memcg: limit change shrink usage

Shrinking memory usage at limit change.

[akpm@linux-foundation.org: coding-style fixes]
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 45 insertions, 6 deletions

diff --git a/Documentation/controllers/memory.txt b/Documentation/controllers/memory.txt
index 866b9cd..9b53d58 100644
--- a/Documentation/controllers/memory.txt
+++ b/Documentation/controllers/memory.txt
@@ -242,8 +242,7 @@ rmdir() if there are no tasks.
 1. Add support for accounting huge pages (as a separate controller)
 2. Make per-cgroup scanner reclaim not-shared pages first
 3. Teach controller to account for shared-pages
-4. Start reclamation when the limit is lowered
-5. Start reclamation in the background when the limit is
+4. Start reclamation in the background when the limit is
    not yet hit but the usage is getting closer
 
 Summary
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0c03564..fba566c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -812,6 +812,30 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 	return 0;
 }
 
+int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
+{
+
+	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	int progress;
+	int ret = 0;
+
+	while (res_counter_set_limit(&memcg->res, val)) {
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+		if (!retry_count) {
+			ret = -EBUSY;
+			break;
+		}
+		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
+		if (!progress)
+			retry_count--;
+	}
+	return ret;
+}
+
+
 /*
  * This routine traverse page_cgroup in given list and drop them all.
  * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
@@ -896,13 +920,29 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 	return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
 				    cft->private);
 }
-
+/*
+ * The user of this function is...
+ * RES_LIMIT.
+ */
 static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 			    const char *buffer)
 {
-	return res_counter_write(&mem_cgroup_from_cont(cont)->res,
-				 cft->private, buffer,
-				 res_counter_memparse_write_strategy);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	unsigned long long val;
+	int ret;
+
+	switch (cft->private) {
+	case RES_LIMIT:
+		/* This function does all necessary parse...reuse it */
+		ret = res_counter_memparse_write_strategy(buffer, &val);
+		if (!ret)
+			ret = mem_cgroup_resize_limit(memcg, val);
+		break;
+	default:
+		ret = -EINVAL; /* should be BUG() ? */
+		break;
+	}
+	return ret;
 }
 
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)