Browse Source

Merge tag 'for-linus-20181026' of git://git.kernel.dk/linux-block

Pull more block layer updates from Jens Axboe:

 - Set of patches improving support for zoned devices. This was ready
   before the merge window, but I was late in picking it up and hence it
   missed the original pull request (Damien, Christoph)

 - libata no link power management quirk addition for a Samsung drive
   (Diego Viola)

 - Fix for a performance regression in BFQ that went into this merge
   window (Federico Motta)

 - Fix for a missing dma mask setting return value check (Gustavo)

 - Typo in the gdrom queue failure case (me)

 - NULL pointer deref fix for xen-blkfront (Vasilis Liaskovitis)

 - Fixing the get_rq trace point placement in blk-mq (Xiaoguang Wang)

 - Removal of a set-but-not-read variable in cdrom (zhong jiang)

* tag 'for-linus-20181026' of git://git.kernel.dk/linux-block:
  libata: Apply NOLPM quirk for SAMSUNG MZ7TD256HAFV-000L9
  block, bfq: fix asymmetric scenarios detection
  gdrom: fix mistake in assignment of error
  blk-mq: place trace_block_getrq() in correct place
  block: Introduce blk_revalidate_disk_zones()
  block: add a report_zones method
  block: Expose queue nr_zones in sysfs
  block: Improve zone reset execution
  block: Introduce BLKGETNRZONES ioctl
  block: Introduce BLKGETZONESZ ioctl
  block: Limit allocation of zone descriptors for report zones
  block: Introduce blkdev_nr_zones() helper
  scsi: sd_zbc: Fix sd_zbc_check_zones() error checks
  scsi: sd_zbc: Reduce boot device scan and revalidate time
  scsi: sd_zbc: Rearrange code
  cdrom: remove set but not used variable 'tocuse'
  skd: fix unchecked return values
  xen/blkfront: avoid NULL blkfront_info dereference on device removal
Linus Torvalds 6 years ago
parent
commit
6080ad3a99

+ 6 - 12
block/bfq-wf2q.c

@@ -792,24 +792,18 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		 * queue, remove the entity from its old weight counter (if
 		 * there is a counter associated with the entity).
 		 */
-		if (prev_weight != new_weight) {
-			if (bfqq) {
-				root = &bfqd->queue_weights_tree;
-				__bfq_weights_tree_remove(bfqd, bfqq, root);
-			} else
-				bfqd->num_active_groups--;
+		if (prev_weight != new_weight && bfqq) {
+			root = &bfqd->queue_weights_tree;
+			__bfq_weights_tree_remove(bfqd, bfqq, root);
 		}
 		entity->weight = new_weight;
 		/*
 		 * Add the entity, if it is not a weight-raised queue,
 		 * to the counter associated with its new weight.
 		 */
-		if (prev_weight != new_weight) {
-			if (bfqq && bfqq->wr_coeff == 1) {
-				/* If we get here, root has been initialized. */
-				bfq_weights_tree_add(bfqd, bfqq, root);
-			} else
-				bfqd->num_active_groups++;
+		if (prev_weight != new_weight && bfqq && bfqq->wr_coeff == 1) {
+			/* If we get here, root has been initialized. */
+			bfq_weights_tree_add(bfqd, bfqq, root);
 		}
 
 		new_st->wsum += entity->weight;

+ 0 - 1
block/blk-core.c

@@ -2300,7 +2300,6 @@ generic_make_request_checks(struct bio *bio)
 		if (!q->limits.max_write_same_sectors)
 			goto not_supported;
 		break;
-	case REQ_OP_ZONE_REPORT:
 	case REQ_OP_ZONE_RESET:
 		if (!blk_queue_is_zoned(q))
 			goto not_supported;

+ 6 - 7
block/blk-lib.c

@@ -10,8 +10,7 @@
 
 #include "blk.h"
 
-static struct bio *next_bio(struct bio *bio, unsigned int nr_pages,
-		gfp_t gfp)
+struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp)
 {
 	struct bio *new = bio_alloc(gfp, nr_pages);
 
@@ -63,7 +62,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 		end_sect = sector + req_sects;
 
-		bio = next_bio(bio, 0, gfp_mask);
+		bio = blk_next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
 		bio_set_op_attrs(bio, op, 0);
@@ -165,7 +164,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
 	max_write_same_sectors = UINT_MAX >> 9;
 
 	while (nr_sects) {
-		bio = next_bio(bio, 1, gfp_mask);
+		bio = blk_next_bio(bio, 1, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
 		bio->bi_vcnt = 1;
@@ -241,7 +240,7 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
 		return -EOPNOTSUPP;
 
 	while (nr_sects) {
-		bio = next_bio(bio, 0, gfp_mask);
+		bio = blk_next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
 		bio->bi_opf = REQ_OP_WRITE_ZEROES;
@@ -292,8 +291,8 @@ static int __blkdev_issue_zero_pages(struct block_device *bdev,
 		return -EPERM;
 
 	while (nr_sects != 0) {
-		bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
-			       gfp_mask);
+		bio = blk_next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects),
+				   gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
 		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);

+ 0 - 1
block/blk-mq-debugfs.c

@@ -283,7 +283,6 @@ static const char *const op_name[] = {
 	REQ_OP_NAME(WRITE),
 	REQ_OP_NAME(FLUSH),
 	REQ_OP_NAME(DISCARD),
-	REQ_OP_NAME(ZONE_REPORT),
 	REQ_OP_NAME(SECURE_ERASE),
 	REQ_OP_NAME(ZONE_RESET),
 	REQ_OP_NAME(WRITE_SAME),

+ 2 - 2
block/blk-mq.c

@@ -1850,8 +1850,6 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	rq_qos_throttle(q, bio, NULL);
 
-	trace_block_getrq(q, bio, bio->bi_opf);
-
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		rq_qos_cleanup(q, bio);
@@ -1860,6 +1858,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		return BLK_QC_T_NONE;
 	}
 
+	trace_block_getrq(q, bio, bio->bi_opf);
+
 	rq_qos_track(q, rq, bio);
 
 	cookie = request_to_qc_t(data.hctx, rq);

+ 13 - 0
block/blk-sysfs.c

@@ -300,6 +300,11 @@ static ssize_t queue_zoned_show(struct request_queue *q, char *page)
 	}
 }
 
+static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
+{
+	return queue_var_show(blk_queue_nr_zones(q), page);
+}
+
 static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
 {
 	return queue_var_show((blk_queue_nomerges(q) << 1) |
@@ -637,6 +642,11 @@ static struct queue_sysfs_entry queue_zoned_entry = {
 	.show = queue_zoned_show,
 };
 
+static struct queue_sysfs_entry queue_nr_zones_entry = {
+	.attr = {.name = "nr_zones", .mode = 0444 },
+	.show = queue_nr_zones_show,
+};
+
 static struct queue_sysfs_entry queue_nomerges_entry = {
 	.attr = {.name = "nomerges", .mode = 0644 },
 	.show = queue_nomerges_show,
@@ -727,6 +737,7 @@ static struct attribute *default_attrs[] = {
 	&queue_write_zeroes_max_entry.attr,
 	&queue_nonrot_entry.attr,
 	&queue_zoned_entry.attr,
+	&queue_nr_zones_entry.attr,
 	&queue_nomerges_entry.attr,
 	&queue_rq_affinity_entry.attr,
 	&queue_iostats_entry.attr,
@@ -841,6 +852,8 @@ static void __blk_release_queue(struct work_struct *work)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
+	blk_queue_free_zone_bitmaps(q);
+
 	if (!q->mq_ops) {
 		if (q->exit_rq_fn)
 			q->exit_rq_fn(q, q->fq->flush_rq);

+ 231 - 128
block/blk-zoned.c

@@ -12,6 +12,9 @@
 #include <linux/module.h>
 #include <linux/rbtree.h>
 #include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+
+#include "blk.h"
 
 static inline sector_t blk_zone_start(struct request_queue *q,
 				      sector_t sector)
@@ -63,14 +66,38 @@ void __blk_req_zone_write_unlock(struct request *rq)
 }
 EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);
 
+static inline unsigned int __blkdev_nr_zones(struct request_queue *q,
+					     sector_t nr_sectors)
+{
+	unsigned long zone_sectors = blk_queue_zone_sectors(q);
+
+	return (nr_sectors + zone_sectors - 1) >> ilog2(zone_sectors);
+}
+
+/**
+ * blkdev_nr_zones - Get number of zones
+ * @bdev:	Target block device
+ *
+ * Description:
+ *    Return the total number of zones of a zoned block device.
+ *    For a regular block device, the number of zones is always 0.
+ */
+unsigned int blkdev_nr_zones(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (!blk_queue_is_zoned(q))
+		return 0;
+
+	return __blkdev_nr_zones(q, bdev->bd_part->nr_sects);
+}
+EXPORT_SYMBOL_GPL(blkdev_nr_zones);
+
 /*
- * Check that a zone report belongs to the partition.
- * If yes, fix its start sector and write pointer, copy it in the
- * zone information array and return true. Return false otherwise.
+ * Check that a zone report belongs to this partition, and if yes, fix its start
+ * sector and write pointer and return true. Return false otherwise.
  */
-static bool blkdev_report_zone(struct block_device *bdev,
-			       struct blk_zone *rep,
-			       struct blk_zone *zone)
+static bool blkdev_report_zone(struct block_device *bdev, struct blk_zone *rep)
 {
 	sector_t offset = get_start_sect(bdev);
 
