Merge branch 'for-4.4/integrity' of git://git.kernel.dk/linux-block

Pull block integrity updates from Jens Axboe:
 ""This is the joint work of Dan and Martin, cleaning up and improving
  the support for block data integrity"

* 'for-4.4/integrity' of git://git.kernel.dk/linux-block:
  block, libnvdimm, nvme: provide a built-in blk_integrity nop profile
  block: blk_flush_integrity() for bio-based drivers
  block: move blk_integrity to request_queue
  block: generic request_queue reference counting
  nvme: suspend i/o during runtime blk_integrity_unregister
  md: suspend i/o during runtime blk_integrity_unregister
  md, dm, scsi, nvme, libnvdimm: drop blk_integrity_unregister() at shutdown
  block: Inline blk_integrity in struct gendisk
  block: Export integrity data interval size in sysfs
  block: Reduce the size of struct blk_integrity
  block: Consolidate static integrity profile properties
  block: Move integrity kobject to struct gendisk

Documentation/ABI/testing/sysfs-block

@@ -60,6 +60,13 @@ Description:
 		Indicates whether a storage device is capable of storing
 		integrity metadata. Set if the device is T10 PI-capable.
 
+What:		/sys/block/<disk>/integrity/protection_interval_bytes
+Date:		July 2015
+Contact:	Martin K. Petersen <martin.petersen@oracle.com>
+Description:
+		Describes the number of data bytes which are protected
+		by one integrity tuple. Typically the device's logical
+		block size.
 
 What:		/sys/block/<disk>/integrity/write_generate
 Date:		June 2008

block/bio-integrity.c

@@ -32,6 +32,11 @@
 static struct kmem_cache *bip_slab;
 static struct workqueue_struct *kintegrityd_wq;
 
+void blk_flush_integrity(void)
+{
+	flush_workqueue(kintegrityd_wq);
+}
+
 /**
  * bio_integrity_alloc - Allocate integrity payload and attach it to bio
  * @bio:	bio to attach integrity metadata to
@@ -177,11 +182,11 @@ bool bio_integrity_enabled(struct bio *bio)
 	if (bi == NULL)
 		return false;
 
-	if (bio_data_dir(bio) == READ && bi->verify_fn != NULL &&
+	if (bio_data_dir(bio) == READ && bi->profile->verify_fn != NULL &&
 	    (bi->flags & BLK_INTEGRITY_VERIFY))
 		return true;
 
-	if (bio_data_dir(bio) == WRITE && bi->generate_fn != NULL &&
+	if (bio_data_dir(bio) == WRITE && bi->profile->generate_fn != NULL &&
 	    (bi->flags & BLK_INTEGRITY_GENERATE))
 		return true;
 
@@ -202,7 +207,7 @@ EXPORT_SYMBOL(bio_integrity_enabled);
 static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 						   unsigned int sectors)
 {
-	return sectors >> (ilog2(bi->interval) - 9);
+	return sectors >> (bi->interval_exp - 9);
 }
 
 static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
@@ -229,7 +234,7 @@ static int bio_integrity_process(struct bio *bio,
 		bip->bip_vec->bv_offset;
 
 	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	iter.interval = bi->interval;
+	iter.interval = 1 << bi->interval_exp;
 	iter.seed = bip_get_seed(bip);
 	iter.prot_buf = prot_buf;
 
@@ -340,7 +345,7 @@ int bio_integrity_prep(struct bio *bio)
 
 	/* Auto-generate integrity metadata if this is a write */
 	if (bio_data_dir(bio) == WRITE)
-		bio_integrity_process(bio, bi->generate_fn);
+		bio_integrity_process(bio, bi->profile->generate_fn);
 
 	return 0;
 }
@@ -361,7 +366,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio *bio = bip->bip_bio;
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
-	bio->bi_error = bio_integrity_process(bio, bi->verify_fn);
+	bio->bi_error = bio_integrity_process(bio, bi->profile->verify_fn);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;

block/blk-core.c

@@ -554,22 +554,23 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
 	 * prevent that q->request_fn() gets invoked after draining finished.
 	 */
-	if (q->mq_ops) {
-		blk_mq_freeze_queue(q);
-		spin_lock_irq(lock);
-	} else {
+	blk_freeze_queue(q);
 	spin_lock_irq(lock);
+	if (!q->mq_ops)
 		__blk_drain_queue(q, true);
-	}
 	queue_flag_set(QUEUE_FLAG_DEAD, q);
 	spin_unlock_irq(lock);
 
+	/* for synchronous bio-based driver finish in-flight integrity i/o */
+	blk_flush_integrity();
+
 	/* @q won't process any more request, flush async actions */
 	del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
 	blk_sync_queue(q);
 
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
+	percpu_ref_exit(&q->q_usage_counter);
 
 	spin_lock_irq(lock);
 	if (q->queue_lock != &q->__queue_lock)
@@ -629,6 +630,40 @@ struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(blk_alloc_queue);
 
+int blk_queue_enter(struct request_queue *q, gfp_t gfp)
+{
+	while (true) {
+		int ret;
+
+		if (percpu_ref_tryget_live(&q->q_usage_counter))
+			return 0;
+
+		if (!(gfp & __GFP_WAIT))
+			return -EBUSY;
+
+		ret = wait_event_interruptible(q->mq_freeze_wq,
+				!atomic_read(&q->mq_freeze_depth) ||
+				blk_queue_dying(q));
+		if (blk_queue_dying(q))
+			return -ENODEV;
+		if (ret)
+			return ret;
+	}
+}
+
+void blk_queue_exit(struct request_queue *q)
+{
+	percpu_ref_put(&q->q_usage_counter);
+}
+
+static void blk_queue_usage_counter_release(struct percpu_ref *ref)
+{
+	struct request_queue *q =
+		container_of(ref, struct request_queue, q_usage_counter);
+
+	wake_up_all(&q->mq_freeze_wq);
+}
+
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 {
 	struct request_queue *q;
@@ -690,11 +725,22 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 
 	init_waitqueue_head(&q->mq_freeze_wq);
 
-	if (blkcg_init_queue(q))
+	/*
+	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
+	 * See blk_register_queue() for details.
+	 */
+	if (percpu_ref_init(&q->q_usage_counter,
+				blk_queue_usage_counter_release,
+				PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
 		goto fail_bdi;
 
+	if (blkcg_init_queue(q))
+		goto fail_ref;
+
 	return q;
 
+fail_ref:
+	percpu_ref_exit(&q->q_usage_counter);
 fail_bdi:
 	bdi_destroy(&q->backing_dev_info);
 fail_split:
@@ -1992,9 +2038,19 @@ void generic_make_request(struct bio *bio)
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
+		if (likely(blk_queue_enter(q, __GFP_WAIT) == 0)) {
+
 			q->make_request_fn(q, bio);
 
+			blk_queue_exit(q);
+
 			bio = bio_list_pop(current->bio_list);
+		} else {
+			struct bio *bio_next = bio_list_pop(current->bio_list);
+
+			bio_io_error(bio);
+			bio = bio_next;
+		}
 	} while (bio);
 	current->bio_list = NULL; /* deactivate */
 }

block/blk-integrity.c

@@ -30,10 +30,6 @@
 
 #include "blk.h"
 
-static struct kmem_cache *integrity_cachep;
-
-static const char *bi_unsupported_name = "unsupported";
-
 /**
  * blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
  * @q:		request queue
@@ -146,40 +142,40 @@ EXPORT_SYMBOL(blk_rq_map_integrity_sg);
  */
 int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
 {
-	struct blk_integrity *b1 = gd1->integrity;
-	struct blk_integrity *b2 = gd2->integrity;
+	struct blk_integrity *b1 = &gd1->queue->integrity;
+	struct blk_integrity *b2 = &gd2->queue->integrity;
 
-	if (!b1 && !b2)
+	if (!b1->profile && !b2->profile)
 		return 0;
 
-	if (!b1 || !b2)
+	if (!b1->profile || !b2->profile)
 		return -1;
 
-	if (b1->interval != b2->interval) {
+	if (b1->interval_exp != b2->interval_exp) {
 		pr_err("%s: %s/%s protection interval %u != %u\n",
 		       __func__, gd1->disk_name, gd2->disk_name,
-		       b1->interval, b2->interval);
+		       1 << b1->interval_exp, 1 << b2->interval_exp);
 		return -1;
 	}
 
 	if (b1->tuple_size != b2->tuple_size) {
-		printk(KERN_ERR "%s: %s/%s tuple sz %u != %u\n", __func__,
+		pr_err("%s: %s/%s tuple sz %u != %u\n", __func__,
 		       gd1->disk_name, gd2->disk_name,
 		       b1->tuple_size, b2->tuple_size);
 		return -1;
 	}
 
 	if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) {
-		printk(KERN_ERR "%s: %s/%s tag sz %u != %u\n", __func__,
+		pr_err("%s: %s/%s tag sz %u != %u\n", __func__,
 		       gd1->disk_name, gd2->disk_name,
 		       b1->tag_size, b2->tag_size);
 		return -1;
 	}
 
-	if (strcmp(b1->name, b2->name)) {
-		printk(KERN_ERR "%s: %s/%s type %s != %s\n", __func__,
+	if (b1->profile != b2->profile) {
+		pr_err("%s: %s/%s type %s != %s\n", __func__,
 		       gd1->disk_name, gd2->disk_name,
-		       b1->name, b2->name);
+		       b1->profile->name, b2->profile->name);
 		return -1;
 	}
 
@@ -249,8 +245,8 @@ struct integrity_sysfs_entry {
 static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr,
 				   char *page)
 {
-	struct blk_integrity *bi =
-		container_of(kobj, struct blk_integrity, kobj);
+	struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
+	struct blk_integrity *bi = &disk->queue->integrity;
 	struct integrity_sysfs_entry *entry =
 		container_of(attr, struct integrity_sysfs_entry, attr);
 
@@ -261,8 +257,8 @@ static ssize_t integrity_attr_store(struct kobject *kobj,
 				    struct attribute *attr, const char *page,
 				    size_t count)
 {
-	struct blk_integrity *bi =
-		container_of(kobj, struct blk_integrity, kobj);
+	struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
+	struct blk_integrity *bi = &disk->queue->integrity;
 	struct integrity_sysfs_entry *entry =
 		container_of(attr, struct integrity_sysfs_entry, attr);
 	ssize_t ret = 0;
@@ -275,18 +271,21 @@ static ssize_t integrity_attr_store(struct kobject *kobj,
 
 static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
 {
-	if (bi != NULL && bi->name != NULL)
-		return sprintf(page, "%s\n", bi->name);
+	if (bi->profile && bi->profile->name)
+		return sprintf(page, "%s\n", bi->profile->name);
 	else
 		return sprintf(page, "none\n");
 }
 
 static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
 {
-	if (bi != NULL)
 	return sprintf(page, "%u\n", bi->tag_size);
-	else
-		return sprintf(page, "0\n");
+}
+
+static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page)
+{
+	return sprintf(page, "%u\n",
+		       bi->interval_exp ? 1 << bi->interval_exp : 0);
 }
 
 static ssize_t integrity_verify_store(struct blk_integrity *bi,
@@ -343,6 +342,11 @@ static struct integrity_sysfs_entry integrity_tag_size_entry = {
 	.show = integrity_tag_size_show,
 };
 
+static struct integrity_sysfs_entry integrity_interval_entry = {
+	.attr = { .name = "protection_interval_bytes", .mode = S_IRUGO },
+	.show = integrity_interval_show,
+};
+
 static struct integrity_sysfs_entry integrity_verify_entry = {
 	.attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
 	.show = integrity_verify_show,
@@ -363,6 +367,7 @@ static struct integrity_sysfs_entry integrity_device_entry = {
 static struct attribute *integrity_attrs[] = {
 	&integrity_format_entry.attr,
 	&integrity_tag_size_entry.attr,
+	&integrity_interval_entry.attr,
 	&integrity_verify_entry.attr,
 	&integrity_generate_entry.attr,
 	&integrity_device_entry.attr,
@@ -374,114 +379,89 @@ static const struct sysfs_ops integrity_ops = {
 	.store	= &integrity_attr_store,
 };
 
