Merge tag 'for-5.5/zoned-20191122' of git://git.kernel.dk/linux-block

Pull zoned block device update from Jens Axboe:
 "Enhancements and improvements to the zoned device support"

* tag 'for-5.5/zoned-20191122' of git://git.kernel.dk/linux-block:
  scsi: sd_zbc: Remove set but not used variable 'buflen'
  block: rework zone reporting
  scsi: sd_zbc: Cleanup sd_zbc_alloc_report_buffer()
  null_blk: Add zone_nr_conv to features
  null_blk: clean up report zones
  null_blk: clean up the block device operations
  block: Remove partition support for zoned block devices
  block: Simplify report zones execution
  block: cleanup the !zoned case in blk_revalidate_disk_zones
  block: Enhance blk_revalidate_disk_zones()

3 files changed, 156 insertions, 280 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index f0d82227a2fc..a1e228752083 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -851,11 +851,7 @@ static inline int blk_partition_remap(struct bio *bio)
 	if (unlikely(bio_check_ro(bio, p)))
 		goto out;
 
-	/*
-	 * Zone management bios do not have a sector count but they do have
-	 * a start sector filled out and need to be remapped.
-	 */
-	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) {
+	if (bio_sectors(bio)) {
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 481eaf7d04d4..6fad6f3f6980 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -93,112 +93,43 @@ unsigned int blkdev_nr_zones(struct block_device *bdev)
 	if (!blk_queue_is_zoned(q))
 		return 0;
 
-	return __blkdev_nr_zones(q, bdev->bd_part->nr_sects);
+	return __blkdev_nr_zones(q, get_capacity(bdev->bd_disk));
 }
 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);
-
-	if (rep->start < offset)
-		return false;
-
-	rep->start -= offset;
-	if (rep->start + rep->len > bdev->bd_part->nr_sects)
-		return false;
-
-	if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL)
-		rep->wp = rep->start + rep->len;
-	else
-		rep->wp -= offset;
-	return true;
-}
-
-static int blk_report_zones(struct gendisk *disk, sector_t sector,
-			    struct blk_zone *zones, unsigned int *nr_zones)
-{
-	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);
-		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
  * @sector:	Sector from which to report zones
- * @zones:	Array of zone structures where to return the zones information
- * @nr_zones:	Number of zone structures in the zone array
+ * @nr_zones:	Maximum number of zones to report
+ * @cb:		Callback function called for each reported zone
+ * @data:	Private data for the callback
  *
  * Description:
- *    Get zone information starting from the zone containing @sector.
- *    The number of zone information reported may be less than the number
- *    requested by @nr_zones. The number of zones actually reported is
- *    returned in @nr_zones.
- *    The caller must use memalloc_noXX_save/restore() calls to control
- *    memory allocations done within this function (zone array and command
- *    buffer allocation by the device driver).
+ *    Get zone information starting from the zone containing @sector for at most
+ *    @nr_zones, and call @cb for each zone reported by the device.
+ *    To report all zones in a device starting from @sector, the BLK_ALL_ZONES
+ *    constant can be passed to @nr_zones.
+ *    Returns the number of zones reported by the device, or a negative errno
+ *    value in case of failure.
+ *
+ *    Note: The caller must use memalloc_noXX_save/restore() calls to control
+ *    memory allocations done within this function.
  */
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			struct blk_zone *zones, unsigned int *nr_zones)
+			unsigned int nr_zones, report_zones_cb cb, void *data)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-	unsigned int i, nrz;
-	int ret;
+	struct gendisk *disk = bdev->bd_disk;
+	sector_t capacity = get_capacity(disk);
 
-	if (!blk_queue_is_zoned(q))
+	if (!blk_queue_is_zoned(bdev_get_queue(bdev)) ||
+	    WARN_ON_ONCE(!disk->fops->report_zones))
 		return -EOPNOTSUPP;
 
