diff options
Diffstat (limited to 'mm')
44 files changed, 1062 insertions, 692 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index a5dae9a7eb51..fbdc5c70e487 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -576,19 +576,6 @@ config ZSMALLOC returned by an alloc(). This handle must be mapped in order to access the allocated space. -config PGTABLE_MAPPING - bool "Use page table mapping to access object in zsmalloc" - depends on ZSMALLOC - help - By default, zsmalloc uses a copy-based object mapping method to - access allocations that span two pages. However, if a particular - architecture (ex, ARM) performs VM mapping faster than copying, - then you should select this. This causes zsmalloc to use page table - mapping rather than copying for object mapping. - - You can check speed with zsmalloc benchmark: - https://github.com/spartacus06/zsmapbench - config ZSMALLOC_STAT bool "Export zsmalloc statistics" depends on ZSMALLOC diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 3f2480e4c5af..3954ef0cc770 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1013,6 +1013,13 @@ void bdi_unregister(struct backing_dev_info *bdi) wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); + /* + * If this BDI's min ratio has been set, use bdi_set_min_ratio() to + * update the global bdi_min_ratio. + */ + if (bdi->min_ratio) + bdi_set_min_ratio(bdi, 0); + if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); diff --git a/mm/compaction.c b/mm/compaction.c index 92470625f0b1..0758afd6325d 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1276,7 +1276,7 @@ fast_isolate_freepages(struct compact_control *cc) { unsigned int limit = min(1U, freelist_scan_limit(cc) >> 1); unsigned int nr_scanned = 0; - unsigned long low_pfn, min_pfn, high_pfn = 0, highest = 0; + unsigned long low_pfn, min_pfn, highest = 0; unsigned long nr_isolated = 0; unsigned long distance; struct page *page = NULL; @@ -1321,6 +1321,7 @@ fast_isolate_freepages(struct compact_control *cc) struct page *freepage; unsigned long flags; unsigned int order_scanned = 0; + unsigned long high_pfn = 0; if (!area->nr_free) continue; @@ -1629,6 +1630,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) unsigned long pfn = cc->migrate_pfn; unsigned long high_pfn; int order; + bool found_block = false; /* Skip hints are relied on to avoid repeats on the fast search */ if (cc->ignore_skip_hint) @@ -1671,7 +1673,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) high_pfn = pageblock_start_pfn(cc->migrate_pfn + distance); for (order = cc->order - 1; - order >= PAGE_ALLOC_COSTLY_ORDER && pfn == cc->migrate_pfn && nr_scanned < limit; + order >= PAGE_ALLOC_COSTLY_ORDER && !found_block && nr_scanned < limit; order--) { struct free_area *area = &cc->zone->free_area[order]; struct list_head *freelist; @@ -1686,7 +1688,11 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) list_for_each_entry(freepage, freelist, lru) { unsigned long free_pfn; - nr_scanned++; + if (nr_scanned++ >= limit) { + move_freelist_tail(freelist, freepage); + break; + } + free_pfn = page_to_pfn(freepage); if (free_pfn < high_pfn) { /* @@ -1695,28 +1701,21 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) * the list assumes an entry is deleted, not * reordered. */ - if (get_pageblock_skip(freepage)) { - if (list_is_last(freelist, &freepage->lru)) - break; - + if (get_pageblock_skip(freepage)) continue; - } /* Reorder to so a future search skips recent pages */ move_freelist_tail(freelist, freepage); update_fast_start_pfn(cc, free_pfn); pfn = pageblock_start_pfn(free_pfn); + if (pfn < cc->zone->zone_start_pfn) + pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; + found_block = true; set_pageblock_skip(freepage); break; } - - if (nr_scanned >= limit) { - cc->fast_search_fail++; - move_freelist_tail(freelist, freepage); - break; - } } spin_unlock_irqrestore(&cc->zone->lock, flags); } @@ -1727,9 +1726,10 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) * If fast scanning failed then use a cached entry for a page block * that had free pages as the basis for starting a linear scan. */ - if (pfn == cc->migrate_pfn) + if (!found_block) { + cc->fast_search_fail++; pfn = reinit_migrate_pfn(cc); - + } return pfn; } diff --git a/mm/filemap.c b/mm/filemap.c index 51b2cb5aa503..c10e237cc2c6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -847,16 +847,15 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask, - void **shadowp) +noinline int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); struct mem_cgroup *memcg; int error; - void *old; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); @@ -872,21 +871,41 @@ static int __add_to_page_cache_locked(struct page *page, get_page(page); page->mapping = mapping; page->index = offset; + gfp_mask &= GFP_RECLAIM_MASK; do { + unsigned int order = xa_get_order(xas.xa, xas.xa_index); + void *entry, *old = NULL; + + if (order > thp_order(page)) + xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), + order, gfp_mask); xas_lock_irq(&xas); - old = xas_load(&xas); - if (old && !xa_is_value(old)) - xas_set_err(&xas, -EEXIST); + xas_for_each_conflict(&xas, entry) { + old = entry; + if (!xa_is_value(entry)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + } + + if (old) { + if (shadowp) + *shadowp = old; + /* entry may have been split before we acquired lock */ + order = xa_get_order(xas.xa, xas.xa_index); + if (order > thp_order(page)) { + xas_split(&xas, old, order); + xas_reset(&xas); + } + } + xas_store(&xas, page); if (xas_error(&xas)) goto unlock; - if (xa_is_value(old)) { + if (old) mapping->nrexceptional--; - if (shadowp) - *shadowp = old; - } mapping->nrpages++; /* hugetlb pages do not participate in page cache accounting */ @@ -894,7 +913,7 @@ static int __add_to_page_cache_locked(struct page *page, __inc_node_page_state(page, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); - } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); + } while (xas_nomem(&xas, gfp_mask)); if (xas_error(&xas)) goto error; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 873de55d93fb..e50799d7002e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -61,6 +61,7 @@ static struct shrinker deferred_split_shrinker; static atomic_t huge_zero_refcount; struct page *huge_zero_page __read_mostly; +unsigned long huge_zero_pfn __read_mostly = ~0UL; bool transparent_hugepage_enabled(struct vm_area_struct *vma) { @@ -97,6 +98,7 @@ retry: __free_pages(zero_page, compound_order(zero_page)); goto retry; } + WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); @@ -146,6 +148,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct page *zero_page = xchg(&huge_zero_page, NULL); BUG_ON(zero_page == NULL); + WRITE_ONCE(huge_zero_pfn, ~0UL); __free_pages(zero_page, compound_order(zero_page)); return HPAGE_PMD_NR; } @@ -722,7 +725,6 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) transparent_hugepage_use_zero_page()) { pgtable_t pgtable; struct page *zero_page; - bool set; vm_fault_t ret; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) @@ -735,25 +737,25 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); ret = 0; - set = false; if (pmd_none(*vmf->pmd)) { ret = check_stable_address_space(vma->vm_mm); if (ret) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); + pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { set_huge_zero_page(pgtable, vma->vm_mm, vma, haddr, vmf->pmd, zero_page); spin_unlock(vmf->ptl); - set = true; } - } else + } else { spin_unlock(vmf->ptl); - if (!set) pte_free(vma->vm_mm, pgtable); + } return ret; } gfp = alloc_hugepage_direct_gfpmask(vma); @@ -1721,7 +1723,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, * If other processes are mapping this page, we couldn't discard * the page unless they all do MADV_FREE so let's skip the page. */ - if (page_mapcount(page) != 1) + if (total_mapcount(page) != 1) goto out; if (!trylock_page(page)) @@ -2156,7 +2158,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { - _pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); + old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it @@ -2165,16 +2167,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, zap_deposited_table(mm, pmd); if (vma_is_dax(vma)) return; - page = pmd_page(_pmd); - if (!PageDirty(page) && pmd_dirty(_pmd)) - set_page_dirty(page); - if (!PageReferenced(page) && pmd_young(_pmd)) - SetPageReferenced(page); - page_remove_rmap(page, true); - put_page(page); + if (unlikely(is_pmd_migration_entry(old_pmd))) { + swp_entry_t entry; + + entry = pmd_to_swp_entry(old_pmd); + page = migration_entry_to_page(entry); + } else { + page = pmd_page(old_pmd); + if (!PageDirty(page) && pmd_dirty(old_pmd)) + set_page_dirty(page); + if (!PageReferenced(page) && pmd_young(old_pmd)) + SetPageReferenced(page); + page_remove_rmap(page, true); + put_page(page); + } add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; - } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { + } + + if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside @@ -2307,7 +2318,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, { spinlock_t *ptl; struct mmu_notifier_range range; - bool was_locked = false; + bool do_unlock_page = false; pmd_t _pmd; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, @@ -2323,7 +2334,6 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, VM_BUG_ON(freeze && !page); if (page) { VM_WARN_ON_ONCE(!PageLocked(page)); - was_locked = true; if (page != pmd_page(*pmd)) goto out; } @@ -2332,19 +2342,29 @@ repeat: if (pmd_trans_huge(*pmd)) { if (!page) { page = pmd_page(*pmd); - if (unlikely(!trylock_page(page))) { - get_page(page); - _pmd = *pmd; - spin_unlock(ptl); - lock_page(page); - spin_lock(ptl); - if (unlikely(!pmd_same(*pmd, _pmd))) { - unlock_page(page); + /* + * An anonymous page must be locked, to ensure that a + * concurrent reuse_swap_page() sees stable mapcount; + * but reuse_swap_page() is not used on shmem or file, + * and page lock must not be taken when zap_pmd_range() + * calls __split_huge_pmd() while i_mmap_lock is held. + */ + if (PageAnon(page)) { + if (unlikely(!trylock_page(page))) { + get_page(page); + _pmd = *pmd; + spin_unlock(ptl); + lock_page(page); + spin_lock(ptl); + if (unlikely(!pmd_same(*pmd, _pmd))) { + unlock_page(page); + put_page(page); + page = NULL; + goto repeat; + } put_page(page); - page = NULL; - goto repeat; } - put_page(page); + do_unlock_page = true; } } if (PageMlocked(page)) @@ -2354,7 +2374,7 @@ repeat: __split_huge_pmd_locked(vma, pmd, range.start, freeze); out: spin_unlock(ptl); - if (!was_locked && page) + if (do_unlock_page) unlock_page(page); /* * No need to double call mmu_notifier->invalidate_range() callback. @@ -2441,16 +2461,16 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma, static void unmap_page(struct page *page) { enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS | - TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD; - bool unmap_success; + TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC; VM_BUG_ON_PAGE(!PageHead(page), page); if (PageAnon(page)) ttu_flags |= TTU_SPLIT_FREEZE; - unmap_success = try_to_unmap(page, ttu_flags); - VM_BUG_ON_PAGE(!unmap_success, page); + try_to_unmap(page, ttu_flags); + + VM_WARN_ON_ONCE_PAGE(page_mapped(page), page); } static void remap_page(struct page *page) @@ -2569,7 +2589,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, ClearPageCompound(head); - split_page_owner(head, HPAGE_PMD_ORDER); + split_page_owner(head, HPAGE_PMD_NR); /* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { @@ -2729,7 +2749,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) struct deferred_split *ds_queue = get_deferred_split_queue(page); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; - int count, mapcount, extra_pins, ret; + int extra_pins, ret; bool mlocked; unsigned long flags; pgoff_t end; @@ -2791,7 +2811,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) mlocked = PageMlocked(page); unmap_page(head); - VM_BUG_ON_PAGE(compound_mapcount(head), head); /* Make sure the page is not on per-CPU pagevec as it takes pin */ if (mlocked) @@ -2814,9 +2833,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&ds_queue->split_queue_lock); - count = page_count(head); - mapcount = total_mapcount(head); - if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { + if (page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { ds_queue->split_queue_len--; list_del(page_deferred_list(head)); @@ -2837,16 +2854,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) } else ret = 0; } else { - if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - pr_alert("total_mapcount: %u, page_count(): %u\n", - mapcount, count); - if (PageTail(page)) - dump_page(head, NULL); - dump_page(page, "total_mapcount(head) > 0"); - BUG(); - } spin_unlock(&ds_queue->split_queue_lock); -fail: if (mapping) +fail: + if (mapping) xa_unlock(&mapping->i_pages); spin_unlock_irqrestore(&pgdata->lru_lock, flags); remap_page(head); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 62ec514dae65..b6f029a1059f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -71,6 +71,21 @@ DEFINE_SPINLOCK(hugetlb_lock); static int