---

yaml
---
r: 127569
b: refs/heads/master
c: 28dbc4b
h: refs/heads/master
i:
  127567: 3fc64e6
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 52bc0d82100cd896213a9a25ec01c1ba87b939db
+refs/heads/master: 28dbc4b6a01fb579a9441c7b81e3d3413dc452df

trunk/include/linux/res_counter.h

@@ -43,6 +43,10 @@ struct res_counter {
 	 * the routines below consider this to be IRQ-safe
 	 */
 	spinlock_t lock;
+	/*
+	 * Parent counter, used for hierarchial resource accounting
+	 */
+	struct res_counter *parent;
 };
 
 /**
@@ -87,7 +91,7 @@ enum {
  * helpers for accounting
  */
 
-void res_counter_init(struct res_counter *counter);
+void res_counter_init(struct res_counter *counter, struct res_counter *parent);
 
 /*
  * charge - try to consume more resource.
@@ -103,7 +107,7 @@ void res_counter_init(struct res_counter *counter);
 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);
+		unsigned long val, struct res_counter **limit_fail_at);
 
 /*
  * uncharge - tell that some portion of the resource is released

trunk/kernel/res_counter.c

@@ -15,10 +15,11 @@
 #include <linux/uaccess.h>
 #include <linux/mm.h>
 
-void res_counter_init(struct res_counter *counter)
+void res_counter_init(struct res_counter *counter, struct res_counter *parent)
 {
 	spin_lock_init(&counter->lock);
 	counter->limit = (unsigned long long)LLONG_MAX;
+	counter->parent = parent;
 }
 
 int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
@@ -34,14 +35,34 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
 	return 0;
 }
 
-int res_counter_charge(struct res_counter *counter, unsigned long val)
+int res_counter_charge(struct res_counter *counter, unsigned long val,
+			struct res_counter **limit_fail_at)
 {
 	int ret;
 	unsigned long flags;
-
-	spin_lock_irqsave(&counter->lock, flags);
-	ret = res_counter_charge_locked(counter, val);
-	spin_unlock_irqrestore(&counter->lock, flags);
+	struct res_counter *c, *u;
+
+	*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);
+		spin_unlock(&c->lock);
+		if (ret < 0) {
+			*limit_fail_at = c;
+			goto undo;
+		}
+	}
+	ret = 0;
+	goto done;
+undo:
+	for (u = counter; u != c; u = u->parent) {
+		spin_lock(&u->lock);
+		res_counter_uncharge_locked(u, val);
+		spin_unlock(&u->lock);
+	}
+done:
+	local_irq_restore(flags);
 	return ret;
 }
 
@@ -56,10 +77,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
 void res_counter_uncharge(struct res_counter *counter, unsigned long val)
 {
 	unsigned long flags;
+	struct res_counter *c;
 
-	spin_lock_irqsave(&counter->lock, flags);
-	res_counter_uncharge_locked(counter, val);
-	spin_unlock_irqrestore(&counter->lock, flags);
+	local_irq_save(flags);
+	for (c = counter; c != NULL; c = c->parent) {
+		spin_lock(&c->lock);
+		res_counter_uncharge_locked(c, val);
+		spin_unlock(&c->lock);
+	}
+	local_irq_restore(flags);
 }
 
 

trunk/mm/memcontrol.c

@@ -471,6 +471,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 {
 	struct mem_cgroup *mem;
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct res_counter *fail_res;
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
@@ -499,11 +500,12 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 		int ret;
 		bool noswap = false;
 
-		ret = res_counter_charge(&mem->res, PAGE_SIZE);
+		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
 		if (likely(!ret)) {
 			if (!do_swap_account)
 				break;
-			ret = res_counter_charge(&mem->memsw, PAGE_SIZE);
+			ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
+							&fail_res);
 			if (likely(!ret))
 				break;
 			/* mem+swap counter fails */
@@ -1709,22 +1711,26 @@ static void __init enable_swap_cgroup(void)
 static struct cgroup_subsys_state *
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem, *parent;
 	int node;
 
 	mem = mem_cgroup_alloc();
 	if (!mem)
 		return ERR_PTR(-ENOMEM);
 
-	res_counter_init(&mem->res);
-	res_counter_init(&mem->memsw);
-
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
 			goto free_out;
 	/* root ? */
-	if (cont->parent == NULL)
+	if (cont->parent == NULL) {
 		enable_swap_cgroup();
+		parent = NULL;
+	} else
+		parent = mem_cgroup_from_cont(cont->parent);
+
+	res_counter_init(&mem->res, parent ? &parent->res : NULL);
+	res_counter_init(&mem->memsw, parent ? &parent->memsw : NULL);
+
 
 	return &mem->css;
 free_out: