diff options
| -rw-r--r-- | .mailmap | 1 | ||||
| -rw-r--r-- | MAINTAINERS | 66 | ||||
| -rw-r--r-- | include/linux/alloc_tag.h | 12 | ||||
| -rw-r--r-- | include/linux/codetag.h | 8 | ||||
| -rw-r--r-- | include/linux/highmem.h | 10 | ||||
| -rw-r--r-- | include/linux/hugetlb.h | 5 | ||||
| -rw-r--r-- | include/linux/mm.h | 2 | ||||
| -rw-r--r-- | include/linux/mman.h | 2 | ||||
| -rw-r--r-- | include/linux/page-flags.h | 7 | ||||
| -rw-r--r-- | include/linux/percpu.h | 4 | ||||
| -rw-r--r-- | include/uapi/linux/taskstats.h | 47 | ||||
| -rw-r--r-- | kernel/module/main.c | 1 | ||||
| -rw-r--r-- | lib/alloc_tag.c | 87 | ||||
| -rw-r--r-- | lib/codetag.c | 5 | ||||
| -rw-r--r-- | mm/cma.c | 5 | ||||
| -rw-r--r-- | mm/hugetlb.c | 24 | ||||
| -rw-r--r-- | mm/kasan/shadow.c | 92 | ||||
| -rw-r--r-- | mm/memcontrol.c | 6 | ||||
| -rw-r--r-- | mm/mremap.c | 3 | ||||
| -rw-r--r-- | mm/page_alloc.c | 8 | ||||
| -rw-r--r-- | mm/truncate.c | 20 | ||||
| -rw-r--r-- | mm/vma.c | 1 | ||||
| -rw-r--r-- | mm/vmalloc.c | 13 |
23 files changed, 338 insertions, 91 deletions
@@ -313,6 +313,7 @@ Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com> Jan Kuliga <jtkuliga.kdev@gmail.com> <jankul@alatek.krakow.pl> Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@linux.intel.com> Jarkko Sakkinen <jarkko@kernel.org> <jarkko@profian.com> +Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@opinsys.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> diff --git a/MAINTAINERS b/MAINTAINERS index 3c6f9e70ace0..dd844ac8d910 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11106,6 +11106,14 @@ L: linuxppc-dev@lists.ozlabs.org S: Odd Fixes F: drivers/tty/hvc/ +HUNG TASK DETECTOR +M: Andrew Morton <akpm@linux-foundation.org> +R: Lance Yang <lance.yang@linux.dev> +L: linux-kernel@vger.kernel.org +S: Maintained +F: include/linux/hung_task.h +F: kernel/hung_task.c + I2C ACPI SUPPORT M: Mika Westerberg <westeri@kernel.org> L: linux-i2c@vger.kernel.org @@ -15561,6 +15569,41 @@ W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm F: mm/gup.c +MEMORY MANAGEMENT - KSM (Kernel Samepage Merging) +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Xu Xin <xu.xin16@zte.com.cn> +R: Chengming Zhou <chengming.zhou@linux.dev> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: Documentation/admin-guide/mm/ksm.rst +F: Documentation/mm/ksm.rst +F: include/linux/ksm.h +F: include/trace/events/ksm.h +F: mm/ksm.c + +MEMORY MANAGEMENT - MEMORY POLICY AND MIGRATION +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Zi Yan <ziy@nvidia.com> +R: Matthew Brost <matthew.brost@intel.com> +R: Joshua Hahn <joshua.hahnjy@gmail.com> +R: Rakie Kim <rakie.kim@sk.com> +R: Byungchul Park <byungchul@sk.com> +R: Gregory Price <gourry@gourry.net> +R: Ying Huang <ying.huang@linux.alibaba.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: include/linux/mempolicy.h +F: include/linux/migrate.h +F: mm/mempolicy.c +F: mm/migrate.c +F: mm/migrate_device.c + MEMORY MANAGEMENT - NUMA MEMBLOCKS AND NUMA EMULATION M: Andrew Morton <akpm@linux-foundation.org> M: Mike Rapoport <rppt@kernel.org> @@ -15573,7 +15616,7 @@ F: mm/numa_memblks.c MEMORY MANAGEMENT - PAGE ALLOCATOR M: Andrew Morton <akpm@linux-foundation.org> -R: Vlastimil Babka <vbabka@suse.cz> +M: Vlastimil Babka <vbabka@suse.cz> R: Suren Baghdasaryan <surenb@google.com> R: Michal Hocko <mhocko@suse.com> R: Brendan Jackman <jackmanb@google.com> @@ -15581,10 +15624,25 @@ R: Johannes Weiner <hannes@cmpxchg.org> R: Zi Yan <ziy@nvidia.com> L: linux-mm@kvack.org S: Maintained +F: include/linux/compaction.h +F: include/linux/gfp.h +F: include/linux/page-isolation.h F: mm/compaction.c F: mm/page_alloc.c -F: include/linux/gfp.h -F: include/linux/compaction.h +F: mm/page_isolation.c + +MEMORY MANAGEMENT - RECLAIM +M: Andrew Morton <akpm@linux-foundation.org> +M: Johannes Weiner <hannes@cmpxchg.org> +R: David Hildenbrand <david@redhat.com> +R: Michal Hocko <mhocko@kernel.org> +R: Qi Zheng <zhengqi.arch@bytedance.com> +R: Shakeel Butt <shakeel.butt@linux.dev> +R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +L: linux-mm@kvack.org +S: Maintained +F: mm/pt_reclaim.c +F: mm/vmscan.c MEMORY MANAGEMENT - RMAP (REVERSE MAPPING) M: Andrew Morton <akpm@linux-foundation.org> @@ -25912,7 +25970,7 @@ F: tools/testing/vsock/ VMALLOC M: Andrew Morton <akpm@linux-foundation.org> -R: Uladzislau Rezki <urezki@gmail.com> +M: Uladzislau Rezki <urezki@gmail.com> L: linux-mm@kvack.org S: Maintained W: http://www.linux-mm.org diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h index a946e0203e6d..8f7931eb7d16 100644 --- a/include/linux/alloc_tag.h +++ b/include/linux/alloc_tag.h @@ -104,6 +104,16 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); #else /* ARCH_NEEDS_WEAK_PER_CPU */ +#ifdef MODULE + +#define DEFINE_ALLOC_TAG(_alloc_tag) \ + static struct alloc_tag _alloc_tag __used __aligned(8) \ + __section(ALLOC_TAG_SECTION_NAME) = { \ + .ct = CODE_TAG_INIT, \ + .counters = NULL }; + +#else /* MODULE */ + #define DEFINE_ALLOC_TAG(_alloc_tag) \ static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr); \ static struct alloc_tag _alloc_tag __used __aligned(8) \ @@ -111,6 +121,8 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag); .ct = CODE_TAG_INIT, \ .counters = &_alloc_tag_cntr }; +#endif /* MODULE */ + #endif /* ARCH_NEEDS_WEAK_PER_CPU */ DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT, diff --git a/include/linux/codetag.h b/include/linux/codetag.h index d14dbd26b370..0ee4c21c6dbc 100644 --- a/include/linux/codetag.h +++ b/include/linux/codetag.h @@ -36,10 +36,10 @@ union codetag_ref { struct codetag_type_desc { const char *section; size_t tag_size; - void (*module_load)(struct codetag_type *cttype, - struct codetag_module *cmod); - void (*module_unload)(struct codetag_type *cttype, - struct codetag_module *cmod); + void (*module_load)(struct module *mod, + struct codetag *start, struct codetag *end); + void (*module_unload)(struct module *mod, + struct codetag *start, struct codetag *end); #ifdef CONFIG_MODULES void (*module_replaced)(struct module *mod, struct module *new_mod); bool (*needs_section_mem)(struct module *mod, unsigned long size); diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 5c6bea81a90e..c698f8415675 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -461,7 +461,7 @@ static inline void memcpy_from_folio(char *to, struct folio *folio, const char *from = kmap_local_folio(folio, offset); size_t chunk = len; - if (folio_test_highmem(folio) && + if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); @@ -489,7 +489,7 @@ static inline void memcpy_to_folio(struct folio *folio, size_t offset, char *to = kmap_local_folio(folio, offset); size_t chunk = len; - if (folio_test_highmem(folio) && + if (folio_test_partial_kmap(folio) && chunk > PAGE_SIZE - offset_in_page(offset)) chunk = PAGE_SIZE - offset_in_page(offset); memcpy(to, from, chunk); @@ -522,7 +522,7 @@ static inline __must_check void *folio_zero_tail(struct folio *folio, { size_t len = folio_size(folio) - offset; - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { @@ -560,7 +560,7 @@ static inline void folio_fill_tail(struct folio *folio, size_t offset, VM_BUG_ON(offset + len > folio_size(folio)); - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { size_t max = PAGE_SIZE - offset_in_page(offset); while (len > max) { @@ -597,7 +597,7 @@ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio, size_t offset = offset_in_folio(folio, pos); char *from = kmap_local_folio(folio, offset); - if (folio_test_highmem(folio)) { + if (folio_test_partial_kmap(folio)) { offset = offset_in_page(offset); len = min_t(size_t, len, PAGE_SIZE - offset); } else diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 8f3ac832ee7f..4861a7e304bb 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -275,6 +275,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, bool is_hugetlb_entry_migration(pte_t pte); bool is_hugetlb_entry_hwpoisoned(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void fixup_hugetlb_reservations(struct vm_area_struct *vma); #else /* !CONFIG_HUGETLB_PAGE */ @@ -468,6 +469,10 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } +static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ +} + #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write diff --git a/include/linux/mm.h b/include/linux/mm.h index bf55206935c4..fdda6b16263b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -385,7 +385,7 @@ extern unsigned int kobjsize(const void *objp); #endif #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR -# define VM_UFFD_MINOR_BIT 38 +# define VM_UFFD_MINOR_BIT 41 # define VM_UFFD_MINOR BIT(VM_UFFD_MINOR_BIT) /* UFFD minor faults */ #else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ # define VM_UFFD_MINOR VM_NONE diff --git a/include/linux/mman.h b/include/linux/mman.h index bce214fece16..f4c6346a8fcd 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -155,7 +155,9 @@ calc_vm_flag_bits(struct file *file, unsigned long flags) return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | +#ifdef CONFIG_TRANSPARENT_HUGEPAGE _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | +#endif arch_calc_vm_flag_bits(file, flags); } diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e6a21b62dcce..3b814ce08331 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -615,6 +615,13 @@ FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE) PAGEFLAG_FALSE(HighMem, highmem) #endif +/* Does kmap_local_folio() only allow access to one page of the folio? */ +#ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP +#define folio_test_partial_kmap(f) true +#else +#define folio_test_partial_kmap(f) folio_test_highmem(f) +#endif + #ifdef CONFIG_SWAP static __always_inline bool folio_test_swapcache(const struct folio *folio) { diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 52b5ea663b9f..85bf8dd9f087 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -15,11 +15,7 @@ /* enough to cover all DEFINE_PER_CPUs in modules */ #ifdef CONFIG_MODULES -#ifdef CONFIG_MEM_ALLOC_PROFILING -#define PERCPU_MODULE_RESERVE (8 << 13) -#else #define PERCPU_MODULE_RESERVE (8 << 10) -#endif #else #define PERCPU_MODULE_RESERVE 0 #endif diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 95762232e018..5929030d4e8b 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 15 +#define TASKSTATS_VERSION 16 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -72,8 +72,6 @@ struct taskstats { */ __u64 cpu_count __attribute__((aligned(8))); __u64 cpu_delay_total; - __u64 cpu_delay_max; - __u64 cpu_delay_min; /* Following four fields atomically updated using task->delays->lock */ @@ -82,14 +80,10 @@ struct taskstats { */ __u64 blkio_count; __u64 blkio_delay_total; - __u64 blkio_delay_max; - __u64 blkio_delay_min; /* Delay waiting for page fault I/O (swap in only) */ __u64 swapin_count; __u64 swapin_delay_total; - __u64 swapin_delay_max; - __u64 swapin_delay_min; /* cpu "wall-clock" running time * On some architectures, value will adjust for cpu time stolen @@ -172,14 +166,11 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; - __u64 freepages_delay_max; - __u64 freepages_delay_min; + /* Delay waiting for thrashing page */ __u64 thrashing_count; __u64 thrashing_delay_total; - __u64 thrashing_delay_max; - __u64 thrashing_delay_min; /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ @@ -187,8 +178,6 @@ struct taskstats { /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; - __u64 