Merge tag 'for-6.7/dm-changes' of...

Merge tag 'for-6.7/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm

Pull device mapper updates from Mike Snitzer:

 - Update DM core to directly call the map function for both the linear
   and stripe targets; which are provided by DM core

 - Various updates to use new safer string functions

 - Update DM core to respect REQ_NOWAIT flag in normal bios so that
   memory allocations are always attempted with GFP_NOWAIT

 - Add Mikulas Patocka to MAINTAINERS as a DM maintainer!

 - Improve DM delay target's handling of short delays (< 50ms) by using
   a kthread to check expiration of IOs rather than timers and a wq

 - Update the DM error target so that it works with zoned storage. This
   helps xfstests to provide proper IO error handling coverage when
   testing a filesystem with native zoned storage support

 - Update both DM crypt and integrity targets to improve performance by
   using crypto_shash_digest() rather than init+update+final sequence

 - Fix DM crypt target by backfilling missing memory allocation
   accounting for compound pages

* tag 'for-6.7/dm-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/device-mapper/linux-dm:
  dm crypt: account large pages in cc->n_allocated_pages
  dm integrity: use crypto_shash_digest() in sb_mac()
  dm crypt: use crypto_shash_digest() in crypt_iv_tcw_whitening()
  dm error: Add support for zoned block devices
  dm delay: for short delays, use kthread instead of timers and wq
  MAINTAINERS: add Mikulas Patocka as a DM maintainer
  dm: respect REQ_NOWAIT flag in normal bios issued to DM
  dm: enhance alloc_multiple_bios() to be more versatile
  dm: make __send_duplicate_bios return unsigned int
  dm log userspace: replace deprecated strncpy with strscpy
  dm ioctl: replace deprecated strncpy with strscpy_pad
  dm crypt: replace open-coded kmemdup_nul
  dm cache metadata: replace deprecated strncpy with strscpy
  dm: shortcut the calls to linear_map and stripe_map

MAINTAINERS

@@ -6028,6 +6028,7 @@ F:	include/linux/devm-helpers.h
 DEVICE-MAPPER  (LVM)
 M:	Alasdair Kergon <agk@redhat.com>
 M:	Mike Snitzer <snitzer@kernel.org>
+M:	Mikulas Patocka <mpatocka@redhat.com>
 M:	dm-devel@lists.linux.dev
 L:	dm-devel@lists.linux.dev
 S:	Maintained

drivers/md/dm-cache-metadata.c

@@ -597,7 +597,7 @@ static void read_superblock_fields(struct dm_cache_metadata *cmd,
 	cmd->discard_nr_blocks = to_dblock(le64_to_cpu(disk_super->discard_nr_blocks));
 	cmd->data_block_size = le32_to_cpu(disk_super->data_block_size);
 	cmd->cache_blocks = to_cblock(le32_to_cpu(disk_super->cache_blocks));
-	strncpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name));
+	strscpy(cmd->policy_name, disk_super->policy_name, sizeof(cmd->policy_name));
 	cmd->policy_version[0] = le32_to_cpu(disk_super->policy_version[0]);
 	cmd->policy_version[1] = le32_to_cpu(disk_super->policy_version[1]);
 	cmd->policy_version[2] = le32_to_cpu(disk_super->policy_version[2]);
@@ -707,7 +707,7 @@ static int __commit_transaction(struct dm_cache_metadata *cmd,
 	disk_super->discard_block_size = cpu_to_le64(cmd->discard_block_size);
 	disk_super->discard_nr_blocks = cpu_to_le64(from_dblock(cmd->discard_nr_blocks));
 	disk_super->cache_blocks = cpu_to_le32(from_cblock(cmd->cache_blocks));
-	strncpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name));
+	strscpy(disk_super->policy_name, cmd->policy_name, sizeof(disk_super->policy_name));
 	disk_super->policy_version[0] = cpu_to_le32(cmd->policy_version[0]);
 	disk_super->policy_version[1] = cpu_to_le32(cmd->policy_version[1]);
 	disk_super->policy_version[2] = cpu_to_le32(cmd->policy_version[2]);
@@ -1726,7 +1726,7 @@ static int write_hints(struct dm_cache_metadata *cmd, struct dm_cache_policy *po
 	    (strlen(policy_name) > sizeof(cmd->policy_name) - 1))
 		return -EINVAL;
 
