While performing the rq locking dance in dispatch_to_local_dsq(), we may
trigger the following lock imbalance condition, in particular when
multiple tasks are rapidly changing CPU affinity (i.e., running a
`stress-ng --race-sched 0`):

[   13.413579] =====================================
[   13.413660] WARNING: bad unlock balance detected!
[   13.413729] 6.13.0-virtme #15 Not tainted
[   13.413792] -------------------------------------
[   13.413859] kworker/1:1/80 is trying to release lock (&rq->__lock) at:
[   13.413954] [<ffffffff873c6c48>] dispatch_to_local_dsq+0x108/0x1a0
[   13.414111] but there are no more locks to release!
[   13.414176]
[   13.414176] other info that might help us debug this:
[   13.414258] 1 lock held by kworker/1:1/80:
[   13.414318]  #0: ffff8b66feb41698 (&rq->__lock){-.-.}-{2:2}, at: raw_spin_rq_lock_nested+0x20/0x90
[   13.414612]
[   13.414612] stack backtrace:
[   13.415255] CPU: 1 UID: 0 PID: 80 Comm: kworker/1:1 Not tainted 6.13.0-virtme #15
[   13.415505] Workqueue:  0x0 (events)
[   13.415567] Sched_ext: dsp_local_on (enabled+all), task: runnable_at=-2ms
[   13.415570] Call Trace:
[   13.415700]  <TASK>
[   13.415744]  dump_stack_lvl+0x78/0xe0
[   13.415806]  ? dispatch_to_local_dsq+0x108/0x1a0
[   13.415884]  print_unlock_imbalance_bug+0x11b/0x130
[   13.415965]  ? dispatch_to_local_dsq+0x108/0x1a0
[   13.416226]  lock_release+0x231/0x2c0
[   13.416326]  _raw_spin_unlock+0x1b/0x40
[   13.416422]  dispatch_to_local_dsq+0x108/0x1a0
[   13.416554]  flush_dispatch_buf+0x199/0x1d0
[   13.416652]  balance_one+0x194/0x370
[   13.416751]  balance_scx+0x61/0x1e0
[   13.416848]  prev_balance+0x43/0xb0
[   13.416947]  __pick_next_task+0x6b/0x1b0
[   13.417052]  __schedule+0x20d/0x1740

This happens because dispatch_to_local_dsq() is racing with
dispatch_dequeue() and, when the latter wins, we incorrectly assume that
the task has been moved to dst_rq.

Fix by properly tracking the currently locked rq.

Fixes: 4d3ca89bdd31 ("sched_ext: Refactor consume_remote_task()")
Signed-off-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/ext.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

ChangeLog v4 -> v5:
 - apply the fix without introducing any code refactoring

ChangeLog v3 -> v4:
 - small refactoring to fix an unused variable build warning on UP

ChangeLog v2 -> v3:
 - keep track of the currently locked rq in dispatch_to_local_dsq()

ChangeLog v1 -> v2:
 - more comments to clarify the race with dequeue
 - rebase to tip

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 773fa2e4d6a5..41c41a082a97 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2557,6 +2557,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 {
 	struct rq *src_rq = task_rq(p);
 	struct rq *dst_rq = container_of(dst_dsq, struct rq, scx.local_dsq);
+#ifdef CONFIG_SMP
+	struct rq *locked_rq = rq;
+#endif
 
 	/*
 	 * We're synchronized against dequeue through DISPATCHING. As @p can't
@@ -2593,8 +2596,9 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 	atomic_long_set_release(&p->scx.ops_state, SCX_OPSS_NONE);
 
 	/* switch to @src_rq lock */
-	if (rq != src_rq) {
-		raw_spin_rq_unlock(rq);
+	if (locked_rq != src_rq) {
+		raw_spin_rq_unlock(locked_rq);
+		locked_rq = src_rq;
 		raw_spin_rq_lock(src_rq);
 	}
 
@@ -2612,6 +2616,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 		} else {
 			move_remote_task_to_local_dsq(p, enq_flags,
 						      src_rq, dst_rq);
+			/* task has been moved to dst_rq, which is now locked */
+			locked_rq = dst_rq;
 		}
 
 		/* if the destination CPU is idle, wake it up */
@@ -2620,8 +2626,8 @@ static void dispatch_to_local_dsq(struct rq *rq, struct scx_dispatch_q *dst_dsq,
 	}
 
 	/* switch back to @rq lock */
-	if (rq != dst_rq) {
-		raw_spin_rq_unlock(dst_rq);
+	if (locked_rq != rq) {
+		raw_spin_rq_unlock(locked_rq);
 		raw_spin_rq_lock(rq);
 	}
 #else	/* CONFIG_SMP */
-- 
2.48.1

On Mon, Jan 27, 2025 at 11:06:16PM +0100, Andrea Righi wrote:
> While performing the rq locking dance in dispatch_to_local_dsq(), we may
> trigger the following lock imbalance condition, in particular when
> multiple tasks are rapidly changing CPU affinity (i.e., running a
> `stress-ng --race-sched 0`):
> 
> [   13.413579] =====================================
> [   13.413660] WARNING: bad unlock balance detected!
> [   13.413729] 6.13.0-virtme #15 Not tainted
> [   13.413792] -------------------------------------
> [   13.413859] kworker/1:1/80 is trying to release lock (&rq->__lock) at:
> [   13.413954] [<ffffffff873c6c48>] dispatch_to_local_dsq+0x108/0x1a0
> [   13.414111] but there are no more locks to release!
> [   13.414176]
> [   13.414176] other info that might help us debug this:
> [   13.414258] 1 lock held by kworker/1:1/80:
> [   13.414318]  #0: ffff8b66feb41698 (&rq->__lock){-.-.}-{2:2}, at: raw_spin_rq_lock_nested+0x20/0x90
> [   13.414612]
> [   13.414612] stack backtrace:
> [   13.415255] CPU: 1 UID: 0 PID: 80 Comm: kworker/1:1 Not tainted 6.13.0-virtme #15
> [   13.415505] Workqueue:  0x0 (events)
> [   13.415567] Sched_ext: dsp_local_on (enabled+all), task: runnable_at=-2ms
> [   13.415570] Call Trace:
> [   13.415700]  <TASK>
> [   13.415744]  dump_stack_lvl+0x78/0xe0
> [   13.415806]  ? dispatch_to_local_dsq+0x108/0x1a0
> [   13.415884]  print_unlock_imbalance_bug+0x11b/0x130
> [   13.415965]  ? dispatch_to_local_dsq+0x108/0x1a0
> [   13.416226]  lock_release+0x231/0x2c0
> [   13.416326]  _raw_spin_unlock+0x1b/0x40
> [   13.416422]  dispatch_to_local_dsq+0x108/0x1a0
> [   13.416554]  flush_dispatch_buf+0x199/0x1d0
> [   13.416652]  balance_one+0x194/0x370
> [   13.416751]  balance_scx+0x61/0x1e0
> [   13.416848]  prev_balance+0x43/0xb0
> [   13.416947]  __pick_next_task+0x6b/0x1b0
> [   13.417052]  __schedule+0x20d/0x1740
> 
> This happens because dispatch_to_local_dsq() is racing with
> dispatch_dequeue() and, when the latter wins, we incorrectly assume that
> the task has been moved to dst_rq.
> 
> Fix by properly tracking the currently locked rq.
> 
> Fixes: 4d3ca89bdd31 ("sched_ext: Refactor consume_remote_task()")
> Signed-off-by: Andrea Righi <arighi@nvidia.com>

Applied to sched_ext/for-6.14-fixes.

Thanks.

-- 
tejun