[PATCH 5.19 1085/1157] btrfs: zoned: revive max_zone_append_bytes

[Greg Kroah-Hartman]

From: Naohiro Aota <naohiro.aota@xxxxxxx>

[ 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>
---
 fs/btrfs/ctree.h |  2 ++
 fs/btrfs/zoned.c | 17 +++++++++++++++++
 fs/btrfs/zoned.h |  1 +
 3 files changed, 20 insertions(+)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9c21e214d29e..7abfbfd7c94c 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1047,6 +1047,8 @@ struct btrfs_fs_info {
 	 */
 	u64 zone_size;
 
+	/* 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 d99026df6f67..52607569cf49 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -415,6 +415,16 @@ 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++;
 
@@ -640,6 +650,7 @@ 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;
 
@@ -674,6 +685,11 @@ 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++;
 	}
@@ -723,6 +739,7 @@ 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 6b2eec99162b..9caeab07fd38 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -19,6 +19,7 @@ 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;
-- 
2.35.1