-	strncpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name));
+	strscpy(cmd->policy_name, policy_name, sizeof(cmd->policy_name));
 	memcpy(cmd->policy_version, policy_version, sizeof(cmd->policy_version));
 
 	hint_size = dm_cache_policy_get_hint_size(policy);

drivers/md/dm-crypt.c

@@ -652,13 +652,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 	/* calculate crc32 for every 32bit part and xor it */
 	desc->tfm = tcw->crc32_tfm;
 	for (i = 0; i < 4; i++) {
-		r = crypto_shash_init(desc);
-		if (r)
-			goto out;
-		r = crypto_shash_update(desc, &buf[i * 4], 4);
-		if (r)
-			goto out;
-		r = crypto_shash_final(desc, &buf[i * 4]);
+		r = crypto_shash_digest(desc, &buf[i * 4], 4, &buf[i * 4]);
 		if (r)
 			goto out;
 	}
@@ -1699,11 +1693,17 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size)
 		order = min(order, remaining_order);
 
 		while (order > 0) {
+			if (unlikely(percpu_counter_read_positive(&cc->n_allocated_pages) +
+					(1 << order) > dm_crypt_pages_per_client))
+				goto decrease_order;
 			pages = alloc_pages(gfp_mask
 				| __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | __GFP_COMP,
 				order);
-			if (likely(pages != NULL))
+			if (likely(pages != NULL)) {
+				percpu_counter_add(&cc->n_allocated_pages, 1 << order);
 				goto have_pages;
+			}
+decrease_order:
 			order--;
 		}
 
@@ -1741,10 +1741,13 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone)
 
 	if (clone->bi_vcnt > 0) { /* bio_for_each_folio_all crashes with an empty bio */
 		bio_for_each_folio_all(fi, clone) {
-			if (folio_test_large(fi.folio))
+			if (folio_test_large(fi.folio)) {
+				percpu_counter_sub(&cc->n_allocated_pages,
+						1 << folio_order(fi.folio));
 				folio_put(fi.folio);
-			else
+			} else {
 				mempool_free(&fi.folio->page, &cc->page_pool);
+			}
 		}
 	}
 }
@@ -2859,10 +2862,9 @@ static int crypt_ctr_auth_cipher(struct crypt_config *cc, char *cipher_api)
 	if (!start || !end || ++start > end)
 		return -EINVAL;
 
-	mac_alg = kzalloc(end - start + 1, GFP_KERNEL);
+	mac_alg = kmemdup_nul(start, end - start, GFP_KERNEL);
 	if (!mac_alg)
 		return -ENOMEM;
-	strncpy(mac_alg, start, end - start);
 
 	mac = crypto_alloc_ahash(mac_alg, 0, CRYPTO_ALG_ALLOCATES_MEMORY);
 	kfree(mac_alg);

drivers/md/dm-delay.c

@@ -13,6 +13,7 @@
 #include <linux/blkdev.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
+#include <linux/kthread.h>
 
 #include <linux/device-mapper.h>
 
@@ -31,6 +32,7 @@ struct delay_c {
 	struct workqueue_struct *kdelayd_wq;
 	struct work_struct flush_expired_bios;
 	struct list_head delayed_bios;
+	struct task_struct *worker;
 	atomic_t may_delay;
 
 	struct delay_class read;
@@ -66,6 +68,44 @@ static void queue_timeout(struct delay_c *dc, unsigned long expires)
 	mutex_unlock(&dc->timer_lock);
 }
 
+static inline bool delay_is_fast(struct delay_c *dc)
+{
+	return !!dc->worker;
+}
+
+static void flush_delayed_bios_fast(struct delay_c *dc, bool flush_all)
+{
+	struct dm_delay_info *delayed, *next;
+
+	mutex_lock(&delayed_bios_lock);
+	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
+			struct bio *bio = dm_bio_from_per_bio_data(delayed,
+						sizeof(struct dm_delay_info));
+			list_del(&delayed->list);
+			dm_submit_bio_remap(bio, NULL);
+			delayed->class->ops--;
+		}
+	}
+	mutex_unlock(&delayed_bios_lock);
+}
+
+static int flush_worker_fn(void *data)
+{
+	struct delay_c *dc = data;
+
+	while (1) {
+		flush_delayed_bios_fast(dc, false);
+		if (unlikely(list_empty(&dc->delayed_bios))) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+		} else
+			cond_resched();
+	}
+
+	return 0;
+}
+
 static void flush_bios(struct bio *bio)
 {
 	struct bio *n;
@@ -78,7 +118,7 @@ static void flush_bios(struct bio *bio)
 	}
 }
 
