block, fs: replace HARDBARRIER with FLUSH/FUA

index a381be8..999dac0 100644
@@ -441,19 +441,6 @@ void do_ide_request(struct request_queue *q)
 	struct request	*rq = NULL;
 	ide_startstop_t	startstop;
 
-	/*
-	 * drive is doing pre-flush, ordered write, post-flush sequence. even
-	 * though that is 3 requests, it must be seen as a single transaction.
-	 * we must not preempt this drive until that is complete
-	 */
-	if (blk_queue_flushing(q))
-		/*
-		 * small race where queue could get replugged during
-		 * the 3-request flush cycle, just yank the plug since
-		 * we want it to finish asap
-		 */
-		blk_remove_plug(q);
-
 	spin_unlock_irq(q->queue_lock);
 
 	/* HLD do_request() callback might sleep, make sure it's okay */

index 2c54906..015375c 100644
@@ -521,7 +521,6 @@ enum {
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
 #define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
 #define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
-#define blk_queue_flushing(q)	((q)->ordseq)
 #define blk_queue_stackable(q)	\
 	test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags)
 #define blk_queue_discard(q)	test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags)

index f3c636d..c3a4a2e 100644
@@ -832,7 +832,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->lo_queue->unplug_fn = loop_unplug;
 
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
-		blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN);
+		blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN_FLUSH);
 
 	set_capacity(lo->lo_disk, size);
 	bd_set_size(bdev, size << 9);

index f0faefc..c807e9c 100644
@@ -26,10 +26,7 @@ int blk_queue_ordered(struct request_queue *q, unsigned ordered)
 	if (ordered != QUEUE_ORDERED_NONE &&
 	    ordered != QUEUE_ORDERED_DRAIN &&
 	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
-	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
-	    ordered != QUEUE_ORDERED_TAG &&
-	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
-	    ordered != QUEUE_ORDERED_TAG_FUA) {
+	    ordered != QUEUE_ORDERED_DRAIN_FUA) {
 		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
 		return -EINVAL;
 	}

@@ -155,21 +152,9 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	 * For an empty barrier, there's no actual BAR request, which
 	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
 	 */
-	if (!blk_rq_sectors(rq)) {
+	if (!blk_rq_sectors(rq))
 		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
 				QUEUE_ORDERED_DO_POSTFLUSH);
-		/*
-		 * Empty barrier on a write-through device w/ ordered
-		 * tag has no command to issue and without any command
-		 * to issue, ordering by tag can't be used.  Drain
-		 * instead.
-		 */
-		if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
-		    !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
-			q->ordered &= ~QUEUE_ORDERED_BY_TAG;
-			q->ordered |= QUEUE_ORDERED_BY_DRAIN;
-		}
-	}
 
 	/* stash away the original request */
 	blk_dequeue_request(rq);

@@ -210,7 +195,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	} else
 		skip |= QUEUE_ORDSEQ_PREFLUSH;
 
-	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
+	if (queue_in_flight(q))
 		rq = NULL;
 	else
 		skip |= QUEUE_ORDSEQ_DRAIN;

@@ -257,16 +242,10 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
 		return true;
 
-	if (q->ordered & QUEUE_ORDERED_BY_TAG) {
-		/* Ordered by tag.  Blocking the next barrier is enough. */
-		if (is_barrier && rq != &q->bar_rq)
-			*rqp = NULL;
-	} else {
-		/* Ordered by draining.  Wait for turn. */
-		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
-		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
-			*rqp = NULL;
-	}
+	/* Ordered by draining.  Wait for turn. */
+	WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
+	if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
+		*rqp = NULL;
 
 	return true;
 }

index 1c7f637..47a4127 100644
@@ -482,7 +482,7 @@ static struct brd_device *brd_alloc(int i)
 	if (!brd->brd_queue)
 		goto out_free_dev;
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
-	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG);
+	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_DRAIN);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 

index 2aafafc..7965280 100644
@@ -395,15 +395,6 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 		 * to implement write barrier support.
 		 */
 		blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
-	} else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) {
-		/*
-		 * If the BARRIER feature is supported the host expects us
-		 * to order request by tags.  This implies there is not
-		 * volatile write cache on the host, and that the host
-		 * never re-orders outstanding I/O.  This feature is not
-		 * useful for real life scenarious and deprecated.
-		 */
-		blk_queue_ordered(q, QUEUE_ORDERED_TAG);
 	} else {
 		/*
 		 * If the FLUSH feature is not supported we must assume that

index ab735a6..8341862 100644
@@ -424,8 +424,7 @@ static int xlvbd_barrier(struct blkfront_info *info)
 	const char *barrier;
 
 	switch (info->feature_barrier) {
-	case QUEUE_ORDERED_DRAIN:	barrier = "enabled (drain)"; break;
-	case QUEUE_ORDERED_TAG:		barrier = "enabled (tag)"; break;
+	case QUEUE_ORDERED_DRAIN:	barrier = "enabled"; break;
 	case QUEUE_ORDERED_NONE:	barrier = "disabled"; break;
 	default:			return -EINVAL;
 	}

@@ -1078,8 +1077,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	 * we're dealing with a very old backend which writes
 	 * synchronously; draining will do what needs to get done.
 	 *
-	 * If there are barriers, then we can do full queued writes
-	 * with tagged barriers.
+	 * If there are barriers, then we use flush.
 	 *
 	 * If barriers are not supported, then there's no much we can
 	 * do, so just set ordering to NONE.

@@ -1087,7 +1085,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	if (err)
 		info->feature_barrier = QUEUE_ORDERED_DRAIN;
 	else if (barrier)
-		info->feature_barrier = QUEUE_ORDERED_TAG;
+		info->feature_barrier = QUEUE_ORDERED_DRAIN_FLUSH;
 	else
 		info->feature_barrier = QUEUE_ORDERED_NONE;
 

index 2714bec..cdfc51a 100644
@@ -2151,9 +2151,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 
 	/*
 	 * We now have all cache related info, determine how we deal
-	 * with ordered requests.  Note that as the current SCSI
-	 * dispatch function can alter request order, we cannot use
-	 * QUEUE_ORDERED_TAG_* even when ordered tag is supported.
+	 * with ordered requests.
 	 */
 	if (sdkp->WCE)
 		ordered = sdkp->DPOFUA

index 015375c..7077bc0 100644
@@ -470,12 +470,7 @@ enum {
 	 * DRAIN	: ordering by draining is enough
 	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
 	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
-	 * TAG		: ordering by tag is enough
-	 * TAG_FLUSH	: ordering by tag w/ pre and post flushes
-	 * TAG_FUA	: ordering by tag w/ pre flush and FUA write
 	 */
-	QUEUE_ORDERED_BY_DRAIN		= 0x01,
-	QUEUE_ORDERED_BY_TAG		= 0x02,
 	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
 	QUEUE_ORDERED_DO_BAR		= 0x20,
 	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,

@@ -483,8 +478,7 @@ enum {
 
 	QUEUE_ORDERED_NONE		= 0x00,
 
-	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_BY_DRAIN |
-					  QUEUE_ORDERED_DO_BAR,
+	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_DO_BAR,
 	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
 					  QUEUE_ORDERED_DO_PREFLUSH |
 					  QUEUE_ORDERED_DO_POSTFLUSH,

@@ -492,15 +486,6 @@ enum {
 					  QUEUE_ORDERED_DO_PREFLUSH |
 					  QUEUE_ORDERED_DO_FUA,
 
-	QUEUE_ORDERED_TAG		= QUEUE_ORDERED_BY_TAG |
-					  QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_TAG_FLUSH		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_TAG_FUA		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
 	/*
 	 * Ordered operation sequence
 	 */

index f0faefc..c807e9c 100644
@@ -26,10 +26,7 @@ int blk_queue_ordered(struct request_queue *q, unsigned ordered)
 	if (ordered != QUEUE_ORDERED_NONE &&
 	    ordered != QUEUE_ORDERED_DRAIN &&
 	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
-	    ordered != QUEUE_ORDERED_DRAIN_FUA &&
-	    ordered != QUEUE_ORDERED_TAG &&
-	    ordered != QUEUE_ORDERED_TAG_FLUSH &&
-	    ordered != QUEUE_ORDERED_TAG_FUA) {
+	    ordered != QUEUE_ORDERED_DRAIN_FUA) {
 		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
 		return -EINVAL;
 	}

@@ -155,21 +152,9 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	 * For an empty barrier, there's no actual BAR request, which
 	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
 	 */
-	if (!blk_rq_sectors(rq)) {
+	if (!blk_rq_sectors(rq))
 		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
 				QUEUE_ORDERED_DO_POSTFLUSH);
-		/*
-		 * Empty barrier on a write-through device w/ ordered
-		 * tag has no command to issue and without any command
-		 * to issue, ordering by tag can't be used.  Drain
-		 * instead.
-		 */
-		if ((q->ordered & QUEUE_ORDERED_BY_TAG) &&
-		    !(q->ordered & QUEUE_ORDERED_DO_PREFLUSH)) {
-			q->ordered &= ~QUEUE_ORDERED_BY_TAG;
-			q->ordered |= QUEUE_ORDERED_BY_DRAIN;
-		}
-	}
 
 	/* stash away the original request */
 	blk_dequeue_request(rq);

@@ -210,7 +195,7 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	} else
 		skip |= QUEUE_ORDSEQ_PREFLUSH;
 
-	if ((q->ordered & QUEUE_ORDERED_BY_DRAIN) && queue_in_flight(q))
+	if (queue_in_flight(q))
 		rq = NULL;
 	else
 		skip |= QUEUE_ORDSEQ_DRAIN;

@@ -257,16 +242,10 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
 		return true;
 
-	if (q->ordered & QUEUE_ORDERED_BY_TAG) {
-		/* Ordered by tag.  Blocking the next barrier is enough. */
-		if (is_barrier && rq != &q->bar_rq)
-			*rqp = NULL;
-	} else {
-		/* Ordered by draining.  Wait for turn. */
-		WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
-		if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
-			*rqp = NULL;
-	}
+	/* Ordered by draining.  Wait for turn. */
+	WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
+	if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
+		*rqp = NULL;
 
 	return true;
 }

index 1c7f637..47a4127 100644
@@ -482,7 +482,7 @@ static struct brd_device *brd_alloc(int i)
 	if (!brd->brd_queue)
 		goto out_free_dev;
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
-	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_TAG);
+	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_DRAIN);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 

index 2aafafc..7965280 100644
@@ -395,15 +395,6 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 		 * to implement write barrier support.
 		 */
 		blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
-	} else if (virtio_has_feature(vdev, VIRTIO_BLK_F_BARRIER)) {
-		/*
-		 * If the BARRIER feature is supported the host expects us
-		 * to order request by tags.  This implies there is not
-		 * volatile write cache on the host, and that the host
-		 * never re-orders outstanding I/O.  This feature is not
-		 * useful for real life scenarious and deprecated.
-		 */
-		blk_queue_ordered(q, QUEUE_ORDERED_TAG);
 	} else {
 		/*
 		 * If the FLUSH feature is not supported we must assume that

index ab735a6..8341862 100644
@@ -424,8 +424,7 @@ static int xlvbd_barrier(struct blkfront_info *info)
 	const char *barrier;
 
 	switch (info->feature_barrier) {
-	case QUEUE_ORDERED_DRAIN:	barrier = "enabled (drain)"; break;
-	case QUEUE_ORDERED_TAG:		barrier = "enabled (tag)"; break;
+	case QUEUE_ORDERED_DRAIN:	barrier = "enabled"; break;
 	case QUEUE_ORDERED_NONE:	barrier = "disabled"; break;
 	default:			return -EINVAL;
 	}

@@ -1078,8 +1077,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	 * we're dealing with a very old backend which writes
 	 * synchronously; draining will do what needs to get done.
 	 *
-	 * If there are barriers, then we can do full queued writes
-	 * with tagged barriers.
+	 * If there are barriers, then we use flush.
 	 *
 	 * If barriers are not supported, then there's no much we can
 	 * do, so just set ordering to NONE.