-static int __init blk_dev_integrity_init(void)
-{
-	integrity_cachep = kmem_cache_create("blkdev_integrity",
-					     sizeof(struct blk_integrity),
-					     0, SLAB_PANIC, NULL);
-	return 0;
-}
-subsys_initcall(blk_dev_integrity_init);
-
-static void blk_integrity_release(struct kobject *kobj)
-{
-	struct blk_integrity *bi =
-		container_of(kobj, struct blk_integrity, kobj);
-
-	kmem_cache_free(integrity_cachep, bi);
-}
-
 static struct kobj_type integrity_ktype = {
 	.default_attrs	= integrity_attrs,
 	.sysfs_ops	= &integrity_ops,
-	.release	= blk_integrity_release,
 };
 
-bool blk_integrity_is_initialized(struct gendisk *disk)
+static int blk_integrity_nop_fn(struct blk_integrity_iter *iter)
 {
-	struct blk_integrity *bi = blk_get_integrity(disk);
-
-	return (bi && bi->name && strcmp(bi->name, bi_unsupported_name) != 0);
+	return 0;
 }
-EXPORT_SYMBOL(blk_integrity_is_initialized);
+
+static struct blk_integrity_profile nop_profile = {
+	.name = "nop",
+	.generate_fn = blk_integrity_nop_fn,
+	.verify_fn = blk_integrity_nop_fn,
+};
 
 /**
  * blk_integrity_register - Register a gendisk as being integrity-capable
  * @disk:	struct gendisk pointer to make integrity-aware
- * @template:	optional integrity profile to register
+ * @template:	block integrity profile to register
  *
- * Description: When a device needs to advertise itself as being able
- * to send/receive integrity metadata it must use this function to
- * register the capability with the block layer.  The template is a
- * blk_integrity struct with values appropriate for the underlying
- * hardware.  If template is NULL the new profile is allocated but
- * not filled out. See Documentation/block/data-integrity.txt.
+ * Description: When a device needs to advertise itself as being able to
+ * send/receive integrity metadata it must use this function to register
+ * the capability with the block layer. The template is a blk_integrity
+ * struct with values appropriate for the underlying hardware. See
+ * Documentation/block/data-integrity.txt.
  */
-int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
+void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
 {
-	struct blk_integrity *bi;
-
-	BUG_ON(disk == NULL);
+	struct blk_integrity *bi = &disk->queue->integrity;
 
-	if (disk->integrity == NULL) {
-		bi = kmem_cache_alloc(integrity_cachep,
-				      GFP_KERNEL | __GFP_ZERO);
-		if (!bi)
-			return -1;
-
-		if (kobject_init_and_add(&bi->kobj, &integrity_ktype,
-					 &disk_to_dev(disk)->kobj,
-					 "%s", "integrity")) {
-			kmem_cache_free(integrity_cachep, bi);
-			return -1;
-		}
-
-		kobject_uevent(&bi->kobj, KOBJ_ADD);
-
-		bi->flags |= BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE;
-		bi->interval = queue_logical_block_size(disk->queue);
-		disk->integrity = bi;
-	} else
-		bi = disk->integrity;
-
-	/* Use the provided profile as template */
-	if (template != NULL) {
-		bi->name = template->name;
-		bi->generate_fn = template->generate_fn;
-		bi->verify_fn = template->verify_fn;
+	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
+		template->flags;
+	bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
+	bi->profile = template->profile ? template->profile : &nop_profile;
 	bi->tuple_size = template->tuple_size;
 	bi->tag_size = template->tag_size;
-		bi->flags |= template->flags;
-	} else
-		bi->name = bi_unsupported_name;
-
-	disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
 
-	return 0;
+	blk_integrity_revalidate(disk);
 }
 EXPORT_SYMBOL(blk_integrity_register);
 
 /**
- * blk_integrity_unregister - Remove block integrity profile
- * @disk:	disk whose integrity profile to deallocate
+ * blk_integrity_unregister - Unregister block integrity profile
+ * @disk:	disk whose integrity profile to unregister
  *
- * Description: This function frees all memory used by the block
- * integrity profile.  To be called at device teardown.
+ * Description: This function unregisters the integrity capability from
+ * a block device.
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
-	struct blk_integrity *bi;
+	blk_integrity_revalidate(disk);
+	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
+}
+EXPORT_SYMBOL(blk_integrity_unregister);
 
-	if (!disk || !disk->integrity)
+void blk_integrity_revalidate(struct gendisk *disk)
+{
+	struct blk_integrity *bi = &disk->queue->integrity;
+
+	if (!(disk->flags & GENHD_FL_UP))
 		return;
 
-	disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES;
+	if (bi->profile)
+		disk->queue->backing_dev_info.capabilities |=
+			BDI_CAP_STABLE_WRITES;
+	else
+		disk->queue->backing_dev_info.capabilities &=
+			~BDI_CAP_STABLE_WRITES;
+}
+
+void blk_integrity_add(struct gendisk *disk)
+{
+	if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
+				 &disk_to_dev(disk)->kobj, "%s", "integrity"))
+		return;
 
-	bi = disk->integrity;
+	kobject_uevent(&disk->integrity_kobj, KOBJ_ADD);
+}
 
-	kobject_uevent(&bi->kobj, KOBJ_REMOVE);
-	kobject_del(&bi->kobj);
-	kobject_put(&bi->kobj);
-	disk->integrity = NULL;
+void blk_integrity_del(struct gendisk *disk)
+{
+	kobject_uevent(&disk->integrity_kobj, KOBJ_REMOVE);
+	kobject_del(&disk->integrity_kobj);
+	kobject_put(&disk->integrity_kobj);
 }
-EXPORT_SYMBOL(blk_integrity_unregister);

block/blk-mq-sysfs.c

@@ -413,12 +413,6 @@ static void blk_mq_sysfs_init(struct request_queue *q)
 		kobject_init(&ctx->kobj, &blk_mq_ctx_ktype);
 }
 
-/* see blk_register_queue() */
-void blk_mq_finish_init(struct request_queue *q)
-{
-	percpu_ref_switch_to_percpu(&q->mq_usage_counter);
-}
-
 int blk_mq_register_disk(struct gendisk *disk)
 {
 	struct device *dev = disk_to_dev(disk);

block/blk-mq.c

@@ -78,47 +78,13 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 	clear_bit(CTX_TO_BIT(hctx, ctx), &bm->word);
 }
 