-static struct bio *flush_delayed_bios(struct delay_c *dc, int flush_all)
+static struct bio *flush_delayed_bios(struct delay_c *dc, bool flush_all)
 {
 	struct dm_delay_info *delayed, *next;
 	unsigned long next_expires = 0;
@@ -115,7 +155,10 @@ static void flush_expired_bios(struct work_struct *work)
 	struct delay_c *dc;
 
 	dc = container_of(work, struct delay_c, flush_expired_bios);
-	flush_bios(flush_delayed_bios(dc, 0));
+	if (delay_is_fast(dc))
+		flush_delayed_bios_fast(dc, false);
+	else
+		flush_bios(flush_delayed_bios(dc, false));
 }
 
 static void delay_dtr(struct dm_target *ti)
@@ -131,8 +174,11 @@ static void delay_dtr(struct dm_target *ti)
 		dm_put_device(ti, dc->write.dev);
 	if (dc->flush.dev)
 		dm_put_device(ti, dc->flush.dev);
+	if (dc->worker)
+		kthread_stop(dc->worker);
 
-	mutex_destroy(&dc->timer_lock);
+	if (!delay_is_fast(dc))
+		mutex_destroy(&dc->timer_lock);
 
 	kfree(dc);
 }
@@ -175,6 +221,7 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 {
 	struct delay_c *dc;
 	int ret;
+	unsigned int max_delay;
 
 	if (argc != 3 && argc != 6 && argc != 9) {
 		ti->error = "Requires exactly 3, 6 or 9 arguments";
@@ -188,16 +235,14 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ti->private = dc;
-	timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
-	INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
 	INIT_LIST_HEAD(&dc->delayed_bios);
-	mutex_init(&dc->timer_lock);
 	atomic_set(&dc->may_delay, 1);
 	dc->argc = argc;
 
 	ret = delay_class_ctr(ti, &dc->read, argv);
 	if (ret)
 		goto bad;
+	max_delay = dc->read.delay;
 
 	if (argc == 3) {
 		ret = delay_class_ctr(ti, &dc->write, argv);
@@ -206,6 +251,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ret = delay_class_ctr(ti, &dc->flush, argv);
 		if (ret)
 			goto bad;
+		max_delay = max(max_delay, dc->write.delay);
+		max_delay = max(max_delay, dc->flush.delay);
 		goto out;
 	}
 
@@ -216,19 +263,37 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		ret = delay_class_ctr(ti, &dc->flush, argv + 3);
 		if (ret)
 			goto bad;
+		max_delay = max(max_delay, dc->flush.delay);
 		goto out;
 	}
 
 	ret = delay_class_ctr(ti, &dc->flush, argv + 6);
 	if (ret)
 		goto bad;
+	max_delay = max(max_delay, dc->flush.delay);
 
 out:
-	dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
-	if (!dc->kdelayd_wq) {
-		ret = -EINVAL;
-		DMERR("Couldn't start kdelayd");
-		goto bad;
+	if (max_delay < 50) {
+		/*
+		 * In case of small requested delays, use kthread instead of
+		 * timers and workqueue to achieve better latency.
+		 */
+		dc->worker = kthread_create(&flush_worker_fn, dc,
+					    "dm-delay-flush-worker");
+		if (IS_ERR(dc->worker)) {
+			ret = PTR_ERR(dc->worker);
+			goto bad;
+		}
+	} else {
+		timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
+		INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
+		mutex_init(&dc->timer_lock);
+		dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
+		if (!dc->kdelayd_wq) {
+			ret = -EINVAL;
+			DMERR("Couldn't start kdelayd");
+			goto bad;
+		}
 	}
 
 	ti->num_flush_bios = 1;
@@ -260,7 +325,10 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
 	list_add_tail(&delayed->list, &dc->delayed_bios);
 	mutex_unlock(&delayed_bios_lock);
 
