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
  ...

Documentation/device-mapper/verity.txt

@@ -109,6 +109,17 @@ fec_start <offset>
     This is the offset, in <data_block_size> blocks, from the start of the
     FEC device to the beginning of the encoding data.
 
+check_at_most_once
+    Verify data blocks only the first time they are read from the data device,
+    rather than every time.  This reduces the overhead of dm-verity so that it
+    can be used on systems that are memory and/or CPU constrained.  However, it
+    provides a reduced level of security because only offline tampering of the
+    data device's content will be detected, not online tampering.
+
+    Hash blocks are still verified each time they are read from the hash device,
+    since verification of hash blocks is less performance critical than data
+    blocks, and a hash block will not be verified any more after all the data
+    blocks it covers have been verified anyway.
 
 Theory of operation
 ===================

drivers/md/dm-cache-target.c

@@ -3387,7 +3387,8 @@ static int process_invalidate_cblocks_message(struct cache *cache, unsigned coun
  *
  * The key migration_threshold is supported by the cache target core.
  */
-static int cache_message(struct dm_target *ti, unsigned argc, char **argv)
+static int cache_message(struct dm_target *ti, unsigned argc, char **argv,
+			 char *result, unsigned maxlen)
 {
 	struct cache *cache = ti->private;
 

drivers/md/dm-crypt.c

@@ -148,6 +148,8 @@ struct crypt_config {
 	mempool_t *tag_pool;
 	unsigned tag_pool_max_sectors;
 
+	struct percpu_counter n_allocated_pages;
+
 	struct bio_set *bs;
 	struct mutex bio_alloc_lock;
 
@@ -219,6 +221,12 @@ struct crypt_config {
 #define MAX_TAG_SIZE	480
 #define POOL_ENTRY_SIZE	512
 
+static DEFINE_SPINLOCK(dm_crypt_clients_lock);
+static unsigned dm_crypt_clients_n = 0;
+static volatile unsigned long dm_crypt_pages_per_client;
+#define DM_CRYPT_MEMORY_PERCENT			2
+#define DM_CRYPT_MIN_PAGES_PER_CLIENT		(BIO_MAX_PAGES * 16)
+
 static void clone_init(struct dm_crypt_io *, struct bio *);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
 static struct scatterlist *crypt_get_sg_data(struct crypt_config *cc,
@@ -2155,6 +2163,43 @@ static int crypt_wipe_key(struct crypt_config *cc)
 	return r;
 }
 
+static void crypt_calculate_pages_per_client(void)
+{
+	unsigned long pages = (totalram_pages - totalhigh_pages) * DM_CRYPT_MEMORY_PERCENT / 100;
+
+	if (!dm_crypt_clients_n)
+		return;
+
+	pages /= dm_crypt_clients_n;
+	if (pages < DM_CRYPT_MIN_PAGES_PER_CLIENT)
+		pages = DM_CRYPT_MIN_PAGES_PER_CLIENT;
+	dm_crypt_pages_per_client = pages;
+}
+
+static void *crypt_page_alloc(gfp_t gfp_mask, void *pool_data)
+{
+	struct crypt_config *cc = pool_data;
+	struct page *page;
+
+	if (unlikely(percpu_counter_compare(&cc->n_allocated_pages, dm_crypt_pages_per_client) >= 0) &&
+	    likely(gfp_mask & __GFP_NORETRY))
+		return NULL;
+
+	page = alloc_page(gfp_mask);
+	if (likely(page != NULL))
+		percpu_counter_add(&cc->n_allocated_pages, 1);
+
+	return page;
+}
+
+static void crypt_page_free(void *page, void *pool_data)
+{
+	struct crypt_config *cc = pool_data;
+
+	__free_page(page);
+	percpu_counter_sub(&cc->n_allocated_pages, 1);
+}
+
 static void crypt_dtr(struct dm_target *ti)
 {
 	struct crypt_config *cc = ti->private;
@@ -2181,6 +2226,10 @@ static void crypt_dtr(struct dm_target *ti)
 	mempool_destroy(cc->req_pool);
 	mempool_destroy(cc->tag_pool);
 