@@ -85,11 +112,36 @@ static bool blkdev_report_zone(struct block_device *bdev,
 		rep->wp = rep->start + rep->len;
 	else
 		rep->wp -= offset;
-	memcpy(zone, rep, sizeof(struct blk_zone));
-
 	return true;
 }
 
+static int blk_report_zones(struct gendisk *disk, sector_t sector,
+			    struct blk_zone *zones, unsigned int *nr_zones,
+			    gfp_t gfp_mask)
+{
+	struct request_queue *q = disk->queue;
+	unsigned int z = 0, n, nrz = *nr_zones;
+	sector_t capacity = get_capacity(disk);
+	int ret;
+
+	while (z < nrz && sector < capacity) {
+		n = nrz - z;
+		ret = disk->fops->report_zones(disk, sector, &zones[z], &n,
+					       gfp_mask);
+		if (ret)
+			return ret;
+		if (!n)
+			break;
+		sector += blk_queue_zone_sectors(q) * n;
+		z += n;
+	}
+
+	WARN_ON(z > *nr_zones);
+	*nr_zones = z;
+
+	return 0;
+}
+
 /**
  * blkdev_report_zones - Get zones information
  * @bdev:	Target block device
@@ -104,130 +156,46 @@ static bool blkdev_report_zone(struct block_device *bdev,
  *    requested by @nr_zones. The number of zones actually reported is
  *    returned in @nr_zones.
  */
-int blkdev_report_zones(struct block_device *bdev,
-			sector_t sector,
-			struct blk_zone *zones,
-			unsigned int *nr_zones,
+int blkdev_report_zones(struct block_device *bdev, sector_t sector,
+			struct blk_zone *zones, unsigned int *nr_zones,
 			gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	struct blk_zone_report_hdr *hdr;
-	unsigned int nrz = *nr_zones;
-	struct page *page;
-	unsigned int nr_rep;
-	size_t rep_bytes;
-	unsigned int nr_pages;
-	struct bio *bio;
-	struct bio_vec *bv;
-	unsigned int i, n, nz;
-	unsigned int ofst;
-	void *addr;
+	unsigned int i, nrz;
 	int ret;
 
-	if (!q)
-		return -ENXIO;
-
 	if (!blk_queue_is_zoned(q))
 		return -EOPNOTSUPP;
 
-	if (!nrz)
-		return 0;
-
-	if (sector > bdev->bd_part->nr_sects) {
-		*nr_zones = 0;
-		return 0;
-	}
-
 	/*
-	 * The zone report has a header. So make room for it in the
-	 * payload. Also make sure that the report fits in a single BIO
-	 * that will not be split down the stack.
+	 * A block device that advertized itself as zoned must have a
+	 * report_zones method. If it does not have one defined, the device
+	 * driver has a bug. So warn about that.
 	 */
-	rep_bytes = sizeof(struct blk_zone_report_hdr) +
-		sizeof(struct blk_zone) * nrz;
-	rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK;
-	if (rep_bytes > (queue_max_sectors(q) << 9))
-		rep_bytes = queue_max_sectors(q) << 9;
-
-	nr_pages = min_t(unsigned int, BIO_MAX_PAGES,
-			 rep_bytes >> PAGE_SHIFT);
-	nr_pages = min_t(unsigned int, nr_pages,
-			 queue_max_segments(q));
-
-	bio = bio_alloc(gfp_mask, nr_pages);
-	if (!bio)
-		return -ENOMEM;
-
-	bio_set_dev(bio, bdev);
-	bio->bi_iter.bi_sector = blk_zone_start(q, sector);
-	bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0);
+	if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones))
+		return -EOPNOTSUPP;
 
-	for (i = 0; i < nr_pages; i++) {
-		page = alloc_page(gfp_mask);
-		if (!page) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
-			__free_page(page);
-			break;
-		}
+	if (!*nr_zones || sector >= bdev->bd_part->nr_sects) {
+		*nr_zones = 0;
+		return 0;
 	}
 
-	if (i == 0)
-		ret = -ENOMEM;
-	else
-		ret = submit_bio_wait(bio);
+	nrz = min(*nr_zones,
+		  __blkdev_nr_zones(q, bdev->bd_part->nr_sects - sector));
+	ret = blk_report_zones(bdev->bd_disk, get_start_sect(bdev) + sector,
+			       zones, &nrz, gfp_mask);
 	if (ret)
-		goto out;
-
-	/*
-	 * Process the report result: skip the header and go through the
-	 * reported zones to fixup and fixup the zone information for
-	 * partitions. At the same time, return the zone information into
-	 * the zone array.
-	 */
-	n = 0;
-	nz = 0;
-	nr_rep = 0;
-	bio_for_each_segment_all(bv, bio, i) {
-
-		if (!bv->bv_page)
-			break;
-
-		addr = kmap_atomic(bv->bv_page);
-
-		/* Get header in the first page */
-		ofst = 0;
-		if (!nr_rep) {
-			hdr = addr;
-			nr_rep = hdr->nr_zones;
-			ofst = sizeof(struct blk_zone_report_hdr);
-		}
-
-		/* Fixup and report zones */
-		while (ofst < bv->bv_len &&
-		       n < nr_rep && nz < nrz) {
-			if (blkdev_report_zone(bdev, addr + ofst, &zones[nz]))
-				nz++;
-			ofst += sizeof(struct blk_zone);
-			n++;
-		}
-
-		kunmap_atomic(addr);
+		return ret;
 
-		if (n >= nr_rep || nz >= nrz)
+	for (i = 0; i < nrz; i++) {
+		if (!blkdev_report_zone(bdev, zones))
 			break;
-
+		zones++;
 	}
 
-	*nr_zones = nz;
-out:
-	bio_for_each_segment_all(bv, bio, i)
-		__free_page(bv->bv_page);
-	bio_put(bio);
+	*nr_zones = i;
 
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
@@ -250,16 +218,17 @@ int blkdev_reset_zones(struct block_device *bdev,
 	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t zone_sectors;
 	sector_t end_sector = sector + nr_sectors;
-	struct bio *bio;
+	struct bio *bio = NULL;
+	struct blk_plug plug;
 	int ret;
 
-	if (!q)
-		return -ENXIO;
-
 	if (!blk_queue_is_zoned(q))
 		return -EOPNOTSUPP;
 
-	if (end_sector > bdev->bd_part->nr_sects)
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
 		/* Out of range */
 		return -EINVAL;
 
@@ -272,19 +241,14 @@ int blkdev_reset_zones(struct block_device *bdev,
 	    end_sector != bdev->bd_part->nr_sects)
 		return -EINVAL;
 
+	blk_start_plug(&plug);
 	while (sector < end_sector) {
 
-		bio = bio_alloc(gfp_mask, 0);
+		bio = blk_next_bio(bio, 0, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
 		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
 
-		ret = submit_bio_wait(bio);
-		bio_put(bio);
-
-		if (ret)
-			return ret;
-
 		sector += zone_sectors;
 
 		/* This may take a while, so be nice to others */
@@ -292,7 +256,12 @@ int blkdev_reset_zones(struct block_device *bdev,
 
 	}
 
-	return 0;
+	ret = submit_bio_wait(bio);
+	bio_put(bio);
+
+	blk_finish_plug(&plug);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(blkdev_reset_zones);
 
@@ -328,8 +297,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!rep.nr_zones)
 		return -EINVAL;
 
-	if (rep.nr_zones > INT_MAX / sizeof(struct blk_zone))
-		return -ERANGE;
+	rep.nr_zones = min(blkdev_nr_zones(bdev), rep.nr_zones);
 
