From a6de734bc002fe2027ccc074fbbd87d72957b7a4 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 12 Dec 2016 16:44:41 -0800 Subject: mm, page_alloc: keep pcp count and list contents in sync if struct page is corrupted Vlastimil Babka pointed out that commit 479f854a207c ("mm, page_alloc: defer debugging checks of pages allocated from the PCP") will allow the per-cpu list counter to be out of sync with the per-cpu list contents if a struct page is corrupted. The consequence is an infinite loop if the per-cpu lists get fully drained by free_pcppages_bulk because all the lists are empty but the count is positive. The infinite loop occurs here do { batch_free++; if (++migratetype == MIGRATE_PCPTYPES) migratetype = 0; list = &pcp->lists[migratetype]; } while (list_empty(list)); What the user sees is a bad page warning followed by a soft lockup with interrupts disabled in free_pcppages_bulk(). This patch keeps the accounting in sync. Fixes: 479f854a207c ("mm, page_alloc: defer debugging checks of pages allocated from the PCP") Link: http://lkml.kernel.org/r/20161202112951.23346-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Acked-by: Michal Hocko Acked-by: Hillf Danton Cc: Christoph Lameter Cc: Johannes Weiner Cc: Jesper Dangaard Brouer Cc: Joonsoo Kim Cc: [4.7+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2b69e28706b1..3f2c9e535f7f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2218,7 +2218,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, bool cold) { - int i; + int i, alloced = 0; spin_lock(&zone->lock); for (i = 0; i < count; ++i) { @@ -2243,13 +2243,21 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, else list_add_tail(&page->lru, list); list = &page->lru; + alloced++; if (is_migrate_cma(get_pcppage_migratetype(page))) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, -(1 << order)); } + + /* + * i pages were removed from the buddy list even if some leak due + * to check_pcp_refill failing so adjust NR_FREE_PAGES based + * on i. Do not confuse with 'alloced' which is the number of + * pages added to the pcp list. + */ __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock(&zone->lock); - return i; + return alloced; } #ifdef CONFIG_NUMA -- cgit v1.2.3