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;
Message-ID: <a7a409dc-4cf3-7096-50f6-7f794d4a0b9b@suse.de>
Date:   Tue, 24 May 2022 07:19:26 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.4.0
Subject: Re: [PATCH v5 2/7] block: allow blk-zoned devices to have
 non-power-of-2 zone size
Content-Language: en-US
To:     Pankaj Raghav <p.raghav@samsung.com>, axboe@kernel.dk, hch@lst.de,
        snitzer@redhat.com, damien.lemoal@opensource.wdc.com,
        Johannes.Thumshirn@wdc.com
Cc:     linux-nvme@lists.infradead.org, dm-devel@redhat.com,
        dsterba@suse.com, jiangbo.365@bytedance.com,
        linux-kernel@vger.kernel.org, gost.dev@samsung.com,
        linux-block@vger.kernel.org, jaegeuk@kernel.org,
        Luis Chamberlain <mcgrof@kernel.org>
References: <20220523161601.58078-1-p.raghav@samsung.com>
 <CGME20220523161606eucas1p2676c4d47f9fcb145f69b29db1f04fe6e@eucas1p2.samsung.com>
 <20220523161601.58078-3-p.raghav@samsung.com>
From:   Hannes Reinecke <hare@suse.de>
In-Reply-To: <20220523161601.58078-3-p.raghav@samsung.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 5/23/22 18:15, Pankaj Raghav wrote:
> 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      | 26 ++++++++++++++++++++------
>   include/linux/blkdev.h | 21 +++++++++++++++++++++
>   3 files changed, 42 insertions(+), 8 deletions(-)
> 
> diff --git a/block/blk-core.c b/block/blk-core.c
> index bc0506772152..bf1eae142118 100644
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -630,8 +630,7 @@ 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 e7eec513dd42..665993b13668 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 +489,28 @@ 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 c4e4c7071b7b..f5c7a41032ba 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -676,6 +676,21 @@ 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;
> +

Not sure if we need this here; surely blk_queue_zone_sectors() will
already barf, and none of the callers did this check.

> +	if (is_power_of_2(zone_sectors))
> +		return IS_ALIGNED(sec, zone_sectors);
> +
> +	div64_u64_rem(sec, zone_sectors, &remainder);
> +	return remainder == 0;
> +}
> +
>   static inline bool blk_queue_zone_is_seq(struct request_queue *q,
>   					 sector_t sector)
>   {
> @@ -722,6 +737,12 @@ 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;
Otherwise looks good.

Cheers,

Hannes
-- 
Dr. Hannes Reinecke                Kernel Storage Architect
hare@suse.de                              +49 911 74053 688
SUSE Software Solutions GmbH, Maxfeldstr. 5, 90409 Nürnberg
HRB 36809 (AG Nürnberg), Geschäftsführer: Ivo Totev, Andrew
Myers, Andrew McDonald, Martje Boudien Moerman