 	zones = kvmalloc_array(rep.nr_zones, sizeof(struct blk_zone),
 			       GFP_KERNEL | __GFP_ZERO);
@@ -392,3 +360,138 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
 				  GFP_KERNEL);
 }
+
+static inline unsigned long *blk_alloc_zone_bitmap(int node,
+						   unsigned int nr_zones)
+{
+	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
+			    GFP_NOIO, node);
+}
+
+/*
+ * Allocate an array of struct blk_zone to get nr_zones zone information.
+ * The allocated array may be smaller than nr_zones.
+ */
+static struct blk_zone *blk_alloc_zones(int node, unsigned int *nr_zones)
+{
+	size_t size = *nr_zones * sizeof(struct blk_zone);
+	struct page *page;
+	int order;
+
+	for (order = get_order(size); order > 0; order--) {
+		page = alloc_pages_node(node, GFP_NOIO | __GFP_ZERO, order);
+		if (page) {
+			*nr_zones = min_t(unsigned int, *nr_zones,
+				(PAGE_SIZE << order) / sizeof(struct blk_zone));
+			return page_address(page);
+		}
+	}
+
+	return NULL;
+}
+
+void blk_queue_free_zone_bitmaps(struct request_queue *q)
+{
+	kfree(q->seq_zones_bitmap);
+	q->seq_zones_bitmap = NULL;
+	kfree(q->seq_zones_wlock);
+	q->seq_zones_wlock = NULL;
+}
+
+/**
+ * blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
+ * @disk:	Target disk
+ *
+ * Helper function for low-level device drivers to (re) allocate and initialize
+ * a disk request queue zone bitmaps. This functions should normally be called
+ * within the disk ->revalidate method. For BIO based queues, no zone bitmap
+ * is allocated.
+ */
+int blk_revalidate_disk_zones(struct gendisk *disk)
+{
+	struct request_queue *q = disk->queue;
+	unsigned int nr_zones = __blkdev_nr_zones(q, get_capacity(disk));
+	unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
+	unsigned int i, rep_nr_zones = 0, z = 0, nrz;
+	struct blk_zone *zones = NULL;
+	sector_t sector = 0;
+	int ret = 0;
+
+	/*
+	 * BIO based queues do not use a scheduler so only q->nr_zones
+	 * needs to be updated so that the sysfs exposed value is correct.
+	 */
+	if (!queue_is_rq_based(q)) {
+		q->nr_zones = nr_zones;
+		return 0;
+	}
+
+	if (!blk_queue_is_zoned(q) || !nr_zones) {
+		nr_zones = 0;
+		goto update;
+	}
+
+	/* Allocate bitmaps */
+	ret = -ENOMEM;
+	seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!seq_zones_wlock)
+		goto out;
+	seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!seq_zones_bitmap)
+		goto out;
+
+	/* Get zone information and initialize seq_zones_bitmap */
+	rep_nr_zones = nr_zones;
+	zones = blk_alloc_zones(q->node, &rep_nr_zones);
+	if (!zones)
+		goto out;
+
+	while (z < nr_zones) {
+		nrz = min(nr_zones - z, rep_nr_zones);
+		ret = blk_report_zones(disk, sector, zones, &nrz, GFP_NOIO);
+		if (ret)
+			goto out;
+		if (!nrz)
+			break;
+		for (i = 0; i < nrz; i++) {
+			if (zones[i].type != BLK_ZONE_TYPE_CONVENTIONAL)
+				set_bit(z, seq_zones_bitmap);
+			z++;
+		}
+		sector += nrz * blk_queue_zone_sectors(q);
+	}
+
+	if (WARN_ON(z != nr_zones)) {
+		ret = -EIO;
+		goto out;
+	}
+
+update:
+	/*
+	 * Install the new bitmaps, making sure the queue is stopped and
+	 * all I/Os are completed (i.e. a scheduler is not referencing the
+	 * bitmaps).
+	 */
+	blk_mq_freeze_queue(q);
+	q->nr_zones = nr_zones;
+	swap(q->seq_zones_wlock, seq_zones_wlock);
+	swap(q->seq_zones_bitmap, seq_zones_bitmap);
+	blk_mq_unfreeze_queue(q);
+
+out:
+	free_pages((unsigned long)zones,
+		   get_order(rep_nr_zones * sizeof(struct blk_zone)));
+	kfree(seq_zones_wlock);
+	kfree(seq_zones_bitmap);
+
+	if (ret) {
+		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
+		blk_mq_freeze_queue(q);
+		blk_queue_free_zone_bitmaps(q);
+		blk_mq_unfreeze_queue(q);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
+

+ 8 - 0
block/blk.h

@@ -488,4 +488,12 @@ extern int blk_iolatency_init(struct request_queue *q);
 static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
 #endif
 
+struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp);
+
+#ifdef CONFIG_BLK_DEV_ZONED
+void blk_queue_free_zone_bitmaps(struct request_queue *q);
+#else
+static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {}
+#endif
+
 #endif /* BLK_INTERNAL_H */

+ 4 - 0
block/ioctl.c

@@ -532,6 +532,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
 	case BLKRESETZONE:
 		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKGETZONESZ:
+		return put_uint(arg, bdev_zone_sectors(bdev));
+	case BLKGETNRZONES:
+		return put_uint(arg, blkdev_nr_zones(bdev));
 	case HDIO_GETGEO:
 		return blkdev_getgeo(bdev, argp);
 	case BLKRAGET:

+ 1 - 0
drivers/ata/libata-core.c

@@ -4553,6 +4553,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
 	/* These specific Samsung models/firmware-revs do not handle LPM well */
 	{ "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, },
 	{ "SAMSUNG SSD PM830 mSATA *",  "CXM13D1Q", ATA_HORKAGE_NOLPM, },
+	{ "SAMSUNG MZ7TD256HAFV-000L9", "DXT02L5Q", ATA_HORKAGE_NOLPM, },
 
 	/* devices that don't properly handle queued TRIM commands */
 	{ "Micron_M500IT_*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |

+ 7 - 4
drivers/block/null_blk.h

@@ -87,7 +87,9 @@ struct nullb {
 #ifdef CONFIG_BLK_DEV_ZONED
 int null_zone_init(struct nullb_device *dev);
 void null_zone_exit(struct nullb_device *dev);
-blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio);
+int null_zone_report(struct gendisk *disk, sector_t sector,
+		     struct blk_zone *zones, unsigned int *nr_zones,
+		     gfp_t gfp_mask);
 void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 			unsigned int nr_sectors);
 void null_zone_reset(struct nullb_cmd *cmd, sector_t sector);
@@ -97,10 +99,11 @@ static inline int null_zone_init(struct nullb_device *dev)
 	return -EINVAL;
 }
 static inline void null_zone_exit(struct nullb_device *dev) {}
-static inline blk_status_t null_zone_report(struct nullb *nullb,
-					    struct bio *bio)
+static inline int null_zone_report(struct gendisk *disk, sector_t sector,
+				   struct blk_zone *zones,
+				   unsigned int *nr_zones, gfp_t gfp_mask)
 {
-	return BLK_STS_NOTSUPP;
+	return -EOPNOTSUPP;
 }
 static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 				   unsigned int nr_sectors)

+ 8 - 22
drivers/block/null_blk_main.c

@@ -1129,34 +1129,12 @@ static void null_restart_queue_async(struct nullb *nullb)
 		blk_mq_start_stopped_hw_queues(q, true);
 }
 
-static bool cmd_report_zone(struct nullb *nullb, struct nullb_cmd *cmd)
-{
-	struct nullb_device *dev = cmd->nq->dev;
-
-	if (dev->queue_mode == NULL_Q_BIO) {
-		if (bio_op(cmd->bio) == REQ_OP_ZONE_REPORT) {
-			cmd->error = null_zone_report(nullb, cmd->bio);
-			return true;
-		}
-	} else {
-		if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
-			cmd->error = null_zone_report(nullb, cmd->rq->bio);
-			return true;
-		}
-	}
-
-	return false;
-}
-
 static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 {
 	struct nullb_device *dev = cmd->nq->dev;
 	struct nullb *nullb = dev->nullb;
 	int err = 0;
 
-	if (cmd_report_zone(nullb, cmd))
-		goto out;
-
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
 		struct request *rq = cmd->rq;
 
@@ -1443,6 +1421,7 @@ static const struct block_device_operations null_fops = {
 	.owner =	THIS_MODULE,
 	.open =		null_open,
 	.release =	null_release,
+	.report_zones =	null_zone_report,
 };
 
 static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
@@ -1549,6 +1528,13 @@ static int null_gendisk_register(struct nullb *nullb)
 	disk->queue		= nullb->q;
 	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
 
+	if (nullb->dev->zoned) {
+		int ret = blk_revalidate_disk_zones(disk);
+
+		if (ret != 0)
+			return ret;
+	}
+
 	add_disk(disk);
 	return 0;
 }

+ 15 - 42
drivers/block/null_blk_zoned.c

@@ -48,54 +48,27 @@ void null_zone_exit(struct nullb_device *dev)
 	kvfree(dev->zones);
 }
 
-static void null_zone_fill_bio(struct nullb_device *dev, struct bio *bio,
-			       unsigned int zno, unsigned int nr_zones)
+int null_zone_report(struct gendisk *disk, sector_t sector,
+		     struct blk_zone *zones, unsigned int *nr_zones,
+		     gfp_t gfp_mask)
 {
-	struct blk_zone_report_hdr *hdr = NULL;
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-	void *addr;
-	unsigned int zones_to_cpy;
-
-	bio_for_each_segment(bvec, bio, iter) {
-		addr = kmap_atomic(bvec.bv_page);
-
-		zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone);
-
-		if (!hdr) {
-			hdr = (struct blk_zone_report_hdr *)addr;
-			hdr->nr_zones = nr_zones;
-			zones_to_cpy--;
-			addr += sizeof(struct blk_zone_report_hdr);
-		}
-
-		zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones);
-
-		memcpy(addr, &dev->zones[zno],
-				zones_to_cpy * sizeof(struct blk_zone));
-
-		kunmap_atomic(addr);
+	struct nullb *nullb = disk->private_data;
+	struct nullb_device *dev = nullb->dev;
+	unsigned int zno, nrz = 0;
 
-		nr_zones -= zones_to_cpy;
-		zno += zones_to_cpy;
+	if (!dev->zoned)
+		/* Not a zoned null device */
+		return -EOPNOTSUPP;
 
-		if (!nr_zones)
-			break;
+	zno = null_zone_no(dev, sector);
+	if (zno < dev->nr_zones) {
+		nrz = min_t(unsigned int, *nr_zones, dev->nr_zones - zno);
+		memcpy(zones, &dev->zones[zno], nrz * sizeof(struct blk_zone));
 	}
-}
 
-blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio)
-{
-	struct nullb_device *dev = nullb->dev;
-	unsigned int zno = null_zone_no(dev, bio->bi_iter.bi_sector);
-	unsigned int nr_zones = dev->nr_zones - zno;
-	unsigned int max_zones;
+	*nr_zones = nrz;
 
