Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
Date:   Fri, 22 Sep 2023 16:05:35 -0700
In-Reply-To: <20230922230535.296350-1-joshdon@google.com>
Mime-Version: 1.0
References: <20230922230535.296350-1-joshdon@google.com>
Message-ID: <20230922230535.296350-2-joshdon@google.com>
Subject: [PATCH 2/2] sched: fix warning in bandwidth distribution
From:   Josh Don <joshdon@google.com>
To:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>
Cc:     Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        linux-kernel@vger.kernel.org, Josh Don <joshdon@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

We've observed the following warning being hit in
distribute_cfs_runtime():
	SCHED_WARN_ON(cfs_rq->runtime_remaining > 0)

We have the following race:

- cpu0: running bandwidth distribution (distribute_cfs_runtime).
  Inspects the local cfs_rq and makes its runtime_remaining positive.
  However, we defer unthrottling the local cfs_rq until after
  considering all remote cfs_rq's.
- cpu1: starts running bandwidth distribution from the slack timer. When
  it finds the cfs_rq for cpu 0 on the throttled list, it observers the
  that the cfs_rq is throttled, yet is not on the CSD list, and has a
  positive runtime_remaining, thus triggering the warning in
  distribute_cfs_runtime.

To fix this, we can rework the local unthrottling logic to put the local
cfs_rq on a local list, so that any future bandwidth distributions will
realize that the cfs_rq is about to be unthrottled.

Signed-off-by: Josh Don <joshdon@google.com>
---
 kernel/sched/fair.c | 36 +++++++++++++++++++++++++-----------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8f4e63fc8900..de002dab28cf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5743,13 +5743,13 @@ static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
 
 static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 {
-	struct cfs_rq *local_unthrottle = NULL;
 	int this_cpu = smp_processor_id();
 	u64 runtime, remaining = 1;
 	bool throttled = false;
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *tmp;
 	struct rq_flags rf;
 	struct rq *rq;
+	LIST_HEAD(local_unthrottle);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
@@ -5784,11 +5784,17 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 
 		/* we check whether we're throttled above */
 		if (cfs_rq->runtime_remaining > 0) {
-			if (cpu_of(rq) != this_cpu ||
-			    SCHED_WARN_ON(local_unthrottle))
+			if (cpu_of(rq) != this_cpu) {
 				unthrottle_cfs_rq_async(cfs_rq);
-			else
-				local_unthrottle = cfs_rq;
+			} else {
+				/*
+				 * We currently only expect to be unthrottling
+				 * a single cfs_rq locally.
+				 */
+				SCHED_WARN_ON(!list_empty(&local_unthrottle));
+				list_add_tail(&cfs_rq->throttled_csd_list,
+					      &local_unthrottle);
+			}
 		} else {
 			throttled = true;
 		}
@@ -5796,15 +5802,23 @@ static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
 next:
 		rq_unlock_irqrestore(rq, &rf);
 	}
-	rcu_read_unlock();
 
-	if (local_unthrottle) {
-		rq = cpu_rq(this_cpu);
+	list_for_each_entry_safe(cfs_rq, tmp, &local_unthrottle,
+				 throttled_csd_list) {
+		struct rq *rq = rq_of(cfs_rq);
+
 		rq_lock_irqsave(rq, &rf);
-		if (cfs_rq_throttled(local_unthrottle))
-			unthrottle_cfs_rq(local_unthrottle);
+
+		list_del_init(&cfs_rq->throttled_csd_list);
+
+		if (cfs_rq_throttled(cfs_rq))
+			unthrottle_cfs_rq(cfs_rq);
+
 		rq_unlock_irqrestore(rq, &rf);
 	}
+	SCHED_WARN_ON(!list_empty(&local_unthrottle));
+
+	rcu_read_unlock();
 
 	return throttled;
 }
-- 
2.42.0.515.g380fc7ccd1-goog