Merge tag 'for-5.10/dm-changes' of...

Merge tag 'for-5.10/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Improve DM core's bio splitting to use blk_max_size_offset(). Also
   fix bio splitting for bios that were deferred to the worker thread
   due to a DM device being suspended.

 - Remove DM core's special handling of NVMe devices now that block core
   has internalized efficiencies drivers previously needed to be
   concerned about (via now removed direct_make_request).

 - Fix request-based DM to not bounce through indirect dm_submit_bio;
   instead have block core make direct call to blk_mq_submit_bio().

 - Various DM core cleanups to simplify and improve code.

 - Update DM cryot to not use drivers that set
   CRYPTO_ALG_ALLOCATES_MEMORY.

 - Fix DM raid's raid1 and raid10 discard limits for the purposes of
   linux-stable. But then remove DM raid's discard limits settings now
   that MD raid can efficiently handle large discards.

 - A couple small cleanups across various targets.

* tag 'for-5.10/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm: fix request-based DM to not bounce through indirect dm_submit_bio
  dm: remove special-casing of bio-based immutable singleton target on NVMe
  dm: export dm_copy_name_and_uuid
  dm: fix comment in __dm_suspend()
  dm: fold dm_process_bio() into dm_submit_bio()
  dm: fix missing imposition of queue_limits from dm_wq_work() thread
  dm snap persistent: simplify area_io()
  dm thin metadata: Remove unused local variable when create thin and snap
  dm raid: remove unnecessary discard limits for raid10
  dm raid: fix discard limits for raid1 and raid10
  dm crypt: don't use drivers that have CRYPTO_ALG_ALLOCATES_MEMORY
  dm: use dm_table_get_device_name() where appropriate in targets
  dm table: make 'struct dm_table' definition accessible to all of DM core
  dm: eliminate need for start_io_acct() forward declaration
  dm: simplify __process_abnormal_io()
  dm: push use of on-stack flush_bio down to __send_empty_flush()
  dm: optimize max_io_len() by inlining max_io_len_target_boundary()
  dm: push md->immutable_target optimization down to __process_bio()
  dm: change max_io_len() to use blk_max_size_offset()
  dm table: stack 'chunk_sectors' limit to account for target-specific splitting

block/blk-mq.c

@@ -2270,7 +2270,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 	blk_queue_exit(q);
 	return BLK_QC_T_NONE;
 }
-EXPORT_SYMBOL_GPL(blk_mq_submit_bio); /* only for request based dm */
 
 void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags,
 		     unsigned int hctx_idx)

drivers/md/dm-cache-target.c

@@ -925,7 +925,7 @@ static enum cache_metadata_mode get_cache_mode(struct cache *cache)
 
 static const char *cache_device_name(struct cache *cache)
 {
-	return dm_device_name(dm_table_get_md(cache->ti->table));
+	return dm_table_device_name(cache->ti->table);
 }
 
 static void notify_mode_switch(struct cache *cache, enum cache_metadata_mode mode)

drivers/md/dm-core.h

@@ -11,6 +11,7 @@
 
 #include <linux/kthread.h>
 #include <linux/ktime.h>
+#include <linux/genhd.h>
 #include <linux/blk-mq.h>
 
 #include <trace/events/block.h>
@@ -25,9 +26,11 @@ struct dm_kobject_holder {
 };
 
 /*
- * DM core internal structure that used directly by dm.c and dm-rq.c
- * DM targets must _not_ deference a mapped_device to directly access its members!
+ * DM core internal structures used directly by dm.c, dm-rq.c and dm-table.c.
+ * DM targets must _not_ deference a mapped_device or dm_table to directly
+ * access their members!
  */
+
 struct mapped_device {
 	struct mutex suspend_lock;
 
@@ -119,6 +122,55 @@ void disable_discard(struct mapped_device *md);
 void disable_write_same(struct mapped_device *md);
 void disable_write_zeroes(struct mapped_device *md);
 
