block: convert to REQ_FLUSH/FUA

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 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..ed0fb7d 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));
 
 	/*

@@ -157,6 +154,8 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		if (rq_data_dir(vbr->req) == WRITE) {
 			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
 			out += num;
+			if (req->cmd_flags & REQ_FUA)
+				vbr->out_hdr.type |= VIRTIO_BLK_T_FUA;
 		} else {
 			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
 			in += num;

@@ -307,6 +306,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
 	struct request_queue *q;
+	unsigned int flush;
 	int err;
 	u64 cap;
 	u32 v, blk_size, sg_elems, opt_io_size;

@@ -388,15 +388,13 @@ 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 */
+	flush = 0;
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
-		blk_queue_flush(q, REQ_FLUSH);
+		flush |= REQ_FLUSH;
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FUA))
+		flush |= REQ_FUA;
+	blk_queue_flush(q, flush);
 
 	/* If disk is read-only in the host, the guest should obey */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))

@@ -515,9 +513,9 @@ 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, VIRTIO_BLK_F_FUA,
 };
 
 /*

index 167720d..f453f3c 100644
@@ -16,6 +16,7 @@
 #define VIRTIO_BLK_F_SCSI	7	/* Supports scsi command passthru */
 #define VIRTIO_BLK_F_FLUSH	9	/* Cache flush command support */
 #define VIRTIO_BLK_F_TOPOLOGY	10	/* Topology information is available */
+#define VIRTIO_BLK_F_FUA	11	/* Forced Unit Access write support */
 
 #define VIRTIO_BLK_ID_BYTES	20	/* ID string length */
 

@@ -70,7 +71,10 @@ struct virtio_blk_config {
 #define VIRTIO_BLK_T_FLUSH	4
 
 /* Get device ID command */
-#define VIRTIO_BLK_T_GET_ID    8
+#define VIRTIO_BLK_T_GET_ID	8
+
+/* FUA command */
+#define VIRTIO_BLK_T_FUA	16
 
 /* Barrier before this op. */
 #define VIRTIO_BLK_T_BARRIER	0x80000000

Index: block/drivers/block/virtio_blk.c
===================================================================
@@ -128,9 +128,6 @@ static bool do_req(struct request_queue
 		}
 	}
 
-	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(struc
 	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_
 };
 
 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 d10b635..ed0fb7d 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));
 
 	/*

@@ -157,6 +154,8 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		if (rq_data_dir(vbr->req) == WRITE) {
 			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
 			out += num;
+			if (req->cmd_flags & REQ_FUA)
+				vbr->out_hdr.type |= VIRTIO_BLK_T_FUA;
 		} else {
 			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
 			in += num;

@@ -307,6 +306,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 {
 	struct virtio_blk *vblk;
 	struct request_queue *q;
+	unsigned int flush;
 	int err;
 	u64 cap;
 	u32 v, blk_size, sg_elems, opt_io_size;

@@ -388,15 +388,13 @@ 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 */
+	flush = 0;
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FLUSH))
-		blk_queue_flush(q, REQ_FLUSH);
+		flush |= REQ_FLUSH;
+	if (virtio_has_feature(vdev, VIRTIO_BLK_F_FUA))
+		flush |= REQ_FUA;
+	blk_queue_flush(q, flush);
 
 	/* If disk is read-only in the host, the guest should obey */
 	if (virtio_has_feature(vdev, VIRTIO_BLK_F_RO))

@@ -515,9 +513,9 @@ 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, VIRTIO_BLK_F_FUA,
 };
 
 /*

index 167720d..f453f3c 100644
@@ -16,6 +16,7 @@
 #define VIRTIO_BLK_F_SCSI	7	/* Supports scsi command passthru */
 #define VIRTIO_BLK_F_FLUSH	9	/* Cache flush command support */
 #define VIRTIO_BLK_F_TOPOLOGY	10	/* Topology information is available */
+#define VIRTIO_BLK_F_FUA	11	/* Forced Unit Access write support */
 
 #define VIRTIO_BLK_ID_BYTES	20	/* ID string length */
 

@@ -70,7 +71,10 @@ struct virtio_blk_config {
 #define VIRTIO_BLK_T_FLUSH	4
 
 /* Get device ID command */
-#define VIRTIO_BLK_T_GET_ID    8
+#define VIRTIO_BLK_T_GET_ID	8
+
+/* FUA command */
+#define VIRTIO_BLK_T_FUA	16
 
 /* Barrier before this op. */
 #define VIRTIO_BLK_T_BARRIER	0x80000000

index e9ce3c5..3be47d4 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 +1670,19 @@ static void blk_request(struct virtqueue *vq)
 			/* Die, bad Guest, die. */
 			errx(1, "Write past end %llu+%u", off, ret);
 		}
+
+		/* Honor FUA by syncing everything. */
+		if (ret >= 0 && (out->type & VIRTIO_BLK_T_FUA)) {
+			ret = fdatasync(vblk->fd);
+			verbose("FUA fdatasync: %i\n", 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 +1706,6 @@ 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 +1730,9 @@ 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 and FUA. */
+	add_feature(dev, VIRTIO_BLK_F_FLUSH);
+	add_feature(dev, VIRTIO_BLK_F_FUA);
 
