diff --git a/arch/mips/vdso/vdso.h b/arch/mips/vdso/vdso.h index 14b1931be69c..b65b169778e3 100644 --- a/arch/mips/vdso/vdso.h +++ b/arch/mips/vdso/vdso.h @@ -9,6 +9,7 @@ #if _MIPS_SIM != _MIPS_SIM_ABI64 && defined(CONFIG_64BIT) /* Building 32-bit VDSO for the 64-bit kernel. Fake a 32-bit Kconfig. */ +#define BUILD_VDSO32_64 #undef CONFIG_64BIT #define CONFIG_32BIT 1 #ifndef __ASSEMBLY__ diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 0e28270b0fd8..aad6be5c0af0 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2204,6 +2204,12 @@ int __init acpi_scan_init(void) acpi_gpe_apply_masked_gpes(); acpi_update_all_gpes(); + /* + * Although we call __add_memory() that is documented to require the + * device_hotplug_lock, it is not necessary here because this is an + * early code when userspace or any other code path cannot trigger + * hotplug/hotunplug operations. + */ mutex_lock(&acpi_scan_lock); /* * Enumerate devices in the ACPI namespace. diff --git a/fs/coredump.c b/fs/coredump.c index e42e17e55bfd..b1ea7dfbd149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -187,11 +188,13 @@ static int cn_print_exe_file(struct core_name *cn) * name into corename, which must have space for at least * CORENAME_MAX_SIZE bytes plus one byte for the zero terminator. */ -static int format_corename(struct core_name *cn, struct coredump_params *cprm) +static int format_corename(struct core_name *cn, struct coredump_params *cprm, + size_t **argv, int *argc) { const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); + bool was_space = false; int pid_in_pattern = 0; int err = 0; @@ -201,12 +204,35 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm) return -ENOMEM; cn->corename[0] = '\0'; - if (ispipe) + if (ispipe) { + int argvs = sizeof(core_pattern) / 2; + (*argv) = kmalloc_array(argvs, sizeof(**argv), GFP_KERNEL); + if (!(*argv)) + return -ENOMEM; + (*argv)[(*argc)++] = 0; ++pat_ptr; + } /* Repeat as long as we have more pattern to process and more output space */ while (*pat_ptr) { + /* + * Split on spaces before doing template expansion so that + * %e and %E don't get split if they have spaces in them + */ + if (ispipe) { + if (isspace(*pat_ptr)) { + was_space = true; + pat_ptr++; + continue; + } else if (was_space) { + was_space = false; + err = cn_printf(cn, "%c", '\0'); + if (err) + return err; + (*argv)[(*argc)++] = cn->used; + } + } if (*pat_ptr != '%') { err = cn_printf(cn, "%c", *pat_ptr++); } else { @@ -546,6 +572,8 @@ void do_coredump(const kernel_siginfo_t *siginfo) struct cred *cred; int retval = 0; int ispipe; + size_t *argv = NULL; + int argc = 0; struct files_struct *displaced; /* require nonrelative corefile path and be extra careful */ bool need_suid_safe = false; @@ -592,9 +620,10 @@ void do_coredump(const kernel_siginfo_t *siginfo) old_cred = override_creds(cred); - ispipe = format_corename(&cn, &cprm); + ispipe = format_corename(&cn, &cprm, &argv, &argc); if (ispipe) { + int argi; int dump_count; char **helper_argv; struct subprocess_info *sub_info; @@ -637,12 +666,16 @@ void do_coredump(const kernel_siginfo_t *siginfo) goto fail_dropcount; } - helper_argv = argv_split(GFP_KERNEL, cn.corename, NULL); + helper_argv = kmalloc_array(argc + 1, sizeof(*helper_argv), + GFP_KERNEL); if (!helper_argv) { printk(KERN_WARNING "%s failed to allocate memory\n", __func__); goto fail_dropcount; } + for (argi = 0; argi < argc; argi++) + helper_argv[argi] = cn.corename + argv[argi]; + helper_argv[argi] = NULL; retval = -ENOMEM; sub_info = call_usermodehelper_setup(helper_argv[0], @@ -652,7 +685,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) retval = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC); - argv_free(helper_argv); + kfree(helper_argv); if (retval) { printk(KERN_INFO "Core dump to |%s pipe failed\n", cn.corename); @@ -766,6 +799,7 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (ispipe) atomic_dec(&core_dump_count); fail_unlock: + kfree(argv); kfree(cn.corename); coredump_finish(mm, core_dumped); revert_creds(old_cred); diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 385f3aaa2448..90c830e3758e 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -3825,7 +3825,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb); int low_bucket = 0, bucket, high_bucket; struct ocfs2_xattr_bucket *search; - u32 last_hash; u64 blkno, lower_blkno = 0; search = ocfs2_xattr_bucket_new(inode); @@ -3869,8 +3868,6 @@ static int ocfs2_xattr_bucket_find(struct inode *inode, if (xh->xh_count) xe = &xh->xh_entries[le16_to_cpu(xh->xh_count) - 1]; - last_hash = le32_to_cpu(xe->xe_name_hash); - /* record lower_blkno which may be the insert place. */ lower_blkno = blkno; diff --git a/include/asm-generic/getorder.h b/include/asm-generic/getorder.h index c64bea7a52be..e9f20b813a69 100644 --- a/include/asm-generic/getorder.h +++ b/include/asm-generic/getorder.h @@ -7,24 +7,6 @@ #include #include -/* - * Runtime evaluation of get_order() - */ -static inline __attribute_const__ -int __get_order(unsigned long size) -{ - int order; - - size--; - size >>= PAGE_SHIFT; -#if BITS_PER_LONG == 32 - order = fls(size); -#else - order = fls64(size); -#endif - return order; -} - /** * get_order - Determine the allocation order of a memory size * @size: The size for which to get the order @@ -43,19 +25,27 @@ int __get_order(unsigned long size) * to hold an object of the specified size. * * The result is undefined if the size is 0. - * - * This function may be used to initialise variables with compile time - * evaluations of constants. */ -#define get_order(n) \ -( \ - __builtin_constant_p(n) ? ( \ - ((n) == 0UL) ? BITS_PER_LONG - PAGE_SHIFT : \ - (((n) < (1UL << PAGE_SHIFT)) ? 0 : \ - ilog2((n) - 1) - PAGE_SHIFT + 1) \ - ) : \ - __get_order(n) \ -) +static inline __attribute_const__ int get_order(unsigned long size) +{ + if (__builtin_constant_p(size)) { + if (!size) + return BITS_PER_LONG - PAGE_SHIFT; + + if (size < (1UL << PAGE_SHIFT)) + return 0; + + return ilog2((size) - 1) - PAGE_SHIFT + 1; + } + + size--; + size >>= PAGE_SHIFT; +#if BITS_PER_LONG == 32 + return fls(size); +#else + return fls64(size); +#endif +} #endif /* __ASSEMBLY__ */ diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h index 1dda31825ec4..71283739ffd2 100644 --- a/include/linux/page-flags-layout.h +++ b/include/linux/page-flags-layout.h @@ -32,6 +32,7 @@ #endif /* CONFIG_SPARSEMEM */ +#ifndef BUILD_VDSO32_64 /* * page->flags layout: * @@ -76,20 +77,22 @@ #define LAST_CPUPID_SHIFT 0 #endif -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS +#ifdef CONFIG_KASAN_SW_TAGS +#define KASAN_TAG_WIDTH 8 +#else +#define KASAN_TAG_WIDTH 0 +#endif + +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT+LAST_CPUPID_SHIFT+KASAN_TAG_WIDTH \ + <= BITS_PER_LONG - NR_PAGEFLAGS #define LAST_CPUPID_WIDTH LAST_CPUPID_SHIFT #else #define LAST_CPUPID_WIDTH 0 #endif -#ifdef CONFIG_KASAN_SW_TAGS -#define KASAN_TAG_WIDTH 8 #if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH+LAST_CPUPID_WIDTH+KASAN_TAG_WIDTH \ > BITS_PER_LONG - NR_PAGEFLAGS -#error "KASAN: not enough bits in page flags for tag" -#endif -#else -#define KASAN_TAG_WIDTH 0 +#error "Not enough bits in page flags" #endif /* @@ -104,4 +107,5 @@ #define LAST_CPUPID_NOT_IN_PAGE_FLAGS #endif +#endif #endif /* _LINUX_PAGE_FLAGS_LAYOUT */ diff --git a/kernel/Makefile b/kernel/Makefile index a8d923b5481b..ef0d95a190b4 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -111,7 +111,6 @@ obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o