-	queue_timeout(dc, expires);
+	if (delay_is_fast(dc))
+		wake_up_process(dc->worker);
+	else
+		queue_timeout(dc, expires);
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -270,8 +338,13 @@ static void delay_presuspend(struct dm_target *ti)
 	struct delay_c *dc = ti->private;
 
 	atomic_set(&dc->may_delay, 0);
-	del_timer_sync(&dc->delay_timer);
-	flush_bios(flush_delayed_bios(dc, 1));
+
+	if (delay_is_fast(dc))
+		flush_delayed_bios_fast(dc, true);
+	else {
+		del_timer_sync(&dc->delay_timer);
+		flush_bios(flush_delayed_bios(dc, true));
+	}
 }
 
 static void delay_resume(struct dm_target *ti)
@@ -356,7 +429,7 @@ static int delay_iterate_devices(struct dm_target *ti,
 
 static struct target_type delay_target = {
 	.name	     = "delay",
-	.version     = {1, 3, 0},
+	.version     = {1, 4, 0},
 	.features    = DM_TARGET_PASSES_INTEGRITY,
 	.module      = THIS_MODULE,
 	.ctr	     = delay_ctr,

drivers/md/dm-integrity.c

@@ -493,42 +493,32 @@ static int sb_mac(struct dm_integrity_c *ic, bool wr)
 {
 	SHASH_DESC_ON_STACK(desc, ic->journal_mac);
 	int r;
-	unsigned int size = crypto_shash_digestsize(ic->journal_mac);
+	unsigned int mac_size = crypto_shash_digestsize(ic->journal_mac);
+	__u8 *sb = (__u8 *)ic->sb;
+	__u8 *mac = sb + (1 << SECTOR_SHIFT) - mac_size;
 
-	if (sizeof(struct superblock) + size > 1 << SECTOR_SHIFT) {
+	if (sizeof(struct superblock) + mac_size > 1 << SECTOR_SHIFT) {
 		dm_integrity_io_error(ic, "digest is too long", -EINVAL);
 		return -EINVAL;
 	}
 
 	desc->tfm = ic->journal_mac;
 
-	r = crypto_shash_init(desc);
-	if (unlikely(r < 0)) {
-		dm_integrity_io_error(ic, "crypto_shash_init", r);
-		return r;
-	}
-
-	r = crypto_shash_update(desc, (__u8 *)ic->sb, (1 << SECTOR_SHIFT) - size);
-	if (unlikely(r < 0)) {
-		dm_integrity_io_error(ic, "crypto_shash_update", r);
-		return r;
-	}
-
 	if (likely(wr)) {
-		r = crypto_shash_final(desc, (__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size);
+		r = crypto_shash_digest(desc, sb, mac - sb, mac);
 		if (unlikely(r < 0)) {
-			dm_integrity_io_error(ic, "crypto_shash_final", r);
+			dm_integrity_io_error(ic, "crypto_shash_digest", r);
 			return r;
 		}
 	} else {
-		__u8 result[HASH_MAX_DIGESTSIZE];
+		__u8 actual_mac[HASH_MAX_DIGESTSIZE];
 
-		r = crypto_shash_final(desc, result);
+		r = crypto_shash_digest(desc, sb, mac - sb, actual_mac);
 		if (unlikely(r < 0)) {
-			dm_integrity_io_error(ic, "crypto_shash_final", r);
+			dm_integrity_io_error(ic, "crypto_shash_digest", r);
 			return r;
 		}
-		if (memcmp((__u8 *)ic->sb + (1 << SECTOR_SHIFT) - size, result, size)) {
+		if (memcmp(mac, actual_mac, mac_size)) {
 			dm_integrity_io_error(ic, "superblock mac", -EILSEQ);
 			dm_audit_log_target(DM_MSG_PREFIX, "mac-superblock", ic->ti, 0);
 			return -EILSEQ;

drivers/md/dm-ioctl.c

@@ -1295,8 +1295,8 @@ static void retrieve_status(struct dm_table *table,
 		spec->status = 0;
 		spec->sector_start = ti->begin;
 		spec->length = ti->len;
-		strncpy(spec->target_type, ti->type->name,
-			sizeof(spec->target_type) - 1);
+		strscpy_pad(spec->target_type, ti->type->name,
+			sizeof(spec->target_type));
 
 		outptr += sizeof(struct dm_target_spec);
 		remaining = len - (outptr - outbuf);

drivers/md/dm-linear.c

@@ -85,7 +85,7 @@ static sector_t linear_map_sector(struct dm_target *ti, sector_t bi_sector)
 	return lc->start + dm_target_offset(ti, bi_sector);
 }
 
