block: make blkdev_get/put() handle exclusive access

Over time, block layer has accumulated a set of APIs dealing with bdev
open, close, claim and release.

* blkdev_get/put() are the primary open and close functions.

* bd_claim/release() deal with exclusive open.

* open/close_bdev_exclusive() are combination of open and claim and
  the other way around, respectively.

* bd_link/unlink_disk_holder() to create and remove holder/slave
  symlinks.

* open_by_devnum() wraps bdget() + blkdev_get().

The interface is a bit confusing and the decoupling of open and claim
makes it impossible to properly guarantee exclusive access as
in-kernel open + claim sequence can disturb the existing exclusive
open even before the block layer knows the current open if for another
exclusive access.  Reorganize the interface such that,

* blkdev_get() is extended to include exclusive access management.
  @holder argument is added and, if is @FMODE_EXCL specified, it will
  gain exclusive access atomically w.r.t. other exclusive accesses.

* blkdev_put() is similarly extended.  It now takes @mode argument and
  if @FMODE_EXCL is set, it releases an exclusive access.  Also, when
  the last exclusive claim is released, the holder/slave symlinks are
  removed automatically.

* bd_claim/release() and close_bdev_exclusive() are no longer
  necessary and either made static or removed.

* bd_link_disk_holder() remains the same but bd_unlink_disk_holder()
  is no longer necessary and removed.

* open_bdev_exclusive() becomes a simple wrapper around lookup_bdev()
  and blkdev_get().  It also has an unexpected extra bdev_read_only()
  test which probably should be moved into blkdev_get().

* open_by_devnum() is modified to take @holder argument and pass it to
  blkdev_get().

Most of bdev open/close operations are unified into blkdev_get/put()
and most exclusive accesses are tested atomically at the open time (as
it should).  This cleans up code and removes some, both valid and
invalid, but unnecessary all the same, corner cases.

open_bdev_exclusive() and open_by_devnum() can use further cleanup -
rename to blkdev_get_by_path() and blkdev_get_by_devt() and drop
special features.  Well, let's leave them for another day.

Most conversions are straight-forward.  drbd conversion is a bit more
involved as there was some reordering, but the logic should stay the
same.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Neil Brown <neilb@suse.de>
Acked-by: Ryusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Acked-by: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Peter Osterlund <petero2@telia.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Joel Becker <joel.becker@oracle.com>
Cc: Alex Elder <aelder@sgi.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: dm-devel@redhat.com
Cc: drbd-dev@lists.linbit.com
Cc: Leo Chen <leochen@broadcom.com>
Cc: Scott Branden <sbranden@broadcom.com>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Steven Whitehouse <swhiteho@redhat.com>
Cc: Dave Kleikamp <shaggy@linux.vnet.ibm.com>
Cc: Joern Engel <joern@logfs.org>
Cc: reiserfs-devel@vger.kernel.org
Cc: Alexander Viro <viro@zeniv.linux.org.uk>

4 files changed, 46 insertions, 88 deletions

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 9bdcf4393c0a..0590b9f67ec6 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -923,8 +923,6 @@ struct drbd_md {
 struct drbd_backing_dev {
 	struct block_device *backing_bdev;
 	struct block_device *md_bdev;
-	struct file *lo_file;
-	struct file *md_file;
 	struct drbd_md md;
 	struct disk_conf dc; /* The user provided config... */
 	sector_t known_size; /* last known size of that backing device */
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 25c7a73c5062..7ec1a82064a9 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -3361,11 +3361,8 @@ void drbd_free_bc(struct drbd_backing_dev *ldev)
 	if (ldev == NULL)
 		return;
 
-	bd_release(ldev->backing_bdev);
-	bd_release(ldev->md_bdev);
-
-	fput(ldev->lo_file);
-	fput(ldev->md_file);
+	blkdev_put(ldev->backing_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+	blkdev_put(ldev->md_bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 
 	kfree(ldev);
 }
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 87925e97e613..fd0346090289 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -855,7 +855,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	sector_t max_possible_sectors;
 	sector_t min_md_device_sectors;
 	struct drbd_backing_dev *nbc = NULL; /* new_backing_conf */
-	struct inode *inode, *inode2;
+	struct block_device *bdev;
 	struct lru_cache *resync_lru = NULL;
 	union drbd_state ns, os;
 	unsigned int max_seg_s;
@@ -902,46 +902,40 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 		}
 	}
 
