From: Muchun Song <songmuc...@bytedance.com> [ Upstream commit eefbfa7fd678805b38a46293e78543f98f353d3e ]
The rcu_read_lock/unlock only can guarantee that the memcg will not be freed, but it cannot guarantee the success of css_get to memcg. If the whole process of a cgroup offlining is completed between reading a objcg->memcg pointer and bumping the css reference on another CPU, and there are exactly 0 external references to this memory cgroup (how we get to the obj_cgroup_charge() then?), css_get() can change the ref counter from 0 back to 1. Link: https://lkml.kernel.org/r/20201028035013.99711-2-songmuc...@bytedance.com Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API") Signed-off-by: Muchun Song <songmuc...@bytedance.com> Acked-by: Roman Gushchin <g...@fb.com> Reviewed-by: Shakeel Butt <shake...@google.com> Cc: Johannes Weiner <han...@cmpxchg.org> Cc: Michal Hocko <mho...@kernel.org> Cc: Vladimir Davydov <vdavydov....@gmail.com> Cc: Joonsoo Kim <iamjoonsoo....@lge.com> Cc: Yafang Shao <laoar.s...@gmail.com> Cc: Chris Down <ch...@chrisdown.name> Cc: Christian Brauner <christian.brau...@ubuntu.com> Signed-off-by: Andrew Morton <a...@linux-foundation.org> Signed-off-by: Linus Torvalds <torva...@linux-foundation.org> Signed-off-by: Sasha Levin <sas...@kernel.org> --- mm/memcontrol.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 74b85077f89ad..a717728cc7b4a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3247,8 +3247,10 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) * independently later. */ rcu_read_lock(); +retry: memcg = obj_cgroup_memcg(objcg); - css_get(&memcg->css); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; rcu_read_unlock(); nr_pages = size >> PAGE_SHIFT; -- 2.27.0