-static int blk_mq_queue_enter(struct request_queue *q, gfp_t gfp)
-{
-	while (true) {
-		int ret;
-
-		if (percpu_ref_tryget_live(&q->mq_usage_counter))
-			return 0;
-
-		if (!(gfp & __GFP_WAIT))
-			return -EBUSY;
-
-		ret = wait_event_interruptible(q->mq_freeze_wq,
-				!atomic_read(&q->mq_freeze_depth) ||
-				blk_queue_dying(q));
-		if (blk_queue_dying(q))
-			return -ENODEV;
-		if (ret)
-			return ret;
-	}
-}
-
-static void blk_mq_queue_exit(struct request_queue *q)
-{
-	percpu_ref_put(&q->mq_usage_counter);
-}
-
-static void blk_mq_usage_counter_release(struct percpu_ref *ref)
-{
-	struct request_queue *q =
-		container_of(ref, struct request_queue, mq_usage_counter);
-
-	wake_up_all(&q->mq_freeze_wq);
-}
-
 void blk_mq_freeze_queue_start(struct request_queue *q)
 {
 	int freeze_depth;
 
 	freeze_depth = atomic_inc_return(&q->mq_freeze_depth);
 	if (freeze_depth == 1) {
-		percpu_ref_kill(&q->mq_usage_counter);
+		percpu_ref_kill(&q->q_usage_counter);
 		blk_mq_run_hw_queues(q, false);
 	}
 }
@@ -126,18 +92,34 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
 
 static void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
-	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->mq_usage_counter));
+	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
 }
 
 /*
  * Guarantee no request is in use, so we can change any data structure of
  * the queue afterward.
  */
-void blk_mq_freeze_queue(struct request_queue *q)
+void blk_freeze_queue(struct request_queue *q)
 {
+	/*
+	 * In the !blk_mq case we are only calling this to kill the
+	 * q_usage_counter, otherwise this increases the freeze depth
+	 * and waits for it to return to zero.  For this reason there is
+	 * no blk_unfreeze_queue(), and blk_freeze_queue() is not
+	 * exported to drivers as the only user for unfreeze is blk_mq.
+	 */
 	blk_mq_freeze_queue_start(q);
 	blk_mq_freeze_queue_wait(q);
 }
+
+void blk_mq_freeze_queue(struct request_queue *q)
+{
+	/*
+	 * ...just an alias to keep freeze and unfreeze actions balanced
+	 * in the blk_mq_* namespace
+	 */
+	blk_freeze_queue(q);
+}
 EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
 
 void blk_mq_unfreeze_queue(struct request_queue *q)
@@ -147,7 +129,7 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
 	freeze_depth = atomic_dec_return(&q->mq_freeze_depth);
 	WARN_ON_ONCE(freeze_depth < 0);
 	if (!freeze_depth) {
-		percpu_ref_reinit(&q->mq_usage_counter);
+		percpu_ref_reinit(&q->q_usage_counter);
 		wake_up_all(&q->mq_freeze_wq);
 	}
 }
@@ -256,7 +238,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 	struct blk_mq_alloc_data alloc_data;
 	int ret;
 
-	ret = blk_mq_queue_enter(q, gfp);
+	ret = blk_queue_enter(q, gfp);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -279,7 +261,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw, gfp_t gfp,
 	}
 	blk_mq_put_ctx(ctx);
 	if (!rq) {
-		blk_mq_queue_exit(q);
+		blk_queue_exit(q);
 		return ERR_PTR(-EWOULDBLOCK);
 	}
 	return rq;
@@ -298,7 +280,7 @@ static void __blk_mq_free_request(struct blk_mq_hw_ctx *hctx,
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 	blk_mq_put_tag(hctx, tag, &ctx->last_tag);
-	blk_mq_queue_exit(q);
+	blk_queue_exit(q);
 }
 
 void blk_mq_free_hctx_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
@@ -1185,11 +1167,7 @@ static struct request *blk_mq_map_request(struct request_queue *q,
 	int rw = bio_data_dir(bio);
 	struct blk_mq_alloc_data alloc_data;
 
-	if (unlikely(blk_mq_queue_enter(q, GFP_KERNEL))) {
-		bio_io_error(bio);
-		return NULL;
-	}
-
+	blk_queue_enter_live(q);
 	ctx = blk_mq_get_ctx(q);
 	hctx = q->mq_ops->map_queue(q, ctx->cpu);
 
@@ -2024,14 +2002,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		hctxs[i]->queue_num = i;
 	}
 
-	/*
-	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
-	 * See blk_register_queue() for details.
-	 */
-	if (percpu_ref_init(&q->mq_usage_counter, blk_mq_usage_counter_release,
-			    PERCPU_REF_INIT_ATOMIC, GFP_KERNEL))
-		goto err_hctxs;
-
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
 	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
@@ -2112,8 +2082,6 @@ void blk_mq_free_queue(struct request_queue *q)
 
 	blk_mq_exit_hw_queues(q, set, set->nr_hw_queues);
 	blk_mq_free_hw_queues(q, set);
-
-	percpu_ref_exit(&q->mq_usage_counter);
 }
 
 /* Basically redo blk_mq_init_queue with queue frozen */

block/blk-sysfs.c

@@ -600,9 +600,8 @@ int blk_register_queue(struct gendisk *disk)
 	 */
 	if (!blk_queue_init_done(q)) {
 		queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q);
+		percpu_ref_switch_to_percpu(&q->q_usage_counter);
 		blk_queue_bypass_end(q);
-		if (q->mq_ops)
-			blk_mq_finish_init(q);
 	}
 
 	ret = blk_trace_init_sysfs(dev);

block/blk.h

@@ -72,6 +72,28 @@ void blk_dequeue_request(struct request *rq);
 void __blk_queue_free_tags(struct request_queue *q);
 bool __blk_end_bidi_request(struct request *rq, int error,
 			    unsigned int nr_bytes, unsigned int bidi_bytes);
+int blk_queue_enter(struct request_queue *q, gfp_t gfp);
+void blk_queue_exit(struct request_queue *q);
+void blk_freeze_queue(struct request_queue *q);
+
+static inline void blk_queue_enter_live(struct request_queue *q)
+{
+	/*
+	 * Given that running in generic_make_request() context
+	 * guarantees that a live reference against q_usage_counter has
+	 * been established, further references under that same context
+	 * need not check that the queue has been frozen (marked dead).
+	 */
+	percpu_ref_get(&q->q_usage_counter);
+}
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+void blk_flush_integrity(void);
+#else
+static inline void blk_flush_integrity(void)
+{
+}
+#endif
 
 void blk_rq_timed_out_timer(unsigned long data);
 unsigned long blk_rq_timeout(unsigned long timeout);

block/genhd.c

@@ -630,6 +630,7 @@ void add_disk(struct gendisk *disk)
 	WARN_ON(retval);
 
 	disk_add_events(disk);
+	blk_integrity_add(disk);
 }
 EXPORT_SYMBOL(add_disk);
 
