From 9c4e6b1a7027f102990c0395296015a812525f4d Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 21 Feb 2018 14:45:28 -0800 Subject: mm, mlock, vmscan: no more skipping pagevecs When a thread mlocks an address space backed either by file pages which are currently not present in memory or swapped out anon pages (not in swapcache), a new page is allocated and added to the local pagevec (lru_add_pvec), I/O is triggered and the thread then sleeps on the page. On I/O completion, the thread can wake on a different CPU, the mlock syscall will then sets the PageMlocked() bit of the page but will not be able to put that page in unevictable LRU as the page is on the pagevec of a different CPU. Even on drain, that page will go to evictable LRU because the PageMlocked() bit is not checked on pagevec drain. The page will eventually go to right LRU on reclaim but the LRU stats will remain skewed for a long time. This patch puts all the pages, even unevictable, to the pagevecs and on the drain, the pages will be added on their LRUs correctly by checking their evictability. This resolves the mlocked pages on pagevec of other CPUs issue because when those pagevecs will be drained, the mlocked file pages will go to unevictable LRU. Also this makes the race with munlock easier to resolve because the pagevec drains happen in LRU lock. However there is still one place which makes a page evictable and does PageLRU check on that page without LRU lock and needs special attention. TestClearPageMlocked() and isolate_lru_page() in clear_page_mlock(). #0: __pagevec_lru_add_fn #1: clear_page_mlock SetPageLRU() if (!TestClearPageMlocked()) return smp_mb() // <--required // inside does PageLRU if (!PageMlocked()) if (isolate_lru_page()) move to evictable LRU putback_lru_page() else move to unevictable LRU In '#1', TestClearPageMlocked() provides full memory barrier semantics and thus the PageLRU check (inside isolate_lru_page) can not be reordered before it. In '#0', without explicit memory barrier, the PageMlocked() check can be reordered before SetPageLRU(). If that happens, '#0' can put a page in unevictable LRU and '#1' might have just cleared the Mlocked bit of that page but fails to isolate as PageLRU fails as '#0' still hasn't set PageLRU bit of that page. That page will be stranded on the unevictable LRU. There is one (good) side effect though. Without this patch, the pages allocated for System V shared memory segment are added to evictable LRUs even after shmctl(SHM_LOCK) on that segment. This patch will correctly put such pages to unevictable LRU. Link: http://lkml.kernel.org/r/20171121211241.18877-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Vlastimil Babka Cc: Jérôme Glisse Cc: Huang Ying Cc: Tim Chen Cc: Michal Hocko Cc: Greg Thelen Cc: Johannes Weiner Cc: Balbir Singh Cc: Minchan Kim Cc: Shaohua Li Cc: Jan Kara Cc: Nicholas Piggin Cc: Dan Williams Cc: Mel Gorman Cc: Hugh Dickins Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap.c | 82 ++++++++++++++++++++++++++++++++++++--------------------------- 1 file changed, 47 insertions(+), 35 deletions(-) (limited to 'mm/swap.c') diff --git a/mm/swap.c b/mm/swap.c index 567a7b96e41d..2d337710218f 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -445,30 +445,6 @@ void lru_cache_add(struct page *page) __lru_cache_add(page); } -/** - * add_page_to_unevictable_list - add a page to the unevictable list - * @page: the page to be added to the unevictable list - * - * Add page directly to its zone's unevictable list. To avoid races with - * tasks that might be making the page evictable, through eg. munlock, - * munmap or exit, while it's not on the lru, we want to add the page - * while it's locked or otherwise "invisible" to other tasks. This is - * difficult to do when using the pagevec cache, so bypass that. - */ -void add_page_to_unevictable_list(struct page *page) -{ - struct pglist_data *pgdat = page_pgdat(page); - struct lruvec *lruvec; - - spin_lock_irq(&pgdat->lru_lock); - lruvec = mem_cgroup_page_lruvec(page, pgdat); - ClearPageActive(page); - SetPageUnevictable(page); - SetPageLRU(page); - add_page_to_lru_list(page, lruvec, LRU_UNEVICTABLE); - spin_unlock_irq(&pgdat->lru_lock); -} - /** * lru_cache_add_active_or_unevictable * @page: the page to be added to LRU @@ -484,13 +460,9 @@ void lru_cache_add_active_or_unevictable(struct page *page, { VM_BUG_ON_PAGE(PageLRU(page), page); - if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) { + if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED)) SetPageActive(page); - lru_cache_add(page); - return; - } - - if (!TestSetPageMlocked(page)) { + else if (!TestSetPageMlocked(page)) { /* * We use the irq-unsafe __mod_zone_page_stat because this * counter is not modified from interrupt context, and the pte @@ -500,7 +472,7 @@ void lru_cache_add_active_or_unevictable(struct page *page, hpage_nr_pages(page)); count_vm_event(UNEVICTABLE_PGMLOCKED); } - add_page_to_unevictable_list(page); + lru_cache_add(page); } /* @@ -886,15 +858,55 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec, void *arg) { - int file = page_is_file_cache(page); - int active = PageActive(page); - enum lru_list lru = page_lru(page); + enum lru_list lru; + int was_unevictable = TestClearPageUnevictable(page); VM_BUG_ON_PAGE(PageLRU(page), page); SetPageLRU(page); + /* + * Page becomes evictable in two ways: + * 1) Within LRU lock [munlock_vma_pages() and __munlock_pagevec()]. + * 2) Before acquiring LRU lock to put the page to correct LRU and then + * a) do PageLRU check with lock [check_move_unevictable_pages] + * b) do PageLRU check before lock [clear_page_mlock] + * + * (1) & (2a) are ok as LRU lock will serialize them. For (2b), we need + * following strict ordering: + * + * #0: __pagevec_lru_add_fn #1: clear_page_mlock + * + * SetPageLRU() TestClearPageMlocked() + * smp_mb() // explicit ordering // above provides strict + * // ordering + * PageMlocked() PageLRU() + * + * + * if '#1' does not observe setting of PG_lru by '#0' and fails + * isolation, the explicit barrier will make sure that page_evictable + * check will put the page in correct LRU. Without smp_mb(), SetPageLRU + * can be reordered after PageMlocked check and can make '#1' to fail + * the isolation of the page whose Mlocked bit is cleared (#0 is also + * looking at the same page) and the evictable page will be stranded + * in an unevictable LRU. + */ + smp_mb(); + + if (page_evictable(page)) { + lru = page_lru(page); + update_page_reclaim_stat(lruvec, page_is_file_cache(page), + PageActive(page)); + if (was_unevictable) + count_vm_event(UNEVICTABLE_PGRESCUED); + } else { + lru = LRU_UNEVICTABLE; + ClearPageActive(page); + SetPageUnevictable(page); + if (!was_unevictable) + count_vm_event(UNEVICTABLE_PGCULLED); + } + add_page_to_lru_list(page, lruvec, lru); - update_page_reclaim_stat(lruvec, file, active); trace_mm_lru_insertion(page, lru); } -- cgit v1.2.3-55-g7522