obj-$(CONFIG_HAS_IOMEM) += iomem.o -obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_RSEQ) += rseq.o obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o diff --git a/kernel/signal.c b/kernel/signal.c index 349f5a67f100..e667be6907d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -349,7 +349,7 @@ void task_clear_jobctl_pending(struct task_struct *task, unsigned long mask) * @task has %JOBCTL_STOP_PENDING set and is participating in a group stop. * Group stop states are cleared and the group stop count is consumed if * %JOBCTL_STOP_CONSUME was set. If the consumption completes the group - * stop, the appropriate %SIGNAL_* flags are set. + * stop, the appropriate `SIGNAL_*` flags are set. * * CONTEXT: * Must be called with @task->sighand->siglock held. diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index 4fafba1a923b..7fa97a8b5717 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -106,7 +106,6 @@ endchoice config KASAN_STACK_ENABLE bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST - default !(CLANG_VERSION < 90000) depends on KASAN help The LLVM stack address sanitizer has a know problem that @@ -115,11 +114,11 @@ config KASAN_STACK_ENABLE Disabling asan-stack makes it safe to run kernels build with clang-8 with KASAN enabled, though it loses some of the functionality. - This feature is always disabled when compile-testing with clang-8 - or earlier to avoid cluttering the output in stack overflow - warnings, but clang-8 users can still enable it for builds without - CONFIG_COMPILE_TEST. On gcc and later clang versions it is - assumed to always be safe to use and enabled by default. + This feature is always disabled when compile-testing with clang + to avoid cluttering the output in stack overflow warnings, + but clang users can still enable it for builds without + CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe + to use and enabled by default. config KASAN_STACK int diff --git a/lib/Makefile b/lib/Makefile index 095601ce371d..29c02a924973 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -279,7 +279,8 @@ obj-$(CONFIG_UCS2_STRING) += ucs2_string.o obj-$(CONFIG_UBSAN) += ubsan.o UBSAN_SANITIZE_ubsan.o := n -CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +KASAN_SANITIZE_ubsan.o := n +CFLAGS_ubsan.o := $(call cc-option, -fno-stack-protector) $(DISABLE_STACKLEAK_PLUGIN) obj-$(CONFIG_SBITMAP) += sbitmap.o diff --git a/lib/test_meminit.c b/lib/test_meminit.c index 62d19f270cad..9729f271d150 100644 --- a/lib/test_meminit.c +++ b/lib/test_meminit.c @@ -222,7 +222,7 @@ static int __init do_kmem_cache_size(size_t size, bool want_ctor, * Copy the buffer to check that it's not wiped on * free(). */ - buf_copy = kmalloc(size, GFP_KERNEL); + buf_copy = kmalloc(size, GFP_ATOMIC); if (buf_copy) memcpy(buf_copy, buf, size); diff --git a/mm/Makefile b/mm/Makefile index 338e528ad436..d0b295c3b764 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -102,5 +102,6 @@ obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o +obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o diff --git a/mm/compaction.c b/mm/compaction.c index 9e1b9acb116b..952dc2fb24e5 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -842,13 +842,15 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, /* * Periodically drop the lock (if held) regardless of its - * contention, to give chance to IRQs. Abort async compaction - * if contended. + * contention, to give chance to IRQs. Abort completely if + * a fatal signal is pending. */ if (!