diff mbox series

[v4,03/13] nvme: zns: Allow ZNS drives that have non-power_of_2 zone size

Message ID 20220516133921.126925-4-p.raghav@samsung.com (mailing list archive)
State New, archived
Headers show
Series [v4,01/13] block: make blkdev_nr_zones and blk_queue_zone_no generic for npo2 zsze | expand

Commit Message

Pankaj Raghav May 16, 2022, 1:39 p.m. UTC
Remove the condition which disallows non-power_of_2 zone size ZNS drive
to be updated and use generic method to calculate number of zones
instead of relying on log and shift based calculation on zone size.

The power_of_2 calculation has been replaced directly with generic
calculation without special handling. Both modified functions are not
used in hot paths, they are only used during initialization &
revalidation of the ZNS device.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed by: Adam Manzanares <a.manzanares@samsung.com>
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
---
 drivers/nvme/host/zns.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

Comments

Damien Le Moal May 16, 2022, 2:02 p.m. UTC | #1
On 2022/05/16 15:39, Pankaj Raghav wrote:
> Remove the condition which disallows non-power_of_2 zone size ZNS drive
> to be updated and use generic method to calculate number of zones
> instead of relying on log and shift based calculation on zone size.
> 
> The power_of_2 calculation has been replaced directly with generic
> calculation without special handling. Both modified functions are not
> used in hot paths, they are only used during initialization &
> revalidation of the ZNS device.
> 
> Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
> Reviewed by: Adam Manzanares <a.manzanares@samsung.com>
> Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
> ---
>  drivers/nvme/host/zns.c | 24 +++++++++++++++---------
>  1 file changed, 15 insertions(+), 9 deletions(-)
> 
> diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
> index 9f81beb4d..65d2aa68a 100644
> --- a/drivers/nvme/host/zns.c
> +++ b/drivers/nvme/host/zns.c
> @@ -101,13 +101,6 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
>  	}
>  
>  	ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
> -	if (!is_power_of_2(ns->zsze)) {
> -		dev_warn(ns->ctrl->device,
> -			"invalid zone size:%llu for namespace:%u\n",
> -			ns->zsze, ns->head->ns_id);
> -		status = -ENODEV;
> -		goto free_data;
> -	}
>  
>  	blk_queue_set_zoned(ns->disk, BLK_ZONED_HM);
>  	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
> @@ -128,8 +121,13 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
>  	const size_t min_bufsize = sizeof(struct nvme_zone_report) +
>  				   sizeof(struct nvme_zone_descriptor);
>  
> +	/*
> +	 * Division is used to calculate nr_zones with no special handling
> +	 * for power of 2 zone sizes as this function is not invoked in a
> +	 * hot path
> +	 */

Comment not very useful.

>  	nr_zones = min_t(unsigned int, nr_zones,
> -			 get_capacity(ns->disk) >> ilog2(ns->zsze));
> +			 div64_u64(get_capacity(ns->disk), ns->zsze));
>  
>  	bufsize = sizeof(struct nvme_zone_report) +
>  		nr_zones * sizeof(struct nvme_zone_descriptor);
> @@ -182,6 +180,7 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
>  	int ret, zone_idx = 0;
>  	unsigned int nz, i;
>  	size_t buflen;
> +	u64 remainder = 0;
>  
>  	if (ns->head->ids.csi != NVME_CSI_ZNS)
>  		return -EINVAL;
> @@ -197,7 +196,14 @@ int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
>  	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
>  	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
>  
> -	sector &= ~(ns->zsze - 1);
> +	/*
> +	 * rounddown the sector value to the nearest zone size. roundown macro
> +	 * provided in math.h will not work for 32 bit architectures.
> +	 * Division is used here with no special handling for power of 2
> +	 * zone sizes as this function is not invoked in a hot path
> +	 */

Please simplify this to:

	/* Round down the sector value to the nearest zone start */

> +	div64_u64_rem(sector, ns->zsze, &remainder);
> +	sector -= remainder;
>  	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
>  		memset(report, 0, buflen);
>
diff mbox series

Patch

diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 9f81beb4d..65d2aa68a 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -101,13 +101,6 @@  int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf)
 	}
 
 	ns->zsze = nvme_lba_to_sect(ns, le64_to_cpu(id->lbafe[lbaf].zsze));
-	if (!is_power_of_2(ns->zsze)) {
-		dev_warn(ns->ctrl->device,
-			"invalid zone size:%llu for namespace:%u\n",
-			ns->zsze, ns->head->ns_id);
-		status = -ENODEV;
-		goto free_data;
-	}
 
 	blk_queue_set_zoned(ns->disk, BLK_ZONED_HM);
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
@@ -128,8 +121,13 @@  static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 	const size_t min_bufsize = sizeof(struct nvme_zone_report) +
 				   sizeof(struct nvme_zone_descriptor);
 
+	/*
+	 * Division is used to calculate nr_zones with no special handling
+	 * for power of 2 zone sizes as this function is not invoked in a
+	 * hot path
+	 */
 	nr_zones = min_t(unsigned int, nr_zones,
-			 get_capacity(ns->disk) >> ilog2(ns->zsze));
+			 div64_u64(get_capacity(ns->disk), ns->zsze));
 
 	bufsize = sizeof(struct nvme_zone_report) +
 		nr_zones * sizeof(struct nvme_zone_descriptor);
@@ -182,6 +180,7 @@  int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	int ret, zone_idx = 0;
 	unsigned int nz, i;
 	size_t buflen;
+	u64 remainder = 0;
 
 	if (ns->head->ids.csi != NVME_CSI_ZNS)
 		return -EINVAL;
@@ -197,7 +196,14 @@  int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
 	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
 
-	sector &= ~(ns->zsze - 1);
+	/*
+	 * rounddown the sector value to the nearest zone size. roundown macro
+	 * provided in math.h will not work for 32 bit architectures.
+	 * Division is used here with no special handling for power of 2
+	 * zone sizes as this function is not invoked in a hot path
+	 */
+	div64_u64_rem(sector, ns->zsze, &remainder);
+	sector -= remainder;
 	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
 		memset(report, 0, buflen);