqs_disabled(): the kernel may run some IO completion from the idle thread, but + * it is being executed with irqs disabled. + */ + if (in_irq() || irqs_disabled()) { tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work); tasklet_schedule(&io->tasklet); return; diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 5a7a1b90e671..81df019ab284 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -1379,12 +1379,52 @@ thorough_test: #undef MAY_BE_HASH } -static void dm_integrity_flush_buffers(struct dm_integrity_c *ic) +struct flush_request { + struct dm_io_request io_req; + struct dm_io_region io_reg; + struct dm_integrity_c *ic; + struct completion comp; +}; + +static void flush_notify(unsigned long error, void *fr_) +{ + struct flush_request *fr = fr_; + if (unlikely(error != 0)) + dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO); + complete(&fr->comp); +} + +static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data) { int r; + + struct flush_request fr; + + if (!ic->meta_dev) + flush_data = false; + if (flush_data) { + fr.io_req.bi_op = REQ_OP_WRITE, + fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC, + fr.io_req.mem.type = DM_IO_KMEM, + fr.io_req.mem.ptr.addr = NULL, + fr.io_req.notify.fn = flush_notify, + fr.io_req.notify.context = &fr; + fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio), + fr.io_reg.bdev = ic->dev->bdev, + fr.io_reg.sector = 0, + fr.io_reg.count = 0, + fr.ic = ic; + init_completion(&fr.comp); + r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL); + BUG_ON(r); + } + r = dm_bufio_write_dirty_buffers(ic->bufio); if (unlikely(r)) dm_integrity_io_error(ic, "writing tags", r); + + if (flush_data) + wait_for_completion(&fr.comp); } static void sleep_on_endio_wait(struct dm_integrity_c *ic) @@ -2110,7 +2150,7 @@ offload_to_thread: if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) { integrity_metadata(&dio->work); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, false); dio->in_flight = (atomic_t)ATOMIC_INIT(1); dio->completion = NULL; @@ -2195,7 +2235,7 @@ static void integrity_commit(struct work_struct *w) flushes = bio_list_get(&ic->flush_bio_list); if (unlikely(ic->mode != 'J')) { spin_unlock_irq(&ic->endio_wait.lock); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); goto release_flush_bios; } @@ -2409,7 +2449,7 @@ skip_io: complete_journal_op(&comp); wait_for_completion_io(&comp.comp); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); } static void integrity_writer(struct work_struct *w) @@ -2451,7 +2491,7 @@ static void recalc_write_super(struct dm_integrity_c *ic) { int r; - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, false); if (dm_integrity_failed(ic)) return; @@ -2654,7 +2694,7 @@ static void bitmap_flush_work(struct work_struct *work) unsigned long limit; struct bio *bio; - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, false); range.logical_sector = 0; range.n_sectors = ic->provided_data_sectors; @@ -2663,9 +2703,7 @@ static void bitmap_flush_work(struct work_struct *work) add_new_range_and_wait(ic, &range); spin_unlock_irq(&ic->endio_wait.lock); - dm_integrity_flush_buffers(ic); - if (ic->meta_dev) - blkdev_issue_flush(ic->dev->bdev, GFP_NOIO); + dm_integrity_flush_buffers(ic, true); limit = ic->provided_data_sectors; if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) { @@ -2934,11 +2972,11 @@ static void dm_integrity_postsuspend(struct dm_target *ti) if (ic->meta_dev) queue_work(ic->writer_wq, &ic->writer_work); drain_workqueue(ic->writer_wq); - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); } if (ic->mode == 'B') { - dm_integrity_flush_buffers(ic); + dm_integrity_flush_buffers(ic, true); #if 1 /* set to 0 to test bitmap replay code */ init_journal(ic, 0, ic->journal_sections, 0); @@ -3754,7 +3792,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) unsigned extra_args; struct dm_arg_set as; static const struct dm_arg _args[] = { - {0, 9, "Invalid number of feature args"}, + {0, 15, "Invalid number of feature args"}, }; unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec; bool should_write_sb; diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 23c38777e8f6..cab12b2251ba 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3729,10 +3729,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs)); /* - * RAID1 and RAID10 personalities require bio splitting, - * RAID0/4/5/6 don't and process large discard bios properly. + * RAID0 and RAID10 personalities require bio splitting, + * RAID1/4/5/6 don't and process large discard bios properly. */ - if (rs_is_raid1(rs) || rs_is_raid10(rs)) { + if (rs_is_raid0(rs) || rs_is_raid10(rs)) { limits->discard_granularity = chunk_size_bytes; limits->max_discard_sectors = rs->md.chunk_sectors; } diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c index 4668b2cd98f4..11890db71f3f 100644 --- a/drivers/md/dm-snap.c +++ b/drivers/md/dm-snap.c @@ -141,6 +141,11 @@ struct dm_snapshot { * for them to be committed. */ struct bio_list bios_queued_during_merge; + + /* + * Flush data after merge. + */ + struct bio flush_bio; }; /* @@ -1121,6 +1126,17 @@ shut: static void error_bios(struct bio *bio); +static int flush_data(struct dm_snapshot *s) +{ + struct bio *flush_bio = &s->flush_bio; + + bio_reset(flush_bio); + bio_set_dev(flush_bio, s->origin->bdev); + flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; + + return submit_bio_wait(flush_bio); +} + static void merge_callback(int read_err, unsigned long write_err, void *context) { struct dm_snapshot *s = context; @@ -1134,6 +1150,11 @@ static void merge_callback(int read_err, unsigned long write_err, void *context) goto shut; } + if (flush_data(s) < 0) { + DMERR("Flush after merge failed: shutting down merge"); + goto shut; + } + if (s->store->type->commit_merge(s->store, s->num_merging_chunks) < 0) { DMERR("Write error in exception store: shutting down merge"); @@ -1318,6 +1339,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv) s->first_merging_chunk = 0; s->num_merging_chunks = 0; bio_list_init(&s->bios_queued_during_merge); + bio_init(&s->flush_bio, NULL, 0); /* Allocate hash table for COW data */ if (init_hash_tables(s)) { @@ -1504,6 +1526,8 @@ static void snapshot_dtr(struct dm_target *ti) dm_exception_store_destroy(s->store); + bio_uninit(&s->flush_bio); + dm_put_device(ti, s->cow); dm_put_device(ti, s->origin); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b3c3c8b4cb42..7bac564f3faa 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -562,7 +562,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode, * subset of the parent bdev; require extra privileges. */ if (!capable(CAP_SYS_RAWIO)) { - DMWARN_LIMIT( + DMDEBUG_LIMIT( "%s: sending ioctl %x to DM device without required privilege.", current->comm, cmd); r = -ENOIOCTLCMD; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f320273fc672..200bdd672c28 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2856,6 +2856,11 @@ static const struct attribute_group *nvme_subsys_attrs_groups[] = { NULL, }; +static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl) +{ + return ctrl->opts && ctrl->opts->discovery_nqn; +} + static bool nvme_validate_cntlid(struct nvme_subsystem *subsys, struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) { @@ -2875,7 +2880,7 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys, } if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) || - (ctrl->opts && ctrl->opts->discovery_nqn)) + nvme_discovery_ctrl(ctrl)) continue; dev_err(ctrl->device, @@ -3144,7 +3149,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) goto out_free; } - if (!ctrl->opts->discovery_nqn && !ctrl->kas) { + if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) { dev_err(ctrl->device, "keep-alive support is mandatory for fabrics\n"); ret = -EINVAL; @@ -3184,7 +3189,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret < 0) return ret; - if (!ctrl->identified) { + if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) { ret = nvme_hwmon_init(ctrl); if (ret < 0) return ret; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 979ee31b8dd1..216619926563 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -201,7 +201,7 @@ static inline size_t nvme_tcp_req_cur_offset(struct nvme_tcp_request *req) static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req) { - return min_t(size_t, req->iter.bvec->bv_len - req->iter.iov_offset, + return min_t(size_t, iov_iter_single_seg_count(&req->iter), req->pdu_len - req->pdu_sent); } @@ -286,7 +286,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req, * directly, otherwise queue io_work. Also, only do that if we * are on the same cpu, so we don't introduce contention. */ - if (queue->io_cpu == smp_processor_id() && + if (queue->io_cpu == __smp_processor_id() && sync && empty && mutex_trylock(&queue->send_mutex)) { queue->more_requests = !last; nvme_tcp_send_all(queue); diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index bdfc22eb2a10..06b6b742bb21 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1220,6 +1220,14 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id) } ndev->inline_data_size = nport->inline_data_size; ndev->inline_page_count = inline_page_count; + + if (nport->pi_enable && !(cm_id->device->attrs.device_cap_flags & + IB_DEVICE_INTEGRITY_HANDOVER)) { + pr_warn("T10-PI is not supported by device %s. Disabling it\n", + cm_id->device->name); + nport->pi_enable = false; + } + ndev->device = cm_id->device; kref_init(&ndev->ref); @@ -1855,14 +1863,6 @@ static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port) goto out_destroy_id; } - if (port->nport->pi_enable && - !(cm_id->device->attrs.device_cap_flags & - IB_DEVICE_INTEGRITY_HANDOVER)) { - pr_err("T10-PI is not supported for %pISpcs\n", addr); - ret = -EINVAL; - goto out_destroy_id; - } - port->cm_id = cm_id; return 0; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 794a37d50853..cb2f55f450e4 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -726,11 +726,6 @@ static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu) return per_cpu(hw_events->irq, cpu); } -bool arm_pmu_irq_is_nmi(void) -{ - return has_nmi; -} - /* * PMU hardware loses all context when a CPU goes offline. * When a CPU is hotplugged back in, since some hardware registers are diff --git a/drivers/scsi/mpt3sas/Kconfig b/drivers/scsi/mpt3sas/Kconfig index 86209455172d..c299f7e078fb 100644 --- a/drivers/scsi/mpt3sas/Kconfig +++ b/drivers/scsi/mpt3sas/Kconfig @@ -79,5 +79,5 @@ config SCSI_MPT2SAS select SCSI_MPT3SAS depends on PCI && SCSI help - Dummy config option for backwards compatiblity: configure the MPT3SAS + Dummy config option for backwards compatibility: configure the MPT3SAS driver instead. diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index f5fc7f518f8a..47ad64b06623 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -2245,7 +2245,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, chap_name); break; case ISCSI_BOOT_TGT_CHAP_SECRET: - rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, chap_secret); break; case ISCSI_BOOT_TGT_REV_CHAP_NAME: @@ -2253,7 +2253,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type, mchap_name); break; case ISCSI_BOOT_TGT_REV_CHAP_SECRET: - rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN, + rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN, mchap_secret); break; case ISCSI_BOOT_TGT_FLAGS: diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 24c0f7ec0351..4a08c450b756 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -6740,7 +6740,7 @@ static int __init scsi_debug_init(void) k = sdeb_zbc_model_str(sdeb_zbc_model_s); if (k < 0) { ret = k; - goto free_vm; + goto free_q_arr; } sdeb_zbc_model = k; switch (sdeb_zbc_model) { @@ -6753,7 +6753,8 @@ static int __init scsi_debug_init(void) break; default: pr_err("Invalid ZBC model\n"); - return -EINVAL; + ret = -EINVAL; + goto free_q_arr; } } if (sdeb_zbc_model != BLK_ZONED_NONE) { diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 679c2c025047..a3d2d4bc4a3d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -984,8 +984,10 @@ static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd) } } - if (sdp->no_write_same) + if (sdp->no_write_same) { + rq->rq_flags |= RQF_QUIET; return BLK_STS_TARGET; + } if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff) return sd_setup_write_same16_cmnd(cmd, false); @@ -3510,10 +3512,8 @@ static int sd_probe(struct device *dev) static int sd_remove(struct device *dev) { struct scsi_disk *sdkp; - dev_t devt; sdkp = dev_get_drvdata(dev); - devt = disk_devt(sdkp->disk); scsi_autopm_get_device(sdkp->device); async_synchronize_full_domain(&scsi_sd_pm_domain); diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 82ad31781bc9..e31d2c5c7b23 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -289,7 +289,8 @@ static inline void ufshcd_wb_config(struct ufs_hba *hba) if (ret) dev_err(hba->dev, "%s: En WB flush during H8: failed: %d\n", __func__, ret); - ufshcd_wb_toggle_flush(hba, true); + if (!(hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL)) + ufshcd_wb_toggle_flush(hba, true); } static void ufshcd_scsi_unblock_requests(struct ufs_hba *hba) @@ -5436,9 +5437,6 @@ static int ufshcd_wb_toggle_flush_during_h8(struct ufs_hba *hba, bool set) static inline void ufshcd_wb_toggle_flush(struct ufs_hba *hba, bool enable) { - if (hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL) - return; - if (enable) ufshcd_wb_buf_flush_enable(hba); else @@ -6661,19 +6659,16 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd) { struct Scsi_Host *host; struct ufs_hba *hba; - unsigned int tag; u32 pos; int err; - u8 resp = 0xF; - struct ufshcd_lrb *lrbp; + u8 resp = 0xF, lun; unsigned long flags; host = cmd->device->host; hba = shost_priv(host); - tag = cmd->request->tag; - lrbp = &hba->lrb[tag]; - err = ufshcd_issue_tm_cmd(hba, lrbp->lun, 0, UFS_LOGICAL_RESET, &resp); + lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun); + err = ufshcd_issue_tm_cmd(hba, lun, 0, UFS_LOGICAL_RESET, &resp); if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) { if (!err) err = resp; @@ -6682,7 +6677,7 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd) /* clear the commands that were pending for corresponding LUN */ for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) { - if (hba->lrb[pos].lun == lrbp->lun) { + if (hba->lrb[pos].lun == lun) { err = ufshcd_clear_cmd(hba, pos); if (err) break; @@ -8698,6 +8693,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) ufshcd_wb_need_flush(hba)); } + flush_work(&hba->eeh_work); + if (req_dev_pwr_mode != hba->curr_dev_pwr_mode) { if (!ufshcd_is_runtime_pm(pm_op)) /* ensure that bkops is disabled */ @@ -8710,8 +8707,6 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) } } - flush_work(&hba->eeh_work); - /* * In the case of DeepSleep, the device is expected to remain powered * with the link off, so do not check for bkops. @@ -8938,7 +8933,8 @@ int ufshcd_system_suspend(struct ufs_hba *hba) if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) == hba->curr_dev_pwr_mode) && (ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) == - hba->uic_link_state)) + hba->uic_link_state) && + !hba->dev_info.b_rpm_dev_flush_capable) goto out; if (pm_runtime_suspended(hba->dev)) { diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c index 1066eebe3b28..328d5a78792f 100644 --- a/drivers/tty/serial/sifive.c +++ b/drivers/tty/serial/sifive.c @@ -1000,6 +1000,7 @@ static int sifive_serial_probe(struct platform_device *pdev) /* Set up clock divider */ ssp->clkin_rate = clk_get_rate(ssp->clk); ssp->baud_rate = SIFIVE_DEFAULT_BAUD_RATE; + ssp->port.uartclk = ssp->baud_rate * 16; __ssp_update_div(ssp); platform_set_drvdata(pdev, ssp); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index b9df85506938..5d39129406ea 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -3740,7 +3740,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses, if (!ses->binding) { ses->capabilities = server->capabilities; - if (linuxExtEnabled == 0) + if (!linuxExtEnabled) ses->capabilities &= (~server->vals->cap_unix); if (ses->auth_key.response) { diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 6ad6ba5f6ebe..0fdb0de7ff86 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1260,7 +1260,8 @@ void dfs_cache_del_vol(const char *fullpath) vi = find_vol(fullpath); spin_unlock(&vol_list_lock); - kref_put(&vi->refcnt, vol_release); + if (!IS_ERR(vi)) + kref_put(&vi->refcnt, vol_release); } /** diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 0afccbbed2e6..076bcadc756a 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -303,8 +303,6 @@ do { \ int smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx) { - int rc = 0; - memcpy(new_ctx, ctx, sizeof(*ctx)); new_ctx->prepath = NULL; new_ctx->mount_options = NULL; @@ -327,7 +325,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx DUP_CTX_STR(nodename); DUP_CTX_STR(iocharset); - return rc; + return 0; } static int diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 067eb44c7baa..794fc3b68b4f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3248,7 +3248,7 @@ close_exit: free_rsp_buf(resp_buftype, rsp); /* retry close in a worker thread if this one is interrupted */ - if (rc == -EINTR) { + if (is_interrupt_error(rc)) { int tmp_rc; tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 204a622b89ed..d85edf5d1429 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -424,7 +424,7 @@ struct smb2_rdma_transform_capabilities_context { __le16 TransformCount; __u16 Reserved1; __u32 Reserved2; - __le16 RDMATransformIds[1]; + __le16 RDMATransformIds[]; } __packed; /* Signing algorithms */ diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 1a0a827a7f34..be799040a415 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -372,20 +372,3 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, } return err; } - -int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb) -{ - struct buffer_head *bh = EXT4_SB(sb)->s_sbh; - int err = 0; - - ext4_superblock_csum_set(sb); - if (ext4_handle_valid(handle)) { - err = jbd2_journal_dirty_metadata(handle, bh); - if (err) - ext4_journal_abort_handle(where, line, __func__, - bh, handle, err); - } else - mark_buffer_dirty(bh); - return err; -} diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index a124c68b0c75..0d2fa423b7ad 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -244,9 +244,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct buffer_head *bh); -int __ext4_handle_dirty_super(const char *where, unsigned int line, - handle_t *handle, struct super_block *sb); - #define ext4_journal_get_write_access(handle, bh) \ __ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh)) #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \ @@ -257,8 +254,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line, #define ext4_handle_dirty_metadata(handle, inode, bh) \ __ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \ (bh)) -#define ext4_handle_dirty_super(handle, sb) \ - __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb)) handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line, int type, int blocks, int rsv_blocks, diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 4fcc21c25e79..0a14a7c87bf8 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -604,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star trace_ext4_fc_track_range(inode, start, end, ret); } -static void ext4_fc_submit_bh(struct super_block *sb) +static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail) { int write_flags = REQ_SYNC; struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh; - /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */ - if (test_opt(sb, BARRIER)) + /* Add REQ_FUA | REQ_PREFLUSH only its tail */ + if (test_opt(sb, BARRIER) && is_tail) write_flags |= REQ_FUA | REQ_PREFLUSH; lock_buffer(bh); set_buffer_dirty(bh); @@ -684,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc) *crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl)); if (pad_len > 0) ext4_fc_memzero(sb, tl + 1, pad_len, crc); - ext4_fc_submit_bh(sb); + ext4_fc_submit_bh(sb, false); ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh); if (ret) @@ -741,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc) tail.fc_crc = cpu_to_le32(crc); ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL); - ext4_fc_submit_bh(sb); + ext4_fc_submit_bh(sb, true); return 0; } @@ -1268,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full) list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING], &sbi->s_fc_dentry_q[FC_Q_MAIN]); list_splice_init(&sbi->s_fc_q[FC_Q_STAGING], - &sbi->s_fc_q[FC_Q_STAGING]); + &sbi->s_fc_q[FC_Q_MAIN]); ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); @@ -1318,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl) entry.len = darg.dname_len; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found", darg.ino); return 0; } old_parent = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(old_parent)) { + if (IS_ERR(old_parent)) { jbd_debug(1, "Dir with inode %d not found", darg.parent_ino); iput(inode); return 0; @@ -1410,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl) darg.parent_ino, darg.dname_len); inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; } @@ -1466,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) trace_ext4_fc_replay(sb, tag, ino, 0, 0); inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); - if (!IS_ERR_OR_NULL(inode)) { + if (!IS_ERR(inode)) { ext4_ext_clear_bb(inode); iput(inode); } + inode = NULL; ext4_fc_record_modified_inode(sb, ino); @@ -1512,7 +1513,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl) /* Given that we just wrote the inode on disk, this