Merge branch 'for-6.11/block-limits' into for-6.11/block

Pull in block limits branch, which exists as a shared branch for both
the block and SCSI tree.

* for-6.11/block-limits: (26 commits)
  block: move integrity information into queue_limits
  block: invert the BLK_INTEGRITY_{GENERATE,VERIFY} flags
  block: bypass the STABLE_WRITES flag for protection information
  block: don't require stable pages for non-PI metadata
  block: use kstrtoul in flag_store
  block: factor out flag_{store,show} helper for integrity
  block: remove the blk_flush_integrity call in blk_integrity_unregister
  block: remove the blk_integrity_profile structure
  dm-integrity: use the nop integrity profile
  md/raid1: don't free conf on raid0_run failure
  md/raid0: don't free conf on raid0_run failure
  block: initialize integrity buffer to zero before writing it to media
  block: add special APIs for run-time disabling of discard and friends
  block: remove unused queue limits API
  sr: convert to the atomic queue limits API
  sd: convert to the atomic queue limits API
  sd: cleanup zoned queue limits initialization
  sd: factor out a sd_discard_mode helper
  sd: simplify the disable case in sd_config_discard
  sd: add a sd_disable_write_same helper
  ...

10 files changed, 79 insertions, 240 deletions

diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 08700bfc3e23..14a44c0f8286 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -206,7 +206,6 @@ struct dm_table {
 
 	bool integrity_supported:1;
 	bool singleton:1;
-	unsigned integrity_added:1;
 
 	/*
 	 * Indicates the rw permissions for the new logical device.  This
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 1b7a97cc3779..6c013ceb0e5f 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1176,8 +1176,8 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 	struct blk_integrity *bi = blk_get_integrity(cc->dev->bdev->bd_disk);
 	struct mapped_device *md = dm_table_get_md(ti->table);
 
-	/* From now we require underlying device with our integrity profile */
-	if (!bi || strcasecmp(bi->profile->name, "DM-DIF-EXT-TAG")) {
+	/* We require an underlying device with non-PI metadata */
+	if (!bi || bi->csum_type != BLK_INTEGRITY_CSUM_NONE) {
 		ti->error = "Integrity profile not supported.";
 		return -EINVAL;
 	}
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 417fddebe367..2a89f8eb4713 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -350,25 +350,6 @@ static struct kmem_cache *journal_io_cache;
 #define DEBUG_bytes(bytes, len, msg, ...)	do { } while (0)
 #endif
 
-static void dm_integrity_prepare(struct request *rq)
-{
-}
-
-static void dm_integrity_complete(struct request *rq, unsigned int nr_bytes)
-{
-}
-
-/*
- * DM Integrity profile, protection is performed layer above (dm-crypt)
- */
-static const struct blk_integrity_profile dm_integrity_profile = {
-	.name			= "DM-DIF-EXT-TAG",
-	.generate_fn		= NULL,
-	.verify_fn		= NULL,
-	.prepare_fn		= dm_integrity_prepare,
-	.complete_fn		= dm_integrity_complete,
-};
-
 static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map);
 static void integrity_bio_wait(struct work_struct *w);
 static void dm_integrity_dtr(struct dm_target *ti);
@@ -3494,6 +3475,17 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim
 		limits->dma_alignment = limits->logical_block_size - 1;
 		limits->discard_granularity = ic->sectors_per_block << SECTOR_SHIFT;
 	}
+
+	if (!ic->internal_hash) {
+		struct blk_integrity *bi = &limits->integrity;
+
+		memset(bi, 0, sizeof(*bi));
+		bi->tuple_size = ic->tag_size;
+		bi->tag_size = bi->tuple_size;
+		bi->interval_exp =
+			ic->sb->log2_sectors_per_block + SECTOR_SHIFT;
+	}
+
 	limits->max_integrity_segments = USHRT_MAX;
 }
 