@@ -638,6 +639,7 @@ void del_gendisk(struct gendisk *disk)
 	struct disk_part_iter piter;
 	struct hd_struct *part;
 
+	blk_integrity_del(disk);
 	disk_del_events(disk);
 
 	/* invalidate stuff */

block/partition-generic.c

@@ -428,6 +428,7 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
+	blk_integrity_revalidate(disk);
 	check_disk_size_change(disk, bdev);
 	bdev->bd_invalidated = 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))

block/t10-pi.c

@@ -160,38 +160,30 @@ static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 	return t10_pi_verify(iter, t10_pi_ip_fn, 3);
 }
 
-struct blk_integrity t10_pi_type1_crc = {
+struct blk_integrity_profile t10_pi_type1_crc = {
 	.name			= "T10-DIF-TYPE1-CRC",
 	.generate_fn		= t10_pi_type1_generate_crc,
 	.verify_fn		= t10_pi_type1_verify_crc,
-	.tuple_size		= sizeof(struct t10_pi_tuple),
-	.tag_size		= 0,
 };
 EXPORT_SYMBOL(t10_pi_type1_crc);
 
-struct blk_integrity t10_pi_type1_ip = {
+struct blk_integrity_profile t10_pi_type1_ip = {
 	.name			= "T10-DIF-TYPE1-IP",
 	.generate_fn		= t10_pi_type1_generate_ip,
 	.verify_fn		= t10_pi_type1_verify_ip,
-	.tuple_size		= sizeof(struct t10_pi_tuple),
-	.tag_size		= 0,
 };
 EXPORT_SYMBOL(t10_pi_type1_ip);
 
-struct blk_integrity t10_pi_type3_crc = {
+struct blk_integrity_profile t10_pi_type3_crc = {
 	.name			= "T10-DIF-TYPE3-CRC",
 	.generate_fn		= t10_pi_type3_generate_crc,
 	.verify_fn		= t10_pi_type3_verify_crc,
-	.tuple_size		= sizeof(struct t10_pi_tuple),
-	.tag_size		= 0,
 };
 EXPORT_SYMBOL(t10_pi_type3_crc);
 
-struct blk_integrity t10_pi_type3_ip = {
+struct blk_integrity_profile t10_pi_type3_ip = {
 	.name			= "T10-DIF-TYPE3-IP",
 	.generate_fn		= t10_pi_type3_generate_ip,
 	.verify_fn		= t10_pi_type3_verify_ip,
-	.tuple_size		= sizeof(struct t10_pi_tuple),
-	.tag_size		= 0,
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);

drivers/md/dm-table.c

@@ -1014,15 +1014,16 @@ 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.
- * If %match_all is true, all devices' profiles must match.
- * If %match_all is false, all devices must at least have an
- * allocated integrity profile; but uninitialized is ok.
  * Returns NULL if integrity support was inconsistent or unavailable.
  */
-static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
-						    bool match_all)
+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;
@@ -1030,10 +1031,8 @@ static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
 
 	list_for_each_entry(dd, devices, list) {
 		template_disk = dd->dm_dev->bdev->bd_disk;
-		if (!blk_get_integrity(template_disk))
+		if (!integrity_profile_exists(template_disk))
 			goto no_integrity;
-		if (!match_all && !blk_integrity_is_initialized(template_disk))
-			continue; /* skip uninitialized profiles */
 		else if (prev_disk &&
 			 blk_integrity_compare(prev_disk, template_disk) < 0)
 			goto no_integrity;
@@ -1052,34 +1051,40 @@ static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
 }
 
 /*
- * 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
+ * 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).
- * Stacked DM devices force a 2 stage integrity profile validation:
- * 1 - during load, validate all initialized integrity profiles match
- * 2 - during resume, validate all integrity profiles match
+ * 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_prealloc_integrity(struct dm_table *t, struct mapped_device *md)
+static int dm_table_register_integrity(struct dm_table *t)
 {
+	struct mapped_device *md = t->md;
 	struct gendisk *template_disk = NULL;
 
-	template_disk = dm_table_get_integrity_disk(t, false);
+	template_disk = dm_table_get_integrity_disk(t);
 	if (!template_disk)
 		return 0;
 
-	if (!blk_integrity_is_initialized(dm_disk(md))) {
+	if (!integrity_profile_exists(dm_disk(md))) {
 		t->integrity_supported = 1;
-		return blk_integrity_register(dm_disk(md), NULL);
+		/*
+		 * 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 initalized integrity
+	 * If DM device already has an initialized integrity
 	 * profile the new profile should not conflict.
 	 */
-	if (blk_integrity_is_initialized(template_disk) &&
-	    blk_integrity_compare(dm_disk(md), template_disk) < 0) {
+	if (blk_integrity_compare(dm_disk(md), template_disk) < 0) {
 		DMWARN("%s: conflict with existing integrity profile: "
 		       "%s profile mismatch",
 		       dm_device_name(t->md),
@@ -1087,7 +1092,7 @@ static int dm_table_prealloc_integrity(struct dm_table *t, struct mapped_device
 		return 1;
 	}
 
-	/* Preserve existing initialized integrity profile */
+	/* Preserve existing integrity profile */
 	t->integrity_supported = 1;
 	return 0;
 }
@@ -1112,7 +1117,7 @@ int dm_table_complete(struct dm_table *t)
 		return r;
 	}
 
-	r = dm_table_prealloc_integrity(t, t->md);
+	r = dm_table_register_integrity(t);
 	if (r) {
 		DMERR("could not register integrity profile.");
 		return r;
@@ -1278,29 +1283,30 @@ int dm_calculate_queue_limits(struct dm_table *table,
 }
 