-	max_zones = (bio->bi_iter.bi_size / sizeof(struct blk_zone)) - 1;
-	nr_zones = min_t(unsigned int, nr_zones, max_zones);
-	null_zone_fill_bio(nullb->dev, bio, zno, nr_zones);
-
-	return BLK_STS_OK;
+	return 0;
 }
 
 void null_zone_write(struct nullb_cmd *cmd, sector_t sector,

+ 2 - 2
drivers/block/skd_main.c

@@ -3175,7 +3175,7 @@ static int skd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out;
 	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (rc)
-		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (rc) {
 		dev_err(&pdev->dev, "DMA mask error %d\n", rc);
 		goto err_out_regions;
@@ -3364,7 +3364,7 @@ static int skd_pci_resume(struct pci_dev *pdev)
 		goto err_out;
 	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (rc)
-		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (rc) {
 		dev_err(&pdev->dev, "DMA mask error %d\n", rc);
 		goto err_out_regions;

+ 3 - 0
drivers/block/xen-blkfront.c

@@ -2493,6 +2493,9 @@ static int blkfront_remove(struct xenbus_device *xbdev)
 
 	dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename);
 
+	if (!info)
+		return 0;
+
 	blkif_free(info, 0);
 
 	mutex_lock(&info->mutex);

+ 4 - 4
drivers/cdrom/gdrom.c

@@ -327,15 +327,15 @@ static int get_entry_track(int track)
 static int gdrom_get_last_session(struct cdrom_device_info *cd_info,
 	struct cdrom_multisession *ms_info)
 {
-	int fentry, lentry, track, data, tocuse, err;
+	int fentry, lentry, track, data, err;
+
 	if (!gd.toc)
 		return -ENOMEM;
-	tocuse = 1;
+
 	/* Check if GD-ROM */
 	err = gdrom_readtoc_cmd(gd.toc, 1);
 	/* Not a GD-ROM so check if standard CD-ROM */
 	if (err) {
-		tocuse = 0;
 		err = gdrom_readtoc_cmd(gd.toc, 0);
 		if (err) {
 			pr_info("Could not get CD table of contents\n");
@@ -794,7 +794,7 @@ static int probe_gdrom(struct platform_device *devptr)
 	gd.gdrom_rq = blk_mq_init_sq_queue(&gd.tag_set, &gdrom_mq_ops, 1,
 				BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING);
 	if (IS_ERR(gd.gdrom_rq)) {
-		rc = PTR_ERR(gd.gdrom_rq);
+		err = PTR_ERR(gd.gdrom_rq);
 		gd.gdrom_rq = NULL;
 		goto probe_fail_requestq;
 	}

+ 21 - 9
drivers/md/dm-flakey.c

@@ -315,10 +315,6 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 	if (bio_op(bio) == REQ_OP_ZONE_RESET)
 		goto map_bio;
 
-	/* We need to remap reported zones, so remember the BIO iter */
-	if (bio_op(bio) == REQ_OP_ZONE_REPORT)
-		goto map_bio;
-
 	/* Are we alive ? */
 	elapsed = (jiffies - fc->start_time) / HZ;
 	if (elapsed % (fc->up_interval + fc->down_interval) >= fc->up_interval) {
@@ -380,11 +376,6 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio,
 	if (bio_op(bio) == REQ_OP_ZONE_RESET)
 		return DM_ENDIO_DONE;
 
-	if (bio_op(bio) == REQ_OP_ZONE_REPORT) {
-		dm_remap_zone_report(ti, bio, fc->start);
-		return DM_ENDIO_DONE;
-	}
-
 	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
 		if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
 		    all_corrupt_bio_flags_match(bio, fc)) {
@@ -457,6 +448,26 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 	return 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int flakey_report_zones(struct dm_target *ti, sector_t sector,
+			       struct blk_zone *zones, unsigned int *nr_zones,
+			       gfp_t gfp_mask)
+{
+	struct flakey_c *fc = ti->private;
+	int ret;
+
+	/* Do report and remap it */
+	ret = blkdev_report_zones(fc->dev->bdev, flakey_map_sector(ti, sector),
+				  zones, nr_zones, gfp_mask);
+	if (ret != 0)
+		return ret;
+
+	if (*nr_zones)
+		dm_remap_zone_report(ti, fc->start, zones, nr_zones);
+	return 0;
+}
+#endif
+
 static int flakey_iterate_devices(struct dm_target *ti, iterate_devices_callout_fn fn, void *data)
 {
 	struct flakey_c *fc = ti->private;
@@ -469,6 +480,7 @@ static struct target_type flakey_target = {
 	.version = {1, 5, 0},
 #ifdef CONFIG_BLK_DEV_ZONED
 	.features = DM_TARGET_ZONED_HM,
+	.report_zones = flakey_report_zones,
 #endif
 	.module = THIS_MODULE,
 	.ctr    = flakey_ctr,

+ 21 - 14
drivers/md/dm-linear.c

@@ -102,19 +102,6 @@ static int linear_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_REMAPPED;
 }
 
-#ifdef CONFIG_BLK_DEV_ZONED
-static int linear_end_io(struct dm_target *ti, struct bio *bio,
-			 blk_status_t *error)
-{
-	struct linear_c *lc = ti->private;
-
-	if (!*error && bio_op(bio) == REQ_OP_ZONE_REPORT)
-		dm_remap_zone_report(ti, bio, lc->start);
-
-	return DM_ENDIO_DONE;
-}
-#endif
-
 static void linear_status(struct dm_target *ti, status_type_t type,
 			  unsigned status_flags, char *result, unsigned maxlen)
 {
@@ -148,6 +135,26 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev
 	return 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static int linear_report_zones(struct dm_target *ti, sector_t sector,
+			       struct blk_zone *zones, unsigned int *nr_zones,
+			       gfp_t gfp_mask)
+{
+	struct linear_c *lc = (struct linear_c *) ti->private;
+	int ret;
+
+	/* Do report and remap it */
+	ret = blkdev_report_zones(lc->dev->bdev, linear_map_sector(ti, sector),
+				  zones, nr_zones, gfp_mask);
+	if (ret != 0)
+		return ret;
+
+	if (*nr_zones)
+		dm_remap_zone_report(ti, lc->start, zones, nr_zones);
+	return 0;
+}
+#endif
+
 static int linear_iterate_devices(struct dm_target *ti,
 				  iterate_devices_callout_fn fn, void *data)
 {
@@ -211,8 +218,8 @@ static struct target_type linear_target = {
 	.name   = "linear",
 	.version = {1, 4, 0},
 #ifdef CONFIG_BLK_DEV_ZONED
-	.end_io = linear_end_io,
 	.features = DM_TARGET_PASSES_INTEGRITY | DM_TARGET_ZONED_HM,
+	.report_zones = linear_report_zones,
 #else
 	.features = DM_TARGET_PASSES_INTEGRITY,
 #endif

+ 10 - 0
drivers/md/dm-table.c

@@ -1937,6 +1937,16 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 */
 	if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random))
 		blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
+
+	/*
+	 * For a zoned target, the number of zones should be updated for the
+	 * correct value to be exposed in sysfs queue/nr_zones. For a BIO based
+	 * target, this is all that is needed. For a request based target, the
+	 * queue zone bitmaps must also be updated.
+	 * Use blk_revalidate_disk_zones() to handle this.
+	 */
+	if (blk_queue_is_zoned(q))
+		blk_revalidate_disk_zones(t->md->disk);
 }
 
 unsigned int dm_table_get_num_targets(struct dm_table *t)

+ 1 - 2
drivers/md/dm-zoned-target.c

@@ -702,8 +702,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path)
 	dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors);
 	dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks);
 
-	dev->nr_zones = (dev->capacity + dev->zone_nr_sectors - 1)
-		>> dev->zone_nr_sectors_shift;
+	dev->nr_zones = blkdev_nr_zones(dev->bdev);
 
 	dmz->dev = dev;
 

+ 84 - 85
drivers/md/dm.c

@@ -458,6 +458,57 @@ static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 	return dm_get_geometry(md, geo);
 }
 
+static int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
+			       struct blk_zone *zones, unsigned int *nr_zones,
+			       gfp_t gfp_mask)
+{
+#ifdef CONFIG_BLK_DEV_ZONED
+	struct mapped_device *md = disk->private_data;
+	struct dm_target *tgt;
+	struct dm_table *map;
+	int srcu_idx, ret;
+
+	if (dm_suspended_md(md))
+		return -EAGAIN;
+
+	map = dm_get_live_table(md, &srcu_idx);
+	if (!map)
+		return -EIO;
+
+	tgt = dm_table_find_target(map, sector);
+	if (!dm_target_is_valid(tgt)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	/*
+	 * If we are executing this, we already know that the block device
+	 * is a zoned device and so each target should have support for that
+	 * type of drive. A missing report_zones method means that the target
+	 * driver has a problem.
+	 */
+	if (WARN_ON(!tgt->type->report_zones)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	/*
+	 * blkdev_report_zones() will loop and call this again to cover all the
+	 * zones of the target, eventually moving on to the next target.
+	 * So there is no need to loop here trying to fill the entire array
+	 * of zones.
+	 */
+	ret = tgt->type->report_zones(tgt, sector, zones,
+				      nr_zones, gfp_mask);
+
+out:
+	dm_put_live_table(md, srcu_idx);
+	return ret;
+#else
+	return -ENOTSUPP;
+#endif
+}
+
 static int dm_prepare_ioctl(struct mapped_device *md, int *srcu_idx,
 			    struct block_device **bdev)
 	__acquires(md->io_barrier)
@@ -1155,93 +1206,49 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
 
 /*
- * The zone descriptors obtained with a zone report indicate zone positions
- * within the target backing device, regardless of that device is a partition
- * and regardless of the target mapping start sector on the device or partition.
- * The zone descriptors start sector and write pointer position must be adjusted
- * to match their relative position within the dm device.
- * A target may call dm_remap_zone_report() after completion of a
- * REQ_OP_ZONE_REPORT bio to remap the zone descriptors obtained from the
- * backing device.
+ * The zone descriptors obtained with a zone report indicate
+ * zone positions within the underlying device of the target. The zone
+ * descriptors must be remapped to match their position within the dm device.
+ * The caller target should obtain the zones information using
+ * blkdev_report_zones() to ensure that remapping for partition offset is
+ * already handled.
  */
-void dm_remap_zone_report(struct dm_target *ti, struct bio *bio, sector_t start)
+void dm_remap_zone_report(struct dm_target *ti, sector_t start,
+			  struct blk_zone *zones, unsigned int *nr_zones)
 {
 #ifdef CONFIG_BLK_DEV_ZONED
-	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
-	struct bio *report_bio = tio->io->orig_bio;
-	struct blk_zone_report_hdr *hdr = NULL;
 	struct blk_zone *zone;
-	unsigned int nr_rep = 0;
-	unsigned int ofst;
-	sector_t part_offset;
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-	void *addr;
-
-	if (bio->bi_status)
-		return;
-
-	/*
-	 * bio sector was incremented by the request size on completion. Taking
-	 * into account the original request sector, the target start offset on
-	 * the backing device and the target mapping offset (ti->begin), the
-	 * start sector of the backing device. The partition offset is always 0
-	 * if the target uses a whole device.
-	 */
-	part_offset = bio->bi_iter.bi_sector + ti->begin - (start + bio_end_sector(report_bio));
+	unsigned int nrz = *nr_zones;
+	int i;
 
 	/*
-	 * Remap the start sector of the reported zones. For sequential zones,
-	 * also remap the write pointer position.
+	 * Remap the start sector and write pointer position of the zones in
+	 * the array. Since we may have obtained from the target underlying
+	 * device more zones that the target size, also adjust the number
+	 * of zones.
 	 */
-	bio_for_each_segment(bvec, report_bio, iter) {
-		addr = kmap_atomic(bvec.bv_page);
-
-		/* Remember the report header in the first page */
-		if (!hdr) {
-			hdr = addr;
-			ofst = sizeof(struct blk_zone_report_hdr);
-		} else
-			ofst = 0;
-
-		/* Set zones start sector */
-		while (hdr->nr_zones && ofst < bvec.bv_len) {
-			zone = addr + ofst;
-			zone->start -= part_offset;
-			if (zone->start >= start + ti->len) {
-				hdr->nr_zones = 0;
-				break;
-			}
-			zone->start = zone->start + ti->begin - start;
-			if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
-				if (zone->cond == BLK_ZONE_COND_FULL)
-					zone->wp = zone->start + zone->len;
-				else if (zone->cond == BLK_ZONE_COND_EMPTY)
-					zone->wp = zone->start;
-				else
-					zone->wp = zone->wp + ti->begin - start - part_offset;
-			}
-			ofst += sizeof(struct blk_zone);
-			hdr->nr_zones--;
-			nr_rep++;
+	for (i = 0; i < nrz; i++) {
+		zone = zones + i;
+		if (zone->start >= start + ti->len) {
+			memset(zone, 0, sizeof(struct blk_zone) * (nrz - i));
+			break;
 		}
 
-		if (addr != hdr)
-			kunmap_atomic(addr);
+		zone->start = zone->start + ti->begin - start;
+		if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL)
+			continue;
 
-		if (!hdr->nr_zones)
-			break;
-	}
-
-	if (hdr) {
-		hdr->nr_zones = nr_rep;
-		kunmap_atomic(hdr);
+		if (zone->cond == BLK_ZONE_COND_FULL)
+			zone->wp = zone->start + zone->len;
+		else if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->wp = zone->start;
+		else
+			zone->wp = zone->wp + ti->begin - start;
 	}
 
-	bio_advance(report_bio, report_bio->bi_iter.bi_size);
-
+	*nr_zones = i;
 #else /* !CONFIG_BLK_DEV_ZONED */
-	bio->bi_status = BLK_STS_NOTSUPP;
+	*nr_zones = 0;
 #endif
 }
 EXPORT_SYMBOL_GPL(dm_remap_zone_report);
@@ -1327,8 +1334,7 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio,
 			return r;
 	}
 
-	if (bio_op(bio) != REQ_OP_ZONE_REPORT)
-		bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
+	bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
 	clone->bi_iter.bi_size = to_bytes(len);
 
 	if (unlikely(bio_integrity(bio) != NULL))
@@ -1541,7 +1547,6 @@ static bool __process_abnormal_io(struct clone_info *ci, struct dm_target *ti,
  */
 static int __split_and_process_non_flush(struct clone_info *ci)
 {
-	struct bio *bio = ci->bio;
 	struct dm_target *ti;
 	unsigned len;
 	int r;
@@ -1553,11 +1558,7 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 	if (unlikely(__process_abnormal_io(ci, ti, &r)))
 		return r;
 
-	if (bio_op(bio) == REQ_OP_ZONE_REPORT)
-		len = ci->sector_count;
-	else
-		len = min_t(sector_t, max_io_len(ci->sector, ti),
-			    ci->sector_count);
+	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
 
 	r = __clone_and_map_data_bio(ci, ti, ci->sector, &len);
 	if (r < 0)
@@ -1616,9 +1617,6 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 				 * We take a clone of the original to store in
 				 * ci.io->orig_bio to be used by end_io_acct() and
 				 * for dec_pending to use for completion handling.
-				 * As this path is not used for REQ_OP_ZONE_REPORT,
-				 * the usage of io->orig_bio in dm_remap_zone_report()
-				 * won't be affected by this reassignment.
 				 */
 				struct bio *b = bio_split(bio, bio_sectors(bio) - ci.sector_count,
 							  GFP_NOIO, &md->queue->bio_split);
@@ -3167,6 +3165,7 @@ static const struct block_device_operations dm_blk_dops = {
 	.release = dm_blk_close,
 	.ioctl = dm_blk_ioctl,
 	.getgeo = dm_blk_getgeo,
+	.report_zones = dm_blk_report_zones,
 	.pr_ops = &dm_pr_ops,
 	.owner = THIS_MODULE
 };

+ 1 - 14
drivers/scsi/sd.c

@@ -1272,8 +1272,6 @@ static int sd_init_command(struct scsi_cmnd *cmd)
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
 		return sd_setup_read_write_cmnd(cmd);
-	case REQ_OP_ZONE_REPORT:
-		return sd_zbc_setup_report_cmnd(cmd);
 	case REQ_OP_ZONE_RESET:
 		return sd_zbc_setup_reset_cmnd(cmd);
 	default:
@@ -1802,6 +1800,7 @@ static const struct block_device_operations sd_fops = {
 	.check_events		= sd_check_events,
 	.revalidate_disk	= sd_revalidate_disk,
 	.unlock_native_capacity	= sd_unlock_native_capacity,
+	.report_zones		= sd_zbc_report_zones,
 	.pr_ops			= &sd_pr_ops,
 };
 
@@ -1953,16 +1952,6 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 			scsi_set_resid(SCpnt, blk_rq_bytes(req));
 		}
 		break;
-	case REQ_OP_ZONE_REPORT:
-		if (!result) {
-			good_bytes = scsi_bufflen(SCpnt)
-				- scsi_get_resid(SCpnt);
-			scsi_set_resid(SCpnt, 0);
-		} else {
-			good_bytes = 0;
-			scsi_set_resid(SCpnt, blk_rq_bytes(req));
-		}
-		break;
 	default:
 		/*
 		 * In case of bogus fw or device, we could end up having
@@ -3425,8 +3414,6 @@ static int sd_remove(struct device *dev)
 	del_gendisk(sdkp->disk);
 	sd_shutdown(dev);
 
-	sd_zbc_remove(sdkp);
-
 	free_opal_dev(sdkp->opal_dev);
 
 	blk_register_region(devt, SD_MINORS, NULL,

+ 5 - 10
drivers/scsi/sd.h

@@ -76,7 +76,6 @@ struct scsi_disk {
 #ifdef CONFIG_BLK_DEV_ZONED
 	u32		nr_zones;
 	u32		zone_blocks;
-	u32		zone_shift;
 	u32		zones_optimal_open;
 	u32		zones_optimal_nonseq;
 	u32		zones_max_open;
@@ -271,12 +270,13 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 #ifdef CONFIG_BLK_DEV_ZONED
 
 extern int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer);
-extern void sd_zbc_remove(struct scsi_disk *sdkp);
 extern void sd_zbc_print_zones(struct scsi_disk *sdkp);
-extern int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd);
 extern int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd);
 extern void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 			    struct scsi_sense_hdr *sshdr);
+extern int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
+			       struct blk_zone *zones, unsigned int *nr_zones,
+			       gfp_t gfp_mask);
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
@@ -286,15 +286,8 @@ static inline int sd_zbc_read_zones(struct scsi_disk *sdkp,
 	return 0;
 }
 
-static inline void sd_zbc_remove(struct scsi_disk *sdkp) {}
-
 static inline void sd_zbc_print_zones(struct scsi_disk *sdkp) {}
 
-static inline int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
-{
-	return BLKPREP_INVALID;
-}
-
 static inline int sd_zbc_setup_reset_cmnd(struct scsi_cmnd *cmd)
 {
 	return BLKPREP_INVALID;
@@ -304,6 +297,8 @@ static inline void sd_zbc_complete(struct scsi_cmnd *cmd,
 				   unsigned int good_bytes,
 				   struct scsi_sense_hdr *sshdr) {}
 
