[PATCH V3 1/1] blk-mq: avoid double ->queue_rq() because of early timeout

[Ming Lei <ming.lei@xxxxxxxxxx>]

From: David Jeffery <djeffery@xxxxxxxxxx>

David Jeffery found one double ->queue_rq() issue, so far it can
be triggered in VM use case because of long vmexit latency or preempt
latency of vCPU pthread or long page fault in vCPU pthread, then block
IO req could be timed out before queuing the request to hardware but after
calling blk_mq_start_request() during ->queue_rq(), then timeout handler
may handle it by requeue, then double ->queue_rq() is caused, and kernel
panic.

So far, it is driver's responsibility to cover the race between timeout
and completion, so it seems supposed to be solved in driver in theory,
given driver has enough knowledge.

But it is really one common problem, lots of driver could have similar
issue, and could be hard to fix all affected drivers, even it isn't easy
for driver to handle the race. So David suggests this patch by draining
in-progress ->queue_rq() for solving this issue.

Cc: Stefan Hajnoczi <stefanha@xxxxxxxxxx>
Cc: Keith Busch <kbusch@xxxxxxxxxx>
Cc: virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
Cc: Bart Van Assche <bvanassche@xxxxxxx>
Signed-off-by: David Jeffery <djeffery@xxxxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
V3:
	- add callback for handle expired only, suggested by Keith Busch
V2:
	- follow Jens's suggestion to run sync rcu only if there is timeout
	- rename 'now' as 'start_timeout'
 block/blk-mq.c | 56 +++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 44 insertions(+), 12 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 33292c01875d..030bbb8deca6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1523,7 +1523,13 @@ static void blk_mq_rq_timed_out(struct request *req)
 	blk_add_timer(req);
 }
 
-static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
+struct blk_expired_data {
+	bool has_timedout_rq;
+	unsigned long next;
+	unsigned long timeout_start;
+};
+
+static bool blk_mq_req_expired(struct request *rq, struct blk_expired_data *expired)
 {
 	unsigned long deadline;
 
@@ -1533,13 +1539,13 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
 		return false;
 
 	deadline = READ_ONCE(rq->deadline);
-	if (time_after_eq(jiffies, deadline))
+	if (time_after_eq(expired->timeout_start, deadline))
 		return true;
 
-	if (*next == 0)
-		*next = deadline;
-	else if (time_after(*next, deadline))
-		*next = deadline;
+	if (expired->next == 0)
+		expired->next = deadline;
+	else if (time_after(expired->next, deadline))
+		expired->next = deadline;
 	return false;
 }
 
@@ -1555,7 +1561,7 @@ void blk_mq_put_rq_ref(struct request *rq)
 
 static bool blk_mq_check_expired(struct request *rq, void *priv)
 {
-	unsigned long *next = priv;
+	struct blk_expired_data *expired = priv;
 
 	/*
 	 * blk_mq_queue_tag_busy_iter() has locked the request, so it cannot
@@ -1564,7 +1570,18 @@ static bool blk_mq_check_expired(struct request *rq, void *priv)
 	 * it was completed and reallocated as a new request after returning
 	 * from blk_mq_check_expired().
 	 */
-	if (blk_mq_req_expired(rq, next))
+	if (blk_mq_req_expired(rq, expired)) {
+		expired->has_timedout_rq = true;
+		return false;
+	}
+	return true;
+}
+
+static bool blk_mq_handle_expired(struct request *rq, void *priv)
+{
+	struct blk_expired_data *expired = priv;
+
+	if (blk_mq_req_expired(rq, expired))
 		blk_mq_rq_timed_out(rq);
 	return true;
 }
@@ -1573,7 +1590,9 @@ static void blk_mq_timeout_work(struct work_struct *work)
 {
 	struct request_queue *q =
 		container_of(work, struct request_queue, timeout_work);
-	unsigned long next = 0;
+	struct blk_expired_data expired = {
+		.timeout_start = jiffies,
+	};
 	struct blk_mq_hw_ctx *hctx;
 	unsigned long i;
 
@@ -1593,10 +1612,23 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	if (!percpu_ref_tryget(&q->q_usage_counter))
 		return;
 
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next);
+	/* check if there is any timed-out request */
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &expired);
+	if (expired.has_timedout_rq) {
+		/*
+		 * Before walking tags, we must ensure any submit started
+		 * before the current time has finished. Since the submit
+		 * uses srcu or rcu, wait for a synchronization point to
+		 * ensure all running submits have finished
+		 */
+		blk_mq_wait_quiesce_done(q);
+
+		expired.next = 0;
+		blk_mq_queue_tag_busy_iter(q, blk_mq_handle_expired, &expired);
+	}
 
-	if (next != 0) {
-		mod_timer(&q->timeout, next);
+	if (expired.next != 0) {
+		mod_timer(&q->timeout, expired.next);
 	} else {
 		/*
 		 * Request timeouts are handled as a forward rolling timer. If
-- 
2.31.1