 /*
- * Set the integrity profile for this device if all devices used have
- * matching profiles.  We're quite deep in the resume path but still
- * don't know if all devices (particularly DM devices this device
- * may be stacked on) have matching profiles.  Even if the profiles
- * don't match we have no way to fail (to resume) at this point.
+ * 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_set_integrity(struct dm_table *t)
+static void dm_table_verify_integrity(struct dm_table *t)
 {
 	struct gendisk *template_disk = NULL;
 
-	if (!blk_get_integrity(dm_disk(t->md)))
+	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;
+	}
 
-	template_disk = dm_table_get_integrity_disk(t, true);
-	if (template_disk)
-		blk_integrity_register(dm_disk(t->md),
-				       blk_get_integrity(template_disk));
-	else if (blk_integrity_is_initialized(dm_disk(t->md)))
-		DMWARN("%s: device no longer has a valid integrity profile",
-		       dm_device_name(t->md));
-	else
+	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,
@@ -1500,7 +1506,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	else
 		queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
 
-	dm_table_set_integrity(t);
+	dm_table_verify_integrity(t);
 
 	/*
 	 * Determine whether or not this queue's I/O timings contribute

drivers/md/dm.c

@@ -2234,8 +2234,6 @@ static void cleanup_mapped_device(struct mapped_device *md)
 		spin_lock(&_minor_lock);
 		md->disk->private_data = NULL;
 		spin_unlock(&_minor_lock);
-		if (blk_get_integrity(md->disk))
-			blk_integrity_unregister(md->disk);
 		del_gendisk(md->disk);
 		put_disk(md->disk);
 	}

drivers/md/md.c

@@ -1962,12 +1962,9 @@ int md_integrity_register(struct mddev *mddev)
 	 * All component devices are integrity capable and have matching
 	 * profiles, register the common profile for the md device.
 	 */
-	if (blk_integrity_register(mddev->gendisk,
-			bdev_get_integrity(reference->bdev)) != 0) {
-		printk(KERN_ERR "md: failed to register integrity for %s\n",
-			mdname(mddev));
-		return -EINVAL;
-	}
+	blk_integrity_register(mddev->gendisk,
+			       bdev_get_integrity(reference->bdev));
+
 	printk(KERN_NOTICE "md: data integrity enabled on %s\n", mdname(mddev));
 	if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) {
 		printk(KERN_ERR "md: failed to create integrity pool for %s\n",
@@ -1997,6 +1994,7 @@ void md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev)
 	if (bi_rdev && blk_integrity_compare(mddev->gendisk,
 					     rdev->bdev->bd_disk) >= 0)
 		return;
+	WARN_ON_ONCE(!mddev->suspended);
 	printk(KERN_NOTICE "disabling data integrity on %s\n", mdname(mddev));
 	blk_integrity_unregister(mddev->gendisk);
 }
@@ -5542,7 +5540,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 		if (mddev->hold_active == UNTIL_STOP)
 			mddev->hold_active = 0;
 	}
-	blk_integrity_unregister(disk);
 	md_new_event(mddev);
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
 	return 0;

drivers/md/multipath.c

@@ -264,7 +264,9 @@ static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			spin_unlock_irq(&conf->device_lock);
 			rcu_assign_pointer(p->rdev, rdev);
 			err = 0;
+			mddev_suspend(mddev);
 			md_integrity_add_rdev(rdev, mddev);
+			mddev_resume(mddev);
 			break;
 		}
 

drivers/md/raid1.c

@@ -1621,7 +1621,9 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 			break;
 		}
 	}
+	mddev_suspend(mddev);
 	md_integrity_add_rdev(rdev, mddev);
+	mddev_resume(mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
 	print_conf(conf);

drivers/md/raid10.c

@@ -1739,7 +1739,9 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 		rcu_assign_pointer(p->rdev, rdev);
 		break;
 	}
+	mddev_suspend(mddev);
 	md_integrity_add_rdev(rdev, mddev);
+	mddev_resume(mddev);
 	if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
 

drivers/nvdimm/btt.c

@@ -1279,7 +1279,6 @@ static int btt_blk_init(struct btt *btt)
 
 static void btt_blk_cleanup(struct btt *btt)
 {
-	blk_integrity_unregister(btt->btt_disk);
 	del_gendisk(btt->btt_disk);
 	put_disk(btt->btt_disk);
 	blk_cleanup_queue(btt->btt_queue);

drivers/nvdimm/core.c

@@ -392,29 +392,18 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus)
 EXPORT_SYMBOL_GPL(nvdimm_bus_unregister);
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-static int nd_pi_nop_generate_verify(struct blk_integrity_iter *iter)
-{
-	return 0;
-}
-
 int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
 {
-	struct blk_integrity integrity = {
-		.name = "ND-PI-NOP",
-		.generate_fn = nd_pi_nop_generate_verify,
-		.verify_fn = nd_pi_nop_generate_verify,
-		.tuple_size = meta_size,
-		.tag_size = meta_size,
-	};
-	int ret;
+	struct blk_integrity bi;
 
 	if (meta_size == 0)
 		return 0;
 
-	ret = blk_integrity_register(disk, &integrity);
-	if (ret)
-		return ret;
+	bi.profile = NULL;
+	bi.tuple_size = meta_size;
+	bi.tag_size = meta_size;
 
+	blk_integrity_register(disk, &bi);
 	blk_queue_max_integrity_segments(disk->queue, 1);
 
 	return 0;

drivers/nvme/host/pci.c

@@ -538,7 +538,7 @@ static void nvme_dif_remap(struct request *req,
 	virt = bip_get_seed(bip);
 	phys = nvme_block_nr(ns, blk_rq_pos(req));
 	nlb = (blk_rq_bytes(req) >> ns->lba_shift);
-	ts = ns->disk->integrity->tuple_size;
+	ts = ns->disk->queue->integrity.tuple_size;
 
 	for (i = 0; i < nlb; i++, virt++, phys++) {
 		pi = (struct t10_pi_tuple *)p;
@@ -548,36 +548,20 @@ static void nvme_dif_remap(struct request *req,
 	kunmap_atomic(pmap);
 }
 
