If more than one IO is issued for one file extent, these IO can be written to separate regions on a device. Since we cannot map one file extent to such a separate area on a zoned filesystem, we need to follow the "one IO == one ordered extent" rule.
The normal buffered, uncompressed and not pre-allocated write path (used by cow_file_range()) sometimes does not follow this rule. It can write a part of an ordered extent when specified a region to write e.g., when its called from fdatasync(). Introduce a dedicated (uncompressed buffered) data write path for zoned filesystems, that will CoW the region and write it at once. Reviewed-by: Josef Bacik <jo...@toxicpanda.com> Signed-off-by: Naohiro Aota <naohiro.a...@wdc.com> --- fs/btrfs/inode.c | 34 ++++++++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dd6fe8afd0e0..c4779cde83c6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1394,6 +1394,29 @@ static int cow_file_range_async(struct btrfs_inode *inode, return 0; } +static noinline int run_delalloc_zoned(struct btrfs_inode *inode, + struct page *locked_page, u64 start, + u64 end, int *page_started, + unsigned long *nr_written) +{ + int ret; + + ret = cow_file_range(inode, locked_page, start, end, page_started, + nr_written, 0); + if (ret) + return ret; + + if (*page_started) + return 0; + + __set_page_dirty_nobuffers(locked_page); + account_page_redirty(locked_page); + extent_write_locked_range(&inode->vfs_inode, start, end, WB_SYNC_ALL); + *page_started = 1; + + return 0; +} + static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes) { @@ -1871,17 +1894,24 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page { int ret; int force_cow = need_force_cow(inode, start, end); + const bool zoned = btrfs_is_zoned(inode->root->fs_info); if (inode->flags & BTRFS_INODE_NODATACOW && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 1, nr_written); } else if (inode->flags & BTRFS_INODE_PREALLOC && !force_cow) { + ASSERT(!zoned); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); } else if (!inode_can_compress(inode) || !inode_need_compress(inode, start, end)) { - ret = cow_file_range(inode, locked_page, start, end, - page_started, nr_written, 1); + if (zoned) + ret = run_delalloc_zoned(inode, locked_page, start, end, + page_started, nr_written); + else + ret = cow_file_range(inode, locked_page, start, end, + page_started, nr_written, 1); } else { set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags); ret = cow_file_range_async(inode, wbc, locked_page, start, end, -- 2.30.0