+#define sd_zbc_report_zones NULL
+
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 #endif /* _SCSI_DISK_H */

+ 129 - 372
drivers/scsi/sd_zbc.c

@@ -62,16 +62,22 @@ static void sd_zbc_parse_report(struct scsi_disk *sdkp, u8 *buf,
 }
 
 /**
- * sd_zbc_report_zones - Issue a REPORT ZONES scsi command.
+ * sd_zbc_do_report_zones - Issue a REPORT ZONES scsi command.
  * @sdkp: The target disk
  * @buf: Buffer to use for the reply
  * @buflen: the buffer size
  * @lba: Start LBA of the report
+ * @partial: Do partial report
  *
  * For internal use during device validation.
+ * Using partial=true can significantly speed up execution of a report zones
+ * command because the disk does not have to count all possible report matching
+ * zones and will only report the count of zones fitting in the command reply
+ * buffer.
  */
-static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
-			       unsigned int buflen, sector_t lba)
+static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
+				  unsigned int buflen, sector_t lba,
+				  bool partial)
 {
 	struct scsi_device *sdp = sdkp->device;
 	const int timeout = sdp->request_queue->rq_timeout;
@@ -85,6 +91,8 @@ static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 	cmd[1] = ZI_REPORT_ZONES;
 	put_unaligned_be64(lba, &cmd[2]);
 	put_unaligned_be32(buflen, &cmd[10]);
+	if (partial)
+		cmd[14] = ZBC_REPORT_ZONE_PARTIAL;
 	memset(buf, 0, buflen);
 
 	result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE,
@@ -110,108 +118,56 @@ static int sd_zbc_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
 }
 
 /**
- * sd_zbc_setup_report_cmnd - Prepare a REPORT ZONES scsi command
- * @cmd: The command to setup
+ * sd_zbc_report_zones - Disk report zones operation.
+ * @disk: The target disk
+ * @sector: Start 512B sector of the report
+ * @zones: Array of zone descriptors
+ * @nr_zones: Number of descriptors in the array
+ * @gfp_mask: Memory allocation mask
  *
- * Call in sd_init_command() for a REQ_OP_ZONE_REPORT request.
+ * Execute a report zones command on the target disk.
  */
-int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
+int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
+			struct blk_zone *zones, unsigned int *nr_zones,
+			gfp_t gfp_mask)
 {
-	struct request *rq = cmd->request;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
-	sector_t lba, sector = blk_rq_pos(rq);
-	unsigned int nr_bytes = blk_rq_bytes(rq);
-	int ret;
-
-	WARN_ON(nr_bytes == 0);
+	struct scsi_disk *sdkp = scsi_disk(disk);
+	unsigned int i, buflen, nrz = *nr_zones;
+	unsigned char *buf;
+	size_t offset = 0;
+	int ret = 0;
 
 	if (!sd_is_zoned(sdkp))
 		/* Not a zoned device */
-		return BLKPREP_KILL;
-
-	ret = scsi_init_io(cmd);
-	if (ret != BLKPREP_OK)
-		return ret;
-
-	cmd->cmd_len = 16;
-	memset(cmd->cmnd, 0, cmd->cmd_len);
-	cmd->cmnd[0] = ZBC_IN;
-	cmd->cmnd[1] = ZI_REPORT_ZONES;
-	lba = sectors_to_logical(sdkp->device, sector);
-	put_unaligned_be64(lba, &cmd->cmnd[2]);
-	put_unaligned_be32(nr_bytes, &cmd->cmnd[10]);
-	/* Do partial report for speeding things up */
-	cmd->cmnd[14] = ZBC_REPORT_ZONE_PARTIAL;
-
-	cmd->sc_data_direction = DMA_FROM_DEVICE;
-	cmd->sdb.length = nr_bytes;
-	cmd->transfersize = sdkp->device->sector_size;
-	cmd->allowed = 0;
-
-	return BLKPREP_OK;
-}
-
-/**
- * sd_zbc_report_zones_complete - Process a REPORT ZONES scsi command reply.
- * @scmd: The completed report zones command
- * @good_bytes: reply size in bytes
- *
- * Convert all reported zone descriptors to struct blk_zone. The conversion
- * is done in-place, directly in the request specified sg buffer.
- */
-static void sd_zbc_report_zones_complete(struct scsi_cmnd *scmd,
-					 unsigned int good_bytes)
-{
-	struct request *rq = scmd->request;
-	struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
-	struct sg_mapping_iter miter;
-	struct blk_zone_report_hdr hdr;
-	struct blk_zone zone;
-	unsigned int offset, bytes = 0;
-	unsigned long flags;
-	u8 *buf;
-
-	if (good_bytes < 64)
-		return;
+		return -EOPNOTSUPP;
 
-	memset(&hdr, 0, sizeof(struct blk_zone_report_hdr));
-
-	sg_miter_start(&miter, scsi_sglist(scmd), scsi_sg_count(scmd),
-		       SG_MITER_TO_SG | SG_MITER_ATOMIC);
-
-	local_irq_save(flags);
-	while (sg_miter_next(&miter) && bytes < good_bytes) {
+	/*
+	 * Get a reply buffer for the number of requested zones plus a header.
+	 * For ATA, buffers must be aligned to 512B.
+	 */
+	buflen = roundup((nrz + 1) * 64, 512);
+	buf = kmalloc(buflen, gfp_mask);
+	if (!buf)
+		return -ENOMEM;
 
-		buf = miter.addr;
-		offset = 0;
+	ret = sd_zbc_do_report_zones(sdkp, buf, buflen,
+			sectors_to_logical(sdkp->device, sector), true);
+	if (ret)
+		goto out_free_buf;
 
-		if (bytes == 0) {
-			/* Set the report header */
-			hdr.nr_zones = min_t(unsigned int,
-					 (good_bytes - 64) / 64,
-					 get_unaligned_be32(&buf[0]) / 64);
-			memcpy(buf, &hdr, sizeof(struct blk_zone_report_hdr));
-			offset += 64;
-			bytes += 64;
-		}
+	nrz = min(nrz, get_unaligned_be32(&buf[0]) / 64);
+	for (i = 0; i < nrz; i++) {
+		offset += 64;
+		sd_zbc_parse_report(sdkp, buf + offset, zones);
+		zones++;
+	}
 
-		/* Parse zone descriptors */
-		while (offset < miter.length && hdr.nr_zones) {
-			WARN_ON(offset > miter.length);
-			buf = miter.addr + offset;
-			sd_zbc_parse_report(sdkp, buf, &zone);
-			memcpy(buf, &zone, sizeof(struct blk_zone));
-			offset += 64;
-			bytes += 64;
-			hdr.nr_zones--;
-		}
+	*nr_zones = nrz;
 
-		if (!hdr.nr_zones)
-			break;
+out_free_buf:
+	kfree(buf);
 
-	}
-	sg_miter_stop(&miter);
-	local_irq_restore(flags);
+	return ret;
 }
 
 /**
@@ -294,30 +250,23 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 	case REQ_OP_WRITE_ZEROES:
 	case REQ_OP_WRITE_SAME:
 		break;
-
-	case REQ_OP_ZONE_REPORT:
-
-		if (!result)
-			sd_zbc_report_zones_complete(cmd, good_bytes);
-		break;
-
 	}
 }
 
 /**
- * sd_zbc_read_zoned_characteristics - Read zoned block device characteristics
+ * sd_zbc_check_zoned_characteristics - Check zoned block device characteristics
  * @sdkp: Target disk
  * @buf: Buffer where to store the VPD page data
  *
- * Read VPD page B6.
+ * Read VPD page B6, get information and check that reads are unconstrained.
  */
-static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp,
-					     unsigned char *buf)
+static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
+					      unsigned char *buf)
 {
 
 	if (scsi_get_vpd_page(sdkp->device, 0xb6, buf, 64)) {
 		sd_printk(KERN_NOTICE, sdkp,
-			  "Unconstrained-read check failed\n");
+			  "Read zoned characteristics VPD page failed\n");
 		return -ENODEV;
 	}
 
@@ -335,43 +284,17 @@ static int sd_zbc_read_zoned_characteristics(struct scsi_disk *sdkp,
 		sdkp->zones_max_open = get_unaligned_be32(&buf[16]);
 	}
 
-	return 0;
-}
-
-/**
- * sd_zbc_check_capacity - Check reported capacity.
- * @sdkp: Target disk
- * @buf: Buffer to use for commands
- *
- * ZBC drive may report only the capacity of the first conventional zones at
- * LBA 0. This is indicated by the RC_BASIS field of the read capacity reply.
- * Check this here. If the disk reported only its conventional zones capacity,
- * get the total capacity by doing a report zones.
- */
-static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
-{
-	sector_t lba;
-	int ret;
-
-	if (sdkp->rc_basis != 0)
-		return 0;
-
-	/* Do a report zone to get the maximum LBA to check capacity */
-	ret = sd_zbc_report_zones(sdkp, buf, SD_BUF_SIZE, 0);
-	if (ret)
-		return ret;
-
-	/* The max_lba field is the capacity of this device */
-	lba = get_unaligned_be64(&buf[8]);
-	if (lba + 1 == sdkp->capacity)
-		return 0;
-
-	if (sdkp->first_scan)
-		sd_printk(KERN_WARNING, sdkp,
-			  "Changing capacity from %llu to max LBA+1 %llu\n",
-			  (unsigned long long)sdkp->capacity,
-			  (unsigned long long)lba + 1);
-	sdkp->capacity = lba + 1;
+	/*
+	 * Check for unconstrained reads: host-managed devices with
+	 * constrained reads (drives failing read after write pointer)
+	 * are not supported.
+	 */
+	if (!sdkp->urswrz) {
+		if (sdkp->first_scan)
+			sd_printk(KERN_NOTICE, sdkp,
+			  "constrained reads devices are not supported\n");
+		return -ENODEV;
+	}
 
 	return 0;
 }
@@ -379,24 +302,27 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
 #define SD_ZBC_BUF_SIZE 131072U
 
 /**
- * sd_zbc_check_zone_size - Check the device zone sizes
+ * sd_zbc_check_zones - Check the device capacity and zone sizes
  * @sdkp: Target disk
  *
- * Check that all zones of the device are equal. The last zone can however
- * be smaller. The zone size must also be a power of two number of LBAs.
+ * Check that the device capacity as reported by READ CAPACITY matches the
+ * max_lba value (plus one)of the report zones command reply. Also check that
+ * all zones of the device have an equal size, only allowing the last zone of
+ * the disk to have a smaller size (runt zone). The zone size must also be a
+ * power of two.
  *
  * Returns the zone size in number of blocks upon success or an error code
  * upon failure.
  */
-static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
+static int sd_zbc_check_zones(struct scsi_disk *sdkp, u32 *zblocks)
 {
 	u64 zone_blocks = 0;
-	sector_t block = 0;
+	sector_t max_lba, block = 0;
 	unsigned char *buf;
 	unsigned char *rec;
 	unsigned int buf_len;
 	unsigned int list_length;
-	s64 ret;
+	int ret;
 	u8 same;
 
 	/* Get a buffer */
@@ -404,11 +330,28 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 	if (!buf)
 		return -ENOMEM;
 
-	/* Do a report zone to get the same field */
-	ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0);
+	/* Do a report zone to get max_lba and the same field */
+	ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, 0, false);
 	if (ret)
 		goto out_free;
 
+	if (sdkp->rc_basis == 0) {
+		/* The max_lba field is the capacity of this device */
+		max_lba = get_unaligned_be64(&buf[8]);
+		if (sdkp->capacity != max_lba + 1) {
+			if (sdkp->first_scan)
+				sd_printk(KERN_WARNING, sdkp,
+					"Changing capacity from %llu to max LBA+1 %llu\n",
+					(unsigned long long)sdkp->capacity,
+					(unsigned long long)max_lba + 1);
+			sdkp->capacity = max_lba + 1;
+		}
+	}
+
+	/*
+	 * Check same field: for any value other than 0, we know that all zones
+	 * have the same size.
+	 */
 	same = buf[4] & 0x0f;
 	if (same > 0) {
 		rec = &buf[64];
@@ -445,8 +388,8 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 		}
 
 		if (block < sdkp->capacity) {
-			ret = sd_zbc_report_zones(sdkp, buf,
-						  SD_ZBC_BUF_SIZE, block);
+			ret = sd_zbc_do_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
+						     block, true);
 			if (ret)
 				goto out_free;
 		}
@@ -470,9 +413,10 @@ out:
 		if (sdkp->first_scan)
 			sd_printk(KERN_NOTICE, sdkp,
 				  "Zone size too large\n");
-		ret = -ENODEV;
+		ret = -EFBIG;
 	} else {
-		ret = zone_blocks;
+		*zblocks = zone_blocks;
+		ret = 0;
 	}
 
 out_free:
@@ -481,191 +425,11 @@ out_free:
 	return ret;
 }
 
-/**
- * sd_zbc_alloc_zone_bitmap - Allocate a zone bitmap (one bit per zone).
- * @nr_zones: Number of zones to allocate space for.
- * @numa_node: NUMA node to allocate the memory from.
- */
-static inline unsigned long *
-sd_zbc_alloc_zone_bitmap(u32 nr_zones, int numa_node)
-{
-	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
-			    GFP_KERNEL, numa_node);
-}
-
-/**
- * sd_zbc_get_seq_zones - Parse report zones reply to identify sequential zones
- * @sdkp: disk used
- * @buf: report reply buffer
- * @buflen: length of @buf
- * @zone_shift: logarithm base 2 of the number of blocks in a zone
- * @seq_zones_bitmap: bitmap of sequential zones to set
- *
- * Parse reported zone descriptors in @buf to identify sequential zones and
- * set the reported zone bit in @seq_zones_bitmap accordingly.
- * Since read-only and offline zones cannot be written, do not
- * mark them as sequential in the bitmap.
- * Return the LBA after the last zone reported.
- */
-static sector_t sd_zbc_get_seq_zones(struct scsi_disk *sdkp, unsigned char *buf,
-				     unsigned int buflen, u32 zone_shift,
-				     unsigned long *seq_zones_bitmap)
-{
-	sector_t lba, next_lba = sdkp->capacity;
-	unsigned int buf_len, list_length;
-	unsigned char *rec;
-	u8 type, cond;
-
-	list_length = get_unaligned_be32(&buf[0]) + 64;
-	buf_len = min(list_length, buflen);
-	rec = buf + 64;
-
-	while (rec < buf + buf_len) {
-		type = rec[0] & 0x0f;
-		cond = (rec[1] >> 4) & 0xf;
-		lba = get_unaligned_be64(&rec[16]);
-		if (type != ZBC_ZONE_TYPE_CONV &&
-		    cond != ZBC_ZONE_COND_READONLY &&
-		    cond != ZBC_ZONE_COND_OFFLINE)
-			set_bit(lba >> zone_shift, seq_zones_bitmap);
-		next_lba = lba + get_unaligned_be64(&rec[8]);
-		rec += 64;
-	}
-
-	return next_lba;
-}
-
-/**
- * sd_zbc_setup_seq_zones_bitmap - Initialize a seq zone bitmap.
- * @sdkp: target disk
- * @zone_shift: logarithm base 2 of the number of blocks in a zone
- * @nr_zones: number of zones to set up a seq zone bitmap for
- *
- * Allocate a zone bitmap and initialize it by identifying sequential zones.
- */
-static unsigned long *
-sd_zbc_setup_seq_zones_bitmap(struct scsi_disk *sdkp, u32 zone_shift,
-			      u32 nr_zones)
-{
-	struct request_queue *q = sdkp->disk->queue;
-	unsigned long *seq_zones_bitmap;
-	sector_t lba = 0;
-	unsigned char *buf;
-	int ret = -ENOMEM;
-
-	seq_zones_bitmap = sd_zbc_alloc_zone_bitmap(nr_zones, q->node);
-	if (!seq_zones_bitmap)
-		return ERR_PTR(-ENOMEM);
-
-	buf = kmalloc(SD_ZBC_BUF_SIZE, GFP_KERNEL);
-	if (!buf)
-		goto out;
-
-	while (lba < sdkp->capacity) {
-		ret = sd_zbc_report_zones(sdkp, buf, SD_ZBC_BUF_SIZE, lba);
-		if (ret)
-			goto out;
-		lba = sd_zbc_get_seq_zones(sdkp, buf, SD_ZBC_BUF_SIZE,
-					   zone_shift, seq_zones_bitmap);
-	}
-
-	if (lba != sdkp->capacity) {
-		/* Something went wrong */
-		ret = -EIO;
-	}
-
-out:
-	kfree(buf);
-	if (ret) {
-		kfree(seq_zones_bitmap);
-		return ERR_PTR(ret);
-	}
-	return seq_zones_bitmap;
-}
-
-static void sd_zbc_cleanup(struct scsi_disk *sdkp)
-{
-	struct request_queue *q = sdkp->disk->queue;
-
-	kfree(q->seq_zones_bitmap);
-	q->seq_zones_bitmap = NULL;
-
-	kfree(q->seq_zones_wlock);
-	q->seq_zones_wlock = NULL;
-
-	q->nr_zones = 0;
-}
-
-static int sd_zbc_setup(struct scsi_disk *sdkp, u32 zone_blocks)
-{
-	struct request_queue *q = sdkp->disk->queue;
-	u32 zone_shift = ilog2(zone_blocks);
-	u32 nr_zones;
-	int ret;
-
-	/* chunk_sectors indicates the zone size */
-	blk_queue_chunk_sectors(q,
-			logical_to_sectors(sdkp->device, zone_blocks));
-	nr_zones = round_up(sdkp->capacity, zone_blocks) >> zone_shift;
-
-	/*
-	 * Initialize the device request queue information if the number
-	 * of zones changed.
-	 */
-	if (nr_zones != sdkp->nr_zones || nr_zones != q->nr_zones) {
-		unsigned long *seq_zones_wlock = NULL, *seq_zones_bitmap = NULL;
-		size_t zone_bitmap_size;
-
-		if (nr_zones) {
-			seq_zones_wlock = sd_zbc_alloc_zone_bitmap(nr_zones,
-								   q->node);
-			if (!seq_zones_wlock) {
-				ret = -ENOMEM;
-				goto err;
-			}
-
-			seq_zones_bitmap = sd_zbc_setup_seq_zones_bitmap(sdkp,
-							zone_shift, nr_zones);
-			if (IS_ERR(seq_zones_bitmap)) {
-				ret = PTR_ERR(seq_zones_bitmap);
-				kfree(seq_zones_wlock);
-				goto err;
-			}
-		}
-		zone_bitmap_size = BITS_TO_LONGS(nr_zones) *
-			sizeof(unsigned long);
-		blk_mq_freeze_queue(q);
-		if (q->nr_zones != nr_zones) {
-			/* READ16/WRITE16 is mandatory for ZBC disks */
-			sdkp->device->use_16_for_rw = 1;
-			sdkp->device->use_10_for_rw = 0;
-
-			sdkp->zone_blocks = zone_blocks;
-			sdkp->zone_shift = zone_shift;
-			sdkp->nr_zones = nr_zones;
-			q->nr_zones = nr_zones;
-			swap(q->seq_zones_wlock, seq_zones_wlock);
-			swap(q->seq_zones_bitmap, seq_zones_bitmap);
-		} else if (memcmp(q->seq_zones_bitmap, seq_zones_bitmap,
-				  zone_bitmap_size) != 0) {
-			memcpy(q->seq_zones_bitmap, seq_zones_bitmap,
-			       zone_bitmap_size);
-		}
-		blk_mq_unfreeze_queue(q);
-		kfree(seq_zones_wlock);
-		kfree(seq_zones_bitmap);
-	}
-
-	return 0;
-
-err:
-	sd_zbc_cleanup(sdkp);
-	return ret;
-}
-
 int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 {
-	int64_t zone_blocks;
+	struct gendisk *disk = sdkp->disk;
+	unsigned int nr_zones;
+	u32 zone_blocks;
 	int ret;
 
