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

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;

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;

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);

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),

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);

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);

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);
 
-/*
- * 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.
+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.
  */
-static bool blkdev_report_zone(struct block_device *bdev,
-			       struct blk_zone *rep,
-			       struct blk_zone *zone)
+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 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)
 {
 	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;
+	/*
+	 * 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.
+	 */
+	if (WARN_ON_ONCE(!bdev->bd_disk->fops->report_zones))
+		return -EOPNOTSUPP;
 
-	if (sector > bdev->bd_part->nr_sects) {
+	if (!*nr_zones || 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.
-	 */
-	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);
-
-	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 (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;
+		return ret;
 
-	/*
-	 * 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)
+	for (i = 0; i < nrz; i++) {
+		if (!blkdev_report_zone(bdev, zones))
 			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);
-
-		if (n >= nr_rep || nz >= nrz)
-			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);
+

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 */

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:

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 |

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)

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;
 }

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)
-{
-	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);
-
-		nr_zones -= zones_to_cpy;
-		zno += zones_to_cpy;
-
-		if (!nr_zones)
-			break;
-	}
-}
-
-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)
 {
+	struct nullb *nullb = disk->private_data;
 	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;
+	unsigned int zno, nrz = 0;
 
-	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);
+	if (!dev->zoned)
+		/* Not a zoned null device */
+		return -EOPNOTSUPP;
 
-	return BLK_STS_OK;
+	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));
+	}
+
+	*nr_zones = nrz;
+
+	return 0;
 }
 
 void null_zone_write(struct nullb_cmd *cmd, sector_t sector,

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;

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);

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;
 	}

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,

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

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)

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;