mm/memcontrol.c: try harder to decrease [memory,memsw].limit_in_bytes

aryabinin · torvalds · commit 1ab5c05695bd · 2018-01-31T17:18:40.000-08:00
mem_cgroup_resize_[memsw]_limit() tries to free only 32 (SWAP_CLUSTER_MAX) pages on each iteration. This makes it practically impossible to decrease limit of memory cgroup. Tasks could easily allocate back 32 pages, so we can't reduce memory usage, and once retry_count reaches zero we return -EBUSY. Easy to reproduce the problem by running the following commands: mkdir /sys/fs/cgroup/memory/test echo $$ >> /sys/fs/cgroup/memory/test/tasks cat big_file > /dev/null & sleep 1 && echo $((100*1024*1024)) > /sys/fs/cgroup/memory/test/memory.limit_in_bytes -bash: echo: write error: Device or resource busy Instead of relying on retry_count, keep retrying the reclaim until the desired limit is reached or fail if the reclaim doesn't make any progress or a signal is pending. Link: http://lkml.kernel.org/r/20180119132544.19569-1-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com> Acked-by: Michal Hocko <mhocko@suse.com> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Shakeel Butt <shakeelb@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
@@ -1176,20 +1176,6 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	}
 }
 
-/*
- * This function returns the number of memcg under hierarchy tree. Returns
- * 1(self count) if no children.
- */
-static int mem_cgroup_count_children(struct mem_cgroup *memcg)
-{
-	int num = 0;
-	struct mem_cgroup *iter;
-
-	for_each_mem_cgroup_tree(iter, memcg)
-		num++;
-	return num;
-}
-
 /*
  * Return the memory (and swap, if configured) limit for a memcg.
  */
@@ -2463,24 +2449,11 @@ static DEFINE_MUTEX(memcg_limit_mutex);
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 				   unsigned long limit, bool memsw)
 {
-	unsigned long curusage;
-	unsigned long oldusage;
 	bool enlarge = false;
-	int retry_count;
 	int ret;
 	bool limits_invariant;
 	struct page_counter *counter = memsw ? &memcg->memsw : &memcg->memory;
 
-	/*
-	 * For keeping hierarchical_reclaim simple, how long we should retry
-	 * is depends on callers. We set our retry-count to be function
-	 * of # of children which we should visit in this loop.
-	 */
-	retry_count = MEM_CGROUP_RECLAIM_RETRIES *
-		      mem_cgroup_count_children(memcg);
-
-	oldusage = page_counter_read(counter);
-
 	do {
 		if (signal_pending(current)) {
 			ret = -EINTR;
@@ -2507,15 +2480,12 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, !memsw);
-
-		curusage = page_counter_read(counter);
-		/* Usage is reduced ? */
-		if (curusage >= oldusage)
-			retry_count--;
-		else
-			oldusage = curusage;
-	} while (retry_count);
+		if (!try_to_free_mem_cgroup_pages(memcg, 1,
+					GFP_KERNEL, !memsw)) {
+			ret = -EBUSY;
+			break;
+		}
+	} while (true);
 
 	if (!ret && enlarge)
 		memcg_oom_recover(memcg);
