Merge tag 'for-4.17/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - DM core passthrough ioctl fix to retain reference to DM table, and
   that table's block devices, while issuing the ioctl to one of those
   block devices.

 - DM core passthrough ioctl fix to _not_ override the fmode_t used to
   issue the ioctl. Overriding by using the fmode_t that the block
   device was originally open with during DM table load is a liability.

 - Add DM core support for secure erase forwarding and update the DM
   linear and DM striped targets to support them.

 - A DM core 4.16 stable fix to allow abnormal IO (e.g. discard, write
   same, write zeroes) for targets that make use of the non-splitting IO
   variant (as is done for multipath or thinp when layered directly on
   NVMe).

 - Allow DM targets to return a payload in response to a DM message that
   they are sent. This is useful for DM targets that would like to
   provide statistics data in response to DM messages.

 - Update DM bufio to support non-power-of-2 block sizes. Numerous other
   related changes prepare the DM bufio code for this support.

 - Fix DM crypt to use a bounded amount of memory across the entire
   system. This is to avoid OOM that can otherwise occur in response to
   certain pathological IO workloads (e.g. discarding a large DM crypt
   device).

 - Add a 'check_at_most_once' feature to the DM verity target to allow
   verity to be used on mobile devices that have very limited resources.

 - Fix the DM integrity target to fail early if a keyed algorithm (e.g.
   HMAC) is to be used but the key isn't set.

 - Add non-power-of-2 support to the DM unstripe target.

 - Eliminate the use of a Variable Length Array in the DM stripe target.

 - Update the DM log-writes target to record metadata (REQ_META flag).

 - DM raid fixes for its nosync status and some variable range issues.

* tag 'for-4.17/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (28 commits)
  dm: remove fmode_t argument from .prepare_ioctl hook
  dm: hold DM table for duration of ioctl rather than use blkdev_get
  dm raid: fix parse_raid_params() variable range issue
  dm verity: make verity_for_io_block static
  dm verity: add 'check_at_most_once' option to only validate hashes once
  dm bufio: don't embed a bio in the dm_buffer structure
  dm bufio: support non-power-of-two block sizes
  dm bufio: use slab cache for dm_buffer structure allocations
  dm bufio: reorder fields in dm_buffer structure
  dm bufio: relax alignment constraint on slab cache
  dm bufio: remove code that merges slab caches
  dm bufio: get rid of slab cache name allocations
  dm bufio: move dm-bufio.h to include/linux/
  dm bufio: delete outdated comment
  dm: add support for secure erase forwarding
  dm: backfill abnormal IO support to non-splitting IO submission
  dm raid: fix nosync status
  dm mpath: use DM_MAPIO_SUBMITTED instead of magic number 0 in process_queued_bios()
  dm stripe: get rid of a Variable Length Array (VLA)
  dm log writes: record metadata flag for better flags record
  ...

1 files changed, 80 insertions, 65 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ded74e1eb0d1..5a81c47be4e4 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -458,67 +458,56 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return dm_get_geometry(md, geo);
 }
 
-static char *_dm_claim_ptr = "I belong to device-mapper";
-
-static int dm_get_bdev_for_ioctl(struct mapped_device *md,
-				 struct block_device **bdev,
-				 fmode_t *mode)
+static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
+			    struct block_device **bdev)
+	__acquires(md->io_barrier)
 {
 	struct dm_target *tgt;
 	struct dm_table *map;
-	int srcu_idx, r, r2;
+	int r;
 
 retry:
 	r = -ENOTTY;
-	map = dm_get_live_table(md, &srcu_idx);
+	map = dm_get_live_table(md, srcu_idx);
 	if (!map || !dm_table_get_size(map))
-		goto out;
+		return r;
 
 	/* We only support devices that have a single target */
 	if (dm_table_get_num_targets(map) != 1)
-		goto out;
+		return r;
 
 	tgt = dm_table_get_target(map, 0);
 	if (!tgt->type->prepare_ioctl)
-		goto out;
-
-	if (dm_suspended_md(md)) {
-		r = -EAGAIN;
-		goto out;
-	}
-
-	r = tgt->type->prepare_ioctl(tgt, bdev, mode);
-	if (r < 0)
-		goto out;
-
-	bdgrab(*bdev);
-	r2 = blkdev_get(*bdev, *mode, _dm_claim_ptr);
-	if (r2 < 0) {
-		r = r2;
-		goto out;
-	}
+		return r;
 
-	dm_put_live_table(md, srcu_idx);
-	return r;
+	if (dm_suspended_md(md))
+		return -EAGAIN;
 
-out:
-	dm_put_live_table(md, srcu_idx);
+	r = tgt->type->prepare_ioctl(tgt, bdev);
 	if (r == -ENOTCONN && !fatal_signal_pending(current)) {
+		dm_put_live_table(md, *srcu_idx);
 		msleep(10);
 		goto retry;
 	}
+
 	return r;
 }
 
+static void dm_unprepare_ioctl(struct mapped_device *md, int srcu_idx)
+	__releases(md->io_barrier)
+{
+	dm_put_live_table(md, srcu_idx);
+}
+
 static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 			unsigned int cmd, unsigned long arg)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
-	int r;
+	int r, srcu_idx;
 
-	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
 	if (r < 0)
-		return r;
+		goto out;
 
 	if (r > 0) {
 		/*
@@ -536,7 +525,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
 
 	r =  __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 out:
-	blkdev_put(bdev, mode);
+	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
 }
 
@@ -710,6 +699,8 @@ static void dm_put_live_table_fast(struct mapped_device *md) __releases(RCU)
 	rcu_read_unlock();
 }
 
