[PATCH v4 2/2] sched: Use kfree_rcu() in do_set_cpus_allowed()

[Waiman Long]

Commit 851a723e45d1 ("sched: Always clear user_cpus_ptr in
do_set_cpus_allowed()") may call kfree() if user_cpus_ptr was previously
set. Unfortunately, some of the callers of do_set_cpus_allowed()
may have pi_lock held when calling it. So the following splats may be
printed especially when running with a PREEMPT_RT kernel:

   WARNING: possible circular locking dependency detected
   BUG: sleeping function called from invalid context

To avoid these problems, kfree_rcu() is used instead. An internal
cpumask_rcuhead union is created for the sole purpose of facilitating
the use of kfree_rcu() to free the cpumask.

Fixes: 851a723e45d1 ("sched: Always clear user_cpus_ptr in do_set_cpus_allowed()")
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 kernel/sched/core.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b93d030b9fd5..c2df236fd8c1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2604,9 +2604,19 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		.user_mask = NULL,
 		.flags     = SCA_USER,	/* clear the user requested mask */
 	};
+	union cpumask_rcuhead {
+		cpumask_t cpumask;
+		struct rcu_head rcu;
+	};
 
 	__do_set_cpus_allowed(p, &ac);
-	kfree(ac.user_mask);
+
+	/*
+	 * Because this is called with p->pi_lock held, it is not possible
+	 * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
+	 * kfree_rcu().
+	 */
+	kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
 }
 
 int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
@@ -2614,6 +2624,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 {
 	cpumask_t *user_mask;
 	unsigned long flags;
+	int size;
 
 	/*
 	 * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
@@ -2629,7 +2640,11 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
 	if (data_race(!src->user_cpus_ptr))
 		return 0;
 
-	user_mask = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
+	/*
+	 * See do_set_cpus_allowed() for the rcu_head usage.
+	 */
+	size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+	user_mask = kmalloc_node(size, GFP_KERNEL, node);
 	if (!user_mask)
 		return -ENOMEM;
 
@@ -8230,7 +8245,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	struct affinity_context ac;
 	struct cpumask *user_mask;
 	struct task_struct *p;
-	int retval;
+	int retval, size;
 
 	rcu_read_lock();
 
@@ -8263,7 +8278,11 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (retval)
 		goto out_put_task;
 
-	user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
+	/*
+	 * See do_set_cpus_allowed() for the rcu_head usage.
+	 */
+	size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+	user_mask = kmalloc(size, GFP_KERNEL);
 	if (!user_mask) {
 		retval = -ENOMEM;
 		goto out_put_task;
-- 
2.31.1