From 3ea67d06e4679a16f69f66f43a8d6ee4778985fc Mon Sep 17 00:00:00 2001 From: Sha Zhengju Date: Thu, 12 Sep 2013 15:13:53 -0700 Subject: memcg: add per cgroup writeback pages accounting Add memcg routines to count writeback pages, later dirty pages will also be accounted. After Kame's commit 89c06bd52fb9 ("memcg: use new logic for page stat accounting"), we can use 'struct page' flag to test page state instead of per page_cgroup flag. But memcg has a feature to move a page from a cgroup to another one and may have race between "move" and "page stat accounting". So in order to avoid the race we have designed a new lock: mem_cgroup_begin_update_page_stat() modify page information -->(a) mem_cgroup_update_page_stat() -->(b) mem_cgroup_end_update_page_stat() It requires both (a) and (b)(writeback pages accounting) to be pretected in mem_cgroup_{begin/end}_update_page_stat(). It's full no-op for !CONFIG_MEMCG, almost no-op if memcg is disabled (but compiled in), rcu read lock in the most cases (no task is moving), and spin_lock_irqsave on top in the slow path. There're two writeback interfaces to modify: test_{clear/set}_page_writeback(). And the lock order is: --> memcg->move_lock --> mapping->tree_lock Signed-off-by: Sha Zhengju Acked-by: Michal Hocko Reviewed-by: Greg Thelen Cc: Fengguang Wu Cc: KAMEZAWA Hiroyuki Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'mm/page-writeback.c') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6c7b0187be8e..f5236f804aa6 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2143,11 +2143,17 @@ EXPORT_SYMBOL(account_page_dirtied); /* * Helper function for set_page_writeback family. + * + * The caller must hold mem_cgroup_begin/end_update_page_stat() lock + * while calling this function. + * See test_set_page_writeback for example. + * * NOTE: Unlike account_page_dirtied this does not rely on being atomic * wrt interrupts. */ void account_page_writeback(struct page *page) { + mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); inc_zone_page_state(page, NR_WRITEBACK); } EXPORT_SYMBOL(account_page_writeback); @@ -2364,7 +2370,10 @@ int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2385,9 +2394,11 @@ int test_clear_page_writeback(struct page *page) ret = TestClearPageWriteback(page); } if (ret) { + mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK); dec_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } @@ -2395,7 +2406,10 @@ int test_set_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); int ret; + bool locked; + unsigned long memcg_flags; + mem_cgroup_begin_update_page_stat(page, &locked, &memcg_flags); if (mapping) { struct backing_dev_info *bdi = mapping->backing_dev_info; unsigned long flags; @@ -2422,6 +2436,7 @@ int test_set_page_writeback(struct page *page) } if (!ret) account_page_writeback(page); + mem_cgroup_end_update_page_stat(page, &locked, &memcg_flags); return ret; } -- cgit v1.2.3