Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   Pankaj Raghav <p.raghav@samsung.com>
To:     jaegeuk@kernel.org, axboe@kernel.dk, snitzer@kernel.org,
        hch@lst.de, mcgrof@kernel.org, naohiro.aota@wdc.com,
        sagi@grimberg.me, damien.lemoal@opensource.wdc.com,
        dsterba@suse.com, johannes.thumshirn@wdc.com
Cc:     linux-kernel@vger.kernel.org, linux-btrfs@vger.kernel.org,
        clm@fb.com, gost.dev@samsung.com, chao@kernel.org,
        linux-f2fs-devel@lists.sourceforge.net, josef@toxicpanda.com,
        jonathan.derrick@linux.dev, agk@redhat.com, kbusch@kernel.org,
        kch@nvidia.com, linux-nvme@lists.infradead.org,
        dm-devel@redhat.com, bvanassche@acm.org, jiangbo.365@bytedance.com,
        linux-fsdevel@vger.kernel.org, matias.bjorling@wdc.com,
        linux-block@vger.kernel.org, Pankaj Raghav <p.raghav@samsung.com>
Subject: [PATCH 13/16] null_blk: allow non power of 2 zoned devices
Date:   Wed, 27 Apr 2022 18:02:52 +0200
Message-Id: <20220427160255.300418-14-p.raghav@samsung.com>
In-Reply-To: <20220427160255.300418-1-p.raghav@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 201P
References: <20220427160255.300418-1-p.raghav@samsung.com>
        <CGME20220427160310eucas1p28cd3c5ff4fb7a04bc77c4c0b9d96bb74@eucas1p2.samsung.com>
Precedence: bulk

Convert the power of 2 based calculation with zone size to be generic in
null_zone_no with optimization for power of 2 based zone sizes.

The nr_zones calculation in null_init_zoned_dev has been replaced with a
division without special handling for power of 2 based zone sizes as
this function is called only during the initialization and will not
invoked in the hot path.

Performance Measurement:

Device:
zone size = 128M, blocksize=4k

FIO cmd:

fio --name=zbc --filename=/dev/nullb0 --direct=1 --zonemode=zbd  --size=23G
--io_size=<iosize> --ioengine=io_uring --iodepth=<iod> --rw=<mode> --bs=4k
--loops=4

The following results are an average of 4 runs on AMD Ryzen 5 5600X with
32GB of RAM:

Sequential Write:

x-----------------x---------------------------------x---------------------------------x
|     IOdepth     |            8                    |            16                   |
x-----------------x---------------------------------x---------------------------------x
|                 |  KIOPS   |BW(MiB/s) | Lat(usec) |  KIOPS   |BW(MiB/s) | Lat(usec) |
x-----------------x---------------------------------x---------------------------------x
| Without patch   |  578     |  2257    |   12.80   |  576     |  2248    |   25.78   |
x-----------------x---------------------------------x---------------------------------x
|  With patch     |  581     |  2268    |   12.74   |  576     |  2248    |   25.85   |
x-----------------x---------------------------------x---------------------------------x

Sequential read:

x-----------------x---------------------------------x---------------------------------x
| IOdepth         |            8                    |            16                   |
x-----------------x---------------------------------x---------------------------------x
|                 |  KIOPS   |BW(MiB/s) | Lat(usec) |  KIOPS   |BW(MiB/s) | Lat(usec) |
x-----------------x---------------------------------x---------------------------------x
| Without patch   |  667     |  2605    |   11.79   |  675     |  2637    |   23.49   |
x-----------------x---------------------------------x---------------------------------x
|  With patch     |  667     |  2605    |   11.79   |  675     |  2638    |   23.48   |
x-----------------x---------------------------------x---------------------------------x

Random read:

x-----------------x---------------------------------x---------------------------------x
| IOdepth         |            8                    |            16                   |
x-----------------x---------------------------------x---------------------------------x
|                 |  KIOPS   |BW(MiB/s) | Lat(usec) |  KIOPS   |BW(MiB/s) | Lat(usec) |
x-----------------x---------------------------------x---------------------------------x
| Without patch   |  522     |  2038    |   15.05   |  514     |  2006    |   30.87   |
x-----------------x---------------------------------x---------------------------------x
|  With patch     |  522     |  2039    |   15.04   |  523     |  2042    |   30.33   |
x-----------------x---------------------------------x---------------------------------x

Minor variations are noticed in Sequential write with io depth 8 and
in random read with io depth 16. But overall no noticeable differences
were noticed

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
---
 drivers/block/null_blk/main.c  |  4 ++--
 drivers/block/null_blk/zoned.c | 14 +++++++-------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index c441a4972064..82a62b543782 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1931,8 +1931,8 @@ static int null_validate_conf(struct nullb_device *dev)
 		dev->mbps = 0;
 
 	if (dev->zoned &&
-	    (!dev->zone_size || !is_power_of_2(dev->zone_size))) {
-		pr_err("zone_size must be power-of-two\n");
+	    (!dev->zone_size)) {
+		pr_err("zone_size must not be zero\n");
 		return -EINVAL;
 	}
 
diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c
index dae54dd1aeac..00c34e65ef0a 100644
--- a/drivers/block/null_blk/zoned.c
+++ b/drivers/block/null_blk/zoned.c
@@ -13,7 +13,10 @@ static inline sector_t mb_to_sects(unsigned long mb)
 
 static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
 {
-	return sect >> ilog2(dev->zone_size_sects);
+	if (is_power_of_2(dev->zone_size_sects))
+		return sect >> ilog2(dev->zone_size_sects);
+
+	return div64_u64(sect, dev->zone_size_sects);
 }
 
 static inline void null_lock_zone_res(struct nullb_device *dev)
@@ -62,10 +65,6 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 	sector_t sector = 0;
 	unsigned int i;
 
-	if (!is_power_of_2(dev->zone_size)) {
-		pr_err("zone_size must be power-of-two\n");
-		return -EINVAL;
-	}
 	if (dev->zone_size > dev->size) {
 		pr_err("Zone size larger than device capacity\n");
 		return -EINVAL;
@@ -83,8 +82,9 @@ int null_init_zoned_dev(struct nullb_device *dev, struct request_queue *q)
 	zone_capacity_sects = mb_to_sects(dev->zone_capacity);
 	dev_capacity_sects = mb_to_sects(dev->size);
 	dev->zone_size_sects = mb_to_sects(dev->zone_size);
-	dev->nr_zones = round_up(dev_capacity_sects, dev->zone_size_sects)
-		>> ilog2(dev->zone_size_sects);
+	dev->nr_zones =
+		div64_u64(roundup(dev_capacity_sects, dev->zone_size_sects),
+			  dev->zone_size_sects);
 
 	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct nullb_zone),
 				    GFP_KERNEL | __GFP_ZERO);
-- 
2.25.1