block: deprecate barrier and replace blk_queue_ordered() with blk_queue_flush()

Barrier is deemed too heavy and will soon be replaced by FLUSH/FUA
requests.  Deprecate barrier.  All REQ_HARDBARRIERs are failed with
-EOPNOTSUPP and blk_queue_ordered() is replaced with simpler
blk_queue_flush().

blk_queue_flush() takes combinations of REQ_FLUSH and FUA.  If a
device has write cache and can flush it, it should set REQ_FLUSH.  If
the device can handle FUA writes, it should also set REQ_FUA.

All blk_queue_ordered() users are converted.

* ORDERED_DRAIN is mapped to 0 which is the default value.
* ORDERED_DRAIN_FLUSH is mapped to REQ_FLUSH.
* ORDERED_DRAIN_FLUSH_FUA is mapped to REQ_FLUSH | REQ_FUA.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Boaz Harrosh <bharrosh@panasas.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Jeremy Fitzhardinge <jeremy@xensource.com>
Cc: Chris Wright <chrisw@sous-sol.org>
Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Alasdair G Kergon <agk@redhat.com>
Cc: Pierre Ossman <drzeus@drzeus.cx>
Cc: Stefan Weinhuber <wein@de.ibm.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

6 files changed, 24 insertions, 51 deletions

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 47a41272d26b..fa33f97722ba 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -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);
 
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index c3a4a2e176da..953d1e12f4d4 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -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);
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index 2284b4f05c62..72d62462433d 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -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;
 
diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c
index e9da874d0419..4911f9e57bc7 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 79652809eee8..d10b635b3946 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -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))
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 50ec6f834996..0b1eea643262 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -95,7 +95,7 @@ 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;
 };
 
@@ -418,25 +418,12 @@ 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"; 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");
 }
 
 
@@ -515,7 +502,7 @@ 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);
@@ -661,8 +648,8 @@ 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:
@@ -1075,19 +1062,13 @@ 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 use flush.
-         *
-         * If barriers are not supported, then there's no much we can
-         * do, so just set ordering to NONE.
          */
-        if (err)
-                info->feature_barrier = QUEUE_ORDERED_DRAIN;
-        else if (barrier)
-                info->feature_barrier = QUEUE_ORDERED_DRAIN_FLUSH;
-        else
-                info->feature_barrier = QUEUE_ORDERED_NONE;
+        info->feature_flush = 0;
+        if (!err && barrier)
+                info->feature_flush = REQ_FLUSH;
 
         err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
         if (err) {