num_fault_mutexes; struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; +static inline bool PageHugeFreed(struct page *head) +{ + return page_private(head + 4) == -1UL; +} + +static inline void SetPageHugeFreed(struct page *head) +{ + set_page_private(head + 4, -1UL); +} + +static inline void ClearPageHugeFreed(struct page *head) +{ + set_page_private(head + 4, 0); +} + /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); @@ -576,13 +591,20 @@ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; + bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); - if (rsv_adjust) { + if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); - hugetlb_acct_memory(h, 1); + if (!hugetlb_acct_memory(h, 1)) + reserved = true; + } else if (!rsv_adjust) { + reserved = true; } + + if (!reserved) + pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* @@ -869,6 +891,7 @@ static void enqueue_huge_page(struct hstate *h, struct page *page) list_move(&page->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; + SetPageHugeFreed(page); } static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) @@ -886,6 +909,7 @@ static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid) return NULL; list_move(&page->lru, &h->hugepage_activelist); set_page_refcounted(page); + ClearPageHugeFreed(page); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return page; @@ -1175,14 +1199,16 @@ static inline void destroy_compound_gigantic_page(struct page *page, static void update_and_free_page(struct hstate *h, struct page *page) { int i; + struct page *subpage = page; if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) return; h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; - for (i = 0; i < pages_per_huge_page(h); i++) { - page[i].flags &= ~(1 << PG_locked | 1 << PG_error | + for (i = 0; i < pages_per_huge_page(h); + i++, subpage = mem_map_next(subpage, page, i)) { + subpage->flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced | 1 << PG_dirty | 1 << PG_active | 1 << PG_private | 1 << PG_writeback); @@ -1217,12 +1243,11 @@ struct hstate *size_to_hstate(unsigned long size) */ bool page_huge_active(struct page *page) { - VM_BUG_ON_PAGE(!PageHuge(page), page); - return PageHead(page) && PagePrivate(&page[1]); + return PageHeadHuge(page) && PagePrivate(&page[1]); } /* never called for tail page */ -static void set_page_huge_active(struct page *page) +void set_page_huge_active(struct page *page) { VM_BUG_ON_PAGE(!PageHeadHuge(page), page); SetPagePrivate(&page[1]); @@ -1375,6 +1400,7 @@ static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) set_hugetlb_cgroup(page, NULL); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; + ClearPageHugeFreed(page); spin_unlock(&hugetlb_lock); } @@ -1435,15 +1461,12 @@ int PageHeadHuge(struct page *page_head) return get_compound_page_dtor(page_head) == free_huge_page; } -pgoff_t __basepage_index(struct page *page) +pgoff_t hugetlb_basepage_index(struct page *page) { struct page *page_head = compound_head(page); pgoff_t index = page_index(page_head); unsigned long compound_idx; - if (!PageHuge(page_head)) - return page_index(page); - if (compound_order(page_head) >= MAX_ORDER) compound_idx = page_to_pfn(page) - page_to_pfn(page_head); else @@ -1602,6 +1625,7 @@ int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; +retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!PageHuge(page)) return 0; @@ -1618,6 +1642,26 @@ int dissolve_free_huge_page(struct page *page) int nid = page_to_nid(head); if (h->free_huge_pages - h->resv_huge_pages == 0) goto out; + + /* + * We should make sure that the page is already on the free list + * when it is dissolved. + */ + if (unlikely(!PageHugeFreed(head))) { + spin_unlock(&hugetlb_lock); + cond_resched(); + + /* + * Theoretically, we should return -EBUSY when we + * encounter this race. In fact, we have a chance + * to successfully dissolve the page if we do a + * retry. Because the race window is quite small. + * If we seize this opportunity, it is an optimization + * for increasing the success rate of dissolving page. + */ + goto retry; + } + /* * Move PageHWPoison flag from head page to the raw error page, * which makes any subpages rather than the error page reusable. @@ -2774,8 +2818,10 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, return -ENOMEM; retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group); - if (retval) + if (retval) { kobject_put(hstate_kobjs[hi]); + hstate_kobjs[hi] = NULL; + } return retval; } @@ -3543,6 +3589,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mmu_notifier_range range; + bool force_flush = false; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3571,10 +3618,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { spin_unlock(ptl); - /* - * We just unmapped a page of PMDs by clearing a PUD. - * The caller's TLB flush range should cover this area. - */ + tlb_flush_pmd_range(tlb, address & PUD_MASK, PUD_SIZE); + force_flush = true; continue; } @@ -3631,6 +3676,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, } mmu_notifier_invalidate_range_end(&range); tlb_end_vma(tlb, vma); + + /* + * If we unshared PMDs, the TLB flush was not recorded in mmu_gather. We + * could defer the flush until now, since by holding i_mmap_rwsem we + * guaranteed that the last refernece would not be dropped. But we must + * do the flushing before we return, as otherwise i_mmap_rwsem will be + * dropped and the last reference to the shared PMDs page might be + * dropped as well. + * + * In theory we could defer the freeing of the PMD pages as well, but + * huge_pmd_unshare() relies on the exact page_count for the PMD page to + * detect sharing, so we cannot defer the release of the page either. + * Instead, do flush now. + */ + if (force_flush) + tlb_flush_mmu_tlbonly(tlb); } void __unmap_hugepage_range_final(struct mmu_gather *tlb, @@ -3978,7 +4039,7 @@ retry: * handling userfault. Reacquire after handling * fault to make calling code simpler. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); ret = handle_userfault(&vmf, VM_UFFD_MISSING); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -4036,7 +4097,7 @@ 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; } @@ -4106,7 +4167,7 @@ backout_unlocked: #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address) + pgoff_t idx) { unsigned long key[2]; u32 hash; @@ -4114,7 +4175,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, key[0] = (unsigned long) mapping; key[1] = idx; - hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0); + hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } @@ -4124,7 +4185,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping, - pgoff_t idx, unsigned long address) + pgoff_t idx) { return 0; } @@ -4168,7 +4229,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ - hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); entry = huge_ptep_get(ptep); @@ -4289,10 +4350,20 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, struct page *page; if (!*pagep) { - ret = -ENOMEM; + /* If a page already exists, then it's UFFDIO_COPY for + * a non-missing case. Return -EEXIST. + */ + if (vm_shared && + hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { + ret = -EEXIST; + goto out; + } + page = alloc_huge_page(dst_vma, dst_addr, 0); - if (IS_ERR(page)) + if (IS_ERR(page)) { + ret = -ENOMEM; goto out; + } ret = copy_huge_page_from_user(page, (const void __user *) src_addr, @@ -4860,21 +4931,23 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { - unsigned long a_start, a_end; + unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), + v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); - if (!(vma->vm_flags & VM_MAYSHARE)) + /* + * vma need span at least one aligned PUD size and the start,end range + * must at least partialy within it. + */ + if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || + (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ - a_start = ALIGN_DOWN(*start, PUD_SIZE); - a_end = ALIGN(*end, PUD_SIZE); + if (*start > v_start) + *start = ALIGN_DOWN(*start, PUD_SIZE); - /* - * Intersect the range with the vma range, since pmd sharing won't be - * across vma after all - */ - *start = max(vma->vm_start, a_start); - *end = min(vma->vm_end, a_end); + if (*end < v_end) + *end = ALIGN(*end, PUD_SIZE); } /* @@ -4960,7 +5033,14 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); - *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; + /* + * This update of passed address optimizes loops sequentially + * processing addresses in increments of huge page size (PMD_SIZE + * in this case). By clearing the pud, a PUD_SIZE area is unmapped. + * Update address to the 'last page' in the cleared area so that + * calling loop can move to first page past this area. + */ + *addr |= PUD_SIZE - PMD_SIZE; return 1; } #define want_pmd_share() (1) @@ -5136,9 +5216,9 @@ bool isolate_huge_page(struct page *page, struct list_head *list) { bool ret = true; - VM_BUG_ON_PAGE(!PageHead(page), page); spin_lock(&hugetlb_lock); - if (!page_huge_active(page) || !get_page_unless_zero(page)) { + if (!PageHeadHuge(page) || !page_huge_active(page) || + !get_page_unless_zero(page)) { ret = false; goto unlock; } diff --git a/mm/internal.h b/mm/internal.h index 7dd7fbb577a9..cf382549dd70 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -339,27 +339,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page) extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); /* - * At what user virtual address is page expected in @vma? + * At what user virtual address is page expected in vma? + * Returns -EFAULT if all of the page is outside the range of vma. + * If page is a compound head, the entire compound page is considered. */ static inline unsigned long -__vma_address(struct page *page, struct vm_area_struct *vma) +vma_address(struct page *page, struct vm_area_struct *vma) { - pgoff_t pgoff = page_to_pgoff(page); - return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page); + if (pgoff >= vma->vm_pgoff) { + address = vma->vm_start + + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address >= vma->vm_end) + address = -EFAULT; + } else if (PageHead(page) && + pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) { + /* Test above avoids possibility of wrap to 0 on 32-bit */ + address = vma->vm_start; + } else { + address = -EFAULT; + } + return address; } +/* + * Then at what user virtual address will none of the page be found in vma? + * Assumes that vma_address() already returned a good starting address. + * If page is a compound head, the entire compound page is considered. + */ static inline unsigned long -vma_address(struct page *page, struct vm_area_struct *vma) +vma_address_end(struct page *page, struct vm_area_struct *vma) { - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); - - /* page should be within @vma mapping range */ - VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma); - - return max(start, vma->vm_start); + pgoff_t pgoff; + unsigned long address; + + VM_BUG_ON_PAGE(PageKsm(page), page); /* KSM page->index unusable */ + pgoff = page_to_pgoff(page) + compound_nr(page); + address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); + /* Check for address beyond vma (or wrapped through 0?) */ + if (address < vma->vm_start || address > vma->vm_end) + address = vma->vm_end; + return address; } static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, diff --git a/mm/kasan/init.c b/mm/kasan/init.c index ce45c491ebcd..ee21e1c1150c 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -388,9 +388,10 @@ static void kasan_remove_pmd_table(pmd_t *pmd, unsigned long addr, if (kasan_pte_table(*pmd)) { if (IS_ALIGNED(addr, PMD_SIZE) && - IS_ALIGNED(next, PMD_SIZE)) + IS_ALIGNED(next, PMD_SIZE)) { pmd_clear(pmd); - continue; + continue; + } } pte = pte_offset_kernel(pmd, addr); kasan_remove_pte_table(pte, addr, next); @@ -413,9 +414,10 @@ static void kasan_remove_pud_table(pud_t *pud, unsigned long addr, if (kasan_pmd_table(*pud)) { if (IS_ALIGNED(addr, PUD_SIZE) && - IS_ALIGNED(next, PUD_SIZE)) + IS_ALIGNED(next, PUD_SIZE)) { pud_clear(pud); - continue; + continue; + } } pmd = pmd_offset(pud, addr); pmd_base = pmd_offset(pud, 0); @@ -439,9 +441,10 @@ static void kasan_remove_p4d_table(p4d_t *p4d, unsigned long addr, if (kasan_pud_table(*p4d)) { if (IS_ALIGNED(addr, P4D_SIZE) && - IS_ALIGNED(next, P4D_SIZE)) + IS_ALIGNED(next, P4D_SIZE)) { p4d_clear(p4d); - continue; + continue; + } } pud = pud_offset(p4d, addr); kasan_remove_pud_table(pud, addr, next); @@ -473,9 +476,10 @@ void kasan_remove_zero_shadow(void *start, unsigned long size) if (kasan_p4d_table(*pgd)) { if (IS_ALIGNED(addr, PGDIR_SIZE) && - IS_ALIGNED(next, PGDIR_SIZE)) + IS_ALIGNED(next, PGDIR_SIZE)) { pgd_clear(pgd); - continue; + continue; + } } p4d = p4d_offset(pgd, addr); @@ -499,7 +503,6 @@ int kasan_add_zero_shadow(void *start, unsigned long size) ret = kasan_populate_early_shadow(shadow_start, shadow_end); if (ret) - kasan_remove_zero_shadow(shadow_start, - size >> KASAN_SHADOW_SCALE_SHIFT); + kasan_remove_zero_shadow(start, size); return ret; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 9ec618d5ea55..3c2326568193 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -54,6 +54,9 @@ enum scan_result { #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> +static struct task_struct *khugepaged_thread __read_mostly; +static DEFINE_MUTEX(khugepaged_mutex); + /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; @@ -625,17 +628,17 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, mmu_notifier_test_young(vma->vm_mm, address)) referenced++; } - if (likely(writable)) { - if (likely(referenced)) { - result = SCAN_SUCCEED; - trace_mm_collapse_huge_page_isolate(page, none_or_zero, - referenced, writable, result); - return 1; - } - } else { + + if (unlikely(!writable)) { result = SCAN_PAGE_RO; + } else if (unlikely(!referenced)) { + result = SCAN_LACK_REFERENCED_PAGE; + } else { + result = SCAN_SUCCEED; + trace_mm_collapse_huge_page_isolate(page, none_or_zero, + referenced, writable, result); + return 1; } - out: release_pte_pages(pte, _pte); trace_mm_collapse_huge_page_isolate(page, none_or_zero, @@ -832,6 +835,18 @@ static struct page *khugepaged_alloc_hugepage(bool *wait) static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { + /* + * If the hpage allocated earlier was briefly exposed in page cache + * before collapse_file() failed, it is possible that racing lookups + * have not yet completed, and would then be unpleasantly surprised by + * finding the hpage reused for the same mapping at a different offset. + * Just release the previous allocation if there is any danger of that. + */ + if (*hpage && page_count(*hpage) > 1) { + put_page(*hpage); + *hpage = NULL; + } + if (!