diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/backing-dev.c | 1 | ||||
| -rw-r--r-- | mm/gup.c | 3 | ||||
| -rw-r--r-- | mm/hugetlb.c | 84 | ||||
| -rw-r--r-- | mm/kasan/Makefile | 1 | ||||
| -rw-r--r-- | mm/kasan/common.c | 65 | ||||
| -rw-r--r-- | mm/memblock.c | 11 | ||||
| -rw-r--r-- | mm/memory-failure.c | 19 | ||||
| -rw-r--r-- | mm/memory.c | 26 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 62 | ||||
| -rw-r--r-- | mm/migrate.c | 25 | ||||
| -rw-r--r-- | mm/mincore.c | 94 | ||||
| -rw-r--r-- | mm/oom_kill.c | 12 | ||||
| -rw-r--r-- | mm/page_alloc.c | 28 | ||||
| -rw-r--r-- | mm/page_ext.c | 4 | ||||
| -rw-r--r-- | mm/rmap.c | 8 | ||||
| -rw-r--r-- | mm/slab.c | 6 | ||||
| -rw-r--r-- | mm/slub.c | 2 | ||||
| -rw-r--r-- | mm/usercopy.c | 9 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 11 | ||||
| -rw-r--r-- | mm/util.c | 2 | ||||
| -rw-r--r-- | mm/vmscan.c | 10 |
21 files changed, 262 insertions, 221 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8a8bb8796c6c..72e6d0c55cfa 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -689,6 +689,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; mutex_init(&bdi->cgwb_release_mutex); + init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) { @@ -1674,7 +1674,8 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, if (!pmd_present(pmd)) return 0; - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) { + if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || + pmd_devmap(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 745088810965..afef61656c1e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3238,7 +3238,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct page *ptepage; unsigned long addr; int cow; - struct address_space *mapping = vma->vm_file->f_mapping; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; @@ -3250,23 +3249,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, mmu_notifier_range_init(&range, src, vma->vm_start, vma->vm_end); mmu_notifier_invalidate_range_start(&range); - } else { - /* - * For shared mappings i_mmap_rwsem must be held to call - * huge_pte_alloc, otherwise the returned ptep could go - * away if part of a shared pmd and another thread calls - * huge_pmd_unshare. - */ - i_mmap_lock_read(mapping); } for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; - src_pte = huge_pte_offset(src, addr, sz); if (!src_pte) continue; - dst_pte = huge_pte_alloc(dst, addr, sz); if (!dst_pte) { ret = -ENOMEM; @@ -3337,8 +3326,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, if (cow) mmu_notifier_invalidate_range_end(&range); - else - i_mmap_unlock_read(mapping); return ret; } @@ -3755,16 +3742,16 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, } /* - * We can not race with truncation due to holding i_mmap_rwsem. - * Check once here for faults beyond end of file. + * Use page lock to guard against racing truncation + * before we get page_table_lock. */ - size = i_size_read(mapping->host) >> huge_page_shift(h); - if (idx >= size) - goto out; - retry: page = find_lock_page(mapping, idx); if (!page) { + size = i_size_read(mapping->host) >> huge_page_shift(h); + if (idx >= size) + goto out; + /* * Check for page in userfault range */ @@ -3784,18 +3771,14 @@ retry: }; /* - * hugetlb_fault_mutex and i_mmap_rwsem must be - * dropped before handling userfault. Reacquire - * after handling fault to make calling code simpler. + * hugetlb_fault_mutex must be dropped before + * handling userfault. Reacquire after handling + * fault to make calling code simpler. */ hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr); mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); - ret = handle_userfault(&vmf, VM_UFFD_MISSING); - - i_mmap_lock_read(mapping); mutex_lock(&hugetlb_fault_mutex_table[hash]); goto out; } @@ -3854,6 +3837,9 @@ retry: } ptl = huge_pte_lock(h, mm, ptep); + size = i_size_read(mapping->host) >> huge_page_shift(h); + if (idx >= size) + goto backout; ret = 0; if (!huge_pte_none(huge_ptep_get(ptep))) @@ -3940,11 +3926,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (ptep) { - /* - * Since we hold no locks, ptep could be stale. That is - * OK as we are only making decisions based on content and - * not actually modifying content here. - */ entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { migration_entry_wait_huge(vma, mm, ptep); @@ -3952,33 +3933,20 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); + } else { + ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); + if (!ptep) + return VM_FAULT_OOM; } - /* - * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold - * until finished with ptep. This serves two purposes: - * 1) It prevents huge_pmd_unshare from being called elsewhere - * and making the ptep no longer valid. - * 2) It synchronizes us with file truncation. - * - * ptep could have already be assigned via huge_pte_offset. That - * is OK, as huge_pte_alloc will return the same value unless - * something changed. - */ mapping = vma->vm_file->f_mapping; - i_mmap_lock_read(mapping); - ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); - if (!ptep) { - i_mmap_unlock_read(mapping); - return VM_FAULT_OOM; - } + idx = vma_hugecache_offset(h, vma, haddr); /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -4066,7 +4034,6 @@ out_ptl: } out_mutex: mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and @@ -4301,7 +4268,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } if (ret & VM_FAULT_RETRY) { - if (nonblocking) + if (nonblocking && + !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *nonblocking = 0; *nr_pages = 0; /* @@ -4671,12 +4639,10 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the - * code much cleaner. - * - * This routine must be called with i_mmap_rwsem held in at least read mode. - * For hugetlbfs, this prevents removal of any page table entries associated - * with the address space. This is important as we are setting up sharing - * based on existing page table entries (mappings). + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_rwsem section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. */ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { @@ -4693,6 +4659,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); + i_mmap_lock_write(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; @@ -4722,6 +4689,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); + i_mmap_unlock_write(mapping); return pte; } @@ -4732,7 +4700,7 @@ out: * indicated by page_count > 1, unmap is achieved by clearing pud and * decrementing the ref count. If count == 1, the pte page is not shared. * - * Called with page table lock held and i_mmap_rwsem held in write mode. + * called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 0a14fcff70ed..e2bb06c1b45e 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -5,6 +5,7 @@ UBSAN_SANITIZE_generic.o := n UBSAN_SANITIZE_tags.o := n KCOV_INSTRUMENT := n +CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_generic.o = -pg # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 03d5d1374ca7..73c9cbfdedf4 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -298,8 +298,6 @@ void kasan_cache_create(struct kmem_cache *cache, unsigned int *size, return; } - cache->align = round_up(cache->align, KASAN_SHADOW_SCALE_SIZE); - *flags |= SLAB_KASAN; } @@ -349,28 +347,43 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object) } /* - * Since it's desirable to only call object contructors once during slab - * allocation, we preassign tags to all such objects. Also preassign tags for - * SLAB_TYPESAFE_BY_RCU slabs to avoid use-after-free reports. - * For SLAB allocator we can't preassign tags randomly since the freelist is - * stored as an array of indexes instead of a linked list. Assign tags based - * on objects indexes, so that objects that are next to each other get - * different tags. - * After a tag is assigned, the object always gets allocated with the same tag. - * The reason is that we can't change tags for objects with constructors on - * reallocation (even for non-SLAB_TYPESAFE_BY_RCU), because the constructor - * code can save the pointer to the object somewhere (e.g. in the object - * itself). Then if we retag it, the old saved pointer will become invalid. + * This function assigns a tag to an object considering the following: + * 1. A cache might have a constructor, which might save a pointer to a slab + * object somewhere (e.g. in the object itself). We preassign a tag for + * each object in caches with constructors during slab creation and reuse + * the same tag each time a particular object is allocated. + * 2. A cache might be SLAB_TYPESAFE_BY_RCU, which means objects can be + * accessed after being freed. We preassign tags for objects in these + * caches as well. + * 3. For SLAB allocator we can't preassign tags randomly since the freelist + * is stored as an array of indexes instead of a linked list. Assign tags + * based on objects indexes, so that objects that are next to each other + * get different tags. */ -static u8 assign_tag(struct kmem_cache *cache, const void *object, bool new) +static u8 assign_tag(struct kmem_cache *cache, const void *object, + bool init, bool krealloc) { + /* Reuse the same tag for krealloc'ed objects. */ + if (krealloc) + return get_tag(object); + + /* + * If the cache neither has a constructor nor has SLAB_TYPESAFE_BY_RCU + * set, assign a tag when the object is being allocated (init == false). + */ if (!cache->ctor && !