This is a note to let you know that I've just added the patch titled btrfs: zoned: revive max_zone_append_bytes to the 5.18-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: btrfs-zoned-revive-max_zone_append_bytes.patch and it can be found in the queue-5.18 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. commit 33903083ab3fd9bee96c3d8ade9c045e2b61060a Author: Naohiro Aota <naohiro.aota@xxxxxxx> Date: Sat Jul 9 08:18:39 2022 +0900 btrfs: zoned: revive max_zone_append_bytes [ Upstream commit c2ae7b772ef4e86c5ddf3fd47bf59045ae96a414 ] This patch is basically a revert of commit 5a80d1c6a270 ("btrfs: zoned: remove max_zone_append_size logic"), but without unnecessary ASSERT and check. The max_zone_append_size will be used as a hint to estimate the number of extents to cover delalloc/writeback region in the later commits. The size of a ZONE APPEND bio is also limited by queue_max_segments(), so this commit considers it to calculate max_zone_append_size. Technically, a bio can be larger than queue_max_segments() * PAGE_SIZE if the pages are contiguous. But, it is safe to consider "queue_max_segments() * PAGE_SIZE" as an upper limit of an extent size to calculate the number of extents needed to write data. Reviewed-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx> Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx> Signed-off-by: David Sterba <dsterba@xxxxxxxx> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 077c95e9baa5..1c377bcfe787 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1050,6 +1050,8 @@ struct btrfs_fs_info { u64 zoned; }; + /* Max size to emit ZONE_APPEND write command */ + u64 max_zone_append_size; struct mutex zoned_meta_io_lock; spinlock_t treelog_bg_lock; u64 treelog_bg; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 84b6d39509bd..1d5b9308f5ef 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -407,6 +407,16 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) nr_sectors = bdev_nr_sectors(bdev); zone_info->zone_size_shift = ilog2(zone_info->zone_size); zone_info->nr_zones = nr_sectors >> ilog2(zone_sectors); + /* + * We limit max_zone_append_size also by max_segments * + * PAGE_SIZE. Technically, we can have multiple pages per segment. But, + * since btrfs adds the pages one by one to a bio, and btrfs cannot + * increase the metadata reservation even if it increases the number of + * extents, it is safe to stick with the limit. + */ + zone_info->max_zone_append_size = + min_t(u64, (u64)bdev_max_zone_append_sectors(bdev) << SECTOR_SHIFT, + (u64)bdev_max_segments(bdev) << PAGE_SHIFT); if (!IS_ALIGNED(nr_sectors, zone_sectors)) zone_info->nr_zones++; @@ -632,6 +642,7 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) u64 zoned_devices = 0; u64 nr_devices = 0; u64 zone_size = 0; + u64 max_zone_append_size = 0; const bool incompat_zoned = btrfs_fs_incompat(fs_info, ZONED); int ret = 0; @@ -666,6 +677,11 @@ int btrfs_check_zoned_mode(struct btrfs_fs_info *fs_info) 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++; } @@ -715,6 +731,7 @@ 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; fs_info->fs_devices->chunk_alloc_policy = BTRFS_CHUNK_ALLOC_ZONED; /* diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index cf6320feef46..2d6da8f4b55a 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -23,6 +23,7 @@ struct btrfs_zoned_device_info { */ u64 zone_size; u8 zone_size_shift; + u64 max_zone_append_size; u32 nr_zones; unsigned int max_active_zones; atomic_t active_zones_left;