block: Initial support for data-less (or empty) barrier support

This implements functionality to pass down or insert a barrier
in a queue, without having data attached to it. The ->prepare_flush_fn()
infrastructure from data barriers are reused to provide this
functionality.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

5 files changed, 71 insertions, 21 deletions

diff --git a/block/elevator.c b/block/elevator.c
index ec23ca02f2fe..952aee04a68a 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -712,6 +712,14 @@ struct request *elv_next_request(struct request_queue *q)
 	int ret;
 
 	while ((rq = __elv_next_request(q)) != NULL) {
+		/*
+		 * Kill the empty barrier place holder, the driver must
+		 * not ever see it.
+		 */
+		if (blk_empty_barrier(rq)) {
+			end_queued_request(rq, 1);
+			continue;
+		}
 		if (!(rq->cmd_flags & REQ_STARTED)) {
 			/*
 			 * This is the first time the device driver
diff --git a/block/ll_rw_blk.c b/block/ll_rw_blk.c
index 548f0d826679..4fde3a3c92d3 100644
--- a/block/ll_rw_blk.c
+++ b/block/ll_rw_blk.c
@@ -458,9 +458,12 @@ static inline struct request *start_ordered(struct request_queue *q,
 	 * Queue ordered sequence.  As we stack them at the head, we
 	 * need to queue in reverse order.  Note that we rely on that
 	 * no fs request uses ELEVATOR_INSERT_FRONT and thus no fs
-	 * request gets inbetween ordered sequence.
+	 * request gets inbetween ordered sequence. If this request is
+	 * an empty barrier, we don't need to do a postflush ever since
+	 * there will be no data written between the pre and post flush.
+	 * Hence a single flush will suffice.
 	 */
-	if (q->ordered & QUEUE_ORDERED_POSTFLUSH)
+	if ((q->ordered & QUEUE_ORDERED_POSTFLUSH) && !blk_empty_barrier(rq))
 		queue_flush(q, QUEUE_ORDERED_POSTFLUSH);
 	else
 		q->ordseq |= QUEUE_ORDSEQ_POSTFLUSH;
@@ -484,7 +487,7 @@ static inline struct request *start_ordered(struct request_queue *q,
 int blk_do_ordered(struct request_queue *q, struct request **rqp)
 {
 	struct request *rq = *rqp;
-	int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
+	const int is_barrier = blk_fs_request(rq) && blk_barrier_rq(rq);
 
 	if (!q->ordseq) {
 		if (!is_barrier)
@@ -3054,7 +3057,7 @@ static inline void blk_partition_remap(struct bio *bio)
 {
 	struct block_device *bdev = bio->bi_bdev;
 
-	if (bdev != bdev->bd_contains) {
+	if (bio_sectors(bio) && bdev != bdev->bd_contains) {
 		struct hd_struct *p = bdev->bd_part;
 		const int rw = bio_data_dir(bio);
 
@@ -3313,23 +3316,32 @@ void submit_bio(int rw, struct bio *bio)
 {
 	int count = bio_sectors(bio);
 
-	BIO_BUG_ON(!bio->bi_size);
-	BIO_BUG_ON(!bio->bi_io_vec);
 	bio->bi_rw |= rw;
-	if (rw & WRITE) {
-		count_vm_events(PGPGOUT, count);
-	} else {
-		task_io_account_read(bio->bi_size);
-		count_vm_events(PGPGIN, count);
-	}
 
-	if (unlikely(block_dump)) {
-		char b[BDEVNAME_SIZE];
-		printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
-			current->comm, current->pid,
-			(rw & WRITE) ? "WRITE" : "READ",
-			(unsigned long long)bio->bi_sector,
-			bdevname(bio->bi_bdev,b));
+	/*
+	 * If it's a regular read/write or a barrier with data attached,
+	 * go through the normal accounting stuff before submission.
+	 */
+	if (!bio_empty_barrier(bio)) {
+
+		BIO_BUG_ON(!bio->bi_size);
+		BIO_BUG_ON(!bio->bi_io_vec);
+
+		if (rw & WRITE) {
+			count_vm_events(PGPGOUT, count);
+		} else {
+			task_io_account_read(bio->bi_size);
+			count_vm_events(PGPGIN, count);
+		}
+
+		if (unlikely(block_dump)) {
+			char b[BDEVNAME_SIZE];
+			printk(KERN_DEBUG "%s(%d): %s block %Lu on %s\n",
+				current->comm, current->pid,
+				(rw & WRITE) ? "WRITE" : "READ",
+				(unsigned long long)bio->bi_sector,
+				bdevname(bio->bi_bdev,b));
+		}
 	}
 
 	generic_make_request(bio);
@@ -3405,6 +3417,14 @@ static int __end_that_request_first(struct request *req, int uptodate,
 	while ((bio = req->bio) != NULL) {
 		int nbytes;
 
+		/*
+		 * For an empty barrier request, the low level driver must
+		 * store a potential error location in ->sector. We pass
+		 * that back up in ->bi_sector.
+		 */
+		if (blk_empty_barrier(req))
+			bio->bi_sector = req->sector;
+
 		if (nr_bytes >= bio->bi_size) {
 			req->bio = bio->bi_next;
 			nbytes = bio->bi_size;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 089a8bc55dd4..4da441337d6e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -176,13 +176,28 @@ struct bio {
 #define bio_offset(bio)		bio_iovec((bio))->bv_offset
 #define bio_segments(bio)	((bio)->bi_vcnt - (bio)->bi_idx)
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
-#define bio_cur_sectors(bio)	(bio_iovec(bio)->bv_len >> 9)
-#define bio_data(bio)		(page_address(bio_page((bio))) + bio_offset((bio)))
 #define bio_barrier(bio)	((bio)->bi_rw & (1 << BIO_RW_BARRIER))
 #define bio_sync(bio)		((bio)->bi_rw & (1 << BIO_RW_SYNC))
 #define bio_failfast(bio)	((bio)->bi_rw & (1 << BIO_RW_FAILFAST))
 #define bio_rw_ahead(bio)	((bio)->bi_rw & (1 << BIO_RW_AHEAD))
 #define bio_rw_meta(bio)	((bio)->bi_rw & (1 << BIO_RW_META))
+#define bio_empty_barrier(bio)	(bio_barrier(bio) && !(bio)->bi_size)
+
+static inline unsigned int bio_cur_sectors(struct bio *bio)
+{
+	if (bio->bi_vcnt)
+		return bio_iovec(bio)->bv_len >> 9;
+
+	return 0;
+}
+
+static inline void *bio_data(struct bio *bio)
+{
+	if (bio->bi_vcnt)
+		return page_address(bio_page(bio)) + bio_offset(bio);
+
+	return NULL;
+}
 
 /*
  * will die
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 610967992ddb..fb2ff749dc1f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -540,6 +540,7 @@ enum {
 #define blk_barrier_rq(rq)	((rq)->cmd_flags & REQ_HARDBARRIER)
 #define blk_fua_rq(rq)		((rq)->cmd_flags & REQ_FUA)
 #define blk_bidi_rq(rq)		((rq)->next_rq != NULL)
+#define blk_empty_barrier(rq)	(blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
 
 #define list_entry_rq(ptr)	list_entry((ptr), struct request, queuelist)
 
diff --git a/mm/bounce.c b/mm/bounce.c
index 3b549bf31f7d..b6d2d0f1019b 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -265,6 +265,12 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	mempool_t *pool;
 
 	/*
+	 * Data-less bio, nothing to bounce
+	 */
+	if (bio_empty_barrier(*bio_orig))
+		return;
+
+	/*
 	 * for non-isa bounce case, just check if the bounce pfn is equal
 	 * to or bigger than the highest pfn in the system -- in that case,
 	 * don't waste time iterating over bio segments