+	if (cc->page_pool)
+		WARN_ON(percpu_counter_sum(&cc->n_allocated_pages) != 0);
+	percpu_counter_destroy(&cc->n_allocated_pages);
+
 	if (cc->iv_gen_ops && cc->iv_gen_ops->dtr)
 		cc->iv_gen_ops->dtr(cc);
 
@@ -2197,6 +2246,12 @@ static void crypt_dtr(struct dm_target *ti)
 
 	/* Must zero key material before freeing */
 	kzfree(cc);
+
+	spin_lock(&dm_crypt_clients_lock);
+	WARN_ON(!dm_crypt_clients_n);
+	dm_crypt_clients_n--;
+	crypt_calculate_pages_per_client();
+	spin_unlock(&dm_crypt_clients_lock);
 }
 
 static int crypt_ctr_ivmode(struct dm_target *ti, const char *ivmode)
@@ -2644,6 +2699,15 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->private = cc;
 
+	spin_lock(&dm_crypt_clients_lock);
+	dm_crypt_clients_n++;
+	crypt_calculate_pages_per_client();
+	spin_unlock(&dm_crypt_clients_lock);
+
+	ret = percpu_counter_init(&cc->n_allocated_pages, 0, GFP_KERNEL);
+	if (ret < 0)
+		goto bad;
+
 	/* Optional parameters need to be read before cipher constructor */
 	if (argc > 5) {
 		ret = crypt_ctr_optional(ti, argc - 5, &argv[5]);
@@ -2698,7 +2762,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size,
 		      ARCH_KMALLOC_MINALIGN);
 
-	cc->page_pool = mempool_create_page_pool(BIO_MAX_PAGES, 0);
+	cc->page_pool = mempool_create(BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
 	if (!cc->page_pool) {
 		ti->error = "Cannot allocate page mempool";
 		goto bad;
@@ -2942,7 +3006,8 @@ static void crypt_resume(struct dm_target *ti)
  *	key set <key>
  *	key wipe
  */
-static int crypt_message(struct dm_target *ti, unsigned argc, char **argv)
+static int crypt_message(struct dm_target *ti, unsigned argc, char **argv,
+			 char *result, unsigned maxlen)
 {
 	struct crypt_config *cc = ti->private;
 	int key_size, ret = -EINVAL;

drivers/md/dm-era-target.c

@@ -1635,7 +1635,8 @@ err:
 	DMEMIT("Error");
 }
 
-static int era_message(struct dm_target *ti, unsigned argc, char **argv)
+static int era_message(struct dm_target *ti, unsigned argc, char **argv,
+		       char *result, unsigned maxlen)
 {
 	struct era *era = ti->private;
 

drivers/md/dm-flakey.c

@@ -442,8 +442,7 @@ static void flakey_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int flakey_prepare_ioctl(struct dm_target *ti,
-		struct block_device **bdev, fmode_t *mode)
+static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
 {
 	struct flakey_c *fc = ti->private;
 

drivers/md/dm-integrity.c

@@ -18,7 +18,7 @@
 #include <crypto/hash.h>
 #include <crypto/skcipher.h>
 #include <linux/async_tx.h>
-#include "dm-bufio.h"
+#include <linux/dm-bufio.h>
 
 #define DM_MSG_PREFIX "integrity"
 