 	/* Tell Guest how many sectors this device has. */
 	conf.capacity = cpu_to_le64(vblk->len / 512);

Index: block/Documentation/lguest/lguest.c
===================================================================
@@ -1639,15 +1639,6 @@ static void blk_request(struct virtqueue
 	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
 			/* 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
 		}
 	}
 
-	/*
-	 * 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
 	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..3be47d4 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 +1670,19 @@ static void blk_request(struct virtqueue *vq)
 			/* Die, bad Guest, die. */
 			errx(1, "Write past end %llu+%u", off, ret);
 		}
+
+		/* Honor FUA by syncing everything. */
+		if (ret >= 0 && (out->type & VIRTIO_BLK_T_FUA)) {
+			ret = fdatasync(vblk->fd);
+			verbose("FUA fdatasync: %i\n", 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 +1706,6 @@ 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 +1730,9 @@ 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 and FUA. */
+	add_feature(dev, VIRTIO_BLK_F_FLUSH);
+	add_feature(dev, VIRTIO_BLK_F_FUA);
 
 	/* 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 fc56e0f..de4a365 100644
@@ -67,7 +67,6 @@ 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 */

@@ -249,13 +248,6 @@ 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;

@@ -308,16 +300,13 @@ struct mddev_s
 	struct list_head		all_mddevs;
 
 	struct attribute_group		*to_remove;
-	/* 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;
 };
 
 

@@ -458,7 +447,7 @@ 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 5551ccf..cc00c10 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 int do_sync = (bio->bi_rw & REQ_SYNC);
+	const unsigned int 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;
 	}
 

@@ -947,7 +948,7 @@ 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);

index 20ac2f1..7eabd99 100644
@@ -507,9 +507,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 		int rw;
 		struct bio *bi;
 		mdk_rdev_t *rdev;
-		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-			rw = WRITE;
-		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
+		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
+			if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
+				rw = WRITE_FUA;
+			else
+				rw = WRITE;
+		} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
 			rw = READ;
 		else
 			continue;

@@ -1032,6 +1035,8 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 
 			while (wbi && wbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
+				if (wbi->bi_rw & REQ_FUA)
+					set_bit(R5_WantFUA, &dev->flags);
 				tx = async_copy_data(1, wbi, dev->page,
 					dev->sector, tx);
 				wbi = r5_next_bio(wbi, dev->sector);

@@ -1049,15 +1054,22 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
 	int pd_idx = sh->pd_idx;
 	int qd_idx = sh->qd_idx;
 	int i;
+	bool fua = false;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
+	for (i = disks; i--; )
+		fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
+
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
-		if (dev->written || i == pd_idx || i == qd_idx)
+		if (dev->written || i == pd_idx || i == qd_idx) {
 			set_bit(R5_UPTODATE, &dev->flags);
+			if (fua)
+				set_bit(R5_WantFUA, &dev->flags);
+		}
 	}
 
 	if (sh->reconstruct_state == reconstruct_state_drain_run)

@@ -3278,7 +3290,7 @@ static void handle_stripe5(struct stripe_head *sh)
 
 	if (dec_preread_active) {
 		/* We delay this until after ops_run_io so that if make_request
-		 * is waiting on a barrier, it won't continue until the writes
+		 * is waiting on a flush, it won't continue until the writes
 		 * have actually been submitted.
 		 */
 		atomic_dec(&conf->preread_active_stripes);

@@ -3580,7 +3592,7 @@ static void handle_stripe6(struct stripe_head *sh)
 
 	if (dec_preread_active) {
 		/* We delay this until after ops_run_io so that if make_request
-		 * is waiting on a barrier, it won't continue until the writes
+		 * is waiting on a flush, it won't continue until the writes
 		 * have actually been submitted.
 		 */
 		atomic_dec(&conf->preread_active_stripes);

@@ -3958,14 +3970,8 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 	const int rw = bio_data_dir(bi);
 	int remaining;
 
-	if (unlikely(bi->bi_rw & REQ_HARDBARRIER)) {
-		/* Drain all pending writes.  We only really need
-		 * to ensure they have been submitted, but this is
-		 * easier.
-		 */
-		mddev->pers->quiesce(mddev, 1);
-		mddev->pers->quiesce(mddev, 0);
-		md_barrier_request(mddev, bi);
+	if (unlikely(bi->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bi);
 		return 0;
 	}
 

@@ -4083,7 +4089,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 			finish_wait(&conf->wait_for_overlap, &w);
 			set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
-			if (mddev->barrier && 
+			if (mddev->flush_bio &&
 			    !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 				atomic_inc(&conf->preread_active_stripes);
 			release_stripe(sh);

@@ -4106,7 +4112,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 		bio_endio(bi, 0);
 	}
 
-	if (mddev->barrier) {
+	if (mddev->flush_bio) {
 		/* We need to wait for the stripes to all be handled.
 		 * So: wait for preread_active_stripes to drop to 0.
 		 */

index 0f86f5e..ff9cad2 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: block/drivers/md/linear.c
===================================================================
@@ -294,8 +294,8 @@ static int linear_make_request (mddev_t
 	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: block/drivers/md/md.h
===================================================================
@@ -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,
 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: block/drivers/md/raid0.c
===================================================================
@@ -483,8 +483,8 @@ static int raid0_make_request(mddev_t *m
 	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;
 	}
 