SHOULD succeed. */ inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return -EFSCORRUPTED; } @@ -1564,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) goto out; inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "inode %d not found.", darg.ino); inode = NULL; ret = -EINVAL; @@ -1577,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl) * dot and dot dot dirents are setup properly. */ dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(dir)) { + if (IS_ERR(dir)) { jbd_debug(1, "Dir %d not found.", darg.ino); goto out; } @@ -1653,7 +1654,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb, inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino), EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode not found."); return 0; } @@ -1777,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl) le32_to_cpu(lrange->fc_ino), cur, remaining); inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino)); return 0; } @@ -1832,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) for (i = 0; i < state->fc_modified_inodes_used; i++) { inode = ext4_iget(sb, state->fc_modified_inodes[i], EXT4_IGET_NORMAL); - if (IS_ERR_OR_NULL(inode)) { + if (IS_ERR(inode)) { jbd_debug(1, "Inode %d not found.", state->fc_modified_inodes[i]); continue; @@ -1849,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb) if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, NULL, 0); - if (!IS_ERR_OR_NULL(path)) { + if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, 1); diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 3ed8c048fb12..349b27f0dda0 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -809,9 +809,12 @@ static int ext4_sample_last_mounted(struct super_block *sb, err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto out_journal; - strlcpy(sbi->s_es->s_last_mounted, cp, + lock_buffer(sbi->s_sbh); + strncpy(sbi->s_es->s_last_mounted, cp, sizeof(sbi->s_es->s_last_mounted)); - ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); + ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); out_journal: ext4_journal_stop(handle); out: diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 27946882d4ce..c173c8405856 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5150,9 +5150,13 @@ static int ext4_do_update_inode(handle_t *handle, err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh); if (err) goto out_brelse; + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_large_file(sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_sync(handle); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, + EXT4_SB(sb)->s_sbh); } ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_brelse: diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 524e13432447..d9665d2f82db 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1157,7 +1157,10 @@ resizefs_out: err = ext4_journal_get_write_access(handle, sbi->s_sbh); if (err) goto pwsalt_err_journal; + lock_buffer(sbi->s_sbh); generate_random_uuid(sbi->s_es->s_encrypt_pw_salt); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); pwsalt_err_journal: diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b17a082b7db1..cf652ba3e74d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2976,14 +2976,17 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) (le32_to_cpu(sbi->s_es->s_inodes_count))) { /* Insert this inode at the head of the on-disk orphan list */ NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan); + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); dirty = true; } list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan); mutex_unlock(&sbi->s_orphan_lock); if (dirty) { - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; @@ -3059,9 +3062,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode) mutex_unlock(&sbi->s_orphan_lock); goto out_brelse; } + lock_buffer(sbi->s_sbh); sbi->s_es->s_last_orphan = cpu_to_le32(ino_next); + ext4_superblock_csum_set(inode->i_sb); + unlock_buffer(sbi->s_sbh); mutex_unlock(&sbi->s_orphan_lock); - err = ext4_handle_dirty_super(handle, inode->i_sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); } else { struct ext4_iloc iloc2; struct inode *i_prev = @@ -3593,9 +3599,6 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, return retval2; } } - brelse(ent->bh); - ent->bh = NULL; - return retval; } @@ -3794,6 +3797,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, } } + old_file_type = old.de->file_type; if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir)) ext4_handle_sync(handle); @@ -3821,7 +3825,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, force_reread = (new.dir->i_ino == old.dir->i_ino && ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA)); - old_file_type = old.de->file_type; if (whiteout) { /* * Do this before adding a new entry, so the old entry is sure @@ -3919,15 +3922,19 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, retval = 0; end_rename: - brelse(old.dir_bh); - brelse(old.bh); - brelse(new.bh); if (whiteout) { - if (retval) + if (retval) { + ext4_setent(handle, &old, + old.inode->i_ino, old_file_type); drop_nlink(whiteout); + } unlock_new_inode(whiteout); iput(whiteout); + } + brelse(old.dir_bh); + brelse(old.bh); + brelse(new.bh); if (handle) ext4_journal_stop(handle); return retval; diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 928700d57eb6..bd0d185654f3 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -899,8 +899,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, EXT4_SB(sb)->s_gdb_count++; ext4_kvfree_array_rcu(o_group_desc); + lock_buffer(EXT4_SB(sb)->s_sbh); le16_add_cpu(&es->s_reserved_gdt_blocks, -1); - err = ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); if (err) ext4_std_error(sb, err); return err; @@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb, reserved_blocks *= blocks_count; do_div(reserved_blocks, 100); + lock_buffer(sbi->s_sbh); ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks); le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) * @@ -1421,6 +1425,8 @@ static void ext4_update_super(struct super_block *sb, * active. */ ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) + reserved_blocks); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); /* Update the free space counts */ percpu_counter_add(&sbi->s_freeclusters_counter, @@ -1515,7 +1521,7 @@ static int ext4_flex_group_add(struct super_block *sb, ext4_update_super(sb, flex_gd); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); exit_journal: err2 = ext4_journal_stop(handle); @@ -1717,15 +1723,18 @@ static int ext4_group_extend_no_check(struct super_block *sb, goto errout; } + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_blocks_count_set(es, o_blocks_count + add); ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); /* We add the blocks to the bitmap and set the group need init bit */ err = ext4_group_add_blocks(handle, sb, o_blocks_count, add); if (err) goto errout; - ext4_handle_dirty_super(handle, sb); + ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); ext4_debug("freed blocks %llu through %llu\n", o_blocks_count, o_blocks_count + add); errout: @@ -1874,12 +1883,15 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode) if (err) goto