@@ -2548,6 +2548,9 @@ static int get_mac(struct crypto_shash **hash, struct alg_spec *a, char **error,
 				*error = error_key;
 				return r;
 			}
+		} else if (crypto_shash_get_flags(*hash) & CRYPTO_TFM_NEED_KEY) {
+			*error = error_key;
+			return -ENOKEY;
 		}
 	}
 

drivers/md/dm-ioctl.c

@@ -1595,7 +1595,7 @@ static int target_message(struct file *filp, struct dm_ioctl *param, size_t para
 		DMWARN("Target message sector outside device.");
 		r = -EINVAL;
 	} else if (ti->type->message)
-		r = ti->type->message(ti, argc, argv);
+		r = ti->type->message(ti, argc, argv, result, maxlen);
 	else {
 		DMWARN("Target type does not support messages");
 		r = -EINVAL;

drivers/md/dm-linear.c

@@ -59,6 +59,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->num_flush_bios = 1;
 	ti->num_discard_bios = 1;
+	ti->num_secure_erase_bios = 1;
 	ti->num_write_same_bios = 1;
 	ti->num_write_zeroes_bios = 1;
 	ti->private = lc;
@@ -129,8 +130,7 @@ static void linear_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int linear_prepare_ioctl(struct dm_target *ti,
-		struct block_device **bdev, fmode_t *mode)
+static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
 {
 	struct linear_c *lc = (struct linear_c *) ti->private;
 	struct dm_dev *dev = lc->dev;

drivers/md/dm-log-writes.c

@@ -52,10 +52,11 @@
  * in fact we want to do the data and the discard in the order that they
  * completed.
  */
-#define LOG_FLUSH_FLAG (1 << 0)
-#define LOG_FUA_FLAG (1 << 1)
-#define LOG_DISCARD_FLAG (1 << 2)
-#define LOG_MARK_FLAG (1 << 3)
+#define LOG_FLUSH_FLAG		(1 << 0)
+#define LOG_FUA_FLAG		(1 << 1)
+#define LOG_DISCARD_FLAG	(1 << 2)
+#define LOG_MARK_FLAG		(1 << 3)
+#define LOG_METADATA_FLAG	(1 << 4)
 
 #define WRITE_LOG_VERSION 1ULL
 #define WRITE_LOG_MAGIC 0x6a736677736872ULL
@@ -699,6 +700,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 	bool flush_bio = (bio->bi_opf & REQ_PREFLUSH);
 	bool fua_bio = (bio->bi_opf & REQ_FUA);
 	bool discard_bio = (bio_op(bio) == REQ_OP_DISCARD);
+	bool meta_bio = (bio->bi_opf & REQ_META);
 
 	pb->block = NULL;
 
@@ -743,6 +745,8 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 		block->flags |= LOG_FUA_FLAG;
 	if (discard_bio)
 		block->flags |= LOG_DISCARD_FLAG;
+	if (meta_bio)
+		block->flags |= LOG_METADATA_FLAG;
 
 	block->sector = bio_to_dev_sectors(lc, bio->bi_iter.bi_sector);
 	block->nr_sectors = bio_to_dev_sectors(lc, bio_sectors(bio));
@@ -860,7 +864,7 @@ static void log_writes_status(struct dm_target *ti, status_type_t type,
 }
 
 static int log_writes_prepare_ioctl(struct dm_target *ti,
-		struct block_device **bdev, fmode_t *mode)
+				    struct block_device **bdev)
 {
 	struct log_writes_c *lc = ti->private;
 	struct dm_dev *dev = lc->dev;
@@ -887,7 +891,8 @@ static int log_writes_iterate_devices(struct dm_target *ti,
  * Messages supported:
  *   mark <mark data> - specify the marked data.
  */
-static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv)
+static int log_writes_message(struct dm_target *ti, unsigned argc, char **argv,
+			      char *result, unsigned maxlen)
 {
 	int r = -EINVAL;
 	struct log_writes_c *lc = ti->private;

drivers/md/dm-mpath.c

@@ -714,7 +714,7 @@ static void process_queued_bios(struct work_struct *work)
 		case DM_MAPIO_REMAPPED:
 			generic_make_request(bio);
 			break;
-		case 0:
+		case DM_MAPIO_SUBMITTED:
 			break;
 		default:
 			WARN_ONCE(true, "__multipath_map_bio() returned %d\n", r);
@@ -1811,7 +1811,8 @@ static void multipath_status(struct dm_target *ti, status_type_t type,
 	spin_unlock_irqrestore(&m->lock, flags);
 }
 