compact_delay_max; - __u64 compact_delay_min; /* v12 begin */ __u32 ac_tgid; /* thread group ID */ @@ -210,15 +199,37 @@ struct taskstats { /* v13: Delay waiting for write-protect copy */ __u64 wpcopy_count; __u64 wpcopy_delay_total; - __u64 wpcopy_delay_max; - __u64 wpcopy_delay_min; /* v14: Delay waiting for IRQ/SOFTIRQ */ __u64 irq_count; __u64 irq_delay_total; - __u64 irq_delay_max; - __u64 irq_delay_min; - /* v15: add Delay max */ + + /* v15: add Delay max and Delay min */ + + /* v16: move Delay max and Delay min to the end of taskstat */ + __u64 cpu_delay_max; + __u64 cpu_delay_min; + + __u64 blkio_delay_max; + __u64 blkio_delay_min; + + __u64 swapin_delay_max; + __u64 swapin_delay_min; + + __u64 freepages_delay_max; + __u64 freepages_delay_min; + + __u64 thrashing_delay_max; + __u64 thrashing_delay_min; + + __u64 compact_delay_max; + __u64 compact_delay_min; + + __u64 wpcopy_delay_max; + __u64 wpcopy_delay_min; + + __u64 irq_delay_max; + __u64 irq_delay_min; }; diff --git a/kernel/module/main.c b/kernel/module/main.c index a2859dc3eea6..5c6ab20240a6 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2829,6 +2829,7 @@ static void module_deallocate(struct module *mod, struct load_info *info) { percpu_modfree(mod); module_arch_freeing_init(mod); + codetag_free_module_sections(mod); free_mod_mem(mod); } diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c index 25ecc1334b67..c7f602fa7b23 100644 --- a/lib/alloc_tag.c +++ b/lib/alloc_tag.c @@ -350,18 +350,28 @@ static bool needs_section_mem(struct module *mod, unsigned long size) return size >= sizeof(struct alloc_tag); } -static struct alloc_tag *find_used_tag(struct alloc_tag *from, struct alloc_tag *to) +static bool clean_unused_counters(struct alloc_tag *start_tag, + struct alloc_tag *end_tag) { - while (from <= to) { + struct alloc_tag *tag; + bool ret = true; + + for (tag = start_tag; tag <= end_tag; tag++) { struct alloc_tag_counters counter; - counter = alloc_tag_read(from); - if (counter.bytes) - return from; - from++; + if (!tag->counters) + continue; + + counter = alloc_tag_read(tag); + if (!counter.bytes) { + free_percpu(tag->counters); + tag->counters = NULL; + } else { + ret = false; + } } - return NULL; + return ret; } /* Called with mod_area_mt locked */ @@ -371,12 +381,16 @@ static void clean_unused_module_areas_locked(void) struct module *val; mas_for_each(&mas, val, module_tags.size) { + struct alloc_tag *start_tag; + struct alloc_tag *end_tag; + if (val != &unloaded_mod) continue; /* Release area if all tags are unused */ - if (!find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), - (struct alloc_tag *)(module_tags.start_addr + mas.last))) + start_tag = (struct alloc_tag *)(module_tags.start_addr + mas.index); + end_tag = (struct alloc_tag *)(module_tags.start_addr + mas.last); + if (clean_unused_counters(start_tag, end_tag)) mas_erase(&mas); } } @@ -561,7 +575,8 @@ unlock: static void release_module_tags(struct module *mod, bool used) { MA_STATE(mas, &mod_area_mt, module_tags.size, module_tags.size); - struct alloc_tag *tag; + struct alloc_tag *start_tag; + struct alloc_tag *end_tag; struct module *val; mas_lock(&mas); @@ -575,15 +590,22 @@ static void release_module_tags(struct module *mod, bool used) if (!used) goto release_area; - /* Find out if the area is used */ - tag = find_used_tag((struct alloc_tag *)(module_tags.start_addr + mas.index), - (struct alloc_tag *)(module_tags.start_addr + mas.last)); - if (tag) { - struct alloc_tag_counters counter = alloc_tag_read(tag); + start_tag = (struct alloc_tag *)(module_tags.start_addr + mas.index); + end_tag = (struct alloc_tag *)(module_tags.start_addr + mas.last); + if (!clean_unused_counters(start_tag, end_tag)) { + struct alloc_tag *tag; + + for (tag = start_tag; tag <= end_tag; tag++) { + struct alloc_tag_counters