@@ -789,6 +789,18 @@ static void dd_prepare_request(struct request *rq)
rq->elv.priv[0] = NULL;
}
+static bool dd_has_write_work(struct blk_mq_hw_ctx *hctx)
+{
+ struct deadline_data *dd = hctx->queue->elevator->elevator_data;
+ enum dd_prio p;
+
+ for (p = 0; p <= DD_PRIO_MAX; p++)
+ if (!list_empty_careful(&dd->per_prio[p].fifo_list[DD_WRITE]))
+ return true;
+
+ return false;
+}
+
/*
* Callback from inside blk_mq_free_request().
*
@@ -828,9 +840,10 @@ static void dd_finish_request(struct request *rq)
spin_lock_irqsave(&dd->zone_lock, flags);
blk_req_zone_write_unlock(rq);
- if (!list_empty(&per_prio->fifo_list[DD_WRITE]))
- blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
spin_unlock_irqrestore(&dd->zone_lock, flags);
+
+ if (dd_has_write_work(rq->mq_hctx))
+ blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
}
}
dd_finish_request() tests if the per prio fifo_list is not empty to determine if request dispatching must be restarted for handling blocked write requests to zoned devices with a call to blk_mq_sched_mark_restart_hctx(). While simple, this implementation has 2 problems: 1) Only the priority level of the completed request is considered. However, writes to a zone may be blocked due to other writes to the same zone using a different priority level. While this is unlikely to happen in practice, as writing a zone with different IO priorirites does not make sense, nothing in the code prevents this from happening. 2) The use of list_empty() is dangerous as dd_finish_request() does not take dd->lock and may run concurrently with the insert and dispatch code. Fix these 2 problems by testing the write fifo list of all priority levels using the new helper dd_has_write_work(), and by testing each fifo list using list_empty_careful(). Fixes: c807ab520fc3 ("block/mq-deadline: Add I/O priority support") Cc: <stable@vger.kernel.org> Signed-off-by: Damien Le Moal <damien.lemoal@opensource.wdc.com> --- block/mq-deadline.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-)