+static inline sector_t dm_get_size(struct mapped_device *md)
+{
+	return get_capacity(md->disk);
+}
+
+static inline struct dm_stats *dm_get_stats(struct mapped_device *md)
+{
+	return &md->stats;
+}
+
+#define DM_TABLE_MAX_DEPTH 16
+
+struct dm_table {
+	struct mapped_device *md;
+	enum dm_queue_mode type;
+
+	/* btree table */
+	unsigned int depth;
+	unsigned int counts[DM_TABLE_MAX_DEPTH]; /* in nodes */
+	sector_t *index[DM_TABLE_MAX_DEPTH];
+
+	unsigned int num_targets;
+	unsigned int num_allocated;
+	sector_t *highs;
+	struct dm_target *targets;
+
+	struct target_type *immutable_target_type;
+
+	bool integrity_supported:1;
+	bool singleton:1;
+	unsigned integrity_added:1;
+
+	/*
+	 * Indicates the rw permissions for the new logical
+	 * device.  This should be a combination of FMODE_READ
+	 * and FMODE_WRITE.
+	 */
+	fmode_t mode;
+
+	/* a list of devices used by this table */
+	struct list_head devices;
+
+	/* events get handed up using this callback */
+	void (*event_fn)(void *);
+	void *event_context;
+
+	struct dm_md_mempools *mempools;
+};
+
 static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
 {
 	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;

drivers/md/dm-crypt.c

@@ -424,7 +424,8 @@ static int crypt_iv_lmk_ctr(struct crypt_config *cc, struct dm_target *ti,
 		return -EINVAL;
 	}
 
-	lmk->hash_tfm = crypto_alloc_shash("md5", 0, 0);
+	lmk->hash_tfm = crypto_alloc_shash("md5", 0,
+					   CRYPTO_ALG_ALLOCATES_MEMORY);
 	if (IS_ERR(lmk->hash_tfm)) {
 		ti->error = "Error initializing LMK hash";
 		return PTR_ERR(lmk->hash_tfm);
@@ -586,7 +587,8 @@ static int crypt_iv_tcw_ctr(struct crypt_config *cc, struct dm_target *ti,
 		return -EINVAL;
 	}
 
-	tcw->crc32_tfm = crypto_alloc_shash("crc32", 0, 0);
+	tcw->crc32_tfm = crypto_alloc_shash("crc32", 0,
+					    CRYPTO_ALG_ALLOCATES_MEMORY);
 	if (IS_ERR(tcw->crc32_tfm)) {
 		ti->error = "Error initializing CRC32 in TCW";
 		return PTR_ERR(tcw->crc32_tfm);
@@ -773,7 +775,8 @@ static int crypt_iv_elephant_ctr(struct crypt_config *cc, struct dm_target *ti,
 	struct iv_elephant_private *elephant = &cc->iv_gen_private.elephant;
 	int r;
 
-	elephant->tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0);
+	elephant->tfm = crypto_alloc_skcipher("ecb(aes)", 0,
+					      CRYPTO_ALG_ALLOCATES_MEMORY);
 	if (IS_ERR(elephant->tfm)) {
 		r = PTR_ERR(elephant->tfm);
 		elephant->tfm = NULL;
@@ -2154,7 +2157,8 @@ static int crypt_alloc_tfms_skcipher(struct crypt_config *cc, char *ciphermode)
 		return -ENOMEM;
 
 	for (i = 0; i < cc->tfms_count; i++) {
-		cc->cipher_tfm.tfms[i] = crypto_alloc_skcipher(ciphermode, 0, 0);
+		cc->cipher_tfm.tfms[i] = crypto_alloc_skcipher(ciphermode, 0,
+						CRYPTO_ALG_ALLOCATES_MEMORY);
 		if (IS_ERR(cc->cipher_tfm.tfms[i])) {
 			err = PTR_ERR(cc->cipher_tfm.tfms[i]);
 			crypt_free_tfms(cc);
@@ -2180,7 +2184,8 @@ static int crypt_alloc_tfms_aead(struct crypt_config *cc, char *ciphermode)
 	if (!cc->cipher_tfm.tfms)
 		return -ENOMEM;
 
-	cc->cipher_tfm.tfms_aead[0] = crypto_alloc_aead(ciphermode, 0, 0);
+	cc->cipher_tfm.tfms_aead[0] = crypto_alloc_aead(ciphermode, 0,
+						CRYPTO_ALG_ALLOCATES_MEMORY);
 	if (IS_ERR(cc->cipher_tfm.tfms_aead[0])) {
 		err = PTR_ERR(cc->cipher_tfm.tfms_aead[0]);
 		crypt_free_tfms(cc);
@@ -2667,7 +2672,7 @@ static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api)
 		return -ENOMEM;
 	strncpy(mac_alg, start, end - start);
 
-	mac = crypto_alloc_ahash(mac_alg, 0, 0);
+	mac = crypto_alloc_ahash(mac_alg, 0, CRYPTO_ALG_ALLOCATES_MEMORY);
 	kfree(mac_alg);
 
 	if (IS_ERR(mac))

drivers/md/dm-ioctl.c

@@ -2044,7 +2044,7 @@ int dm_copy_name_and_uuid(struct mapped_device *md, char *name, char *uuid)
 
 	return r;
 }
-
+EXPORT_SYMBOL_GPL(dm_copy_name_and_uuid);
 
