From: Tejun Heo <tj@kernel.org>
Date: Mon, 10 Feb 2025 20:45:43 +0000 (-1000)
Subject: Merge branch 'for-6.14-fixes' into for-6.15
X-Git-Tag: io_uring-6.15-20250403~149^2~23
X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=78e4690de4227393c7cc260739ba94d10ca1df47;p=linux-block.git

Merge branch 'for-6.14-fixes' into for-6.15

Pull to receive f3f08c3acfb8 ("sched_ext: Fix incorrect assumption about
migration disabled tasks in task_can_run_on_remote_rq()") which conflicts
with 26176116d931 ("sched_ext: Count SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE in
the right spot") in for-6.15.
---

78e4690de4227393c7cc260739ba94d10ca1df47
diff --cc kernel/sched/ext.c
index 90a66a2a43d5,54edd0e2132a..98d5f2f68f38
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@@ -2446,6 -2343,25 +2446,25 @@@ static bool task_can_run_on_remote_rq(s
  
  	SCHED_WARN_ON(task_cpu(p) == cpu);
  
+ 	/*
+ 	 * If @p has migration disabled, @p->cpus_ptr is updated to contain only
+ 	 * the pinned CPU in migrate_disable_switch() while @p is being switched
+ 	 * out. However, put_prev_task_scx() is called before @p->cpus_ptr is
+ 	 * updated and thus another CPU may see @p on a DSQ inbetween leading to
+ 	 * @p passing the below task_allowed_on_cpu() check while migration is
+ 	 * disabled.
+ 	 *
+ 	 * Test the migration disabled state first as the race window is narrow
+ 	 * and the BPF scheduler failing to check migration disabled state can
+ 	 * easily be masked if task_allowed_on_cpu() is done first.
+ 	 */
+ 	if (unlikely(is_migration_disabled(p))) {
 -		if (trigger_error)
++		if (enforce)
+ 			scx_ops_error("SCX_DSQ_LOCAL[_ON] cannot move migration disabled %s[%d] from CPU %d to %d",
+ 				      p->comm, p->pid, task_cpu(p), cpu);
+ 		return false;
+ 	}
+ 
  	/*
  	 * We don't require the BPF scheduler to avoid dispatching to offline
  	 * CPUs mostly for convenience but also because CPUs can go offline
@@@ -2453,23 -2369,14 +2472,17 @@@
  	 * picked CPU is outside the allowed mask.
  	 */
  	if (!task_allowed_on_cpu(p, cpu)) {
 -		if (trigger_error)
 +		if (enforce)
- 			scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]",
- 				      cpu_of(rq), p->comm, p->pid);
+ 			scx_ops_error("SCX_DSQ_LOCAL[_ON] target CPU %d not allowed for %s[%d]",
+ 				      cpu, p->comm, p->pid);
  		return false;
  	}
  
- 	/*
- 	 * If @p has migration disabled, @p->cpus_ptr only contains its current
- 	 * CPU and the above task_allowed_on_cpu() test should have failed.
- 	 */
- 	SCHED_WARN_ON(is_migration_disabled(p));
- 
 -	if (!scx_rq_online(rq))
 +	if (!scx_rq_online(rq)) {
 +		if (enforce)
 +			__scx_add_event(SCX_EV_DISPATCH_LOCAL_DSQ_OFFLINE, 1);
  		return false;
 +	}
  
  	return true;
  }