227 lines not on this page · raw message

Index: block/drivers/md/raid1.h
===================================================================
@@ -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

99 lines not on this page · raw message

Index: block/drivers/md/multipath.c
===================================================================
@@ -142,8 +142,8 @@ static int multipath_make_request(mddev_
 	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: block/drivers/md/raid10.c
===================================================================
@@ -800,12 +800,13 @@ static int make_request(mddev_t *mddev,
 	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,
 			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);

Index: block/drivers/md/raid5.h
===================================================================
@@ -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 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 fc56e0f..de4a365 100644
@@ -67,7 +67,6 @@ 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 */

@@ -249,13 +248,6 @@ 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;

@@ -308,16 +300,13 @@ struct mddev_s
 	struct list_head		all_mddevs;
 
 	struct attribute_group		*to_remove;
-	/* 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;
 };
 
 

@@ -458,7 +447,7 @@ 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 5551ccf..cc00c10 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 int do_sync = (bio->bi_rw & REQ_SYNC);
+	const unsigned int 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;
 	}
 

@@ -947,7 +948,7 @@ 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);

index 20ac2f1..7eabd99 100644
@@ -507,9 +507,12 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 		int rw;
 		struct bio *bi;
 		mdk_rdev_t *rdev;
-		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
-			rw = WRITE;
-		else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
+		if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
+			if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
+				rw = WRITE_FUA;
+			else
+				rw = WRITE;
+		} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
 			rw = READ;
 		else
 			continue;

@@ -1032,6 +1035,8 @@ ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
 
 			while (wbi && wbi->bi_sector <
 				dev->sector + STRIPE_SECTORS) {
+				if (wbi->bi_rw & REQ_FUA)
+					set_bit(R5_WantFUA, &dev->flags);
 				tx = async_copy_data(1, wbi, dev->page,
 					dev->sector, tx);
 				wbi = r5_next_bio(wbi, dev->sector);

@@ -1049,15 +1054,22 @@ static void ops_complete_reconstruct(void *stripe_head_ref)
 	int pd_idx = sh->pd_idx;
 	int qd_idx = sh->qd_idx;
 	int i;
+	bool fua = false;
 
 	pr_debug("%s: stripe %llu\n", __func__,
 		(unsigned long long)sh->sector);
 
+	for (i = disks; i--; )
+		fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
+
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 
-		if (dev->written || i == pd_idx || i == qd_idx)
+		if (dev->written || i == pd_idx || i == qd_idx) {
 			set_bit(R5_UPTODATE, &dev->flags);
+			if (fua)
+				set_bit(R5_WantFUA, &dev->flags);
+		}
 	}
 
 	if (sh->reconstruct_state == reconstruct_state_drain_run)

@@ -3278,7 +3290,7 @@ static void handle_stripe5(struct stripe_head *sh)
 
 	if (dec_preread_active) {
 		/* We delay this until after ops_run_io so that if make_request
-		 * is waiting on a barrier, it won't continue until the writes
+		 * is waiting on a flush, it won't continue until the writes
 		 * have actually been submitted.
 		 */
 		atomic_dec(&conf->preread_active_stripes);

@@ -3580,7 +3592,7 @@ static void handle_stripe6(struct stripe_head *sh)
 
 	if (dec_preread_active) {
 		/* We delay this until after ops_run_io so that if make_request
-		 * is waiting on a barrier, it won't continue until the writes
+		 * is waiting on a flush, it won't continue until the writes
 		 * have actually been submitted.
 		 */
 		atomic_dec(&conf->preread_active_stripes);

@@ -3958,14 +3970,8 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 	const int rw = bio_data_dir(bi);
 	int remaining;
 
-	if (unlikely(bi->bi_rw & REQ_HARDBARRIER)) {
-		/* Drain all pending writes.  We only really need
-		 * to ensure they have been submitted, but this is
-		 * easier.
-		 */
-		mddev->pers->quiesce(mddev, 1);
-		mddev->pers->quiesce(mddev, 0);
-		md_barrier_request(mddev, bi);
+	if (unlikely(bi->bi_rw & REQ_FLUSH)) {
+		md_flush_request(mddev, bi);
 		return 0;
 	}
 

@@ -4083,7 +4089,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 			finish_wait(&conf->wait_for_overlap, &w);
 			set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
-			if (mddev->barrier && 
+			if (mddev->flush_bio &&
 			    !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
 				atomic_inc(&conf->preread_active_stripes);
 			release_stripe(sh);

@@ -4106,7 +4112,7 @@ static int make_request(mddev_t *mddev, struct bio * bi)
 		bio_endio(bi, 0);
 	}
 
-	if (mddev->barrier) {
+	if (mddev->flush_bio) {
 		/* We need to wait for the stripes to all be handled.
 		 * So: wait for preread_active_stripes to drop to 0.
 		 */

index 0f86f5e..ff9cad2 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 3bdbb61..da11652 100644
@@ -1249,7 +1249,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio,
 	struct dm_crypt_io *io;
 	struct crypt_config *cc;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		cc = ti->private;
 		bio->bi_bdev = cc->dev->bdev;
 		return DM_MAPIO_REMAPPED;

index 0590c75..136d4f7 100644
@@ -31,7 +31,6 @@ struct dm_io_client {
  */
 struct io {
 	unsigned long error_bits;
-	unsigned long eopnotsupp_bits;
 	atomic_t count;
 	struct task_struct *sleeper;
 	struct dm_io_client *client;

