Organize cgroups over soft limit in a RB-Tree

Introduce an RB-Tree for storing memory cgroups that are over their soft
limit.  The overall goal is to

1. Add a memory cgroup to the RB-Tree when the soft limit is exceeded.
   We are careful about updates, updates take place only after a particular
   time interval has passed
2. We remove the node from the RB-Tree when the usage goes below the soft
   limit

The next set of patches will exploit the RB-Tree to get the group that is
over its soft limit by the largest amount and reclaim from it, when we
face memory contention.
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: 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>

include/linux/res_counter.h

@@ -114,7 +114,8 @@ void res_counter_init(struct res_counter *counter, struct res_counter *parent);
 int __must_check res_counter_charge_locked(struct res_counter *counter,
 		unsigned long val);
 int __must_check res_counter_charge(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
+		unsigned long val, struct res_counter **limit_fail_at,
+		struct res_counter **soft_limit_at);
 
 /*
  * uncharge - tell that some portion of the resource is released
@@ -127,7 +128,8 @@ int __must_check res_counter_charge(struct res_counter *counter,
  */
 
 void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
-void res_counter_uncharge(struct res_counter *counter, unsigned long val);
+void res_counter_uncharge(struct res_counter *counter, unsigned long val,
+				bool *was_soft_limit_excess);
 
 static inline bool res_counter_limit_check_locked(struct res_counter *cnt)
 {

kernel/res_counter.c

@@ -37,17 +37,27 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
 }
 
 int res_counter_charge(struct res_counter *counter, unsigned long val,
-			struct res_counter **limit_fail_at)
+			struct res_counter **limit_fail_at,
+			struct res_counter **soft_limit_fail_at)
 {
 	int ret;
 	unsigned long flags;
 	struct res_counter *c, *u;
 
 	*limit_fail_at = NULL;
+	if (soft_limit_fail_at)
+		*soft_limit_fail_at = NULL;
 	local_irq_save(flags);
 	for (c = counter; c != NULL; c = c->parent) {
 		spin_lock(&c->lock);
 		ret = res_counter_charge_locked(c, val);
+		/*
+		 * With soft limits, we return the highest ancestor
+		 * that exceeds its soft limit
+		 */
+		if (soft_limit_fail_at &&
+			!res_counter_soft_limit_check_locked(c))
+			*soft_limit_fail_at = c;
 		spin_unlock(&c->lock);
 		if (ret < 0) {
 			*limit_fail_at = c;
@@ -75,7 +85,8 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
 	counter->usage -= val;
 }
 
-void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+void res_counter_uncharge(struct res_counter *counter, unsigned long val,
+				bool *was_soft_limit_excess)
 {
 	unsigned long flags;
 	struct res_counter *c;
@@ -83,6 +94,9 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val)
 	local_irq_save(flags);
 	for (c = counter; c != NULL; c = c->parent) {
 		spin_lock(&c->lock);
+		if (was_soft_limit_excess)
+			*was_soft_limit_excess =
+				!res_counter_soft_limit_check_locked(c);
 		res_counter_uncharge_locked(c, val);
 		spin_unlock(&c->lock);
 	}