errout; + lock_buffer(sbi->s_sbh); ext4_clear_feature_resize_inode(sb); ext4_set_feature_meta_bg(sb); sbi->s_es->s_first_meta_bg = cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count)); + ext4_superblock_csum_set(sb); + unlock_buffer(sbi->s_sbh); - err = ext4_handle_dirty_super(handle, sb); + err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh); if (err) { ext4_std_error(sb, err); goto errout; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 21121787c874..9a6f9875aa34 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -65,7 +65,8 @@ static struct ratelimit_state ext4_mount_msg_ratelimit; static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); -static int ext4_commit_super(struct super_block *sb, int sync); +static void ext4_update_super(struct super_block *sb); +static int ext4_commit_super(struct super_block *sb); static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); static int ext4_clear_journal_err(struct super_block *sb, @@ -586,15 +587,12 @@ static int ext4_errno_to_code(int errno) return EXT4_ERR_UNKNOWN; } -static void __save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) +static void save_error_info(struct super_block *sb, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { struct ext4_sb_info *sbi = EXT4_SB(sb); - EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; - if (bdev_read_only(sb->s_bdev)) - return; /* We default to EFSCORRUPTED error... */ if (error == 0) error = EFSCORRUPTED; @@ -618,15 +616,6 @@ static void __save_error_info(struct super_block *sb, int error, spin_unlock(&sbi->s_error_lock); } -static void save_error_info(struct super_block *sb, int error, - __u32 ino, __u64 block, - const char *func, unsigned int line) -{ - __save_error_info(sb, error, ino, block, func, line); - if (!bdev_read_only(sb->s_bdev)) - ext4_commit_super(sb, 1); -} - /* Deal with the reporting of failure conditions on a filesystem such as * inconsistencies detected or read IO failures. * @@ -647,19 +636,40 @@ static void save_error_info(struct super_block *sb, int error, * used to deal with unrecoverable failures such as journal IO errors or ENOMEM * at a critical moment in log management. */ -static void ext4_handle_error(struct super_block *sb, bool force_ro) +static void ext4_handle_error(struct super_block *sb, bool force_ro, int error, + __u32 ino, __u64 block, + const char *func, unsigned int line) { journal_t *journal = EXT4_SB(sb)->s_journal; + bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT); + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - if (sb_rdonly(sb) || (!force_ro && test_opt(sb, ERRORS_CONT))) + if (!continue_fs && !sb_rdonly(sb)) { + ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); + if (journal) + jbd2_journal_abort(journal, -EIO); + } + + if (!bdev_read_only(sb->s_bdev)) { + save_error_info(sb, error, ino, block, func, line); + /* + * In case the fs should keep running, we need to writeout + * superblock through the journal. Due to lock ordering + * constraints, it may not be safe to do it right here so we + * defer superblock flushing to a workqueue. + */ + if (continue_fs) + schedule_work(&EXT4_SB(sb)->s_error_work); + else + ext4_commit_super(sb); + } + + if (sb_rdonly(sb) || continue_fs) return; - ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED); - if (journal) - jbd2_journal_abort(journal, -EIO); /* * We force ERRORS_RO behavior when system is rebooting. Otherwise we * could panic during 'reboot -f' as the underlying device got already @@ -682,8 +692,39 @@ static void flush_stashed_error_work(struct work_struct *work) { struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info, s_error_work); + journal_t *journal = sbi->s_journal; + handle_t *handle; - ext4_commit_super(sbi->s_sb, 1); + /* + * If the journal is still running, we have to write out superblock + * through the journal to avoid collisions of other journalled sb + * updates. + * + * We use directly jbd2 functions here to avoid recursing back into + * ext4 error handling code during handling of previous errors. + */ + if (!sb_rdonly(sbi->s_sb) && journal) { + handle = jbd2_journal_start(journal, 1); + if (IS_ERR(handle)) + goto write_directly; + if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) { + jbd2_journal_stop(handle); + goto write_directly; + } + ext4_update_super(sbi->s_sb); + if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) { + jbd2_journal_stop(handle); + goto write_directly; + } + jbd2_journal_stop(handle); + return; + } +write_directly: + /* + * Write through journal failed. Write sb directly to get error info + * out and hope for the best. + */ + ext4_commit_super(sbi->s_sb); } #define ext4_error_ratelimit(sb) \ @@ -710,8 +751,7 @@ void __ext4_error(struct super_block *sb, const char *function, sb->s_id, function, line, current->comm, &vaf); va_end(args); } - save_error_info(sb, error, 0, block, function, line); - ext4_handle_error(sb, force_ro); + ext4_handle_error(sb, force_ro, error, 0, block, function, line); } void __ext4_error_inode(struct inode *inode, const char *function, @@ -741,9 +781,8 @@ void __ext4_error_inode(struct inode *inode, const char *function, current->comm, &vaf); va_end(args); } - save_error_info(inode->i_sb, error, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb, false); + ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block, + function, line); } void __ext4_error_file(struct file *file, const char *function, @@ -780,9 +819,8 @@ void __ext4_error_file(struct file *file, const char *function, current->comm, path, &vaf); va_end(args); } - save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block, - function, line); - ext4_handle_error(inode->i_sb, false); + ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block, + function, line); } const char *ext4_decode_error(struct super_block *sb, int errno, @@ -849,8 +887,7 @@ void __ext4_std_error(struct super_block *sb, const char *function, sb->s_id, function, line, errstr); } - save_error_info(sb, -errno, 0, 0, function, line); - ext4_handle_error(sb, false); + ext4_handle_error(sb, false, -errno, 0, 0, function, line); } void __ext4_msg(struct super_block *sb, @@ -944,13 +981,16 @@ __acquires(bitlock) if (test_opt(sb, ERRORS_CONT)) { if (test_opt(sb, WARN_ON_ERROR)) WARN_ON_ONCE(1); - __save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - schedule_work(&EXT4_SB(sb)->s_error_work); + EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; + if (!bdev_read_only(sb->s_bdev)) { + save_error_info(sb, EFSCORRUPTED, ino, block, function, + line); + schedule_work(&EXT4_SB(sb)->s_error_work); + } return; } ext4_unlock_group(sb, grp); - save_error_info(sb, EFSCORRUPTED, ino, block, function, line); - ext4_handle_error(sb, false); + ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line); /* * We only get here in the ERRORS_RO case; relocking the group * may be dangerous, but nothing bad will happen since the @@ -1152,7 +1192,7 @@ static void ext4_put_super(struct super_block *sb) es->s_state = cpu_to_le16(sbi->s_mount_state); } if (!sb_rdonly(sb)) - ext4_commit_super(sb, 1); + ext4_commit_super(sb); rcu_read_lock(); group_desc = rcu_dereference(sbi->s_group_desc); @@ -2642,7 +2682,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es, if (sbi->s_journal) ext4_set_feature_journal_needs_recovery(sb); - err = ext4_commit_super(sb, 1); + err = ext4_commit_super(sb); done: if (test_opt(sb, DEBUG)) printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, " @@ -4868,7 +4908,7 @@ no_journal: if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) && !ext4_has_feature_encrypt(sb)) { ext4_set_feature_encrypt(sb); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } /* @@ -5418,7 +5458,7 @@ static int ext4_load_journal(struct super_block *sb, es->s_journal_dev = cpu_to_le32(journal_devnum); /* Make sure we flush the recovery flag to disk. */ - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } return 0; @@ -5428,16 +5468,14 @@ err_out: return err; } -static int ext4_commit_super(struct super_block *sb, int sync) +/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */ +static void ext4_update_super(struct super_block *sb) { struct ext4_sb_info *sbi = EXT4_SB(sb); - struct ext4_super_block *es = EXT4_SB(sb)->s_es; - struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; - int error = 0; - - if (!sbh || block_device_ejected(sb)) - return error; + struct ext4_super_block *es = sbi->s_es; + struct buffer_head *sbh = sbi->s_sbh; + lock_buffer(sbh); /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock @@ -5451,17 +5489,17 @@ static int ext4_commit_super(struct super_block *sb, int sync) if (!(sb->s_flags & SB_RDONLY)) ext4_update_tstamp(es, s_wtime); es->s_kbytes_written = - cpu_to_le64(EXT4_SB(sb)->s_kbytes_written + + cpu_to_le64(sbi->s_kbytes_written + ((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) - - EXT4_SB(sb)->s_sectors_written_start) >> 1)); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter)) + sbi->s_sectors_written_start) >> 1)); + if (percpu_counter_initialized(&sbi->s_freeclusters_counter)) ext4_free_blocks_count_set(es, - EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeclusters_counter))); - if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter)) + EXT4_C2B(sbi, percpu_counter_sum_positive( + &sbi->s_freeclusters_counter))); + if (percpu_counter_initialized(&sbi->s_freeinodes_counter)) es->s_free_inodes_count = cpu_to_le32(percpu_counter_sum_positive( - &EXT4_SB(sb)->s_freeinodes_counter)); + &sbi->s_freeinodes_counter)); /* Copy error information to the on-disk superblock */ spin_lock(&sbi->s_error_lock); if (sbi->s_add_error_count > 0) { @@ -5502,10 +5540,20 @@ static int ext4_commit_super(struct super_block *sb, int sync) } spin_unlock(&sbi->s_error_lock); - BUFFER_TRACE(sbh, "marking dirty"); ext4_superblock_csum_set(sb); - if (sync) - lock_buffer(sbh); + unlock_buffer(sbh); +} + +static int ext4_commit_super(struct super_block *sb) +{ + struct buffer_head *sbh = EXT4_SB(sb)->s_sbh; + int error = 0; + + if (!sbh || block_device_ejected(sb)) + return error; + + ext4_update_super(sb); + if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) { /* * Oh, dear. A previous attempt to write the @@ -5520,17 +5568,15 @@ static int ext4_commit_super(struct super_block *sb, int sync) clear_buffer_write_io_error(sbh); set_buffer_uptodate(sbh); } + BUFFER_TRACE(sbh, "marking dirty"); mark_buffer_dirty(sbh); - if (sync) { - unlock_buffer(sbh); - error = __sync_dirty_buffer(sbh, - REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); - if (buffer_write_io_error(sbh)) { - ext4_msg(sb, KERN_ERR, "I/O error while writing " - "superblock"); - clear_buffer_write_io_error(sbh); - set_buffer_uptodate(sbh); - } + error = __sync_dirty_buffer(sbh, + REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0)); + if (buffer_write_io_error(sbh)) { + ext4_msg(sb, KERN_ERR, "I/O error while writing " + "superblock"); + clear_buffer_write_io_error(sbh); + set_buffer_uptodate(sbh); } return error; } @@ -5561,7 +5607,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb, if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); } out: jbd2_journal_unlock_updates(journal); @@ -5603,7 +5649,7 @@ static int ext4_clear_journal_err(struct super_block *sb, EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS; es->s_state |= cpu_to_le16(EXT4_ERROR_FS); - ext4_commit_super(sb, 1); + ext4_commit_super(sb); jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); @@ -5705,7 +5751,7 @@ static int ext4_freeze(struct super_block *sb) ext4_clear_feature_journal_needs_recovery(sb); } - error = ext4_commit_super(sb, 1); + error = ext4_commit_super(sb); out: if (journal) /* we rely on upper layer to stop further updates */ @@ -5727,7 +5773,7 @@ static int ext4_unfreeze(struct super_block *sb) ext4_set_feature_journal_needs_recovery(sb); } - ext4_commit_super(sb, 1); + ext4_commit_super(sb); return 0; } @@ -5987,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { - err = ext4_commit_super(sb, 1); + err = ext4_commit_super(sb); if (err) goto restore_opts; } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 4e3b1f8c2e81..372208500f4e 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -792,8 +792,11 @@ static void ext4_xattr_update_super_block(handle_t *handle, BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) { + lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_xattr(sb); - ext4_handle_dirty_super(handle, sb); + ext4_superblock_csum_set(sb); + unlock_buffer(EXT4_SB(sb)->s_sbh); + ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); } } diff --git a/fs/io_uring.c b/fs/io_uring.c index 2f305c097bd5..985a9e3f976d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -354,6 +354,7 @@ struct io_ring_ctx { unsigned cq_entries; unsigned cq_mask; atomic_t cq_timeouts; + unsigned cq_last_tm_flush; unsigned long cq_check_overflow; struct wait_queue_head cq_wait; struct fasync_struct *cq_fasync; @@ -1106,6 +1107,9 @@ static void io_sq_thread_drop_mm_files(void) static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx) { + if (current->flags & PF_EXITING) + return -EFAULT; + if (!current->files) { struct files_struct *files; struct nsproxy *nsproxy; @@ -1133,6 +1137,8 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx) { struct mm_struct *mm; + if (current->flags & PF_EXITING) + return -EFAULT; if (current->mm) return 0; @@ -1634,19 +1640,38 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) static void io_flush_timeouts(struct io_ring_ctx *ctx) { - while (!list_empty(&ctx->timeout_list)) { + u32 seq; + + if (list_empty(&ctx->timeout_list)) + return; + + seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); + + do { + u32 events_needed, events_got; struct io_kiocb *req = list_first_entry(&ctx->timeout_list, struct io_kiocb, timeout.list); if (io_is_timeout_noseq(req)) break; - if (req->timeout.target_seq != ctx->cached_cq_tail - - atomic_read(&ctx->cq_timeouts)) + + /* + * Since seq can easily wrap around over time, subtract + * the last seq at which timeouts were flushed before comparing. + * Assuming not more than 2^31-1 events have happened since, + * these subtractions won't have wrapped, so we can check if + * target is in [last_seq, current_seq] by comparing the two. + */ + events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush; + events_got = seq - ctx->cq_last_tm_flush; + if (events_got < events_needed) break; list_del_init(&req->timeout.list); io_kill_timeout(req); - } + } while (!list_empty(&ctx->timeout_list)); + + ctx->cq_last_tm_flush = seq; } static void io_commit_cqring(struct io_ring_ctx *ctx) @@ -5832,6 +5857,12 @@ static int io_timeout(struct io_kiocb *req) tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); req->timeout.target_seq = tail + off; + /* Update the last seq here in case io_flush_timeouts() hasn't. + * This is safe because ->completion_lock is held, and submissions + * and completions are never mixed in the same ->completion_lock section. + */ + ctx->cq_last_tm_flush = tail; + /* * Insertion sort, ensuring the first entry in the list is always * the one we need first. @@ -7056,6 +7087,7 @@ static int io_sq_thread(void *data) if (sqt_spin || !time_after(jiffies, timeout)) { io_run_task_work(); + io_sq_thread_drop_mm_files(); cond_resched(); if (sqt_spin) timeout = jiffies + sqd->sq_thread_idle; @@ -7093,6 +7125,7 @@ static int io_sq_thread(void *data) } io_run_task_work(); + io_sq_thread_drop_mm_files(); if (cur_css) io_sq_thread_unassociate_blkcg(); @@ -8888,7 +8921,8 @@ static void io_disable_sqo_submit(struct io_ring_ctx *ctx) mutex_unlock(&ctx->uring_lock); /* make sure callers enter the ring to get error */ - io_ring_set_wakeup_flag(ctx); + if (ctx->rings) + io_ring_set_wakeup_flag(ctx); } /* @@ -9067,6 +9101,7 @@ void __io_uring_task_cancel(void) finish_wait(&tctx->wait, &wait); } while (1); + finish_wait(&tctx->wait, &wait); atomic_dec(&tctx->in_idle); io_uring_remove_task_files(tctx); @@ -9700,6 +9735,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p, */ ret = io_uring_install_fd(ctx, file); if (ret < 0) { + io_disable_sqo_submit(ctx); /* fput will clean it up */ fput(file); return ret; diff --git a/fs/namespace.c b/fs/namespace.c index d2db7dfe232b..9d33909d0f9e 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1713,8 +1713,6 @@ static int can_umount(const struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); - if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) - return -EINVAL; if (!may_mount()) return -EPERM; if (path->dentry != path->mnt->mnt_root) @@ -1728,6 +1726,7 @@ static int can_umount(const struct path *path, int flags) return 0; } +// caller is responsible for flags being sane int path_umount(struct path *path, int flags) { struct mount *mnt = real_mount(path->mnt); @@ -1749,6 +1748,10 @@ static int ksys_umount(char __user *name, int flags) struct path path; int ret; + // basic validity checks done first + if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW)) + return -EINVAL; + if (!(flags & UMOUNT_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; ret = user_path_at(AT_FDCWD, name, lookup_flags, &path); diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ee5a235b3056..602e3a52884d 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1035,6 +1035,25 @@ struct clear_refs_private { }; #ifdef CONFIG_MEM_SOFT_DIRTY + +#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE) + +static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte) +{ + struct page *page; + + if (!pte_write(pte)) + return false; + if (!is_cow_mapping(vma->vm_flags)) + return false; + if (likely(!atomic_read(&vma->vm_mm->has_pinned))) + return false; + page = vm_normal_page(vma, addr, pte); + if (!page) + return false; + return page_maybe_dma_pinned(page); +} + static inline void clear_soft_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { @@ -1049,6 +1068,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, if (pte_present(ptent)) { pte_t old_pte; + if (pte_is_pinned(vma, addr, ptent)) + return; old_pte = ptep_modify_prot_start(vma, addr, pte); ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); @@ -1215,41 +1236,26 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, .type = type, }; + if (mmap_write_lock_killable(mm)) { + count = -EINTR; + goto out_mm; + } if (type == CLEAR_REFS_MM_HIWATER_RSS) { - if (mmap_write_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } - /* * Writing 5 to /proc/pid/clear_refs resets the peak * resident set size to this mm's current rss value. */ reset_mm_hiwater_rss(mm); - mmap_write_unlock(mm); - goto out_mm; + goto out_unlock; } - if (mmap_read_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } tlb_gather_mmu(&tlb, mm, 0, -1); if (type == CLEAR_REFS_SOFT_DIRTY) { for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!(vma->vm_flags & VM_SOFTDIRTY)) continue; - mmap_read_unlock(mm); - if (mmap_write_lock_killable(mm)) { - count = -EINTR; - goto out_mm; - } - for (vma = mm->mmap; vma; vma = vma->vm_next) { - vma->vm_flags &= ~VM_SOFTDIRTY; - vma_set_page_prot(vma); - } - mmap_write_downgrade(mm); - break; + vma->vm_flags &= ~VM_SOFTDIRTY; + vma_set_page_prot(vma); } mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY, @@ -1261,7 +1267,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, if (type == CLEAR_REFS_SOFT_DIRTY) mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb, 0, -1); - mmap_read_unlock(mm); +out_unlock: + mmap_write_unlock(mm); out_mm: mmput(mm); } diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index dd90c9792909..0e7316a86240 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -11,19 +11,19 @@ * See Documentation/atomic_bitops.txt for details. */ -static inline void set_bit(unsigned int nr, volatile unsigned long *p) +static __always_inline void set_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p); } -static inline void clear_bit(unsigned int nr, volatile unsigned long *p) +static __always_inline void clear_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p); } -static inline void change_bit(unsigned int nr, volatile unsigned long *p) +static __always_inline void change_bit(unsigned int nr, volatile unsigned long *p) { p += BIT_WORD(nr); atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p); diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 74c6c0486eed..555ab0fddbef 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -13,6 +13,12 @@ /* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */ #if GCC_VERSION < 40900 # error Sorry, your version of GCC is too old - please use 4.9 or newer. +#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100 +/* + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293 + * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk + */ +# error Sorry, your version of GCC is too old - please use 5.1 or newer. #endif /* diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h index 29d255fdd5d6..90bd558a17f5 100644 --- a/include/linux/dm-bufio.h +++ b/include/linux/dm-bufio.h @@ -150,6 +150,7 @@ void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n); unsigned dm_bufio_get_block_size(struct dm_bufio_client *c); sector_t dm_bufio_get_device_size(struct dm_bufio_client *c); +struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c); sector_t dm_bufio_get_block_number(struct dm_buffer *b); void *dm_bufio_get_block_data(struct dm_buffer *b); void *dm_bufio_get_aux_data(struct dm_buffer *b); diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 5e0655fb2a6f..fe1ae73ff8b5 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -35,8 +35,12 @@ struct kunit_kasan_expectation { #define KASAN_SHADOW_INIT 0 #endif +#ifndef PTE_HWTABLE_PTRS +#define PTE_HWTABLE_PTRS 0 +#endif + extern unsigned