With the use of wake_q, we can do task wakeups without holding the
wait_lock. There is one exception in the rwsem code, though. It is
when the writer in the slowpath detects that there are waiters ahead
but the rwsem is not held by a writer. This can lead to a long wait_lock
hold time especially when a large number of readers are to be woken up.
Remediate this situation by releasing the wait_lock before waking up
tasks and re-acquiring it afterward.
Suggested-by: Peter Zijlstra <pet...@infradead.org>
Signed-off-by: Waiman Long <long...@redhat.com>
---
include/linux/sched/wake_q.h | 5 +++++
kernel/locking/rwsem.c | 30 +++++++++++++++++++-----------
2 files changed, 24 insertions(+), 11 deletions(-)
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index ad826d2a4557..26a2013ac39c 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -51,6 +51,11 @@ static inline void wake_q_init(struct wake_q_head *head)
head->lastp = &head->first;
}
+static inline bool wake_q_empty(struct wake_q_head *head)
+{
+ return head->first == WAKE_Q_TAIL;
+}
+
extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct
*task);
extern void wake_up_q(struct wake_q_head *head);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index dd90884a80b8..750f407b83cf 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -747,17 +747,25 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int
state)
? RWSEM_WAKE_READERS
: RWSEM_WAKE_ANY, &wake_q);
- /*
- * The wakeup is normally called _after_ the wait_lock
- * is released, but given that we are proactively waking
- * readers we can deal with the wake_q overhead as it is
- * similar to releasing and taking the wait_lock again
- * for attempting rwsem_try_write_lock().
- */
- wake_up_q(&wake_q);
-
- /* We need wake_q again below, reinitialize */
- wake_q_init(&wake_q);
+ if (!wake_q_empty(&wake_q)) {
+ /*
+ * We want to minimize wait_lock hold time especially
+ * when a large number of readers are to be woken up.
+ */
+ raw_spin_unlock_irq(&sem->wait_lock);
+ wake_up_q(&wake_q);
+ wake_q_init(&wake_q); /* Used again, reinit */
+ raw_spin_lock_irq(&sem->wait_lock);
+ /*
+ * This waiter may have become first in the wait
+ * list after re-acquring the wait_lock. The
+ * rwsem_first_waiter() test in the main while
+ * loop below will correctly detect that. We do
+ * need to reload count to perform proper trylock
+ * and avoid missed wakeup.
+ */
+ count = atomic_long_read(&sem->count);
+ }
} else {
count = atomic_long_add_return(RWSEM_FLAG_WAITERS, &sem->count);
}
--
2.18.1