-	nbc->lo_file = filp_open(nbc->dc.backing_dev, O_RDWR, 0);
-	if (IS_ERR(nbc->lo_file)) {
+	bdev = open_bdev_exclusive(nbc->dc.backing_dev,
+				   FMODE_READ | FMODE_WRITE, mdev);
+	if (IS_ERR(bdev)) {
 		dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.backing_dev,
-		    PTR_ERR(nbc->lo_file));
-		nbc->lo_file = NULL;
+			PTR_ERR(bdev));
 		retcode = ERR_OPEN_DISK;
 		goto fail;
 	}
+	nbc->backing_bdev = bdev;
 
-	inode = nbc->lo_file->f_dentry->d_inode;
-
-	if (!S_ISBLK(inode->i_mode)) {
-		retcode = ERR_DISK_NOT_BDEV;
-		goto fail;
-	}
-
-	nbc->md_file = filp_open(nbc->dc.meta_dev, O_RDWR, 0);
-	if (IS_ERR(nbc->md_file)) {
+	/*
+	 * meta_dev_idx >= 0: external fixed size, possibly multiple
+	 * drbd sharing one meta device.  TODO in that case, paranoia
+	 * check that [md_bdev, meta_dev_idx] is not yet used by some
+	 * other drbd minor!  (if you use drbd.conf + drbdadm, that
+	 * should check it for you already; but if you don't, or
+	 * someone fooled it, we need to double check here)
+	 */
+	bdev = open_bdev_exclusive(nbc->dc.meta_dev,
+				   FMODE_READ | FMODE_WRITE,
+				   (nbc->dc.meta_dev_idx < 0) ?
+				   (void *)mdev : (void *)drbd_m_holder);
+	if (IS_ERR(bdev)) {
 		dev_err(DEV, "open(\"%s\") failed with %ld\n", nbc->dc.meta_dev,
-		    PTR_ERR(nbc->md_file));
-		nbc->md_file = NULL;
+			PTR_ERR(bdev));
 		retcode = ERR_OPEN_MD_DISK;
 		goto fail;
 	}
+	nbc->md_bdev = bdev;
 
-	inode2 = nbc->md_file->f_dentry->d_inode;
-
-	if (!S_ISBLK(inode2->i_mode)) {
-		retcode = ERR_MD_NOT_BDEV;
-		goto fail;
-	}
-
-	nbc->backing_bdev = inode->i_bdev;
-	if (bd_claim(nbc->backing_bdev, mdev)) {
-		printk(KERN_ERR "drbd: bd_claim(%p,%p); failed [%p;%p;%u]\n",
-		       nbc->backing_bdev, mdev,
-		       nbc->backing_bdev->bd_holder,
-		       nbc->backing_bdev->bd_contains->bd_holder,
-		       nbc->backing_bdev->bd_holders);
-		retcode = ERR_BDCLAIM_DISK;
+	if ((nbc->backing_bdev == nbc->md_bdev) !=
+	    (nbc->dc.meta_dev_idx == DRBD_MD_INDEX_INTERNAL ||
+	     nbc->dc.meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) {
+		retcode = ERR_MD_IDX_INVALID;
 		goto fail;
 	}
 
@@ -950,28 +944,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 			offsetof(struct bm_extent, lce));
 	if (!resync_lru) {
 		retcode = ERR_NOMEM;
-		goto release_bdev_fail;
-	}
-
-	/* meta_dev_idx >= 0: external fixed size,
-	 * possibly multiple drbd sharing one meta device.
-	 * TODO in that case, paranoia check that [md_bdev, meta_dev_idx] is
-	 * not yet used by some other drbd minor!
-	 * (if you use drbd.conf + drbdadm,
-	 * that should check it for you already; but if you don't, or someone
-	 * fooled it, we need to double check here) */
-	nbc->md_bdev = inode2->i_bdev;
-	if (bd_claim(nbc->md_bdev, (nbc->dc.meta_dev_idx < 0) ? (void *)mdev
-				: (void *) drbd_m_holder)) {
-		retcode = ERR_BDCLAIM_MD_DISK;
-		goto release_bdev_fail;
-	}
-
-	if ((nbc->backing_bdev == nbc->md_bdev) !=
-	    (nbc->dc.meta_dev_idx == DRBD_MD_INDEX_INTERNAL ||
-	     nbc->dc.meta_dev_idx == DRBD_MD_INDEX_FLEX_INT)) {
-		retcode = ERR_MD_IDX_INVALID;
-		goto release_bdev2_fail;
+		goto fail;
 	}
 
