1 files changed, 226 insertions, 255 deletions

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 6c503824ba3f..05741c6f618b 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -70,159 +70,98 @@ 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)
-{
-	sector_t 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
+ * @disk:	Target gendisk
  *
- * Description:
- *    Return the total number of zones of a zoned block device.
- *    For a regular block device, the number of zones is always 0.
+ * Return the total number of zones of a zoned block device.  For a block
+ * device without zone capabilities, the number of zones is always 0.
  */
-unsigned int blkdev_nr_zones(struct block_device *bdev)
+unsigned int blkdev_nr_zones(struct gendisk *disk)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
+	sector_t zone_sectors = blk_queue_zone_sectors(disk->queue);
 
-	if (!blk_queue_is_zoned(q))
+	if (!blk_queue_is_zoned(disk->queue))
 		return 0;
-
-	return __blkdev_nr_zones(q, bdev->bd_part->nr_sects);
+	return (get_capacity(disk) + zone_sectors - 1) >> ilog2(zone_sectors);
 }
 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;
-
-	if (!blk_queue_is_zoned(q))
-		return -EOPNOTSUPP;
+	struct gendisk *disk = bdev->bd_disk;
+	sector_t capacity = get_capacity(disk);
 
-	/*
-	 * 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))
+	if (!blk_queue_is_zoned(bdev_get_queue(bdev)) ||
+	    WARN_ON_ONCE(!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++;
-	}
+	return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
+}
+EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-	*nr_zones = i;
+static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
+						sector_t sector,
+						sector_t nr_sectors)
+{
+	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
+		return false;
 
-	return 0;
+	/*
+	 * REQ_OP_ZONE_RESET_ALL can be executed only if the number of sectors
+	 * of the applicable zone range is the entire disk.
+	 */
+	return !sector && nr_sectors == get_capacity(bdev->bd_disk);
 }
-EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
 /**
- * blkdev_reset_zones - Reset zones write pointer
+ * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
  * @bdev:	Target block device
- * @sector:	Start sector of the first zone to reset
- * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @op:		Operation to be performed on the zones
+ * @sector:	Start sector of the first zone to operate on
+ * @nr_sectors:	Number of sectors, should be at least the length of one zone and
+ *		must be zone size aligned.
  * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
- *    Reset the write pointer of the zones contained in the range
+ *    Perform the specified operation on the range of zones specified by
  *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
  *    is valid, but the specified range should not contain conventional zones.
+ *    The operation to execute on each zone can be a zone reset, open, close
+ *    or finish request.
  */
-int blkdev_reset_zones(struct block_device *bdev,
-		       sector_t sector, sector_t nr_sectors,
-		       gfp_t gfp_mask)
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+		     sector_t sector, sector_t nr_sectors,
+		     gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t zone_sectors;
+	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;
-	struct blk_plug plug;
 	int ret;
 
 	if (!blk_queue_is_zoned(q))
@@ -231,42 +170,62 @@ int blkdev_reset_zones(struct block_device *bdev,
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
-	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
+	if (!op_is_zone_mgmt(op))
+		return -EOPNOTSUPP;
+
+	if (!nr_sectors || end_sector > capacity)
 		/* Out of range */
 		return -EINVAL;
 
 	/* Check alignment (handle eventual smaller last zone) */
-	zone_sectors = blk_queue_zone_sectors(q);
 	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;
 
-	blk_start_plug(&plug);
 	while (sector < end_sector) {
-
 		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);
 
+		/*
+		 * Special case for the zone reset operation that reset all
+		 * zones, this is useful for applications like mkfs.
+		 */
+		if (op == REQ_OP_ZONE_RESET &&
+		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
+			bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
+			break;
+		}
+
+		bio->bi_opf = op | REQ_SYNC;
+		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
 		/* This may take a while, so be nice to others */
 		cond_resched();
-
 	}
 
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
-	blk_finish_plug(&plug);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+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.
@@ -276,9 +235,9 @@ 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)
@@ -300,44 +259,29 @@ 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;
 }
 
 /*
- * BLKRESETZONE ioctl processing.
+ * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
  * Called from blkdev_ioctl.
  */
-int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long arg)
+int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+			   unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct request_queue *q;
 	struct blk_zone_range zrange;
+	enum req_opf op;
 
 	if (!argp)
 		return -EINVAL;
@@ -358,8 +302,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
 		return -EFAULT;
 
-	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
-				  GFP_KERNEL);
+	switch (cmd) {
+	case BLKRESETZONE:
+		op = REQ_OP_ZONE_RESET;
+		break;
+	case BLKOPENZONE:
+		op = REQ_OP_ZONE_OPEN;
+		break;
+	case BLKCLOSEZONE:
+		op = REQ_OP_ZONE_CLOSE;
+		break;
+	case BLKFINISHZONE:
+		op = REQ_OP_ZONE_FINISH;
+		break;
+	default:
+		return -ENOTTY;
+	}
+
+	return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
+				GFP_KERNEL);
 }
 
 static inline unsigned long *blk_alloc_zone_bitmap(int node,
@@ -369,37 +330,96 @@ 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->conv_zones_bitmap);
+	q->conv_zones_bitmap = NULL;
+	kfree(q->seq_zones_wlock);
+	q->seq_zones_wlock = NULL;
+}
+
+struct blk_revalidate_zone_args {
+	struct gendisk	*disk;
+	unsigned long	*conv_zones_bitmap;
+	unsigned long	*seq_zones_wlock;
+	unsigned int	nr_zones;
+	sector_t	zone_sectors;
+	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 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 == 0) {
+		if (zone->len == 0 || !is_power_of_2(zone->len)) {
+			pr_warn("%s: Invalid zoned device with non power of two zone size (%llu)\n",
+				disk->disk_name, zone->len);
+			return -ENODEV;
+		}
+
+		args->zone_sectors = zone->len;
+		args->nr_zones = (capacity + zone->len - 1) >> ilog2(zone->len);
+	} else if (zone->start + args->zone_sectors < capacity) {
+		if (zone->len != args->zone_sectors) {
+			pr_warn("%s: Invalid zoned device with non constant zone size\n",
+				disk->disk_name);
+			return -ENODEV;
+		}
+	} else {
+		if (zone->len > args->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;
+	}
 
-	return zones;
-}
+	/* Check zone type */
+	switch (zone->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+		if (!args->conv_zones_bitmap) {
+			args->conv_zones_bitmap =
+				blk_alloc_zone_bitmap(q->node, args->nr_zones);
+			if (!args->conv_zones_bitmap)
+				return -ENOMEM;
+		}
+		set_bit(idx, args->conv_zones_bitmap);
+		break;
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
+		if (!args->seq_zones_wlock) {
+			args->seq_zones_wlock =
+				blk_alloc_zone_bitmap(q->node, args->nr_zones);
+			if (!args->seq_zones_wlock)
+				return -ENOMEM;
+		}
+		break;
+	default:
+		pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
+			disk->disk_name, (int)zone->type, zone->start);
+		return -ENODEV;
+	}
 
-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;
+	args->sector += zone->len;
+	return 0;
 }
 
 /**
@@ -408,102 +428,53 @@ void blk_queue_free_zone_bitmaps(struct request_queue *q)
  *
  * 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.
+ * within the disk ->revalidate method for blk-mq based drivers.  For BIO based
+ * drivers only q->nr_zones needs to be updated so that the sysfs exposed value
+ * is correct.
  */
 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;
+	struct blk_revalidate_zone_args args = {
+		.disk		= disk,
+	};
 	unsigned int noio_flag;
-	sector_t sector = 0;
-	int ret = 0;
+	int ret;
 
-	/*
-	 * 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_mq(q)) {
-		q->nr_zones = nr_zones;
-		return 0;
-	}
+	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
+		return -EIO;
+	if (WARN_ON_ONCE(!queue_is_mq(q)))
+		return -EIO;
 
 	/*
-	 * Ensure that all memory allocations in this context are done as
-	 * if GFP_NOIO was specified.
+	 * Ensure that all memory allocations in this context are done as if
+	 * GFP_NOIO was specified.
 	 */
 	noio_flag = memalloc_noio_save();
+	ret = disk->fops->report_zones(disk, 0, UINT_MAX,
+				       blk_revalidate_zone_cb, &args);
+	memalloc_noio_restore(noio_flag);
 
-	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).
+	 * Install the new bitmaps and update nr_zones only once 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) {
+		blk_queue_chunk_sectors(q, args.zone_sectors);
+		q->nr_zones = args.nr_zones;
+		swap(q->seq_zones_wlock, args.seq_zones_wlock);
+		swap(q->conv_zones_bitmap, args.conv_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.conv_zones_bitmap);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
-