counter; + + if (!tag->counters) + continue; - pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n", - tag->ct.filename, tag->ct.lineno, tag->ct.modname, - tag->ct.function, counter.bytes); + counter = alloc_tag_read(tag); + pr_info("%s:%u module %s func:%s has %llu allocated at module unload\n", + tag->ct.filename, tag->ct.lineno, tag->ct.modname, + tag->ct.function, counter.bytes); + } } else { used = false; } @@ -596,6 +618,34 @@ out: mas_unlock(&mas); } +static void load_module(struct module *mod, struct codetag *start, struct codetag *stop) +{ + /* Allocate module alloc_tag percpu counters */ + struct alloc_tag *start_tag; + struct alloc_tag *stop_tag; + struct alloc_tag *tag; + + if (!mod) + return; + + start_tag = ct_to_alloc_tag(start); + stop_tag = ct_to_alloc_tag(stop); + for (tag = start_tag; tag < stop_tag; tag++) { + WARN_ON(tag->counters); + tag->counters = alloc_percpu(struct alloc_tag_counters); + if (!tag->counters) { + while (--tag >= start_tag) { + free_percpu(tag->counters); + tag->counters = NULL; + } + shutdown_mem_profiling(true); + pr_err("Failed to allocate memory for allocation tag percpu counters in the module %s. Memory allocation profiling is disabled!\n", + mod->name); + break; + } + } +} + static void replace_module(struct module *mod, struct module *new_mod) { MA_STATE(mas, &mod_area_mt, 0, module_tags.size); @@ -757,6 +807,7 @@ static int __init alloc_tag_init(void) .needs_section_mem = needs_section_mem, .alloc_section_mem = reserve_module_tags, .free_section_mem = release_module_tags, + .module_load = load_module, .module_replaced = replace_module, #endif }; diff --git a/lib/codetag.c b/lib/codetag.c index 42aadd6c1454..de332e98d6f5 100644 --- a/lib/codetag.c +++ b/lib/codetag.c @@ -194,7 +194,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod) if (err >= 0) { cttype->count += range_size(cttype, &range); if (cttype->desc.module_load) - cttype->desc.module_load(cttype, cmod); + cttype->desc.module_load(mod, range.start, range.stop); } up_write(&cttype->mod_lock); @@ -333,7 +333,8 @@ void codetag_unload_module(struct module *mod) } if (found) { if (cttype->desc.module_unload) - cttype->desc.module_unload(cttype, cmod); + cttype->desc.module_unload(cmod->mod, + cmod->range.start, cmod->range.stop); cttype->count -= range_size(cttype, &cmod->range); idr_remove(&cttype->mod_idr, mod_id); @@ -608,7 +608,10 @@ static int __init __cma_declare_contiguous_nid(phys_addr_t *basep, * complain. Find the boundary by adding one to the last valid * address. */ - highmem_start = __pa(high_memory - 1) + 1; + if (IS_ENABLED(CONFIG_HIGHMEM)) + highmem_start = __pa(high_memory - 1) + 1; + else + highmem_start = memblock_end_of_DRAM(); pr_debug("%s(size %pa, base %pa, limit %pa alignment %pa)\n", __func__, &size, &base, &limit, &alignment); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7ae38bfb9096..6a3cf7935c14 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1250,7 +1250,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. - * This function should be only used by move_vma() and operate on + * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ @@ -2949,12 +2949,20 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) while (start_pfn < end_pfn) { folio = pfn_folio(start_pfn); + + /* + * The folio might have been dissolved from under our feet, so make sure + * to carefully check the state under the lock. + */ + spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { h = folio_hstate(folio); } else { + spin_unlock_irq(&hugetlb_lock); start_pfn++; continue; } + spin_unlock_irq(&hugetlb_lock); if (!folio_ref_count(folio)) { ret = alloc_and_dissolve_hugetlb_folio(h, folio, @@ -7931,3 +7939,17 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE)); } + +/* + * For hugetlb, mremap() is an odd edge case - while the VMA copying is + * performed, we permit both the old and new VMAs to reference the same + * reservation. + * + * We fix this up after the operation succeeds, or if a newly allocated VMA + * is closed as a result of a failure to allocate memory. + */ +void fixup_hugetlb_reservations(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + clear_vma_resv_huge_pages(vma); +} diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 88d1c9dcb507..d2c70cd2afb1 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -292,33 +292,99 @@ void __init __weak kasan_populate_early_vm_area_shadow(void *start, { } +struct vmalloc_populate_data { + unsigned long start; + struct page **pages; +}; + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, - void *unused) + void *_data) { - unsigned long page; + struct vmalloc_populate_data *data = _data; + struct page *page; pte_t pte; + int index; if (likely(!pte_none(ptep_get(ptep)))) return 0; - page = __get_free_page(GFP_KERNEL); - if (!page) - return -ENOMEM; - - __memset((void *)page, KASAN_VMALLOC_INVALID, PAGE_SIZE); - pte = pfn_pte(PFN_DOWN(__pa(page)), PAGE_KERNEL); + index = PFN_DOWN(addr - data->start); + page = data->pages[index]; + __memset(page_to_virt(page), KASAN_VMALLOC_INVALID, PAGE_SIZE); + pte = pfn_pte(page_to_pfn(page), PAGE_KERNEL); spin_lock(&init_mm.page_table_lock); if (likely(pte_none(ptep_get(ptep)))) { set_pte_at(&init_mm, addr, ptep, pte); - page = 0; + data->pages[index] = NULL; } spin_unlock(&init_mm.page_table_lock); - if (page) - free_page(page); + + return 0; +} + +static void ___free_pages_bulk(struct page **pages, int nr_pages) +{ + int i; + + for (i = 0; i < nr_pages; i++) { + if (pages[i]) { + __free_pages(pages[i], 0); + pages[i] = NULL; + } + } +} + +static int ___alloc_pages_bulk(struct page **pages, int nr_pages) +{ + unsigned long nr_populated, nr_total = nr_pages; + struct page **page_array = pages; + + while (nr_pages) { + nr_populated = alloc_pages_bulk(GFP_KERNEL, nr_pages, pages); + if (!nr_populated) { + ___free_pages_bulk(page_array, nr_total - nr_pages); + return -ENOMEM; + } + pages += nr_populated; + nr_pages -= nr_populated; + } + return 0; } +static int __kasan_populate_vmalloc(unsigned long start, unsigned long end) +{ + unsigned long nr_pages, nr_total = PFN_UP(end - start); + struct vmalloc_populate_data data; + int ret = 0; + + data.pages = (struct page **)__get_free_page(GFP_KERNEL | __GFP_ZERO); + if (!data.pages) + return -ENOMEM; + + while (nr_total) { + nr_pages = min(nr_total, PAGE_SIZE / sizeof(data.pages[0])); + ret = ___alloc_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + data.start = start; + ret = apply_to_page_range(&init_mm, start, nr_pages * PAGE_SIZE, + kasan_populate_vmalloc_pte, &data); + ___free_pages_bulk(data.pages, nr_pages); + if (ret) + break; + + start += nr_pages * PAGE_SIZE; + nr_total -= nr_pages; + } + + free_page((unsigned long)data.pages); + + return ret; +} + int kasan_populate_vmalloc(unsigned long addr, unsigned long size) { unsigned long shadow_start, shadow_end; @@ -348,9 +414,7 @@ int kasan_populate_vmalloc(unsigned long addr, unsigned long size) shadow_start = PAGE_ALIGN_DOWN(shadow_start); shadow_end = PAGE_ALIGN(shadow_end); - ret = apply_to_page_range(&init_mm, shadow_start, - shadow_end - shadow_start, - kasan_populate_vmalloc_pte, NULL); + ret = __kasan_populate_vmalloc(shadow_start, shadow_end); if (ret) return ret; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c96c1f2b9cf5..2d4d65f25fec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1168,7 +1168,6 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; - int i = 0; BUG_ON(mem_cgroup_is_root(memcg)); @@ -1178,10 +1177,9 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); while (!ret && (task = css_task_iter_next(&it))) { - /* Avoid potential softlockup warning */ - if ((++i & 