diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/filemap.c | 2 | ||||
-rw-r--r-- | mm/frame_vector.c | 31 | ||||
-rw-r--r-- | mm/hugetlb.c | 2 | ||||
-rw-r--r-- | mm/kmemleak.c | 8 | ||||
-rw-r--r-- | mm/migrate.c | 5 | ||||
-rw-r--r-- | mm/mmap.c | 9 | ||||
-rw-r--r-- | mm/page_alloc.c | 65 | ||||
-rw-r--r-- | mm/slub.c | 5 |
8 files changed, 81 insertions, 46 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index f2e777003b90..e61ec2c88bd0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3140,7 +3140,7 @@ ssize_t generic_perform_write(struct file *file, unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ - void *fsdata; + void *fsdata = NULL; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, diff --git a/mm/frame_vector.c b/mm/frame_vector.c index c64dca6e27c2..7124410a0016 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -37,7 +37,6 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int ret = 0; - int err; int locked; if (nr_frames == 0) @@ -72,32 +71,14 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, vec->is_pfns = false; ret = get_user_pages_locked(start, nr_frames, gup_flags, (struct page **)(vec->ptrs), &locked); - goto out; + if (likely(ret > 0)) + goto out; } - vec->got_ref = false; - vec->is_pfns = true; - do { - unsigned long *nums = frame_vector_pfns(vec); - - while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { - err = follow_pfn(vma, start, &nums[ret]); - if (err) { - if (ret == 0) - ret = err; - goto out; - } - start += PAGE_SIZE; - ret++; - } - /* - * We stop if we have enough pages or if VMA doesn't completely - * cover the tail page. - */ - if (ret >= nr_frames || start < vma->vm_end) - break; - vma = find_vma_intersection(mm, start, start + 1); - } while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP)); + /* This used to (racily) return non-refcounted pfns. Let people know */ + WARN_ONCE(1, "get_vaddr_frames() cannot follow VM_IO mapping"); + vec->nr_frames = 0; + out: if (locked) up_read(&mm->mmap_sem); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 45e874fafdd7..47e98a5726c4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2116,11 +2116,11 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, page = alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; + spin_lock(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { SetPagePrivate(page); h->resv_huge_pages--; } - spin_lock(&hugetlb_lock); list_move(&page->lru, &h->hugepage_activelist); /* Fall through */ } diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 639acbb91fd5..f54734abf946 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1196,7 +1196,7 @@ EXPORT_SYMBOL(kmemleak_no_scan); void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, gfp_t gfp) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_alloc(__va(phys), size, min_count, gfp); } EXPORT_SYMBOL(kmemleak_alloc_phys); @@ -1210,7 +1210,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_free_part(__va(phys), size); } EXPORT_SYMBOL(kmemleak_free_part_phys); @@ -1222,7 +1222,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys); */ void __ref kmemleak_not_leak_phys(phys_addr_t phys) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_not_leak(__va(phys)); } EXPORT_SYMBOL(kmemleak_not_leak_phys); @@ -1234,7 +1234,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) + if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) kmemleak_ignore(__va(phys)); } EXPORT_SYMBOL(kmemleak_ignore_phys); diff --git a/mm/migrate.c b/mm/migrate.c index 76f8dedc0e02..171573613c39 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2359,13 +2359,14 @@ next: migrate->dst[migrate->npages] = 0; migrate->src[migrate->npages++] = mpfn; } - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(ptep - 1, ptl); /* Only flush the TLB if we actually modified any entries */ if (unmapped) flush_tlb_range(walk->vma, start, end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(ptep - 1, ptl); + return 0; } diff --git a/mm/mmap.c b/mm/mmap.c index 5ee3c91450de..38541885ea45 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2567,6 +2567,7 @@ static void unmap_region(struct mm_struct *mm, { struct vm_area_struct *next = prev ? prev->vm_next : mm->mmap; struct mmu_gather tlb; + struct vm_area_struct *cur_vma; lru_add_drain(); tlb_gather_mmu(&tlb, mm, start, end); @@ -2581,8 +2582,12 @@ static void unmap_region(struct mm_struct *mm, * concurrent flush in this region has to be coming through the rmap, * and we synchronize against that using the rmap lock. */ - if ((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) - tlb_flush_mmu(&tlb); + for (cur_vma = vma; cur_vma; cur_vma = cur_vma->vm_next) { + if ((cur_vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) { + tlb_flush_mmu(&tlb); + break; + } + } free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9c35403d9646..1cffd4e1fd8f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3779,6 +3779,30 @@ void fs_reclaim_release(gfp_t gfp_mask) EXPORT_SYMBOL_GPL(fs_reclaim_release); #endif +/* + * Zonelists may change due to hotplug during allocation. Detect when zonelists + * have been rebuilt so allocation retries. Reader side does not lock and + * retries the allocation if zonelist changes. Writer side is protected by the + * embedded spin_lock. + */ +static DEFINE_SEQLOCK(zonelist_update_seq); + +static unsigned int zonelist_iter_begin(void) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqbegin(&zonelist_update_seq); + + return 0; +} + +static unsigned int check_retry_zonelist(unsigned int seq) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqretry(&zonelist_update_seq, seq); + + return seq; +} + /* Perform direct synchronous page reclaim */ static int __perform_reclaim(gfp_t gfp_mask, unsigned int order, @@ -4084,6 +4108,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int compaction_retries; int no_progress_loops; unsigned int cpuset_mems_cookie; + unsigned int zonelist_iter_cookie; int reserve_flags; /* @@ -4094,11 +4119,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) gfp_mask &= ~__GFP_ATOMIC; -retry_cpuset: +restart: compaction_retries = 0; no_progress_loops = 0; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist_iter_cookie = zonelist_iter_begin(); /* * The fast path uses conservative alloc_flags to succeed only until @@ -4247,9 +4273,13 @@ retry: goto retry; - /* Deal with possible cpuset update races before we start OOM killing */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* Reclaim has failed us, start killing things */ page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); @@ -4269,9 +4299,13 @@ retry: } nopage: - /* Deal with possible cpuset update races before we fail */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* * Make sure that __GFP_NOFAIL request doesn't leak out and make sure @@ -4569,6 +4603,18 @@ refill: /* reset page count bias and offset to start of new frag */ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } } nc->pagecnt_bias--; @@ -5379,9 +5425,8 @@ static void __build_all_zonelists(void *data) int nid; int __maybe_unused cpu; pg_data_t *self = data; - static DEFINE_SPINLOCK(lock); - spin_lock(&lock); + write_seqlock(&zonelist_update_seq); #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); @@ -5414,7 +5459,7 @@ static void __build_all_zonelists(void *data) #endif } - spin_unlock(&lock); + write_sequnlock(&zonelist_update_seq); } static noinline void __init diff --git a/mm/slub.c b/mm/slub.c index 0fefe0ad8f57..ef730ea8263c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5688,7 +5688,8 @@ static char *create_unique_id(struct kmem_cache *s) char *name = kmalloc(ID_STR_LENGTH, GFP_KERNEL); char *p = name; - BUG_ON(!name); + if (!name) + return ERR_PTR(-ENOMEM); *p++ = ':'; /* @@ -5770,6 +5771,8 @@ static int sysfs_slab_add(struct kmem_cache *s) * for the symlinks. */ name = create_unique_id(s); + if (IS_ERR(name)) + return PTR_ERR(name); } s->kobj.kset = kset; |