@@ -3650,20 +3642,6 @@ try_smaller_buffer:
 	return 0;
 }
 
-static void dm_integrity_set(struct dm_target *ti, struct dm_integrity_c *ic)
-{
-	struct gendisk *disk = dm_disk(dm_table_get_md(ti->table));
-	struct blk_integrity bi;
-
-	memset(&bi, 0, sizeof(bi));
-	bi.profile = &dm_integrity_profile;
-	bi.tuple_size = ic->tag_size;
-	bi.tag_size = bi.tuple_size;
-	bi.interval_exp = ic->sb->log2_sectors_per_block + SECTOR_SHIFT;
-
-	blk_integrity_register(disk, &bi);
-}
-
 static void dm_integrity_free_page_list(struct page_list *pl)
 {
 	unsigned int i;
@@ -4649,9 +4627,6 @@ try_smaller_buffer:
 		}
 	}
 
-	if (!ic->internal_hash)
-		dm_integrity_set(ti, ic);
-
 	ti->num_flush_bios = 1;
 	ti->flush_supported = true;
 	if (ic->discard)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index b2d5246cff21..fd789eeb62d9 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -425,6 +425,13 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 		       q->limits.logical_block_size,
 		       q->limits.alignment_offset,
 		       (unsigned long long) start << SECTOR_SHIFT);
+
+	/*
+	 * Only stack the integrity profile if the target doesn't have native
+	 * integrity support.
+	 */
+	if (!dm_target_has_integrity(ti->type))
+		queue_limits_stack_integrity_bdev(limits, bdev);
 	return 0;
 }
 
@@ -702,9 +709,6 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 		t->immutable_target_type = ti->type;
 	}
 
-	if (dm_target_has_integrity(ti->type))
-		t->integrity_added = 1;
-
 	ti->table = t;
 	ti->begin = start;
 	ti->len = len;
@@ -1119,99 +1123,6 @@ static int dm_table_build_index(struct dm_table *t)
 	return r;
 }
 
-static bool integrity_profile_exists(struct gendisk *disk)
-{
-	return !!blk_get_integrity(disk);
-}
-
-/*
- * Get a disk whose integrity profile reflects the table's profile.
- * Returns NULL if integrity support was inconsistent or unavailable.
- */
-static struct gendisk *dm_table_get_integrity_disk(struct dm_table *t)
-{
-	struct list_head *devices = dm_table_get_devices(t);
-	struct dm_dev_internal *dd = NULL;
-	struct gendisk *prev_disk = NULL, *template_disk = NULL;
-
-	for (unsigned int i = 0; i < t->num_targets; i++) {
-		struct dm_target *ti = dm_table_get_target(t, i);
-
-		if (!dm_target_passes_integrity(ti->type))
-			goto no_integrity;
-	}
-
-	list_for_each_entry(dd, devices, list) {
-		template_disk = dd->dm_dev->bdev->bd_disk;
-		if (!integrity_profile_exists(template_disk))
-			goto no_integrity;
-		else if (prev_disk &&
-			 blk_integrity_compare(prev_disk, template_disk) < 0)
-			goto no_integrity;
-		prev_disk = template_disk;
-	}
-
-	return template_disk;
-
-no_integrity:
-	if (prev_disk)
-		DMWARN("%s: integrity not set: %s and %s profile mismatch",
-		       dm_device_name(t->md),
-		       prev_disk->disk_name,
-		       template_disk->disk_name);
-	return NULL;
-}
-
-/*
- * Register the mapped device for blk_integrity support if the
- * underlying devices have an integrity profile.  But all devices may
- * not have matching profiles (checking all devices isn't reliable
- * during table load because this table may use other DM device(s) which
- * must be resumed before they will have an initialized integity
- * profile).  Consequently, stacked DM devices force a 2 stage integrity
- * profile validation: First pass during table load, final pass during
- * resume.
- */
-static int dm_table_register_integrity(struct dm_table *t)
-{
-	struct mapped_device *md = t->md;
-	struct gendisk *template_disk = NULL;
-
-	/* If target handles integrity itself do not register it here. */
-	if (t->integrity_added)
-		return 0;
-
-	template_disk = dm_table_get_integrity_disk(t);
-	if (!template_disk)
-		return 0;
-
-	if (!integrity_profile_exists(dm_disk(md))) {
-		t->integrity_supported = true;
-		/*
-		 * Register integrity profile during table load; we can do
-		 * this because the final profile must match during resume.
-		 */
-		blk_integrity_register(dm_disk(md),
-				       blk_get_integrity(template_disk));
-		return 0;
-	}
-
-	/*
-	 * If DM device already has an initialized integrity
-	 * profile the new profile should not conflict.
-	 */
-	if (blk_integrity_compare(dm_disk(md), template_disk) < 0) {
-		DMERR("%s: conflict with existing integrity profile: %s profile mismatch",
-		      dm_device_name(t->md),
-		      template_disk->disk_name);
-		return 1;
-	}
-
-	/* Preserve existing integrity profile */
-	t->integrity_supported = true;
-	return 0;
-}
-
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 
 struct dm_crypto_profile {
@@ -1423,12 +1334,6 @@ int dm_table_complete(struct dm_table *t)
 		return r;
 	}
 