-static int nvme_noop_verify(struct blk_integrity_iter *iter)
-{
-	return 0;
-}
-
-static int nvme_noop_generate(struct blk_integrity_iter *iter)
-{
-	return 0;
-}
-
-struct blk_integrity nvme_meta_noop = {
-	.name			= "NVME_META_NOOP",
-	.generate_fn		= nvme_noop_generate,
-	.verify_fn		= nvme_noop_verify,
-};
-
 static void nvme_init_integrity(struct nvme_ns *ns)
 {
 	struct blk_integrity integrity;
 
 	switch (ns->pi_type) {
 	case NVME_NS_DPS_PI_TYPE3:
-		integrity = t10_pi_type3_crc;
+		integrity.profile = &t10_pi_type3_crc;
 		break;
 	case NVME_NS_DPS_PI_TYPE1:
 	case NVME_NS_DPS_PI_TYPE2:
-		integrity = t10_pi_type1_crc;
+		integrity.profile = &t10_pi_type1_crc;
 		break;
 	default:
-		integrity = nvme_meta_noop;
+		integrity.profile = NULL;
 		break;
 	}
 	integrity.tuple_size = ns->ms;
@@ -2052,6 +2036,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 	pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
 					id->dps & NVME_NS_DPS_PI_MASK : 0;
 
+	blk_mq_freeze_queue(disk->queue);
 	if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
 				ns->ms != old_ms ||
 				bs != queue_logical_block_size(disk->queue) ||
@@ -2061,8 +2046,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 	ns->pi_type = pi_type;
 	blk_queue_logical_block_size(ns->queue, bs);
 
-	if (ns->ms && !blk_get_integrity(disk) && (disk->flags & GENHD_FL_UP) &&
-								!ns->ext)
+	if (ns->ms && !ns->ext)
 		nvme_init_integrity(ns);
 
 	if ((ns->ms && !(ns->ms == 8 && ns->pi_type) &&
@@ -2074,6 +2058,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
 
 	if (dev->oncs & NVME_CTRL_ONCS_DSM)
 		nvme_config_discard(ns);
+	blk_mq_unfreeze_queue(disk->queue);
 
 	kfree(id);
 	return 0;
@@ -2429,11 +2414,8 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 
 	if (kill)
 		blk_set_queue_dying(ns->queue);
-	if (ns->disk->flags & GENHD_FL_UP) {
-		if (blk_get_integrity(ns->disk))
-			blk_integrity_unregister(ns->disk);
+	if (ns->disk->flags & GENHD_FL_UP)
 		del_gendisk(ns->disk);
-	}
 	if (kill || !blk_queue_dying(ns->queue)) {
 		blk_mq_abort_requeue_list(ns->queue);
 		blk_cleanup_queue(ns->queue);

drivers/scsi/sd.c

@@ -3068,7 +3068,6 @@ static void scsi_disk_release(struct device *dev)
 	ida_remove(&sd_index_ida, sdkp->index);
 	spin_unlock(&sd_index_lock);
 
-	blk_integrity_unregister(disk);
 	disk->private_data = NULL;
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);

drivers/scsi/sd_dif.c

@@ -43,6 +43,7 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 	struct scsi_device *sdp = sdkp->device;
 	struct gendisk *disk = sdkp->disk;
 	u8 type = sdkp->protection_type;
+	struct blk_integrity bi;
 	int dif, dix;
 
 	dif = scsi_host_dif_capable(sdp->host, type);
@@ -55,39 +56,43 @@ void sd_dif_config_host(struct scsi_disk *sdkp)
 	if (!dix)
 		return;
 
+	memset(&bi, 0, sizeof(bi));
+
 	/* Enable DMA of protection information */
 	if (scsi_host_get_guard(sdkp->device->host) & SHOST_DIX_GUARD_IP) {
 		if (type == SD_DIF_TYPE3_PROTECTION)
-			blk_integrity_register(disk, &t10_pi_type3_ip);
+			bi.profile = &t10_pi_type3_ip;
 		else
-			blk_integrity_register(disk, &t10_pi_type1_ip);
+			bi.profile = &t10_pi_type1_ip;
 
-		disk->integrity->flags |= BLK_INTEGRITY_IP_CHECKSUM;
+		bi.flags |= BLK_INTEGRITY_IP_CHECKSUM;
 	} else
 		if (type == SD_DIF_TYPE3_PROTECTION)
-			blk_integrity_register(disk, &t10_pi_type3_crc);
+			bi.profile = &t10_pi_type3_crc;
 		else
-			blk_integrity_register(disk, &t10_pi_type1_crc);
+			bi.profile = &t10_pi_type1_crc;
 
+	bi.tuple_size = sizeof(struct t10_pi_tuple);
 	sd_printk(KERN_NOTICE, sdkp,
-		  "Enabling DIX %s protection\n", disk->integrity->name);
+		  "Enabling DIX %s protection\n", bi.profile->name);
 
-	/* Signal to block layer that we support sector tagging */
 	if (dif && type) {
-
-		disk->integrity->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
+		bi.flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
 
 		if (!sdkp->ATO)
-			return;
+			goto out;
 
 		if (type == SD_DIF_TYPE3_PROTECTION)
-			disk->integrity->tag_size = sizeof(u16) + sizeof(u32);
+			bi.tag_size = sizeof(u16) + sizeof(u32);
 		else
-			disk->integrity->tag_size = sizeof(u16);
+			bi.tag_size = sizeof(u16);
 
 		sd_printk(KERN_NOTICE, sdkp, "DIF application tag size %u\n",
-			  disk->integrity->tag_size);
+			  bi.tag_size);
 	}
+
+out:
+	blk_integrity_register(disk, &bi);
 }
 
 /*

drivers/target/target_core_iblock.c

@@ -155,17 +155,17 @@ static int iblock_configure_device(struct se_device *dev)
 	if (bi) {
 		struct bio_set *bs = ib_dev->ibd_bio_set;
 
-		if (!strcmp(bi->name, "T10-DIF-TYPE3-IP") ||
-		    !strcmp(bi->name, "T10-DIF-TYPE1-IP")) {
+		if (!strcmp(bi->profile->name, "T10-DIF-TYPE3-IP") ||
+		    !strcmp(bi->profile->name, "T10-DIF-TYPE1-IP")) {
 			pr_err("IBLOCK export of blk_integrity: %s not"
-			       " supported\n", bi->name);
+			       " supported\n", bi->profile->name);
 			ret = -ENOSYS;
 			goto out_blkdev_put;
 		}
 