 /**
  * dm_early_create - create a mapped device in early boot.

drivers/md/dm-mpath.c

@@ -466,10 +466,8 @@ static struct pgpath *choose_pgpath(struct multipath *m, size_t nr_bytes)
  */
 #define dm_report_EIO(m)						\
 do {									\
-	struct mapped_device *md = dm_table_get_md((m)->ti->table);	\
-									\
 	DMDEBUG_LIMIT("%s: returning EIO; QIFNP = %d; SQIFNP = %d; DNFS = %d", \
-		      dm_device_name(md),				\
+		      dm_table_device_name((m)->ti->table),		\
 		      test_bit(MPATHF_QUEUE_IF_NO_PATH, &(m)->flags),	\
 		      test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &(m)->flags), \
 		      dm_noflush_suspending((m)->ti));			\
@@ -736,7 +734,7 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
 {
 	unsigned long flags;
 	bool queue_if_no_path_bit, saved_queue_if_no_path_bit;
-	const char *dm_dev_name = dm_device_name(dm_table_get_md(m->ti->table));
+	const char *dm_dev_name = dm_table_device_name(m->ti->table);
 
 	DMDEBUG("%s: %s caller=%s queue_if_no_path=%d save_old_value=%d",
 		dm_dev_name, __func__, caller, queue_if_no_path, save_old_value);
@@ -781,9 +779,9 @@ static int queue_if_no_path(struct multipath *m, bool queue_if_no_path,
 static void queue_if_no_path_timeout_work(struct timer_list *t)
 {
 	struct multipath *m = from_timer(m, t, nopath_timer);
-	struct mapped_device *md = dm_table_get_md(m->ti->table);
 
-	DMWARN("queue_if_no_path timeout on %s, failing queued IO", dm_device_name(md));
+	DMWARN("queue_if_no_path timeout on %s, failing queued IO",
+	       dm_table_device_name(m->ti->table));
 	queue_if_no_path(m, false, false, __func__);
 }
 
@@ -1334,7 +1332,7 @@ static int fail_path(struct pgpath *pgpath)
 		goto out;
 
 	DMWARN("%s: Failing path %s.",
-	       dm_device_name(dm_table_get_md(m->ti->table)),
+	       dm_table_device_name(m->ti->table),
 	       pgpath->path.dev->name);
 
 	pgpath->pg->ps.type->fail_path(&pgpath->pg->ps, &pgpath->path);
@@ -1375,7 +1373,7 @@ static int reinstate_path(struct pgpath *pgpath)
 		goto out;
 
 	DMWARN("%s: Reinstating path %s.",
-	       dm_device_name(dm_table_get_md(m->ti->table)),
+	       dm_table_device_name(m->ti->table),
 	       pgpath->path.dev->name);
 
 	r = pgpath->pg->ps.type->reinstate_path(&pgpath->pg->ps, &pgpath->path);
@@ -1766,7 +1764,7 @@ static void multipath_resume(struct dm_target *ti)
 	}
 
 	DMDEBUG("%s: %s finished; QIFNP = %d; SQIFNP = %d",
-		dm_device_name(dm_table_get_md(m->ti->table)), __func__,
+		dm_table_device_name(m->ti->table), __func__,
 		test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags),
 		test_bit(MPATHF_SAVED_QUEUE_IF_NO_PATH, &m->flags));
 

drivers/md/dm-raid.c

@@ -3728,15 +3728,6 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 	blk_limits_io_min(limits, chunk_size_bytes);
 	blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
-
-	/*
-	 * RAID1 and RAID10 personalities require bio splitting,
-	 * RAID0/4/5/6 don't and process large discard bios properly.
-	 */
-	if (rs_is_raid1(rs) || rs_is_raid10(rs)) {
-		limits->discard_granularity = chunk_size_bytes;
-		limits->max_discard_sectors = rs->md.chunk_sectors;
-	}
 }
 
 static void raid_postsuspend(struct dm_target *ti)

drivers/md/dm-rq.c

@@ -175,7 +175,7 @@ static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long mse
 
 void dm_mq_kick_requeue_list(struct mapped_device *md)
 {
-	__dm_mq_kick_requeue_list(dm_get_md_queue(md), 0);
+	__dm_mq_kick_requeue_list(md->queue, 0);
 }
 EXPORT_SYMBOL(dm_mq_kick_requeue_list);
 

drivers/md/dm-snap-persistent.c

@@ -284,16 +284,9 @@ static void skip_metadata(struct pstore *ps)
  */
 static int area_io(struct pstore *ps, int op, int op_flags)
 {
-	int r;
-	chunk_t chunk;
-
-	chunk = area_location(ps, ps->current_area);
+	chunk_t chunk = area_location(ps, ps->current_area);
 