@@ -130,11 +129,8 @@ static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io,
  *---------------------------------------------------------------*/
 static void dec_count(struct io *io, unsigned int region, int error)
 {
-	if (error) {
+	if (error)
 		set_bit(region, &io->error_bits);
-		if (error == -EOPNOTSUPP)
-			set_bit(region, &io->eopnotsupp_bits);
-	}
 
 	if (atomic_dec_and_test(&io->count)) {
 		if (io->sleeper)

@@ -310,8 +306,8 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 	sector_t remaining = where->count;
 
 	/*
-	 * where->count may be zero if rw holds a write barrier and we
-	 * need to send a zero-sized barrier.
+	 * where->count may be zero if rw holds a flush and we need to
+	 * send a zero-sized flush.
 	 */
 	do {
 		/*

@@ -364,7 +360,7 @@ static void dispatch_io(int rw, unsigned int num_regions,
 	 */
 	for (i = 0; i < num_regions; i++) {
 		*dp = old_pages;
-		if (where[i].count || (rw & REQ_HARDBARRIER))
+		if (where[i].count || (rw & REQ_FLUSH))
 			do_region(rw, i, where + i, dp, io);
 	}
 

@@ -393,9 +389,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 		return -EIO;
 	}
 
-retry:
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = current;
 	io->client = client;

@@ -412,11 +406,6 @@ retry:
 	}
 	set_current_state(TASK_RUNNING);
 
-	if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) {
-		rw &= ~REQ_HARDBARRIER;
-		goto retry;
-	}
-
 	if (error_bits)
 		*error_bits = io->error_bits;
 

@@ -437,7 +426,6 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = NULL;
 	io->client = client;

index 5a08be0..33420e6 100644
@@ -300,7 +300,7 @@ static int flush_header(struct log_c *lc)
 		.count = 0,
 	};
 
-	lc->io_req.bi_rw = WRITE_BARRIER;
+	lc->io_req.bi_rw = WRITE_FLUSH;
 
 	return dm_io(&lc->io_req, 1, &null_location, NULL);
 }

index 7413626..af33245 100644
@@ -259,7 +259,7 @@ static int mirror_flush(struct dm_target *ti)
 	struct dm_io_region io[ms->nr_mirrors];
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE_BARRIER,
+		.bi_rw = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.bvec = NULL,
 		.client = ms->io_client,

@@ -629,7 +629,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	struct dm_io_region io[ms->nr_mirrors], *dest = io;
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE | (bio->bi_rw & WRITE_BARRIER),
+		.bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
 		.mem.type = DM_IO_BVEC,
 		.mem.ptr.bvec = bio->bi_io_vec + bio->bi_idx,
 		.notify.fn = write_callback,

@@ -670,7 +670,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		if (unlikely(bio_empty_barrier(bio))) {
+		if (bio->bi_rw & REQ_FLUSH) {
 			bio_list_add(&sync, bio);
 			continue;
 		}

@@ -1203,7 +1203,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		if (likely(!bio_empty_barrier(bio)))
+		if (!(bio->bi_rw & REQ_FLUSH))
 			dm_rh_dec(ms->rh, map_context->ll);
 		return error;
 	}

index bd5c58b..dad011a 100644
@@ -81,9 +81,9 @@ struct dm_region_hash {
 	struct list_head failed_recovered_regions;
 
 	/*
-	 * If there was a barrier failure no regions can be marked clean.
+	 * If there was a flush failure no regions can be marked clean.
 	 */
-	int barrier_failure;
+	int flush_failure;
 
 	void *context;
 	sector_t target_begin;

@@ -217,7 +217,7 @@ struct dm_region_hash *dm_region_hash_create(
 	INIT_LIST_HEAD(&rh->quiesced_regions);
 	INIT_LIST_HEAD(&rh->recovered_regions);
 	INIT_LIST_HEAD(&rh->failed_recovered_regions);
-	rh->barrier_failure = 0;
+	rh->flush_failure = 0;
 
 	rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
 						      sizeof(struct dm_region));

@@ -399,8 +399,8 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
 	region_t region = dm_rh_bio_to_region(rh, bio);
 	int recovering = 0;
 
-	if (bio_empty_barrier(bio)) {
-		rh->barrier_failure = 1;
+	if (bio->bi_rw & REQ_FLUSH) {
+		rh->flush_failure = 1;
 		return;
 	}
 

@@ -524,7 +524,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
 	struct bio *bio;
 
 	for (bio = bios->head; bio; bio = bio->bi_next) {
-		if (bio_empty_barrier(bio))
+		if (bio->bi_rw & REQ_FLUSH)
 			continue;
 		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
 	}

@@ -555,9 +555,9 @@ void dm_rh_dec(struct dm_region_hash *rh, region_t region)
 		 */
 
 		/* do nothing for DM_RH_NOSYNC */
-		if (unlikely(rh->barrier_failure)) {
+		if (unlikely(rh->flush_failure)) {
 			/*
-			 * If a write barrier failed some time ago, we
+			 * If a write flush failed some time ago, we
 			 * don't know whether or not this write made it
 			 * to the disk, so we must resync the device.
 			 */

index c097d8a..b9048f0 100644
@@ -687,7 +687,7 @@ static void persistent_commit_exception(struct dm_exception_store *store,
 	/*
 	 * Commit exceptions to disk.
 	 */
-	if (ps->valid && area_io(ps, WRITE_BARRIER))
+	if (ps->valid && area_io(ps, WRITE_FLUSH_FUA))
 		ps->valid = 0;
 
 	/*

index 5485377..62a6586 100644
@@ -1581,7 +1581,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio,
 	chunk_t chunk;
 	struct dm_snap_pending_exception *pe = NULL;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		bio->bi_bdev = s->cow->bdev;
 		return DM_MAPIO_REMAPPED;
 	}

@@ -1685,7 +1685,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio,
 	int r = DM_MAPIO_REMAPPED;
 	chunk_t chunk;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		if (!map_context->flush_request)
 			bio->bi_bdev = s->origin->bdev;
 		else

@@ -2123,7 +2123,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio,
 	struct dm_dev *dev = ti->private;
 	bio->bi_bdev = dev->bdev;
 
-	if (unlikely(bio_empty_barrier(bio)))
+	if (bio->bi_rw & REQ_FLUSH)
 		return DM_MAPIO_REMAPPED;
 
 	/* Only tell snapshots if this is a write */

index d6e28d7..0f534ca 100644
@@ -214,7 +214,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio,
 	sector_t offset, chunk;
 	uint32_t stripe;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		BUG_ON(map_context->flush_request >= sc->stripes);
 		bio->bi_bdev = sc->stripe[map_context->flush_request].dev->bdev;
 		return DM_MAPIO_REMAPPED;

425 lines not on this page · raw message

index 3bdbb61..da11652 100644
@@ -1249,7 +1249,7 @@ static int crypt_map(struct dm_target *ti, struct bio *bio,
 	struct dm_crypt_io *io;
 	struct crypt_config *cc;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		cc = ti->private;
 		bio->bi_bdev = cc->dev->bdev;
 		return DM_MAPIO_REMAPPED;

index 0590c75..136d4f7 100644
@@ -31,7 +31,6 @@ struct dm_io_client {
  */
 struct io {
 	unsigned long error_bits;
-	unsigned long eopnotsupp_bits;
 	atomic_t count;
 	struct task_struct *sleeper;
 	struct dm_io_client *client;

@@ -130,11 +129,8 @@ static void retrieve_io_and_region_from_bio(struct bio *bio, struct io **io,
  *---------------------------------------------------------------*/
 static void dec_count(struct io *io, unsigned int region, int error)
 {
-	if (error) {
+	if (error)
 		set_bit(region, &io->error_bits);
-		if (error == -EOPNOTSUPP)
-			set_bit(region, &io->eopnotsupp_bits);
-	}
 
 	if (atomic_dec_and_test(&io->count)) {
 		if (io->sleeper)

@@ -310,8 +306,8 @@ static void do_region(int rw, unsigned region, struct dm_io_region *where,
 	sector_t remaining = where->count;
 
 	/*
-	 * where->count may be zero if rw holds a write barrier and we
-	 * need to send a zero-sized barrier.
+	 * where->count may be zero if rw holds a flush and we need to
+	 * send a zero-sized flush.
 	 */
 	do {
 		/*

@@ -364,7 +360,7 @@ static void dispatch_io(int rw, unsigned int num_regions,
 	 */
 	for (i = 0; i < num_regions; i++) {
 		*dp = old_pages;
-		if (where[i].count || (rw & REQ_HARDBARRIER))
+		if (where[i].count || (rw & REQ_FLUSH))
 			do_region(rw, i, where + i, dp, io);
 	}
 

@@ -393,9 +389,7 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 		return -EIO;
 	}
 
-retry:
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = current;
 	io->client = client;

@@ -412,11 +406,6 @@ retry:
 	}
 	set_current_state(TASK_RUNNING);
 
-	if (io->eopnotsupp_bits && (rw & REQ_HARDBARRIER)) {
-		rw &= ~REQ_HARDBARRIER;
-		goto retry;
-	}
-
 	if (error_bits)
 		*error_bits = io->error_bits;
 

@@ -437,7 +426,6 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
 
 	io = mempool_alloc(client->pool, GFP_NOIO);
 	io->error_bits = 0;
-	io->eopnotsupp_bits = 0;
 	atomic_set(&io->count, 1); /* see dispatch_io() */
 	io->sleeper = NULL;
 	io->client = client;

index 5a08be0..33420e6 100644
@@ -300,7 +300,7 @@ static int flush_header(struct log_c *lc)
 		.count = 0,
 	};
 
-	lc->io_req.bi_rw = WRITE_BARRIER;
+	lc->io_req.bi_rw = WRITE_FLUSH;
 
 	return dm_io(&lc->io_req, 1, &null_location, NULL);
 }

index 7413626..af33245 100644
@@ -259,7 +259,7 @@ static int mirror_flush(struct dm_target *ti)
 	struct dm_io_region io[ms->nr_mirrors];
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE_BARRIER,
+		.bi_rw = WRITE_FLUSH,
 		.mem.type = DM_IO_KMEM,
 		.mem.ptr.bvec = NULL,
 		.client = ms->io_client,