@@ -1087,7 +1085,7 @@ static void blkfront_connect(struct blkfront_info *info)
 	if (err)
 		info->feature_barrier = QUEUE_ORDERED_DRAIN;
 	else if (barrier)
-		info->feature_barrier = QUEUE_ORDERED_TAG;
+		info->feature_barrier = QUEUE_ORDERED_DRAIN_FLUSH;
 	else
 		info->feature_barrier = QUEUE_ORDERED_NONE;
 

index 2714bec..cdfc51a 100644
@@ -2151,9 +2151,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 
 	/*
 	 * We now have all cache related info, determine how we deal
-	 * with ordered requests.  Note that as the current SCSI
-	 * dispatch function can alter request order, we cannot use
-	 * QUEUE_ORDERED_TAG_* even when ordered tag is supported.
+	 * with ordered requests.
 	 */
 	if (sdkp->WCE)
 		ordered = sdkp->DPOFUA

index 015375c..7077bc0 100644
@@ -470,12 +470,7 @@ enum {
 	 * DRAIN	: ordering by draining is enough
 	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
 	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
-	 * TAG		: ordering by tag is enough
-	 * TAG_FLUSH	: ordering by tag w/ pre and post flushes
-	 * TAG_FUA	: ordering by tag w/ pre flush and FUA write
 	 */
-	QUEUE_ORDERED_BY_DRAIN		= 0x01,
-	QUEUE_ORDERED_BY_TAG		= 0x02,
 	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
 	QUEUE_ORDERED_DO_BAR		= 0x20,
 	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,

@@ -483,8 +478,7 @@ enum {
 
 	QUEUE_ORDERED_NONE		= 0x00,
 
-	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_BY_DRAIN |
-					  QUEUE_ORDERED_DO_BAR,
+	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_DO_BAR,
 	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
 					  QUEUE_ORDERED_DO_PREFLUSH |
 					  QUEUE_ORDERED_DO_POSTFLUSH,

@@ -492,15 +486,6 @@ enum {
 					  QUEUE_ORDERED_DO_PREFLUSH |
 					  QUEUE_ORDERED_DO_FUA,
 
-	QUEUE_ORDERED_TAG		= QUEUE_ORDERED_BY_TAG |
-					  QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_TAG_FLUSH		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_TAG_FUA		= QUEUE_ORDERED_TAG |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
 	/*
 	 * Ordered operation sequence
 	 */

index c807e9c..ed0aba5 100644
@@ -9,35 +9,6 @@
 
 #include "blk.h"
 
-/**
- * blk_queue_ordered - does this queue support ordered writes
- * @q:        the request queue
- * @ordered:  one of QUEUE_ORDERED_*
- *
- * Description:
- *   For journalled file systems, doing ordered writes on a commit
- *   block instead of explicitly doing wait_on_buffer (which is bad
- *   for performance) can be a big win. Block drivers supporting this
- *   feature should call this function and indicate so.
- *
- **/
-int blk_queue_ordered(struct request_queue *q, unsigned ordered)
-{
-	if (ordered != QUEUE_ORDERED_NONE &&
-	    ordered != QUEUE_ORDERED_DRAIN &&
-	    ordered != QUEUE_ORDERED_DRAIN_FLUSH &&
-	    ordered != QUEUE_ORDERED_DRAIN_FUA) {
-		printk(KERN_ERR "blk_queue_ordered: bad value %d\n", ordered);
-		return -EINVAL;
-	}
-
-	q->ordered = ordered;
-	q->next_ordered = ordered;
-
-	return 0;
-}
-EXPORT_SYMBOL(blk_queue_ordered);
-
 /*
  * Cache flushing for ordered writes handling
  */

index ee1a1e7..f063541 100644
@@ -1203,11 +1203,13 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	int rw_flags;
 
-	if ((bio->bi_rw & REQ_HARDBARRIER) &&
-	    (q->next_ordered == QUEUE_ORDERED_NONE)) {
+	/* REQ_HARDBARRIER is no more */
+	if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER,
+		"block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) {
 		bio_endio(bio, -EOPNOTSUPP);
 		return 0;
 	}
+
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even

index a234f4b..9b18afc 100644
@@ -794,6 +794,26 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
 }
 EXPORT_SYMBOL(blk_queue_update_dma_alignment);
 
+/**
+ * blk_queue_flush - configure queue's cache flush capability
+ * @q:		the request queue for the device
+ * @flush:	0, REQ_FLUSH or REQ_FLUSH | REQ_FUA
+ *
+ * Tell block layer cache flush capability of @q.  If it supports
+ * flushing, REQ_FLUSH should be set.  If it supports bypassing
+ * write cache for individual writes, REQ_FUA should be set.
+ */
+void blk_queue_flush(struct request_queue *q, unsigned int flush)
+{
+	WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA));
+
+	if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA)))
+		flush &= ~REQ_FUA;
+
+	q->flush_flags = flush & (REQ_FLUSH | REQ_FUA);
+}
+EXPORT_SYMBOL_GPL(blk_queue_flush);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;

index 47a4127..fa33f97 100644
@@ -482,7 +482,6 @@ static struct brd_device *brd_alloc(int i)
 	if (!brd->brd_queue)
 		goto out_free_dev;
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
-	blk_queue_ordered(brd->brd_queue, QUEUE_ORDERED_DRAIN);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
 	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 

index c3a4a2e..953d1e1 100644
@@ -832,7 +832,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->lo_queue->unplug_fn = loop_unplug;
 
 	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
-		blk_queue_ordered(lo->lo_queue, QUEUE_ORDERED_DRAIN_FLUSH);
+		blk_queue_flush(lo->lo_queue, REQ_FLUSH);
 
 	set_capacity(lo->lo_disk, size);
 	bd_set_size(bdev, size << 9);

index 2284b4f..72d6246 100644
@@ -439,7 +439,7 @@ static int osdblk_init_disk(struct osdblk_device *osdev)
 	blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
 
 	blk_queue_prep_rq(q, blk_queue_start_tag);
-	blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
+	blk_queue_flush(q, REQ_FLUSH);
 
 	disk->queue = q;
 

index e9da874..4911f9e 100644
@@ -468,7 +468,7 @@ static int __devinit ps3disk_probe(struct ps3_system_bus_device *_dev)
 	blk_queue_dma_alignment(queue, dev->blk_size-1);
 	blk_queue_logical_block_size(queue, dev->blk_size);
 
-	blk_queue_ordered(queue, QUEUE_ORDERED_DRAIN_FLUSH);
+	blk_queue_flush(queue, REQ_FLUSH);
 
 	blk_queue_max_segments(queue, -1);
 	blk_queue_max_segment_size(queue, dev->bounce_size);

index 7965280..d10b635 100644
@@ -388,22 +388,15 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	vblk->disk->driverfs_dev = &vdev->dev;
 	index++;
 
-	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH)) {
-		/*
-		 * If the FLUSH feature is supported we do have support for
-		 * flushing a volatile write cache on the host.  Use that
-		 * to implement write barrier support.
-		 */
-		blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH);
-	} else {
-		/*
-		 * If the FLUSH feature is not supported we must assume that
-		 * the host does not perform any kind of volatile write
-		 * caching. We still need to drain the queue to provider
-		 * proper barrier semantics.
-		 */
-		blk_queue_ordered(q, QUEUE_ORDERED_DRAIN);
-	}
+	/*
+	 * If the FLUSH feature is supported we do have support for
+	 * flushing a volatile write cache on the host.  Use that to
+	 * implement write barrier support; otherwise, we must assume
+	 * that the host does not perform any kind of volatile write
+	 * caching.
+	 */
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
+		blk_queue_flush(q, REQ_FLUSH);
 
 	/* If disk is read-only in the host, the guest should obey */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))

78 lines not on this page · raw message

index 7433e07..7c5b01c 100644
@@ -516,10 +516,10 @@ static int ide_do_setfeature(ide_drive_t *drive, u8 feature, u8 nsect)
 	return ide_no_data_taskfile(drive, &cmd);
 }
 
-static void update_ordered(ide_drive_t *drive)
+static void update_flush(ide_drive_t *drive)
 {
 	u16 *id = drive->id;
-	unsigned ordered = QUEUE_ORDERED_NONE;
+	unsigned flush = 0;
 
 	if (drive->dev_flags & IDE_DFLAG_WCACHE) {
 		unsigned long long capacity;

@@ -543,13 +543,12 @@ static void update_ordered(ide_drive_t *drive)
 		       drive->name, barrier ? "" : "not ");
 
 		if (barrier) {
-			ordered = QUEUE_ORDERED_DRAIN_FLUSH;
+			flush = REQ_FLUSH;
 			blk_queue_prep_rq(drive->queue, idedisk_prep_fn);
 		}
-	} else
-		ordered = QUEUE_ORDERED_DRAIN;
+	}
 
-	blk_queue_ordered(drive->queue, ordered);
+	blk_queue_flush(drive->queue, flush);
 }
 
 ide_devset_get_flag(wcache, IDE_DFLAG_WCACHE);

@@ -572,7 +571,7 @@ static int set_wcache(ide_drive_t *drive, int arg)
 		}
 	}
 
-	update_ordered(drive);
+	update_flush(drive);
 
 	return err;
 }

index ac384b2..b1d92be 100644
@@ -2245,7 +2245,7 @@ static int dm_init_request_based_queue(struct mapped_device *md)
 	blk_queue_softirq_done(md->queue, dm_softirq_done);
 	blk_queue_prep_rq(md->queue, dm_prep_fn);
 	blk_queue_lld_busy(md->queue, dm_lld_busy);
-	blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN_FLUSH);
+	blk_queue_flush(md->queue, REQ_FLUSH);
 
 	elv_register_queue(md->queue);
 

index e876678..9c0b42b 100644
@@ -128,7 +128,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card, spinlock_t *lock
 	mq->req = NULL;
 
 	blk_queue_prep_rq(mq->queue, mmc_prep_request);
-	blk_queue_ordered(mq->queue, QUEUE_ORDERED_DRAIN);
 	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, mq->queue);
 	if (mmc_can_erase(card)) {
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mq->queue);

index 8373ca0..9b106d8 100644
@@ -2197,7 +2197,6 @@ static void dasd_setup_queue(struct dasd_block *block)
 	 */
 	blk_queue_max_segment_size(block->request_queue, PAGE_SIZE);
 	blk_queue_segment_boundary(block->request_queue, PAGE_SIZE - 1);
-	blk_queue_ordered(block->request_queue, QUEUE_ORDERED_DRAIN);
 }
 
 /*

index cdfc51a..63bd01a 100644
@@ -2109,7 +2109,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	struct scsi_disk *sdkp = scsi_disk(disk);
 	struct scsi_device *sdp = sdkp->device;
 	unsigned char *buffer;
-	unsigned ordered;
+	unsigned flush = 0;
 
 	SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp,
 				      "sd_revalidate_disk\n"));

@@ -2151,15 +2151,15 @@ static int sd_revalidate_disk(struct gendisk *disk)
 
 	/*
 	 * We now have all cache related info, determine how we deal
-	 * with ordered requests.
+	 * with flush requests.
 	 */
-	if (sdkp->WCE)
-		ordered = sdkp->DPOFUA
-			? QUEUE_ORDERED_DRAIN_FUA : QUEUE_ORDERED_DRAIN_FLUSH;
-	else
-		ordered = QUEUE_ORDERED_DRAIN;
+	if (sdkp->WCE) {
+		flush |= REQ_FLUSH;
+		if (sdkp->DPOFUA)
+			flush |= REQ_FUA;
+	}
 
-	blk_queue_ordered(sdkp->disk->queue, ordered);
+	blk_queue_flush(sdkp->disk->queue, flush);
 
 	set_capacity(disk, sdkp->capacity);
 	kfree(buffer);

index 7077bc0..e97911d 100644
@@ -355,8 +355,10 @@ struct request_queue
 	struct blk_trace	*blk_trace;
 #endif
 	/*
-	 * reserved for flush operations
+	 * for flush operations
 	 */
+	unsigned int		flush_flags;
+
 	unsigned int		ordered, next_ordered, ordseq;
 	int			orderr, ordcolor;
 	struct request		pre_flush_rq, bar_rq, post_flush_rq;

@@ -865,8 +867,8 @@ extern void blk_queue_update_dma_alignment(struct request_queue *, int);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
 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 int blk_queue_ordered(struct request_queue *, unsigned);
 extern bool blk_do_ordered(struct request_queue *, struct request **);
 extern unsigned blk_ordered_cur_seq(struct request_queue *);
 extern unsigned blk_ordered_req_seq(struct request *);

index 72d6246..87311eb 100644
@@ -310,8 +310,7 @@ static void osdblk_rq_fn(struct request_queue *q)
 			break;
 
 		/* filter out block requests we don't understand */
-		if (rq->cmd_type != REQ_TYPE_FS &&
-		    !(rq->cmd_flags & REQ_HARDBARRIER)) {
+		if (rq->cmd_type != REQ_TYPE_FS) {
 			blk_end_request_all(rq, 0);
 			continue;
 		}

index b1cbeb5..0166ea1 100644
@@ -753,7 +753,6 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 
 	rq->timeout = 60*HZ;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_HARDBARRIER;
 	if (cgc->quiet)
 		rq->cmd_flags |= REQ_QUIET;
 

index 93984c9..e1cd606 100644
@@ -2850,12 +2850,6 @@ aic7xxx_done(struct aic7xxx_host *p, struct aic7xxx_scb *scb)
       aic_dev->r_total++;
       ptr = aic_dev->r_bins;
     }
-    if(cmd->device->simple_tags && cmd->request->cmd_flags & REQ_HARDBARRIER)
-    {
-      aic_dev->barrier_total++;
-      if(scb->tag_action == MSG_ORDERED_Q_TAG)
-        aic_dev->ordered_total++;
-    }
     x = scb->sg_length;
     x >>= 10;
     for(i=0; i<6; i++)

@@ -10144,19 +10138,8 @@ static void aic7xxx_buildscb(struct aic7xxx_host *p, struct scsi_cmnd *cmd,
     /* We always force TEST_UNIT_READY to untagged */
     if (cmd->cmnd[0] != TEST_UNIT_READY && sdptr->simple_tags)
     {
-      if (req->cmd_flags & REQ_HARDBARRIER)
-      {
-	if(sdptr->ordered_tags)
-	{
-          hscb->control |= MSG_ORDERED_Q_TAG;
-          scb->tag_action = MSG_ORDERED_Q_TAG;
-	}
-      }
-      else
-      {
-        hscb->control |= MSG_SIMPLE_Q_TAG;
-        scb->tag_action = MSG_SIMPLE_Q_TAG;
-      }
+      hscb->control |= MSG_SIMPLE_Q_TAG;
+      scb->tag_action = MSG_SIMPLE_Q_TAG;
     }
   }
   if ( !(aic_dev->dtr_pending) &&

index f0cfba9..535085c 100644
@@ -130,17 +130,6 @@ static void sas_scsi_task_done(struct sas_task *task)
 	sc->scsi_done(sc);
 }
 
-static enum task_attribute sas_scsi_get_task_attr(struct scsi_cmnd *cmd)
-{
-	enum task_attribute ta = TASK_ATTR_SIMPLE;
-	if (cmd->request && blk_rq_tagged(cmd->request)) {
-		if (cmd->device->ordered_tags &&
-		    (cmd->request->cmd_flags & REQ_HARDBARRIER))
-			ta = TASK_ATTR_ORDERED;
-	}
-	return ta;
-}
-
 static struct sas_task *sas_create_task(struct scsi_cmnd *cmd,
 					       struct domain_device *dev,
 					       gfp_t gfp_flags)

@@ -160,7 +149,7 @@ static struct sas_task *sas_create_task(struct scsi_cmnd *cmd,
 	task->ssp_task.retry_count = 1;
 	int_to_scsilun(cmd->device->lun, &lun);
 	memcpy(task->ssp_task.LUN, &lun.scsi_lun, 8);
-	task->ssp_task.task_attr = sas_scsi_get_task_attr(cmd);
+	task->ssp_task.task_attr = TASK_ATTR_SIMPLE;
 	memcpy(task->ssp_task.cdb, cmd->cmnd, 16);
 
 	task->scatter = scsi_sglist(cmd);

index 1723138..d6e7994 100644
@@ -97,13 +97,9 @@ static inline void scsi_deactivate_tcq(struct scsi_device *sdev, int depth)
 static inline int scsi_populate_tag_msg(struct scsi_cmnd *cmd, char *msg)
 {
         struct request *req = cmd->request;
-	struct scsi_device *sdev = cmd->device;
 
         if (blk_rq_tagged(req)) {
-		if (sdev->ordered_tags && req->cmd_flags & REQ_HARDBARRIER)
-        	        *msg++ = MSG_ORDERED_TAG;
-        	else
-        	        *msg++ = MSG_SIMPLE_TAG;
+		*msg++ = MSG_SIMPLE_TAG;
         	*msg++ = req->tag;
         	return 2;
 	}

index ed0aba5..f1be85b 100644
@@ -110,9 +110,9 @@ static void queue_flush(struct request_queue *q, unsigned which)
 	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 }
 
-static inline bool start_ordered(struct request_queue *q, struct request **rqp)
+static inline struct request *start_ordered(struct request_queue *q,
+					    struct request *rq)
 {
-	struct request *rq = *rqp;
 	unsigned skip = 0;
 
 	q->orderr = 0;

@@ -149,11 +149,9 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 
 		/* initialize proxy request and queue it */
 		blk_rq_init(q, rq);
-		if (bio_data_dir(q->orig_bar_rq->bio) == WRITE)
-			rq->cmd_flags |= REQ_WRITE;
+		init_request_from_bio(rq, q->orig_bar_rq->bio);
 		if (q->ordered & QUEUE_ORDERED_DO_FUA)
 			rq->cmd_flags |= REQ_FUA;
-		init_request_from_bio(rq, q->orig_bar_rq->bio);
 		rq->end_io = bar_end_io;
 
 		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);

@@ -171,27 +169,26 @@ static inline bool start_ordered(struct request_queue *q, struct request **rqp)
 	else
 		skip |= QUEUE_ORDSEQ_DRAIN;
 
-	*rqp = rq;
-
 	/*
 	 * Complete skipped sequences.  If whole sequence is complete,
-	 * return false to tell elevator that this request is gone.
+	 * return %NULL to tell elevator that this request is gone.
 	 */
-	return !blk_ordered_complete_seq(q, skip, 0);
+	if (blk_ordered_complete_seq(q, skip, 0))
+		rq = NULL;
+	return rq;
 }
 
-bool blk_do_ordered(struct request_queue *q, struct request **rqp)
+struct request *blk_do_ordered(struct request_queue *q, struct request *rq)
 {
-	struct request *rq = *rqp;
 	const int is_barrier = rq->cmd_type == REQ_TYPE_FS &&
 				(rq->cmd_flags & REQ_HARDBARRIER);
 
 	if (!q->ordseq) {
 		if (!is_barrier)
-			return true;
+			return rq;
 
 		if (q->next_ordered != QUEUE_ORDERED_NONE)
-			return start_ordered(q, rqp);
+			return start_ordered(q, rq);
 		else {
 			/*
 			 * Queue ordering not supported.  Terminate

@@ -199,8 +196,7 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 			 */
 			blk_dequeue_request(rq);
 			__blk_end_request_all(rq, -EOPNOTSUPP);
-			*rqp = NULL;
-			return false;
+			return NULL;
 		}
 	}
 

@@ -211,14 +207,14 @@ bool blk_do_ordered(struct request_queue *q, struct request **rqp)
 	/* Special requests are not subject to ordering rules. */
 	if (rq->cmd_type != REQ_TYPE_FS &&
 	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
-		return true;
+		return rq;
 
 	/* Ordered by draining.  Wait for turn. */
 	WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
 	if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
-		*rqp = NULL;
+		rq = ERR_PTR(-EAGAIN);
 
-	return true;
+	return rq;
 }
 
 static void bio_end_empty_barrier(struct bio *bio, int err)

index f063541..f8d37a8 100644
@@ -1037,22 +1037,6 @@ void blk_insert_request(struct request_queue *q, struct request *rq,
 }
 EXPORT_SYMBOL(blk_insert_request);
 
-/*
- * add-request adds a request to the linked list.
- * queue lock is held and interrupts disabled, as we muck with the
- * request queue list.
- */
-static inline void add_request(struct request_queue *q, struct request *req)
-{
-	drive_stat_acct(req, 1);
-
-	/*
-	 * elevator indicated where it wants this request to be
-	 * inserted at elevator_merge time
-	 */
-	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
-}
-
 static void part_round_stats_single(int cpu, struct hd_struct *part,
 				    unsigned long now)
 {

@@ -1316,7 +1300,10 @@ get_rq:
 		req->cpu = blk_cpu_to_group(smp_processor_id());
 	if (queue_should_plug(q) && elv_queue_empty(q))
 		blk_plug_device(q);
-	add_request(q, req);
+
+	/* insert the request into the elevator */
+	drive_stat_acct(req, 1);
+	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
 out:
 	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);

index 6e7dc87..874eb4e 100644
@@ -51,6 +51,8 @@ static inline void blk_clear_rq_complete(struct request *rq)
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
+struct request *blk_do_ordered(struct request_queue *q, struct request *rq);
+
 static inline struct request *__elv_next_request(struct request_queue *q)
 {
 	struct request *rq;

@@ -58,8 +60,9 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
-			if (blk_do_ordered(q, &rq))
-				return rq;
+			rq = blk_do_ordered(q, rq);
+			if (rq)
+				return !IS_ERR(rq) ? rq : NULL;
 		}
 
 		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))

index e97911d..996549d 100644
@@ -869,7 +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 bool blk_do_ordered(struct request_queue *, struct request **);
 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);

index f1be85b..e8b2e5c 100644
@@ -9,6 +9,8 @@
 
 #include "blk.h"
 
+static struct request *queue_next_ordseq(struct request_queue *q);
+
 /*
  * Cache flushing for ordered writes handling
  */

@@ -19,38 +21,10 @@ unsigned blk_ordered_cur_seq(struct request_queue *q)
 	return 1 << ffz(q->ordseq);
 }
 
