Merge branch 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.37/barrier' of git://git.kernel.dk/linux-2.6-block: (46 commits)
  xen-blkfront: disable barrier/flush write support
  Added blk-lib.c and blk-barrier.c was renamed to blk-flush.c
  block: remove BLKDEV_IFL_WAIT
  aic7xxx_old: removed unused 'req' variable
  block: remove the BH_Eopnotsupp flag
  block: remove the BLKDEV_IFL_BARRIER flag
  block: remove the WRITE_BARRIER flag
  swap: do not send discards as barriers
  fat: do not send discards as barriers
  ext4: do not send discards as barriers
  jbd2: replace barriers with explicit flush / FUA usage
  jbd2: Modify ASYNC_COMMIT code to not rely on queue draining on barrier
  jbd: replace barriers with explicit flush / FUA usage
  nilfs2: replace barriers with explicit flush / FUA usage
  reiserfs: replace barriers with explicit flush / FUA usage
  gfs2: replace barriers with explicit flush / FUA usage
  btrfs: replace barriers with explicit flush / FUA usage
  xfs: replace barriers with explicit flush / FUA usage
  block: pass gfp_mask and flags to sb_issue_discard
  dm: convey that all flushes are processed as empty
  ...

9 files changed, 41 insertions, 84 deletions

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 82bfd5bb4a9..b7f51e4594f 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -483,7 +483,6 @@ 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_TAG);
         blk_queue_max_hw_sectors(brd->brd_queue, 1024);
         blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index c07c370c4c8..9bdcf4393c0 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -2409,8 +2409,7 @@ static inline void drbd_md_flush(struct drbd_conf *mdev)
         if (test_bit(MD_NO_BARRIER, &mdev->flags))
                 return;
 
-        r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL,
-                        BLKDEV_IFL_WAIT);
+        r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL);
         if (r) {
                 set_bit(MD_NO_BARRIER, &mdev->flags);
                 dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 760ae0df925..efd6169acf2 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -987,7 +987,7 @@ static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct d
 
         if (mdev->write_ordering >= WO_bdev_flush && get_ldev(mdev)) {
                 rv = blkdev_issue_flush(mdev->ldev->backing_bdev, GFP_KERNEL,
-                                        NULL, BLKDEV_IFL_WAIT);
+                                        NULL);
                 if (rv) {
                         dev_err(DEV, "local disk flush failed with status %d\n", rv);
                         /* would rather check on EOPNOTSUPP, but that is not reliable.
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index de3083b0a4f..6c48b3545f8 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -479,17 +479,17 @@ 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;
                         }
@@ -497,9 +497,9 @@ 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
@@ -931,7 +931,7 @@ 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_flush(lo->lo_queue, REQ_FLUSH);
 
         set_capacity(lo->lo_disk, size);
         bd_set_size(bdev, size << 9);
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 2284b4f05c6..87311ebac0d 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -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;
                 }
@@ -439,7 +438,7 @@ 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;
 
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index ef58fccadad..19b3568e932 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -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;
 
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index 03688c2da31..8e1ce2e2916 100644
--- a/drivers/block/ps3disk.c
+++ b/drivers/block/ps3disk.c
@@ -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);
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 8320490226b..6ecf89cdf00 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -127,9 +127,6 @@ 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));
 
         /*
@@ -379,31 +376,9 @@ 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 (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
-                 * 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);
-        }
+        /* configure queue flush support */
+        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))
@@ -522,9 +497,9 @@ 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
 };
 
 /*
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 3ff06f475ee..4b33a18c32e 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -96,7 +96,7 @@ struct blkfront_info
         struct gnttab_free_callback callback;
         struct blk_shadow shadow[BLK_RING_SIZE];
         unsigned long shadow_free;
-        int feature_barrier;
+        unsigned int feature_flush;
         int is_ready;
 };
 
@@ -419,26 +419,12 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
 }
 
 
-static int xlvbd_barrier(struct blkfront_info *info)
+static void xlvbd_flush(struct blkfront_info *info)
 {
-        int err;
-        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_NONE:        barrier = "disabled"; break;
-        default:                        return -EINVAL;
-        }
-
-        err = blk_queue_ordered(info->rq, info->feature_barrier);
-
-        if (err)
-                return err;
-
+        blk_queue_flush(info->rq, info->feature_flush);
         printk(KERN_INFO "blkfront: %s: barriers %s\n",
-               info->gd->disk_name, barrier);
-        return 0;
+               info->gd->disk_name,
+               info->feature_flush ? "enabled" : "disabled");
 }
 
 
@@ -517,7 +503,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
         info->rq = gd->queue;
         info->gd = gd;
 
-        xlvbd_barrier(info);
+        xlvbd_flush(info);
 
         if (vdisk_info & VDISK_READONLY)
                 set_disk_ro(gd, 1);
@@ -663,8 +649,8 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
                                 printk(KERN_WARNING "blkfront: %s: write barrier op failed\n",
                                        info->gd->disk_name);
                                 error = -EOPNOTSUPP;
-                                info->feature_barrier = QUEUE_ORDERED_NONE;
-                                xlvbd_barrier(info);
+                                info->feature_flush = 0;
+                                xlvbd_flush(info);
                         }
                         /* fall through */
                 case BLKIF_OP_READ:
@@ -1077,20 +1063,20 @@ static void blkfront_connect(struct blkfront_info *info)
         /*
          * If there's no "feature-barrier" defined, then it means
          * we're dealing with a very old backend which writes
-         * synchronously; draining will do what needs to get done.
+         * synchronously; nothing to do.
          *
-         * If there are barriers, then we can do full queued writes
-         * with tagged barriers.
-         *
-         * If barriers are not supported, then there's no much we can
-         * do, so just set ordering to NONE.
+         * If there are barriers, then we use flush.
          */
-        if (err)
-                info->feature_barrier = QUEUE_ORDERED_DRAIN;
-        else if (barrier)
-                info->feature_barrier = QUEUE_ORDERED_TAG;
-        else
-                info->feature_barrier = QUEUE_ORDERED_NONE;
+        info->feature_flush = 0;
+
+        /*
+         * The driver doesn't properly handled empty flushes, so
+         * lets disable barrier support for now.
+         */
+#if 0
+        if (!err && barrier)
+                info->feature_flush = REQ_FLUSH;
+#endif
 
         err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
         if (err) {