blk-mq: Remove generation seqeunce

This patch simplifies the timeout handling by relying on the request
reference counting to ensure the iterator is operating on an inflight
and truly timed out request. Since the reference counting prevents the
tag from being reallocated, the block layer no longer needs to prevent
drivers from completing their requests while the timeout handler is
operating on it: a driver completing a request is allowed to proceed to
the next state without additional syncronization with the block layer.

This also removes any need for generation sequence numbers since the
request lifetime is prevented from being reallocated as a new sequence
while timeout handling is operating on it.

To enables this a refcount is added to struct request so that request
users can be sure they're operating on the same request without it
changing while they're processing it.  The request's tag won't be
released for reuse until both the timeout handler and the completion
are done with it.

Signed-off-by: Keith Busch <keith.busch@intel.com>
[hch: slight cleanups, added back submission side hctx lock, use cmpxchg
 for completions]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 2 insertions, 40 deletions

diff --git a/block/blk-mq.h b/block/blk-mq.h
index e1bb420dc5d6..89231e439b2f 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -30,20 +30,6 @@ struct blk_mq_ctx {
 	struct kobject		kobj;
 } ____cacheline_aligned_in_smp;
 
-/*
- * Bits for request->gstate.  The lower two bits carry MQ_RQ_* state value
- * and the upper bits the generation number.
- */
-enum mq_rq_state {
-	MQ_RQ_IDLE		= 0,
-	MQ_RQ_IN_FLIGHT		= 1,
-	MQ_RQ_COMPLETE		= 2,
-
-	MQ_RQ_STATE_BITS	= 2,
-	MQ_RQ_STATE_MASK	= (1 << MQ_RQ_STATE_BITS) - 1,
-	MQ_RQ_GEN_INC		= 1 << MQ_RQ_STATE_BITS,
-};
-
 void blk_mq_freeze_queue(struct request_queue *q);
 void blk_mq_free_queue(struct request_queue *q);
 int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
@@ -107,33 +93,9 @@ void blk_mq_release(struct request_queue *q);
  * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
  * @rq: target request.
  */
-static inline int blk_mq_rq_state(struct request *rq)
+static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
 {
-	return READ_ONCE(rq->gstate) & MQ_RQ_STATE_MASK;
-}
-
-/**
- * blk_mq_rq_update_state() - set the current MQ_RQ_* state of a request
- * @rq: target request.
- * @state: new state to set.
- *
- * Set @rq's state to @state.  The caller is responsible for ensuring that
- * there are no other updaters.  A request can transition into IN_FLIGHT
- * only from IDLE and doing so increments the generation number.
- */
-static inline void blk_mq_rq_update_state(struct request *rq,
-					  enum mq_rq_state state)
-{
-	u64 old_val = READ_ONCE(rq->gstate);
-	u64 new_val = (old_val & ~MQ_RQ_STATE_MASK) | state;
-
-	if (state == MQ_RQ_IN_FLIGHT) {
-		WARN_ON_ONCE((old_val & MQ_RQ_STATE_MASK) != MQ_RQ_IDLE);
-		new_val += MQ_RQ_GEN_INC;
-	}
-
-	/* avoid exposing interim values */
-	WRITE_ONCE(rq->gstate, new_val);
+	return READ_ONCE(rq->state);
 }
 
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,