[PATCH 5/7] blk-mq: remove REQ_ATOM_COMPLETE usages from blk-mq

[Tejun Heo]

After the recent updates to use generation number and state based
synchronization, blk-mq no longer depends on REQ_ATOM_COMPLETE except
to avoid firing the same timeout multiple times.

Remove all REQ_ATOM_COMPLETE usages and use a new rq_flags flag
RQF_MQ_TIMEOUT_EXPIRED to avoid firing the same timeout multiple
times.  This removes atomic bitops from hot paths too.

v2: Removed blk_clear_rq_complete() from blk_mq_rq_timed_out().

v3: Added RQF_MQ_TIMEOUT_EXPIRED flag.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: "jianchao.wang" <jianchao.w.wang@xxxxxxxxxx>
---
 block/blk-mq.c         | 18 ++++++++----------
 block/blk-timeout.c    |  1 +
 include/linux/blkdev.h |  2 ++
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 88baa82..47e722b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -607,14 +607,12 @@ void blk_mq_complete_request(struct request *rq)
 	 */
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
-		if (blk_mq_rq_aborted_gstate(rq) != rq->gstate &&
-		    !blk_mark_rq_complete(rq))
+		if (blk_mq_rq_aborted_gstate(rq) != rq->gstate)
 			__blk_mq_complete_request(rq);
 		rcu_read_unlock();
 	} else {
 		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
-		if (blk_mq_rq_aborted_gstate(rq) != rq->gstate &&
-		    !blk_mark_rq_complete(rq))
+		if (blk_mq_rq_aborted_gstate(rq) != rq->gstate)
 			__blk_mq_complete_request(rq);
 		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
 	}
@@ -665,8 +663,6 @@ void blk_mq_start_request(struct request *rq)
 	preempt_enable();
 
 	set_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
-	if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
-		clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags);
 
 	if (q->dma_drain_size && blk_rq_bytes(rq)) {
 		/*
@@ -817,6 +813,8 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 	if (!test_bit(REQ_ATOM_STARTED, &req->atomic_flags))
 		return;
 
+	req->rq_flags |= RQF_MQ_TIMEOUT_EXPIRED;
+
 	if (ops->timeout)
 		ret = ops->timeout(req, reserved);
 
@@ -832,7 +830,6 @@ static void blk_mq_rq_timed_out(struct request *req, bool reserved)
 		 */
 		blk_mq_rq_update_aborted_gstate(req, 0);
 		blk_add_timer(req);
-		blk_clear_rq_complete(req);
 		break;
 	case BLK_EH_NOT_HANDLED:
 		break;
@@ -851,7 +848,8 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
 
 	might_sleep();
 
-	if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+	if ((rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED) ||
+	    !test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
 		return;
 
 	/* read coherent snapshots of @rq->state_gen and @rq->deadline */
@@ -886,8 +884,8 @@ static void blk_mq_terminate_expired(struct blk_mq_hw_ctx *hctx,
 	 * now guaranteed to see @rq->aborted_gstate and yield.  If
 	 * @rq->aborted_gstate still matches @rq->gstate, @rq is ours.
 	 */
-	if (READ_ONCE(rq->gstate) == rq->aborted_gstate &&
-	    !blk_mark_rq_complete(rq))
+	if (!(rq->rq_flags & RQF_MQ_TIMEOUT_EXPIRED) &&
+	    READ_ONCE(rq->gstate) == rq->aborted_gstate)
 		blk_mq_rq_timed_out(rq, reserved);
 }
 
diff --git a/block/blk-timeout.c b/block/blk-timeout.c
index d580af3..25c4ffa 100644
--- a/block/blk-timeout.c
+++ b/block/blk-timeout.c
@@ -209,6 +209,7 @@ void blk_add_timer(struct request *req)
 		req->timeout = q->rq_timeout;
 
 	req->deadline = jiffies + req->timeout;
+	req->rq_flags &= ~RQF_MQ_TIMEOUT_EXPIRED;
 
 	/*
 	 * Only the non-mq case needs to add the request to a protected list.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2d6fd11..13186a7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -123,6 +123,8 @@ typedef __u32 __bitwise req_flags_t;
 /* Look at ->special_vec for the actual data payload instead of the
    bio chain. */
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
+/* timeout is expired */
+#define RQF_MQ_TIMEOUT_EXPIRED	((__force req_flags_t)(1 << 19))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
-- 
2.9.5