From 44b7a8d33d666268062e0f725d5f14813a63a6ea Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 20 Jan 2016 15:03:16 -0800 Subject: mm: memcontrol: do not uncharge old page in page cache replacement Changing page->mem_cgroup of a live page is tricky and fragile. In particular, the memcg writeback code relies on that mapping being stable and users of mem_cgroup_replace_page() not overlapping with dirtyable inodes. Page cache replacement doesn't have to do that, though. Instead of being clever and transferring the charge from the old page to the new, force-charge the new page and leave the old page alone. A temporary overcharge won't matter in practice, and the old page is going to be freed shortly after this anyway. And this is not performance critical. Signed-off-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6a0007965e31..bf35bff282fc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -366,13 +366,6 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) * * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup * is returned. - * - * XXX: The above description of behavior on the default hierarchy isn't - * strictly true yet as replace_page_cache_page() can modify the - * association before @page is released even on the default hierarchy; - * however, the current and planned usages don't mix the the two functions - * and replace_page_cache_page() will soon be updated to make the invariant - * actually true. */ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) { @@ -5464,7 +5457,8 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) { struct mem_cgroup *memcg; - int isolated; + unsigned int nr_pages; + bool compound; VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); @@ -5484,11 +5478,21 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) if (!memcg) return; - lock_page_lru(oldpage, &isolated); - oldpage->mem_cgroup = NULL; - unlock_page_lru(oldpage, isolated); + /* Force-charge the new page. The old one will be freed soon */ + compound = PageTransHuge(newpage); + nr_pages = compound ? hpage_nr_pages(newpage) : 1; + + page_counter_charge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_charge(&memcg->memsw, nr_pages); + css_get_many(&memcg->css, nr_pages); commit_charge(newpage, memcg, true); + + local_irq_disable(); + mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); + memcg_check_events(memcg, newpage); + local_irq_enable(); } DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); -- cgit v1.2.3-55-g7522