-	r = chunk_io(ps, ps->area, chunk, op, op_flags, 0);
-	if (r)
-		return r;
-
-	return 0;
+	return chunk_io(ps, ps->area, chunk, op, op_flags, 0);
 }
 
 static void zero_memory_area(struct pstore *ps)

drivers/md/dm-table.c

@@ -18,54 +18,17 @@
 #include <linux/mutex.h>
 #include <linux/delay.h>
 #include <linux/atomic.h>
+#include <linux/lcm.h>
 #include <linux/blk-mq.h>
 #include <linux/mount.h>
 #include <linux/dax.h>
 
 #define DM_MSG_PREFIX "table"
 
-#define MAX_DEPTH 16
 #define NODE_SIZE L1_CACHE_BYTES
 #define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
 #define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
 
-struct dm_table {
-	struct mapped_device *md;
-	enum dm_queue_mode type;
-
-	/* btree table */
-	unsigned int depth;
-	unsigned int counts[MAX_DEPTH];	/* in nodes */
-	sector_t *index[MAX_DEPTH];
-
-	unsigned int num_targets;
-	unsigned int num_allocated;
-	sector_t *highs;
-	struct dm_target *targets;
-
-	struct target_type *immutable_target_type;
-
-	bool integrity_supported:1;
-	bool singleton:1;
-	unsigned integrity_added:1;
-
-	/*
-	 * Indicates the rw permissions for the new logical
-	 * device.  This should be a combination of FMODE_READ
-	 * and FMODE_WRITE.
-	 */
-	fmode_t mode;
-
-	/* a list of devices used by this table */
-	struct list_head devices;
-
-	/* events get handed up using this callback */
-	void (*event_fn)(void *);
-	void *event_context;
-
-	struct dm_md_mempools *mempools;
-};
-
 /*
  * Similar to ceiling(log_size(n))
  */
@@ -841,8 +804,7 @@ EXPORT_SYMBOL(dm_consume_args);
 static bool __table_type_bio_based(enum dm_queue_mode table_type)
 {
 	return (table_type == DM_TYPE_BIO_BASED ||
-		table_type == DM_TYPE_DAX_BIO_BASED ||
-		table_type == DM_TYPE_NVME_BIO_BASED);
+		table_type == DM_TYPE_DAX_BIO_BASED);
 }
 
 static bool __table_type_request_based(enum dm_queue_mode table_type)
@@ -898,8 +860,6 @@ bool dm_table_supports_dax(struct dm_table *t,
 	return true;
 }
 
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t);
-
 static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev,
 				  sector_t start, sector_t len, void *data)
 {
@@ -929,7 +889,6 @@ static int dm_table_determine_type(struct dm_table *t)
 			goto verify_bio_based;
 		}
 		BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED);
-		BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED);
 		goto verify_rq_based;
 	}
 
@@ -968,15 +927,6 @@ static int dm_table_determine_type(struct dm_table *t)
 		if (dm_table_supports_dax(t, device_supports_dax, &page_size) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
-		} else {
-			/* Check if upgrading to NVMe bio-based is valid or required */
-			tgt = dm_table_get_immutable_target(t);
-			if (tgt && !tgt->max_io_len && dm_table_does_not_support_partial_completion(t)) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-				goto verify_rq_based; /* must be stacked directly on NVMe (blk-mq) */
-			} else if (list_empty(devices) && live_md_type == DM_TYPE_NVME_BIO_BASED) {
-				t->type = DM_TYPE_NVME_BIO_BASED;
-			}
 		}
 		return 0;
 	}
@@ -993,8 +943,7 @@ static int dm_table_determine_type(struct dm_table *t)
 	 * (e.g. request completion process for partial completion.)
 	 */
 	if (t->num_targets > 1) {
-		DMERR("%s DM doesn't support multiple targets",
-		      t->type == DM_TYPE_NVME_BIO_BASED ? "nvme bio-based" : "request-based");
+		DMERR("request-based DM doesn't support multiple targets");
 		return -EINVAL;
 	}
 
@@ -1506,6 +1455,10 @@ int dm_calculate_queue_limits(struct dm_table *table,
 			zone_sectors = ti_limits.chunk_sectors;
 		}
 
+		/* Stack chunk_sectors if target-specific splitting is required */
+		if (ti->max_io_len)
+			ti_limits.chunk_sectors = lcm_not_zero(ti->max_io_len,
+							       ti_limits.chunk_sectors);
 		/* Set I/O hints portion of queue limits */
 		if (ti->type->io_hints)
 			ti->type->io_hints(ti, &ti_limits);
@@ -1684,20 +1637,6 @@ static bool dm_table_all_devices_attribute(struct dm_table *t,
 	return true;
 }
 
-static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev,
-					sector_t start, sector_t len, void *data)
-{
-	char b[BDEVNAME_SIZE];
-
-	/* For now, NVMe devices are the only devices of this class */
-	return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0);
-}
-
-static bool dm_table_does_not_support_partial_completion(struct dm_table *t)
-{
-	return dm_table_all_devices_attribute(t, device_no_partial_completion);
-}
-
 static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev,
 					 sector_t start, sector_t len, void *data)
 {
@@ -2080,16 +2019,11 @@ EXPORT_SYMBOL_GPL(dm_table_device_name);
 
 void dm_table_run_md_queue_async(struct dm_table *t)
 {
-	struct mapped_device *md;
-	struct request_queue *queue;
-
 	if (!dm_table_request_based(t))
 		return;
 
-	md = dm_table_get_md(t);
-	queue = dm_get_md_queue(md);
-	if (queue)
-		blk_mq_run_hw_queues(queue, true);
+	if (t->md->queue)
+		blk_mq_run_hw_queues(t->md->queue, true);
 }
 EXPORT_SYMBOL(dm_table_run_md_queue_async);
 

drivers/md/dm-thin-metadata.c

@@ -1051,12 +1051,11 @@ static int __create_thin(struct dm_pool_metadata *pmd,
 	int r;
 	dm_block_t dev_root;
 	uint64_t key = dev;
-	struct disk_device_details details_le;
 	struct dm_thin_device *td;
 	__le64 value;
 
 	r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
-			    &key, &details_le);
+			    &key, NULL);
 	if (!r)
 		return -EEXIST;
 
@@ -1129,12 +1128,11 @@ static int __create_snap(struct dm_pool_metadata *pmd,
 	dm_block_t origin_root;
 	uint64_t key = origin, dev_key = dev;
 	struct dm_thin_device *td;
-	struct disk_device_details details_le;
 	__le64 value;
 
 	/* check this device is unused */
 	r = dm_btree_lookup(&pmd->details_info, pmd->details_root,
-			    &dev_key, &details_le);
+			    &dev_key, NULL);
 	if (!r)
 		return -EEXIST;
 

drivers/md/dm.h

@@ -179,12 +179,9 @@ int dm_open_count(struct mapped_device *md);
 int dm_lock_for_deletion(struct mapped_device *md, bool mark_deferred, bool only_deferred);
 int dm_cancel_deferred_remove(struct mapped_device *md);
 int dm_request_based(struct mapped_device *md);
-sector_t dm_get_size(struct mapped_device *md);
-struct request_queue *dm_get_md_queue(struct mapped_device *md);
 int dm_get_table_device(struct mapped_device *md, dev_t dev, fmode_t mode,
 			struct dm_dev **result);
 void dm_put_table_device(struct mapped_device *md, struct dm_dev *d);
-struct dm_stats *dm_get_stats(struct mapped_device *md);
 
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
 		      unsigned cookie);

drivers/md/persistent-data/dm-btree.c

@@ -366,6 +366,7 @@ static int btree_lookup_raw(struct ro_spine *s, dm_block_t block, uint64_t key,
 	} while (!(flags & LEAF_NODE));
 
 	*result_key = le64_to_cpu(ro_node(s)->keys[i]);
+	if (v)
 		memcpy(v, value_ptr(ro_node(s), i), value_size);
 
 	return 0;

include/linux/device-mapper.h

@@ -29,7 +29,6 @@ enum dm_queue_mode {
 	DM_TYPE_BIO_BASED	 = 1,
 	DM_TYPE_REQUEST_BASED	 = 2,
 	DM_TYPE_DAX_BIO_BASED	 = 3,
-	DM_TYPE_NVME_BIO_BASED	 = 4,
 };
 
 typedef enum { STATUSTYPE_INFO, STATUSTYPE_TABLE } status_type_t;

include/uapi/linux/dm-ioctl.h

@@ -272,9 +272,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	42
+#define DM_VERSION_MINOR	43
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2020-02-27)"
+#define DM_VERSION_EXTRA	"-ioctl (2020-10-01)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */