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

12 files changed, 93 insertions, 112 deletions

diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index e76ed003769e..061152a43730 100644
--- a/drivers/md/dm-table.c
+++ b/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 @@ no_integrity:
 }
 
 /*
- * 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 @@ combine_limits:
 }
 
 /*
- * 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)))
-		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;
+	}
 
-	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
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1b5c6047e4f1..485760ebba76 100644
--- a/drivers/md/dm.c
+++ b/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);
 	}
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 3fe3d04a968a..740ee9bc5ad3 100644
--- a/drivers/md/md.c
+++ b/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;
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index d132f06afdd1..7331a80d89f1 100644
--- a/drivers/md/multipath.c
+++ b/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;
 		}
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index d9d031ede4bf..33e59876678b 100644
--- a/drivers/md/raid1.c
+++ b/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);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 96f365968306..826210f095be 100644
--- a/drivers/md/raid10.c
+++ b/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);
 
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 254239746020..eae93ab8ffcd 100644
--- a/drivers/nvdimm/btt.c
+++ b/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);
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index cb62ec6a12d0..82c49bb87055 100644
--- a/drivers/nvdimm/core.c
+++ b/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;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 6c0d0fecaeb3..381d2a0aa461 100644
--- a/drivers/nvme/host/pci.c
+++ b/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);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3f370228bf31..9e85211ea1d1 100644
--- a/drivers/scsi/sd.c
+++ b/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);
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 5c06d292b94c..987bf392c336 100644
--- a/drivers/scsi/sd_dif.c
+++ b/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);
 }
 
 /*
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 0f19e11acac2..f29c69120054 100644
--- a/drivers/target/target_core_iblock.c
+++ b/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;
 		}