From ae41be374293e70e1ed441d986afcc6e744ef9d9 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Thu, 7 Feb 2008 00:14:10 -0800 Subject: bugfix for memory cgroup controller: migration under memory controller fix While using memory control cgroup, page-migration under it works as following. == 1. uncharge all refs at try to unmap. 2. charge regs again remove_migration_ptes() == This is simple but has following problems. == The page is uncharged and charged back again if *mapped*. - This means that cgroup before migration can be different from one after migration - If page is not mapped but charged as page cache, charge is just ignored (because not mapped, it will not be uncharged before migration) This is memory leak. == This patch tries to keep memory cgroup at page migration by increasing one refcnt during it. 3 functions are added. mem_cgroup_prepare_migration() --- increase refcnt of page->page_cgroup mem_cgroup_end_migration() --- decrease refcnt of page->page_cgroup mem_cgroup_page_migration() --- copy page->page_cgroup from old page to new page. During migration - old page is under PG_locked. - new page is under PG_locked, too. - both old page and new page is not on LRU. These 3 facts guarantee that page_cgroup() migration has no race. Tested and worked well in x86_64/fake-NUMA box. Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Pavel Emelianov Cc: Paul Menage Cc: Peter Zijlstra Cc: "Eric W. Biederman" Cc: Nick Piggin Cc: Kirill Korotaev Cc: Herbert Poetzl Cc: David Rientjes Cc: Vaidyanathan Srinivasan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3270ce7375db..128f45c16fa6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -492,6 +492,49 @@ void mem_cgroup_uncharge(struct page_cgroup *pc) } } } +/* + * Returns non-zero if a page (under migration) has valid page_cgroup member. + * Refcnt of page_cgroup is incremented. + */ + +int mem_cgroup_prepare_migration(struct page *page) +{ + struct page_cgroup *pc; + int ret = 0; + lock_page_cgroup(page); + pc = page_get_page_cgroup(page); + if (pc && atomic_inc_not_zero(&pc->ref_cnt)) + ret = 1; + unlock_page_cgroup(page); + return ret; +} + +void mem_cgroup_end_migration(struct page *page) +{ + struct page_cgroup *pc = page_get_page_cgroup(page); + mem_cgroup_uncharge(pc); +} +/* + * We know both *page* and *newpage* are now not-on-LRU and Pg_locked. + * And no race with uncharge() routines because page_cgroup for *page* + * has extra one reference by mem_cgroup_prepare_migration. + */ + +void mem_cgroup_page_migration(struct page *page, struct page *newpage) +{ + struct page_cgroup *pc; +retry: + pc = page_get_page_cgroup(page); + if (!pc) + return; + if (clear_page_cgroup(page, pc) != pc) + goto retry; + pc->page = newpage; + lock_page_cgroup(newpage); + page_assign_page_cgroup(newpage, pc); + unlock_page_cgroup(newpage); + return; +} int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp) { -- cgit v1.2.3-59-g8ed1b