@@ -629,7 +629,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	struct dm_io_region io[ms->nr_mirrors], *dest = io;
 	struct mirror *m;
 	struct dm_io_request io_req = {
-		.bi_rw = WRITE | (bio->bi_rw & WRITE_BARRIER),
+		.bi_rw = WRITE | (bio->bi_rw & WRITE_FLUSH_FUA),
 		.mem.type = DM_IO_BVEC,
 		.mem.ptr.bvec = bio->bi_io_vec + bio->bi_idx,
 		.notify.fn = write_callback,

@@ -670,7 +670,7 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		if (unlikely(bio_empty_barrier(bio))) {
+		if (bio->bi_rw & REQ_FLUSH) {
 			bio_list_add(&sync, bio);
 			continue;
 		}

@@ -1203,7 +1203,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		if (likely(!bio_empty_barrier(bio)))
+		if (!(bio->bi_rw & REQ_FLUSH))
 			dm_rh_dec(ms->rh, map_context->ll);
 		return error;
 	}

index bd5c58b..dad011a 100644
@@ -81,9 +81,9 @@ struct dm_region_hash {
 	struct list_head failed_recovered_regions;
 
 	/*
-	 * If there was a barrier failure no regions can be marked clean.
+	 * If there was a flush failure no regions can be marked clean.
 	 */
-	int barrier_failure;
+	int flush_failure;
 
 	void *context;
 	sector_t target_begin;

@@ -217,7 +217,7 @@ struct dm_region_hash *dm_region_hash_create(
 	INIT_LIST_HEAD(&rh->quiesced_regions);
 	INIT_LIST_HEAD(&rh->recovered_regions);
 	INIT_LIST_HEAD(&rh->failed_recovered_regions);
-	rh->barrier_failure = 0;
+	rh->flush_failure = 0;
 
 	rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
 						      sizeof(struct dm_region));

@@ -399,8 +399,8 @@ void dm_rh_mark_nosync(struct dm_region_hash *rh, struct bio *bio)
 	region_t region = dm_rh_bio_to_region(rh, bio);
 	int recovering = 0;
 
-	if (bio_empty_barrier(bio)) {
-		rh->barrier_failure = 1;
+	if (bio->bi_rw & REQ_FLUSH) {
+		rh->flush_failure = 1;
 		return;
 	}
 

@@ -524,7 +524,7 @@ void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
 	struct bio *bio;
 
 	for (bio = bios->head; bio; bio = bio->bi_next) {
-		if (bio_empty_barrier(bio))
+		if (bio->bi_rw & REQ_FLUSH)
 			continue;
 		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
 	}

@@ -555,9 +555,9 @@ void dm_rh_dec(struct dm_region_hash *rh, region_t region)
 		 */
 
 		/* do nothing for DM_RH_NOSYNC */
-		if (unlikely(rh->barrier_failure)) {
+		if (unlikely(rh->flush_failure)) {
 			/*
-			 * If a write barrier failed some time ago, we
+			 * If a write flush failed some time ago, we
 			 * don't know whether or not this write made it
 			 * to the disk, so we must resync the device.
 			 */

index c097d8a..b9048f0 100644
@@ -687,7 +687,7 @@ static void persistent_commit_exception(struct dm_exception_store *store,
 	/*
 	 * Commit exceptions to disk.
 	 */
-	if (ps->valid && area_io(ps, WRITE_BARRIER))
+	if (ps->valid && area_io(ps, WRITE_FLUSH_FUA))
 		ps->valid = 0;
 
 	/*

index 5485377..62a6586 100644
@@ -1581,7 +1581,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio,
 	chunk_t chunk;
 	struct dm_snap_pending_exception *pe = NULL;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		bio->bi_bdev = s->cow->bdev;
 		return DM_MAPIO_REMAPPED;
 	}

@@ -1685,7 +1685,7 @@ static int snapshot_merge_map(struct dm_target *ti, struct bio *bio,
 	int r = DM_MAPIO_REMAPPED;
 	chunk_t chunk;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		if (!map_context->flush_request)
 			bio->bi_bdev = s->origin->bdev;
 		else

@@ -2123,7 +2123,7 @@ static int origin_map(struct dm_target *ti, struct bio *bio,
 	struct dm_dev *dev = ti->private;
 	bio->bi_bdev = dev->bdev;
 
-	if (unlikely(bio_empty_barrier(bio)))
+	if (bio->bi_rw & REQ_FLUSH)
 		return DM_MAPIO_REMAPPED;
 
 	/* Only tell snapshots if this is a write */

index d6e28d7..0f534ca 100644
@@ -214,7 +214,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio,
 	sector_t offset, chunk;
 	uint32_t stripe;
 
-	if (unlikely(bio_empty_barrier(bio))) {
+	if (bio->bi_rw & REQ_FLUSH) {
 		BUG_ON(map_context->flush_request >= sc->stripes);
 		bio->bi_bdev = sc->stripe[map_context->flush_request].dev->bdev;
 		return DM_MAPIO_REMAPPED;

