From 15ff646fd5ca343f92d88675a61bd68abd4d207c Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Tue, 15 Dec 2020 12:34:16 -0800 Subject: [PATCH] BACKPORT: mm/lru: introduce TestClearPageLRU() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently lru_lock still guards both lru list and page's lru bit, that's ok. but if we want to use specific lruvec lock on the page, we need to pin down the page's lruvec/memcg during locking. Just taking lruvec lock first may be undermined by the page's memcg charge/migration. To fix this problem, we will clear the lru bit out of locking and use it as pin down action to block the page isolation in memcg changing. So now a standard steps of page isolation is following: 1, get_page(); #pin the page avoid to be free 2, TestClearPageLRU(); #block other isolation like memcg change 3, spin_lock on lru_lock; #serialize lru list access 4, delete page from lru list; This patch start with the first part: TestClearPageLRU, which combines PageLRU check and ClearPageLRU into a macro func TestClearPageLRU. This function will be used as page isolation precondition to prevent other isolations some where else. Then there are may !PageLRU page on lru list, need to remove BUG() checking accordingly. There 2 rules for lru bit now: 1, the lru bit still indicate if a page on lru list, just in some temporary moment(isolating), the page may have no lru bit when it's on lru list. but the page still must be on lru list when the lru bit set. 2, have to remove lru bit before delete it from lru list. As Andrew Morton mentioned this change would dirty cacheline for a page which isn't on the LRU. But the loss would be acceptable in Rong Chen report: https://lore.kernel.org/lkml/20200304090301.GB5972@shao2-debian/ Link: https://lkml.kernel.org/r/1604566549-62481-15-git-send-email-alex.shi@linux.alibaba.com Suggested-by: Johannes Weiner Signed-off-by: Alex Shi Acked-by: Hugh Dickins Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Michal Hocko Cc: Vladimir Davydov Cc: Alexander Duyck Cc: Andrea Arcangeli Cc: Andrey Ryabinin Cc: Daniel Jordan Cc: "Huang, Ying" Cc: Jann Horn Cc: Joonsoo Kim Cc: Kirill A. Shutemov Cc: Kirill A. Shutemov Cc: Konstantin Khlebnikov Cc: Matthew Wilcox (Oracle) Cc: Mel Gorman Cc: Michal Hocko Cc: Mika Penttilä Cc: Minchan Kim Cc: Shakeel Butt Cc: Tejun Heo Cc: Thomas Gleixner Cc: Wei Yang Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: UtsavBalar1231 Change-Id: I49a9f0c981e49efe5819f5556528b9db9181c18c --- include/linux/page-flags.h | 1 + mm/mlock.c | 3 +-- mm/vmscan.c | 40 ++++++++++++++++++++------------------ 3 files changed, 23 insertions(+), 21 deletions(-) diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e76da317451a..bbda923b453d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -279,6 +279,7 @@ PAGEFLAG(Referenced, referenced, PF_HEAD) PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) __CLEARPAGEFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) + TESTCLEARFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) PAGEFLAG(Workingset, workingset, PF_HEAD) diff --git a/mm/mlock.c b/mm/mlock.c index ca87032bda0c..a64b0be7a0ec 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -108,13 +108,12 @@ void mlock_vma_page(struct page *page) */ static bool __munlock_isolate_lru_page(struct page *page, bool getpage) { - if (PageLRU(page)) { + if (TestClearPageLRU(page)) { struct lruvec *lruvec; lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (getpage) get_page(page); - ClearPageLRU(page); del_page_from_lru_list(page, lruvec); return true; } diff --git a/mm/vmscan.c b/mm/vmscan.c index e3ecd9c1f575..b09194782dee 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1631,7 +1631,7 @@ unsigned long reclaim_pages(struct list_head *page_list) */ int __isolate_lru_page(struct page *page, isolate_mode_t mode) { - int ret = -EINVAL; + int ret = -EBUSY; /* Only take pages on the LRU. */ if (!PageLRU(page)) @@ -1641,8 +1641,6 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE)) return ret; - ret = -EBUSY; - /* * To minimise LRU disruption, the caller can indicate that it only * wants to isolate pages it will be able to operate on without @@ -1689,8 +1687,10 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode) * sure the page is not being freed elsewhere -- the * page release code relies on it. */ - ClearPageLRU(page); - ret = 0; + if (TestClearPageLRU(page)) + ret = 0; + else + put_page(page); } return ret; @@ -1757,8 +1757,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, page = lru_to_page(src); prefetchw_prev_lru_page(page, src, flags); - VM_BUG_ON_PAGE(!PageLRU(page), page); - if (page_zonenum(page) > sc->reclaim_idx) { list_move(&page->lru, &pages_skipped); nr_skipped[page_zonenum(page)]++; @@ -1849,20 +1847,19 @@ int isolate_lru_page(struct page *page) VM_BUG_ON_PAGE(!page_count(page), page); WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); - if (PageLRU(page)) { + if (TestClearPageLRU(page)) { struct zone *zone = page_zone(page); struct lruvec *lruvec; - spin_lock_irq(zone_lru_lock(zone)); + get_page(page); lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat); - if (PageLRU(page)) { - get_page(page); - ClearPageLRU(page); - del_page_from_lru_list(page, lruvec); - ret = 0; - } + + spin_lock_irq(zone_lru_lock(zone)); + del_page_from_lru_list(page, lruvec); spin_unlock_irq(zone_lru_lock(zone)); + ret = 0; } + return ret; } @@ -6924,6 +6921,11 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) struct pglist_data *pagepgdat = page_pgdat(page); pgscanned++; + + /* block memcg migration during page moving between lru */ + if (!TestClearPageLRU(page)) + continue; + if (pagepgdat != pgdat) { if (pgdat) spin_unlock_irq(&pgdat->lru_lock); @@ -6932,21 +6934,21 @@ void check_move_unevictable_pages(struct page **pages, int nr_pages) } lruvec = mem_cgroup_page_lruvec(page, pgdat); - if (!PageLRU(page) || !PageUnevictable(page)) - continue; - - if (page_evictable(page)) { + if (page_evictable(page) && PageUnevictable(page)) { del_page_from_lru_list(page, lruvec); ClearPageUnevictable(page); add_page_to_lru_list(page, lruvec); pgrescued++; } + SetPageLRU(page); } if (pgdat) { __count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued); __count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); spin_unlock_irq(&pgdat->lru_lock); + } else if (pgscanned) { + count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned); } } #endif /* CONFIG_SHMEM */