(cache->flags & SLAB_TYPESAFE_BY_RCU)) - return new ? KASAN_TAG_KERNEL : random_tag(); + return init ? KASAN_TAG_KERNEL : random_tag(); + /* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */ #ifdef CONFIG_SLAB + /* For SLAB assign tags based on the object index in the freelist. */ return (u8)obj_to_index(cache, virt_to_page(object), (void *)object); #else - return new ? random_tag() : get_tag(object); + /* + * For SLUB assign a random tag during slab creation, otherwise reuse + * the already assigned tag. + */ + return init ? random_tag() : get_tag(object); #endif } @@ -386,7 +399,8 @@ void * __must_check kasan_init_slab_obj(struct kmem_cache *cache, __memset(alloc_info, 0, sizeof(*alloc_info)); if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) - object = set_tag(object, assign_tag(cache, object, true)); + object = set_tag(object, + assign_tag(cache, object, true, false)); return (void *)object; } @@ -452,8 +466,8 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip) return __kasan_slab_free(cache, object, ip, true); } -void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object, - size_t size, gfp_t flags) +static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object, + size_t size, gfp_t flags, bool krealloc) { unsigned long redzone_start; unsigned long redzone_end; @@ -471,7 +485,7 @@ void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object, KASAN_SHADOW_SCALE_SIZE); if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) - tag = assign_tag(cache, object, false); + tag = assign_tag(cache, object, false, krealloc); /* Tag is ignored in set_tag without CONFIG_KASAN_SW_TAGS */ kasan_unpoison_shadow(set_tag(object, tag), size); @@ -483,6 +497,12 @@ void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object, return set_tag(object, tag); } + +void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object, + size_t size, gfp_t flags) +{ + return __kasan_kmalloc(cache, object, size, flags, false); +} EXPORT_SYMBOL(kasan_kmalloc); void * __must_check kasan_kmalloc_large(const void *ptr, size_t size, @@ -522,7 +542,8 @@ void * __must_check kasan_krealloc(const void *object, size_t size, gfp_t flags) if (unlikely(!PageSlab(page))) return kasan_kmalloc_large(object, size, flags); else - return kasan_kmalloc(page->slab_cache, object, size, flags); + return __kasan_kmalloc(page->slab_cache, object, size, + flags, true); } void kasan_poison_kfree(void *ptr, unsigned long ip) diff --git a/mm/memblock.c b/mm/memblock.c index 022d4cbb3618..ea31045ba704 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -26,6 +26,13 @@ #include "internal.h" +#define INIT_MEMBLOCK_REGIONS 128 +#define INIT_PHYSMEM_REGIONS 4 + +#ifndef INIT_MEMBLOCK_RESERVED_REGIONS +# define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS +#endif + /** * DOC: memblock overview * @@ -92,7 +99,7 @@ unsigned long max_pfn; unsigned long long max_possible_pfn; static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; -static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock; #endif @@ -105,7 +112,7 @@ struct memblock memblock __initdata_memblock = { .reserved.regions = memblock_reserved_init_regions, .reserved.cnt = 1, /* empty dummy entry */ - .reserved.max = INIT_MEMBLOCK_REGIONS, + .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 6379fff1a5ff..831be5ff5f4d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -372,7 +372,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, if (fail || tk->addr_valid == 0) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); - force_sig(SIGKILL, tk->tsk); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, + tk->tsk, PIDTYPE_PID); } /* @@ -966,7 +967,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; struct address_space *mapping; LIST_HEAD(tokill); - bool unmap_success = true; + bool unmap_success; int kill = 1, forcekill; struct page *hpage = *hpagep; bool mlocked = PageMlocked(hpage); @@ -1028,19 +1029,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (kill) collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); - if (!PageHuge(hpage)) { - unmap_success = try_to_unmap(hpage, ttu); - } else if (mapping) { - /* - * For hugetlb pages, try_to_unmap could potentially call - * huge_pmd_unshare. Because of this, take semaphore in - * write mode here and set TTU_RMAP_LOCKED to indicate we - * have taken the lock at this higer level. - */ - i_mmap_lock_write(mapping); - unmap_success = try_to_unmap(hpage, ttu|TTU_RMAP_LOCKED); - i_mmap_unlock_write(mapping); - } + unmap_success = try_to_unmap(hpage, ttu); if (!unmap_success) pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", pfn, page_mapcount(hpage)); diff --git a/mm/memory.c b/mm/memory.c index a52663c0612d..e11ca9dd823f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2994,6 +2994,28 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; + /* + * Preallocate pte before we take page_lock because this might lead to + * deadlocks for memcg reclaim which waits for pages under writeback: + * lock_page(A) + * SetPageWriteback(A) + * unlock_page(A) + * lock_page(B) + * lock_page(B) + * pte_alloc_pne + * shrink_page_list + * wait_on_page_writeback(A) + * SetPageWriteback(B) + * unlock_page(B) + * # flush A, B to clear the writeback + */ + if (pmd_none(*vmf->pmd) && !vmf->prealloc_pte) { + vmf->prealloc_pte = pte_alloc_one(vmf->vma->vm_mm); + if (!vmf->prealloc_pte) + return VM_FAULT_OOM; + smp_wmb(); /* See comment in __pte_alloc() */ + } + ret = vma->vm_ops->fault(vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY | VM_FAULT_DONE_COW))) @@ -4077,8 +4099,8 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, goto out; if (range) { - range->start = address & PAGE_MASK; - range->end = range->start + PAGE_SIZE; + mmu_notifier_range_init(range, mm, address & PAGE_MASK, + (address & PAGE_MASK) + PAGE_SIZE); mmu_notifier_invalidate_range_start(range); } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b9a667d36c55..124e794867c5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1233,7 +1233,8 @@ static bool is_pageblock_removable_nolock(struct page *page) bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); - struct page *end_page = page + nr_pages; + unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page))); + struct page *end_page = pfn_to_page(end_pfn); /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { @@ -1273,6 +1274,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; + /* Check if we got outside of the zone */ + if (zone && !zone_spans_pfn(zone, pfn + i)) + return 0; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; @@ -1301,23 +1305,27 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { unsigned long pfn; - struct page *page; + for (pfn = start; pfn < end; pfn++) { - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (PageLRU(page)) - return pfn; - if (__PageMovable(page)) - return pfn; - if (PageHuge(page)) { - if (hugepage_migration_supported(page_hstate(page)) && - page_huge_active(page)) - return pfn; - else - pfn = round_up(pfn + 1, - 1 << compound_order(page)) - 1; - } - } + struct page *page, *head; + unsigned long skip; + + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + if (PageLRU(page)) + return pfn; + if (__PageMovable(page)) + return pfn; + + if (!PageHuge(page)) + continue; + head = compound_head(page); + if (hugepage_migration_supported(page_hstate(head)) && + page_huge_active(head)) + return pfn; + skip = (1 << compound_order(head)) - (page - head); + pfn += skip - 1; } return 0; } @@ -1344,7 +1352,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; - int not_managed = 0; int ret = 0; LIST_HEAD(source); @@ -1392,7 +1399,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) else ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); if (!ret) { /* Success */ - put_page(page); list_add_tail(&page->lru, &source); if (!__PageMovable(page)) inc_node_page_state(page, NR_ISOLATED_ANON + @@ -1401,22 +1407,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } else { pr_warn("failed to isolate pfn %lx\n", pfn); dump_page(page, "isolation failed"); - put_page(page); - /* Because we don't have big zone->lock. we should - check this again here. */ - if (page_count(page)) { - not_managed++; - ret = -EBUSY; - break; - } } + put_page(page); } if (!list_empty(&source)) { - if (not_managed) { - putback_movable_pages(&source); - goto out; - } - /* Allocate a new page from the nearest neighbor node */ ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); @@ -1429,7 +1423,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) putback_movable_pages(&source); } } -out: + return ret; } @@ -1576,7 +1570,6 @@ static int __ref __offline_pages(unsigned long start_pfn, we assume this for now. .*/ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) { - mem_hotplug_done(); ret = -EINVAL; reason = "multizone range"; goto failed_removal; @@ -1591,7 +1584,6 @@ static int __ref __offline_pages(unsigned long start_pfn, MIGRATE_MOVABLE, SKIP_HWPOISON | REPORT_FAILURE); if (ret) { - mem_hotplug_done(); reason = "failure to isolate range"; goto failed_removal; } diff --git a/mm/migrate.c b/mm/migrate.c index ccf8966caf6f..d4fd680be3b0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -709,7 +709,6 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* Simple case, sync compaction */ if (mode != MIGRATE_ASYNC) { do { - get_bh(bh); lock_buffer(bh); bh = bh->b_this_page; @@ -720,18 +719,15 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* async case, we cannot block on lock_buffer so use trylock_buffer */ do { - get_bh(bh); if (!trylock_buffer(bh)) { /* * We failed to lock the buffer and cannot stall in * async migration. Release the taken locks */ struct buffer_head *failed_bh = bh; - put_bh(failed_bh); bh = head; while (bh != failed_bh) { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } return false; @@ -818,7 +814,6 @@ unlock_buffers: bh = head; do { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } while (bh != head); @@ -1135,10 +1130,13 @@ out: * If migration is successful, decrease refcount of the newpage * which will not free the page because new page owner increased * refcounter. As well, if it is LRU page, add the page to LRU - * list in here. + * list in here. Use the old state of the isolated source page to + * determine if we migrated a LRU page. newpage was already unlocked + * and possibly modified by its owner - don't rely on the page + * state. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (unlikely(__PageMovable(newpage))) + if (unlikely(!is_lru)) put_page(newpage); else putback_lru_page(newpage); @@ -1324,19 +1322,8 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, goto put_anon; if (page_mapped(hpage)) { - struct address_space *mapping = page_mapping(hpage); - - /* - * try_to_unmap could potentially call huge_pmd_unshare. - * Because of this, take semaphore in write mode here and - * set TTU_RMAP_LOCKED to let lower levels know we have - * taken the lock. - */ - i_mmap_lock_write(mapping); try_to_unmap(hpage, - TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS| - TTU_RMAP_LOCKED); - i_mmap_unlock_write(mapping); + TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); page_was_mapped = 1; } diff --git a/mm/mincore.c b/mm/mincore.c index f0f91461a9f4..218099b5ed31 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -42,14 +42,72 @@ static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, return 0; } -static int mincore_unmapped_range(unsigned long addr, unsigned long end, - struct mm_walk *walk) +/* + * Later we can get more picky about what "in core" means precisely. + * For now, simply check to see if the page is in the page cache, + * and is up to date; i.e. that no page-in operation would be required + * at this time if an application were to map and access this page. + */ +static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) +{ + unsigned char present = 0; + struct page *page; + + /* + * When tmpfs swaps out a page from a file, any process mapping that + * file will not get a swp_entry_t in its pte, but rather it is like + * any other file mapping (ie. marked !present and faulted in with + * tmpfs's .fault). So swapped out tmpfs mappings are tested here. + */ +#ifdef CONFIG_SWAP + if (shmem_mapping(mapping)) { + page = find_get_entry(mapping, pgoff); + /* + * shmem/tmpfs may return swap: account for swapcache + * page too. + */ + if (xa_is_value(page)) { + swp_entry_t swp = radix_to_swp_entry(page); + page = find_get_page(swap_address_space(swp), + swp_offset(swp)); + } + } else + page = find_get_page(mapping, pgoff); +#else + page = find_get_page(mapping, pgoff); +#endif + if (page) { + present = PageUptodate(page); + put_page(page); + } + + return present; +} + +static int __mincore_unmapped_range(unsigned long addr, unsigned long end, + struct vm_area_struct *vma, unsigned char *vec) { - unsigned char *vec = walk->private; unsigned long nr = (end - addr) >> PAGE_SHIFT; + int i; - memset(vec, 0, nr); - walk->private += nr; + if (vma->vm_file) { + pgoff_t pgoff; + + pgoff = linear_page_index(vma, addr); + for (i = 0; i < nr; i++, pgoff++) + vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff); + } else { + for (i = 0; i < nr; i++) + vec[i] = 0; + } + return nr; +} + +static int mincore_unmapped_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + walk->private += __mincore_unmapped_range(addr, end, + walk->vma, walk->private); return 0; } @@ -69,9 +127,8 