-	/*
-	 * 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 (!*nr_zones || sector >= bdev->bd_part->nr_sects) {
-		*nr_zones = 0;
+	if (!nr_zones || sector >= capacity)
 		return 0;
-	}
-
-	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);
-	if (ret)
-		return ret;
-
-	for (i = 0; i < nrz; i++) {
-		if (!blkdev_report_zone(bdev, zones))
-			break;
-		zones++;
-	}
-
-	*nr_zones = i;
 
-	return 0;
+	return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
@@ -209,15 +140,11 @@ static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
 	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
 		return false;
 
-	if (sector || nr_sectors != part_nr_sects_read(bdev->bd_part))
-		return false;
 	/*
-	 * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
-	 * the entire disk, that is, if the blocks device start offset is 0 and
-	 * its capacity is the same as the entire disk.
+	 * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors
+	 * of the applicable zone range is the entire disk.
 	 */
-	return get_start_sect(bdev) == 0 &&
-	       part_nr_sects_read(bdev->bd_part) == get_capacity(bdev->bd_disk);
+	return !sector && nr_sectors == get_capacity(bdev->bd_disk);
 }
 
 /**
@@ -242,6 +169,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	sector_t capacity = get_capacity(bdev->bd_disk);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
 	int ret;
@@ -255,7 +183,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 	if (!op_is_zone_mgmt(op))
 		return -EOPNOTSUPP;
 
-	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
+	if (!nr_sectors || end_sector > capacity)
 		/* Out of range */
 		return -EINVAL;
 
@@ -263,8 +191,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 	if (sector & (zone_sectors - 1))
 		return -EINVAL;
 
-	if ((nr_sectors & (zone_sectors - 1)) &&
-	    end_sector != bdev->bd_part->nr_sects)
+	if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
 		return -EINVAL;
 
 	while (sector < end_sector) {
@@ -296,6 +223,20 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
 }
 EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
 
+struct zone_report_args {
+	struct blk_zone __user *zones;
+};
+
+static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
+				    void *data)
+{
+	struct zone_report_args *args = data;
+
+	if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone)))
+		return -EFAULT;
+	return 0;
+}
+
 /*
  * BLKREPORTZONE ioctl processing.
  * Called from blkdev_ioctl.
@@ -304,9 +245,9 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 			      unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
+	struct zone_report_args args;
 	struct request_queue *q;
 	struct blk_zone_report rep;
-	struct blk_zone *zones;
 	int ret;
 
 	if (!argp)
@@ -328,32 +269,16 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (!rep.nr_zones)
 		return -EINVAL;
 
-	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);
-	if (!zones)
-		return -ENOMEM;
-
-	ret = blkdev_report_zones(bdev, rep.sector, zones, &rep.nr_zones);
-	if (ret)
-		goto out;
-
-	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	if (rep.nr_zones) {
-		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
-				 sizeof(struct blk_zone) * rep.nr_zones))
-			ret = -EFAULT;
-	}
-
- out:
-	kvfree(zones);
+	args.zones = argp + sizeof(struct blk_zone_report);
+	ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones,
+				  blkdev_copy_zone_to_user, &args);
+	if (ret < 0)
+		return ret;
 
-	return ret;
+	rep.nr_zones = ret;
+	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
+		return -EFAULT;
+	return 0;
 }
 
 /*
@@ -415,37 +340,99 @@ static inline unsigned long *blk_alloc_zone_bitmap(int node,
 			    GFP_NOIO, node);
 }
 
+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;
+}
+
+struct blk_revalidate_zone_args {
+	struct gendisk	*disk;
+	unsigned long	*seq_zones_bitmap;
+	unsigned long	*seq_zones_wlock;
+	sector_t	sector;
+};
+
 /*
- * Allocate an array of struct blk_zone to get nr_zones zone information.
- * The allocated array may be smaller than nr_zones.
+ * Helper function to check the validity of zones of a zoned block device.
  */
-static struct blk_zone *blk_alloc_zones(unsigned int *nr_zones)
+static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
+				  void *data)
 {
-	struct blk_zone *zones;
-	size_t nrz = min(*nr_zones, BLK_ZONED_REPORT_MAX_ZONES);
+	struct blk_revalidate_zone_args *args = data;
+	struct gendisk *disk = args->disk;
+	struct request_queue *q = disk->queue;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
+	sector_t capacity = get_capacity(disk);
 