*hpage) *hpage = khugepaged_alloc_hugepage(wait); @@ -2165,8 +2180,6 @@ static void set_recommended_min_free_kbytes(void) int start_stop_khugepaged(void) { - static struct task_struct *khugepaged_thread __read_mostly; - static DEFINE_MUTEX(khugepaged_mutex); int err = 0; mutex_lock(&khugepaged_mutex); @@ -2193,3 +2206,11 @@ fail: mutex_unlock(&khugepaged_mutex); return err; } + +void khugepaged_min_free_kbytes_update(void) +{ + mutex_lock(&khugepaged_mutex); + if (khugepaged_enabled() && khugepaged_thread) + set_recommended_min_free_kbytes(); + mutex_unlock(&khugepaged_mutex); +} diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 312942d78405..3761c79137b1 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -787,6 +787,8 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) unsigned long flags; struct kmemleak_object *object; struct kmemleak_scan_area *area = NULL; + unsigned long untagged_ptr; + unsigned long untagged_objp; object = find_and_get_object(ptr, 1); if (!object) { @@ -795,6 +797,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) return; } + untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); + untagged_objp = (unsigned long)kasan_reset_tag((void *)object->pointer); + if (scan_area_cache) area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp)); @@ -806,8 +811,8 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp) goto out_unlock; } if (size == SIZE_MAX) { - size = object->pointer + object->size - ptr; - } else if (ptr + size > object->pointer + object->size) { + size = untagged_objp + object->size - untagged_ptr; + } else if (untagged_ptr + size > untagged_objp + object->size) { kmemleak_warn("Scan area larger than object 0x%08lx\n", ptr); dump_object_info(object); kmem_cache_free(scan_area_cache, area); @@ -1118,7 +1123,7 @@ EXPORT_SYMBOL(kmemleak_no_scan); void __ref kmemleak_alloc_phys(phys_addr_t phys, size_t size, int min_count, gfp_t gfp) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_alloc(__va(phys), size, min_count, gfp); } EXPORT_SYMBOL(kmemleak_alloc_phys); @@ -1132,7 +1137,7 @@ EXPORT_SYMBOL(kmemleak_alloc_phys); */ void __ref kmemleak_free_part_phys(phys_addr_t phys, size_t size) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_free_part(__va(phys), size); } EXPORT_SYMBOL(kmemleak_free_part_phys); @@ -1144,7 +1149,7 @@ EXPORT_SYMBOL(kmemleak_free_part_phys); */ void __ref kmemleak_not_leak_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_not_leak(__va(phys)); } EXPORT_SYMBOL(kmemleak_not_leak_phys); @@ -1156,7 +1161,7 @@ EXPORT_SYMBOL(kmemleak_not_leak_phys); */ void __ref kmemleak_ignore_phys(phys_addr_t phys) { - if (!IS_ENABLED(CONFIG_HIGHMEM) || PHYS_PFN(phys) < max_low_pfn) + if (PHYS_PFN(phys) >= min_low_pfn && PHYS_PFN(phys) < max_low_pfn) kmemleak_ignore(__va(phys)); } EXPORT_SYMBOL(kmemleak_ignore_phys); @@ -1399,7 +1404,8 @@ static void kmemleak_scan(void) { unsigned long flags; struct kmemleak_object *object; - int i; + struct zone *zone; + int __maybe_unused i; int new_leaks = 0; jiffies_last_scan = jiffies; @@ -1439,9 +1445,9 @@ static void kmemleak_scan(void) * Struct page scanning for each node. */ get_online_mems(); - for_each_online_node(i) { - unsigned long start_pfn = node_start_pfn(i); - unsigned long end_pfn = node_end_pfn(i); + for_each_populated_zone(zone) { + unsigned long start_pfn = zone->zone_start_pfn; + unsigned long end_pfn = zone_end_pfn(zone); unsigned long pfn; for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -1450,8 +1456,8 @@ static void kmemleak_scan(void) if (!page) continue; - /* only scan pages belonging to this node */ - if (page_to_nid(page) != i) + /* only scan pages belonging to this zone */ + if (page_zone(page) != zone) continue; /* only scan if page is in use */ if (page_count(page) == 0) @@ -793,6 +793,7 @@ static void remove_rmap_item_from_tree(struct rmap_item *rmap_item) stable_node->rmap_hlist_len--; put_anon_vma(rmap_item->anon_vma); + rmap_item->head = NULL; rmap_item->address &= PAGE_MASK; } else if (rmap_item->address & UNSTABLE_FLAG) { diff --git a/mm/list_lru.c b/mm/list_lru.c index 0f1f6b06b7f3..d12c1943f6f3 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -544,7 +544,6 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, struct list_lru_node *nlru = &lru->node[nid]; int dst_idx = dst_memcg->kmemcg_id; struct list_lru_one *src, *dst; - bool set; /* * Since list_lru_{add,del} may be called under an IRQ-safe lock, @@ -556,11 +555,12 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid, dst = list_lru_from_memcg_idx(nlru, dst_idx); list_splice_init(&src->list, &dst->list); - set = (!dst->nr_items && src->nr_items); - dst->nr_items += src->nr_items; - if (set) + + if (src->nr_items) { + dst->nr_items += src->nr_items; memcg_set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru)); - src->nr_items = 0; + src->nr_items = 0; + } spin_unlock_irq(&nlru->lock); } diff --git a/mm/memblock.c b/mm/memblock.c index c4b16cae2bc9..a75cc65f0330 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -164,6 +164,8 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type, { unsigned long i; + memblock_cap_size(base, &size); + for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) @@ -257,14 +259,6 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, * * Find @size free area aligned to @align in the specified range and node. * - * When allocation direction is bottom-up, the @start should be greater - * than the end of the kernel image. Otherwise, it will be trimmed. The - * reason is that we want the bottom-up allocation just near the kernel - * image so it is highly likely that the allocated memory and the kernel - * will reside in the same node. - * - * If bottom-up allocation failed, will try to allocate memory top-down. - * * Return: * Found address on success, 0 on failure. */ @@ -273,8 +267,6 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t end, int nid, enum memblock_flags flags) { - phys_addr_t kernel_end, ret; - /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || end == MEMBLOCK_ALLOC_KASAN) @@ -283,40 +275,13 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); - kernel_end = __pa_symbol(_end); - - /* - * try bottom-up allocation only when bottom-up mode - * is set and @end is above the kernel image. - */ - if (memblock_bottom_up() && end > kernel_end) { - phys_addr_t bottom_up_start; - - /* make sure we will allocate above the kernel */ - bottom_up_start = max(start, kernel_end); - /* ok, try bottom-up allocation first */ - ret = __memblock_find_range_bottom_up(bottom_up_start, end, - size, align, nid, flags); - if (ret) - return ret; - - /* - * we always limit bottom-up allocation above the kernel, - * but top-down allocation doesn't have the limit, so - * retrying top-down allocation may succeed when bottom-up - * allocation failed. - * - * bottom-up allocation is expected to be fail very rarely, - * so we use WARN_ONCE() here to see the stack trace if - * fail happens. - */ - WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE), - "memblock: bottom-up allocation failed, memory hotremove may be affected\n"); - } - - return __memblock_find_range_top_down(start, end, size, align, nid, - flags); + if (memblock_bottom_up()) + return __memblock_find_range_bottom_up(start, end, size, align, + nid, flags); + else + return __memblock_find_range_top_down(start, end, size, align, + nid, flags); } /** @@ -383,14 +348,20 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - __memblock_free_late(addr, size); + if (memblock_reserved_in_slab) + kfree(memblock.reserved.regions); + else + __memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - __memblock_free_late(addr, size); + if (memblock_memory_in_slab) + kfree(memblock.memory.regions); + else + __memblock_free_late(addr, size); } } #endif @@ -1797,7 +1768,6 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { - memblock_cap_size(base, &size); return memblock_overlaps_region(&memblock.reserved, base, size); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ca1632850fb7..8fc663545498 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -776,8 +776,13 @@ void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) rcu_read_lock(); memcg = memcg_from_slab_page(page); - /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!memcg || memcg == root_mem_cgroup) { + /* + * Untracked pages have no memcg, no lruvec. Update only the + * node. If we reparent the slab objects to the root memcg, + * when we free the slab object, we need to update the per-memcg + * vmstats to keep it correct for the root memcg. + */ + if (!memcg) { __mod_node_page_state(pgdat, idx, val); } else { lruvec = mem_cgroup_lruvec(pgdat, memcg); @@ -5398,7 +5403,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, struct page *page = NULL; swp_entry_t ent = pte_to_swp_entry(ptent); - if (!(mc.flags & MOVE_ANON) || non_swap_entry(ent)) + if (!(mc.flags & MOVE_ANON)) return NULL; /* @@ -5417,6 +5422,9 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, return page; } + if (non_swap_entry(ent)) + return NULL; + /* * Because lookup_swap_cache() updates some statistics counter, * we call find_get_page() with swapper_space directly. @@ -6438,6 +6446,14 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, if (!root) root = root_mem_cgroup; + + /* + * Effective values of the reclaim targets are ignored so they + * can be stale. Have a look at mem_cgroup_protection for more + * details. + * TODO: calculation should be more robust so that we do not need + * that special casing. + */ if (memcg == root) return MEMCG_PROT_NONE; @@ -6957,7 +6973,7 @@ static int __init cgroup_memory(char *s) if (!strcmp(token, "nokmem")) cgroup_memory_nokmem = true; } - return 0; + return 1; } __setup("cgroup.memory=", cgroup_memory); diff --git a/mm/memfd.c b/mm/memfd.c index 2647c898990c..fae4142f7d25 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -31,20 +31,28 @@ static void memfd_tag_pins(struct xa_state *xas) { struct page *page; - unsigned int tagged = 0; + int latency = 0; + int cache_count; lru_add_drain(); xas_lock_irq(xas); xas_for_each(xas, page, ULONG_MAX) { - if (xa_is_value(page)) - continue; - page = find_subpage(page, xas->xa_index); - if (page_count(page) - page_mapcount(page) > 1) + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && + page_count(page) - total_mapcount(page) != cache_count) xas_set_mark(xas, MEMFD_TAG_PINNED); + if (cache_count != 1) + xas_set(xas, page->index + cache_count); - if (++tagged % XA_CHECK_SCHED) + latency += cache_count; + if (latency < XA_CHECK_SCHED) continue; + latency = 0; xas_pause(xas); xas_unlock_irq(xas); @@ -73,7 +81,8 @@ static int memfd_wait_for_pins(struct address_space *mapping) error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { - unsigned int tagged = 0; + int latency = 0; + int cache_count; if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break; @@ -87,10 +96,14 @@ static int memfd_wait_for_pins(struct address_space *mapping) xas_lock_irq(&xas); xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) { bool clear = true; - if (xa_is_value(page)) - continue; - page = find_subpage(page, xas.xa_index); - if (page_count(page) - page_mapcount(page) != 1) { + + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && cache_count != + page_count(page) - total_mapcount(page)) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still @@ -103,8 +116,11 @@ static int memfd_wait_for_pins(struct address_space *mapping) } if (clear) xas_clear_mark(&xas, MEMFD_TAG_PINNED); - if (++tagged % XA_CHECK_SCHED) + + latency += cache_count; + if (latency < XA_CHECK_SCHED) continue; + latency = 0; xas_pause(&xas); xas_unlock_irq(&xas); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3151c87dff73..9030ab0d9d97 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1215,7 +1215,7 @@ static int memory_failure_dev_pagemap(unsigned long pfn, int flags, * communicated in siginfo, see kill_proc() */ start = (page->index << PAGE_SHIFT) & ~(size - 1); - unmap_mapping_range(page->mapping, start, start + size, 0); + unmap_mapping_range(page->mapping, start, size, 0); } kill_procs(&tokill, flags & MF_MUST_KILL, !unmap_success, pfn, flags); rc = 0; @@ -1382,7 +1382,12 @@ int memory_failure(unsigned long pfn, int flags) return 0; } - if (!PageTransTail(p) && !PageLRU(p)) + /* + * __munlock_pagevec may clear a writeback page's LRU flag without + * page_lock. We need wait writeback completion for this page or it + * may trigger vfs BUG while evict inode. + */ + if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p)) goto identify_page_state; /* diff --git a/mm/memory.c b/mm/memory.c index 2157bb28117a..d416e329442d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -150,7 +150,7 @@ static int __init init_zero_pfn(void) zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } -core_initcall(init_zero_pfn); +early_initcall(init_zero_pfn); #if defined(SPLIT_RSS_COUNTING) @@ -1013,6 +1013,17 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, return ret; } +/* Whether we should zap all COWed (private) pages too */ +static inline bool should_zap_cows(struct zap_details *details) +{ + /* By default, zap all pages */ + if (!details) + return true; + + /* Or, we zap COWed pages only if the caller wants to */ + return !details->check_mapping; +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1104,16 +1115,18 @@ again: continue; } - /* If details->check_mapping, we leave swap entries. */ - if (unlikely(details)) - continue; - - if (!non_swap_entry(entry)) + if (!non_swap_entry(entry)) { + /* Genuine swap entry, hence a private anon page */ + if (!should_zap_cows(details)) + continue; rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { + } else if (is_migration_entry(entry)) { struct page *page; page = migration_entry_to_page(entry); + if (details && details->check_mapping && + details->check_mapping != page_rmapping(page)) + continue; rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) @@ -1165,7 +1178,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ + } else if (details && details->single_page && + PageTransCompound(details->single_page) && + next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { + spinlock_t *ptl = pmd_lock(tlb->mm, pmd); + /* + * Take and drop THP pmd lock so that we cannot return + * prematurely, while zap_huge_pmd() has cleared *pmd, + * but not yet decremented compound_mapcount(). + */ + spin_unlock(ptl); } + /* * Here there can be other concurrent MADV_DONTNEED or * trans huge page faults running, and if the pmd is @@ -1804,11 +1828,11 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, pgprot_t prot) { - pte_t *pte; + pte_t *pte, *mapped_pte; spinlock_t *ptl; int err = 0; - pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + mapped_pte = pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; arch_enter_lazy_mmu_mode(); @@ -1822,7 +1846,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(mapped_pte, ptl); return err; } @@ -2770,6 +2794,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } /** + * unmap_mapping_page() - Unmap single page from processes. + * @page: The locked page to be unmapped. + * + * Unmap this page from any userspace process which still has it mmaped. + * Typically, for efficiency, the range of nearby pages has already been + * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once + * truncation or invalidation holds the lock on a page, it may find that + * the page has been remapped again: and then uses unmap_mapping_page() + * to unmap it finally. + */ +void unmap_mapping_page(struct page *page) +{ + struct address_space *mapping = page->mapping; + struct zap_details details = { }; + + VM_BUG_ON(!PageLocked(page)); + VM_BUG_ON(PageTail(page)); + + details.check_mapping = mapping; + details.first_index = page->index; + details.last_index = page->index + hpage_nr_pages(page) - 1; + details.single_page = page; + + i_mmap_lock_write(mapping); + if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + i_mmap_unlock_write(mapping); +} + +/** * unmap_mapping_pages() - Unmap pages from processes. * @mapping: The address space containing pages to be unmapped. * @start: Index of first page to be unmapped. @@ -3204,11 +3258,20 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) return ret; if (unlikely(PageHWPoison(vmf->page))) { - if (ret & VM_FAULT_LOCKED) - unlock_page(vmf->page); - put_page(vmf->page); + struct page *page = vmf->page; + vm_fault_t poisonret = VM_FAULT_HWPOISON; + if (ret & VM_FAULT_LOCKED) { + if (page_mapped(page)) + unmap_mapping_pages(page_mapping(page), + page->index, 1, false); + /* Retry if a clean page was removed from the cache. */ + if (invalidate_inode_page(page)) + poisonret = VM_FAULT_NOPAGE; + unlock_page(page); + } + put_page(page); vmf->page = NULL; - return VM_FAULT_HWPOISON; + return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) @@ -4222,9 +4285,9 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) } #endif /* __PAGETABLE_PMD_FOLDED */ -static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, - pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) +int follow_invalidate_pte(struct mm_struct *mm, unsigned long address, + struct mmu_notifier_range *range, pte_t **ptepp, + pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; @@ -4289,31 +4352,33 @@ out: return -EINVAL; } -static inline int follow_pte(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, spinlock_t **ptlp) -{ - int res; - - /* (void) is needed to make gcc happy */ - (void) __cond_lock(*ptlp, - !(res = __follow_pte_pmd(mm, address, NULL, - ptepp, NULL, ptlp))); - return res; -} - -int follow_pte_pmd(struct mm_struct *mm, unsigned long address, - struct mmu_notifier_range *range, - pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) +/** + * follow_pte - look up PTE at a user virtual address + * @mm: the mm_struct of the target address space + * @address: user virtual address + * @ptepp: location to store found PTE + * @ptlp: location to store the lock for the PTE + * + * On a successful return, the pointer to the PTE is stored in @ptepp; + * the corresponding lock is taken and its location is stored in @ptlp. + * The contents of the PTE are only stable until @ptlp is released; + * any further use, if any, must be protected against invalidation + * with MMU notifiers. + * + * Only IO mappings and raw PFN mappings are allowed. The mmap semaphore + * should be taken for read. + * + * KVM uses this function. While it is arguably less bad than ``follow_pfn``, + * it is not a good general-purpose API. + * + * Return: zero on success, -ve otherwise. + */ +int follow_pte(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, spinlock_t **ptlp) { - int res; - - /* (void) is needed to make gcc happy */ - (void) __cond_lock(*ptlp, - !(res = __follow_pte_pmd(mm, address, range, - ptepp, pmdpp, ptlp))); - return res; + return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp); } -EXPORT_SYMBOL(follow_pte_pmd); +EXPORT_SYMBOL_GPL(follow_pte); /** * follow_pfn - look up PFN at a user virtual address @@ -4323,6 +4388,9 @@ EXPORT_SYMBOL(follow_pte_pmd); * * Only IO mappings and raw PFN mappings are allowed. * + * This function does not allow the caller to read the permissions + * of the PTE. Do not use it. + * * Return: zero and the pfn at @pfn on success, -ve otherwise. */ int follow_pfn(struct vm_area_struct *vma, unsigned long address, @@ -4713,17 +4781,19 @@ long copy_huge_page_from_user(struct page *dst_page, void *page_kaddr; unsigned long i, rc = 0; unsigned long ret_val = pages_per_huge_page * PAGE_SIZE; + struct page *subpage = dst_page; - for (i = 0; i < pages_per_huge_page; i++) { + for (i = 0; i < pages_per_huge_page; + i++, subpage = mem_map_next(subpage, dst_page, i)) { if (allow_pagefault) - page_kaddr = kmap(dst_page + i); + page_kaddr = kmap(subpage); else - page_kaddr = kmap_atomic(dst_page + i); + page_kaddr = kmap_atomic(subpage); rc = copy_from_user(page_kaddr, (const void __user *)(src + i * PAGE_SIZE), PAGE_SIZE); if (allow_pagefault) - kunmap(dst_page + i); + kunmap(subpage); else kunmap_atomic(page_kaddr); @@ -4731,6 +4801,8 @@ long copy_huge_page_from_user(struct page *dst_page, if (rc) break; + flush_dcache_page(subpage); + cond_resched(); } return ret_val; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 308beca3ffeb..bcc2686bd0a1 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -775,8 +775,8 @@ static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn return movable_node_enabled ? movable_zone : kernel_zone; } -struct zone * zone_for_pfn_range(int online_type, int nid, unsigned start_pfn, - unsigned long nr_pages) +struct zone *zone_for_pfn_range(int online_type, int nid, + unsigned long start_pfn, unsigned long nr_pages) { if (online_type == MMOP_ONLINE_KERNEL) return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 787c5fc91b21..d79ab5116a7b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -496,7 +496,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, unsigned long flags = qp->flags; int ret; bool has_unmovable = false; - pte_t *pte; + pte_t *pte, *mapped_pte; spinlock_t *ptl; ptl = pmd_trans_huge_lock(pmd, vma); @@ -510,7 +510,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, if (pmd_trans_unstable(pmd)) return 0; - pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; @@ -542,7 +542,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, } else break; } - pte_unmap_unlock(pte - 1, ptl); + pte_unmap_unlock(mapped_pte, ptl); cond_resched(); if (has_unmovable) @@ -731,7 +731,6 @@ static int vma_replace_policy(struct vm_area_struct *vma, static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct mempolicy *new_pol) { - struct vm_area_struct *next; struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; @@ -747,8 +746,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, if (start > vma->vm_start) prev = vma; - for (; vma && vma->vm_start < end; prev = vma, vma = next) { - next = vma->vm_next; + for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) { vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); @@ -762,10 +760,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, new_pol, vma->vm_userfaultfd_ctx); if (prev) { vma = prev; - next = vma->vm_next; - if (mpol_equal(vma_policy(vma), new_pol)) - continue; - /* vma_merge() joined vma && vma->next, case 8 */ goto replace; } if (vma->vm_start != vmstart) { @@ -2143,8 +2137,9 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, * memory as well. */ if (!page && (gfp & __GFP_DIRECT_RECLAIM)) - page = __alloc_pages_node(hpage_node, - gfp | __GFP_NORETRY, order); + page = __alloc_pages_nodemask(gfp | __GFP_NORETRY, + order, hpage_node, + nmask); goto out; } @@ -2564,6 +2559,7 @@ alloc_new: mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; + atomic_set(&mpol_new->refcnt, 1); goto restart; } diff --git a/mm/migrate.c b/mm/migrate.c index c4c313e47f12..6948d6ec0fd0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -321,6 +321,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, goto out; page = migration_entry_to_page(entry); + page = compound_head(page); /* * Once page cache replacement of page migration started, page_count @@ -993,9 +994,12 @@ static int move_to_new_page(struct page *newpage, struct page *page, if (!PageMappingFlags(page)) page->mapping = NULL; - if (likely(!is_zone_device_page(newpage))) - flush_dcache_page(newpage); + if (likely(!is_zone_device_page(newpage))) { + int i, nr = compound_nr(newpage); + for (i = 0; i < nr; i++) + flush_dcache_page(newpage + i); + } } out: return rc; @@ -2771,6 +2775,13 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); entry = swp_entry_to_pte(swp_entry); + } else { + /* + * For now we only support migrating to un-addressable + * device memory. + */ + pr_warn_once("Unsupported ZONE_DEVICE page type.