-static int linear_map(struct dm_target *ti, struct bio *bio)
+int linear_map(struct dm_target *ti, struct bio *bio)
 {
 	struct linear_c *lc = ti->private;
 

drivers/md/dm-log-userspace-base.c

@@ -224,7 +224,7 @@ static int userspace_ctr(struct dm_dirty_log *log, struct dm_target *ti,
 
 	lc->usr_argc = argc;
 
-	strncpy(lc->uuid, argv[0], DM_UUID_LEN);
+	strscpy(lc->uuid, argv[0], sizeof(lc->uuid));
 	argc--;
 	argv++;
 	spin_lock_init(&lc->flush_lock);

drivers/md/dm-stripe.c

@@ -268,7 +268,7 @@ static int stripe_map_range(struct stripe_c *sc, struct bio *bio,
 	return DM_MAPIO_SUBMITTED;
 }
 
-static int stripe_map(struct dm_target *ti, struct bio *bio)
+int stripe_map(struct dm_target *ti, struct bio *bio)
 {
 	struct stripe_c *sc = ti->private;
 	uint32_t stripe;

drivers/md/dm-table.c

@@ -844,7 +844,8 @@ static bool dm_table_supports_dax(struct dm_table *t,
 		if (!ti->type->direct_access)
 			return false;
 
-		if (!ti->type->iterate_devices ||
+		if (dm_target_is_wildcard(ti->type) ||
+		    !ti->type->iterate_devices ||
 		    ti->type->iterate_devices(ti, iterate_fn, NULL))
 			return false;
 	}
@@ -1587,6 +1588,14 @@ static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev,
 	return blk_queue_zoned_model(q) != *zoned_model;
 }
 
+static int device_is_zoned_model(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 blk_queue_zoned_model(q) != BLK_ZONED_NONE;
+}
+
 /*
  * Check the device zoned model based on the target feature flag. If the target
  * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are
@@ -1600,6 +1609,18 @@ static bool dm_table_supports_zoned_model(struct dm_table *t,
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
 
+		/*
+		 * For the wildcard target (dm-error), if we do not have a
+		 * backing device, we must always return false. If we have a
+		 * backing device, the result must depend on checking zoned
+		 * model, like for any other target. So for this, check directly
+		 * if the target backing device is zoned as we get "false" when
+		 * dm-error was set without a backing device.
+		 */
+		if (dm_target_is_wildcard(ti->type) &&
+		    !ti->type->iterate_devices(ti, device_is_zoned_model, NULL))
+			return false;
+
 		if (dm_target_supports_zoned_hm(ti->type)) {
 			if (!ti->type->iterate_devices ||
 			    ti->type->iterate_devices(ti, device_not_zoned_model,

drivers/md/dm-target.c

@@ -116,8 +116,62 @@ EXPORT_SYMBOL(dm_unregister_target);
  * io-err: always fails an io, useful for bringing
  * up LVs that have holes in them.
  */
+struct io_err_c {
+	struct dm_dev *dev;
+	sector_t start;
+};
+
+static int io_err_get_args(struct dm_target *tt, unsigned int argc, char **args)
+{
+	unsigned long long start;
+	struct io_err_c *ioec;
+	char dummy;
+	int ret;
+
+	ioec = kmalloc(sizeof(*ioec), GFP_KERNEL);
+	if (!ioec) {
+		tt->error = "Cannot allocate io_err context";
+		return -ENOMEM;
+	}
+
+	ret = -EINVAL;
+	if (sscanf(args[1], "%llu%c", &start, &dummy) != 1 ||
+	    start != (sector_t)start) {
+		tt->error = "Invalid device sector";
+		goto bad;
+	}
+	ioec->start = start;
+
+	ret = dm_get_device(tt, args[0], dm_table_get_mode(tt->table), &ioec->dev);
+	if (ret) {
+		tt->error = "Device lookup failed";
+		goto bad;
+	}
+
+	tt->private = ioec;
+
+	return 0;
+
+bad:
+	kfree(ioec);
+
+	return ret;
+}
+
 static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args)
 {
+	/*
+	 * If we have arguments, assume it is the path to the backing
+	 * block device and its mapping start sector (same as dm-linear).
+	 * In this case, get the device so that we can get its limits.
+	 */
+	if (argc == 2) {
+		int ret = io_err_get_args(tt, argc, args);
+
+		if (ret)
+			return ret;
+	}
+
 	/*
 	 * Return error for discards instead of -EOPNOTSUPP
 	 */
@@ -129,7 +183,12 @@ static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args)
 