-static int multipath_message(struct dm_target *ti, unsigned argc, char **argv)
+static int multipath_message(struct dm_target *ti, unsigned argc, char **argv,
+			     char *result, unsigned maxlen)
 {
 	int r = -EINVAL;
 	struct dm_dev *dev;
@@ -1875,7 +1876,7 @@ out:
 }
 
 static int multipath_prepare_ioctl(struct dm_target *ti,
-		struct block_device **bdev, fmode_t *mode)
+				   struct block_device **bdev)
 {
 	struct multipath *m = ti->private;
 	struct pgpath *current_pgpath;
@@ -1888,7 +1889,6 @@ static int multipath_prepare_ioctl(struct dm_target *ti,
 	if (current_pgpath) {
 		if (!test_bit(MPATHF_QUEUE_IO, &m->flags)) {
 			*bdev = current_pgpath->path.dev->bdev;
-			*mode = current_pgpath->path.dev->mode;
 			r = 0;
 		} else {
 			/* pg_init has not started or completed */

drivers/md/dm-raid.c

@@ -1370,19 +1370,18 @@ static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
 			 * In device-mapper, we specify things in sectors, but
 			 * MD records this value in kB
 			 */
-			value /= 2;
-			if (value > COUNTER_MAX) {
+			if (value < 0 || value / 2 > COUNTER_MAX) {
 				rs->ti->error = "Max write-behind limit out of range";
 				return -EINVAL;
 			}
 
-			rs->md.bitmap_info.max_write_behind = value;
+			rs->md.bitmap_info.max_write_behind = value / 2;
 		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_DAEMON_SLEEP))) {
 			if (test_and_set_bit(__CTR_FLAG_DAEMON_SLEEP, &rs->ctr_flags)) {
 				rs->ti->error = "Only one daemon_sleep argument pair allowed";
 				return -EINVAL;
 			}
-			if (!value || (value > MAX_SCHEDULE_TIMEOUT)) {
+			if (value < 0) {
 				rs->ti->error = "daemon sleep period out of range";
 				return -EINVAL;
 			}
@@ -1424,27 +1423,33 @@ static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
 				return -EINVAL;
 			}
 
+			if (value < 0) {
+				rs->ti->error = "Bogus stripe cache entries value";
+				return -EINVAL;
+			}
 			rs->stripe_cache_entries = value;
 		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MIN_RECOVERY_RATE))) {
 			if (test_and_set_bit(__CTR_FLAG_MIN_RECOVERY_RATE, &rs->ctr_flags)) {
 				rs->ti->error = "Only one min_recovery_rate argument pair allowed";
 				return -EINVAL;
 			}
-			if (value > INT_MAX) {
+
+			if (value < 0) {
 				rs->ti->error = "min_recovery_rate out of range";
 				return -EINVAL;
 			}
-			rs->md.sync_speed_min = (int)value;
+			rs->md.sync_speed_min = value;
 		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_MAX_RECOVERY_RATE))) {
 			if (test_and_set_bit(__CTR_FLAG_MAX_RECOVERY_RATE, &rs->ctr_flags)) {
 				rs->ti->error = "Only one max_recovery_rate argument pair allowed";
 				return -EINVAL;
 			}
-			if (value > INT_MAX) {
+
+			if (value < 0) {
 				rs->ti->error = "max_recovery_rate out of range";
 				return -EINVAL;
 			}
-			rs->md.sync_speed_max = (int)value;
+			rs->md.sync_speed_max = value;
 		} else if (!strcasecmp(key, dm_raid_arg_name_by_flag(CTR_FLAG_REGION_SIZE))) {
 			if (test_and_set_bit(__CTR_FLAG_REGION_SIZE, &rs->ctr_flags)) {
 				rs->ti->error = "Only one region_size argument pair allowed";
@@ -1490,6 +1495,12 @@ static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as,
 		return -EINVAL;
 	}
 
