Merge branch 'for-2.6.30' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.30' of git://git.kernel.dk/linux-2.6-block:
  Get rid of pdflush_operation() in emergency sync and remount
  btrfs: get rid of current_is_pdflush() in btrfs_btree_balance_dirty
  Move the default_backing_dev_info out of readahead.c and into backing-dev.c
  block: Repeated lines in switching-sched.txt
  bsg: Remove bogus check against request_queue->max_sectors
  block: WARN in __blk_put_request() for potential bio leak
  loop: fix circular locking in loop_clr_fd()
  loop: support barrier writes
  bsg: add support for tail queuing
  cpqarray: enable bus mastering
  block: genhd.h cleanup patch
  block: add private bio_set for bio integrity allocations
  block: genhd.h comment needs updating
  block: get rid of unused blkdev_free_rq() define
  block: remove various blk_queue_*() setting functions in blk_init_queue_node()
  cciss: add BUILD_BUG_ON() for catching bad CommandList_struct alignment
  block: don't create bio_vec slabs of less than the inline number
  block: cleanup bio_alloc_bioset()

Documentation/block/switching-sched.txt

@@ -35,9 +35,3 @@ noop anticipatory deadline [cfq]
 # echo anticipatory > /sys/block/hda/queue/scheduler
 # cat /sys/block/hda/queue/scheduler
 noop [anticipatory] deadline cfq
-
-Each io queue has a set of io scheduler tunables associated with it. These
-tunables control how the io scheduler works. You can find these entries
-in:
-
-/sys/block/<device>/queue/iosched

block/blk-core.c

@@ -603,13 +603,10 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 	q->queue_flags		= QUEUE_FLAG_DEFAULT;
 	q->queue_lock		= lock;
 
-	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
-
+	/*
+	 * This also sets hw/phys segments, boundary and size
+	 */
 	blk_queue_make_request(q, __make_request);
-	blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
-
-	blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
-	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
 
 	q->sg_reserved_size = INT_MAX;
 
@@ -735,7 +732,6 @@ static void freed_request(struct request_queue *q, int rw, int priv)
 		__freed_request(q, rw ^ 1);
 }
 
-#define blkdev_free_rq(list) list_entry((list)->next, struct request, queuelist)
 /*
  * Get a free request, queue_lock must be held.
  * Returns NULL on failure, with queue_lock held.
@@ -1066,6 +1062,9 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 
 	elv_completed_request(q, req);
 
+	/* this is a bio leak */
+	WARN_ON(req->bio != NULL);
+
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
 	 * it didn't come out of our reserved rq pools

block/blk-merge.c

@@ -403,6 +403,8 @@ static int attempt_merge(struct request_queue *q, struct request *req,
 	if (blk_rq_cpu_valid(next))
 		req->cpu = next->cpu;
 
+	/* owner-ship of bio passed from next to req */
+	next->bio = NULL;
 	__blk_put_request(q, next);
 	return 1;
 }

block/bsg.c

@@ -218,9 +218,6 @@ bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw)
 
 	if (hdr->guard != 'Q')
 		return -EINVAL;
-	if (hdr->dout_xfer_len > (q->max_sectors << 9) ||
-	    hdr->din_xfer_len > (q->max_sectors << 9))
-		return -EIO;
 
 	switch (hdr->protocol) {
 	case BSG_PROTOCOL_SCSI:
@@ -353,6 +350,8 @@ static void bsg_rq_end_io(struct request *rq, int uptodate)
 static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 			    struct bsg_command *bc, struct request *rq)
 {
+	int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL));
+
 	/*
 	 * add bc command to busy queue and submit rq for io
 	 */
@@ -368,7 +367,7 @@ static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
 	dprintk("%s: queueing rq %p, bc %p\n", bd->name, rq, bc);
 
 	rq->end_io_data = bc;
-	blk_execute_rq_nowait(q, NULL, rq, 1, bsg_rq_end_io);
+	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
 }
 
 static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
@@ -924,6 +923,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		struct request *rq;
 		struct bio *bio, *bidi_bio = NULL;
 		struct sg_io_v4 hdr;
+		int at_head;
 		u8 sense[SCSI_SENSE_BUFFERSIZE];
 
 		if (copy_from_user(&hdr, uarg, sizeof(hdr)))
@@ -936,7 +936,9 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		bio = rq->bio;
 		if (rq->next_rq)
 			bidi_bio = rq->next_rq->bio;
-		blk_execute_rq(bd->queue, NULL, rq, 0);
+
+		at_head = (0 == (hdr.flags & BSG_FLAG_Q_AT_TAIL));
+		blk_execute_rq(bd->queue, NULL, rq, at_head);
 		ret = blk_complete_sgv4_hdr_rq(rq, &hdr, bio, bidi_bio);
 
 		if (copy_to_user(uarg, &hdr, sizeof(hdr)))

block/scsi_ioctl.c

@@ -214,21 +214,10 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 	return 0;
 }
 
-/*
- * unmap a request that was previously mapped to this sg_io_hdr. handles
- * both sg and non-sg sg_io_hdr.
- */
-static int blk_unmap_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr)
-{
-	blk_rq_unmap_user(rq->bio);
-	blk_put_request(rq);
-	return 0;
-}
-
 static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 				 struct bio *bio)
 {
-	int r, ret = 0;
+	int ret = 0;
 
 	/*
 	 * fill in all the output members
@@ -253,12 +242,10 @@ static int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
 			ret = -EFAULT;
 	}
 
-	rq->bio = bio;
-	r = blk_unmap_sghdr_rq(rq, hdr);
-	if (ret)
-		r = ret;
+	blk_rq_unmap_user(bio);
+	blk_put_request(rq);
 
-	return r;
+	return ret;
 }
 
 static int sg_io(struct request_queue *q, struct gendisk *bd_disk,

drivers/block/cciss.c

@@ -3898,6 +3898,13 @@ static struct pci_driver cciss_pci_driver = {
  */
 static int __init cciss_init(void)
 {
+	/*
+	 * The hardware requires that commands are aligned on a 64-bit
+	 * boundary. Given that we use pci_alloc_consistent() to allocate an
+	 * array of them, the size must be a multiple of 8 bytes.
+	 */
+	BUILD_BUG_ON(sizeof(CommandList_struct) % 8);
+
 	printk(KERN_INFO DRIVER_NAME "\n");
 
 	/* Register for our PCI devices */

drivers/block/cpqarray.c

@@ -617,6 +617,7 @@ static int cpqarray_pci_init(ctlr_info_t *c, struct pci_dev *pdev)
 	int i;
 
 	c->pci_dev = pdev;
+	pci_set_master(pdev);
 	if (pci_enable_device(pdev)) {
 		printk(KERN_ERR "cpqarray: Unable to Enable PCI device\n");
 		return -1;

drivers/block/loop.c

@@ -474,10 +474,35 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	int ret;
 
 	pos = ((loff_t) bio->bi_sector << 9) + lo->lo_offset;
-	if (bio_rw(bio) == WRITE)
+
+	if (bio_rw(bio) == WRITE) {
+		int barrier = bio_barrier(bio);
+		struct file *file = lo->lo_backing_file;
+
+		if (barrier) {
+			if (unlikely(!file->f_op->fsync)) {
+				ret = -EOPNOTSUPP;
+				goto out;
+			}
+
+			ret = vfs_fsync(file, file->f_path.dentry, 0);
+			if (unlikely(ret)) {
+				ret = -EIO;
+				goto out;
+			}
+		}
+
 		ret = lo_send(lo, bio, pos);
-	else
+
+		if (barrier && !ret) {
+			ret = vfs_fsync(file, file->f_path.dentry, 0);
+			if (unlikely(ret))
+				ret = -EIO;
+		}
+	} else
 		ret = lo_receive(lo, bio, lo->lo_blocksize, pos);
+
+out:
 	return ret;
 }
 
@@ -826,6 +851,9 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 	lo->lo_queue->queuedata = lo;
 	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, NULL);
+
 	set_capacity(lo->lo_disk, size);
 	bd_set_size(bdev, size << 9);
 
@@ -941,11 +969,18 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 		bd_set_size(bdev, 0);
 	mapping_set_gfp_mask(filp->f_mapping, gfp);
 	lo->lo_state = Lo_unbound;
-	fput(filp);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
 	if (max_part > 0)
 		ioctl_by_bdev(bdev, BLKRRPART, 0);
+	mutex_unlock(&lo->lo_ctl_mutex);
+	/*
+	 * Need not hold lo_ctl_mutex to fput backing file.
+	 * Calling fput holding lo_ctl_mutex triggers a circular
+	 * lock dependency possibility warning as fput can take
+	 * bd_mutex which is usually taken before lo_ctl_mutex.
+	 */
+	fput(filp);
 	return 0;
 }
 
@@ -1163,7 +1198,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	struct loop_device *lo = bdev->bd_disk->private_data;
 	int err;
 
-	mutex_lock(&lo->lo_ctl_mutex);
+	mutex_lock_nested(&lo->lo_ctl_mutex, 1);
 	switch (cmd) {
 	case LOOP_SET_FD:
 		err = loop_set_fd(lo, mode, bdev, arg);
@@ -1172,7 +1207,10 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		err = loop_change_fd(lo, bdev, arg);
 		break;
 	case LOOP_CLR_FD:
+		/* loop_clr_fd would have unlocked lo_ctl_mutex on success */
 		err = loop_clr_fd(lo, bdev);
+		if (!err)
+			goto out_unlocked;
 		break;
 	case LOOP_SET_STATUS:
 		err = loop_set_status_old(lo, (struct loop_info __user *) arg);
@@ -1190,6 +1228,8 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
 	}
 	mutex_unlock(&lo->lo_ctl_mutex);
+
+out_unlocked:
 	return err;
 }