 	/* RT - for drbd_get_max_capacity() DRBD_MD_INDEX_FLEX_INT */
@@ -982,7 +955,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 			(unsigned long long) drbd_get_max_capacity(nbc),
 			(unsigned long long) nbc->dc.disk_size);
 		retcode = ERR_DISK_TO_SMALL;
-		goto release_bdev2_fail;
+		goto fail;
 	}
 
 	if (nbc->dc.meta_dev_idx < 0) {
@@ -999,7 +972,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 		dev_warn(DEV, "refusing attach: md-device too small, "
 		     "at least %llu sectors needed for this meta-disk type\n",
 		     (unsigned long long) min_md_device_sectors);
-		goto release_bdev2_fail;
+		goto fail;
 	}
 
 	/* Make sure the new disk is big enough
@@ -1007,7 +980,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	if (drbd_get_max_capacity(nbc) <
 	    drbd_get_capacity(mdev->this_bdev)) {
 		retcode = ERR_DISK_TO_SMALL;
-		goto release_bdev2_fail;
+		goto fail;
 	}
 
 	nbc->known_size = drbd_get_capacity(nbc->backing_bdev);
@@ -1030,7 +1003,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	retcode = _drbd_request_state(mdev, NS(disk, D_ATTACHING), CS_VERBOSE);
 	drbd_resume_io(mdev);
 	if (retcode < SS_SUCCESS)
-		goto release_bdev2_fail;
+		goto fail;
 
 	if (!get_ldev_if_state(mdev, D_ATTACHING))
 		goto force_diskless;
@@ -1264,18 +1237,14 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
  force_diskless:
 	drbd_force_state(mdev, NS(disk, D_DISKLESS));
 	drbd_md_sync(mdev);
- release_bdev2_fail:
-	if (nbc)
-		bd_release(nbc->md_bdev);
- release_bdev_fail:
-	if (nbc)
-		bd_release(nbc->backing_bdev);
  fail:
 	if (nbc) {
-		if (nbc->lo_file)
-			fput(nbc->lo_file);
-		if (nbc->md_file)
-			fput(nbc->md_file);
+		if (nbc->backing_bdev)
+			blkdev_put(nbc->backing_bdev,
+				   FMODE_READ | FMODE_WRITE | FMODE_EXCL);
+		if (nbc->md_bdev)
+			blkdev_put(nbc->md_bdev,
+				   FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 		kfree(nbc);
 	}
 	lc_destroy(resync_lru);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 19b3568e9326..77d70eebb6b2 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2296,15 +2296,12 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	 * so bdget() can't fail.
 	 */
 	bdget(pd->bdev->bd_dev);
-	if ((ret = blkdev_get(pd->bdev, FMODE_READ)))
+	if ((ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd)))
 		goto out;
 
-	if ((ret = bd_claim(pd->bdev, pd)))
-		goto out_putdev;
-
 	if ((ret = pkt_get_last_written(pd, &lba))) {
 		printk(DRIVER_NAME": pkt_get_last_written failed\n");
-		goto out_unclaim;
+		goto out_putdev;
 	}
 
 	set_capacity(pd->disk, lba << 2);
@@ -2314,7 +2311,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	q = bdev_get_queue(pd->bdev);
 	if (write) {
 		if ((ret = pkt_open_write(pd)))
-			goto out_unclaim;
+			goto out_putdev;
 		/*
 		 * Some CDRW drives can not handle writes larger than one packet,
 		 * even if the size is a multiple of the packet size.
@@ -2329,23 +2326,21 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	}
 
 	if ((ret = pkt_set_segment_merging(pd, q)))
-		goto out_unclaim;
+		goto out_putdev;
 
 	if (write) {
 		if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
 			printk(DRIVER_NAME": not enough memory for buffers\n");
 			ret = -ENOMEM;
-			goto out_unclaim;
+			goto out_putdev;
 		}
 		printk(DRIVER_NAME": %lukB available on disc\n", lba << 1);
 	}
 
 	return 0;
 
-out_unclaim:
-	bd_release(pd->bdev);
 out_putdev:
-	blkdev_put(pd->bdev, FMODE_READ);
+	blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL);
 out:
 	return ret;
 }
@@ -2362,8 +2357,7 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
 	pkt_lock_door(pd, 0);
 
 	pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
-	bd_release(pd->bdev);
-	blkdev_put(pd->bdev, FMODE_READ);
+	blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL);
 
 	pkt_shrink_pktlist(pd);
 }
@@ -2733,7 +2727,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	bdev = bdget(dev);
 	if (!bdev)
 		return -ENOMEM;
-	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY);
+	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
 	if (ret)
 		return ret;