+	if (rs->md.sync_speed_max &&
+	    rs->md.sync_speed_min > rs->md.sync_speed_max) {
+		rs->ti->error = "Bogus recovery rates";
+		return -EINVAL;
+	}
+
 	if (validate_region_size(rs, region_size))
 		return -EINVAL;
 
@@ -3408,7 +3419,8 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
 		set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
 
 	} else {
-		if (!test_bit(MD_RECOVERY_INTR, &recovery) &&
+		if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags) &&
+		    !test_bit(MD_RECOVERY_INTR, &recovery) &&
 		    (test_bit(MD_RECOVERY_NEEDED, &recovery) ||
 		     test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
 		     test_bit(MD_RECOVERY_RUNNING, &recovery)))
@@ -3663,7 +3675,8 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 	}
 }
 
-static int raid_message(struct dm_target *ti, unsigned int argc, char **argv)
+static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
+			char *result, unsigned maxlen)
 {
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;

drivers/md/dm-snap-persistent.c

@@ -14,7 +14,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/dm-io.h>
-#include "dm-bufio.h"
+#include <linux/dm-bufio.h>
 
 #define DM_MSG_PREFIX "persistent snapshot"
 #define DM_CHUNK_SIZE_DEFAULT_SECTORS 32	/* 16KB */

drivers/md/dm-stripe.c

@@ -169,6 +169,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	ti->num_flush_bios = stripes;
 	ti->num_discard_bios = stripes;
+	ti->num_secure_erase_bios = stripes;
 	ti->num_write_same_bios = stripes;
 	ti->num_write_zeroes_bios = stripes;
 
@@ -295,6 +296,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 		return DM_MAPIO_REMAPPED;
 	}
 	if (unlikely(bio_op(bio) == REQ_OP_DISCARD) ||
+	    unlikely(bio_op(bio) == REQ_OP_SECURE_ERASE) ||
 	    unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES) ||
 	    unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) {
 		target_bio_nr = dm_bio_get_target_bio_nr(bio);
@@ -368,7 +370,6 @@ static void stripe_status(struct dm_target *ti, status_type_t type,
 			  unsigned status_flags, char *result, unsigned maxlen)
 {
 	struct stripe_c *sc = (struct stripe_c *) ti->private;
-	char buffer[sc->stripes + 1];
 	unsigned int sz = 0;
 	unsigned int i;
 
@@ -377,11 +378,12 @@ static void stripe_status(struct dm_target *ti, status_type_t type,
 		DMEMIT("%d ", sc->stripes);
 		for (i = 0; i < sc->stripes; i++)  {
 			DMEMIT("%s ", sc->stripe[i].dev->name);
-			buffer[i] = atomic_read(&(sc->stripe[i].error_count)) ?
-				'D' : 'A';
 		}
-		buffer[i] = '\0';
-		DMEMIT("1 %s", buffer);
+		DMEMIT("1 ");
+		for (i = 0; i < sc->stripes; i++) {
+			DMEMIT("%c", atomic_read(&(sc->stripe[i].error_count)) ?
+			       'D' : 'A');
+		}
 		break;
 
 	case STATUSTYPE_TABLE:

drivers/md/dm-switch.c

@@ -466,7 +466,8 @@ static int process_set_region_mappings(struct switch_ctx *sctx,
  *
  * Only set_region_mappings is supported.
  */
-static int switch_message(struct dm_target *ti, unsigned argc, char **argv)
+static int switch_message(struct dm_target *ti, unsigned argc, char **argv,
+			  char *result, unsigned maxlen)
 {
 	static DEFINE_MUTEX(message_mutex);
 
@@ -511,8 +512,7 @@ static void switch_status(struct dm_target *ti, status_type_t type,
  *
  * Passthrough all ioctls to the path for sector 0
  */
-static int switch_prepare_ioctl(struct dm_target *ti,
-		struct block_device **bdev, fmode_t *mode)
+static int switch_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
 {
 	struct switch_ctx *sctx = ti->private;
 	unsigned path_nr;
@@ -520,7 +520,6 @@ static int switch_prepare_ioctl(struct dm_target *ti,
 	path_nr = switch_get_path_nr(sctx, 0);
 
 	*bdev = sctx->path_list[path_nr].dmdev->bdev;
-	*mode = sctx->path_list[path_nr].dmdev->mode;
 
 	/*
 	 * Only pass ioctls through if the device sizes match exactly.

drivers/md/dm-table.c

@@ -1846,6 +1846,34 @@ static bool dm_table_supports_discards(struct dm_table *t)
 	return true;
 }
 
+static int device_not_secure_erase_capable(struct dm_target *ti,
+					   struct dm_dev *dev, sector_t start,
+					   sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && !blk_queue_secure_erase(q);
+}
+
+static bool dm_table_supports_secure_erase(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned int i;
+
+	for (i = 0; i < dm_table_get_num_targets(t); i++) {
+		ti = dm_table_get_target(t, i);
+
+		if (!ti->num_secure_erase_bios)
+			return false;
+
+		if (!ti->type->iterate_devices ||
+		    ti->type->iterate_devices(ti, device_not_secure_erase_capable, NULL))
+			return false;
+	}
+
+	return true;
+}
+
 void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits)
 {
@@ -1867,6 +1895,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	} else
 		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
 
+	if (dm_table_supports_secure_erase(t))
+		blk_queue_flag_set(QUEUE_FLAG_SECERASE, q);
+
 	if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) {
 		wc = true;
 		if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_FUA)))

drivers/md/dm-target.c

@@ -16,8 +16,6 @@
 static LIST_HEAD(_targets);
 static DECLARE_RWSEM(_lock);
 
-#define DM_MOD_NAME_SIZE 32
-
 static inline struct target_type *__find_target_type(const char *name)
 {
 	struct target_type *tt;

drivers/md/dm-thin.c

@@ -3705,7 +3705,8 @@ static int process_release_metadata_snap_mesg(unsigned argc, char **argv, struct
  *   reserve_metadata_snap
  *   release_metadata_snap
  */
-static int pool_message(struct dm_target *ti, unsigned argc, char **argv)
+static int pool_message(struct dm_target *ti, unsigned argc, char **argv,
+			char *result, unsigned maxlen)
 {
 	int r = -EINVAL;
 	struct pool_c *pt = ti->private;

drivers/md/dm-unstripe.c

@@ -7,12 +7,6 @@
 #include "dm.h"
 
 #include <linux/module.h>
-#include <linux/init.h>
-#include <linux/blkdev.h>
-#include <linux/bio.h>
-#include <linux/slab.h>
-#include <linux/bitops.h>
-#include <linux/device-mapper.h>
 
 struct unstripe_c {
 	struct dm_dev *dev;
@@ -69,12 +63,6 @@ static int unstripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto err;
 	}
 
-	// FIXME: must support non power of 2 chunk_size, dm-stripe.c does
-	if (!is_power_of_2(uc->chunk_size)) {
-		ti->error = "Non power of 2 chunk_size is not supported yet";
-		goto err;
-	}
-
 	if (kstrtouint(argv[2], 10, &uc->unstripe)) {
 		ti->error = "Invalid stripe number";
 		goto err;
@@ -98,7 +86,7 @@ static int unstripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 
 	uc->unstripe_offset = uc->unstripe * uc->chunk_size;
 	uc->unstripe_width = (uc->stripes - 1) * uc->chunk_size;
-	uc->chunk_shift = fls(uc->chunk_size) - 1;
+	uc->chunk_shift = is_power_of_2(uc->chunk_size) ? fls(uc->chunk_size) - 1 : 0;
 
 	tmp_len = ti->len;
 	if (sector_div(tmp_len, uc->chunk_size)) {
@@ -129,14 +117,18 @@ static sector_t map_to_core(struct dm_target *ti, struct bio *bio)
 {
 	struct unstripe_c *uc = ti->private;
 	sector_t sector = bio->bi_iter.bi_sector;
+	sector_t tmp_sector = sector;
 
