Checking if a given sector is aligned to a zone is a common
operation that is performed for zoned devices. Add
blk_queue_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 blk_queue_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.
Reviewed-by: Luis Chamberlain <mcgrof@xxxxxxxxxx>
Reviewed-by: Hannes Reinecke <hare@xxxxxxx>
Signed-off-by: Pankaj Raghav <p.raghav@xxxxxxxxxxx>
---
block/blk-core.c | 3 +--
block/blk-zoned.c | 25 +++++++++++++++++++------
include/linux/blkdev.h | 33 +++++++++++++++++++++++++++++++++
3 files changed, 53 insertions(+), 8 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 06ff5bbfe..248b947e5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -629,8 +629,7 @@ 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 (pos & (blk_queue_zone_sectors(q) - 1) ||
- !blk_queue_zone_is_seq(q, pos))
+ if (!blk_queue_is_zone_start(q, pos) || !blk_queue_zone_is_seq(q, pos))
return BLK_STS_IOERR;
/*
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 8b0615287..7957eec04 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -288,10 +288,10 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
return -EINVAL;
/* Check alignment (handle eventual smaller last zone) */
- if (sector & (zone_sectors - 1))
+ if (!blk_queue_is_zone_start(q, sector))
return -EINVAL;
- if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
+ if (!blk_queue_is_zone_start(q, nr_sectors) && end_sector != capacity)
return -EINVAL;
/*
@@ -489,14 +489,27 @@ 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;
+ }
+
+ /*
+ * Don't allow zoned device with non power_of_2 zone size with
+ * zone capacity less than zone size.
+ */
+ 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);
+ /*
+ * Division is used to calculate nr_zones for both power_of_2
+ * and non power_of_2 zone sizes as it is not in the hot path.
+ */
+ 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 39017ae9d..3c106dba1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -692,6 +692,27 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
return div64_u64(sector, zone_sectors);
}
+static inline sector_t blk_queue_offset_from_zone_start(struct request_queue *q,
+ sector_t sec)
+{
+ sector_t zone_sectors = blk_queue_zone_sectors(q);
+ u64 remainder = 0;
+
+ if (!blk_queue_is_zoned(q))
+ return false;
+
+ if (is_power_of_2(zone_sectors))
+ return sec & (zone_sectors - 1);
+
+ div64_u64_rem(sec, zone_sectors, &remainder);
+ return remainder;
+}
+
+static inline bool blk_queue_is_zone_start(struct request_queue *q, sector_t sec)
+{
+ return blk_queue_offset_from_zone_start(q, sec) == 0;
+}
+
static inline bool blk_queue_zone_is_seq(struct request_queue *q,
sector_t sector)
{
@@ -738,6 +759,18 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
{
return 0;
}
+
+static inline sector_t blk_queue_offset_from_zone_start(struct request_queue *q,
+ sector_t sec)
+{
+ return 0;
+}
+
+static inline bool blk_queue_is_zone_start(struct request_queue *q, sector_t sec)
+{
+ return false;
+}
+
static inline unsigned int queue_max_open_zones(const struct request_queue *q)
{
return 0;
--
2.25.1
--
dm-devel mailing list
dm-devel@xxxxxxxxxx
https://listman.redhat.com/mailman/listinfo/dm-devel
