The zone append write command has a maximum IO size restriction it
accepts. This is because a zone append write command cannot be split, as
we ask the device to place the data into a specific target zone and the
device responds with the actual written location of the data.
Introduce max_zone_append_size to zone_info and fs_info to track the
value, so we can limit all I/O to a zoned block device that we want to
write using the zone append command to the device's limits.
Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
fs/btrfs/ctree.h | 2 ++
fs/btrfs/zoned.c | 19 ++++++++++++++++---
fs/btrfs/zoned.h | 1 +
3 files changed, 19 insertions(+), 3 deletions(-)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 25fd4e97dd2a..383c83a1f5b5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -953,6 +953,8 @@ struct btrfs_fs_info {
u64 zone_size;
u64 zoned;
};
+ /* max size to emit ZONE_APPEND write command */
+ u64 max_zone_append_size;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index e1cdff5af3a3..1b42e13b8227 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -47,6 +47,7 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
{
struct btrfs_zoned_device_info *zone_info = NULL;
struct block_device *bdev = device->bdev;
+ struct request_queue *q = bdev_get_queue(bdev);
sector_t nr_sectors = bdev->bd_part->nr_sects;
sector_t sector = 0;
struct blk_zone *zones = NULL;
@@ -70,6 +71,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device)
ASSERT(is_power_of_2(zone_sectors));
zone_info->zone_size = (u64)zone_sectors << SECTOR_SHIFT;
zone_info->zone_size_shift = ilog2(zone_info->zone_size);
+ zone_info->max_zone_append_size =
+ (u64)queue_max_zone_append_sectors(q) << SECTOR_SHIFT;
zone_info->nr_zones = nr_sectors >> ilog2(bdev_zone_sectors(bdev));
if (!IS_ALIGNED(nr_sectors, zone_sectors))
zone_info->nr_zones++;
@@ -182,7 +185,8 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
u64 hmzoned_devices = 0;
u64 nr_devices = 0;
u64 zone_size = 0;
- int incompat_zoned = btrfs_is_zoned(fs_info);
+ u64 max_zone_append_size = 0;
+ bool incompat_zoned = btrfs_is_zoned(fs_info);
int ret = 0;
/* Count zoned devices */
@@ -195,15 +199,23 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
model = bdev_zoned_model(device->bdev);
if (model == BLK_ZONED_HM ||
(model == BLK_ZONED_HA && incompat_zoned)) {
+ struct btrfs_zoned_device_info *zone_info =
+ device->zone_info;
+
hmzoned_devices++;
if (!zone_size) {
- zone_size = device->zone_info->zone_size;
- } else if (device->zone_info->zone_size != zone_size) {
+ zone_size = zone_info->zone_size;
+ } else if (zone_info->zone_size != zone_size) {
btrfs_err(fs_info,
"Zoned block devices must have equal zone sizes");
ret = -EINVAL;
goto out;
}
+ if (!max_zone_append_size ||
+ (zone_info->max_zone_append_size &&
+ zone_info->max_zone_append_size < max_zone_append_size))
+ max_zone_append_size =
+ zone_info->max_zone_append_size;
}
nr_devices++;
}
@@ -246,6 +258,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info)
}
fs_info->zone_size = zone_size;
+ fs_info->max_zone_append_size = max_zone_append_size;
btrfs_info(fs_info, "ZONED mode enabled, zone size %llu B",
fs_info->zone_size);
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index c4c63c4294f2..a63f6177f9ee 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -12,6 +12,7 @@ struct btrfs_zoned_device_info {
*/
u64 zone_size;
u8 zone_size_shift;
+ u64 max_zone_append_size;
u32 nr_zones;
unsigned long *seq_zones;
unsigned long *empty_zones;
--
2.27.0