char kasan_early_shadow_page[PAGE_SIZE]; -extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE]; +extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]; extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD]; extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD]; extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D]; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d827bd7f3bfe..eeb0b52203e9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -665,7 +665,7 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, { struct mem_cgroup *memcg = page_memcg(page); - VM_WARN_ON_ONCE_PAGE(!memcg, page); + VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page); return mem_cgroup_lruvec(memcg, pgdat); } diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index bf7966776c55..505480217cf1 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -163,8 +163,6 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn); static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } #endif -bool arm_pmu_irq_is_nmi(void); - /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); struct arm_pmu *armpmu_alloc_atomic(void); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 1635111c5bd2..a21e6a5792c5 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1658,7 +1658,7 @@ static int copy_compat_iovec_from_user(struct iovec *iov, (const struct compat_iovec __user *)uvec; int ret = -EFAULT, i; - if (!user_access_begin(uvec, nr_segs * sizeof(*uvec))) + if (!user_access_begin(uiov, nr_segs * sizeof(*uiov))) return -EFAULT; for (i = 0; i < nr_segs; i++) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a2602969873d..18f6ee317900 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4371,7 +4371,7 @@ retry: * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(PageHWPoison(page))) { - ret = VM_FAULT_HWPOISON | + ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } diff --git a/mm/kasan/init.c b/mm/kasan/init.c index bc0ad208b3a7..7ca0b92d5886 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -64,7 +64,8 @@ static inline bool kasan_pmd_table(pud_t pud) return false; } #endif -pte_t kasan_early_shadow_pte[PTRS_PER_PTE] __page_aligned_bss; +pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS] + __page_aligned_bss; static inline bool kasan_pte_table(pmd_t pmd) { diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 5a38e9eade94..04d9f154a130 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1940,7 +1940,7 @@ retry: goto retry; } } else if (ret == -EIO) { - pr_info("%s: %#lx: unknown page type: %lx (%pGP)\n", + pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n", __func__, pfn, page->flags, &page->flags); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8cf96bd21341..2c3a86502053 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1111,7 +1111,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { int busy = 0; - int err; + int err = 0; nodemask_t tmp; migrate_prep(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bdbec4c98173..027f6481ba59 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2862,20 +2862,20 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype, { struct page *page; -#ifdef CONFIG_CMA - /* - * Balance movable allocations between regular and CMA areas by - * allocating from CMA when over half of the zone's free memory - * is in the CMA area. - */ - if (alloc_flags & ALLOC_CMA && - zone_page_state(zone, NR_FREE_CMA_PAGES) > - zone_page_state(zone, NR_FREE_PAGES) / 2) { - page = __rmqueue_cma_fallback(zone, order); - if (page) - return page; + if (IS_ENABLED(CONFIG_CMA)) { + /* + * Balance movable allocations between regular and CMA areas by + * allocating from CMA when over half of the zone's free memory + * is in the CMA area. + */ + if (alloc_flags & ALLOC_CMA && + zone_page_state(zone, NR_FREE_CMA_PAGES) > + zone_page_state(zone, NR_FREE_PAGES) / 2) { + page = __rmqueue_cma_fallback(zone, order); + if (page) + goto out; + } } -#endif retry: page = __rmqueue_smallest(zone, order, migratetype); if (unlikely(!page)) { @@ -2886,8 +2886,9 @@ retry: alloc_flags)) goto retry; } - - trace_mm_page_alloc_zone_locked(page, order, migratetype); +out: + if (page) + trace_mm_page_alloc_zone_locked(page, order, migratetype); return page; } diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 4bcc11958089..f5fee9cf90f8 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -9,6 +9,7 @@ #include <linux/mm.h> #include <linux/uio.h> #include <linux/sched.h> +#include <linux/compat.h> #include <linux/sched/mm.h> #include <linux/highmem.h> #include <linux/ptrace.h> diff --git a/mm/slub.c b/mm/slub.c index dc5b42e700b8..d9e4e10683cc 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1973,7 +1973,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, t = acquire_slab(s, n, page, object == NULL, &objects); if (!t) - break; + continue; /* cmpxchg raced */ available += objects; if (!object) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4d88fe5a277a..e6f352bf0498 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2420,8 +2420,10 @@ void *vmap(struct page **pages, unsigned int count, return NULL; } - if (flags & VM_MAP_PUT_PAGES) + if (flags & VM_MAP_PUT_PAGES) { area->pages = pages; + area->nr_pages = count; + } return area->addr; } EXPORT_SYMBOL(vmap); diff --git a/mm/vmscan.c b/mm/vmscan.c index 257cba79a96d..b1b574ad199d 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1238,6 +1238,8 @@ static unsigned int shrink_page_list(struct list_head *page_list, if (!PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; + if (page_maybe_dma_pinned(page)) + goto keep_locked; if (PageTransHuge(page)) { /* cannot split THP, skip it */ if (!can_split_huge_page(page, NULL)) diff --git a/security/lsm_audit.c b/security/lsm_audit.c index 7d8026f3f377..a0cd28cd31a8 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -275,7 +275,9 @@ static void dump_common_audit_data(struct audit_buffer *ab, struct inode *inode; audit_log_format(ab, " name="); + spin_lock(&a->u.dentry->d_lock); audit_log_untrustedstring(ab, a->u.dentry->d_name.name); + spin_unlock(&a->u.dentry->d_lock); inode = d_backing_inode(a->u.dentry); if (inode) { @@ -293,8 +295,9 @@ static void dump_common_audit_data(struct audit_buffer *ab, dentry = d_find_alias(inode); if (dentry) { audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, - dentry->d_name.name); + spin_lock(&dentry->d_lock); + audit_log_untrustedstring(ab, dentry->d_name.name); + spin_unlock(&dentry->d_lock); dput(dentry); } audit_log_format(ab, " dev="); diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S index 1c5556bdd11d..0dbd594c2747 100644 --- a/tools/testing/selftests/arm64/fp/fpsimd-test.S +++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S @@ -457,7 +457,7 @@ function barf mov x11, x1 // actual data mov x12, x2 // data size - puts "Mistatch: PID=" + puts "Mismatch: PID=" mov x0, x20 bl putdec puts ", iteration=" diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index f95074c9b48b..9210691aa998 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -625,7 +625,7 @@ function barf mov x11, x1 // actual data mov x12, x2 // data size - puts "Mistatch: PID=" + puts "Mismatch: PID=" mov x0, x20 bl putdec puts ", iteration=" |