(low_pfn % SWAP_CLUSTER_MAX) && compact_unlock_should_abort(&pgdat->lru_lock, - flags, &locked, cc)) - break; + flags, &locked, cc)) { + low_pfn = 0; + goto fatal_pending; + } if (!pfn_valid_within(low_pfn)) goto isolate_fail; @@ -1060,6 +1062,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, nr_scanned, nr_isolated); +fatal_pending: cc->total_migrate_scanned += nr_scanned; if (nr_isolated) count_compact_events(COMPACTISOLATED, nr_isolated); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index dbbd518fb6b3..6e9e8cca663e 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -114,7 +114,7 @@ /* GFP bitmask for kmemleak internal allocations */ #define gfp_kmemleak_mask(gfp) (((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \ __GFP_NORETRY | __GFP_NOMEMALLOC | \ - __GFP_NOWARN | __GFP_NOFAIL) + __GFP_NOWARN) /* scanning area inside a memory block */ struct kmemleak_scan_area { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2a9bbddb0e55..c73f09913165 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -132,7 +132,6 @@ static void release_memory_resource(struct resource *res) return; release_resource(res); kfree(res); - return; } #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE @@ -979,7 +978,6 @@ static void rollback_node_hotadd(int nid) arch_refresh_nodedata(nid, NULL); free_percpu(pgdat->per_cpu_nodestats); arch_free_nodedata(pgdat); - return; } diff --git a/kernel/memremap.c b/mm/memremap.c similarity index 100% rename from kernel/memremap.c rename to mm/memremap.c diff --git a/mm/migrate.c b/mm/migrate.c index 8992741f10aa..a42858d8e00b 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -767,12 +767,12 @@ static int __buffer_migrate_page(struct address_space *mapping, } bh = bh->b_this_page; } while (bh != head); - spin_unlock(&mapping->private_lock); if (busy) { if (invalidated) { rc = -EAGAIN; goto unlock_buffers; } + spin_unlock(&mapping->private_lock); invalidate_bh_lrus(); invalidated = true; goto recheck_buffers; @@ -805,6 +805,8 @@ static int __buffer_migrate_page(struct address_space *mapping, rc = MIGRATEPAGE_SUCCESS; unlock_buffers: + if (check_refs) + spin_unlock(&mapping->private_lock); bh = head; do { unlock_buffer(bh); @@ -2338,16 +2340,13 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, static void migrate_vma_collect(struct migrate_vma *migrate) { struct mmu_notifier_range range; - struct mm_walk mm_walk; - - mm_walk.pmd_entry = migrate_vma_collect_pmd; - mm_walk.pte_entry = NULL; - mm_walk.pte_hole = migrate_vma_collect_hole; - mm_walk.hugetlb_entry = NULL; - mm_walk.test_walk = NULL; - mm_walk.vma = migrate->vma; - mm_walk.mm = migrate->vma->vm_mm; - mm_walk.private = migrate; + struct mm_walk mm_walk = { + .pmd_entry = migrate_vma_collect_pmd, + .pte_hole = migrate_vma_collect_hole, + .vma = migrate->vma, + .mm = migrate->vma->vm_mm, + .private = migrate, + }; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm_walk.mm, migrate->start, diff --git a/mm/vmscan.c b/mm/vmscan.c index 44df66a98f2a..dbdc46a84f63 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -699,7 +699,14 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, unsigned long ret, freed = 0; struct shrinker *shrinker; - if (!mem_cgroup_is_root(memcg)) + /* + * The root memcg might be allocated even though memcg is disabled + * via "cgroup_disable=memory" boot parameter. This could make + * mem_cgroup_is_root() return false, then just run memcg slab + * shrink, but skip global shrink. This may result in premature + * oom. + */ + if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); if (!down_read_trylock(&shrinker_rwsem)) diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 4c223266299a..bdb69599c4bd 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -191,8 +191,7 @@ int cg_find_unified_root(char *root, size_t len) strtok(NULL, delim); strtok(NULL, delim); - if (strcmp(fs, "cgroup") == 0 && - strcmp(type, "cgroup2") == 0) { + if (strcmp(type, "cgroup2") == 0) { strncpy(root, mount, len); return 0; }