 	/* Shift us up to the right "row" on the stripe */
-	sector += uc->unstripe_width * (sector >> uc->chunk_shift);
+	if (uc->chunk_shift)
+		tmp_sector >>= uc->chunk_shift;
+	else
+		sector_div(tmp_sector, uc->chunk_size);
+
+	sector += uc->unstripe_width * tmp_sector;
 
 	/* Account for what stripe we're operating on */
-	sector += uc->unstripe_offset;
-
-	return sector;
+	return sector + uc->unstripe_offset;
 }
 
 static int unstripe_map(struct dm_target *ti, struct bio *bio)
@@ -185,7 +177,7 @@ static void unstripe_io_hints(struct dm_target *ti,
 
 static struct target_type unstripe_target = {
 	.name = "unstriped",
-	.version = {1, 0, 0},
+	.version = {1, 1, 0},
 	.module = THIS_MODULE,
 	.ctr = unstripe_ctr,
 	.dtr = unstripe_dtr,
@@ -197,13 +189,7 @@ static struct target_type unstripe_target = {
 
 static int __init dm_unstripe_init(void)
 {
-	int r;
-
-	r = dm_register_target(&unstripe_target);
-	if (r < 0)
-		DMERR("target registration failed");
-
-	return r;
+	return dm_register_target(&unstripe_target);
 }
 
 static void __exit dm_unstripe_exit(void)
@@ -215,5 +201,6 @@ module_init(dm_unstripe_init);
 module_exit(dm_unstripe_exit);
 
 MODULE_DESCRIPTION(DM_NAME " unstriped target");
+MODULE_ALIAS("dm-unstriped");
 MODULE_AUTHOR("Scott Bauer <scott.bauer@intel.com>");
 MODULE_LICENSE("GPL");

drivers/md/dm-verity-target.c

@@ -32,6 +32,7 @@
 #define DM_VERITY_OPT_LOGGING		"ignore_corruption"
 #define DM_VERITY_OPT_RESTART		"restart_on_corruption"
 #define DM_VERITY_OPT_IGN_ZEROES	"ignore_zero_blocks"
+#define DM_VERITY_OPT_AT_MOST_ONCE	"check_at_most_once"
 
 #define DM_VERITY_OPTS_MAX		(2 + DM_VERITY_OPTS_FEC)
 
@@ -347,8 +348,8 @@ out:
 /*
  * Calculates the digest for the given bio
  */
-int verity_for_io_block(struct dm_verity *v, struct dm_verity_io *io,
-			struct bvec_iter *iter, struct crypto_wait *wait)
+static int verity_for_io_block(struct dm_verity *v, struct dm_verity_io *io,
+			       struct bvec_iter *iter, struct crypto_wait *wait)
 {
 	unsigned int todo = 1 << v->data_dev_block_bits;
 	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
@@ -432,6 +433,18 @@ static int verity_bv_zero(struct dm_verity *v, struct dm_verity_io *io,
 	return 0;
 }
 
+/*
+ * Moves the bio iter one data block forward.
+ */
+static inline void verity_bv_skip_block(struct dm_verity *v,
+					struct dm_verity_io *io,
+					struct bvec_iter *iter)
+{
+	struct bio *bio = dm_bio_from_per_bio_data(io, v->ti->per_io_data_size);
+
+	bio_advance_iter(bio, iter, 1 << v->data_dev_block_bits);
+}
+
 /*
  * Verify one "dm_verity_io" structure.
  */
@@ -445,9 +458,16 @@ static int verity_verify_io(struct dm_verity_io *io)
 
 	for (b = 0; b < io->n_blocks; b++) {
 		int r;
+		sector_t cur_block = io->block + b;
 		struct ahash_request *req = verity_io_hash_req(v, io);
 
