From 6e4bd50f3888fa8fea8bc66a0ad4ad5f1c862961 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 14 Aug 2020 17:31:34 -0700 Subject: [PATCH] mm/page_counter: fix various data races at memsw Commit 3e32cb2e0a12 ("mm: memcontrol: lockless page counters") could had memcg->memsw->watermark and memcg->memsw->failcnt been accessed concurrently as reported by KCSAN, BUG: KCSAN: data-race in page_counter_try_charge / page_counter_try_charge read to 0xffff8fb18c4cd190 of 8 bytes by task 1081 on cpu 59: page_counter_try_charge+0x4d/0x150 mm/page_counter.c:138 try_charge+0x131/0xd50 mm/memcontrol.c:2405 __memcg_kmem_charge_memcg+0x58/0x140 __memcg_kmem_charge+0xcc/0x280 __alloc_pages_nodemask+0x1e1/0x450 alloc_pages_current+0xa6/0x120 pte_alloc_one+0x17/0xd0 __pte_alloc+0x3a/0x1f0 copy_p4d_range+0xc36/0x1990 copy_page_range+0x21d/0x360 dup_mmap+0x5f5/0x7a0 dup_mm+0xa2/0x240 copy_process+0x1b3f/0x3460 _do_fork+0xaa/0xa20 __x64_sys_clone+0x13b/0x170 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe write to 0xffff8fb18c4cd190 of 8 bytes by task 1153 on cpu 120: page_counter_try_charge+0x5b/0x150 mm/page_counter.c:139 try_charge+0x131/0xd50 mm/memcontrol.c:2405 mem_cgroup_try_charge+0x159/0x460 mem_cgroup_try_charge_delay+0x3d/0xa0 wp_page_copy+0x14d/0x930 do_wp_page+0x107/0x7b0 __handle_mm_fault+0xce6/0xd40 handle_mm_fault+0xfc/0x2f0 do_page_fault+0x263/0x6f9 page_fault+0x34/0x40 BUG: KCSAN: data-race in page_counter_try_charge / page_counter_try_charge write to 0xffff88809bbf2158 of 8 bytes by task 11782 on cpu 0: page_counter_try_charge+0x100/0x170 mm/page_counter.c:129 try_charge+0x185/0xbf0 mm/memcontrol.c:2405 __memcg_kmem_charge_memcg+0x4a/0xe0 mm/memcontrol.c:2837 __memcg_kmem_charge+0xcf/0x1b0 mm/memcontrol.c:2877 __alloc_pages_nodemask+0x26c/0x310 mm/page_alloc.c:4780 read to 0xffff88809bbf2158 of 8 bytes by task 11814 on cpu 1: page_counter_try_charge+0xef/0x170 mm/page_counter.c:129 try_charge+0x185/0xbf0 mm/memcontrol.c:2405 __memcg_kmem_charge_memcg+0x4a/0xe0 mm/memcontrol.c:2837 __memcg_kmem_charge+0xcf/0x1b0 mm/memcontrol.c:2877 __alloc_pages_nodemask+0x26c/0x310 mm/page_alloc.c:4780 Since watermark could be compared or set to garbage due to a data race which would change the code logic, fix it by adding a pair of READ_ONCE() and WRITE_ONCE() in those places. The "failcnt" counter is tolerant of some degree of inaccuracy and is only used to report stats, a data race will not be harmful, thus mark it as an intentional data race using the data_race() macro. Fixes: 3e32cb2e0a12 ("mm: memcontrol: lockless page counters") Reported-by: syzbot+f36cfe60b1006a94f9dc@syzkaller.appspotmail.com Signed-off-by: Qian Cai Signed-off-by: Andrew Morton Acked-by: Michal Hocko Cc: David Hildenbrand Cc: Tetsuo Handa Cc: Marco Elver Cc: Dmitry Vyukov Cc: Johannes Weiner Link: http://lkml.kernel.org/r/1581519682-23594-1-git-send-email-cai@lca.pw Signed-off-by: Linus Torvalds --- mm/page_counter.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/mm/page_counter.c b/mm/page_counter.c index b4663844c9b3..afe22ad335cc 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -77,8 +77,8 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages) * This is indeed racy, but we can live with some * inaccuracy in the watermark. */ - if (new > c->watermark) - c->watermark = new; + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); } } @@ -119,9 +119,10 @@ bool page_counter_try_charge(struct page_counter *counter, propagate_protected_usage(c, new); /* * This is racy, but we can live with some - * inaccuracy in the failcnt. + * inaccuracy in the failcnt which is only used + * to report stats. */ - c->failcnt++; + data_race(c->failcnt++); *fail = c; goto failed; } @@ -130,8 +131,8 @@ bool page_counter_try_charge(struct page_counter *counter, * Just like with failcnt, we can live with some * inaccuracy in the watermark. */ - if (new > c->watermark) - c->watermark = new; + if (new > READ_ONCE(c->watermark)) + WRITE_ONCE(c->watermark, new); } return true; -- 2.34.1