Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:5 as permitted sender) client-ip=2620:137:e000::3:5;
From:   Waiman Long <longman@redhat.com>
To:     Tejun Heo <tj@kernel.org>, Zefan Li <lizefan.x@bytedance.com>,
        Johannes Weiner <hannes@cmpxchg.org>
Cc:     linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
        Juri Lelli <juri.lelli@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>,
        Qais Yousef <qyousef@layalina.io>, Hao Luo <haoluo@google.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Waiman Long <longman@redhat.com>,
        Xia Fukun <xiafukun@huawei.com>
Subject: [PATCH] cgroup/cpuset: Change nr_deadline_tasks to an atomic_t value
Date:   Mon,  9 Oct 2023 15:15:15 -0400
Message-Id: <20231009191515.3262292-1-longman@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The nr_deadline_tasks field in cpuset structure was introduced by
commit 6c24849f5515 ("sched/cpuset: Keep track of SCHED_DEADLINE task
in cpusets"). Unlike nr_migrate_dl_tasks which is only modified under
cpuset_mutex, nr_deadline_tasks can be updated in various contexts
under different locks. As a result, data races may happen that cause
incorrect value to be stored in nr_deadline_tasks leading to incorrect
exit from dl_update_tasks_root_domain().  Fix that data race problem
by making nr_deadline_tasks an atomic_t value.

Fixes: 6c24849f5515 ("sched/cpuset: Keep track of SCHED_DEADLINE task in cpusets")
Reported-by: Xia Fukun <xiafukun@huawei.com>
Signed-off-by: Waiman Long <longman@redhat.com>
---
 kernel/cgroup/cpuset.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 58ec88efa4f8..3f3da468f058 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -174,7 +174,7 @@ struct cpuset {
 	 * number of SCHED_DEADLINE tasks attached to this cpuset, so that we
 	 * know when to rebuild associated root domain bandwidth information.
 	 */
-	int nr_deadline_tasks;
+	atomic_t nr_deadline_tasks;
 	int nr_migrate_dl_tasks;
 	u64 sum_migrate_dl_bw;
 
@@ -234,14 +234,14 @@ void inc_dl_tasks_cs(struct task_struct *p)
 {
 	struct cpuset *cs = task_cs(p);
 
-	cs->nr_deadline_tasks++;
+	atomic_inc(&cs->nr_deadline_tasks);
 }
 
 void dec_dl_tasks_cs(struct task_struct *p)
 {
 	struct cpuset *cs = task_cs(p);
 
-	cs->nr_deadline_tasks--;
+	atomic_dec(&cs->nr_deadline_tasks);
 }
 
 /* bits in struct cpuset flags field */
@@ -1071,7 +1071,7 @@ static void dl_update_tasks_root_domain(struct cpuset *cs)
 	struct css_task_iter it;
 	struct task_struct *task;
 
-	if (cs->nr_deadline_tasks == 0)
+	if (atomic_read(&cs->nr_deadline_tasks) == 0)
 		return;
 
 	css_task_iter_start(&cs->css, 0, &it);
@@ -2721,8 +2721,8 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cs->old_mems_allowed = cpuset_attach_nodemask_to;
 
 	if (cs->nr_migrate_dl_tasks) {
-		cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks;
-		oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks;
+		atomic_add(cs->nr_migrate_dl_tasks, &cs->nr_deadline_tasks);
+		atomic_sub(cs->nr_migrate_dl_tasks, &oldcs->nr_deadline_tasks);
 		reset_migrate_dl_data(cs);
 	}
 
-- 
2.39.3