-	r = dm_table_register_integrity(t);
-	if (r) {
-		DMERR("could not register integrity profile.");
-		return r;
-	}
-
 	r = dm_table_construct_crypto_profile(t);
 	if (r) {
 		DMERR("could not construct crypto profile.");
@@ -1688,6 +1593,14 @@ int dm_calculate_queue_limits(struct dm_table *t,
 
 	blk_set_stacking_limits(limits);
 
+	t->integrity_supported = true;
+	for (unsigned int i = 0; i < t->num_targets; i++) {
+		struct dm_target *ti = dm_table_get_target(t, i);
+
+		if (!dm_target_passes_integrity(ti->type))
+			t->integrity_supported = false;
+	}
+
 	for (unsigned int i = 0; i < t->num_targets; i++) {
 		struct dm_target *ti = dm_table_get_target(t, i);
 
@@ -1738,6 +1651,18 @@ combine_limits:
 			       dm_device_name(t->md),
 			       (unsigned long long) ti->begin,
 			       (unsigned long long) ti->len);
+
+		if (t->integrity_supported ||
+		    dm_target_has_integrity(ti->type)) {
+			if (!queue_limits_stack_integrity(limits, &ti_limits)) {
+				DMWARN("%s: adding target device (start sect %llu len %llu) "
+				       "disabled integrity support due to incompatibility",
+				       dm_device_name(t->md),
+				       (unsigned long long) ti->begin,
+				       (unsigned long long) ti->len);
+				t->integrity_supported = false;
+			}
+		}
 	}
 
 	/*
@@ -1761,36 +1686,6 @@ combine_limits:
 	return validate_hardware_logical_block_alignment(t, limits);
 }
 
-/*
- * Verify that all devices have an integrity profile that matches the
- * DM device's registered integrity profile.  If the profiles don't
- * match then unregister the DM device's integrity profile.
- */
-static void dm_table_verify_integrity(struct dm_table *t)
-{
-	struct gendisk *template_disk = NULL;
-
-	if (t->integrity_added)
-		return;
-
-	if (t->integrity_supported) {
-		/*
-		 * Verify that the original integrity profile
-		 * matches all the devices in this table.
-		 */
-		template_disk = dm_table_get_integrity_disk(t);
-		if (template_disk &&
-		    blk_integrity_compare(dm_disk(t->md), template_disk) >= 0)
-			return;
-	}
-
-	if (integrity_profile_exists(dm_disk(t->md))) {
-		DMWARN("%s: unable to establish an integrity profile",
-		       dm_device_name(t->md));
-		blk_integrity_unregister(dm_disk(t->md));
-	}
-}
-
 static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
 				sector_t start, sector_t len, void *data)
 {
@@ -2004,8 +1899,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
 
