Merge branch 'for-3.20/drivers' of git://git.kernel.dk/linux-block

Pull block driver changes from Jens Axboe:
 "This contains:

   - The 4k/partition fixes for brd from Boaz/Matthew.

   - A few xen front/back block fixes from David Vrabel and Roger Pau
     Monne.

   - Floppy changes from Takashi, cleaning the device file creation.

   - Switching libata to use the new blk-mq tagging policy, removing
     code (and a suboptimal implementation) from libata.  This will
     throw you a merge conflict, since a bug in the original libata
     tagging code was fixed since this code was branched.  Trivial.
     From Shaohua.

   - Conversion of loop to blk-mq, from Ming Lei.

   - Cleanup of the io_schedule() handling in bsg from Peter Zijlstra.
     He claims it improves on unreadable code, which will cost him a
     beer.

   - Maintainer update or NDB, now handled by Markus Pargmann.

   - NVMe:
        - Optimization from me that avoids a kmalloc/kfree per IO for
          smaller (<= 8KB) IO. This cuts about 1% of high IOPS CPU
          overhead.
        - Removal of (now) dead RCU code, a relic from before NVMe was
          converted to blk-mq"

* 'for-3.20/drivers' of git://git.kernel.dk/linux-block:
  xen-blkback: default to X86_32 ABI on x86
  xen-blkfront: fix accounting of reqs when migrating
  xen-blkback,xen-blkfront: add myself as maintainer
  block: Simplify bsg complete all
  floppy: Avoid manual call of device_create_file()
  NVMe: avoid kmalloc/kfree for smaller IO
  MAINTAINERS: Update NBD maintainer
  libata: make sata_sil24 use fifo tag allocator
  libata: move sas ata tag allocation to libata-scsi.c
  libata: use blk taging
  NVMe: within nvme_free_queues(), delete RCU sychro/deferred free
  null_blk: suppress invalid partition info
  brd: Request from fdisk 4k alignment
  brd: Fix all partitions BUGs
  axonram: Fix bug in direct_access
  loop: add blk-mq.h include
  block: loop: don't handle REQ_FUA explicitly
  block: loop: introduce lo_discard() and lo_req_flush()
  block: loop: say goodby to bio
  block: loop: improve performance via blk-mq

block/bsg.c

@@ -136,42 +136,6 @@ static inline struct hlist_head *bsg_dev_idx_hash(int index)
 	return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)];
 }
 
-static int bsg_io_schedule(struct bsg_device *bd)
-{
-	DEFINE_WAIT(wait);
-	int ret = 0;
-
-	spin_lock_irq(&bd->lock);
-
-	BUG_ON(bd->done_cmds > bd->queued_cmds);
-
-	/*
-	 * -ENOSPC or -ENODATA?  I'm going for -ENODATA, meaning "I have no
-	 * work to do", even though we return -ENOSPC after this same test
-	 * during bsg_write() -- there, it means our buffer can't have more
-	 * bsg_commands added to it, thus has no space left.
-	 */
-	if (bd->done_cmds == bd->queued_cmds) {
-		ret = -ENODATA;
-		goto unlock;
-	}
-
-	if (!test_bit(BSG_F_BLOCK, &bd->flags)) {
-		ret = -EAGAIN;
-		goto unlock;
-	}
-
-	prepare_to_wait(&bd->wq_done, &wait, TASK_UNINTERRUPTIBLE);
-	spin_unlock_irq(&bd->lock);
-	io_schedule();
-	finish_wait(&bd->wq_done, &wait);
-
-	return ret;
-unlock:
-	spin_unlock_irq(&bd->lock);
-	return ret;
-}
-
 static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
 				fmode_t has_write_perm)
@@ -482,6 +446,30 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	return ret;
 }
 
+static bool bsg_complete(struct bsg_device *bd)
+{
+	bool ret = false;
+	bool spin;
+
+	do {
+		spin_lock_irq(&bd->lock);
+
+		BUG_ON(bd->done_cmds > bd->queued_cmds);
+
+		/*
+		 * All commands consumed.
+		 */
+		if (bd->done_cmds == bd->queued_cmds)
+			ret = true;
+
+		spin = !test_bit(BSG_F_BLOCK, &bd->flags);
+
+		spin_unlock_irq(&bd->lock);
+	} while (!ret && spin);
+
+	return ret;
+}
+
 static int bsg_complete_all_commands(struct bsg_device *bd)
 {
 	struct bsg_command *bc;
@@ -492,17 +480,7 @@ static int bsg_complete_all_commands(struct bsg_device *bd)
 	/*
 	 * wait for all commands to complete
 	 */
-	ret = 0;
-	do {
-		ret = bsg_io_schedule(bd);
-		/*
-		 * look for -ENODATA specifically -- we'll sometimes get
-		 * -ERESTARTSYS when we've taken a signal, but we can't
-		 * return until we're done freeing the queue, so ignore
-		 * it.  The signal will get handled when we're done freeing
-		 * the bsg_device.
-		 */
-	} while (ret != -ENODATA);
+	io_wait_event(bd->wq_done, bsg_complete(bd));
 
 	/*
 	 * discard done commands