\n"); + goto abort; } } else { entry = mk_pte(page, vma->vm_page_prot); diff --git a/mm/mmap.c b/mm/mmap.c index ba78f1f1b1bd..88e686367776 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2077,14 +2077,6 @@ found_highest: } -#ifndef arch_get_mmap_end -#define arch_get_mmap_end(addr) (TASK_SIZE) -#endif - -#ifndef arch_get_mmap_base -#define arch_get_mmap_base(addr, base) (base) -#endif - /* Get an address range which is currently unmapped. * For shmat() with addr=0. * @@ -2515,7 +2507,7 @@ static int __init cmdline_parse_stack_guard_gap(char *p) if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; - return 0; + return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); diff --git a/mm/mmzone.c b/mm/mmzone.c index 4686fdc23bb9..f337831affc2 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -72,20 +72,6 @@ struct zoneref *__next_zones_zonelist(struct zoneref *z, return z; } -#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL -bool memmap_valid_within(unsigned long pfn, - struct page *page, struct zone *zone) -{ - if (page_to_pfn(page) != pfn) - return false; - - if (page_zone(page) != zone) - return false; - - return true; -} -#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */ - void lruvec_init(struct lruvec *lruvec) { enum lru_list lru; diff --git a/mm/mremap.c b/mm/mremap.c index 8005d0b2b843..8ce1b7632fbb 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -246,6 +246,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, struct mmu_notifier_range range; pmd_t *old_pmd, *new_pmd; + if (!len) + return 0; + old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d58c481b3df8..ee927ffeb718 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -63,6 +63,8 @@ int sysctl_oom_dump_tasks = 1; * and mark_oom_victim */ DEFINE_MUTEX(oom_lock); +/* Serializes oom_score_adj and oom_score_adj_min updates */ +DEFINE_MUTEX(oom_adj_mutex); static inline bool is_memcg_oom(struct oom_control *oc) { @@ -195,17 +197,17 @@ static bool is_dump_unreclaim_slabs(void) * predictable as possible. The goal is to return the highest value for the * task consuming the most memory to avoid subsequent oom failures. */ -unsigned long oom_badness(struct task_struct *p, unsigned long totalpages) +long oom_badness(struct task_struct *p, unsigned long totalpages) { long points; long adj; if (oom_unkillable_task(p)) - return 0; + return LONG_MIN; p = find_lock_task_mm(p); if (!p) - return 0; + return LONG_MIN; /* * Do not even consider tasks which are explicitly marked oom @@ -217,7 +219,7 @@ unsigned long oom_badness(struct task_struct *p, unsigned long totalpages) test_bit(MMF_OOM_SKIP, &p->mm->flags) || in_vfork(p)) { task_unlock(p); - return 0; + return LONG_MIN; } /* @@ -232,11 +234,7 @@ unsigned long oom_badness(struct task_struct *p, unsigned long totalpages) adj *= totalpages / 1000; points += adj; - /* - * Never return 0 for an eligible task regardless of the root bonus and - * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here). - */ - return points > 0 ? points : 1; + return points; } static const char * const oom_constraint_text[] = { @@ -309,7 +307,7 @@ static enum oom_constraint constrained_alloc(struct oom_control *oc) static int oom_evaluate_task(struct task_struct *task, void *arg) { struct oom_control *oc = arg; - unsigned long points; + long points; if (oom_unkillable_task(task)) goto next; @@ -335,12 +333,12 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) * killed first if it triggers an oom, then select it. */ if (oom_task_origin(task)) { - points = ULONG_MAX; + points = LONG_MAX; goto select; } points = oom_badness(task, oc->totalpages); - if (!points || points < oc->chosen_points) + if (points == LONG_MIN || points < oc->chosen_points) goto next; select: @@ -364,6 +362,8 @@ abort: */ static void select_bad_process(struct oom_control *oc) { + oc->chosen_points = LONG_MIN; + if (is_memcg_oom(oc)) mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); else { @@ -631,7 +631,7 @@ done: */ set_bit(MMF_OOM_SKIP, &mm->flags); - /* Drop a reference taken by wake_oom_reaper */ + /* Drop a reference taken by queue_oom_reaper */ put_task_struct(tsk); } @@ -641,12 +641,12 @@ static int oom_reaper(void *unused) struct task_struct *tsk = NULL; wait_event_freezable(oom_reaper_wait, oom_reaper_list != NULL); - spin_lock(&oom_reaper_lock); + spin_lock_irq(&oom_reaper_lock); if (oom_reaper_list != NULL) { tsk = oom_reaper_list; oom_reaper_list = tsk->oom_reaper_list; } - spin_unlock(&oom_reaper_lock); + spin_unlock_irq(&oom_reaper_lock); if (tsk) oom_reap_task(tsk); @@ -655,22 +655,48 @@ static int oom_reaper(void *unused) return 0; } -static void wake_oom_reaper(struct task_struct *tsk) +static void wake_oom_reaper(struct timer_list *timer) { - /* mm is already queued? */ - if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) - return; + struct task_struct *tsk = container_of(timer, struct task_struct, + oom_reaper_timer); + struct mm_struct *mm = tsk->signal->oom_mm; + unsigned long flags; - get_task_struct(tsk); + /* The victim managed to terminate on its own - see exit_mmap */ + if (test_bit(MMF_OOM_SKIP, &mm->flags)) { + put_task_struct(tsk); + return; + } - spin_lock(&oom_reaper_lock); + spin_lock_irqsave(&oom_reaper_lock, flags); tsk->oom_reaper_list = oom_reaper_list; oom_reaper_list = tsk; - spin_unlock(&oom_reaper_lock); + spin_unlock_irqrestore(&oom_reaper_lock, flags); trace_wake_reaper(tsk->pid); wake_up(&oom_reaper_wait); } +/* + * Give the OOM victim time to exit naturally before invoking the oom_reaping. + * The timers timeout is arbitrary... the longer it is, the longer the worst + * case scenario for the OOM can take. If it is too small, the oom_reaper can + * get in the way and release resources needed by the process exit path. + * e.g. The futex robust list can sit in Anon|Private memory that gets reaped + * before the exit path is able to wake the futex waiters. + */ +#define OOM_REAPER_DELAY (2*HZ) +static void queue_oom_reaper(struct task_struct *tsk) +{ + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) + return; + + get_task_struct(tsk); + timer_setup(&tsk->oom_reaper_timer, wake_oom_reaper, 0); + tsk->oom_reaper_timer.expires = jiffies + OOM_REAPER_DELAY; + add_timer(&tsk->oom_reaper_timer); +} + static int __init oom_init(void) { oom_reaper_th = kthread_run(oom_reaper, NULL, "oom_reaper"); @@ -678,7 +704,7 @@ static int __init oom_init(void) } subsys_initcall(oom_init) #else -static inline void wake_oom_reaper(struct task_struct *tsk) +static inline void queue_oom_reaper(struct task_struct *tsk) { } #endif /* CONFIG_MMU */ @@ -927,7 +953,7 @@ static void __oom_kill_process(struct task_struct *victim, const char *message) rcu_read_unlock(); if (can_oom_reap) - wake_oom_reaper(victim); + queue_oom_reaper(victim); mmdrop(mm); put_task_struct(victim); @@ -963,7 +989,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) task_lock(victim); if (task_will_free_mem(victim)) { mark_oom_victim(victim); - wake_oom_reaper(victim); + queue_oom_reaper(victim); task_unlock(victim); put_task_struct(victim); return; @@ -1061,7 +1087,7 @@ bool out_of_memory(struct oom_control *oc) */ if (task_will_free_mem(current)) { mark_oom_victim(current); - wake_oom_reaper(current); + queue_oom_reaper(current); return true; } @@ -1114,25 +1140,22 @@ bool out_of_memory(struct oom_control *oc) } /* - * The pagefault handler calls here because it is out of memory, so kill a - * memory-hogging task. If oom_lock is held by somebody else, a parallel oom - * killing is already in progress so do nothing. + * The pagefault handler calls here because some allocation has failed. We have + * to take care of the memcg OOM here because this is the only safe context without + * any locks held but let the oom killer triggered from the allocation context care + * about the global OOM. */ void pagefault_out_of_memory(void) { - struct oom_control oc = { - .zonelist = NULL, - .nodemask = NULL, - .memcg = NULL, - .gfp_mask = 0, - .order = 0, - }; + static DEFINE_RATELIMIT_STATE(pfoom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); if (mem_cgroup_oom_synchronize(true)) return; - if (!mutex_trylock(&oom_lock)) + if (fatal_signal_pending(current)) return; - out_of_memory(&oc); - mutex_unlock(&oom_lock); + + if (__ratelimit(&pfoom_rs)) + pr_warn("Huh VM_FAULT_OOM leaked out to the #PF handler. Retrying PF\n"); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 373ca5780758..f08ce248af2a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -68,6 +68,7 @@ #include <linux/lockdep.h> #include <linux/nmi.h> #include <linux/psi.h> +#include <linux/khugepaged.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -905,7 +906,7 @@ static inline void __free_one_page(struct page *page, unsigned int max_order; struct capture_control *capc = task_capc(zone); - max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1); + max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order); VM_BUG_ON(!zone_is_initialized(zone)); VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); @@ -918,7 +919,7 @@ static inline void __free_one_page(struct page *page, VM_BUG_ON_PAGE(bad_range(zone, page), page); continue_merging: - while (order < max_order - 1) { + while (order < max_order) { if (compaction_capture(capc, page, order, migratetype)) { __mod_zone_freepage_state(zone, -(1 << order), migratetype); @@ -944,7 +945,7 @@ continue_merging: pfn = combined_pfn; order++; } - if (max_order < MAX_ORDER) { + if (order < MAX_ORDER - 1) { /* If we are here, it means order is >= pageblock_order. * We want to prevent merge between freepages on isolate * pageblock and normal pageblock. Without this, pageblock @@ -965,7 +966,7 @@ continue_merging: is_migrate_isolate(buddy_mt))) goto done_merging; } - max_order++; + max_order = order + 1; goto continue_merging; } @@ -2345,12 +2346,12 @@ static bool can_steal_fallback(unsigned int order, int start_mt) return false; } -static inline void boost_watermark(struct zone *zone) +static inline bool boost_watermark(struct zone *zone) { unsigned long max_boost; if (!watermark_boost_factor) - return; + return false; /* * Don't bother in zones that are unlikely to produce results. * On small machines, including kdump capture kernels running @@ -2358,7 +2359,7 @@ static inline void boost_watermark(struct zone *zone) * memory situation immediately. */ if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) - return; + return false; max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); @@ -2372,12 +2373,14 @@ static inline void boost_watermark(struct zone *zone) * boosted watermark resulting in a hang. */ if (!max_boost) - return; + return false; max_boost = max(pageblock_nr_pages, max_boost); zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages, max_boost); + + return true; } /* @@ -2416,8 +2419,7 @@ static void steal_suitable_fallback(struct zone *zone, struct page *page, * likelihood of future fallbacks. Wake kswapd now as the node * may be balanced overall and kswapd will not wake naturally. */ - boost_watermark(zone); - if (alloc_flags & ALLOC_KSWAPD) + if (boost_watermark(zone) && (alloc_flags & ALLOC_KSWAPD)) set_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); /* We are not allowed to try stealing from the whole block */ @@ -3129,7 +3131,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); - split_page_owner(page, order); + split_page_owner(page, 1 << order); } EXPORT_SYMBOL_GPL(split_page); @@ -3384,7 +3386,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } @@ -3483,7 +3485,8 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark, } static inline bool zone_watermark_fast(struct zone *z, unsigned int order, - unsigned long mark, int classzone_idx, unsigned int alloc_flags) + unsigned long mark, int classzone_idx, + unsigned int alloc_flags, gfp_t gfp_mask) { long free_pages = zone_page_state(z, NR_FREE_PAGES); long cma_pages = 0; @@ -3504,8 +3507,23 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order, if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx]) return true; - return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, - free_pages); + if (__zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags, + free_pages)) + return true; + /* + * Ignore watermark boosting for GFP_ATOMIC order-0 allocations + * when checking the min watermark. The min watermark is the + * point where boosting is ignored so that kswapd is woken up + * when below the low watermark. + */ + if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost + && ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) { + mark = z->_watermark[WMARK_MIN]; + return __zone_watermark_ok(z, order, mark, classzone_idx, + alloc_flags, free_pages); + } + + return false; } bool zone_watermark_ok_safe(struct zone *z, unsigned int order, @@ -3646,7 +3664,8 @@ retry: mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK); if (!zone_watermark_fast(zone, order, mark, - ac_classzone_idx(ac), alloc_flags)) { + ac_classzone_idx(ac), alloc_flags, + gfp_mask)) { int ret; #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -3748,7 +3767,9 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) va_list args; static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); - if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) + if ((gfp_mask & __GFP_NOWARN) || + !__ratelimit(&nopage_rs) || + ((gfp_mask & __GFP_DMA) && !has_managed_dma())) return; va_start(args, fmt); @@ -4909,6 +4930,11 @@ refill: if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) goto refill; + if (unlikely(nc->pfmemalloc)) { + free_the_page(page, compound_order(page)); + goto refill; + } + #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) /* if size can vary use size else just use PAGE_SIZE */ size = nc->size; @@ -5455,7 +5481,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) do { zone_type--; zone = pgdat->node_zones + zone_type; - if (managed_zone(zone)) { + if (populated_zone(zone)) { zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } @@ -7300,10 +7326,17 @@ restart: out2: /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ - for (nid = 0; nid < MAX_NUMNODES; nid++) + for (nid = 0; nid < MAX_NUMNODES; nid++) { + unsigned long start_pfn, end_pfn; + zone_movable_pfn[nid] = roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + if (zone_movable_pfn[nid] >= end_pfn) + zone_movable_pfn[nid] = 0; + } + out: /* restore the node_state */ node_states[N_MEMORY] = saved_node_state; @@ -7555,7 +7588,7 @@ void __init mem_init_print_info(const char *str) */ #define adj_init_size(start, end, size, pos, adj) \ do { \ - if (start <= pos && pos < end && size > adj) \ + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ size -= adj; \ } while (0) @@ -7870,6 +7903,8 @@ int __meminit init_per_zone_wmark_min(void) setup_min_slab_ratio(); #endif + khugepaged_min_free_kbytes_update(); + return 0; } postcore_initcall(init_per_zone_wmark_min) @@ -8668,3 +8703,18 @@ bool set_hwpoison_free_buddy_page(struct page *page) return hwpoisoned; } #endif + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void) +{ + struct pglist_data *pgdat; + + for_each_online_pgdat(pgdat) { + struct zone *zone = &pgdat->node_zones[ZONE_DMA]; + + if (managed_zone(zone)) + return true; + } + return false; +} +#endif /* CONFIG_ZONE_DMA */ diff --git a/mm/page_io.c b/mm/page_io.c index 60a66a58b9bf..f0e3f2be7b44 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -69,54 +69,6 @@ void end_swap_bio_write(struct bio *bio) bio_put(bio); } -static void swap_slot_free_notify(struct page *page) -{ - struct swap_info_struct *sis; - struct gendisk *disk; - swp_entry_t entry; - - /* - * There is no guarantee that the page is in swap cache - the software - * suspend code (at least) uses end_swap_bio_read() against a non- - * swapcache page. So we must check PG_swapcache before proceeding with - * this optimization. - */ - if (unlikely(!PageSwapCache(page))) - return; - - sis = page_swap_info(page); - if (!(sis->flags & SWP_BLKDEV)) - return; - - /* - * The swap subsystem performs lazy swap slot freeing, - * expecting that the page will be swapped out again. - * So we can avoid an unnecessary write if the page - * isn't redirtied. - * This is good for real swap storage because we can - * reduce unnecessary I/O and enhance wear-leveling - * if an SSD is used as the as swap device. - * But if in-memory swap device (eg zram) is used, - * this causes a duplicated copy between uncompressed - * data in VM-owned memory and compressed data in - * zram-owned memory. So let's free zram-owned memory - * and make the VM-owned decompressed page *dirty*, - * so the page should be swapped out somewhere again if - * we again wish to reclaim it. - */ - disk = sis->bdev->bd_disk; - entry.val = page_private(page); - if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) { - unsigned long offset; - - offset = swp_offset(entry); - - SetPageDirty(page); - disk->fops->swap_slot_free_notify(sis->bdev, - offset); - } -} - static void end_swap_bio_read(struct bio *bio) { struct page *page = bio_first_page_all(bio); @@ -132,7 +84,6 @@ static void end_swap_bio_read(struct bio *bio) } SetPageUptodate(page); - swap_slot_free_notify(page); out: unlock_page(page); WRITE_ONCE(bio->bi_private, NULL); @@ -260,11 +211,6 @@ out: return ret; } -static sector_t swap_page_sector(struct page *page) -{ - return (sector_t)__page_file_index(page) << (PAGE_SHIFT - 9); -} - static inline void count_swpout_vm_event(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -376,11 +322,6 @@ int swap_readpage(struct page *page, bool synchronous) ret = bdev_read_page(sis->bdev, swap_page_sector(page), page); if (!ret) { - if (trylock_page(page)) { - swap_slot_free_notify(page); - unlock_page(page); - } - count_vm_event(PSWPIN); return 0; } diff --git a/mm/page_owner.c b/mm/page_owner.c index 18ecde9f45b2..83d08943bcde 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -204,7 +204,7 @@ void __set_page_owner_migrate_reason(struct page *page, int reason) page_owner->last_migrate_reason = reason; } -void __split_page_owner(struct page *page, unsigned int order) +void __split_page_owner(struct page *page, unsigned int nr) { int i; struct page_ext *page_ext = lookup_page_ext(page); @@ -213,7 +213,7 @@ void __split_page_owner(struct page *page, unsigned int order) if (unlikely(!page_ext)) return; - for (i = 0; i < (1 << order); i++) { + for (i = 0; i < nr; i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; page_ext = page_ext_next(page_ext); diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index eff4b4520c8d..029f5598251c 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -111,6 +111,13 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) return pfn_in_hpage(pvmw->page, pfn); } +static void step_forward(struct page_vma_mapped_walk *pvmw, unsigned long size) +{ + pvmw->address = (pvmw->address + size) & ~(size - 1); + if (!pvmw->address) + pvmw->address = ULONG_MAX; +} + /** * page_vma_mapped_walk - check if @pvmw->page is mapped in @pvmw->vma at * @pvmw->address @@ -139,6 +146,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) { struct mm_struct *mm = pvmw->vma->vm_mm; struct page *page = pvmw->page; + unsigned long end; pgd_t *pgd; p4d_t *p4d; pud_t *pud; @@ -148,10 +156,11 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) if (pvmw->pmd && !pvmw->pte) return not_found(pvmw); - if (pvmw->pte) - goto next_pte; + if (unlikely(PageHuge(page))) { + /* The only possible mapping was handled on last iteration */ + if (pvmw->pte) + return not_found(pvmw); - if (unlikely(PageHuge(pvmw->page))) { /* when pud is not present, pte will be NULL */ pvmw->pte = huge_pte_offset(mm, pvmw->address, page_size(page)); if (!pvmw->pte) @@ -163,78 +172,108 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); return true; } -restart: - pgd = pgd_offset(mm, pvmw->address); - if (!pgd_present(*pgd)) - return false; - p4d = p4d_offset(pgd, pvmw->address); - if (!p4d_present(*p4d)) - return false; - pud = pud_offset(p4d, pvmw->address); - if (!pud_present(*pud)) - return false; - pvmw->pmd = pmd_offset(pud, pvmw->address); + /* - * Make sure the pmd value isn't cached in a register by the - * compiler and used as a stale value after we've observed a - * subsequent update. + * Seek to next pte only makes sense for THP. + * But more important than that optimization, is to filter out + * any PageKsm page: whose page->index misleads vma_address() + * and vma_address_end() to disaster. */ - pmde = READ_ONCE(*pvmw->pmd); - if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { - pvmw->ptl = pmd_lock(mm, pvmw->pmd); - if (likely(pmd_trans_huge(*pvmw->pmd))) { - if (pvmw->flags & PVMW_MIGRATION) - return not_found(pvmw); - if (pmd_page(*pvmw->pmd) != page) - return not_found(pvmw); - return true; - } else if (!pmd_present(*pvmw->pmd)) { - if (thp_migration_supported()) { - if (!(pvmw->flags & PVMW_MIGRATION)) + end = PageTransCompound(page) ? + vma_address_end(page, pvmw->vma) : + pvmw->address + PAGE_SIZE; + if (pvmw->pte) + goto next_pte; +restart: + do { + pgd = pgd_offset(mm, pvmw->address); + if (!pgd_present(*pgd)) { + step_forward(pvmw, PGDIR_SIZE); + continue; + } + p4d = p4d_offset(pgd, pvmw->address); + if (!p4d_present(*p4d)) { + step_forward(pvmw, P4D_SIZE); + continue; + } + pud = pud_offset(p4d, pvmw->address); + if (!pud_present(*pud)) { + step_forward(pvmw, PUD_SIZE); + continue; + } + + pvmw->pmd = pmd_offset(pud, pvmw->address); + /* + * Make sure the pmd value isn't cached in a register by the + * compiler and used as a stale value after we've observed a + * subsequent update. + */ + pmde = READ_ONCE(*pvmw->pmd); + + if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) { + pvmw->ptl = pmd_lock(mm, pvmw->pmd); + pmde = *pvmw->pmd; + if (likely(pmd_trans_huge(pmde))) { + if (pvmw->flags & PVMW_MIGRATION) return not_found(pvmw); - if (is_migration_entry(pmd_to_swp_entry(*pvmw->pmd))) { - swp_entry_t entry = pmd_to_swp_entry(*pvmw->pmd); + if (pmd_page(pmde) != page) + return not_found(pvmw); + return true; + } + if (!pmd_present(pmde)) { + swp_entry_t entry; - if (migration_entry_to_page(entry) != page) - return not_found(pvmw); - return true; - } + if (!thp_migration_supported() || + !(pvmw->flags & PVMW_MIGRATION)) + return not_found(pvmw); + entry = pmd_to_swp_entry(pmde); + if (!is_migration_entry(entry) || + migration_entry_to_page(entry) != page) + return not_found(pvmw); + return true; } - return not_found(pvmw); - } else { /* THP pmd was split under us: handle on pte level */ spin_unlock(pvmw->ptl); pvmw->ptl = NULL; + } else if (!pmd_present(pmde)) { + /* + * If PVMW_SYNC, take and drop THP pmd lock so that we + * cannot return prematurely, while zap_huge_pmd() has + * cleared *pmd but not decremented compound_mapcount(). + */ + if ((pvmw->flags & PVMW_SYNC) && + PageTransCompound(page)) { + spinlock_t *ptl = pmd_lock(mm, pvmw->pmd); + + spin_unlock(ptl); + } + step_forward(pvmw, PMD_SIZE); + continue; } - } else if (!pmd_present(pmde)) { - return false; - } - if (!map_pte(pvmw)) - goto next_pte; - while (1) { + if (!map_pte(pvmw)) + goto next_pte; +this_pte: if (check_pte(pvmw)) return true; next_pte: - /* Seek to next pte only makes sense for THP */ - if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page)) - return not_found(pvmw); do { pvmw->address += PAGE_SIZE; - if (pvmw->address >= pvmw->vma->vm_end || - pvmw->address >= - __vma_address(pvmw->page, pvmw->vma) + - hpage_nr_pages(pvmw->page) * PAGE_SIZE) + if (pvmw->address >= end) return not_found(pvmw); /* Did we cross page table boundary? */ - if (pvmw->address % PMD_SIZE == 0) { - pte_unmap(pvmw->pte); + if ((pvmw->address & (PMD_SIZE - PAGE_SIZE)) == 0) { if (pvmw->ptl) { spin_unlock(pvmw->ptl); pvmw->ptl = NULL; } + pte_unmap(pvmw->pte); + pvmw->pte = NULL; goto restart; - } else { - pvmw->pte++; + } + pvmw->pte++; + if ((pvmw->flags & PVMW_SYNC) && !pvmw->ptl) { + pvmw->ptl = pte_lockptr(mm, pvmw->pmd); + spin_lock(pvmw->ptl); } } while (pte_none(*pvmw->pte)); @@ -242,7 +281,10 @@ next_pte: pvmw->ptl = pte_lockptr(mm, pvmw->pmd); spin_lock(pvmw->ptl); } - } + goto this_pte; + } while (pvmw->address < end); + + return false; } /** @@ -261,14 +303,10 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma) .vma = vma, .flags = PVMW_SYNC, }; - unsigned long start, end; - - start = __vma_address(page, vma); - end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1); - if (unlikely(end < vma->vm_start || start >= vma->vm_end)) + pvmw.address = vma_address(page, vma); + if (pvmw.address == -EFAULT) return 0; - pvmw.address = max(start, vma->vm_start); if (!page_vma_mapped_walk(&pvmw)) return 0; page_vma_mapped_walk_done(&pvmw); diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 532c29276fce..49e8a4fbc205 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -126,8 +126,8 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address, { pmd_t pmd; VM_BUG_ON(address & ~HPAGE_PMD_MASK); - VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && - !pmd_devmap(*pmdp)) || !pmd_present(*pmdp)); + VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) && + !pmd_devmap(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; diff --git a/mm/rmap.c b/mm/rmap.c index 0c7b2a9400d4..6d80e92688fe 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -687,7 +687,6 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) { - unsigned long address; if (PageAnon(page)) { struct anon_vma *page__anon_vma = page_anon_vma(page); /* @@ -697,15 +696,13 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping) { - if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) - return -EFAULT; - } else + } else if (!vma->vm_file) { return -EFAULT; - address = __vma_address(page, vma); - if (unlikely(address < vma->vm_start || address >= vma->vm_end)) + } else if (vma->vm_file->f_mapping != compound_head(page)->mapping) { return -EFAULT; - return address; + } + + return vma_address(page, vma); } pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) @@ -899,7 +896,7 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma, vma->vm_mm, address, - min(vma->vm_end, address + page_size(page))); + vma_address_end(page, vma)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { @@ -1353,6 +1350,15 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)arg; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + if (flags & TTU_SYNC) + pvmw.flags = PVMW_SYNC; + /* munlock has nothing to gain from examining un-locked vmas */ if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED)) return true; @@ -1374,9 +1380,10 @@ 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. */ + range.end = PageKsm(page) ? + address + PAGE_SIZE : vma_address_end(page, vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, vma->vm_mm, - address, - min(vma->vm_end, address + page_size(page))); + address, range.end); if (PageHuge(page)) { /* * If sharing is possible, start and end will be adjusted @@ -1595,7 +1602,30 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* MADV_FREE page check */ if (!PageSwapBacked(page)) { - if (!PageDirty(page)) { + int ref_count, map_count; + + /* + * Synchronize with gup_pte_range(): + * - clear PTE; barrier; read refcount + * - inc refcount; barrier; read PTE + */ + smp_mb(); + + ref_count = page_ref_count(page); + map_count = page_mapcount(page); + + /* + * Order reads for page refcount and dirty flag + * (see comments in __remove_mapping()). + */ + smp_rmb(); + + /* + * The only page refs must be one from isolation + * plus the rmap(s) (dropped by discard:). + */ + if (ref_count == 1 + map_count && + !PageDirty(page)) { /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); @@ -1690,9 +1720,9 @@ static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) return is_vma_temporary_stack(vma); } -static int page_mapcount_is_zero(struct page *page) +static int page_not_mapped(struct page *page) { - return !total_mapcount(page); + return !page_mapped(page); } /** @@ -1710,7 +1740,7 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, - .done = page_mapcount_is_zero, + .done = page_not_mapped, .anon_lock = page_lock_anon_vma_read, }; @@ -1731,14 +1761,15 @@ bool try_to_unmap(struct page *page, enum ttu_flags flags) else rmap_walk(page, &rwc); - return !page_mapcount(page) ? true : false; + /* + * When racing against e.g. zap_pte_range() on another cpu, + * in between its ptep_get_and_clear_full() and page_remove_rmap(), + * try_to_unmap() may return false when it is about to become true, + * if page table locking is skipped: use TTU_SYNC to wait for that. + */ + return !page_mapcount(page); } -static int page_not_mapped(struct page *page) -{ - return !page_mapped(page); -}; - /** * try_to_munlock - try to munlock a page * @page: the page to be munlocked @@ -1833,6 +1864,7 @@ static void rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc, struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) @@ -1887,6 +1919,7 @@ static void rmap_walk_file(struct page *page, struct rmap_walk_control *rwc, pgoff_start, pgoff_end) { unsigned long address = vma_address(page, vma); + VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) diff --git a/mm/shmem.c b/mm/shmem.c index 98802ca76a5c..aae2f408f905 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -466,7 +466,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shmem_inode_info *info; struct page *page; unsigned long batch = sc ? sc->nr_to_scan : 128; - int removed = 0, split = 0; + int split = 0; if (list_empty(&sbinfo->shrinklist)) return SHRINK_STOP; @@ -481,7 +481,6 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, /* inode is about to be evicted */ if (!inode) { list_del_init(&info->shrinklist); - removed++; goto next; } @@ -489,12 +488,12 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { list_move(&info->shrinklist, &to_remove); - removed++; goto next; } list_move(&info->shrinklist, &list); next: + sbinfo->shrinklist_len--; if (!--batch) break; } @@ -514,7 +513,7 @@ next: inode = &info->vfs_inode; if (nr_to_split && split >= nr_to_split) - goto leave; + goto move_back; page = find_get_page(inode->i_mapping, (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); @@ -528,38 +527,44 @@ next: } /* - * Leave the inode on the list if we failed to lock - * the page at this time. + * Move the inode on the list back to shrinklist if we failed + * to lock the page at this time. * * Waiting for the lock may lead to deadlock in the * reclaim path. */ if (!trylock_page(page)) { put_page(page); - goto leave; + goto move_back; } ret = split_huge_page(page); unlock_page(page); put_page(page); - /* If split failed leave the inode on the list */ + /* If split failed move the inode on the list back to shrinklist */ if (ret) - goto leave; + goto move_back; split++; drop: list_del_init(&info->shrinklist); - removed++; -leave: + goto put; +move_back: + /* + * Make sure the inode is either on the global list or deleted + * from any local list before iput() since it could be deleted + * in another thread once we put the inode (then the local list + * is corrupted). + */ + spin_lock(&sbinfo->shrinklist_lock); + list_move(&info->shrinklist, &sbinfo->shrinklist); + sbinfo->shrinklist_len++; + spin_unlock(&sbinfo->shrinklist_lock); +put: iput(inode); } - spin_lock(&sbinfo->shrinklist_lock); - list_splice_tail(&list, &sbinfo->shrinklist); - sbinfo->shrinklist_len -= removed; - spin_unlock(&sbinfo->shrinklist_lock); - return split; } @@ -2208,25 +2213,11 @@ out_nomem: static int shmem_mmap(struct file *file, struct vm_area_struct *vma) { struct shmem_inode_info *info = SHMEM_I(file_inode(file)); + int ret; - if (info->seals & F_SEAL_FUTURE_WRITE) { - /* - * New PROT_WRITE and MAP_SHARED mmaps are not allowed when - * "future write" seal active. - */ - if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE)) - return -EPERM; - - /* - * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as - * MAP_SHARED and read-only, take care to not allow mprotect to - * revert protections on such mappings. Do this only for shared - * mappings. For private mappings, don't need to mask - * VM_MAYWRITE as we still want them to be COW-writable. - */ - if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); - } + ret = seal_check_future_write(info->seals, vma); + if (ret) + return ret; file_accessed(file); vma->vm_ops = &shmem_vm_ops; @@ -2327,8 +2318,18 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, pgoff_t offset, max_off; ret = -ENOMEM; - if (!shmem_inode_acct_block(inode, 1)) + if (!shmem_inode_acct_block(inode, 1)) { + /* + * We may have got a page, returned -ENOENT triggering a retry, + * and now we find ourselves with -ENOMEM. Release the page, to + * avoid a BUG_ON in our caller. + */ + if (unlikely(*pagep)) { + put_page(*pagep); + *pagep = NULL; + } goto out; + } if (!*pagep) { page = shmem_alloc_page(gfp, info, pgoff); diff --git a/mm/slab.h b/mm/slab.h index b2b01694dc43..61feda3d7e00 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -211,7 +211,7 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size, #define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE | SLAB_RECLAIM_ACCOUNT | \ SLAB_TEMPORARY | SLAB_ACCOUNT) #else -#define SLAB_CACHE_FLAGS (0) +#define SLAB_CACHE_FLAGS (SLAB_NOLEAKTRACE) #endif /* Common flags available with current configuration */ diff --git a/mm/slab_common.c b/mm/slab_common.c index e36dd36c7076..8f128245b300 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -85,8 +85,7 @@ EXPORT_SYMBOL(kmem_cache_size); #ifdef CONFIG_DEBUG_VM static int kmem_cache_sanity_check(const char *name, unsigned int size) { - if (!name || in_interrupt() || size < sizeof(void *) || - size > KMALLOC_MAX_SIZE) { + if (!name || in_interrupt() || size > KMALLOC_MAX_SIZE) { pr_err("kmem_cache_create(%s) integrity check failed\n", name); return -EINVAL; } @@ -326,14 +325,6 @@ int slab_unmergeable(struct kmem_cache *s) if (s->refcount < 0) return 1; -#ifdef CONFIG_MEMCG_KMEM - /* - * Skip the dying kmem_cache. - */ - if (s->memcg_params.dying) - return 1; -#endif - return 0; } @@ -974,6 +965,16 @@ void kmem_cache_destroy(struct kmem_cache *s) get_online_mems(); mutex_lock(&slab_mutex); + + /* + * Another thread referenced it again + */ + if (READ_ONCE(s->refcount)) { + spin_lock_irq(&memcg_kmem_wq_lock); + s->memcg_params.dying = false; + spin_unlock_irq(&memcg_kmem_wq_lock); + goto out_unlock; + } #endif err = shutdown_memcg_caches(s); diff --git a/mm/slub.c b/mm/slub.c index d69934eac9e9..63fe43c8d332 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -15,6 +15,7 @@ #include <linux/module.h> #include <linux/bit_spinlock.h> #include <linux/interrupt.h> +#include <linux/swab.h> #include <linux/bitops.h> #include <linux/slab.h> #include "slab.h" @@ -688,15 +689,15 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) p, p - addr, get_freepointer(s, p)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, + print_section(KERN_ERR, "Redzone ", p - s->red_left_pad, s->red_left_pad); else if (p > addr + 16) print_section(KERN_ERR, "Bytes b4 ", p - 16, 16); - print_section(KERN_ERR, "Object ", p, + print_section(KERN_ERR, "Object ", p, min_t(unsigned int, s->object_size, PAGE_SIZE)); if (s->flags & SLAB_RED_ZONE) - print_section(KERN_ERR, "Redzone ", p + s->object_size, + print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); off = get_info_end(s); @@ -708,7 +709,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) if (off != size_from_object(s)) /* Beginning of the filler is the free pointer */ - print_section(KERN_ERR, "Padding ", p + off, + print_section(KERN_ERR, "Padding ", p + off, size_from_object(s) - off); dump_stack(); @@ -882,11 +883,11 @@ static int check_object(struct kmem_cache *s, struct page *page, u8 *endobject = object + s->object_size; if (s->flags & SLAB_RED_ZONE) { - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Left Redzone", object - s->red_left_pad, val, s->red_left_pad)) return 0; - if (!check_bytes_and_report(s, page, object, "Redzone", + if (!check_bytes_and_report(s, page, object, "Right Redzone", endobject, val, s->inuse - s->object_size)) return 0; } else { @@ -901,7 +902,7 @@ static int check_object(struct kmem_cache *s, struct page *page, if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && (!check_bytes_and_report(s, page, p, "Poison", p, POISON_FREE, s->object_size - 1) || - !check_bytes_and_report(s, page, p, "Poison", + !check_bytes_and_report(s, page, p, "End Poison", p + s->object_size - 1, POISON_END, 1))) return 0; /* @@ -1454,7 +1455,8 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s, void *x) } static inline bool slab_free_freelist_hook(struct kmem_cache *s, - void **head, void **tail) + void **head, void **tail, + int *cnt) { void *object; @@ -1489,6 +1491,12 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, *head = object; if (!*tail) *tail = object; + } else { + /* + * Adjust the reconstructed freelist depth + * accordingly if object's reuse is delayed. + */ + --(*cnt); } } while (object != old_tail); @@ -2763,7 +2771,7 @@ redo: object = c->freelist; page = c->page; - if (unlikely(!object || !node_match(page, node))) { + if (unlikely(!object || !page || !node_match(page, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); stat(s, ALLOC_SLOWPATH); } else { @@ -3048,7 +3056,7 @@ static __always_inline void slab_free(struct kmem_cache *s, struct page *page, * With KASAN enabled slab_free_freelist_hook modifies the freelist * to remove objects, whose reuse must be delayed. */ - if (slab_free_freelist_hook(s, &head, &tail)) + if (slab_free_freelist_hook(s, &head, &tail, &cnt)) do_slab_free(s, page, head, tail, cnt, addr); } @@ -3586,15 +3594,17 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) */ s->inuse = size; - if (((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || - s->ctor)) { + if ((flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) || + ((flags & SLAB_RED_ZONE) && s->object_size < sizeof(void *)) || + s->ctor) { /* * Relocate free pointer after the object if it is not * permitted to overwrite the first word of the object on * kmem_cache_free. * * This is the case if we do RCU, have a constructor or - * destructor or are poisoning the objects. + * destructor, are poisoning the objects, or are + * redzoning an object smaller than sizeof(void *). * * The assumption that s->offset >= s->inuse means free * pointer is outside of the object is used in the @@ -3724,8 +3734,8 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) if (alloc_kmem_cache_cpus(s)) return 0; - free_kmem_cache_nodes(s); error: + __kmem_cache_release(s); return -EINVAL; } @@ -5819,10 +5829,8 @@ static int sysfs_slab_add(struct kmem_cache *s) s->kobj.kset = kset; err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name); - if (err) { - kobject_put(&s->kobj); + if (err) goto out; - } err = sysfs_create_group(&s->kobj, &slab_attr_group); if (err) diff --git a/mm/sparse.c b/mm/sparse.c index 78bbecd904c3..191e29cca3fb 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -551,6 +551,7 @@ static void __init sparse_init_nid(int nid, unsigned long pnum_begin, pr_err("%s: node[%d] memory map backing failed. Some memory will not be available.", __func__, nid); pnum_begin = pnum; + sparse_buffer_fini(); goto failed; } check_usemap_section_nr(nid, usage); diff --git a/mm/swapfile.c b/mm/swapfile.c index cf62bdb7b304..f6964212c6c8 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -221,6 +221,19 @@ offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) BUG(); } +sector_t swap_page_sector(struct page *page) +{ + struct swap_info_struct *sis = page_swap_info(page); + struct swap_extent *se; + sector_t sector; + pgoff_t offset; + + offset = __page_file_index(page); + se = offset_to_swap_extent(sis, offset); + sector = se->start_block + (offset - se->start_page); + return sector << (PAGE_SHIFT - 9); +} + /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. @@ -2824,6 +2837,7 @@ late_initcall(max_swapfiles_check); static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; + struct swap_info_struct *defer = NULL; unsigned int type; int i; @@ -2852,7 +2866,7 @@ static struct swap_info_struct *alloc_swap_info(void) smp_wmb(); WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); } else { - kvfree(p); + defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() @@ -2865,6 +2879,7 @@ static struct swap_info_struct *alloc_swap_info(void) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); + kvfree(defer); spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); @@ -3284,7 +3299,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; - goto bad_swap_unlock_inode; + goto free_swap_address_space; } mutex_lock(&swapon_mutex); @@ -3309,6 +3324,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = 0; goto out; +free_swap_address_space: + exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: diff --git a/mm/truncate.c b/mm/truncate.c index dd9ebc1da356..4d5add7d8ab6 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -173,13 +173,10 @@ void do_invalidatepage(struct page *page, unsigned int offset, * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ -static void -truncate_cleanup_page(struct address_space *mapping, struct page *page) +static void truncate_cleanup_page(struct page *page) { - if (page_mapped(page)) { - pgoff_t nr = PageTransHuge(page) ? HPAGE_PMD_NR : 1; - unmap_mapping_pages(mapping, page->index, nr, false); - } + if (page_mapped(page)) + unmap_mapping_page(page); if (page_has_private(page)) do_invalidatepage(page, 0, PAGE_SIZE); @@ -224,7 +221,7 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return -EIO; - truncate_cleanup_page(mapping, page); + truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } @@ -362,7 +359,7 @@ void truncate_inode_pages_range(struct address_space *mapping, pagevec_add(&locked_pvec, page); } for (i = 0; i < pagevec_count(&locked_pvec); i++) - truncate_cleanup_page(mapping, locked_pvec.pages[i]); + truncate_cleanup_page(locked_pvec.pages[i]); delete_from_page_cache_batch(mapping, &locked_pvec); for (i = 0; i < pagevec_count(&locked_pvec); i++) unlock_page(locked_pvec.pages[i]); @@ -715,6 +712,16 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } + if (!did_range_unmap && page_mapped(page)) { + /* + * If page is mapped, before taking its lock, + * zap the rest of the file in one hit. + */ + unmap_mapping_pages(mapping, index, + (1 + end - index), false); + did_range_unmap = 1; + } + lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { @@ -722,23 +729,11 @@ int invalidate_inode_pages2_range(struct address_space *mapping, continue; } wait_on_page_writeback(page); - if (page_mapped(page)) { - if (!did_range_unmap) { - /* - * Zap the rest of the file in one hit. - */ - unmap_mapping_pages(mapping, index, - (1 + end - index), false); - did_range_unmap = 1; - } else { - /* - * Just zap this page - */ - unmap_mapping_pages(mapping, index, - 1, false); - } - } + + if (page_mapped(page)) + unmap_mapping_page(page); BUG_ON(page_mapped(page)); + ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page)) diff --git a/mm/usercopy.c b/mm/usercopy.c index 660717a1ea5c..f70455bad7f3 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -294,7 +294,10 @@ static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { - return strtobool(str, &enable_checks); + if (strtobool(str, &enable_checks)) + pr_warn("Invalid option string for hardened_usercopy: '%s'\n", + str); + return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index c7ae74ce5ff3..6fa66e2111ea 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -53,6 +53,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, /* don't free the page */ goto out; } + + flush_dcache_page(page); } else { page = *pagep; *pagep = NULL; @@ -269,7 +271,7 @@ retry: */ idx = linear_page_index(dst_vma, dst_addr); mapping = dst_vma->vm_file->f_mapping; - hash = hugetlb_fault_mutex_hash(h, mapping, idx, dst_addr); + hash = hugetlb_fault_mutex_hash(h, mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); err = -ENOMEM; @@ -572,6 +574,7 @@ retry: err = -EFAULT; goto out; } + flush_dcache_page(page); goto retry; } else BUG_ON(page); diff --git a/mm/util.c b/mm/util.c index ab358c64bbd3..04ebc76588aa 100644 --- a/mm/util.c +++ b/mm/util.c @@ -320,6 +320,38 @@ unsigned long randomize_stack_top(unsigned long stack_top) #endif } +/** + * randomize_page - Generate a random, page aligned address + * @start: The smallest acceptable address the caller will take. + * @range: The size of the area, starting at @start, within which the + * random address must fall. + * + * If @start + @range would overflow, @range is capped. + * + * NOTE: Historical use of randomize_range, which this replaces, presumed that + * @start was already page aligned. We now align it regardless. + * + * Return: A page aligned address within [start, start + range). On error, + * @start is returned. + */ +unsigned long randomize_page(unsigned long start, unsigned long range) +{ + if (!PAGE_ALIGNED(start)) { + range -= PAGE_ALIGN(start) - start; + start = PAGE_ALIGN(start); + } + + if (start > ULONG_MAX - range) + range = ULONG_MAX - start; + + range >>= PAGE_SHIFT; + + if (range == 0) + return start; + + return start + (get_random_long() % range << PAGE_SHIFT); +} + #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long arch_randomize_brk(struct mm_struct *mm) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 10feb872d9a4..de94881eaa92 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -89,9 +89,12 @@ struct scan_control { unsigned int may_swap:1; /* - * Cgroups are not reclaimed below their configured memory.low, - * unless we threaten to OOM. If any cgroups are skipped due to - * memory.low and nothing was reclaimed, go back for memory.low. + * Cgroup memory below memory.low is protected as long as we + * don't threaten to OOM. If any cgroup is reclaimed at + * reduced force or passed over entirely due to its memory.low + * setting (memcg_low_skipped), and nothing is reclaimed as a + * result, then go back for one more cycle that reclaims the protected + * memory (memcg_low_reclaim) to avert OOM. */ unsigned int memcg_low_reclaim:1; unsigned int memcg_low_skipped:1; @@ -2458,14 +2461,14 @@ out: for_each_evictable_lru(lru) { int file = is_file_lru(lru); unsigned long lruvec_size; + unsigned long low, min; unsigned long scan; - unsigned long protection; lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - protection = mem_cgroup_protection(memcg, - sc->memcg_low_reclaim); + mem_cgroup_protection(sc->target_mem_cgroup, memcg, + &min, &low); - if (protection) { + if (min || low) { /* * Scale a cgroup's reclaim pressure by proportioning * its current usage to its memory.low or memory.min @@ -2496,12 +2499,21 @@ out: * hard protection. */ unsigned long cgroup_size = mem_cgroup_size(memcg); + unsigned long protection; + + /* memory.low scaling, make sure we retry before OOM */ + if (!sc->memcg_low_reclaim && low > min) { + protection = low; + sc->memcg_low_skipped = 1; + } else { + protection = min; + } /* Avoid TOCTOU with earlier protection check */ cgroup_size = max(cgroup_size, protection); scan = lruvec_size - lruvec_size * protection / - cgroup_size; + (cgroup_size + 1); /* * Minimally target SWAP_CLUSTER_MAX pages to keep diff --git a/mm/vmstat.c b/mm/vmstat.c index a8222041bd44..240fe2153ca9 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1444,10 +1444,6 @@ static void pagetypeinfo_showblockcount_print(struct seq_file *m, if (!page) continue; - /* Watch for unexpected holes punched in the memmap */ - if (!memmap_valid_within(pfn, page, zone)) - continue; - if (page_zone(page) != zone) continue; diff --git a/mm/z3fold.c b/mm/z3fold.c index 6d3d3f698ebb..e97143713021 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -839,6 +839,7 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool) destroy_workqueue(pool->compact_wq); destroy_workqueue(pool->release_wq); z3fold_unregister_migration(pool); + free_percpu(pool->unbuddied); kfree(pool); } diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 22d17ecfe7df..6b100f02ee43 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -293,11 +293,7 @@ struct zspage { }; struct mapping_area { -#ifdef CONFIG_PGTABLE_MAPPING - struct vm_struct *vm; /* vm area for mapping object that span pages */ -#else char *vm_buf; /* copy buffer for objects that span pages */ -#endif char *vm_addr; /* address of kmap_atomic()'ed pages */ enum zs_mapmode vm_mm; /* mapping mode */ }; @@ -1113,46 +1109,6 @@ static struct zspage *find_get_zspage(struct size_class *class) return zspage; } -#ifdef CONFIG_PGTABLE_MAPPING -static inline int __zs_cpu_up(struct mapping_area *area) -{ - /* - * Make sure we don't leak memory if a cpu UP notification - * and zs_init() race and both call zs_cpu_up() on the same cpu - */ - if (area->vm) - return 0; - area->vm = alloc_vm_area(PAGE_SIZE * 2, NULL); - if (!area->vm) - return -ENOMEM; - return 0; -} - -static inline void __zs_cpu_down(struct mapping_area *area) -{ - if (area->vm) - free_vm_area(area->vm); - area->vm = NULL; -} - -static inline void *__zs_map_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - BUG_ON(map_vm_area(area->vm, PAGE_KERNEL, pages)); - area->vm_addr = area->vm->addr; - return area->vm_addr + off; -} - -static inline void __zs_unmap_object(struct mapping_area *area, - struct page *pages[2], int off, int size) -{ - unsigned long addr = (unsigned long)area->vm_addr; - - unmap_kernel_range(addr, PAGE_SIZE * 2); -} - -#else /* CONFIG_PGTABLE_MAPPING */ - static inline int __zs_cpu_up(struct mapping_area *area) { /* @@ -1233,8 +1189,6 @@ out: pagefault_enable(); } -#endif /* CONFIG_PGTABLE_MAPPING */ - static int zs_cpu_prepare(unsigned int cpu) { struct mapping_area *area; @@ -1794,11 +1748,40 @@ static enum fullness_group putback_zspage(struct size_class *class, */ static void lock_zspage(struct zspage *zspage) { - struct page *page = get_first_page(zspage); + struct page *curr_page, *page; - do { - lock_page(page); - } while ((page = get_next_page(page)) != NULL); + /* + * Pages we haven't locked yet can be migrated off the list while we're + * trying to lock them, so we need to be careful and only attempt to + * lock each page under migrate_read_lock(). Otherwise, the page we lock + * may no longer belong to the zspage. This means that we may wait for + * the wrong page to unlock, so we must take a reference to the page + * prior to waiting for it to unlock outside migrate_read_lock(). + */ + while (1) { + migrate_read_lock(zspage); + page = get_first_page(zspage); + if (trylock_page(page)) + break; + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + } + + curr_page = page; + while ((page = get_next_page(curr_page))) { + if (trylock_page(page)) { + curr_page = page; + } else { + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + migrate_read_lock(zspage); + } + } + migrate_read_unlock(zspage); } static int zs_init_fs_context(struct fs_context *fc) @@ -1881,10 +1864,11 @@ static inline void zs_pool_dec_isolated(struct zs_pool *pool) VM_BUG_ON(atomic_long_read(&pool->isolated_pages) <= 0); atomic_long_dec(&pool->isolated_pages); /* - * There's no possibility of racing, since wait_for_isolated_drain() - * checks the isolated count under &class->lock after enqueuing - * on migration_wait. + * Checking pool->destroying must happen after atomic_long_dec() + * for pool->isolated_pages above. Paired with the smp_mb() in + * zs_unregister_migration(). */ + smp_mb__after_atomic(); if (atomic_long_read(&pool->isolated_pages) == 0 && pool->destroying) wake_up_all(&pool->migration_wait); } @@ -2262,11 +2246,13 @@ static unsigned long zs_can_compact(struct size_class *class) return obj_wasted * class->pages_per_zspage; } -static void __zs_compact(struct zs_pool *pool, struct size_class *class) +static unsigned long __zs_compact(struct zs_pool *pool, + struct size_class *class) { struct zs_compact_control cc; struct zspage *src_zspage; struct zspage *dst_zspage = NULL; + unsigned long pages_freed = 0; spin_lock(&class->lock); while ((src_zspage = isolate_zspage(class, true))) { @@ -2296,7 +2282,7 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class) putback_zspage(class, dst_zspage); if (putback_zspage(class, src_zspage) == ZS_EMPTY) { free_zspage(pool, class, src_zspage); - pool->stats.pages_compacted += class->pages_per_zspage; + pages_freed += class->pages_per_zspage; } spin_unlock(&class->lock); cond_resched(); @@ -2307,12 +2293,15 @@ static void __zs_compact(struct zs_pool *pool, struct size_class *class) putback_zspage(class, src_zspage); spin_unlock(&class->lock); + + return pages_freed; } unsigned long zs_compact(struct zs_pool *pool) { int i; struct size_class *class; + unsigned long pages_freed = 0; for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) { class = pool->size_class[i]; @@ -2320,10 +2309,11 @@ unsigned long zs_compact(struct zs_pool *pool) continue; if (class->index != i) continue; - __zs_compact(pool, class); + pages_freed += __zs_compact(pool, class); } + atomic_long_add(pages_freed, &pool->stats.pages_compacted); - return pool->stats.pages_compacted; + return pages_freed; } EXPORT_SYMBOL_GPL(zs_compact); @@ -2340,13 +2330,12 @@ static unsigned long zs_shrinker_scan(struct shrinker *shrinker, struct zs_pool *pool = container_of(shrinker, struct zs_pool, shrinker); - pages_freed = pool->stats.pages_compacted; /* * Compact classes and calculate compaction delta. * Can run concurrently with a manually triggered * (by user) compaction. */ - pages_freed = zs_compact(pool) - pages_freed; + pages_freed = zs_compact(pool); return pages_freed ? pages_freed : SHRINK_STOP; } |