[PATCH V3 1/8] block: introduce blk_quiesce_timeout() and blk_unquiesce_timeout()

[Ming Lei]

Turns out the current way can't drain timout completely because mod_timer()
can be triggered in the work func, which can be just run inside the synced
timeout work:

        del_timer_sync(&q->timeout);
        cancel_work_sync(&q->timeout_work);

This patch introduces one flag of 'timeout_off' for fixing this issue, turns
out this simple way does work.

Also blk_quiesce_timeout() and blk_unquiesce_timeout() are introduced for
draining timeout, which is needed by NVMe.

Cc: Bart Van Assche <bart.vanassche at wdc.com>
Cc: Jianchao Wang <jianchao.w.wang at oracle.com>
Cc: Christoph Hellwig <hch at lst.de>
Cc: Sagi Grimberg <sagi at grimberg.me>
Cc: linux-nvme at lists.infradead.org
Cc: Laurence Oberman <loberman at redhat.com>
Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
 block/blk-core.c       | 21 +++++++++++++++++++--
 block/blk-mq.c         |  9 +++++++++
 block/blk-timeout.c    |  5 ++++-
 include/linux/blkdev.h | 13 +++++++++++++
 4 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 85909b431eb0..c277f1023703 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -392,6 +392,22 @@ void blk_stop_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_stop_queue);
 
+void blk_unquiesce_timeout(struct request_queue *q)
+{
+	blk_mark_timeout_quiesce(q, false);
+	mod_timer(&q->timeout, jiffies + q->rq_timeout);
+}
+EXPORT_SYMBOL(blk_unquiesce_timeout);
+
+void blk_quiesce_timeout(struct request_queue *q)
+{
+	blk_mark_timeout_quiesce(q, true);
+
+	del_timer_sync(&q->timeout);
+	cancel_work_sync(&q->timeout_work);
+}
+EXPORT_SYMBOL(blk_quiesce_timeout);
+
 /**
  * blk_sync_queue - cancel any pending callbacks on a queue
  * @q: the queue
@@ -412,8 +428,7 @@ EXPORT_SYMBOL(blk_stop_queue);
  */
 void blk_sync_queue(struct request_queue *q)
 {
-	del_timer_sync(&q->timeout);
-	cancel_work_sync(&q->timeout_work);
+	blk_quiesce_timeout(q);
 
 	if (q->mq_ops) {
 		struct blk_mq_hw_ctx *hctx;
@@ -425,6 +440,8 @@ void blk_sync_queue(struct request_queue *q)
 	} else {
 		cancel_delayed_work_sync(&q->delay_work);
 	}
+
+	blk_mark_timeout_quiesce(q, false);
 }
 EXPORT_SYMBOL(blk_sync_queue);
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c3621453ad87..d0a5dc29c8ef 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -901,6 +901,15 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	};
 	struct blk_mq_hw_ctx *hctx;
 	int i;
+	bool timeout_off;
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	timeout_off = q->timeout_off;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	if (timeout_off)
+		return;
 
 	/* A deadlock might occur if a request is stuck requiring a
 	 * timeout at the same time a queue freeze is waiting
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index 652d4d4d3e97..ffd0b609091e 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -136,12 +136,15 @@ void blk_timeout_work(struct work_struct *work)
 
 	spin_lock_irqsave(q->queue_lock, flags);
 
+	if (q->timeout_off)
+		goto exit;
+
 	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
 		blk_rq_check_expired(rq, &next, &next_set);
 
 	if (next_set)
 		mod_timer(&q->timeout, round_jiffies_up(next));
-
+exit:
 	spin_unlock_irqrestore(q->queue_lock, flags);
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5c4eee043191..a2cc4aaecf50 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -584,6 +584,7 @@ struct request_queue {
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 	struct list_head	timeout_list;
+	bool			timeout_off;
 
 	struct list_head	icq_list;
 #ifdef CONFIG_BLK_CGROUP
@@ -1017,6 +1018,18 @@ extern void blk_execute_rq(struct request_queue *, struct gendisk *,
 extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *,
 				  struct request *, int, rq_end_io_fn *);
 
+static inline void blk_mark_timeout_quiesce(struct request_queue *q, bool quiesce)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	q->timeout_off = quiesce;
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+
+extern void blk_quiesce_timeout(struct request_queue *q);
+extern void blk_unquiesce_timeout(struct request_queue *q);
+
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
 
-- 
2.9.5