[PATCH 2/5] eventpoll: split out wait handling

[Jens Axboe <axboe@kernel.dk>]

In preparation for making changes to how wakeups and sleeps are done,
move the timeout scheduling into a helper and manage it rather than
rely on schedule_hrtimeout_range().

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/eventpoll.c | 70 ++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 56 insertions(+), 14 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 3061bdde6cba..f53bb4ec9e91 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -1762,6 +1762,47 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
 	return ret;
 }
 
+struct epoll_wq {
+	wait_queue_entry_t wait;
+	struct hrtimer timer;
+	bool timed_out;
+};
+
+static enum hrtimer_restart ep_timer(struct hrtimer *timer)
+{
+	struct epoll_wq *ewq = container_of(timer, struct epoll_wq, timer);
+	struct task_struct *task = ewq->wait.private;
+
+	ewq->timed_out = true;
+	wake_up_process(task);
+	return HRTIMER_NORESTART;
+}
+
+static void ep_schedule(struct eventpoll *ep, struct epoll_wq *ewq, ktime_t *to,
+			u64 slack)
+{
+	if (ewq->timed_out)
+		return;
+	if (to && *to == 0) {
+		ewq->timed_out = true;
+		return;
+	}
+	if (!to) {
+		schedule();
+		return;
+	}
+
+	hrtimer_init_on_stack(&ewq->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	ewq->timer.function = ep_timer;
+	hrtimer_set_expires_range_ns(&ewq->timer, *to, slack);
+	hrtimer_start_expires(&ewq->timer, HRTIMER_MODE_ABS);
+
+	schedule();
+
+	hrtimer_cancel(&ewq->timer);
+	destroy_hrtimer_on_stack(&ewq->timer);
+}
+
 /**
  * ep_poll - Retrieves ready events, and delivers them to the caller-supplied
  *           event buffer.
@@ -1782,13 +1823,15 @@ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry,
 static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		   int maxevents, struct timespec64 *timeout)
 {
-	int res, eavail, timed_out = 0;
+	int res, eavail;
 	u64 slack = 0;
-	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
+	struct epoll_wq ewq;
 
 	lockdep_assert_irqs_enabled();
 
+	ewq.timed_out = false;
+
 	if (timeout && (timeout->tv_sec | timeout->tv_nsec)) {
 		slack = select_estimate_accuracy(timeout);
 		to = &expires;
@@ -1798,7 +1841,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		 * Avoid the unnecessary trip to the wait queue loop, if the
 		 * caller specified a non blocking operation.
 		 */
-		timed_out = 1;
+		ewq.timed_out = 1;
 	}
 
 	/*
@@ -1823,10 +1866,10 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 				return res;
 		}
 
-		if (timed_out)
+		if (ewq.timed_out)
 			return 0;
 
-		eavail = ep_busy_loop(ep, timed_out);
+		eavail = ep_busy_loop(ep, ewq.timed_out);
 		if (eavail)
 			continue;
 
@@ -1850,8 +1893,8 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		 * performance issue if a process is killed, causing all of its
 		 * threads to wake up without being removed normally.
 		 */
-		init_wait(&wait);
-		wait.func = ep_autoremove_wake_function;
+		init_wait(&ewq.wait);
+		ewq.wait.func = ep_autoremove_wake_function;
 
 		write_lock_irq(&ep->lock);
 		/*
@@ -1870,10 +1913,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		 */
 		eavail = ep_events_available(ep);
 		if (!eavail) {
-			__add_wait_queue_exclusive(&ep->wq, &wait);
+			__add_wait_queue_exclusive(&ep->wq, &ewq.wait);
 			write_unlock_irq(&ep->lock);
-			timed_out = !schedule_hrtimeout_range(to, slack,
-							      HRTIMER_MODE_ABS);
+			ep_schedule(ep, &ewq, to, slack);
 		} else {
 			write_unlock_irq(&ep->lock);
 		}
@@ -1887,7 +1929,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 		 */
 		eavail = 1;
 
-		if (!list_empty_careful(&wait.entry)) {
+		if (!list_empty_careful(&ewq.wait.entry)) {
 			write_lock_irq(&ep->lock);
 			/*
 			 * If the thread timed out and is not on the wait queue,
@@ -1896,9 +1938,9 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 			 * Thus, when wait.entry is empty, it needs to harvest
 			 * events.
 			 */
-			if (timed_out)
-				eavail = list_empty(&wait.entry);
-			__remove_wait_queue(&ep->wq, &wait);
+			if (ewq.timed_out)
+				eavail = list_empty(&ewq.wait.entry);
+			__remove_wait_queue(&ep->wq, &ewq.wait);
 			write_unlock_irq(&ep->lock);
 		}
 	}
-- 
2.35.1