[PATCH v8 02/11] block: allow blk-zoned devices to have non-power-of-2 zone size

[Pankaj Raghav]

Checking if a given sector is aligned to a zone is a common
operation that is performed for zoned devices. Add
bdev_is_zone_start helper to check for this instead of opencoding it
everywhere.

Convert the calculations on zone size to be generic instead of relying on
power_of_2 based logic in the block layer using the helpers wherever
possible.

The only hot path affected by this change for power_of_2 zoned devices
is in blk_check_zone_append() but bdev_is_zone_start() helper is
used to optimize the calculation for po2 zone sizes. Note that the append
path cannot be accessed by direct raw access to the block device but only
through a filesystem abstraction.

Finally, allow non power of 2 zoned devices provided that their zone
capacity and zone size are equal. The main motivation to allow non
power_of_2 zoned device is to remove the unmapped LBA between zcap and
zsze for devices that cannot have a power_of_2 zcap.

To make this work bdev_get_queue(), bdev_zone_sectors() and
bdev_is_zoned() are moved earlier without modifications.

Reviewed-by: Luis Chamberlain <mcgrof@xxxxxxxxxx>
Reviewed-by: Hannes Reinecke <hare@xxxxxxx>
Signed-off-by: Pankaj Raghav <p.raghav@xxxxxxxxxxx>
---
 block/blk-core.c       |  2 +-
 block/blk-zoned.c      | 24 +++++++++---
 include/linux/blkdev.h | 84 ++++++++++++++++++++++++++++++------------
 3 files changed, 79 insertions(+), 31 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 3d286a256d3d..1f7e9a90e198 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -570,7 +570,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_NOTSUPP;
 
 	/* The bio sector must point to the start of a sequential zone */
-	if (bio->bi_iter.bi_sector & (bdev_zone_sectors(bio->bi_bdev) - 1) ||
+	if (!bdev_is_zone_aligned(bio->bi_bdev, bio->bi_iter.bi_sector) ||
 	    !bio_zone_is_seq(bio))
 		return BLK_STS_IOERR;
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index dce9c95b4bcd..a01a231ad328 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -285,10 +285,10 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 		return -EINVAL;
 
 	/* Check alignment (handle eventual smaller last zone) */
-	if (sector & (zone_sectors - 1))
+	if (!bdev_is_zone_aligned(bdev, sector))
 		return -EINVAL;
 
-	if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
+	if (!bdev_is_zone_aligned(bdev, nr_sectors) && end_sector != capacity)
 		return -EINVAL;
 
 	/*
@@ -486,14 +486,26 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 	 * smaller last zone.
 	 */
 	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);
+		if (zone->len == 0) {
+			pr_warn("%s: Invalid zone size", disk->disk_name);
+			return -ENODEV;
+		}
+
+		/*
+		 * Non power-of-2 zone size support was added to remove the
+		 * gap between zone capacity and zone size. Though it is technically
+		 * possible to have gaps in a non power-of-2 device, Linux requires
+		 * the zone size to be equal to zone capacity for non power-of-2
+		 * zoned devices.
+		 */
+		if (!is_power_of_2(zone->len) && zone->capacity < zone->len) {
+			pr_warn("%s: Invalid zone capacity for non power of 2 zone size",
+				disk->disk_name);
 			return -ENODEV;
 		}
 
 		args->zone_sectors = zone->len;
-		args->nr_zones = (capacity + zone->len - 1) >> ilog2(zone->len);
+		args->nr_zones = div64_u64(capacity + zone->len - 1, 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",
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 85b832908f28..1be805223026 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -634,6 +634,11 @@ static inline bool queue_is_mq(struct request_queue *q)
 	return q->mq_ops;
 }
 
+static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
+{
+	return bdev->bd_queue;	/* this is never NULL */
+}
+
 #ifdef CONFIG_PM
 static inline enum rpm_status queue_rpm_status(struct request_queue *q)
 {
@@ -665,6 +670,25 @@ static inline bool blk_queue_is_zoned(struct request_queue *q)
 	}
 }
 
+static inline bool bdev_is_zoned(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return blk_queue_is_zoned(q);
+
+	return false;
+}
+
+static inline sector_t bdev_zone_sectors(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (!blk_queue_is_zoned(q))
+		return 0;
+	return q->limits.chunk_sectors;
+}
+
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
@@ -684,6 +708,30 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 	return div64_u64(sector, zone_sectors);
 }
 
+static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev,
+						   sector_t sec)
+{
+	sector_t zone_sectors = bdev_zone_sectors(bdev);
+	u64 remainder = 0;
+
+	if (!bdev_is_zoned(bdev))
+		return 0;
+
+	if (is_power_of_2(zone_sectors))
+		return sec & (zone_sectors - 1);
+
+	div64_u64_rem(sec, zone_sectors, &remainder);
+	return remainder;
+}
+
+static inline bool bdev_is_zone_aligned(struct block_device *bdev, sector_t sec)
+{
+	if (!bdev_is_zoned(bdev))
+		return false;
+
+	return bdev_offset_from_zone_start(bdev, sec) == 0;
+}
+
 static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 {
 	if (!blk_queue_is_zoned(disk->queue))
@@ -728,6 +776,18 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	return 0;
 }
+
+static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev,
+						   sector_t sec)
+{
+	return 0;
+}
+
+static inline bool bdev_is_zone_aligned(struct block_device *bdev, sector_t sec)
+{
+	return false;
+}
+
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
 	return 0;
@@ -891,11 +951,6 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags);
 int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob,
 			unsigned int flags);
 
-static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
-{
-	return bdev->bd_queue;	/* this is never NULL */
-}
-
 /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */
 const char *blk_zone_cond_str(enum blk_zone_cond zone_cond);
 
@@ -1295,25 +1350,6 @@ static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 	return BLK_ZONED_NONE;
 }
 
-static inline bool bdev_is_zoned(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return blk_queue_is_zoned(q);
-
-	return false;
-}
-
-static inline sector_t bdev_zone_sectors(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (!blk_queue_is_zoned(q))
-		return 0;
-	return q->limits.chunk_sectors;
-}
-
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
-- 
2.25.1