hrtimer: Mark data-racy accesses to hrtimer_sleeper ->task field

The hrtimer_sleeper structure's ->task field is used as a flag to indicate
that the associated hrtimer has expired.  This means that the hrtimer
handler can be storing to this field while other code is loading from it
to check for expiry.  Note that additional races appear for hrtimers that
can be restarted, which could be argued to be a user error.  However,
that is no reason to let the compiler introduce additional confusion.

Therefore, mark data-racy accesses to the hrtimer_sleeper ->task field
using READ_ONCE() (using a new hrtimer_sleeper_task_get() access function)
and WRITE_ONCE() (using a new hrtimer_sleeper_task_set() access function).

KCSAN located this issue.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Dmitry Ilvokhin <d@ilvokhin.com>
Cc: Anna-Maria Behnsen <anna-maria@linutronix.de>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@kernel.org>
Cc: <linux-aio@kvack.org>
Cc: <linux-fsdevel@vger.kernel.org>
Cc: <io-uring@vger.kernel.org>
Cc: <netdev@vger.kernel.org>

2 files changed, 15 insertions, 7 deletions

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 29072d89e5cb..d44549c0a2c1 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -320,6 +320,14 @@ extern int schedule_hrtimeout_range_clock(ktime_t *expires,
 					  const enum hrtimer_mode mode,
 					  clockid_t clock_id);
 extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
+static inline struct task_struct *hrtimer_sleeper_task_get(struct hrtimer_sleeper *sl)
+{
+	return READ_ONCE(sl->task);
+}
+static inline void hrtimer_sleeper_task_set(struct hrtimer_sleeper *sl, struct task_struct *t)
+{
+	WRITE_ONCE(sl->task, t);
+}
 
 /* Soft interrupt function to run the hrtimer queues: */
 extern void hrtimer_run_queues(void);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 530d61257b9a..53c57d585696 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -2316,9 +2316,9 @@ void hrtimer_run_queues(void)
 static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer)
 {
 	struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer);
-	struct task_struct *task = t->task;
+	struct task_struct *task = hrtimer_sleeper_task_get(t);
 
-	t->task = NULL;
+	hrtimer_sleeper_task_set(t, NULL);
 	if (task)
 		wake_up_process(task);
 
@@ -2347,7 +2347,7 @@ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode
 
 	/* If already expired, clear the task pointer and set current state to running */
 	if (!hrtimer_start_expires_user(&sl->timer, mode)) {
-		sl->task = NULL;
+		hrtimer_sleeper_task_set(sl, NULL);
 		__set_current_state(TASK_RUNNING);
 	}
 }
@@ -2381,7 +2381,7 @@ static void __hrtimer_setup_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_
 	}
 
 	__hrtimer_setup(&sl->timer, hrtimer_wakeup, clock_id, mode);
-	sl->task = current;
+	hrtimer_sleeper_task_set(sl, current);
 }
 
 /**
@@ -2425,17 +2425,17 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod
 		set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE);
 		hrtimer_sleeper_start_expires(t, mode);
 
-		if (likely(t->task))
+		if (likely(hrtimer_sleeper_task_get(t)))
 			schedule();
 
 		hrtimer_cancel(&t->timer);
 		mode = HRTIMER_MODE_ABS;
 
-	} while (t->task && !signal_pending(current));
+	} while (hrtimer_sleeper_task_get(t) && !signal_pending(current));
 
 	__set_current_state(TASK_RUNNING);
 
-	if (!t->task)
+	if (!hrtimer_sleeper_task_get(t))
 		return 0;
 
 	restart = &current->restart_block;