1 files changed, 58 insertions, 27 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 02a8ea5c9963..90899837ea78 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -51,6 +51,7 @@
 #include <linux/stat.h>
 #include <linux/string.h>
 #include <linux/time.h>
+#include <linux/time64.h>
 #include <linux/backing-dev.h>
 #include <linux/sort.h>
 
@@ -68,7 +69,7 @@ struct static_key cpusets_enabled_key __read_mostly = STATIC_KEY_INIT_FALSE;
 struct fmeter {
 	int cnt;		/* unprocessed events count */
 	int val;		/* most recent output value */
-	time_t time;		/* clock (secs) when val computed */
+	time64_t time;		/* clock (secs) when val computed */
 	spinlock_t lock;	/* guards read or write of above */
 };
 
@@ -286,6 +287,8 @@ static struct cpuset top_cpuset = {
 static DEFINE_MUTEX(cpuset_mutex);
 static DEFINE_SPINLOCK(callback_lock);
 
+static struct workqueue_struct *cpuset_migrate_mm_wq;
+
 /*
  * CPU / memory hotplug is handled asynchronously.
  */
@@ -971,31 +974,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 }
 
 /*
- * cpuset_migrate_mm
- *
- *    Migrate memory region from one set of nodes to another.
- *
- *    Temporarilly set tasks mems_allowed to target nodes of migration,
- *    so that the migration code can allocate pages on these nodes.
- *
- *    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
- *    migrating memory region.
+ * Migrate memory region from one set of nodes to another.  This is
+ * performed asynchronously as it can be called from process migration path
+ * holding locks involved in process management.  All mm migrations are
+ * performed in the queued order and can be waited for by flushing
+ * cpuset_migrate_mm_wq.
  */
 
+struct cpuset_migrate_mm_work {
+	struct work_struct	work;
+	struct mm_struct	*mm;
+	nodemask_t		from;
+	nodemask_t		to;
+};
+
+static void cpuset_migrate_mm_workfn(struct work_struct *work)
+{
+	struct cpuset_migrate_mm_work *mwork =
+		container_of(work, struct cpuset_migrate_mm_work, work);
+
+	/* on a wq worker, no need to worry about %current's mems_allowed */
+	do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL);
+	mmput(mwork->mm);
+	kfree(mwork);
+}
+
 static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 							const nodemask_t *to)
 {
-	struct task_struct *tsk = current;
-
-	tsk->mems_allowed = *to;
+	struct cpuset_migrate_mm_work *mwork;
 
-	do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL);
+	mwork = kzalloc(sizeof(*mwork), GFP_KERNEL);
+	if (mwork) {
+		mwork->mm = mm;
+		mwork->from = *from;
+		mwork->to = *to;
+		INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn);
+		queue_work(cpuset_migrate_mm_wq, &mwork->work);
+	} else {
+		mmput(mm);
+	}
+}
 
-	rcu_read_lock();
-	guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed);
-	rcu_read_unlock();
+void cpuset_post_attach_flush(void)
+{
+	flush_workqueue(cpuset_migrate_mm_wq);
 }
 
 /*
@@ -1096,7 +1119,8 @@ static void update_tasks_nodemask(struct cpuset *cs)
 		mpol_rebind_mm(mm, &cs->mems_allowed);
 		if (migrate)
 			cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems);
-		mmput(mm);
+		else
+			mmput(mm);
 	}
 	css_task_iter_end(&it);
 
@@ -1374,7 +1398,7 @@ out:
  */
 
 #define FM_COEF 933		/* coefficient for half-life of 10 secs */
-#define FM_MAXTICKS ((time_t)99) /* useless computing more ticks than this */
+#define FM_MAXTICKS ((u32)99)   /* useless computing more ticks than this */
 #define FM_MAXCNT 1000000	/* limit cnt to avoid overflow */
 #define FM_SCALE 1000		/* faux fixed point scale */
 
@@ -1390,8 +1414,11 @@ static void fmeter_init(struct fmeter *fmp)
 /* Internal meter update - process cnt events and update value */
 static void fmeter_update(struct fmeter *fmp)
 {
-	time_t now = get_seconds();
-	time_t ticks = now - fmp->time;
+	time64_t now;
+	u32 ticks;
+
+	now = ktime_get_seconds();
+	ticks = now - fmp->time;
 
 	if (ticks == 0)
 		return;
@@ -1541,11 +1568,11 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 			 * @old_mems_allowed is the right nodesets that we
 			 * migrate mm from.
 			 */
-			if (is_memory_migrate(cs)) {
+			if (is_memory_migrate(cs))
 				cpuset_migrate_mm(mm, &oldcs->old_mems_allowed,
 						  &cpuset_attach_nodemask_to);
-			}
-			mmput(mm);
+			else
+				mmput(mm);
 		}
 	}
 
@@ -1710,6 +1737,7 @@ out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
+	flush_workqueue(cpuset_migrate_mm_wq);
 	return retval ?: nbytes;
 }
 
@@ -2061,7 +2089,7 @@ struct cgroup_subsys cpuset_cgrp_subsys = {
 	.attach		= cpuset_attach,
 	.bind		= cpuset_bind,
 	.legacy_cftypes	= files,
-	.early_init	= 1,
+	.early_init	= true,
 };
 
 /**
@@ -2355,6 +2383,9 @@ void __init cpuset_init_smp(void)
 	top_cpuset.effective_mems = node_states[N_MEMORY];
 
 	register_hotmemory_notifier(&cpuset_track_online_nodes_nb);
+
+	cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0);
+	BUG_ON(!cpuset_migrate_mm_wq);
 }
 
 /**