cpuset: fix the problem that cpuset_mem_spread_node() returns an offline node

cpuset_mem_spread_node() returns an offline node, and causes an oops.

This patch fixes it by initializing task->mems_allowed to
node_states[N_HIGH_MEMORY], and updating task->mems_allowed when doing
memory hotplug.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Acked-by: David Rientjes <rientjes@google.com>
Reported-by: Nick Piggin <npiggin@suse.de>
Tested-by: Nick Piggin <npiggin@suse.de>
Cc: Paul Menage <menage@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

init/main.c

diff --git a/init/main.c b/init/main.c
index a1ab78c..cbead27 100644
--- a/init/main.c
+++ b/init/main.c
@@ -858,7 +858,7 @@
 	/*
 	 * init can allocate pages on any node
 	 */
-	set_mems_allowed(node_possible_map);
+	set_mems_allowed(node_states[N_HIGH_MEMORY]);
 	/*
 	 * init can run on any cpu.
 	 */

kernel/cpuset.c

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ba401fa..5d38bd7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -920,9 +920,6 @@
  *    call to guarantee_online_mems(), as we know no one is changing
  *    our task's cpuset.
  *
- *    Hold callback_mutex around the two modifications of our tasks
- *    mems_allowed to synchronize with cpuset_mems_allowed().
- *
  *    While the mm_struct we are migrating is typically from some
  *    other task, the task_struct mems_allowed that we are hacking
  *    is for our current task, which must allocate new pages for that
@@ -1391,11 +1388,10 @@
 
 	if (cs == &top_cpuset) {
 		cpumask_copy(cpus_attach, cpu_possible_mask);
-		to = node_possible_map;
 	} else {
 		guarantee_online_cpus(cs, cpus_attach);
-		guarantee_online_mems(cs, &to);
 	}
+	guarantee_online_mems(cs, &to);
 
 	/* do per-task migration stuff possibly for each in the threadgroup */
 	cpuset_attach_task(tsk, &to, cs);
@@ -2090,15 +2086,23 @@
 static int cpuset_track_online_nodes(struct notifier_block *self,
 				unsigned long action, void *arg)
 {
+	nodemask_t oldmems;
+
 	cgroup_lock();
 	switch (action) {
 	case MEM_ONLINE:
-	case MEM_OFFLINE:
+		oldmems = top_cpuset.mems_allowed;
 		mutex_lock(&callback_mutex);
 		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 		mutex_unlock(&callback_mutex);
-		if (action == MEM_OFFLINE)
-			scan_for_empty_cpusets(&top_cpuset);
+		update_tasks_nodemask(&top_cpuset, &oldmems, NULL);
+		break;
+	case MEM_OFFLINE:
+		/*
+		 * needn't update top_cpuset.mems_allowed explicitly because
+		 * scan_for_empty_cpusets() will update it.
+		 */
+		scan_for_empty_cpusets(&top_cpuset);
 		break;
 	default:
 		break;

kernel/kthread.c

diff --git a/kernel/kthread.c b/kernel/kthread.c
index 82ed0ea..83911c78 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -219,7 +219,7 @@
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
 	set_cpus_allowed_ptr(tsk, cpu_all_mask);
-	set_mems_allowed(node_possible_map);
+	set_mems_allowed(node_states[N_HIGH_MEMORY]);
 
 	current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG;