Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Pankaj Raghav <p.raghav@samsung.com>
To:     snitzer@kernel.org, axboe@kernel.dk, agk@redhat.com, hch@lst.de,
        damien.lemoal@opensource.wdc.com
Cc:     jaegeuk@kernel.org, gost.dev@samsung.com, bvanassche@acm.org,
        linux-kernel@vger.kernel.org, hare@suse.de,
        matias.bjorling@wdc.com, Johannes.Thumshirn@wdc.com,
        linux-block@vger.kernel.org, linux-nvme@lists.infradead.org,
        pankydev8@gmail.com, dm-devel@redhat.com,
        Pankaj Raghav <p.raghav@samsung.com>,
        Luis Chamberlain <mcgrof@kernel.org>,
        Johannes Thumshirn <johannes.thumshirn@wdc.com>
Subject: [PATCH v15 03/13] block: allow blk-zoned devices to have
 non-power-of-2 zone size
Date:   Fri, 23 Sep 2022 19:36:08 +0200
Message-Id: <20220923173618.6899-4-p.raghav@samsung.com>
In-Reply-To: <20220923173618.6899-1-p.raghav@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 201P
References: <20220923173618.6899-1-p.raghav@samsung.com>
        <CGME20220923173623eucas1p2aeb5444a1005282b630706d60e18a5ba@eucas1p2.samsung.com>
Precedence: bulk

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(po2) based arithmetic in the block layer using the helpers
wherever possible.

The only hot path affected by this change for zoned devices with po2
zone size is in blk_check_zone_append() but bdev_is_zone_start() helper is
used to optimize the calculation for po2 zone sizes.

Finally, allow zoned devices with non po2 zone sizes provided that their
zone capacity and zone size are equal. The main motivation to allow zoned
devices with non po2 zone size is to remove the unmapped LBA between
zone capcity and zone size for devices that cannot have a po2 zone
capacity.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
---
 block/blk-core.c       |  2 +-
 block/blk-zoned.c      | 24 ++++++++++++++++++------
 include/linux/blkdev.h | 30 ++++++++++++++++++++++++++++++
 3 files changed, 49 insertions(+), 7 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 203be672da52..ed5afdb39751 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -559,7 +559,7 @@ 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_start(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..6806c69c81dc 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_start(bdev, sector))
 		return -EINVAL;
 
-	if ((nr_sectors & (zone_sectors - 1)) && end_sector != capacity)
+	if (!bdev_is_zone_start(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 zero 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_err("%s: Invalid zone capacity %lld with non power-of-2 zone size %lld",
+			       disk->disk_name, zone->capacity, zone->len);
 			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 6cf43f9384cc..e29799076298 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -704,6 +704,30 @@ 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_start(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))
@@ -748,6 +772,12 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	return 0;
 }
+
+static inline bool bdev_is_zone_start(struct block_device *bdev, sector_t sec)
+{
+	return false;
+}
+
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
 	return 0;
-- 
2.25.1