block: drop barrier ordering by queue draining

Filesystems will take all the responsibilities for ordering requests
around commit writes and will only indicate how the commit writes
themselves should be handled by block layers.  This patch drops
barrier ordering by queue draining from block layer.  Ordering by
draining implementation was somewhat invasive to request handling.
List of notable changes follow.

* Each queue has 1 bit color which is flipped on each barrier issue.
  This is used to track whether a given request is issued before the
  current barrier or not.  REQ_ORDERED_COLOR flag and coloring
  implementation in __elv_add_request() are removed.

* Requests which shouldn't be processed yet for draining were stalled
  by returning -EAGAIN from blk_do_ordered() according to the test
  result between blk_ordered_req_seq() and blk_blk_ordered_cur_seq().
  This logic is removed.

* Draining completion logic in elv_completed_request() removed.

* All barrier sequence requests were queued to request queue and then
  trckled to lower layer according to progress and thus maintaining
  request orders during requeue was necessary.  This is replaced by
  queueing the next request in the barrier sequence only after the
  current one is complete from blk_ordered_complete_seq(), which
  removes the need for multiple proxy requests in struct request_queue
  and the request sorting logic in the ELEVATOR_INSERT_REQUEUE path of
  elv_insert().

* As barriers no longer have ordering constraints, there's no need to
  dump the whole elevator onto the dispatch queue on each barrier.
  Insert barriers at the front instead.

* If other barrier requests come to the front of the dispatch queue
  while one is already in progress, they are stored in
  q->pending_barriers and restored to dispatch queue one-by-one after
  each barrier completion from blk_ordered_complete_seq().

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

2 files changed, 8 insertions, 13 deletions

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index ca83a97c971..9192282b425 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -143,7 +143,6 @@ enum rq_flag_bits {
 	__REQ_FAILED,		/* set if the request failed */
 	__REQ_QUIET,		/* don't worry about errors */
 	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
-	__REQ_ORDERED_COLOR,	/* is before or after barrier */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
@@ -184,7 +183,6 @@ enum rq_flag_bits {
 #define REQ_FAILED		(1 << __REQ_FAILED)
 #define REQ_QUIET		(1 << __REQ_QUIET)
 #define REQ_PREEMPT		(1 << __REQ_PREEMPT)
-#define REQ_ORDERED_COLOR	(1 << __REQ_ORDERED_COLOR)
 #define REQ_ALLOCED		(1 << __REQ_ALLOCED)
 #define REQ_COPY_USER		(1 << __REQ_COPY_USER)
 #define REQ_INTEGRITY		(1 << __REQ_INTEGRITY)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 996549d7192..20a3710a481 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -360,9 +360,10 @@ struct request_queue
 	unsigned int		flush_flags;
 
 	unsigned int		ordered, next_ordered, ordseq;
-	int			orderr, ordcolor;
-	struct request		pre_flush_rq, bar_rq, post_flush_rq;
+	int			orderr;
+	struct request		bar_rq;
 	struct request		*orig_bar_rq;
+	struct list_head	pending_barriers;
 
 	struct mutex		sysfs_lock;
 
@@ -491,12 +492,11 @@ enum {
 	/*
 	 * Ordered operation sequence
 	 */
-	QUEUE_ORDSEQ_STARTED	= 0x01,	/* flushing in progress */
-	QUEUE_ORDSEQ_DRAIN	= 0x02,	/* waiting for the queue to be drained */
-	QUEUE_ORDSEQ_PREFLUSH	= 0x04,	/* pre-flushing in progress */
-	QUEUE_ORDSEQ_BAR	= 0x08,	/* original barrier req in progress */
-	QUEUE_ORDSEQ_POSTFLUSH	= 0x10,	/* post-flushing in progress */
-	QUEUE_ORDSEQ_DONE	= 0x20,
+	QUEUE_ORDSEQ_STARTED	= (1 << 0), /* flushing in progress */
+	QUEUE_ORDSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
+	QUEUE_ORDSEQ_BAR	= (1 << 2), /* barrier write in progress */
+	QUEUE_ORDSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
+	QUEUE_ORDSEQ_DONE	= (1 << 4),
 };
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
@@ -869,9 +869,6 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
 extern void blk_queue_flush(struct request_queue *q, unsigned int flush);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
-extern unsigned blk_ordered_cur_seq(struct request_queue *);
-extern unsigned blk_ordered_req_seq(struct request *);
-extern bool blk_ordered_complete_seq(struct request_queue *, unsigned, int);
 
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);