diff mbox series

[v3,07/30] block: Remember zone capacity when revalidating zones

Message ID 20240328004409.594888-8-dlemoal@kernel.org (mailing list archive)
State Superseded
Headers show
Series Zone write plugging | expand

Commit Message

Damien Le Moal March 28, 2024, 12:43 a.m. UTC 
In preparation for adding zone write plugging, modify
blk_revalidate_disk_zones() to get the capacity of zones of a zoned
block device. This capacity value as a number of 512B sectors is stored
in the gendisk zone_capacity field.

Given that host-managed SMR disks (including zoned UFS drives) and all
known NVMe ZNS devices have the same zone capacity for all zones
blk_revalidate_disk_zones() returns an error if different capacities are
detected for different zones.

This also adds check to verify that the values reported by the device
for zone capacities are correct, that is, that the zone capacity is
never 0, does not exceed the zone size and is equal to the zone size for
conventional zones.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 block/blk-zoned.c      | 26 ++++++++++++++++++++++++++
 include/linux/blkdev.h |  1 +
 2 files changed, 27 insertions(+)

Comments

Bart Van Assche March 28, 2024, 9:38 p.m. UTC | #1 
On 3/27/24 5:43 PM, Damien Le Moal wrote:
> +		/*
> +		 * Remember the capacity of the first sequential zone and check
> +		 * if it is constant for all zones.
> +		 */
> +		if (!args->zone_capacity)
> +			args->zone_capacity = zone->capacity;
> +		if (zone->capacity != args->zone_capacity) {
> +			pr_warn("%s: Invalid variable zone capacity\n",
> +				disk->disk_name);
> +			return -ENODEV;
> +		}

SMR disks may have a smaller last zone. Does the above code handle such
SMR disks correctly?

Thanks,

Bart.
Damien Le Moal March 28, 2024, 10:40 p.m. UTC | #2 
On 3/29/24 06:38, Bart Van Assche wrote:
> On 3/27/24 5:43 PM, Damien Le Moal wrote:
>> +		/*
>> +		 * Remember the capacity of the first sequential zone and check
>> +		 * if it is constant for all zones.
>> +		 */
>> +		if (!args->zone_capacity)
>> +			args->zone_capacity = zone->capacity;
>> +		if (zone->capacity != args->zone_capacity) {
>> +			pr_warn("%s: Invalid variable zone capacity\n",
>> +				disk->disk_name);
>> +			return -ENODEV;
>> +		}
> 
> SMR disks may have a smaller last zone. Does the above code handle such
> SMR disks correctly?

SMR drives known to have a smaller last zone have a smaller conventional zone,
not a sequential zone. But good point, I will handle that on the check for
conventional zones.

> 
> Thanks,
> 
> Bart.
diff mbox series

Patch

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index da0f4b2a8fa0..23d9bb21c459 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -438,6 +438,7 @@  struct blk_revalidate_zone_args {
 	unsigned long	*conv_zones_bitmap;
 	unsigned long	*seq_zones_wlock;
 	unsigned int	nr_zones;
+	unsigned int	zone_capacity;
 	sector_t	sector;
 };
 
@@ -482,9 +483,20 @@  static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 		return -ENODEV;
 	}
 
+	if (!zone->capacity || zone->capacity > zone->len) {
+		pr_warn("%s: Invalid zone capacity\n",
+			disk->disk_name);
+		return -ENODEV;
+	}
+
 	/* Check zone type */
 	switch (zone->type) {
 	case BLK_ZONE_TYPE_CONVENTIONAL:
+		if (zone->capacity != zone->len) {
+			pr_warn("%s: Invalid conventional zone capacity\n",
+				disk->disk_name);
+			return -ENODEV;
+		}
 		if (!args->conv_zones_bitmap) {
 			args->conv_zones_bitmap =
 				blk_alloc_zone_bitmap(q->node, args->nr_zones);
@@ -500,6 +512,18 @@  static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 			if (!args->seq_zones_wlock)
 				return -ENOMEM;
 		}
+
+		/*
+		 * Remember the capacity of the first sequential zone and check
+		 * if it is constant for all zones.
+		 */
+		if (!args->zone_capacity)
+			args->zone_capacity = zone->capacity;
+		if (zone->capacity != args->zone_capacity) {
+			pr_warn("%s: Invalid variable zone capacity\n",
+				disk->disk_name);
+			return -ENODEV;
+		}
 		break;
 	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 	default:
@@ -595,6 +619,7 @@  int blk_revalidate_disk_zones(struct gendisk *disk,
 	blk_mq_freeze_queue(q);
 	if (ret > 0) {
 		disk->nr_zones = args.nr_zones;
+		disk->zone_capacity = args.zone_capacity;
 		swap(disk->seq_zones_wlock, args.seq_zones_wlock);
 		swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
 		if (update_driver_data)
@@ -608,6 +633,7 @@  int blk_revalidate_disk_zones(struct gendisk *disk,
 
 	kfree(args.seq_zones_wlock);
 	kfree(args.conv_zones_bitmap);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ec7bd7091467..4e81f714cca7 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -191,6 +191,7 @@  struct gendisk {
 	 * blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
+	unsigned int		zone_capacity;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
 #endif /* CONFIG_BLK_DEV_ZONED */