 static void io_err_dtr(struct dm_target *tt)
 {
-	/* empty */
+	struct io_err_c *ioec = tt->private;
+
+	if (ioec) {
+		dm_put_device(tt, ioec->dev);
+		kfree(ioec);
+	}
 }
 
 static int io_err_map(struct dm_target *tt, struct bio *bio)
@@ -149,6 +208,45 @@ static void io_err_release_clone_rq(struct request *clone,
 {
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static sector_t io_err_map_sector(struct dm_target *ti, sector_t bi_sector)
+{
+	struct io_err_c *ioec = ti->private;
+
+	return ioec->start + dm_target_offset(ti, bi_sector);
+}
+
+static int io_err_report_zones(struct dm_target *ti,
+		struct dm_report_zones_args *args, unsigned int nr_zones)
+{
+	struct io_err_c *ioec = ti->private;
+
+	/*
+	 * This should never be called when we do not have a backing device
+	 * as that mean the target is not a zoned one.
+	 */
+	if (WARN_ON_ONCE(!ioec))
+		return -EIO;
+
+	return dm_report_zones(ioec->dev->bdev, ioec->start,
+			       io_err_map_sector(ti, args->next_sector),
+			       args, nr_zones);
+}
+#else
+#define io_err_report_zones NULL
+#endif
+
+static int io_err_iterate_devices(struct dm_target *ti,
+				  iterate_devices_callout_fn fn, void *data)
+{
+	struct io_err_c *ioec = ti->private;
+
+	if (!ioec)
+		return 0;
+
+	return fn(ti, ioec->dev, ioec->start, ti->len, data);
+}
+
 static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	limits->max_discard_sectors = UINT_MAX;
@@ -165,15 +263,17 @@ static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 
 static struct target_type error_target = {
 	.name = "error",
-	.version = {1, 6, 0},
-	.features = DM_TARGET_WILDCARD,
+	.version = {1, 7, 0},
+	.features = DM_TARGET_WILDCARD | DM_TARGET_ZONED_HM,
 	.ctr  = io_err_ctr,
 	.dtr  = io_err_dtr,
 	.map  = io_err_map,
 	.clone_and_map_rq = io_err_clone_and_map_rq,
 	.release_clone_rq = io_err_release_clone_rq,
+	.iterate_devices = io_err_iterate_devices,
 	.io_hints = io_err_io_hints,
 	.direct_access = io_err_dax_direct_access,
+	.report_zones = io_err_report_zones,
 };
 
 int __init dm_target_init(void)

drivers/md/dm.c

@@ -570,13 +570,15 @@ static void dm_end_io_acct(struct dm_io *io)
 	dm_io_acct(io, true);
 }
 
-static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio)
+static struct dm_io *alloc_io(struct mapped_device *md, struct bio *bio, gfp_t gfp_mask)
 {
 	struct dm_io *io;
 	struct dm_target_io *tio;
 	struct bio *clone;
 
-	clone = bio_alloc_clone(NULL, bio, GFP_NOIO, &md->mempools->io_bs);
+	clone = bio_alloc_clone(NULL, bio, gfp_mask, &md->mempools->io_bs);
+	if (unlikely(!clone))
+		return NULL;
 	tio = clone_to_tio(clone);
 	tio->flags = 0;
 	dm_tio_set_flag(tio, DM_TIO_INSIDE_DM_IO);
@@ -1425,10 +1427,17 @@ static void __map_bio(struct bio *clone)
 		 */
 		if (unlikely(dm_emulate_zone_append(md)))
 			r = dm_zone_map_bio(tio);
+		else
+			goto do_map;
+	} else {
+do_map:
+		if (likely(ti->type->map == linear_map))
+			r = linear_map(ti, clone);
+		else if (ti->type->map == stripe_map)
+			r = stripe_map(ti, clone);
 		else
 			r = ti->type->map(ti, clone);
-	} else
-		r = ti->type->map(ti, clone);
+	}
 
 	switch (r) {
 	case DM_MAPIO_SUBMITTED:
@@ -1473,15 +1482,15 @@ static void setup_split_accounting(struct clone_info *ci, unsigned int len)
 
 static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 				struct dm_target *ti, unsigned int num_bios,
-				unsigned *len)
+				unsigned *len, gfp_t gfp_flag)
 {
 	struct bio *bio;
-	int try;
+	int try = (gfp_flag & GFP_NOWAIT) ? 0 : 1;
 
-	for (try = 0; try < 2; try++) {
+	for (; try < 2; try++) {
 		int bio_nr;
 
-		if (try)
+		if (try && num_bios > 1)
 			mutex_lock(&ci->io->md->table_devices_lock);
 		for (bio_nr = 0; bio_nr < num_bios; bio_nr++) {
 			bio = alloc_tio(ci, ti, bio_nr, len,
@@ -1491,7 +1500,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 
 			bio_list_add(blist, bio);
 		}
-		if (try)
+		if (try && num_bios > 1)
 			mutex_unlock(&ci->io->md->table_devices_lock);
 		if (bio_nr == num_bios)
 			return;
@@ -1501,34 +1510,31 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci,
 	}
 }
 
-static int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
-				 unsigned int num_bios, unsigned int *len)
+static unsigned int __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
+					  unsigned int num_bios, unsigned int *len,
+					  gfp_t gfp_flag)
 {
 	struct bio_list blist = BIO_EMPTY_LIST;
 	struct bio *clone;
 	unsigned int ret = 0;
 
-	switch (num_bios) {
-	case 0:
-		break;
-	case 1:
-		if (len)
-			setup_split_accounting(ci, *len);
-		clone = alloc_tio(ci, ti, 0, len, GFP_NOIO);
-		__map_bio(clone);
-		ret = 1;
-		break;
-	default:
-		if (len)
-			setup_split_accounting(ci, *len);
-		/* dm_accept_partial_bio() is not supported with shared tio->len_ptr */
-		alloc_multiple_bios(&blist, ci, ti, num_bios, len);
-		while ((clone = bio_list_pop(&blist))) {
+	if (WARN_ON_ONCE(num_bios == 0)) /* num_bios = 0 is a bug in caller */
+		return 0;
+
+	/* dm_accept_partial_bio() is not supported with shared tio->len_ptr */
+	if (len)
+		setup_split_accounting(ci, *len);
+
+	/*
+	 * Using alloc_multiple_bios(), even if num_bios is 1, to consistently
+	 * support allocating using GFP_NOWAIT with GFP_NOIO fallback.
+	 */
+	alloc_multiple_bios(&blist, ci, ti, num_bios, len, gfp_flag);
+	while ((clone = bio_list_pop(&blist))) {
+		if (num_bios > 1)
 			dm_tio_set_flag(clone_to_tio(clone), DM_TIO_IS_DUPLICATE_BIO);
-			__map_bio(clone);
-			ret += 1;
-		}
-		break;
+		__map_bio(clone);
+		ret += 1;
 	}
 
 	return ret;
@@ -1555,8 +1561,12 @@ static void __send_empty_flush(struct clone_info *ci)
 		unsigned int bios;
 		struct dm_target *ti = dm_table_get_target(t, i);
 
+		if (unlikely(ti->num_flush_bios == 0))
+			continue;
+
 		atomic_add(ti->num_flush_bios, &ci->io->io_count);
-		bios = __send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
+		bios = __send_duplicate_bios(ci, ti, ti->num_flush_bios,
+					     NULL, GFP_NOWAIT);
 		atomic_sub(ti->num_flush_bios - bios, &ci->io->io_count);
 	}
 
@@ -1569,10 +1579,9 @@ static void __send_empty_flush(struct clone_info *ci)
 	bio_uninit(ci->bio);
 }
 
-static void __send_changing_extent_only(struct clone_info *ci, struct dm_target *ti,
-					unsigned int num_bios,
-					unsigned int max_granularity,
-					unsigned int max_sectors)
+static void __send_abnormal_io(struct clone_info *ci, struct dm_target *ti,
+			       unsigned int num_bios, unsigned int max_granularity,
+			       unsigned int max_sectors)
 {
 	unsigned int len, bios;
 
@@ -1580,7 +1589,7 @@ static void __send_changing_extent_only(struct clone_info *ci, struct dm_target
 		    __max_io_len(ti, ci->sector, max_granularity, max_sectors));
 
 	atomic_add(num_bios, &ci->io->io_count);
-	bios = __send_duplicate_bios(ci, ti, num_bios, &len);
+	bios = __send_duplicate_bios(ci, ti, num_bios, &len, GFP_NOIO);
 	/*
 	 * alloc_io() takes one extra reference for submission, so the
 	 * reference won't reach 0 without the following (+1) subtraction
@@ -1649,8 +1658,8 @@ static blk_status_t __process_abnormal_io(struct clone_info *ci,
 	if (unlikely(!num_bios))
 		return BLK_STS_NOTSUPP;
 
-	__send_changing_extent_only(ci, ti, num_bios,
-				    max_granularity, max_sectors);
+	__send_abnormal_io(ci, ti, num_bios, max_granularity, max_sectors);
+
 	return BLK_STS_OK;
 }
 
@@ -1709,10 +1718,6 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 	if (unlikely(!ti))
 		return BLK_STS_IOERR;
 
-	if (unlikely((ci->bio->bi_opf & REQ_NOWAIT) != 0) &&
-	    unlikely(!dm_target_supports_nowait(ti->type)))
-		return BLK_STS_NOTSUPP;
-
 	if (unlikely(ci->is_abnormal_io))
 		return __process_abnormal_io(ci, ti);
 
@@ -1724,7 +1729,17 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 
 	len = min_t(sector_t, max_io_len(ti, ci->sector), ci->sector_count);
 	setup_split_accounting(ci, len);
-	clone = alloc_tio(ci, ti, 0, &len, GFP_NOIO);
+
+	if (unlikely(ci->bio->bi_opf & REQ_NOWAIT)) {
+		if (unlikely(!dm_target_supports_nowait(ti->type)))
+			return BLK_STS_NOTSUPP;
+
+		clone = alloc_tio(ci, ti, 0, &len, GFP_NOWAIT);
+		if (unlikely(!clone))
+			return BLK_STS_AGAIN;
+	} else {
+		clone = alloc_tio(ci, ti, 0, &len, GFP_NOIO);
+	}
 	__map_bio(clone);
 
 	ci->sector += len;
@@ -1733,11 +1748,11 @@ static blk_status_t __split_and_process_bio(struct clone_info *ci)
 	return BLK_STS_OK;
 }
 
-static void init_clone_info(struct clone_info *ci, struct mapped_device *md,
+static void init_clone_info(struct clone_info *ci, struct dm_io *io,
 			    struct dm_table *map, struct bio *bio, bool is_abnormal)
 {
 	ci->map = map;
-	ci->io = alloc_io(md, bio);
+	ci->io = io;
 	ci->bio = bio;
 	ci->is_abnormal_io = is_abnormal;
 	ci->submit_as_polled = false;
@@ -1772,8 +1787,18 @@ static void dm_split_and_process_bio(struct mapped_device *md,
 			return;
 	}
 
-	init_clone_info(&ci, md, map, bio, is_abnormal);
-	io = ci.io;
+	/* Only support nowait for normal IO */
+	if (unlikely(bio->bi_opf & REQ_NOWAIT) && !is_abnormal) {
+		io = alloc_io(md, bio, GFP_NOWAIT);
+		if (unlikely(!io)) {
+			/* Unable to do anything without dm_io. */
+			bio_wouldblock_error(bio);
+			return;
+		}
+	} else {
+		io = alloc_io(md, bio, GFP_NOIO);
+	}
+	init_clone_info(&ci, io, map, bio, is_abnormal);
 
 	if (bio->bi_opf & REQ_PREFLUSH) {
 		__send_empty_flush(&ci);

drivers/md/dm.h

@@ -188,9 +188,11 @@ void dm_kobject_release(struct kobject *kobj);
 /*
  * Targets for linear and striped mappings
  */
+int linear_map(struct dm_target *ti, struct bio *bio);
 int dm_linear_init(void);
 void dm_linear_exit(void);
 
+int stripe_map(struct dm_target *ti, struct bio *bio);
 int dm_stripe_init(void);
 void dm_stripe_exit(void);