memory controller: soft limit interface

Add an interface to allow get/set of soft limits.  Soft limits for memory
plus swap controller (memsw) is currently not supported.  Resource
counters have been enhanced to support soft limits and new type
RES_SOFT_LIMIT has been added.  Unlike hard limits, soft limits can be
directly set and do not need any reclaim or checks before setting them to
a newer value.

Kamezawa-San raised a question as to whether soft limit should belong to
res_counter.  Since all resources understand the basic concepts of hard
and soft limits, it is justified to add soft limits here.  Soft limits are
a generic resource usage feature, even file system quotas support soft
limits.
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/res_counter.h

@@ -34,6 +34,10 @@ struct res_counter {
 	 * the limit that usage cannot exceed
 	 */
 	unsigned long long limit;
+	/*
+	 * the limit that usage can be exceed
+	 */
+	unsigned long long soft_limit;
 	/*
 	 * the number of unsuccessful attempts to consume the resource
 	 */
@@ -87,6 +91,7 @@ enum {
 	RES_MAX_USAGE,
 	RES_LIMIT,
 	RES_FAILCNT,
+	RES_SOFT_LIMIT,
 };
 
 /*
@@ -132,6 +137,36 @@ static inline bool res_counter_limit_check_locked(struct res_counter *cnt)
 	return false;
 }
 
+static inline bool res_counter_soft_limit_check_locked(struct res_counter *cnt)
+{
+	if (cnt->usage < cnt->soft_limit)
+		return true;
+
+	return false;
+}
+
+/**
+ * Get the difference between the usage and the soft limit
+ * @cnt: The counter
+ *
+ * Returns 0 if usage is less than or equal to soft limit
+ * The difference between usage and soft limit, otherwise.
+ */
+static inline unsigned long long
+res_counter_soft_limit_excess(struct res_counter *cnt)
+{
+	unsigned long long excess;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cnt->lock, flags);
+	if (cnt->usage <= cnt->soft_limit)
+		excess = 0;
+	else
+		excess = cnt->usage - cnt->soft_limit;
+	spin_unlock_irqrestore(&cnt->lock, flags);
+	return excess;
+}
+
 /*
  * Helper function to detect if the cgroup is within it's limit or
  * not. It's currently called from cgroup_rss_prepare()
@@ -147,6 +182,17 @@ static inline bool res_counter_check_under_limit(struct res_counter *cnt)
 	return ret;
 }
 
+static inline bool res_counter_check_under_soft_limit(struct res_counter *cnt)
+{
+	bool ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cnt->lock, flags);
+	ret = res_counter_soft_limit_check_locked(cnt);
+	spin_unlock_irqrestore(&cnt->lock, flags);
+	return ret;
+}
+
 static inline void res_counter_reset_max(struct res_counter *cnt)
 {
 	unsigned long flags;
@@ -180,4 +226,16 @@ static inline int res_counter_set_limit(struct res_counter *cnt,
 	return ret;
 }
 
+static inline int
+res_counter_set_soft_limit(struct res_counter *cnt,
+				unsigned long long soft_limit)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cnt->lock, flags);
+	cnt->soft_limit = soft_limit;
+	spin_unlock_irqrestore(&cnt->lock, flags);
+	return 0;
+}
+
 #endif

kernel/res_counter.c

@@ -19,6 +19,7 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
 	spin_lock_init(&counter->lock);
 	counter->limit = RESOURCE_MAX;
+	counter->soft_limit = RESOURCE_MAX;
 	counter->parent = parent;
 }
 
@@ -101,6 +102,8 @@ res_counter_member(struct res_counter *counter, int member)
 		return &counter->limit;
 	case RES_FAILCNT:
 		return &counter->failcnt;
+	case RES_SOFT_LIMIT:
+		return &counter->soft_limit;
 	};
 
 	BUG();

mm/memcontrol.c

@@ -2123,6 +2123,20 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 		else
 			ret = mem_cgroup_resize_memsw_limit(memcg, val);
 		break;
+	case RES_SOFT_LIMIT:
+		ret = res_counter_memparse_write_strategy(buffer, &val);
+		if (ret)
+			break;
+		/*
+		 * For memsw, soft limits are hard to implement in terms
+		 * of semantics, for now, we support soft limits for
+		 * control without swap
+		 */
+		if (type == _MEM)
+			ret = res_counter_set_soft_limit(&memcg->res, val);
+		else
+			ret = -EINVAL;
+		break;
 	default:
 		ret = -EINVAL; /* should be BUG() ? */
 		break;
@@ -2375,6 +2389,12 @@ static struct cftype mem_cgroup_files[] = {
 		.write_string = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read,
 	},
+	{
+		.name = "soft_limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
+		.write_string = mem_cgroup_write,
+		.read_u64 = mem_cgroup_read,
+	},
 	{
 		.name = "failcnt",
 		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),