1023) == 0) - cond_resched(); ret = fn(task, arg); + /* Avoid potential softlockup warning */ + cond_resched(); } css_task_iter_end(&it); if (ret) { diff --git a/mm/mremap.c b/mm/mremap.c index 7db9da609c84..0d4948b720e2 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1188,8 +1188,7 @@ static int copy_vma_and_data(struct vma_remap_struct *vrm, mremap_userfaultfd_prep(new_vma, vrm->uf); } - if (is_vm_hugetlb_page(vma)) - clear_vma_resv_huge_pages(vma); + fixup_hugetlb_reservations(vma); /* Tell pfnmap has moved from this vma */ if (unlikely(vma->vm_flags & VM_PFNMAP)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8258349e49ac..47fa713ccb4d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4562,6 +4562,14 @@ restart: } retry: + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * infinite retries. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; + /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */ if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); diff --git a/mm/truncate.c b/mm/truncate.c index 5d98054094d1..f2aaf99f2990 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -191,6 +191,7 @@ int truncate_inode_folio(struct address_space *mapping, struct folio *folio) bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { loff_t pos = folio_pos(folio); + size_t size = folio_size(folio); unsigned int offset, length; struct page *split_at, *split_at2; @@ -198,14 +199,13 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) offset = start - pos; else offset = 0; - length = folio_size(folio); - if (pos + length <= (u64)end) - length = length - offset; + if (pos + size <= (u64)end) + length = size - offset; else length = end + 1 - pos - offset; folio_wait_writeback(folio); - if (length == folio_size(folio)) { + if (length == size) { truncate_inode_folio(folio->mapping, folio); return true; } @@ -224,16 +224,20 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) return true; split_at = folio_page(folio, PAGE_ALIGN_DOWN(offset) / PAGE_SIZE); - split_at2 = folio_page(folio, - PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE); - if (!try_folio_split(folio, split_at, NULL)) { /* * try to split at offset + length to make sure folios within * the range can be dropped, especially to avoid memory waste * for shmem truncate */ - struct folio *folio2 = page_folio(split_at2); + struct folio *folio2; + + if (offset + length == size) + goto no_split; + + split_at2 = folio_page(folio, + PAGE_ALIGN_DOWN(offset + length) / PAGE_SIZE); + folio2 = page_folio(split_at2); if (!folio_try_get(folio2)) goto no_split; @@ -1834,6 +1834,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return new_vma; out_vma_link: + fixup_hugetlb_reservations(new_vma); vma_close(new_vma); if (new_vma->vm_file) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 2d7511654831..00cf1b575c89 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -4093,8 +4093,8 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { - /* Zero out "freed" memory. */ - if (want_init_on_free()) + /* Zero out "freed" memory, potentially for future realloc. */ + if (want_init_on_free() || want_init_on_alloc(flags)) memset((void *)p + size, 0, old_size - size); vm->requested_size = size; kasan_poison_vmalloc(p + size, old_size - size); @@ -4107,10 +4107,13 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) if (size <= alloced_size) { kasan_unpoison_vmalloc(p + old_size, size - old_size, KASAN_VMALLOC_PROT_NORMAL); - /* Zero out "alloced" memory. */ - if (want_init_on_alloc(flags)) - memset((void *)p + old_size, 0, size - old_size); + /* + * No need to zero memory here, as unused memory will have + * already been zeroed at initial allocation time or during + * realloc shrink time. + */ vm->requested_size = size; + return (void *)p; } /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ |