From 4db7548ccbd9ec8e666f35df4a530f55904dec39 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 19 May 2016 17:14:32 -0700 Subject: mm, page_alloc: defer debugging checks of freed pages until a PCP drain Every page free checks a number of page fields for validity. This catches premature frees and corruptions but it is also expensive. This patch weakens the debugging check by checking PCP pages at the time they are drained from the PCP list. This will trigger the bug but the site that freed the corrupt page will be lost. To get the full context, a kernel rebuild with DEBUG_VM is necessary. [akpm@linux-foundation.org: fix build] Signed-off-by: Mel Gorman Cc: Vlastimil Babka Cc: Jesper Dangaard Brouer Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 39c441b..759d3f6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -941,6 +941,103 @@ static inline int free_pages_check(struct page *page) return 1; } +static int free_tail_pages_check(struct page *head_page, struct page *page) +{ + int ret = 1; + + /* + * We rely page->lru.next never has bit 0 set, unless the page + * is PageTail(). Let's make sure that's true even for poisoned ->lru. + */ + BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); + + if (!IS_ENABLED(CONFIG_DEBUG_VM)) { + ret = 0; + goto out; + } + switch (page - head_page) { + case 1: + /* the first tail page: ->mapping is compound_mapcount() */ + if (unlikely(compound_mapcount(page))) { + bad_page(page, "nonzero compound_mapcount", 0); + goto out; + } + break; + case 2: + /* + * the second tail page: ->mapping is + * page_deferred_list().next -- ignore value. + */ + break; + default: + if (page->mapping != TAIL_MAPPING) { + bad_page(page, "corrupted mapping in tail page", 0); + goto out; + } + break; + } + if (unlikely(!PageTail(page))) { + bad_page(page, "PageTail not set", 0); + goto out; + } + if (unlikely(compound_head(page) != head_page)) { + bad_page(page, "compound_head not consistent", 0); + goto out; + } + ret = 0; +out: + page->mapping = NULL; + clear_compound_head(page); + return ret; +} + +static bool free_pages_prepare(struct page *page, unsigned int order); + +#ifdef CONFIG_DEBUG_VM +static inline bool free_pcp_prepare(struct page *page) +{ + return free_pages_prepare(page, 0); +} + +static inline bool bulkfree_pcp_prepare(struct page *page) +{ + return false; +} +#else +static bool free_pcp_prepare(struct page *page) +{ + VM_BUG_ON_PAGE(PageTail(page), page); + + trace_mm_page_free(page, 0); + kmemcheck_free_shadow(page, 0); + kasan_free_pages(page, 0); + + if (PageAnonHead(page)) + page->mapping = NULL; + + reset_page_owner(page, 0); + + if (!PageHighMem(page)) { + debug_check_no_locks_freed(page_address(page), + PAGE_SIZE); + debug_check_no_obj_freed(page_address(page), + PAGE_SIZE); + } + arch_free_page(page, 0); + kernel_poison_pages(page, 0, 0); + kernel_map_pages(page, 0, 0); + + page_cpupid_reset_last(page); + page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; + return true; +} + +static bool bulkfree_pcp_prepare(struct page *page) +{ + return free_pages_check(page); +} +#endif /* CONFIG_DEBUG_VM */ + /* * Frees a number of pages from the PCP lists * Assumes all pages on list are in same zone, and of same order. @@ -1002,6 +1099,9 @@ static void free_pcppages_bulk(struct zone *zone, int count, if (unlikely(isolated_pageblocks)) mt = get_pageblock_migratetype(page); + if (bulkfree_pcp_prepare(page)) + continue; + __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); } while (--count && --batch_free && !list_empty(list)); @@ -1028,56 +1128,6 @@ static void free_one_page(struct zone *zone, spin_unlock(&zone->lock); } -static int free_tail_pages_check(struct page *head_page, struct page *page) -{ - int ret = 1; - - /* - * We rely page->lru.next never has bit 0 set, unless the page - * is PageTail(). Let's make sure that's true even for poisoned ->lru. - */ - BUILD_BUG_ON((unsigned long)LIST_POISON1 & 1); - - if (!IS_ENABLED(CONFIG_DEBUG_VM)) { - ret = 0; - goto out; - } - switch (page - head_page) { - case 1: - /* the first tail page: ->mapping is compound_mapcount() */ - if (unlikely(compound_mapcount(page))) { - bad_page(page, "nonzero compound_mapcount", 0); - goto out; - } - break; - case 2: - /* - * the second tail page: ->mapping is - * page_deferred_list().next -- ignore value. - */ - break; - default: - if (page->mapping != TAIL_MAPPING) { - bad_page(page, "corrupted mapping in tail page", 0); - goto out; - } - break; - } - if (unlikely(!PageTail(page))) { - bad_page(page, "PageTail not set", 0); - goto out; - } - if (unlikely(compound_head(page) != head_page)) { - bad_page(page, "compound_head not consistent", 0); - goto out; - } - ret = 0; -out: - page->mapping = NULL; - clear_compound_head(page); - return ret; -} - static void __meminit __init_single_page(struct page *page, unsigned long pfn, unsigned long zone, int nid) { @@ -2339,7 +2389,7 @@ void free_hot_cold_page(struct page *page, bool cold) unsigned long pfn = page_to_pfn(page); int migratetype; - if (!free_pages_prepare(page, 0)) + if (!free_pcp_prepare(page)) return; migratetype = get_pfnblock_migratetype(page, pfn); -- cgit v0.10.2