 	if (!sd_is_zoned(sdkp))
@@ -675,26 +439,8 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 		 */
 		return 0;
 
-	/* Get zoned block device characteristics */
-	ret = sd_zbc_read_zoned_characteristics(sdkp, buf);
-	if (ret)
-		goto err;
-
-	/*
-	 * Check for unconstrained reads: host-managed devices with
-	 * constrained reads (drives failing read after write pointer)
-	 * are not supported.
-	 */
-	if (!sdkp->urswrz) {
-		if (sdkp->first_scan)
-			sd_printk(KERN_NOTICE, sdkp,
-			  "constrained reads devices are not supported\n");
-		ret = -ENODEV;
-		goto err;
-	}
-
-	/* Check capacity */
-	ret = sd_zbc_check_capacity(sdkp, buf);
+	/* Check zoned block device characteristics (unconstrained reads) */
+	ret = sd_zbc_check_zoned_characteristics(sdkp, buf);
 	if (ret)
 		goto err;
 
@@ -702,33 +448,44 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf)
 	 * Check zone size: only devices with a constant zone size (except
 	 * an eventual last runt zone) that is a power of 2 are supported.
 	 */
-	zone_blocks = sd_zbc_check_zone_size(sdkp);
-	ret = -EFBIG;
-	if (zone_blocks != (u32)zone_blocks)
-		goto err;
-	ret = zone_blocks;
-	if (ret < 0)
+	ret = sd_zbc_check_zones(sdkp, &zone_blocks);
+	if (ret != 0)
 		goto err;
 
 	/* The drive satisfies the kernel restrictions: set it up */
-	ret = sd_zbc_setup(sdkp, zone_blocks);
-	if (ret)
-		goto err;
+	blk_queue_chunk_sectors(sdkp->disk->queue,
+			logical_to_sectors(sdkp->device, zone_blocks));
+	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);
+
+	/* READ16/WRITE16 is mandatory for ZBC disks */
+	sdkp->device->use_16_for_rw = 1;
+	sdkp->device->use_10_for_rw = 0;
+
+	/*
+	 * If something changed, revalidate the disk zone bitmaps once we have
+	 * the capacity, that is on the second revalidate execution during disk
+	 * scan and always during normal revalidate.
+	 */
+	if (sdkp->first_scan)
+		return 0;
+	if (sdkp->zone_blocks != zone_blocks ||
+	    sdkp->nr_zones != nr_zones ||
+	    disk->queue->nr_zones != nr_zones) {
+		ret = blk_revalidate_disk_zones(disk);
+		if (ret != 0)
+			goto err;
+		sdkp->zone_blocks = zone_blocks;
+		sdkp->nr_zones = nr_zones;
+	}
 
 	return 0;
 
 err:
 	sdkp->capacity = 0;
-	sd_zbc_cleanup(sdkp);
 
 	return ret;
 }
 
-void sd_zbc_remove(struct scsi_disk *sdkp)
-{
-	sd_zbc_cleanup(sdkp);
-}
-
 void sd_zbc_print_zones(struct scsi_disk *sdkp)
 {
 	if (!sd_is_zoned(sdkp) || !sdkp->capacity)

+ 0 - 2
include/linux/blk_types.h

@@ -283,8 +283,6 @@ enum req_opf {
 	REQ_OP_FLUSH		= 2,
 	/* discard sectors */
 	REQ_OP_DISCARD		= 3,
-	/* get zone information */
-	REQ_OP_ZONE_REPORT	= 4,
 	/* securely erase sectors */
 	REQ_OP_SECURE_ERASE	= 5,
 	/* seset a zone write pointer */

+ 25 - 5
include/linux/blkdev.h

@@ -396,16 +396,13 @@ struct queue_limits {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
-struct blk_zone_report_hdr {
-	unsigned int	nr_zones;
-	u8		padding[60];
-};
-
+extern unsigned int blkdev_nr_zones(struct block_device *bdev);
 extern int blkdev_report_zones(struct block_device *bdev,
 			       sector_t sector, struct blk_zone *zones,
 			       unsigned int *nr_zones, gfp_t gfp_mask);
 extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
 			      sector_t nr_sectors, gfp_t gfp_mask);
+extern int blk_revalidate_disk_zones(struct gendisk *disk);
 
 extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 				     unsigned int cmd, unsigned long arg);
@@ -414,6 +411,16 @@ extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
+static inline unsigned int blkdev_nr_zones(struct block_device *bdev)
+{
+	return 0;
+}
+
+static inline int blk_revalidate_disk_zones(struct gendisk *disk)
+{
+	return 0;
+}
+
 static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 					    fmode_t mode, unsigned int cmd,
 					    unsigned long arg)
@@ -806,6 +813,11 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+{
+	return blk_queue_is_zoned(q) ? q->nr_zones : 0;
+}
+
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
@@ -821,6 +833,11 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return false;
 	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
 }
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
+{
+	return 0;
+}
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
@@ -1852,6 +1869,9 @@ struct block_device_operations {
 	int (*getgeo)(struct block_device *, struct hd_geometry *);
 	/* this callback is with swap_lock and sometimes page table lock held */
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
+	int (*report_zones)(struct gendisk *, sector_t sector,
+			    struct blk_zone *zones, unsigned int *nr_zones,
+			    gfp_t gfp_mask);
 	struct module *owner;
 	const struct pr_ops *pr_ops;
 };

+ 10 - 2
include/linux/device-mapper.h

@@ -92,6 +92,11 @@ typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv,
 
 typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev);
 
+typedef int (*dm_report_zones_fn) (struct dm_target *ti, sector_t sector,
+				   struct blk_zone *zones,
+				   unsigned int *nr_zones,
+				   gfp_t gfp_mask);
+
 /*
  * These iteration functions are typically used to check (and combine)
  * properties of underlying devices.
@@ -180,6 +185,9 @@ struct target_type {
 	dm_status_fn status;
 	dm_message_fn message;
 	dm_prepare_ioctl_fn prepare_ioctl;
+#ifdef CONFIG_BLK_DEV_ZONED
+	dm_report_zones_fn report_zones;
+#endif
 	dm_busy_fn busy;
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
@@ -420,8 +428,8 @@ struct gendisk *dm_disk(struct mapped_device *md);
 int dm_suspended(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors);
-void dm_remap_zone_report(struct dm_target *ti, struct bio *bio,
-			  sector_t start);
+void dm_remap_zone_report(struct dm_target *ti, sector_t start,
+			  struct blk_zone *zones, unsigned int *nr_zones);
 union map_info *dm_get_rq_mapinfo(struct request *rq);
 
 struct queue_limits *dm_get_queue_limits(struct mapped_device *md);

+ 0 - 1
include/trace/events/f2fs.h

@@ -82,7 +82,6 @@ TRACE_DEFINE_ENUM(CP_TRIMMED);
 		{ REQ_OP_WRITE,			"WRITE" },		\
 		{ REQ_OP_FLUSH,			"FLUSH" },		\
 		{ REQ_OP_DISCARD,		"DISCARD" },		\
-		{ REQ_OP_ZONE_REPORT,		"ZONE_REPORT" },	\
 		{ REQ_OP_SECURE_ERASE,		"SECURE_ERASE" },	\
 		{ REQ_OP_ZONE_RESET,		"ZONE_RESET" },		\
 		{ REQ_OP_WRITE_SAME,		"WRITE_SAME" },		\

+ 3 - 0
include/uapi/linux/blkzoned.h

@@ -137,8 +137,11 @@ struct blk_zone_range {
  *                 sector specified in the report request structure.
  * @BLKRESETZONE: Reset the write pointer of the zones in the specified
  *                sector range. The sector range must be zone aligned.
+ * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors.
  */
 #define BLKREPORTZONE	_IOWR(0x12, 130, struct blk_zone_report)
 #define BLKRESETZONE	_IOW(0x12, 131, struct blk_zone_range)
+#define BLKGETZONESZ	_IOW(0x12, 132, __u32)
+#define BLKGETNRZONES	_IOW(0x12, 133, __u32)
 
 #endif /* _UAPI_BLKZONED_H */