From 12d27107867fc7216e8faaff0b894b0f162dcf75 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 12 Jan 2012 17:19:52 -0800 Subject: memcg: fix split_huge_page_refcounts() This patch started off as a cleanup: __split_huge_page_refcounts() has to cope with two scenarios, when the hugepage being split is already on LRU, and when it is not; but why does it have to split that accounting across three different sites? Consolidate it in lru_add_page_tail(), handling evictable and unevictable alike, and use standard add_page_to_lru_list() when accounting is needed (when the head is not yet on LRU). But a recent regression in -next, I guess the removal of PageCgroupAcctLRU test from mem_cgroup_split_huge_fixup(), makes this now a necessary fix: under load, the MEM_CGROUP_ZSTAT count was wrapping to a huge number, messing up reclaim calculations and causing a freeze at rmdir of cgroup. Add a VM_BUG_ON to mem_cgroup_lru_del_list() when we're about to wrap that count - this has not been the only such incident. Document that lru_add_page_tail() is for Transparent HugePages by #ifdef around it. Signed-off-by: Hugh Dickins Cc: Daisuke Nishimura Cc: KAMEZAWA Hiroyuki Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) (limited to 'mm/swap.c') diff --git a/mm/swap.c b/mm/swap.c index ddccf8e0b4ae..db6defaf2e55 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -650,6 +650,7 @@ void __pagevec_release(struct pagevec *pvec) EXPORT_SYMBOL(__pagevec_release); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* used by __split_huge_page_refcount() */ void lru_add_page_tail(struct zone* zone, struct page *page, struct page *page_tail) @@ -666,8 +667,6 @@ void lru_add_page_tail(struct zone* zone, SetPageLRU(page_tail); if (page_evictable(page_tail, NULL)) { - struct lruvec *lruvec; - if (PageActive(page)) { SetPageActive(page_tail); active = 1; @@ -677,18 +676,28 @@ void lru_add_page_tail(struct zone* zone, lru = LRU_INACTIVE_ANON; } update_page_reclaim_stat(zone, page_tail, file, active); - lruvec = mem_cgroup_lru_add_list(zone, page_tail, lru); - if (likely(PageLRU(page))) - list_add(&page_tail->lru, page->lru.prev); - else - list_add(&page_tail->lru, lruvec->lists[lru].prev); - __mod_zone_page_state(zone, NR_LRU_BASE + lru, - hpage_nr_pages(page_tail)); } else { SetPageUnevictable(page_tail); - add_page_to_lru_list(zone, page_tail, LRU_UNEVICTABLE); + lru = LRU_UNEVICTABLE; + } + + if (likely(PageLRU(page))) + list_add_tail(&page_tail->lru, &page->lru); + else { + struct list_head *list_head; + /* + * Head page has not yet been counted, as an hpage, + * so we must account for each subpage individually. + * + * Use the standard add function to put page_tail on the list, + * but then correct its position so they all end up in order. + */ + add_page_to_lru_list(zone, page_tail, lru); + list_head = page_tail->lru.prev; + list_move_tail(&page_tail->lru, list_head); } } +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static void ____pagevec_lru_add_fn(struct page *page, void *arg) { -- cgit v1.2.3