Merge tag 'for-4.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - A major update for DM cache that reduces the latency for deciding
   whether blocks should migrate to/from the cache. The bio-prison-v2
   interface supports this improvement by enabling direct dispatch of
   work to workqueues rather than having to delay the actual work
   dispatch to the DM cache core. So the dm-cache policies are much more
   nimble by being able to drive IO as they see fit. One immediate
   benefit from the improved latency is a cache that should be much more
   adaptive to changing workloads.

 - Add a new DM integrity target that emulates a block device that has
   additional per-sector tags that can be used for storing integrity
   information.

 - Add a new authenticated encryption feature to the DM crypt target
   that builds on the capabilities provided by the DM integrity target.

 - Add MD interface for switching the raid4/5/6 journal mode and update
   the DM raid target to use it to enable aid4/5/6 journal write-back
   support.

 - Switch the DM verity target over to using the asynchronous hash
   crypto API (this helps work better with architectures that have
   access to off-CPU algorithm providers, which should reduce CPU
   utilization).

 - Various request-based DM and DM multipath fixes and improvements from
   Bart and Christoph.

 - A DM thinp target fix for a bio structure leak that occurs for each
   discard IFF discard passdown is enabled.

 - A fix for a possible deadlock in DM bufio and a fix to re-check the
   new buffer allocation watermark in the face of competing admin
   changes to the 'max_cache_size_bytes' tunable.

 - A couple DM core cleanups.

* tag 'for-4.12/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm: (50 commits)
  dm bufio: check new buffer allocation watermark every 30 seconds
  dm bufio: avoid a possible ABBA deadlock
  dm mpath: make it easier to detect unintended I/O request flushes
  dm mpath: cleanup QUEUE_IF_NO_PATH bit manipulation by introducing assign_bit()
  dm mpath: micro-optimize the hot path relative to MPATHF_QUEUE_IF_NO_PATH
  dm: introduce enum dm_queue_mode to cleanup related code
  dm mpath: verify __pg_init_all_paths locking assumptions at runtime
  dm: verify suspend_locking assumptions at runtime
  dm block manager: remove an unused argument from dm_block_manager_create()
  dm rq: check blk_mq_register_dev() return value in dm_mq_init_request_queue()
  dm mpath: delay requeuing while path initialization is in progress
  dm mpath: avoid that path removal can trigger an infinite loop
  dm mpath: split and rename activate_path() to prepare for its expanded use
  dm ioctl: prevent stack leak in dm ioctl call
  dm integrity: use previously calculated log2 of sectors_per_block
  dm integrity: use hex2bin instead of open-coded variant
  dm crypt: replace custom implementation of hex2bin()
  dm crypt: remove obsolete references to per-CPU state
  dm verity: switch to using asynchronous hash crypto API
  dm crypt: use WQ_HIGHPRI for the IO and crypt workqueues
  ...

1 files changed, 26 insertions, 9 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8bf397729bbd..268edf402bbb 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1104,8 +1104,18 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 
 	__bio_clone_fast(clone, bio);
 
-	if (bio_integrity(bio)) {
-		int r = bio_integrity_clone(clone, bio, GFP_NOIO);
+	if (unlikely(bio_integrity(bio) != NULL)) {
+		int r;
+
+		if (unlikely(!dm_target_has_integrity(tio->ti->type) &&
+			     !dm_target_passes_integrity(tio->ti->type))) {
+			DMWARN("%s: the target %s doesn't support integrity data.",
+				dm_device_name(tio->io->md),
+				tio->ti->type->name);
+			return -EIO;
+		}
+
+		r = bio_integrity_clone(clone, bio, GFP_NOIO);
 		if (r < 0)
 			return r;
 	}
@@ -1113,7 +1123,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 	bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
 	clone->bi_iter.bi_size = to_bytes(len);
 
-	if (bio_integrity(bio))
+	if (unlikely(bio_integrity(bio) != NULL))
 		bio_integrity_trim(clone, 0, len);
 
 	return 0;
@@ -1715,6 +1725,8 @@ static void event_callback(void *context)
  */
 static void __set_size(struct mapped_device *md, sector_t size)
 {
+	lockdep_assert_held(&md->suspend_lock);
+
 	set_capacity(md->disk, size);
 
 	i_size_write(md->bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
@@ -1822,13 +1834,13 @@ void dm_unlock_md_type(struct mapped_device *md)
 	mutex_unlock(&md->type_lock);
 }
 
-void dm_set_md_type(struct mapped_device *md, unsigned type)
+void dm_set_md_type(struct mapped_device *md, enum dm_queue_mode type)
 {
 	BUG_ON(!mutex_is_locked(&md->type_lock));
 	md->type = type;
 }
 
-unsigned dm_get_md_type(struct mapped_device *md)
+enum dm_queue_mode dm_get_md_type(struct mapped_device *md)
 {
 	return md->type;
 }
@@ -1855,7 +1867,7 @@ EXPORT_SYMBOL_GPL(dm_get_queue_limits);
 int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 {
 	int r;
-	unsigned type = dm_get_md_type(md);
+	enum dm_queue_mode type = dm_get_md_type(md);
 
 	switch (type) {
 	case DM_TYPE_REQUEST_BASED:
@@ -1886,6 +1898,9 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 		if (type == DM_TYPE_DAX_BIO_BASED)
 			queue_flag_set_unlocked(QUEUE_FLAG_DAX, md->queue);
 		break;
+	case DM_TYPE_NONE:
+		WARN_ON_ONCE(true);
+		break;
 	}
 
 	return 0;
@@ -2164,8 +2179,6 @@ static void unlock_fs(struct mapped_device *md)
  * If __dm_suspend returns 0, the device is completely quiescent
  * now. There is no request-processing activity. All new requests
  * are being added to md->deferred list.
- *
- * Caller must hold md->suspend_lock
  */
 static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
 			unsigned suspend_flags, long task_state,
@@ -2183,6 +2196,8 @@ static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
 	 */
 	if (noflush)
 		set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
+	else
+		pr_debug("%s: suspending with flush\n", dm_device_name(md));
 
 	/*
 	 * This gets reverted if there's an error later and the targets
@@ -2381,6 +2396,8 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
 {
 	struct dm_table *map = NULL;
 
+	lockdep_assert_held(&md->suspend_lock);
+
 	if (md->internal_suspend_count++)
 		return; /* nested internal suspend */
 
@@ -2571,7 +2588,7 @@ int dm_noflush_suspending(struct dm_target *ti)
 }
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);
 
-struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, unsigned type,
+struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_queue_mode type,
 					    unsigned integrity, unsigned per_io_data_size)
 {
 	struct dm_md_mempools *pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id);