[PATCH 6/7] sched: Simplify set_affinity_pending refcounts

[Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>]

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

commit 50caf9c14b1498c90cf808dbba2ca29bd32ccba4 upstream.

Now that we have set_affinity_pending::stop_pending to indicate if a
stopper is in progress, and we have the guarantee that if that stopper
exists, it will (eventually) complete our @pending we can simplify the
refcount scheme by no longer counting the stopper thread.

Fixes: 6d337eab041d ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Cc: stable@xxxxxxxxxx
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Reviewed-by: Valentin Schneider <valentin.schneider@xxxxxxx>
Link: https://lkml.kernel.org/r/20210224131355.724130207@xxxxxxxxxxxxx
Signed-off-by: Paul Gortmaker <paul.gortmaker@xxxxxxxxxxxxx>
---
 kernel/sched/core.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 20588a59300d..35d8b80d7cb8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1898,6 +1898,10 @@ struct migration_arg {
 	struct set_affinity_pending	*pending;
 };
 
+/*
+ * @refs: number of wait_for_completion()
+ * @stop_pending: is @stop_work in use
+ */
 struct set_affinity_pending {
 	refcount_t		refs;
 	unsigned int		stop_pending;
@@ -2033,10 +2037,6 @@ static int migration_cpu_stop(void *data)
 	if (complete)
 		complete_all(&pending->done);
 
-	/* For pending->{arg,stop_work} */
-	if (pending && refcount_dec_and_test(&pending->refs))
-		wake_up_var(&pending->refs);
-
 	return 0;
 }
 
@@ -2235,12 +2235,16 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 			push_task = get_task_struct(p);
 		}
 
+		/*
+		 * If there are pending waiters, but no pending stop_work,
+		 * then complete now.
+		 */
 		pending = p->migration_pending;
-		if (pending) {
-			refcount_inc(&pending->refs);
+		if (pending && !pending->stop_pending) {
 			p->migration_pending = NULL;
 			complete = true;
 		}
+
 		task_rq_unlock(rq, p, rf);
 
 		if (push_task) {
@@ -2249,7 +2253,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		}
 
 		if (complete)
-			goto do_complete;
+			complete_all(&pending->done);
 
 		return 0;
 	}
@@ -2300,9 +2304,9 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		if (!stop_pending)
 			pending->stop_pending = true;
 
-		refcount_inc(&pending->refs); /* pending->{arg,stop_work} */
 		if (flags & SCA_MIGRATE_ENABLE)
 			p->migration_flags &= ~MDF_PUSH;
+
 		task_rq_unlock(rq, p, rf);
 
 		if (!stop_pending) {
@@ -2318,12 +2322,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 			if (task_on_rq_queued(p))
 				rq = move_queued_task(rq, rf, p, dest_cpu);
 
-			p->migration_pending = NULL;
-			complete = true;
+			if (!pending->stop_pending) {
+				p->migration_pending = NULL;
+				complete = true;
+			}
 		}
 		task_rq_unlock(rq, p, rf);
 
-do_complete:
 		if (complete)
 			complete_all(&pending->done);
 	}
@@ -2331,7 +2336,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 	wait_for_completion(&pending->done);
 
 	if (refcount_dec_and_test(&pending->refs))
-		wake_up_var(&pending->refs);
+		wake_up_var(&pending->refs); /* No UaF, just an address */
 
 	/*
 	 * Block the original owner of &pending until all subsequent callers
@@ -2339,6 +2344,9 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 	 */
 	wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs));
 
+	/* ARGH */
+	WARN_ON_ONCE(my_pending.stop_pending);
+
 	return 0;
 }
 
-- 
2.25.1