-unsigned blk_ordered_req_seq(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-
-	BUG_ON(q->ordseq == 0);
-
-	if (rq == &q->pre_flush_rq)
-		return QUEUE_ORDSEQ_PREFLUSH;
-	if (rq == &q->bar_rq)
-		return QUEUE_ORDSEQ_BAR;
-	if (rq == &q->post_flush_rq)
-		return QUEUE_ORDSEQ_POSTFLUSH;
-
-	/*
-	 * !fs requests don't need to follow barrier ordering.  Always
-	 * put them at the front.  This fixes the following deadlock.
-	 *
-	 * http://thread.gmane.org/gmane.linux.kernel/537473
-	 */
-	if (rq->cmd_type != REQ_TYPE_FS)
-		return QUEUE_ORDSEQ_DRAIN;
-
-	if ((rq->cmd_flags & REQ_ORDERED_COLOR) ==
-	    (q->orig_bar_rq->cmd_flags & REQ_ORDERED_COLOR))
-		return QUEUE_ORDSEQ_DRAIN;
-	else
-		return QUEUE_ORDSEQ_DONE;
-}
-
-bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
+static struct request *blk_ordered_complete_seq(struct request_queue *q,
+						unsigned seq, int error)
 {
-	struct request *rq;
+	struct request *next_rq = NULL;
 
 	if (error && !q->orderr)
 		q->orderr = error;

@@ -58,16 +32,22 @@ bool blk_ordered_complete_seq(struct request_queue *q, unsigned seq, int error)
 	BUG_ON(q->ordseq & seq);
 	q->ordseq |= seq;
 
-	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE)
-		return false;
-
-	/*
-	 * Okay, sequence complete.
-	 */
-	q->ordseq = 0;
-	rq = q->orig_bar_rq;
-	__blk_end_request_all(rq, q->orderr);
-	return true;
+	if (blk_ordered_cur_seq(q) != QUEUE_ORDSEQ_DONE) {
+		/* not complete yet, queue the next ordered sequence */
+		next_rq = queue_next_ordseq(q);
+	} else {
+		/* complete this barrier request */
+		__blk_end_request_all(q->orig_bar_rq, q->orderr);
+		q->orig_bar_rq = NULL;
+		q->ordseq = 0;
+
+		/* dispatch the next barrier if there's one */
+		if (!list_empty(&q->pending_barriers)) {
+			next_rq = list_entry_rq(q->pending_barriers.next);
+			list_move(&next_rq->queuelist, &q->queue_head);
+		}
+	}
+	return next_rq;
 }
 
 static void pre_flush_end_io(struct request *rq, int error)

@@ -88,133 +68,105 @@ static void post_flush_end_io(struct request *rq, int error)
 	blk_ordered_complete_seq(rq->q, QUEUE_ORDSEQ_POSTFLUSH, error);
 }
 
-static void queue_flush(struct request_queue *q, unsigned which)
+static void queue_flush(struct request_queue *q, struct request *rq,
+			rq_end_io_fn *end_io)
 {
-	struct request *rq;
-	rq_end_io_fn *end_io;
-
-	if (which == QUEUE_ORDERED_DO_PREFLUSH) {
-		rq = &q->pre_flush_rq;
-		end_io = pre_flush_end_io;
-	} else {
-		rq = &q->post_flush_rq;
-		end_io = post_flush_end_io;
-	}
-
 	blk_rq_init(q, rq);
 	rq->cmd_type = REQ_TYPE_FS;
-	rq->cmd_flags = REQ_HARDBARRIER | REQ_FLUSH;
+	rq->cmd_flags = REQ_FLUSH;
 	rq->rq_disk = q->orig_bar_rq->rq_disk;
 	rq->end_io = end_io;
 
 	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 }
 
-static inline struct request *start_ordered(struct request_queue *q,
-					    struct request *rq)
+static struct request *queue_next_ordseq(struct request_queue *q)
 {
-	unsigned skip = 0;
-
-	q->orderr = 0;
-	q->ordered = q->next_ordered;
-	q->ordseq |= QUEUE_ORDSEQ_STARTED;
-
-	/*
-	 * For an empty barrier, there's no actual BAR request, which
-	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
-	 */
-	if (!blk_rq_sectors(rq))
-		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
-				QUEUE_ORDERED_DO_POSTFLUSH);
-
-	/* stash away the original request */
-	blk_dequeue_request(rq);
-	q->orig_bar_rq = rq;
-	rq = NULL;
-
-	/*
-	 * 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.
-	 */
-	if (q->ordered & QUEUE_ORDERED_DO_POSTFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_DO_POSTFLUSH);
-		rq = &q->post_flush_rq;
-	} else
-		skip |= QUEUE_ORDSEQ_POSTFLUSH;
+	struct request *rq = &q->bar_rq;
 
-	if (q->ordered & QUEUE_ORDERED_DO_BAR) {
-		rq = &q->bar_rq;
+	switch (blk_ordered_cur_seq(q)) {
+	case QUEUE_ORDSEQ_PREFLUSH:
+		queue_flush(q, rq, pre_flush_end_io);
+		break;
 
+	case QUEUE_ORDSEQ_BAR:
 		/* initialize proxy request and queue it */
 		blk_rq_init(q, rq);
 		init_request_from_bio(rq, q->orig_bar_rq->bio);
+		rq->cmd_flags &= ~REQ_HARDBARRIER;
 		if (q->ordered & QUEUE_ORDERED_DO_FUA)
 			rq->cmd_flags |= REQ_FUA;
 		rq->end_io = bar_end_io;
 
 		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
-	} else
-		skip |= QUEUE_ORDSEQ_BAR;
+		break;
 
-	if (q->ordered & QUEUE_ORDERED_DO_PREFLUSH) {
-		queue_flush(q, QUEUE_ORDERED_DO_PREFLUSH);
-		rq = &q->pre_flush_rq;
-	} else
-		skip |= QUEUE_ORDSEQ_PREFLUSH;
+	case QUEUE_ORDSEQ_POSTFLUSH:
+		queue_flush(q, rq, post_flush_end_io);
+		break;
 
-	if (queue_in_flight(q))
-		rq = NULL;
-	else
-		skip |= QUEUE_ORDSEQ_DRAIN;
-
-	/*
-	 * Complete skipped sequences.  If whole sequence is complete,
-	 * return %NULL to tell elevator that this request is gone.
-	 */
-	if (blk_ordered_complete_seq(q, skip, 0))
-		rq = NULL;
+	default:
+		BUG();
+	}
 	return rq;
 }
 
 struct request *blk_do_ordered(struct request_queue *q, struct request *rq)
 {
-	const int is_barrier = rq->cmd_type == REQ_TYPE_FS &&
-				(rq->cmd_flags & REQ_HARDBARRIER);
-
-	if (!q->ordseq) {
-		if (!is_barrier)
-			return rq;
-
-		if (q->next_ordered != QUEUE_ORDERED_NONE)
-			return start_ordered(q, rq);
-		else {
-			/*
-			 * Queue ordering not supported.  Terminate
-			 * with prejudice.
-			 */
-			blk_dequeue_request(rq);
-			__blk_end_request_all(rq, -EOPNOTSUPP);
-			return NULL;
-		}
+	unsigned skip = 0;
+
+	if (!(rq->cmd_flags & REQ_HARDBARRIER))
+		return rq;
+
+	if (q->ordseq) {
+		/*
+		 * Barrier is already in progress and they can't be
+		 * processed in parallel.  Queue for later processing.
+		 */
+		list_move_tail(&rq->queuelist, &q->pending_barriers);
+		return NULL;
+	}
+
+	if (unlikely(q->next_ordered == QUEUE_ORDERED_NONE)) {
+		/*
+		 * Queue ordering not supported.  Terminate
+		 * with prejudice.
+		 */
+		blk_dequeue_request(rq);
+		__blk_end_request_all(rq, -EOPNOTSUPP);
+		return NULL;
 	}
 
 	/*
-	 * Ordered sequence in progress
+	 * Start a new ordered sequence
 	 */
+	q->orderr = 0;
+	q->ordered = q->next_ordered;
+	q->ordseq |= QUEUE_ORDSEQ_STARTED;
 
-	/* Special requests are not subject to ordering rules. */
-	if (rq->cmd_type != REQ_TYPE_FS &&
-	    rq != &q->pre_flush_rq && rq != &q->post_flush_rq)
-		return rq;
+	/*
+	 * For an empty barrier, there's no actual BAR request, which
+	 * in turn makes POSTFLUSH unnecessary.  Mask them off.
+	 */
+	if (!blk_rq_sectors(rq))
+		q->ordered &= ~(QUEUE_ORDERED_DO_BAR |
+				QUEUE_ORDERED_DO_POSTFLUSH);
 
-	/* Ordered by draining.  Wait for turn. */
-	WARN_ON(blk_ordered_req_seq(rq) < blk_ordered_cur_seq(q));
-	if (blk_ordered_req_seq(rq) > blk_ordered_cur_seq(q))
-		rq = ERR_PTR(-EAGAIN);
+	/* stash away the original request */
+	blk_dequeue_request(rq);
+	q->orig_bar_rq = rq;
 
-	return rq;
+	if (!(q->ordered & QUEUE_ORDERED_DO_PREFLUSH))
+		skip |= QUEUE_ORDSEQ_PREFLUSH;
+
+	if (!(q->ordered & QUEUE_ORDERED_DO_BAR))
+		skip |= QUEUE_ORDSEQ_BAR;
+
+	if (!(q->ordered & QUEUE_ORDERED_DO_POSTFLUSH))
+		skip |= QUEUE_ORDSEQ_POSTFLUSH;
+
+	/* complete skipped sequences and return the first sequence */
+	return blk_ordered_complete_seq(q, skip, 0);
 }
 
 static void bio_end_empty_barrier(struct bio *bio, int err)

index f8d37a8..d316662 100644
@@ -520,6 +520,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	init_timer(&q->unplug_timer);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
+	INIT_LIST_HEAD(&q->pending_barriers);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);

@@ -1185,6 +1186,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	const bool sync = (bio->bi_rw & REQ_SYNC);
 	const bool unplug = (bio->bi_rw & REQ_UNPLUG);
 	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	int where = ELEVATOR_INSERT_SORT;
 	int rw_flags;
 
 	/* REQ_HARDBARRIER is no more */

@@ -1203,7 +1205,12 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (unlikely((bio->bi_rw & REQ_HARDBARRIER)) || elv_queue_empty(q))
+	if (bio->bi_rw & REQ_HARDBARRIER) {
+		where = ELEVATOR_INSERT_FRONT;
+		goto get_rq;
+	}
+
+	if (elv_queue_empty(q))
 		goto get_rq;
 
 	el_ret = elv_merge(q, &req, bio);

@@ -1303,7 +1310,7 @@ get_rq:
 
 	/* insert the request into the elevator */
 	drive_stat_acct(req, 1);
-	__elv_add_request(q, req, ELEVATOR_INSERT_SORT, 0);
+	__elv_add_request(q, req, where, 0);
 out:
 	if (unplug || !queue_should_plug(q))
 		__generic_unplug_device(q);

index 874eb4e..08081e4 100644
@@ -62,7 +62,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 			rq = list_entry_rq(q->queue_head.next);
 			rq = blk_do_ordered(q, rq);
 			if (rq)
-				return !IS_ERR(rq) ? rq : NULL;
+				return rq;
 		}
 
 		if (!q->elevator->ops->elevator_dispatch_fn(q, 0))

112 lines not on this page · raw message

index ca83a97..9192282 100644
@@ -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)

index 996549d..20a3710 100644
@@ -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 *);

248 lines not on this page · raw message

248 lines not on this page · raw message

index d316662..8870ae4 100644
@@ -136,7 +136,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 {
 	struct request_queue *q = rq->q;
 
-	if (&q->bar_rq != rq) {
+	if (&q->flush_rq != rq) {
 		if (error)
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))

@@ -160,13 +160,12 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		if (bio->bi_size == 0)
 			bio_endio(bio, error);
 	} else {
-
 		/*
-		 * Okay, this is the barrier request in progress, just
-		 * record the error;
+		 * Okay, this is the sequenced flush request in
+		 * progress, just record the error;
 		 */
-		if (error && !q->orderr)
-			q->orderr = error;
+		if (error && !q->flush_err)
+			q->flush_err = error;
 	}
 }
 

@@ -520,7 +519,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	init_timer(&q->unplug_timer);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
-	INIT_LIST_HEAD(&q->pending_barriers);
+	INIT_LIST_HEAD(&q->pending_flushes);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);

@@ -1764,11 +1763,11 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 static void blk_account_io_done(struct request *req)
 {
 	/*
-	 * Account IO completion.  bar_rq isn't accounted as a normal
-	 * IO on queueing nor completion.  Accounting the containing
-	 * request is enough.
+	 * Account IO completion.  flush_rq isn't accounted as a
+	 * normal IO on queueing nor completion.  Accounting the
+	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
+	if (blk_do_io_stat(req) && req != &req->q->flush_rq) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;

191 lines not on this page · raw message

index 08081e4..24b92bd 100644
@@ -51,7 +51,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
-struct request *blk_do_ordered(struct request_queue *q, struct request *rq);
+struct request *blk_do_flush(struct request_queue *q, struct request *rq);
 
 static inline struct request *__elv_next_request(struct request_queue *q)
 {

@@ -60,7 +60,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
-			rq = blk_do_ordered(q, rq);
+			rq = blk_do_flush(q, rq);
 			if (rq)
 				return rq;
 		}

index 20a3710..1cd83ec 100644
@@ -357,13 +357,13 @@ struct request_queue
 	/*
 	 * for flush operations
 	 */
+	unsigned int		ordered, next_ordered;
 	unsigned int		flush_flags;
-
-	unsigned int		ordered, next_ordered, ordseq;
-	int			orderr;
-	struct request		bar_rq;
-	struct request		*orig_bar_rq;
-	struct list_head	pending_barriers;
+	unsigned int		flush_seq;
+	int			flush_err;
+	struct request		flush_rq;
+	struct request		*orig_flush_rq;
+	struct list_head	pending_flushes;
 
 	struct mutex		sysfs_lock;
 

@@ -490,13 +490,13 @@ enum {
 					  QUEUE_ORDERED_DO_FUA,
 
 	/*
-	 * Ordered operation sequence
+	 * FLUSH/FUA sequences.
 	 */
-	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),
+	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
+	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
+	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
+	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
+	QUEUE_FSEQ_DONE		= (1 << 4),
 };
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)

index d316662..8870ae4 100644
@@ -136,7 +136,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 {
 	struct request_queue *q = rq->q;
 
-	if (&q->bar_rq != rq) {
+	if (&q->flush_rq != rq) {
 		if (error)
 			clear_bit(BIO_UPTODATE, &bio->bi_flags);
 		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))

@@ -160,13 +160,12 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		if (bio->bi_size == 0)
 			bio_endio(bio, error);
 	} else {
-
 		/*
-		 * Okay, this is the barrier request in progress, just
-		 * record the error;
+		 * Okay, this is the sequenced flush request in
+		 * progress, just record the error;
 		 */
-		if (error && !q->orderr)
-			q->orderr = error;
+		if (error && !q->flush_err)
+			q->flush_err = error;
 	}
 }
 

@@ -520,7 +519,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	init_timer(&q->unplug_timer);
 	setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
 	INIT_LIST_HEAD(&q->timeout_list);
-	INIT_LIST_HEAD(&q->pending_barriers);
+	INIT_LIST_HEAD(&q->pending_flushes);
 	INIT_WORK(&q->unplug_work, blk_unplug_work);
 
 	kobject_init(&q->kobj, &blk_queue_ktype);

@@ -1764,11 +1763,11 @@ static void blk_account_io_completion(struct request *req, unsigned int bytes)
 static void blk_account_io_done(struct request *req)
 {
 	/*
-	 * Account IO completion.  bar_rq isn't accounted as a normal
-	 * IO on queueing nor completion.  Accounting the containing
-	 * request is enough.
+	 * Account IO completion.  flush_rq isn't accounted as a
+	 * normal IO on queueing nor completion.  Accounting the
+	 * containing request is enough.
 	 */
-	if (blk_do_io_stat(req) && req != &req->q->bar_rq) {
+	if (blk_do_io_stat(req) && req != &req->q->flush_rq) {
 		unsigned long duration = jiffies - req->start_time;
 		const int rw = rq_data_dir(req);
 		struct hd_struct *part;

191 lines not on this page · raw message

index 08081e4..24b92bd 100644
@@ -51,7 +51,7 @@ static inline void blk_clear_rq_complete(struct request *rq)
  */
 #define ELV_ON_HASH(rq)		(!hlist_unhashed(&(rq)->hash))
 
-struct request *blk_do_ordered(struct request_queue *q, struct request *rq);
+struct request *blk_do_flush(struct request_queue *q, struct request *rq);
 
 static inline struct request *__elv_next_request(struct request_queue *q)
 {

@@ -60,7 +60,7 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
-			rq = blk_do_ordered(q, rq);
+			rq = blk_do_flush(q, rq);
 			if (rq)
 				return rq;
 		}

index 20a3710..1cd83ec 100644
@@ -357,13 +357,13 @@ struct request_queue
 	/*
 	 * for flush operations
 	 */
+	unsigned int		ordered, next_ordered;
 	unsigned int		flush_flags;
-
-	unsigned int		ordered, next_ordered, ordseq;
-	int			orderr;
-	struct request		bar_rq;
-	struct request		*orig_bar_rq;
-	struct list_head	pending_barriers;
+	unsigned int		flush_seq;
+	int			flush_err;
+	struct request		flush_rq;
+	struct request		*orig_flush_rq;
+	struct list_head	pending_flushes;
 
 	struct mutex		sysfs_lock;
 

@@ -490,13 +490,13 @@ enum {
 					  QUEUE_ORDERED_DO_FUA,
 
 	/*
-	 * Ordered operation sequence
+	 * FLUSH/FUA sequences.
 	 */
-	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),
+	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
+	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
+	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
+	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
+	QUEUE_FSEQ_DONE		= (1 << 4),
 };
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)

index 8870ae4..18455c4 100644
@@ -1204,7 +1204,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (bio->bi_rw & REQ_HARDBARRIER) {
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
 		where = ELEVATOR_INSERT_FRONT;
 		goto get_rq;
 	}

135 lines not on this page · raw message

index 24b92bd..a09c18b 100644
@@ -60,6 +60,9 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
+			if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) ||
+			    rq == &q->flush_rq)
+				return rq;
 			rq = blk_do_flush(q, rq);
 			if (rq)
 				return rq;

index 9192282..1797994 100644
@@ -167,7 +167,7 @@ enum rq_flag_bits {
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \
-	 REQ_META| REQ_DISCARD | REQ_NOIDLE)
+	 REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)

index 1cd83ec..8ef705f 100644
@@ -357,7 +357,6 @@ struct request_queue
 	/*
 	 * for flush operations
 	 */
-	unsigned int		ordered, next_ordered;
 	unsigned int		flush_flags;
 	unsigned int		flush_seq;
 	int			flush_err;

@@ -465,40 +464,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	__clear_bit(flag, &q->queue_flags);
 }
 
-enum {
-	/*
-	 * Hardbarrier is supported with one of the following methods.
-	 *
-	 * NONE		: hardbarrier unsupported
-	 * DRAIN	: ordering by draining is enough
-	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
-	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
-	 */
-	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
-	QUEUE_ORDERED_DO_BAR		= 0x20,
-	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,
-	QUEUE_ORDERED_DO_FUA		= 0x80,
-
-	QUEUE_ORDERED_NONE		= 0x00,
-
-	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_DRAIN_FUA		= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
-	/*
-	 * FLUSH/FUA sequences.
-	 */
-	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
-	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
-	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
-	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
-	QUEUE_FSEQ_DONE		= (1 << 4),
-};
-
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)

@@ -578,7 +543,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync)
  * it already be started by driver.
  */
 #define RQ_NOMERGE_FLAGS	\
-	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
+	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \
+	 REQ_FLUSH | REQ_FUA)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
 	 (((rq)->cmd_flags & REQ_DISCARD) || \

index ec94c12..fc999f5 100644
@@ -32,7 +32,7 @@ enum bh_state_bits {
 	BH_Delay,	/* Buffer is not yet allocated on disk */
 	BH_Boundary,	/* Block is followed by a discontiguity */
 	BH_Write_EIO,	/* I/O error on write */
-	BH_Eopnotsupp,	/* operation not supported (barrier) */
+	BH_Eopnotsupp,	/* DEPRECATED: operation not supported (barrier) */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 

index 76041b6..352c486 100644
@@ -135,12 +135,13 @@ struct inodes_stat_t {
  *			immediately after submission. The write equivalent
  *			of READ_SYNC.
  * WRITE_ODIRECT_PLUG	Special case write for O_DIRECT only.
- * WRITE_BARRIER	Like WRITE_SYNC, but tells the block layer that all
- *			previously submitted writes must be safely on storage
- *			before this one is started. Also guarantees that when
- *			this write is complete, it itself is also safely on
- *			storage. Prevents reordering of writes on both sides
- *			of this IO.
+ * WRITE_BARRIER	DEPRECATED. Always fails. Use FLUSH/FUA instead.
+ * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
+ *			non-volatile media on completion.
+ * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
+ *			by a cache flush and data is guaranteed to be on
+ *			non-volatile media on completion.
  *
  */
 #define RW_MASK			REQ_WRITE

@@ -158,6 +159,12 @@ struct inodes_stat_t {
 #define WRITE_META		(WRITE | REQ_META)
 #define WRITE_BARRIER		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
 				 REQ_HARDBARRIER)
+#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH)
+#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FUA)
+#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH | REQ_FUA)
 
 /*
  * These aren't really reads or writes, they pass down information about

index 8870ae4..18455c4 100644
@@ -1204,7 +1204,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 
 	spin_lock_irq(q->queue_lock);
 
-	if (bio->bi_rw & REQ_HARDBARRIER) {
+	if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
 		where = ELEVATOR_INSERT_FRONT;
 		goto get_rq;
 	}

135 lines not on this page · raw message

index 24b92bd..a09c18b 100644
@@ -60,6 +60,9 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	while (1) {
 		while (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
+			if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) ||
+			    rq == &q->flush_rq)
+				return rq;
 			rq = blk_do_flush(q, rq);
 			if (rq)
 				return rq;

index 9192282..1797994 100644
@@ -167,7 +167,7 @@ enum rq_flag_bits {
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
 	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_HARDBARRIER | REQ_SYNC | \
-	 REQ_META| REQ_DISCARD | REQ_NOIDLE)
+	 REQ_META | REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)
 #define REQ_RAHEAD		(1 << __REQ_RAHEAD)

index 1cd83ec..8ef705f 100644
@@ -357,7 +357,6 @@ struct request_queue
 	/*
 	 * for flush operations
 	 */
-	unsigned int		ordered, next_ordered;
 	unsigned int		flush_flags;
 	unsigned int		flush_seq;
 	int			flush_err;

@@ -465,40 +464,6 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 	__clear_bit(flag, &q->queue_flags);
 }
 
-enum {
-	/*
-	 * Hardbarrier is supported with one of the following methods.
-	 *
-	 * NONE		: hardbarrier unsupported
-	 * DRAIN	: ordering by draining is enough
-	 * DRAIN_FLUSH	: ordering by draining w/ pre and post flushes
-	 * DRAIN_FUA	: ordering by draining w/ pre flush and FUA write
-	 */
-	QUEUE_ORDERED_DO_PREFLUSH	= 0x10,
-	QUEUE_ORDERED_DO_BAR		= 0x20,
-	QUEUE_ORDERED_DO_POSTFLUSH	= 0x40,
-	QUEUE_ORDERED_DO_FUA		= 0x80,
-
-	QUEUE_ORDERED_NONE		= 0x00,
-
-	QUEUE_ORDERED_DRAIN		= QUEUE_ORDERED_DO_BAR,
-	QUEUE_ORDERED_DRAIN_FLUSH	= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_POSTFLUSH,
-	QUEUE_ORDERED_DRAIN_FUA		= QUEUE_ORDERED_DRAIN |
-					  QUEUE_ORDERED_DO_PREFLUSH |
-					  QUEUE_ORDERED_DO_FUA,
-
-	/*
-	 * FLUSH/FUA sequences.
-	 */
-	QUEUE_FSEQ_STARTED	= (1 << 0), /* flushing in progress */
-	QUEUE_FSEQ_PREFLUSH	= (1 << 1), /* pre-flushing in progress */
-	QUEUE_FSEQ_DATA		= (1 << 2), /* data write in progress */
-	QUEUE_FSEQ_POSTFLUSH	= (1 << 3), /* post-flushing in progress */
-	QUEUE_FSEQ_DONE		= (1 << 4),
-};
-
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)

@@ -578,7 +543,8 @@ static inline void blk_clear_queue_full(struct request_queue *q, int sync)
  * it already be started by driver.
  */
 #define RQ_NOMERGE_FLAGS	\
-	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER)
+	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \
+	 REQ_FLUSH | REQ_FUA)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
 	 (((rq)->cmd_flags & REQ_DISCARD) || \

index ec94c12..fc999f5 100644
@@ -32,7 +32,7 @@ enum bh_state_bits {
 	BH_Delay,	/* Buffer is not yet allocated on disk */
 	BH_Boundary,	/* Block is followed by a discontiguity */
 	BH_Write_EIO,	/* I/O error on write */
-	BH_Eopnotsupp,	/* operation not supported (barrier) */
+	BH_Eopnotsupp,	/* DEPRECATED: operation not supported (barrier) */
 	BH_Unwritten,	/* Buffer is allocated on disk but not written */
 	BH_Quiet,	/* Buffer Error Prinks to be quiet */
 

index 76041b6..352c486 100644
@@ -135,12 +135,13 @@ struct inodes_stat_t {
  *			immediately after submission. The write equivalent
  *			of READ_SYNC.
  * WRITE_ODIRECT_PLUG	Special case write for O_DIRECT only.
- * WRITE_BARRIER	Like WRITE_SYNC, but tells the block layer that all
- *			previously submitted writes must be safely on storage
- *			before this one is started. Also guarantees that when
- *			this write is complete, it itself is also safely on
- *			storage. Prevents reordering of writes on both sides
- *			of this IO.
+ * WRITE_BARRIER	DEPRECATED. Always fails. Use FLUSH/FUA instead.
+ * WRITE_FLUSH		Like WRITE_SYNC but with preceding cache flush.
+ * WRITE_FUA		Like WRITE_SYNC but data is guaranteed to be on
+ *			non-volatile media on completion.
+ * WRITE_FLUSH_FUA	Combination of WRITE_FLUSH and FUA. The IO is preceded
+ *			by a cache flush and data is guaranteed to be on
+ *			non-volatile media on completion.
  *
  */
 #define RW_MASK			REQ_WRITE

@@ -158,6 +159,12 @@ struct inodes_stat_t {
 #define WRITE_META		(WRITE | REQ_META)
 #define WRITE_BARRIER		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
 				 REQ_HARDBARRIER)
+#define WRITE_FLUSH		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH)
+#define WRITE_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FUA)
+#define WRITE_FLUSH_FUA		(WRITE | REQ_SYNC | REQ_NOIDLE | REQ_UNPLUG | \
+				 REQ_FLUSH | REQ_FUA)
 
 /*
  * These aren't really reads or writes, they pass down information about

index 18455c4..495bdc4 100644
@@ -1509,6 +1509,19 @@ static inline void __generic_make_request(struct bio *bio)
 		if (bio_check_eod(bio, nr_sectors))
 			goto end_io;
 
+		/*
+		 * Filter flush bio's early so that make_request based
+		 * drivers without flush support don't have to worry
+		 * about them.
+		 */
+		if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
+			bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
+			if (!nr_sectors) {
+				err = 0;
+				goto end_io;
+			}
+		}
+
 		if ((bio->bi_rw & REQ_DISCARD) &&
 		    (!blk_queue_discard(q) ||
 		     ((bio->bi_rw & REQ_SECURE) &&

index 452c552..ab765c2 100644
@@ -174,13 +174,10 @@ struct request *blk_do_flush(struct request_queue *q, struct request *rq)
 	return blk_flush_complete_seq(q, skip, 0);
 }
 
-static void bio_end_empty_barrier(struct bio *bio, int err)
+static void bio_end_flush(struct bio *bio, int err)
 {
-	if (err) {
-		if (err == -EOPNOTSUPP)
-			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+	if (err)
 		clear_bit(BIO_UPTODATE, &bio->bi_flags);
-	}
 	if (bio->bi_private)
 		complete(bio->bi_private);
 	bio_put(bio);

@@ -218,19 +215,19 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 	 * some block devices may not have their queue correctly set up here
 	 * (e.g. loop device without a backing file) and so issuing a flush
 	 * here will panic. Ensure there is a request function before issuing
-	 * the barrier.
+	 * the flush.
 	 */
 	if (!q->make_request_fn)
 		return -ENXIO;
 
 	bio = bio_alloc(gfp_mask, 0);
-	bio->bi_end_io = bio_end_empty_barrier;
+	bio->bi_end_io = bio_end_flush;
 	bio->bi_bdev = bdev;
 	if (test_bit(BLKDEV_WAIT, &flags))
 		bio->bi_private = &wait;
 
 	bio_get(bio);
-	submit_bio(WRITE_BARRIER, bio);
+	submit_bio(WRITE_FLUSH, bio);
 	if (test_bit(BLKDEV_WAIT, &flags)) {
 		wait_for_completion(&wait);
 		/*

@@ -242,9 +239,7 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask,
 			*error_sector = bio->bi_sector;
 	}
 
-	if (bio_flagged(bio, BIO_EOPNOTSUPP))
-		ret = -EOPNOTSUPP;
-	else if (!bio_flagged(bio, BIO_UPTODATE))
+	if (!bio_flagged(bio, BIO_UPTODATE))
 		ret = -EIO;
 
 	bio_put(bio);

index ab765c2..4e96e18 100644
@@ -74,16 +74,11 @@ static void post_flush_end_io(struct request *rq, int error)
 	blk_flush_complete_seq(rq->q, QUEUE_FSEQ_POSTFLUSH, error);
 }
 
-static void queue_flush(struct request_queue *q, struct request *rq,
-			rq_end_io_fn *end_io)
+static void init_flush_request(struct request *rq, struct gendisk *disk)
 {
-	blk_rq_init(q, rq);
 	rq->cmd_type = REQ_TYPE_FS;
 	rq->cmd_flags = REQ_FLUSH;
-	rq->rq_disk = q->orig_flush_rq->rq_disk;
-	rq->end_io = end_io;
-
-	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
+	rq->rq_disk = disk;
 }
 
 static struct request *queue_next_fseq(struct request_queue *q)

@@ -91,29 +86,28 @@ static struct request *queue_next_fseq(struct request_queue *q)
 	struct request *orig_rq = q->orig_flush_rq;
 	struct request *rq = &q->flush_rq;
 
+	blk_rq_init(q, rq);
+
 	switch (blk_flush_cur_seq(q)) {
 	case QUEUE_FSEQ_PREFLUSH:
-		queue_flush(q, rq, pre_flush_end_io);
+		init_flush_request(rq, orig_rq->rq_disk);
+		rq->end_io = pre_flush_end_io;
 		break;
-
 	case QUEUE_FSEQ_DATA:
-		/* initialize proxy request, inherit FLUSH/FUA and queue it */
-		blk_rq_init(q, rq);
 		init_request_from_bio(rq, orig_rq->bio);
 		rq->cmd_flags &= ~(REQ_FLUSH | REQ_FUA);
 		rq->cmd_flags |= orig_rq->cmd_flags & (REQ_FLUSH | REQ_FUA);
 		rq->end_io = flush_data_end_io;
-
-		elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 		break;
-
 	case QUEUE_FSEQ_POSTFLUSH:
-		queue_flush(q, rq, post_flush_end_io);
+		init_flush_request(rq, orig_rq->rq_disk);
+		rq->end_io = post_flush_end_io;
 		break;
-
 	default:
 		BUG();
 	}
+
+	elv_insert(q, rq, ELEVATOR_INSERT_FRONT);
 	return rq;
 }
 

index 953d1e1..5d27bc6 100644
@@ -477,17 +477,17 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
 
 	if (bio_rw(bio) == WRITE) {
-		bool barrier = (bio->bi_rw & REQ_HARDBARRIER);
 		struct file *file = lo->lo_backing_file;
 
-		if (barrier) {
-			if (unlikely(!file->f_op->fsync)) {
-				ret = -EOPNOTSUPP;
-				goto out;
-			}
+		/* REQ_HARDBARRIER is deprecated */
+		if (bio->bi_rw & REQ_HARDBARRIER) {
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
 
+		if (bio->bi_rw & REQ_FLUSH) {
 			ret = vfs_fsync(file, 0);
-			if (unlikely(ret)) {
+			if (unlikely(ret && ret != -EINVAL)) {
 				ret = -EIO;
 				goto out;
 			}

@@ -495,9 +495,9 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 
 		ret = lo_send(lo, bio, pos);
 
-		if (barrier && !ret) {
+		if ((bio->bi_rw & REQ_FUA) && !ret) {
 			ret = vfs_fsync(file, 0);
-			if (unlikely(ret))
+			if (unlikely(ret && ret != -EINVAL))
 				ret = -EIO;
 		}
 	} else

index d10b635..1260628 100644
@@ -128,9 +128,6 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		}
 	}
 
-	if (vbr->req->cmd_flags & REQ_HARDBARRIER)
-		vbr->out_hdr.type |= VIRTIO_BLK_T_BARRIER;
-
 	sg_set_buf(&vblk->sg[out++], &vbr->out_hdr, sizeof(vbr->out_hdr));
 
 	/*

@@ -388,13 +385,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	vblk->disk->driverfs_dev = &vdev->dev;
 	index++;
 
-	/*
-	 * If the FLUSH feature is supported we do have support for
-	 * flushing a volatile write cache on the host.  Use that to
-	 * implement write barrier support; otherwise, we must assume
-	 * that the host does not perform any kind of volatile write
-	 * caching.
-	 */
+	/* configure queue flush support */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
 		blk_queue_flush(q, REQ_FLUSH);
 

@@ -515,9 +506,9 @@ static const struct virtio_device_id id_table[] = {
 };
 
 static unsigned int features[] = {
-	VIRTIO_BLK_F_BARRIER, VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX,
-	VIRTIO_BLK_F_GEOMETRY, VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE,
-	VIRTIO_BLK_F_SCSI, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY
+	VIRTIO_BLK_F_SEG_MAX, VIRTIO_BLK_F_SIZE_MAX, VIRTIO_BLK_F_GEOMETRY,
+	VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_SCSI,
+	VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY
 };
 
 /*

index e9ce3c5..fbc64b3 100644
@@ -1639,15 +1639,6 @@ static void blk_request(struct virtqueue *vq)
 	off = out->sector * 512;
 
 	/*
-	 * The block device implements "barriers", where the Guest indicates
-	 * that it wants all previous writes to occur before this write.  We
-	 * don't have a way of asking our kernel to do a barrier, so we just
-	 * synchronize all the data in the file.  Pretty poor, no?
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
-	/*
 	 * In general the virtio block driver is allowed to try SCSI commands.
 	 * It'd be nice if we supported eject, for example, but we don't.
 	 */

@@ -1679,6 +1670,13 @@ static void blk_request(struct virtqueue *vq)
 			/* Die, bad Guest, die. */
 			errx(1, "Write past end %llu+%u", off, ret);
 		}
+
+		wlen = sizeof(*in);
+		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+	} else if (out->type & VIRTIO_BLK_T_FLUSH) {
+		/* Flush */
+		ret = fdatasync(vblk->fd);
+		verbose("FLUSH fdatasync: %i\n", ret);
 		wlen = sizeof(*in);
 		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
 	} else {

@@ -1702,15 +1700,6 @@ static void blk_request(struct virtqueue *vq)
 		}
 	}
 
-	/*
-	 * OK, so we noted that it was pretty poor to use an fdatasync as a
-	 * barrier.  But Christoph Hellwig points out that we need a sync
-	 * *afterwards* as well: "Barriers specify no reordering to the front
-	 * or the back."  And Jens Axboe confirmed it, so here we are:
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
 	/* Finished that request. */
 	add_used(vq, head, wlen);
 }

@@ -1735,8 +1724,8 @@ static void setup_block_file(const char *filename)
 	vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
 	vblk->len = lseek64(vblk->fd, 0, SEEK_END);
 
-	/* We support barriers. */
-	add_feature(dev, VIRTIO_BLK_F_BARRIER);
+	/* We support FLUSH. */
+	add_feature(dev, VIRTIO_BLK_F_FLUSH);
 
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);

index e9ce3c5..fbc64b3 100644
@@ -1639,15 +1639,6 @@ static void blk_request(struct virtqueue *vq)
 	off = out->sector * 512;
 
 	/*
-	 * The block device implements "barriers", where the Guest indicates
-	 * that it wants all previous writes to occur before this write.  We
-	 * don't have a way of asking our kernel to do a barrier, so we just
-	 * synchronize all the data in the file.  Pretty poor, no?
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
-	/*
 	 * In general the virtio block driver is allowed to try SCSI commands.
 	 * It'd be nice if we supported eject, for example, but we don't.
 	 */

@@ -1679,6 +1670,13 @@ static void blk_request(struct virtqueue *vq)
 			/* Die, bad Guest, die. */
 			errx(1, "Write past end %llu+%u", off, ret);
 		}
+
+		wlen = sizeof(*in);
+		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
+	} else if (out->type & VIRTIO_BLK_T_FLUSH) {
+		/* Flush */
+		ret = fdatasync(vblk->fd);
+		verbose("FLUSH fdatasync: %i\n", ret);
 		wlen = sizeof(*in);
 		*in = (ret >= 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR);
 	} else {

@@ -1702,15 +1700,6 @@ static void blk_request(struct virtqueue *vq)
 		}
 	}
 
-	/*
-	 * OK, so we noted that it was pretty poor to use an fdatasync as a
-	 * barrier.  But Christoph Hellwig points out that we need a sync
-	 * *afterwards* as well: "Barriers specify no reordering to the front
-	 * or the back."  And Jens Axboe confirmed it, so here we are:
-	 */
-	if (out->type & VIRTIO_BLK_T_BARRIER)
-		fdatasync(vblk->fd);
-
 	/* Finished that request. */
 	add_used(vq, head, wlen);
 }

@@ -1735,8 +1724,8 @@ static void setup_block_file(const char *filename)
 	vblk->fd = open_or_die(filename, O_RDWR|O_LARGEFILE);
 	vblk->len = lseek64(vblk->fd, 0, SEEK_END);
 
-	/* We support barriers. */
-	add_feature(dev, VIRTIO_BLK_F_BARRIER);
+	/* We support FLUSH. */
+	add_feature(dev, VIRTIO_BLK_F_FLUSH);
 
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);

index ba19060..8a2f767 100644
@@ -294,8 +294,8 @@ static int linear_make_request (mddev_t *mddev, struct bio *bio)
 	dev_info_t *tmp_dev;
 	sector_t start_sector;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 

247 lines not on this page · raw message

index a953fe2..d8e2ab2 100644
@@ -87,7 +87,6 @@ struct mdk_rdev_s
 #define	Faulty		1		/* device is known to have a fault */
 #define	In_sync		2		/* device is in_sync with rest of array */
 #define	WriteMostly	4		/* Avoid reading if at all possible */
-#define	BarriersNotsupp	5		/* REQ_HARDBARRIER is not supported */
 #define	AllReserved	6		/* If whole device is reserved for
 					 * one array */
 #define	AutoDetected	7		/* added by auto-detect */

@@ -273,13 +272,6 @@ struct mddev_s
 	int				degraded;	/* whether md should consider
 							 * adding a spare
 							 */
-	int				barriers_work;	/* initialised to true, cleared as soon
-							 * as a barrier request to slave
-							 * fails.  Only supported
-							 */
-	struct bio			*biolist; 	/* bios that need to be retried
-							 * because REQ_HARDBARRIER is not supported
-							 */
 
 	atomic_t			recovery_active; /* blocks scheduled, but not written */
 	wait_queue_head_t		recovery_wait;

@@ -339,16 +331,13 @@ struct mddev_s
 	struct attribute_group		*to_remove;
 	struct plug_handle		*plug; /* if used by personality */
 
-	/* Generic barrier handling.
-	 * If there is a pending barrier request, all other
-	 * writes are blocked while the devices are flushed.
-	 * The last to finish a flush schedules a worker to
-	 * submit the barrier request (without the barrier flag),
-	 * then submit more flush requests.
+	/* Generic flush handling.
+	 * The last to finish preflush schedules a worker to submit
+	 * the rest of the request (without the REQ_FLUSH flag).
 	 */
-	struct bio *barrier;
+	struct bio *flush_bio;
 	atomic_t flush_pending;
-	struct work_struct barrier_work;
+	struct work_struct flush_work;
 	struct work_struct event_work;	/* used by dm to report failure event */
 };
 

@@ -502,7 +491,7 @@ extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
 extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
 
 extern int mddev_congested(mddev_t *mddev, int bits);
-extern void md_barrier_request(mddev_t *mddev, struct bio *bio);
+extern void md_flush_request(mddev_t *mddev, struct bio *bio);
 extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
 			   sector_t sector, int size, struct page *page);
 extern void md_super_wait(mddev_t *mddev);

index 0307d21..6d7ddf3 100644
@@ -142,8 +142,8 @@ static int multipath_make_request(mddev_t *mddev, struct bio * bio)
 	struct multipath_bh * mp_bh;
 	struct multipath_info *multipath;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 

index 6f7af46..a39f4c3 100644
@@ -483,8 +483,8 @@ static int raid0_make_request(mddev_t *mddev, struct bio *bio)
 	struct strip_zone *zone;
 	mdk_rdev_t *tmp_dev;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 

228 lines not on this page · raw message

index 5f2d443..adf8cfd 100644
@@ -117,8 +117,6 @@ struct r1bio_s {
 #define	R1BIO_IsSync	1
 #define	R1BIO_Degraded	2
 #define	R1BIO_BehindIO	3
-#define	R1BIO_Barrier	4
-#define R1BIO_BarrierRetry 5
 /* For write-behind requests, we call bi_end_io when
  * the last non-write-behind device completes, providing
  * any write was successful.  Otherwise we call when

index 8471838..f0d082f 100644
@@ -800,12 +800,13 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
 	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
+	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
 	struct bio_list bl;
 	unsigned long flags;
 	mdk_rdev_t *blocked_rdev;
 
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER)) {
-		md_barrier_request(mddev, bio);
+	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bio);
 		return 0;
 	}
 

@@ -965,7 +966,7 @@ static int make_request(mddev_t *mddev, struct bio * bio)
 			conf->mirrors[d].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE | do_sync;
+		mbio->bi_rw = WRITE | do_sync | do_fua;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);

99 lines not on this page · raw message

index 36eaed5..2ace058 100644
@@ -275,6 +275,7 @@ struct r6_state {
 				    * filling
 				    */
 #define R5_Wantdrain	13 /* dev->towrite needs to be drained */
+#define R5_WantFUA	14	/* Write should be FUA */
 /*
  * Write method
  */

index 4b4ad4b..df44b34 100644
@@ -2566,7 +2566,8 @@ static inline void ext4_issue_discard(struct super_block *sb,
 	discard_block = block + ext4_group_first_block_no(sb, block_group);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
-	ret = sb_issue_discard(sb, discard_block, count);
+	ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS,
+			       BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 	if (ret == EOPNOTSUPP) {
 		ext4_warning(sb, "discard not supported, disabling");
 		clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);

index 81184d3..3a56a82 100644
@@ -577,7 +577,9 @@ int fat_free_clusters(struct inode *inode, int cluster)
 
 				sb_issue_discard(sb,
 					fat_clus_to_blknr(sbi, first_cl),
-					nr_clus * sbi->sec_per_clus);
+					nr_clus * sbi->sec_per_clus,
+					GFP_NOFS,
+					BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 
 				first_cl = cluster;
 			}

index 8ef705f..6b305eb 100644
@@ -881,13 +881,12 @@ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
-static inline int sb_issue_discard(struct super_block *sb,
-				   sector_t block, sector_t nr_blocks)
+static inline int sb_issue_discard(struct super_block *sb, sector_t block,
+		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
-	block <<= (sb->s_blocksize_bits - 9);
-	nr_blocks <<= (sb->s_blocksize_bits - 9);
-	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS,
-				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+	return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
+				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    gfp_mask, flags);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);

index 4b4ad4b..df44b34 100644
@@ -2566,7 +2566,8 @@ static inline void ext4_issue_discard(struct super_block *sb,
 	discard_block = block + ext4_group_first_block_no(sb, block_group);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
-	ret = sb_issue_discard(sb, discard_block, count);
+	ret = sb_issue_discard(sb, discard_block, count, GFP_NOFS,
+			       BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 	if (ret == EOPNOTSUPP) {
 		ext4_warning(sb, "discard not supported, disabling");
 		clear_opt(EXT4_SB(sb)->s_mount_opt, DISCARD);

index 81184d3..3a56a82 100644
@@ -577,7 +577,9 @@ int fat_free_clusters(struct inode *inode, int cluster)
 
 				sb_issue_discard(sb,
 					fat_clus_to_blknr(sbi, first_cl),
-					nr_clus * sbi->sec_per_clus);
+					nr_clus * sbi->sec_per_clus,
+					GFP_NOFS,
+					BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
 
 				first_cl = cluster;
 			}

index 8ef705f..6b305eb 100644
@@ -881,13 +881,12 @@ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 			sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
-static inline int sb_issue_discard(struct super_block *sb,
-				   sector_t block, sector_t nr_blocks)
+static inline int sb_issue_discard(struct super_block *sb, sector_t block,
+		sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags)
 {
-	block <<= (sb->s_blocksize_bits - 9);
-	nr_blocks <<= (sb->s_blocksize_bits - 9);
-	return blkdev_issue_discard(sb->s_bdev, block, nr_blocks, GFP_NOFS,
-				   BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+	return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9),
+				    nr_blocks << (sb->s_blocksize_bits - 9),
+				    gfp_mask, flags);
 }
 
 extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm);

index ea79072..b93ea33 100644
@@ -929,19 +929,7 @@ xfs_buf_iodone_work(
 	xfs_buf_t		*bp =
 		container_of(work, xfs_buf_t, b_iodone_work);
 
