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.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)
+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,

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;
 

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
 };

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,

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 */

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 */

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;
 };

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);

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" },		\

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 */