memcg: allow kmem limit to be resized down
The userspace memory limit can be freely resized down. Upon attempt,
reclaim will be called to flush the pages away until we either reach the
limit we want or give up.
It wasn't possible so far with the kmem limit, since we had no way to
shrink the kmem buffers other than using the big hammer of shrink_slab,
that effectively frees data around the whole system.
The situation flips now that we have a per-memcg shrinker
infrastructure. We will proceed analogously to our user memory
counterpart and try to shrink our buffers until we either reach the
limit we want or give up.
Signed-off-by: Glauber Costa <glommer@openvz.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4ff9318..6d88f65 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5561,10 +5561,40 @@
 }
 #endif
 
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * This is slightly different than res or memsw reclaim.  We already have
+ * vmscan behind us to deal with driving the reclaim, so we can basically keep
+ * trying until all buffers that can be flushed are flushed. We have a very
+ * clear signal about it, in the form of the return value of
+ * try_to_free_mem_cgroup_kmem.
+ */
+static int mem_cgroup_resize_kmem_limit(struct mem_cgroup *memcg,
+					unsigned long long val)
+{
+	int ret = -EBUSY;
+
+	for (;;) {
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		ret = res_counter_set_limit(&memcg->kmem, val);
+		if (!ret)
+			break;
+
+		/* Can't free anything, pointless to continue */
+		if (!try_to_free_mem_cgroup_kmem(memcg, GFP_KERNEL))
+			break;
+	}
+
+	return ret;
+}
+
 static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
 {
 	int ret = -EINVAL;
-#ifdef CONFIG_MEMCG_KMEM
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	/*
 	 * For simplicity, we won't allow this to be disabled.  It also can't
@@ -5607,16 +5637,15 @@
 		 * need to reference count the memcg because of that.
 		 */
 		mem_cgroup_get(memcg);
-	} else
-		ret = res_counter_set_limit(&memcg->kmem, val);
+	} else {
+		ret = mem_cgroup_resize_kmem_limit(memcg, val);
+	}
 out:
 	mutex_unlock(&set_limit_mutex);
 	mutex_unlock(&memcg_create_mutex);
-#endif
 	return ret;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
 static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 {
 	int ret = 0;
@@ -5655,6 +5684,11 @@
 out:
 	return ret;
 }
+#else
+static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_MEMCG_KMEM */
 
 /*