From cd324edce598ebddde44162a2aa01321c1261b9e Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 25 Jun 2020 20:30:16 -0700 Subject: mm: memcontrol: handle div0 crash race condition in memory.low Tejun reports seeing rare div0 crashes in memory.low stress testing: RIP: 0010:mem_cgroup_calculate_protection+0xed/0x150 Code: 0f 46 d1 4c 39 d8 72 57 f6 05 16 d6 42 01 40 74 1f 4c 39 d8 76 1a 4c 39 d1 76 15 4c 29 d1 4c 29 d8 4d 29 d9 31 d2 48 0f af c1 <49> f7 f1 49 01 c2 4c 89 96 38 01 00 00 5d c3 48 0f af c7 31 d2 49 RSP: 0018:ffffa14e01d6fcd0 EFLAGS: 00010246 RAX: 000000000243e384 RBX: 0000000000000000 RCX: 0000000000008f4b RDX: 0000000000000000 RSI: ffff8b89bee84000 RDI: 0000000000000000 RBP: ffffa14e01d6fcd0 R08: ffff8b89ca7d40f8 R09: 0000000000000000 R10: 0000000000000000 R11: 00000000006422f7 R12: 0000000000000000 R13: ffff8b89d9617000 R14: ffff8b89bee84000 R15: ffffa14e01d6fdb8 FS: 0000000000000000(0000) GS:ffff8b8a1f1c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f93b1fc175b CR3: 000000016100a000 CR4: 0000000000340ea0 Call Trace: shrink_node+0x1e5/0x6c0 balance_pgdat+0x32d/0x5f0 kswapd+0x1d7/0x3d0 kthread+0x11c/0x160 ret_from_fork+0x1f/0x30 This happens when parent_usage == siblings_protected. We check that usage is bigger than protected, which should imply parent_usage being bigger than siblings_protected. However, we don't read (or even update) these values atomically, and they can be out of sync as the memory state changes under us. A bit of fluctuation around the target protection isn't a big deal, but we need to handle the div0 case. Check the parent state explicitly to make sure we have a reasonable positive value for the divisor. Link: http://lkml.kernel.org/r/20200615140658.601684-1-hannes@cmpxchg.org Fixes: 8a931f801340 ("mm: memcontrol: recursive memory.low protection") Signed-off-by: Johannes Weiner Reported-by: Tejun Heo Acked-by: Michal Hocko Acked-by: Chris Down Cc: Roman Gushchin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0b38b6ad547d..5de0a9035b5f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6360,11 +6360,16 @@ static unsigned long effective_protection(unsigned long usage, * We're using unprotected memory for the weight so that if * some cgroups DO claim explicit protection, we don't protect * the same bytes twice. + * + * Check both usage and parent_usage against the respective + * protected values. One should imply the other, but they + * aren't read atomically - make sure the division is sane. */ if (!(cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT)) return ep; - - if (parent_effective > siblings_protected && usage > protected) { + if (parent_effective > siblings_protected && + parent_usage > siblings_protected && + usage > protected) { unsigned long unclaimed; unclaimed = parent_effective - siblings_protected; -- cgit v1.2.3 From 3a98990ae2150277ed34d3b248c60e68bf2244b2 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Thu, 25 Jun 2020 20:30:19 -0700 Subject: mm/memcontrol.c: add missed css_put() We should put the css reference when memory allocation failed. Link: http://lkml.kernel.org/r/20200614122653.98829-1-songmuchun@bytedance.com Fixes: f0a3a24b532d ("mm: memcg/slab: rework non-root kmem_cache lifecycle management") Signed-off-by: Muchun Song Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Qian Cai Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5de0a9035b5f..da15b686caa8 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2772,8 +2772,10 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, return; cw = kmalloc(sizeof(*cw), GFP_NOWAIT | __GFP_NOWARN); - if (!cw) + if (!cw) { + css_put(&memcg->css); return; + } cw->memcg = memcg; cw->cachep = cachep; -- cgit v1.2.3 From 03960e33187ae969187281c3aa6c308d7282c468 Mon Sep 17 00:00:00 2001 From: Chris Down Date: Thu, 25 Jun 2020 20:30:22 -0700 Subject: mm/memcontrol.c: prevent missed memory.low load tears Looks like one of these got missed when massaging in f86b810c2610 ("mm, memcg: prevent memory.low load/store tearing") with other linux-mm changes. Link: http://lkml.kernel.org/r/20200612174437.GA391453@chrisdown.name Signed-off-by: Chris Down Reported-by: Michal Koutny Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index da15b686caa8..19622328e4b5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6423,7 +6423,7 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, if (parent == root) { memcg->memory.emin = READ_ONCE(memcg->memory.min); - memcg->memory.elow = memcg->memory.low; + memcg->memory.elow = READ_ONCE(memcg->memory.low); goto out; } @@ -6435,7 +6435,8 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, atomic_long_read(&parent->memory.children_min_usage))); WRITE_ONCE(memcg->memory.elow, effective_protection(usage, parent_usage, - memcg->memory.low, READ_ONCE(parent->memory.elow), + READ_ONCE(memcg->memory.low), + READ_ONCE(parent->memory.elow), atomic_long_read(&parent->memory.children_low_usage))); out: -- cgit v1.2.3