-		r = verity_hash_for_block(v, io, io->block + b,
+		if (v->validated_blocks &&
+		    likely(test_bit(cur_block, v->validated_blocks))) {
+			verity_bv_skip_block(v, io, &io->iter);
+			continue;
+		}
+
+		r = verity_hash_for_block(v, io, cur_block,
 					  verity_io_want_digest(v, io),
 					  &is_zero);
 		if (unlikely(r < 0))
@@ -481,13 +501,16 @@ static int verity_verify_io(struct dm_verity_io *io)
 			return r;
 
 		if (likely(memcmp(verity_io_real_digest(v, io),
-				  verity_io_want_digest(v, io), v->digest_size) == 0))
+				  verity_io_want_digest(v, io), v->digest_size) == 0)) {
+			if (v->validated_blocks)
+				set_bit(cur_block, v->validated_blocks);
 			continue;
+		}
 		else if (verity_fec_decode(v, io, DM_VERITY_BLOCK_TYPE_DATA,
-					   io->block + b, NULL, &start) == 0)
+					   cur_block, NULL, &start) == 0)
 			continue;
 		else if (verity_handle_err(v, DM_VERITY_BLOCK_TYPE_DATA,
-					   io->block + b))
+					   cur_block))
 			return -EIO;
 	}
 
@@ -673,6 +696,8 @@ static void verity_status(struct dm_target *ti, status_type_t type,
 			args += DM_VERITY_OPTS_FEC;
 		if (v->zero_digest)
 			args++;
+		if (v->validated_blocks)
+			args++;
 		if (!args)
 			return;
 		DMEMIT(" %u", args);
@@ -691,13 +716,14 @@ static void verity_status(struct dm_target *ti, status_type_t type,
 		}
 		if (v->zero_digest)
 			DMEMIT(" " DM_VERITY_OPT_IGN_ZEROES);
+		if (v->validated_blocks)
+			DMEMIT(" " DM_VERITY_OPT_AT_MOST_ONCE);
 		sz = verity_fec_status_table(v, sz, result, maxlen);
 		break;
 	}
 }
 
-static int verity_prepare_ioctl(struct dm_target *ti,
-		struct block_device **bdev, fmode_t *mode)
+static int verity_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
 {
 	struct dm_verity *v = ti->private;
 
@@ -740,6 +766,7 @@ static void verity_dtr(struct dm_target *ti)
 	if (v->bufio)
 		dm_bufio_client_destroy(v->bufio);
 
+	kvfree(v->validated_blocks);
 	kfree(v->salt);
 	kfree(v->root_digest);
 	kfree(v->zero_digest);
@@ -760,6 +787,26 @@ static void verity_dtr(struct dm_target *ti)
 	kfree(v);
 }
 
+static int verity_alloc_most_once(struct dm_verity *v)
+{
+	struct dm_target *ti = v->ti;
+
+	/* the bitset can only handle INT_MAX blocks */
+	if (v->data_blocks > INT_MAX) {
+		ti->error = "device too large to use check_at_most_once";
+		return -E2BIG;
+	}
+
+	v->validated_blocks = kvzalloc(BITS_TO_LONGS(v->data_blocks) *
+				       sizeof(unsigned long), GFP_KERNEL);
+	if (!v->validated_blocks) {
+		ti->error = "failed to allocate bitset for check_at_most_once";
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 static int verity_alloc_zero_digest(struct dm_verity *v)
 {
 	int r = -ENOMEM;
@@ -829,6 +876,12 @@ static int verity_parse_opt_args(struct dm_arg_set *as, struct dm_verity *v)
 			}
 			continue;
 
+		} else if (!strcasecmp(arg_name, DM_VERITY_OPT_AT_MOST_ONCE)) {
+			r = verity_alloc_most_once(v);
+			if (r)
+				return r;
+			continue;
+
 		} else if (verity_is_fec_opt_arg(arg_name)) {
 			r = verity_fec_parse_opt_args(as, v, &argc, arg_name);
 			if (r)
@@ -1096,7 +1149,7 @@ bad:
 
 static struct target_type verity_target = {
 	.name		= "verity",
-	.version	= {1, 3, 0},
+	.version	= {1, 4, 0},
 	.module		= THIS_MODULE,
 	.ctr		= verity_ctr,
 	.dtr		= verity_dtr,