+static char *_dm_claim_ptr = "I belong to device-mapper";
+
 /*
  * Open a table device so we can use it as a map destination.
  */
@@ -1414,6 +1405,11 @@ static unsigned get_num_discard_bios(struct dm_target *ti)
 	return ti->num_discard_bios;
 }
 
+static unsigned get_num_secure_erase_bios(struct dm_target *ti)
+{
+	return ti->num_secure_erase_bios;
+}
+
 static unsigned get_num_write_same_bios(struct dm_target *ti)
 {
 	return ti->num_write_same_bios;
@@ -1467,6 +1463,11 @@ static int __send_discard(struct clone_info *ci, struct dm_target *ti)
 					   is_split_required_for_discard);
 }
 
+static int __send_secure_erase(struct clone_info *ci, struct dm_target *ti)
+{
+	return __send_changing_extent_only(ci, ti, get_num_secure_erase_bios, NULL);
+}
+
 static int __send_write_same(struct clone_info *ci, struct dm_target *ti)
 {
 	return __send_changing_extent_only(ci, ti, get_num_write_same_bios, NULL);
@@ -1477,6 +1478,25 @@ static int __send_write_zeroes(struct clone_info *ci, struct dm_target *ti)
 	return __send_changing_extent_only(ci, ti, get_num_write_zeroes_bios, NULL);
 }
 
+static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti,
+				  int *result)
+{
+	struct bio *bio = ci->bio;
+
+	if (bio_op(bio) == REQ_OP_DISCARD)
+		*result = __send_discard(ci, ti);
+	else if (bio_op(bio) == REQ_OP_SECURE_ERASE)
+		*result = __send_secure_erase(ci, ti);
+	else if (bio_op(bio) == REQ_OP_WRITE_SAME)
+		*result = __send_write_same(ci, ti);
+	else if (bio_op(bio) == REQ_OP_WRITE_ZEROES)
+		*result = __send_write_zeroes(ci, ti);
+	else
+		return false;
+
+	return true;
+}
+
 /*
  * Select the correct strategy for processing a non-flush bio.
  */
@@ -1491,12 +1511,8 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 	if (!dm_target_is_valid(ti))
 		return -EIO;
 
-	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
-		return __send_discard(ci, ti);
-	else if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
-		return __send_write_same(ci, ti);
-	else if (unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES))
-		return __send_write_zeroes(ci, ti);
+	if (unlikely(__process_abnormal_io(ci, ti, &r)))
+		return r;
 
 	if (bio_op(bio) == REQ_OP_ZONE_REPORT)
 		len = ci->sector_count;
@@ -1617,9 +1633,12 @@ static blk_qc_t __process_bio(struct mapped_device *md,
 			goto out;
 		}
 
-		tio = alloc_tio(&ci, ti, 0, GFP_NOIO);
 		ci.bio = bio;
 		ci.sector_count = bio_sectors(bio);
+		if (unlikely(__process_abnormal_io(&ci, ti, &error)))
+			goto out;
+
+		tio = alloc_tio(&ci, ti, 0, GFP_NOIO);
 		ret = __clone_and_map_simple_bio(&ci, tio, NULL);
 	}
 out:
@@ -3015,20 +3034,19 @@ static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type,
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	fmode_t mode;
-	int r;
+	int r, srcu_idx;
 
-	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
 	if (r < 0)
-		return r;
+		goto out;
 
 	ops = bdev->bd_disk->fops->pr_ops;
 	if (ops && ops->pr_reserve)
 		r = ops->pr_reserve(bdev, key, type, flags);
 	else
 		r = -EOPNOTSUPP;
-
-	blkdev_put(bdev, mode);
+out:
+	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
 }
 
@@ -3036,20 +3054,19 @@ static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	fmode_t mode;
-	int r;
+	int r, srcu_idx;
 
-	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
 	if (r < 0)
-		return r;
+		goto out;
 
 	ops = bdev->bd_disk->fops->pr_ops;
 	if (ops && ops->pr_release)
 		r = ops->pr_release(bdev, key, type);
 	else
 		r = -EOPNOTSUPP;
-
-	blkdev_put(bdev, mode);
+out:
+	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
 }
 
@@ -3058,20 +3075,19 @@ static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key,
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	fmode_t mode;
-	int r;
+	int r, srcu_idx;
 
-	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
 	if (r < 0)
-		return r;
+		goto out;
 
 	ops = bdev->bd_disk->fops->pr_ops;
 	if (ops && ops->pr_preempt)
 		r = ops->pr_preempt(bdev, old_key, new_key, type, abort);
 	else
 		r = -EOPNOTSUPP;
-
-	blkdev_put(bdev, mode);
+out:
+	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
 }
 
@@ -3079,20 +3095,19 @@ static int dm_pr_clear(struct block_device *bdev, u64 key)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
 	const struct pr_ops *ops;
-	fmode_t mode;
-	int r;
+	int r, srcu_idx;
 
-	r = dm_get_bdev_for_ioctl(md, &bdev, &mode);
+	r = dm_prepare_ioctl(md, &srcu_idx, &bdev);
 	if (r < 0)
-		return r;
+		goto out;
 
 	ops = bdev->bd_disk->fops->pr_ops;
 	if (ops && ops->pr_clear)
 		r = ops->pr_clear(bdev, key);
 	else
 		r = -EOPNOTSUPP;
-
-	blkdev_put(bdev, mode);
+out:
+	dm_unprepare_ioctl(md, srcu_idx);
 	return r;
 }