425 lines not on this page · raw message

index 1b88af8..2768bf6 100644
@@ -307,20 +307,7 @@ static int scsi_check_sense(struct scsi_cmnd *scmd)
 		    (sshdr.asc == 0x04) && (sshdr.ascq == 0x02))
 			return FAILED;
 
-		if (scmd->request->cmd_flags & REQ_HARDBARRIER)
-			/*
-			 * barrier requests should always retry on UA
-			 * otherwise block will get a spurious error
-			 */
-			return NEEDS_RETRY;
-		else
-			/*
-			 * for normal (non barrier) commands, pass the
-			 * UA upwards for a determination in the
-			 * completion functions
-			 */
-			return SUCCESS;
-
+		return NEEDS_RETRY;
 		/* these three are not supported */
 	case COPY_ABORTED:
 	case VOLUME_OVERFLOW:

@@ -1336,7 +1323,9 @@ int scsi_noretry_cmd(struct scsi_cmnd *scmd)
 		 * assume caller has checked sense and determinted
 		 * the check condition was retryable.
 		 */
-		return (scmd->request->cmd_flags & REQ_FAILFAST_DEV);
+		if (scmd->request->cmd_flags & REQ_FAILFAST_DEV ||
+		    scmd->request->cmd_type == REQ_TYPE_BLOCK_PC)
+			return 1;
 	}
 
 	return 0;

index e63b85a..108daea 100644
@@ -477,8 +477,6 @@ static int scsi_setup_discard_cmnd(struct scsi_device *sdp, struct request *rq)
 
 static int scsi_setup_flush_cmnd(struct scsi_device *sdp, struct request *rq)
 {
-	/* for now, we use REQ_TYPE_BLOCK_PC. */
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->timeout = SD_TIMEOUT;
 	rq->retries = SD_MAX_RETRIES;
 	rq->cmd[0] = SYNCHRONIZE_CACHE;

index 1de30eb..5743196 100644
@@ -320,20 +320,7 @@ static int scsi_check_sense(struct scsi_cmnd *scmd)
 				    "changed. The Linux SCSI layer does not "
 				    "automatically adjust these parameters.\n");
 
-		if (scmd->request->cmd_flags & REQ_HARDBARRIER)
-			/*
-			 * barrier requests should always retry on UA
-			 * otherwise block will get a spurious error
-			 */
-			return NEEDS_RETRY;
-		else
-			/*
-			 * for normal (non barrier) commands, pass the
-			 * UA upwards for a determination in the
-			 * completion functions
-			 */
-			return SUCCESS;
-
+		return NEEDS_RETRY;
 		/* these three are not supported */
 	case COPY_ABORTED:
 	case VOLUME_OVERFLOW:

Index: linux-2.6/block/blk-core.c
===================================================================
@@ -1204,13 +1204,6 @@ static int __make_request(struct request
 	int where = ELEVATOR_INSERT_SORT;
 	int rw_flags;
 
-	/* 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: linux-2.6/block/elevator.c
===================================================================
@@ -429,7 +429,7 @@ void elv_dispatch_sort(struct request_qu
 	q->nr_sorted--;
 
 	boundary = q->end_sector;
-	stop_flags = REQ_SOFTBARRIER | REQ_HARDBARRIER | REQ_STARTED;
+	stop_flags = REQ_SOFTBARRIER | REQ_STARTED;
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 

@@ -691,7 +691,7 @@ void elv_insert(struct request_queue *q,
 void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		       int plug)
 {
-	if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
+	if (rq->cmd_flags & REQ_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS ||
 		    (rq->cmd_flags & REQ_DISCARD)) {

Index: linux-2.6/drivers/block/aoe/aoeblk.c
===================================================================
@@ -178,9 +178,6 @@ aoeblk_make_request(struct request_queue
 		BUG();
 		bio_endio(bio, -ENXIO);
 		return 0;
-	} else if (bio->bi_rw & REQ_HARDBARRIER) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
 	} else if (bio->bi_io_vec == NULL) {
 		printk(KERN_ERR "aoe: bi_io_vec is NULL\n");
 		BUG();

Index: linux-2.6/drivers/block/loop.c
===================================================================
@@ -481,12 +481,6 @@ static int do_bio_filebacked(struct loop
 	if (bio_rw(bio) == WRITE) {
 		struct file *file = lo->lo_backing_file;
 
-		/* 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 && ret != -EINVAL)) {

Index: linux-2.6/drivers/block/xen-blkfront.c
===================================================================
@@ -289,8 +289,6 @@ static int blkif_queue_request(struct re
 
 	ring_req->operation = rq_data_dir(req) ?
 		BLKIF_OP_WRITE : BLKIF_OP_READ;
-	if (req->cmd_flags & REQ_HARDBARRIER)
-		ring_req->operation = BLKIF_OP_WRITE_BARRIER;
 
 	ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
 	BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);

Index: linux-2.6/drivers/scsi/scsi_error.c
===================================================================
@@ -320,19 +320,11 @@ static int scsi_check_sense(struct scsi_
 				    "changed. The Linux SCSI layer does not "
 				    "automatically adjust these parameters.\n");
 
-		if (scmd->request->cmd_flags & REQ_HARDBARRIER)
-			/*
-			 * barrier requests should always retry on UA
-			 * otherwise block will get a spurious error
-			 */
-			return NEEDS_RETRY;
-		else
-			/*
-			 * for normal (non barrier) commands, pass the
-			 * UA upwards for a determination in the
-			 * completion functions
-			 */
-			return SUCCESS;
+		/*
+		 * Pass the UA upwards for a determination in the completion
+		 * functions.
+		 */
+		return SUCCESS;
 
 		/* these three are not supported */
 	case COPY_ABORTED:

Index: linux-2.6/drivers/usb/storage/uas.c
===================================================================
@@ -331,10 +331,7 @@ static struct urb *uas_alloc_cmd_urb(str
 
 	iu->iu_id = IU_ID_COMMAND;
 	iu->tag = cpu_to_be16(stream_id);
-	if (sdev->ordered_tags && (cmnd->request->cmd_flags & REQ_HARDBARRIER))
-		iu->prio_attr = UAS_ORDERED_TAG;
-	else
-		iu->prio_attr = UAS_SIMPLE_TAG;
+	iu->prio_attr = UAS_SIMPLE_TAG;
 	iu->len = len;
 	int_to_scsilun(sdev->lun, &iu->lun);
 	memcpy(iu->cdb, cmnd->cmnd, cmnd->cmd_len);

Index: linux-2.6/include/linux/bio.h
===================================================================
@@ -66,10 +66,6 @@
 #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_empty_barrier(bio) \
-	((bio->bi_rw & REQ_HARDBARRIER) && \
-	 !bio_has_data(bio) && \
-	 !(bio->bi_rw & REQ_DISCARD))
 
 static inline unsigned int bio_cur_bytes(struct bio *bio)
 {

Index: linux-2.6/include/linux/blk_types.h
===================================================================
@@ -122,7 +122,6 @@ enum rq_flag_bits {
 	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
 	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
 
-	__REQ_HARDBARRIER,	/* may not be passed by drive either */
 	__REQ_SYNC,		/* request is sync (sync write or read) */
 	__REQ_META,		/* metadata io request */
 	__REQ_DISCARD,		/* request to discard sectors */

@@ -159,7 +158,6 @@ enum rq_flag_bits {
 #define REQ_FAILFAST_DEV	(1 << __REQ_FAILFAST_DEV)
 #define REQ_FAILFAST_TRANSPORT	(1 << __REQ_FAILFAST_TRANSPORT)
 #define REQ_FAILFAST_DRIVER	(1 << __REQ_FAILFAST_DRIVER)
-#define REQ_HARDBARRIER		(1 << __REQ_HARDBARRIER)
 #define REQ_SYNC		(1 << __REQ_SYNC)
 #define REQ_META		(1 << __REQ_META)
 #define REQ_DISCARD		(1 << __REQ_DISCARD)

@@ -168,8 +166,8 @@ enum rq_flag_bits {
 #define REQ_FAILFAST_MASK \
 	(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_FLUSH | REQ_FUA)
+	(REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_DISCARD | \
+	 REQ_NOIDLE | REQ_FLUSH | REQ_FUA)
 #define REQ_CLONE_MASK		REQ_COMMON_MASK
 
 #define REQ_UNPLUG		(1 << __REQ_UNPLUG)

Index: linux-2.6/include/linux/blkdev.h
===================================================================
@@ -553,8 +553,7 @@ static inline void blk_clear_queue_full(
  * it already be started by driver.
  */
 #define RQ_NOMERGE_FLAGS	\
-	(REQ_NOMERGE | REQ_STARTED | REQ_HARDBARRIER | REQ_SOFTBARRIER | \
-	 REQ_FLUSH | REQ_FUA)
+	(REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA)
 #define rq_mergeable(rq)	\
 	(!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \
 	 (((rq)->cmd_flags & REQ_DISCARD) || \

Index: linux-2.6/kernel/trace/blktrace.c
===================================================================
@@ -168,7 +168,6 @@ static int act_log_check(struct blk_trac
 static const u32 ddir_act[2] = { BLK_TC_ACT(BLK_TC_READ),
 				 BLK_TC_ACT(BLK_TC_WRITE) };
 
-#define BLK_TC_HARDBARRIER	BLK_TC_BARRIER
 #define BLK_TC_RAHEAD		BLK_TC_AHEAD
 
 /* The ilog2() calls fall out because they're constant */

@@ -196,7 +195,6 @@ static void __blk_add_trace(struct blk_t
 		return;
 
 	what |= ddir_act[rw & WRITE];
-	what |= MASK_TC_BIT(rw, HARDBARRIER);
 	what |= MASK_TC_BIT(rw, SYNC);
 	what |= MASK_TC_BIT(rw, RAHEAD);
 	what |= MASK_TC_BIT(rw, META);

@@ -1807,8 +1805,6 @@ void blk_fill_rwbs(char *rwbs, u32 rw, i
 
 	if (rw & REQ_RAHEAD)
 		rwbs[i++] = 'A';
-	if (rw & REQ_HARDBARRIER)
-		rwbs[i++] = 'B';
 	if (rw & REQ_SYNC)
 		rwbs[i++] = 'S';
 	if (rw & REQ_META)