-	/*
-	 * We can get an EOPNOTSUPP to ordered writes.  Here we clear the
-	 * ordered flag and reissue them.  Because we can't tell the higher
-	 * layers directly that they should not issue ordered I/O anymore, they
-	 * need to check if the _XFS_BARRIER_FAILED flag was set during I/O completion.
-	 */
-	if ((bp->b_error == EOPNOTSUPP) &&
-	    (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) {
-		trace_xfs_buf_ordered_retry(bp, _RET_IP_);
-		bp->b_flags &= ~XBF_ORDERED;
-		bp->b_flags |= _XFS_BARRIER_FAILED;
-		xfs_buf_iorequest(bp);
-	} else if (bp->b_iodone)
+	if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
 	else if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);

@@ -1200,7 +1188,7 @@ _xfs_buf_ioapply(
 
 	if (bp->b_flags & XBF_ORDERED) {
 		ASSERT(!(bp->b_flags & XBF_READ));
-		rw = WRITE_BARRIER;
+		rw = WRITE_FLUSH_FUA;
 	} else if (bp->b_flags & XBF_LOG_BUFFER) {
 		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
 		bp->b_flags &= ~_XBF_RUN_QUEUES;

index d072e5f..d533d64 100644
@@ -86,14 +86,6 @@ typedef enum {
  */
 #define _XBF_PAGE_LOCKED	(1 << 22)
 
-/*
- * If we try a barrier write, but it fails we have to communicate
- * this to the upper layers.  Unfortunately b_error gets overwritten
- * when the buffer is re-issued so we have to add another flag to
- * keep this information.
- */
-#define _XFS_BARRIER_FAILED	(1 << 23)
-
 typedef unsigned int xfs_buf_flags_t;
 
 #define XFS_BUF_FLAGS \

@@ -114,8 +106,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_RUN_QUEUES,	"RUN_QUEUES" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
-	{ _XBF_PAGE_LOCKED,	"PAGE_LOCKED" }, \
-	{ _XFS_BARRIER_FAILED,	"BARRIER_FAILED" }
+	{ _XBF_PAGE_LOCKED,	"PAGE_LOCKED" }
 
 
 typedef enum {

index be5dffd..8fe311a 100644
@@ -325,7 +325,6 @@ DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
 DEFINE_BUF_EVENT(xfs_buf_cond_lock);
 DEFINE_BUF_EVENT(xfs_buf_unlock);
-DEFINE_BUF_EVENT(xfs_buf_ordered_retry);
 DEFINE_BUF_EVENT(xfs_buf_iowait);
 DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);

index 925d572..430a8fc 100644
@@ -917,19 +917,6 @@ xlog_iodone(xfs_buf_t *bp)
 	l = iclog->ic_log;
 
 	/*
-	 * If the _XFS_BARRIER_FAILED flag was set by a lower
-	 * layer, it means the underlying device no longer supports
-	 * barrier I/O. Warn loudly and turn off barriers.
-	 */
-	if (bp->b_flags & _XFS_BARRIER_FAILED) {
-		bp->b_flags &= ~_XFS_BARRIER_FAILED;
-		l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		xfs_fs_cmn_err(CE_WARN, l->l_mp,
-				"xlog_iodone: Barriers are no longer supported"
-				" by device. Disabling barriers\n");
-	}
-
-	/*
 	 * Race to shutdown the filesystem if we see an error.
 	 */
 	if (XFS_TEST_ERROR((XFS_BUF_GETERROR(bp)), l->l_mp,

index ea79072..b93ea33 100644
@@ -929,19 +929,7 @@ xfs_buf_iodone_work(
 	xfs_buf_t		*bp =
 		container_of(work, xfs_buf_t, b_iodone_work);
 
-	/*
-	 * We can get an EOPNOTSUPP to ordered writes.  Here we clear the
-	 * ordered flag and reissue them.  Because we can't tell the higher
-	 * layers directly that they should not issue ordered I/O anymore, they
-	 * need to check if the _XFS_BARRIER_FAILED flag was set during I/O completion.
-	 */
-	if ((bp->b_error == EOPNOTSUPP) &&
-	    (bp->b_flags & (XBF_ORDERED|XBF_ASYNC)) == (XBF_ORDERED|XBF_ASYNC)) {
-		trace_xfs_buf_ordered_retry(bp, _RET_IP_);
-		bp->b_flags &= ~XBF_ORDERED;
-		bp->b_flags |= _XFS_BARRIER_FAILED;
-		xfs_buf_iorequest(bp);
-	} else if (bp->b_iodone)
+	if (bp->b_iodone)
 		(*(bp->b_iodone))(bp);
 	else if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);

@@ -1200,7 +1188,7 @@ _xfs_buf_ioapply(
 
 	if (bp->b_flags & XBF_ORDERED) {
 		ASSERT(!(bp->b_flags & XBF_READ));
-		rw = WRITE_BARRIER;
+		rw = WRITE_FLUSH_FUA;
 	} else if (bp->b_flags & XBF_LOG_BUFFER) {
 		ASSERT(!(bp->b_flags & XBF_READ_AHEAD));
 		bp->b_flags &= ~_XBF_RUN_QUEUES;

index d072e5f..d533d64 100644
@@ -86,14 +86,6 @@ typedef enum {
  */
 #define _XBF_PAGE_LOCKED	(1 << 22)
 
-/*
- * If we try a barrier write, but it fails we have to communicate
- * this to the upper layers.  Unfortunately b_error gets overwritten
- * when the buffer is re-issued so we have to add another flag to
- * keep this information.
- */
-#define _XFS_BARRIER_FAILED	(1 << 23)
-
 typedef unsigned int xfs_buf_flags_t;
 
 #define XFS_BUF_FLAGS \

@@ -114,8 +106,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_RUN_QUEUES,	"RUN_QUEUES" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
-	{ _XBF_PAGE_LOCKED,	"PAGE_LOCKED" }, \
-	{ _XFS_BARRIER_FAILED,	"BARRIER_FAILED" }
+	{ _XBF_PAGE_LOCKED,	"PAGE_LOCKED" }
 
 
 typedef enum {

index be5dffd..8fe311a 100644
@@ -325,7 +325,6 @@ DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
 DEFINE_BUF_EVENT(xfs_buf_cond_lock);
 DEFINE_BUF_EVENT(xfs_buf_unlock);
-DEFINE_BUF_EVENT(xfs_buf_ordered_retry);
 DEFINE_BUF_EVENT(xfs_buf_iowait);
 DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);

index 925d572..430a8fc 100644
@@ -917,19 +917,6 @@ xlog_iodone(xfs_buf_t *bp)
 	l = iclog->ic_log;
 
 	/*
-	 * If the _XFS_BARRIER_FAILED flag was set by a lower
-	 * layer, it means the underlying device no longer supports
-	 * barrier I/O. Warn loudly and turn off barriers.
-	 */
-	if (bp->b_flags & _XFS_BARRIER_FAILED) {
-		bp->b_flags &= ~_XFS_BARRIER_FAILED;
-		l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER;
-		xfs_fs_cmn_err(CE_WARN, l->l_mp,
-				"xlog_iodone: Barriers are no longer supported"
-				" by device. Disabling barriers\n");
-	}
-
-	/*
 	 * Race to shutdown the filesystem if we see an error.
 	 */
 	if (XFS_TEST_ERROR((XFS_BUF_GETERROR(bp)), l->l_mp,

index 64f1008..5e789f4 100644
@@ -2063,7 +2063,7 @@ static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 	if (uptodate) {
 		set_buffer_uptodate(bh);
 	} else {
-		if (!buffer_eopnotsupp(bh) && printk_ratelimit()) {
+		if (printk_ratelimit()) {
 			printk(KERN_WARNING "lost page write due to "
 					"I/O error on %s\n",
 				       bdevname(bh->b_bdev, b));

@@ -2200,21 +2200,10 @@ static int write_dev_supers(struct btrfs_device *device,
 			bh->b_end_io = btrfs_end_buffer_write_sync;
 		}
 
-		if (i == last_barrier && do_barriers && device->barriers) {
-			ret = submit_bh(WRITE_BARRIER, bh);
-			if (ret == -EOPNOTSUPP) {
-				printk("btrfs: disabling barriers on dev %s\n",
-				       device->name);
-				set_buffer_uptodate(bh);
-				device->barriers = 0;
-				/* one reference for submit_bh */
-				get_bh(bh);
-				lock_buffer(bh);
-				ret = submit_bh(WRITE_SYNC, bh);
-			}
-		} else {
+		if (i == last_barrier && do_barriers)
+			ret = submit_bh(WRITE_FLUSH_FUA, bh);
+		else
 			ret = submit_bh(WRITE_SYNC, bh);
-		}
 
 		if (ret)
 			errors++;

index 32d0940..43dc9ea 100644
@@ -1696,7 +1696,7 @@ static void btrfs_issue_discard(struct block_device *bdev,
 				u64 start, u64 len)
 {
 	blkdev_issue_discard(bdev, start >> 9, len >> 9, GFP_KERNEL,
-			BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
+			BLKDEV_IFL_WAIT);
 }
 
 static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,

index dd318ff..e25e46a 100644
@@ -398,7 +398,6 @@ static noinline int device_list_add(const char *path,
 		device->work.func = pending_bios_fn;
 		memcpy(device->uuid, disk_super->dev_item.uuid,
 		       BTRFS_UUID_SIZE);
-		device->barriers = 1;
 		spin_lock_init(&device->io_lock);
 		device->name = kstrdup(path, GFP_NOFS);
 		if (!device->name) {

@@ -462,7 +461,6 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		device->devid = orig_dev->devid;
 		device->work.func = pending_bios_fn;
 		memcpy(device->uuid, orig_dev->uuid, sizeof(device->uuid));
-		device->barriers = 1;
 		spin_lock_init(&device->io_lock);
 		INIT_LIST_HEAD(&device->dev_list);
 		INIT_LIST_HEAD(&device->dev_alloc_list);

@@ -1489,7 +1487,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	trans = btrfs_start_transaction(root, 0);
 	lock_chunks(root);
 
-	device->barriers = 1;
 	device->writeable = 1;
 	device->work.func = pending_bios_fn;
 	generate_random_uuid(device->uuid);

@@ -3084,7 +3081,6 @@ static struct btrfs_device *add_missing_dev(struct btrfs_root *root,
 		return NULL;
 	list_add(&device->dev_list,
 		 &fs_devices->devices);
-	device->barriers = 1;
 	device->dev_root = root->fs_info->dev_root;
 	device->devid = devid;
 	device->work.func = pending_bios_fn;

index 31b0fab..2b638b6 100644
@@ -42,7 +42,6 @@ struct btrfs_device {
 	int running_pending;
 	u64 generation;
 
-	int barriers;
 	int writeable;
 	int in_fs_metadata;
 

index cde1248..9c65170 100644
@@ -592,22 +592,13 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	lh->lh_hash = cpu_to_be32(hash);
 
 	bh->b_end_io = end_buffer_write_sync;
-	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
-		goto skip_barrier;
 	get_bh(bh);
-	submit_bh(WRITE_BARRIER | REQ_META, bh);
-	wait_on_buffer(bh);
-	if (buffer_eopnotsupp(bh)) {
-		clear_buffer_eopnotsupp(bh);
-		set_buffer_uptodate(bh);
-		fs_info(sdp, "barrier sync failed - disabling barriers\n");
-		set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
-		lock_buffer(bh);
-skip_barrier:
-		get_bh(bh);
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
 		submit_bh(WRITE_SYNC | REQ_META, bh);
-		wait_on_buffer(bh);
-	}
+	else
+		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
+	wait_on_buffer(bh);
+
 	if (!buffer_uptodate(bh))
 		gfs2_io_error_bh(sdp, bh);
 	brelse(bh);