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, goto out; } - /* We'll consider a THP page under construction to be there */ if (pmd_trans_unstable(pmd)) { - memset(vec, 1, nr); + __mincore_unmapped_range(addr, end, vma, vec); goto out; } @@ -80,17 +137,28 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, pte_t pte = *ptep; if (pte_none(pte)) - *vec = 0; + __mincore_unmapped_range(addr, addr + PAGE_SIZE, + vma, vec); else if (pte_present(pte)) *vec = 1; else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); - /* - * migration or hwpoison entries are always - * uptodate - */ - *vec = !!non_swap_entry(entry); + if (non_swap_entry(entry)) { + /* + * migration or hwpoison entries are always + * uptodate + */ + *vec = 1; + } else { +#ifdef CONFIG_SWAP + *vec = mincore_page(swap_address_space(entry), + swp_offset(entry)); +#else + WARN_ON(1); + *vec = 1; +#endif + } } vec++; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f0e8cd9edb1a..26ea8636758f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -647,8 +647,8 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - /* tsk is already queued? */ - if (tsk == oom_reaper_list || tsk->oom_reaper_list) + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) return; get_task_struct(tsk); @@ -975,6 +975,13 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * still freeing memory. */ read_lock(&tasklist_lock); + + /* + * The task 'p' might have already exited before reaching here. The + * put_task_struct() will free task_struct 'p' while the loop still try + * to access the field of 'p', so, get an extra reference. + */ + get_task_struct(p); for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -994,6 +1001,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) } } } + put_task_struct(p); read_unlock(&tasklist_lock); /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cde5dac6229a..46285d28e43b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2214,7 +2214,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, */ boost_watermark(zone); if (alloc_flags & ALLOC_KSWAPD) - wakeup_kswapd(zone, 0, 0, zone_idx(zone)); + set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); /* We are not allowed to try stealing from the whole block */ if (!whole_block) @@ -3102,6 +3102,12 @@ struct page *rmqueue(struct zone *preferred_zone, local_irq_restore(flags); out: + /* Separate test+clear to avoid unnecessary atomics */ + if (test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags)) { + clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); + wakeup_kswapd(zone, 0, 0, zone_idx(zone)); + } + VM_BUG_ON_PAGE(page && bad_range(zone, page), page); return page; @@ -4669,11 +4675,11 @@ refill: /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ - page_ref_add(page, size - 1); + page_ref_add(page, size); /* reset page count bias and offset to start of new frag */ nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = size; + nc->pagecnt_bias = size + 1; nc->offset = size; } @@ -4689,10 +4695,10 @@ refill: size = nc->size; #endif /* OK, page count is 0, we can safely set it */ - set_page_count(page, size); + set_page_count(page, size + 1); /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size; + nc->pagecnt_bias = size + 1; offset = size - fragsz; } @@ -5695,18 +5701,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, cond_resched(); } } -#ifdef CONFIG_SPARSEMEM - /* - * If the zone does not span the rest of the section then - * we should at least initialize those pages. Otherwise we - * could blow up on a poisoned page in some paths which depend - * on full sections being initialized (e.g. memory hotplug). - */ - while (end_pfn % PAGES_PER_SECTION) { - __init_single_page(pfn_to_page(end_pfn), end_pfn, zone, nid); - end_pfn++; - } -#endif } #ifdef CONFIG_ZONE_DEVICE diff --git a/mm/page_ext.c b/mm/page_ext.c index ae44f7adbe07..8c78b8d45117 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -398,10 +398,8 @@ void __init page_ext_init(void) * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... - * - * Take into account DEFERRED_STRUCT_PAGE_INIT. */ - if (early_pfn_to_nid(pfn) != nid) + if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; diff --git a/mm/rmap.c b/mm/rmap.c index 21a26cf51114..0454ecc29537 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -25,7 +25,6 @@ * page->flags PG_locked (lock_page) * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share) * mapping->i_mmap_rwsem - * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * anon_vma->rwsem * mm->page_table_lock or pte_lock * zone_lru_lock (in mark_page_accessed, isolate_lru_page) @@ -1372,16 +1371,13 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ - mmu_notifier_range_init(&range, vma->vm_mm, vma->vm_start, - min(vma->vm_end, vma->vm_start + + mmu_notifier_range_init(&range, vma->vm_mm, address, + min(vma->vm_end, address + (PAGE_SIZE << compound_order(page)))); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted * accordingly. - * - * If called for a huge page, caller must hold i_mmap_rwsem - * in write mode as it is possible to call huge_pmd_unshare. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); diff --git a/mm/slab.c b/mm/slab.c index 73fe23e649c9..78eb8c5bf4e4 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -666,8 +666,10 @@ static struct alien_cache *__alloc_alien_cache(int node, int entries, struct alien_cache *alc = NULL; alc = kmalloc_node(memsize, gfp, node); - init_arraycache(&alc->ac, entries, batch); - spin_lock_init(&alc->lock); + if (alc) { + init_arraycache(&alc->ac, entries, batch); + spin_lock_init(&alc->lock); + } return alc; } diff --git a/mm/slub.c b/mm/slub.c index 36c0befeebd8..1e3d0ec4e200 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3846,6 +3846,8 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, unsigned int offset; size_t object_size; + ptr = kasan_reset_tag(ptr); + /* Find object and usable object size. */ s = page->slab_cache; diff --git a/mm/usercopy.c b/mm/usercopy.c index 852eb4e53f06..14faadcedd06 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -247,7 +247,8 @@ static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address - * - known-safe heap or stack object + * - fully contained by stack (or stack frame, when available) + * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) @@ -262,9 +263,6 @@ void __check_object_size(const void *ptr, unsigned long n, bool to_user) /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); - /* Check for bad heap object. */ - check_heap_object(ptr, n, to_user); - /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: @@ -282,6 +280,9 @@ void __check_object_size(const void *ptr, unsigned long n, bool to_user) usercopy_abort("process stack", NULL, to_user, 0, n); } + /* Check for bad heap object. */ + check_heap_object(ptr, n, to_user); + /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 065c1ce191c4..d59b5a73dfb3 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -267,14 +267,10 @@ retry: VM_BUG_ON(dst_addr & ~huge_page_mask(h)); /* - * Serialize via i_mmap_rwsem and hugetlb_fault_mutex. - * i_mmap_rwsem ensures the dst_pte remains valid even - * in the case of shared pmds. fault mutex prevents - * races with other faulting threads. + * Serialize via hugetlb_fault_mutex */ - mapping = dst_vma->vm_file->f_mapping; - i_mmap_lock_read(mapping); idx = linear_page_index(dst_vma, dst_addr); + mapping = dst_vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(h, dst_mm, dst_vma, mapping, idx, dst_addr); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -283,7 +279,6 @@ retry: dst_pte = huge_pte_alloc(dst_mm, dst_addr, huge_page_size(h)); if (!dst_pte) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); goto out_unlock; } @@ -291,7 +286,6 @@ retry: dst_pteval = huge_ptep_get(dst_pte); if (!huge_pte_none(dst_pteval)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); goto out_unlock; } @@ -299,7 +293,6 @@ retry: dst_addr, src_addr, &page); mutex_unlock(&hugetlb_fault_mutex_table[hash]); - i_mmap_unlock_read(mapping); vm_alloc_shared = vm_shared; cond_resched(); diff --git a/mm/util.c b/mm/util.c index 4df23d64aac7..1ea055138043 100644 --- a/mm/util.c +++ b/mm/util.c @@ -478,7 +478,7 @@ bool page_mapped(struct page *page) return true; if (PageHuge(page)) return false; - for (i = 0; i < hpage_nr_pages(page); i++) { + for (i = 0; i < (1 << compound_order(page)); i++) { if (atomic_read(&page[i]._mapcount) >= 0) return true; } diff --git a/mm/vmscan.c b/mm/vmscan.c index a714c4f800e9..e979705bbf32 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -491,16 +491,6 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } - /* - * Make sure we apply some minimal pressure on default priority - * even on small cgroups. Stale objects are not only consuming memory - * by themselves, but can also hold a reference to a dying cgroup, - * preventing it from being reclaimed. A dying cgroup with all - * corresponding structures like per-cpu stats and kmem caches - * can be really big, so it may lead to a significant waste of memory. - */ - delta = max_t(unsigned long long, delta, min(freeable, batch_size)); - total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", |