1 files changed, 11 insertions, 30 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index ae643412948a..df403e97b073 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -63,6 +63,7 @@
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
+DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
 
 /* See "Frequency meter" comments, below. */
@@ -1038,40 +1039,25 @@ static void cpuset_post_attach(void)
  * @tsk: the task to change
  * @newmems: new nodes that the task will be set
  *
- * In order to avoid seeing no nodes if the old and new nodes are disjoint,
- * we structure updates as setting all new allowed nodes, then clearing newly
- * disallowed ones.
+ * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed
+ * and rebind an eventual tasks' mempolicy. If the task is allocating in
+ * parallel, it might temporarily see an empty intersection, which results in
+ * a seqlock check and retry before OOM or allocation failure.
  */
 static void cpuset_change_task_nodemask(struct task_struct *tsk,
 					nodemask_t *newmems)
 {
-	bool need_loop;
-
 	task_lock(tsk);
-	/*
-	 * Determine if a loop is necessary if another thread is doing
-	 * read_mems_allowed_begin().  If at least one node remains unchanged and
-	 * tsk does not have a mempolicy, then an empty nodemask will not be
-	 * possible when mems_allowed is larger than a word.
-	 */
-	need_loop = task_has_mempolicy(tsk) ||
-			!nodes_intersects(*newmems, tsk->mems_allowed);
 
-	if (need_loop) {
-		local_irq_disable();
-		write_seqcount_begin(&tsk->mems_allowed_seq);
-	}
+	local_irq_disable();
+	write_seqcount_begin(&tsk->mems_allowed_seq);
 
 	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
-
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
+	mpol_rebind_task(tsk, newmems);
 	tsk->mems_allowed = *newmems;
 
-	if (need_loop) {
-		write_seqcount_end(&tsk->mems_allowed_seq);
-		local_irq_enable();
-	}
+	write_seqcount_end(&tsk->mems_allowed_seq);
+	local_irq_enable();
 
 	task_unlock(tsk);
 }
@@ -1906,6 +1892,7 @@ static struct cftype files[] = {
 	{
 		.name = "memory_pressure",
 		.read_u64 = cpuset_read_u64,
+		.private = FILE_MEMORY_PRESSURE,
 	},
 
 	{
@@ -2357,13 +2344,7 @@ void cpuset_update_active_cpus(void)
 	 * We're inside cpu hotplug critical region which usually nests
 	 * inside cgroup synchronization.  Bounce actual hotplug processing
 	 * to a work item to avoid reverse locking order.
-	 *
-	 * We still need to do partition_sched_domains() synchronously;
-	 * otherwise, the scheduler will get confused and put tasks to the
-	 * dead CPU.  Fall back to the default single domain.
-	 * cpuset_hotplug_workfn() will rebuild it as necessary.
 	 */
-	partition_sched_domains(1, NULL, NULL);
 	schedule_work(&cpuset_hotplug_work);
 }