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:     axboe@kernel.dk, damien.lemoal@opensource.wdc.com,
        pankydev8@gmail.com, dsterba@suse.com, hch@lst.de
Cc:     linux-nvme@lists.infradead.org, linux-fsdevel@vger.kernel.org,
        linux-btrfs@vger.kernel.org, jiangbo.365@bytedance.com,
        linux-block@vger.kernel.org, gost.dev@samsung.com,
        p.raghav@samsung.com, linux-kernel@vger.kernel.org,
        dm-devel@redhat.com, Luis Chamberlain <mcgrof@kernel.org>
Subject: [PATCH v4 02/13] block: allow blk-zoned devices to have
 non-power-of-2 zone size
Date:   Mon, 16 May 2022 18:54:05 +0200
Message-Id: <20220516165416.171196-3-p.raghav@samsung.com>
In-Reply-To: <20220516165416.171196-1-p.raghav@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 201P
References: <20220516165416.171196-1-p.raghav@samsung.com>
        <CGME20220516165421eucas1p2515446ac290987bdb9af24ffb835b287@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
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@kernel.org>
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
---
 block/blk-core.c       |  3 +--
 block/blk-zoned.c      | 27 +++++++++++++++++++++------
 include/linux/blkdev.h | 22 ++++++++++++++++++++++
 3 files changed, 44 insertions(+), 8 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index f305cb66c..b7051b7ea 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -634,8 +634,7 @@ 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 140230134..cfc2fb804 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -289,10 +289,10 @@ 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;
 
 	/*
@@ -490,14 +490,29 @@ 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 zoned size with non power of 2 zone size and zone capacity < 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 22fe512ee..32d7bd7b1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -686,6 +686,22 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 	return div64_u64(sector, zone_sectors);
 }
 
+static inline bool blk_queue_is_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 IS_ALIGNED(sec, zone_sectors);
+
+	div64_u64_rem(sec, zone_sectors, &remainder);
+	/* if there is a remainder, then the sector is not aligned */
+	return remainder == 0;
+}
+
 static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 					 sector_t sector)
 {
@@ -732,6 +748,12 @@ static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 {
 	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