-	dm_table_verify_integrity(t);
-
 	/*
 	 * Some devices don't use blk_integrity but still want stable pages
 	 * because they do their own checksumming.
diff --git a/drivers/md/md.c b/drivers/md/md.c
index c0426a6d2fd1..cf510a68705f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2420,36 +2420,10 @@ static LIST_HEAD(pending_raid_disks);
  */
 int md_integrity_register(struct mddev *mddev)
 {
-	struct md_rdev *rdev, *reference = NULL;
-
 	if (list_empty(&mddev->disks))
 		return 0; /* nothing to do */
-	if (mddev_is_dm(mddev) || blk_get_integrity(mddev->gendisk))
-		return 0; /* shouldn't register, or already is */
-	rdev_for_each(rdev, mddev) {
-		/* skip spares and non-functional disks */
-		if (test_bit(Faulty, &rdev->flags))
-			continue;
-		if (rdev->raid_disk < 0)
-			continue;
-		if (!reference) {
-			/* Use the first rdev as the reference */
-			reference = rdev;
-			continue;
-		}
-		/* does this rdev's profile match the reference profile? */
-		if (blk_integrity_compare(reference->bdev->bd_disk,
-				rdev->bdev->bd_disk) < 0)
-			return -EINVAL;
-	}
-	if (!reference || !bdev_get_integrity(reference->bdev))
-		return 0;
-	/*
-	 * All component devices are integrity capable and have matching
-	 * profiles, register the common profile for the md device.
-	 */
-	blk_integrity_register(mddev->gendisk,
-			       bdev_get_integrity(reference->bdev));
+	if (mddev_is_dm(mddev) || !blk_get_integrity(mddev->gendisk))
+		return 0; /* shouldn't register */
 
 	pr_debug("md: data integrity enabled on %s\n", mdname(mddev));
 	if (bioset_integrity_create(&mddev->bio_set, BIO_POOL_SIZE) ||
@@ -2469,32 +2443,6 @@ int md_integrity_register(struct mddev *mddev)
 }
 EXPORT_SYMBOL(md_integrity_register);
 
-/*
- * Attempt to add an rdev, but only if it is consistent with the current
- * integrity profile
- */
-int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
-{
-	struct blk_integrity *bi_mddev;
-
-	if (mddev_is_dm(mddev))
-		return 0;
-
-	bi_mddev = blk_get_integrity(mddev->gendisk);
-
-	if (!bi_mddev) /* nothing to do */
-		return 0;
-
-	if (blk_integrity_compare(mddev->gendisk, rdev->bdev->bd_disk) != 0) {
-		pr_err("%s: incompatible integrity profile for %pg\n",
-		       mdname(mddev), rdev->bdev);
-		return -ENXIO;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(md_integrity_add_rdev);
-
 static bool rdev_read_only(struct md_rdev *rdev)
 {
 	return bdev_read_only(rdev->bdev) ||
@@ -5840,14 +5788,20 @@ static const struct kobj_type md_ktype = {
 int mdp_major = 0;
 
 /* stack the limit for all rdevs into lim */
-void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim)
+int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
+		unsigned int flags)
 {
 	struct md_rdev *rdev;
 
 	rdev_for_each(rdev, mddev) {
 		queue_limits_stack_bdev(lim, rdev->bdev, rdev->data_offset,
 					mddev->gendisk->disk_name);
+		if ((flags & MDDEV_STACK_INTEGRITY) &&
+		    !queue_limits_stack_integrity_bdev(lim, rdev->bdev))
+			return -EINVAL;
 	}
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(mddev_stack_rdev_limits);
 
