To obtain the pointer to the saved memcg position, mem_cgroup_iter() currently holds css->refcnt during memcg traversal only to put css->refcnt at the end of the routine. This isn't necessary as an rcu_read_lock is already held throughout the function. Remove css->refcnt usage during traversal by leveraging RCU. Signed-off-by: Kinsey Ho <kinseyho@xxxxxxxxxx> --- include/linux/memcontrol.h | 2 +- mm/memcontrol.c | 18 +----------------- 2 files changed, 2 insertions(+), 18 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7e2eb091049a..4cbab85e2e56 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -75,7 +75,7 @@ struct lruvec_stats_percpu; struct lruvec_stats; struct mem_cgroup_reclaim_iter { - struct mem_cgroup *position; + struct mem_cgroup __rcu *position; /* scan generation, increased every round-trip */ unsigned int generation; }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 960371788687..062bfeee799c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1019,20 +1019,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, else if (reclaim->generation != iter->generation) goto out_unlock; - while (1) { - pos = READ_ONCE(iter->position); - if (!pos || css_tryget(&pos->css)) - break; - /* - * css reference reached zero, so iter->position will - * be cleared by ->css_released. However, we should not - * rely on this happening soon, because ->css_released - * is called from a work queue, and by busy-waiting we - * might block it. So we clear iter->position right - * away. - */ - (void)cmpxchg(&iter->position, pos, NULL); - } + pos = rcu_dereference(iter->position); } else if (prev) { pos = prev; } @@ -1073,9 +1060,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, */ (void)cmpxchg(&iter->position, pos, memcg); - if (pos) - css_put(&pos->css); - if (!memcg) iter->generation++; } -- 2.45.2.1089.g2a221341d9-goog