-		if (!strcmp(bi->name, "T10-DIF-TYPE3-CRC")) {
+		if (!strcmp(bi->profile->name, "T10-DIF-TYPE3-CRC")) {
 			dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE3_PROT;
-		} else if (!strcmp(bi->name, "T10-DIF-TYPE1-CRC")) {
+		} else if (!strcmp(bi->profile->name, "T10-DIF-TYPE1-CRC")) {
 			dev->dev_attrib.pi_prot_type = TARGET_DIF_TYPE1_PROT;
 		}
 

fs/block_dev.c

@@ -1075,7 +1075,7 @@ int revalidate_disk(struct gendisk *disk)
 
 	if (disk->fops->revalidate_disk)
 		ret = disk->fops->revalidate_disk(disk);
-
+	blk_integrity_revalidate(disk);
 	bdev = bdget_disk(disk, 0);
 	if (!bdev)
 		return ret;

include/linux/blk-mq.h

@@ -166,7 +166,6 @@ enum {
 struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
 struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 						  struct request_queue *q);
-void blk_mq_finish_init(struct request_queue *q);
 int blk_mq_register_disk(struct gendisk *);
 void blk_mq_unregister_disk(struct gendisk *);
 

include/linux/blkdev.h

@@ -369,6 +369,10 @@ struct request_queue {
 	 */
 	struct kobject mq_kobj;
 
+#ifdef  CONFIG_BLK_DEV_INTEGRITY
+	struct blk_integrity integrity;
+#endif	/* CONFIG_BLK_DEV_INTEGRITY */
+
 #ifdef CONFIG_PM
 	struct device		*dev;
 	int			rpm_status;
@@ -450,7 +454,7 @@ struct request_queue {
 #endif
 	struct rcu_head		rcu_head;
 	wait_queue_head_t	mq_freeze_wq;
-	struct percpu_ref	mq_usage_counter;
+	struct percpu_ref	q_usage_counter;
 	struct list_head	all_q_node;
 
 	struct blk_mq_tag_set	*tag_set;
@@ -1462,22 +1466,13 @@ struct blk_integrity_iter {
 
 typedef int (integrity_processing_fn) (struct blk_integrity_iter *);
 
-struct blk_integrity {
+struct blk_integrity_profile {
 	integrity_processing_fn		*generate_fn;
 	integrity_processing_fn		*verify_fn;
-
-	unsigned short		flags;
-	unsigned short		tuple_size;
-	unsigned short		interval;
-	unsigned short		tag_size;
-
 	const char			*name;
-
-	struct kobject		kobj;
 };
 
-extern bool blk_integrity_is_initialized(struct gendisk *);
-extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
+extern void blk_integrity_register(struct gendisk *, struct blk_integrity *);
 extern void blk_integrity_unregister(struct gendisk *);
 extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
 extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
@@ -1488,15 +1483,20 @@ extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
 extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
 				    struct bio *);
 
-static inline
-struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
-	return bdev->bd_disk->integrity;
+	struct blk_integrity *bi = &disk->queue->integrity;
+
+	if (!bi->profile)
+		return NULL;
+
+	return bi;
 }
 
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+static inline
+struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
 {
-	return disk->integrity;
+	return blk_get_integrity(bdev->bd_disk);
 }
 
 static inline bool blk_integrity_rq(struct request *rq)
@@ -1570,10 +1570,9 @@ static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
 {
 	return 0;
 }
-static inline int blk_integrity_register(struct gendisk *d,
+static inline void blk_integrity_register(struct gendisk *d,
 					 struct blk_integrity *b)
 {
-	return 0;
 }
 static inline void blk_integrity_unregister(struct gendisk *d)
 {
@@ -1598,10 +1597,7 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq,
 {
 	return true;
 }
-static inline bool blk_integrity_is_initialized(struct gendisk *g)
-{
-	return 0;
-}
+
 static inline bool integrity_req_gap_back_merge(struct request *req,
 						struct bio *next)
 {

include/linux/genhd.h

@@ -163,6 +163,18 @@ struct disk_part_tbl {
 
 struct disk_events;
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+
+struct blk_integrity {
+	struct blk_integrity_profile	*profile;
+	unsigned char			flags;
+	unsigned char			tuple_size;
+	unsigned char			interval_exp;
+	unsigned char			tag_size;
+};
+
+#endif	/* CONFIG_BLK_DEV_INTEGRITY */
+
 struct gendisk {
 	/* major, first_minor and minors are input parameters only,
 	 * don't use directly.  Use disk_devt() and disk_max_parts().
@@ -198,8 +210,8 @@ struct gendisk {
 	atomic_t sync_io;		/* RAID */
 	struct disk_events *ev;
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
-	struct blk_integrity *integrity;
-#endif
+	struct kobject integrity_kobj;
+#endif	/* CONFIG_BLK_DEV_INTEGRITY */
 	int node_id;
 };
 
@@ -727,6 +739,16 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 #endif
 }
 
+#if defined(CONFIG_BLK_DEV_INTEGRITY)
+extern void blk_integrity_add(struct gendisk *);
+extern void blk_integrity_del(struct gendisk *);
+extern void blk_integrity_revalidate(struct gendisk *);
+#else	/* CONFIG_BLK_DEV_INTEGRITY */
+static inline void blk_integrity_add(struct gendisk *disk) { }
+static inline void blk_integrity_del(struct gendisk *disk) { }
+static inline void blk_integrity_revalidate(struct gendisk *disk) { }
+#endif	/* CONFIG_BLK_DEV_INTEGRITY */
+
 #else /* CONFIG_BLOCK */
 
 static inline void printk_all_partitions(void) { }

include/linux/t10-pi.h

@@ -14,9 +14,9 @@ struct t10_pi_tuple {
 };
 
 
-extern struct blk_integrity t10_pi_type1_crc;
-extern struct blk_integrity t10_pi_type1_ip;
-extern struct blk_integrity t10_pi_type3_crc;
-extern struct blk_integrity t10_pi_type3_ip;
+extern struct blk_integrity_profile t10_pi_type1_crc;
+extern struct blk_integrity_profile t10_pi_type1_ip;
+extern struct blk_integrity_profile t10_pi_type3_crc;
+extern struct blk_integrity_profile t10_pi_type3_ip;
 
 #endif