 	/*
-	 * GFP_KERNEL here is meaningless as the caller task context has
-	 * the PF_MEMALLOC_NOIO flag set in blk_revalidate_disk_zones()
-	 * with memalloc_noio_save().
+	 * All zones must have the same size, with the exception on an eventual
+	 * smaller last zone.
 	 */
-	zones = kvcalloc(nrz, sizeof(struct blk_zone), GFP_KERNEL);
-	if (!zones) {
-		*nr_zones = 0;
-		return NULL;
+	if (zone->start + zone_sectors < capacity &&
+	    zone->len != zone_sectors) {
+		pr_warn("%s: Invalid zoned device with non constant zone size\n",
+			disk->disk_name);
+		return false;
+	}
+
+	if (zone->start + zone->len >= capacity &&
+	    zone->len > zone_sectors) {
+		pr_warn("%s: Invalid zoned device with larger last zone size\n",
+			disk->disk_name);
+		return -ENODEV;
 	}
 
-	*nr_zones = nrz;
+	/* Check for holes in the zone report */
+	if (zone->start != args->sector) {
+		pr_warn("%s: Zone gap at sectors %llu..%llu\n",
+			disk->disk_name, args->sector, zone->start);
+		return -ENODEV;
+	}
+
+	/* Check zone type */
+	switch (zone->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		break;
+	default:
+		pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
+			disk->disk_name, (int)zone->type, zone->start);
+		return -ENODEV;
+	}
+
+	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL)
+		set_bit(idx, args->seq_zones_bitmap);
 
-	return zones;
+	args->sector += zone->len;
+	return 0;
 }
 
-void blk_queue_free_zone_bitmaps(struct request_queue *q)
+static int blk_update_zone_info(struct gendisk *disk, unsigned int nr_zones,
+				struct blk_revalidate_zone_args *args)
 {
-	kfree(q->seq_zones_bitmap);
-	q->seq_zones_bitmap = NULL;
-	kfree(q->seq_zones_wlock);
-	q->seq_zones_wlock = NULL;
+	/*
+	 * Ensure that all memory allocations in this context are done as
+	 * if GFP_NOIO was specified.
+	 */
+	unsigned int noio_flag = memalloc_noio_save();
+	struct request_queue *q = disk->queue;
+	int ret;
+
+	args->seq_zones_wlock = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!args->seq_zones_wlock)
+		return -ENOMEM;
+	args->seq_zones_bitmap = blk_alloc_zone_bitmap(q->node, nr_zones);
+	if (!args->seq_zones_bitmap)
+		return -ENOMEM;
+
+	ret = disk->fops->report_zones(disk, 0, nr_zones,
+				       blk_revalidate_zone_cb, args);
+	memalloc_noio_restore(noio_flag);
+	return ret;
 }
 
 /**
@@ -461,13 +448,12 @@ 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;
-	unsigned int noio_flag;
-	sector_t sector = 0;
+	struct blk_revalidate_zone_args args = { .disk = disk };
 	int ret = 0;
 
+	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
+		return -EIO;
+
 	/*
 	 * 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.
@@ -477,78 +463,28 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 		return 0;
 	}
 
-	/*
-	 * Ensure that all memory allocations in this context are done as
-	 * if GFP_NOIO was specified.
-	 */
-	noio_flag = memalloc_noio_save();
+	if (nr_zones)
+		ret = blk_update_zone_info(disk, nr_zones, &args);
 
-	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(&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);
-		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:
-	memalloc_noio_restore(noio_flag);
-
-	kvfree(zones);
-	kfree(seq_zones_wlock);
-	kfree(seq_zones_bitmap);
-
-	if (ret) {
+	if (ret >= 0) {
+		q->nr_zones = nr_zones;
+		swap(q->seq_zones_wlock, args.seq_zones_wlock);
+		swap(q->seq_zones_bitmap, args.seq_zones_bitmap);
+		ret = 0;
+	} else {
 		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);
 	}
+	blk_mq_unfreeze_queue(q);
 
+	kfree(args.seq_zones_wlock);
+	kfree(args.seq_zones_bitmap);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3db8b73a96b1..3084d4cba5c7 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -462,56 +462,6 @@ static int drop_partitions(struct gendisk *disk, struct block_device *bdev)
 	return 0;
 }
 
-static bool part_zone_aligned(struct gendisk *disk,
-			      struct block_device *bdev,
-			      sector_t from, sector_t size)
-{
-	unsigned int zone_sectors = bdev_zone_sectors(bdev);
-
-	/*
-	 * If this function is called, then the disk is a zoned block device
-	 * (host-aware or host-managed). This can be detected even if the
-	 * zoned block device support is disabled (CONFIG_BLK_DEV_ZONED not
-	 * set). In this case, however, only host-aware devices will be seen
-	 * as a block device is not created for host-managed devices. Without
-	 * zoned block device support, host-aware drives can still be used as
-	 * regular block devices (no zone operation) and their zone size will
-	 * be reported as 0. Allow this case.
-	 */
-	if (!zone_sectors)
-		return true;
-
-	/*
-	 * Check partition start and size alignement. If the drive has a
-	 * smaller last runt zone, ignore it and allow the partition to
-	 * use it. Check the zone size too: it should be a power of 2 number
-	 * of sectors.
-	 */
-	if (WARN_ON_ONCE(!is_power_of_2(zone_sectors))) {
-		u32 rem;
-
-		div_u64_rem(from, zone_sectors, &rem);
-		if (rem)
-			return false;
-		if ((from + size) < get_capacity(disk)) {
-			div_u64_rem(size, zone_sectors, &rem);
-			if (rem)
-				return false;
-		}
-
-	} else {
-
-		if (from & (zone_sectors - 1))
-			return false;
-		if ((from + size) < get_capacity(disk) &&
-		    (size & (zone_sectors - 1)))
-			return false;
-
-	}
-
-	return true;
-}
-
 int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 {
 	struct parsed_partitions *state = NULL;
@@ -547,6 +497,14 @@ rescan:
 		}
 		return -EIO;
 	}
+
+	/* Partitions are not supported on zoned block devices */
+	if (bdev_is_zoned(bdev)) {
+		pr_warn("%s: ignoring partition table on zoned block device\n",
+			disk->disk_name);
+		goto out;
+	}
+
 	/*
 	 * If any partition code tried to read beyond EOD, try
 	 * unlocking native capacity even if partition table is
@@ -610,21 +568,6 @@ rescan:
 			}
 		}
 
-		/*
-		 * On a zoned block device, partitions should be aligned on the
-		 * device zone size (i.e. zone boundary crossing not allowed).
-		 * Otherwise, resetting the write pointer of the last zone of
-		 * one partition may impact the following partition.
-		 */
-		if (bdev_is_zoned(bdev) &&
-		    !part_zone_aligned(disk, bdev, from, size)) {
-			printk(KERN_WARNING
-			       "%s: p%d start %llu+%llu is not zone aligned\n",
-			       disk->disk_name, p, (unsigned long long) from,
-			       (unsigned long long) size);
-			continue;
-		}
-
 		part = add_partition(disk, p, from, size,
 				     state->parts[p].flags,
 				     &state->parts[p].info);
@@ -638,6 +581,7 @@ rescan:
 			md_autodetect_dev(part_to_dev(part)->devt);
 #endif
 	}
+out:
 	free_partitions(state);
 	return 0;
 }