[v1 0/3] Support memory cgroup hotplug

@@ -63,6 +63,7 @@
 #include <linux/lockdep.h>
 #include <linux/file.h>
 #include <linux/tracehook.h>
+#include <linux/memory.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>

@@ -1342,6 +1343,10 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 {
 	return 0;
 }
+
+static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg)
+{
+}
 #endif
 
 static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,

@@ -4115,14 +4120,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
 	int tmp = node;
-	/*
-	 * This routine is called against possible nodes.
-	 * But it's BUG to call kmalloc() against offline node.
-	 *
-	 * TODO: this routine can waste much memory for nodes which will
-	 *       never be onlined. It's better to use memory hotplug callback
-	 *       function.
-	 */
+
 	if (!node_state(node, N_NORMAL_MEMORY))
 		tmp = -1;
 	pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp);

@@ -5773,6 +5771,59 @@ static int __init cgroup_memory(char *s)
 }
 __setup("cgroup.memory=", cgroup_memory);
 
+static void memcg_node_offline(int node)
+{
+	struct mem_cgroup *memcg;
+
+	if (node < 0)
+		return;
+
+	for_each_mem_cgroup(memcg) {
+		free_mem_cgroup_per_node_info(memcg, node);
+		mem_cgroup_may_update_nodemask(memcg);
+	}
+}
+
+static void memcg_node_online(int node)
+{
+	struct mem_cgroup *memcg;
+
+	if (node < 0)
+		return;
+
+	for_each_mem_cgroup(memcg) {
+		alloc_mem_cgroup_per_node_info(memcg, node);
+		mem_cgroup_may_update_nodemask(memcg);
+	}
+}
+
+static int memcg_memory_hotplug_callback(struct notifier_block *self,
+					unsigned long action, void *arg)
+{
+	struct memory_notify *marg = arg;
+	int node = marg->status_change_nid;
+
+	switch (action) {
+	case MEM_GOING_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+		memcg_node_offline(node);
+		break;
+	case MEM_GOING_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+		memcg_node_online(node);
+		break;
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block memcg_memory_hotplug_nb __meminitdata = {
+	.notifier_call = memcg_memory_hotplug_callback,
+	.priority = IPC_CALLBACK_PRI,
+};
+
 /*
  * subsys_initcall() for memory controller.
  *

@@ -5797,6 +5848,7 @@ static int __init mem_cgroup_init(void)
 #endif
 
 	hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
+	register_hotmemory_notifier(&memcg_memory_hotplug_nb);
 
 	for_each_possible_cpu(cpu)
 		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,

@@ -497,7 +497,7 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
 	struct mem_cgroup_per_node *mz;
 	int nid;
 
-	for_each_node(nid) {
+	for_each_online_node(nid) {
 		mz = mem_cgroup_nodeinfo(memcg, nid);
 		mctz = soft_limit_tree_node(nid);
 		mem_cgroup_remove_exceeded(mz, mctz);

@@ -895,7 +895,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	int i;
 
 	while ((memcg = parent_mem_cgroup(memcg))) {
-		for_each_node(nid) {
+		for_each_online_node(nid) {
 			mz = mem_cgroup_nodeinfo(memcg, nid);
 			for (i = 0; i <= DEF_PRIORITY; i++) {
 				iter = &mz->iter[i];

@@ -4146,7 +4146,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 	int node;
 
 	memcg_wb_domain_exit(memcg);
-	for_each_node(node)
+	for_each_online_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->stat);
 	kfree(memcg);

@@ -4175,7 +4175,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (!memcg->stat)
 		goto fail;
 
-	for_each_node(node)
+	for_each_online_node(node)
 		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
 

@@ -5774,11 +5774,21 @@ __setup("cgroup.memory=", cgroup_memory);
 static void memcg_node_offline(int node)
 {
 	struct mem_cgroup *memcg;
+	struct mem_cgroup_tree_per_node *rtpn;
+	struct mem_cgroup_tree_per_node *mctz;
+	struct mem_cgroup_per_node *mz;
 
 	if (node < 0)
 		return;
 
+	rtpn = soft_limit_tree.rb_tree_per_node[node];
+	kfree(rtpn);
+
 	for_each_mem_cgroup(memcg) {
+		mz = mem_cgroup_nodeinfo(memcg, node);
+		mctz = soft_limit_tree_node(node);
+		mem_cgroup_remove_exceeded(mz, mctz);
+
 		free_mem_cgroup_per_node_info(memcg, node);
 		mem_cgroup_may_update_nodemask(memcg);
 	}

@@ -5787,10 +5797,18 @@ static void memcg_node_offline(int node)
 static void memcg_node_online(int node)
 {
 	struct mem_cgroup *memcg;
+	struct mem_cgroup_tree_per_node *rtpn;
 
 	if (node < 0)
 		return;
 
+	rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL,
+			    node_online(node) ? node : NUMA_NO_NODE);
+
+	rtpn->rb_root = RB_ROOT;
+	spin_lock_init(&rtpn->lock);
+	soft_limit_tree.rb_tree_per_node[node] = rtpn;
+
 	for_each_mem_cgroup(memcg) {
 		alloc_mem_cgroup_per_node_info(memcg, node);
 		mem_cgroup_may_update_nodemask(memcg);

@@ -5854,7 +5872,7 @@ static int __init mem_cgroup_init(void)
 		INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work,
 			  drain_local_stock);
 
-	for_each_node(node) {
+	for_each_online_node(node) {
 		struct mem_cgroup_tree_per_node *rtpn;
 
 		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL,

@@ -916,13 +916,6 @@ void __init initmem_init(void)
 
 	memblock_dump_all();
 
-	/*
-	 * Reduce the possible NUMA nodes to the online NUMA nodes,
-	 * since we do not support node hotplug. This ensures that  we
-	 * lower the maximum NUMA node ID to what is actually present.
-	 */
-	nodes_and(node_possible_map, node_possible_map, node_online_map);
-
 	for_each_online_node(nid) {
 		unsigned long start_pfn, end_pfn;