@@ -5862,6 +5816,14 @@ int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev)
 	lim = queue_limits_start_update(mddev->gendisk->queue);
 	queue_limits_stack_bdev(&lim, rdev->bdev, rdev->data_offset,
 				mddev->gendisk->disk_name);
+
+	if (!queue_limits_stack_integrity_bdev(&lim, rdev->bdev)) {
+		pr_err("%s: incompatible integrity profile for %pg\n",
+		       mdname(mddev), rdev->bdev);
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return -ENXIO;
+	}
+
 	return queue_limits_commit_update(mddev->gendisk->queue, &lim);
 }
 EXPORT_SYMBOL_GPL(mddev_stack_new_rdev);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2dc52edec3fe..c4d7ebf9587d 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -889,7 +889,6 @@ extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
 extern int md_check_no_bitmap(struct mddev *mddev);
 extern int md_integrity_register(struct mddev *mddev);
-extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 
 extern int mddev_init(struct mddev *mddev);
@@ -988,7 +987,9 @@ void md_autostart_arrays(int part);
 int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info);
 int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info);
 int do_md_run(struct mddev *mddev);
-void mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim);
+#define MDDEV_STACK_INTEGRITY	(1u << 0)
+int mddev_stack_rdev_limits(struct mddev *mddev, struct queue_limits *lim,
+		unsigned int flags);
 int mddev_stack_new_rdev(struct mddev *mddev, struct md_rdev *rdev);
 void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
 
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 81c01347cd24..62634e2a33bd 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -377,13 +377,18 @@ static void raid0_free(struct mddev *mddev, void *priv)
 static int raid0_set_limits(struct mddev *mddev)
 {
 	struct queue_limits lim;
+	int err;
 
 	blk_set_stacking_limits(&lim);
 	lim.max_hw_sectors = mddev->chunk_sectors;
 	lim.max_write_zeroes_sectors = mddev->chunk_sectors;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * mddev->raid_disks;
-	mddev_stack_rdev_limits(mddev, &lim);
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err) {
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return err;
+	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 2bbfb4e682b2..1a0eba65b8a9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1906,9 +1906,6 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (mddev->recovery_disabled == conf->recovery_disabled)
 		return -EBUSY;
 
-	if (md_integrity_add_rdev(rdev, mddev))
-		return -ENXIO;
-
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
@@ -3195,10 +3192,15 @@ static struct r1conf *setup_conf(struct mddev *mddev)
 static int raid1_set_limits(struct mddev *mddev)
 {
 	struct queue_limits lim;
+	int err;
 
 	blk_set_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
-	mddev_stack_rdev_limits(mddev, &lim);
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err) {
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return err;
+	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 4e804602d1e5..3334aa803c83 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2082,9 +2082,6 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->saved_raid_disk < 0 && !_enough(conf, 1, -1))
 		return -EINVAL;
 
-	if (md_integrity_add_rdev(rdev, mddev))
-		return -ENXIO;
-
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
@@ -3975,12 +3972,17 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 {
 	struct r10conf *conf = mddev->private;
 	struct queue_limits lim;
+	int err;
 
 	blk_set_stacking_limits(&lim);
 	lim.max_write_zeroes_sectors = 0;
 	lim.io_min = mddev->chunk_sectors << 9;
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
-	mddev_stack_rdev_limits(mddev, &lim);
+	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
+	if (err) {
+		queue_limits_cancel_update(mddev->gendisk->queue);
+		return err;
+	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 547fd15115cd..c62c4122942a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7712,7 +7712,7 @@ static int raid5_set_limits(struct mddev *mddev)
 	lim.raid_partial_stripes_expensive = 1;
 	lim.discard_granularity = stripe;
 	lim.max_write_zeroes_sectors = 0;
-	mddev_stack_rdev_limits(mddev, &lim);
+	mddev_stack_rdev_limits(mddev, &lim, 0);
 	rdev_for_each(rdev, mddev)
 		queue_limits_stack_bdev(&lim, rdev->bdev, rdev->new_data_offset,
 				mddev->gendisk->disk_name);