[PATCH] sched: Fix NULL user_cpus_ptr check in dup_user_cpus_ptr()

[Waiman Long]

In general, a non-null user_cpus_ptr will remain set until the task dies.
A possible exception to this is the fact that do_set_cpus_allowed()
will clear a non-null user_cpus_ptr. To allow this possible racing
condition, we need to check for NULL user_cpus_ptr under the pi_lock
before duping the user mask.

Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()")
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/sched/core.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8df51b08bb38..f447a6285ea2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2625,7 +2625,14 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 		      int node)
 {
 	unsigned long flags;
+	cpumask_t *user_mask = NULL;
 
+	/*
+	 * If there is a concurrent sched_setaffinity(), we may miss the
+	 * newly updated user_cpus_ptr. However, a non-NULL user_cpus_ptr
+	 * is relatively unlikely and it is not worth the extra overhead
+	 * of taking the pi_lock on every fork/clone.
+	 */
 	if (!src->user_cpus_ptr)
 		return 0;
 
@@ -2633,10 +2640,22 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 	if (!dst->user_cpus_ptr)
 		return -ENOMEM;
 
-	/* Use pi_lock to protect content of user_cpus_ptr */
+	/*
+	 * Use pi_lock to protect content of user_cpus_ptr
+	 *
+	 * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
+	 * do_set_cpus_allowed().
+	 */
 	raw_spin_lock_irqsave(&src->pi_lock, flags);
-	cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+	if (src->user_cpus_ptr)
+		cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+	else
+		swap(dst->user_cpus_ptr, user_mask);
 	raw_spin_unlock_irqrestore(&src->pi_lock, flags);
+
+	if (unlikely(user_mask))
+		kfree(user_mask);
+
 	return 0;
 }
 
-- 
2.31.1