diff options
author | Naohiro Aota <naohiro.aota@wdc.com> | 2021-02-04 13:22:00 +0300 |
---|---|---|
committer | David Sterba <dsterba@suse.com> | 2021-02-09 04:46:05 +0300 |
commit | d22002fd37bd970480c59754dfa448866a1f38bd (patch) | |
tree | 2a97ecbc672e51d1e80027c680c9e1f9d80e90a3 /fs/btrfs/ordered-data.c | |
parent | cfe94440d17404478771179150e6e4554f092dd5 (diff) | |
download | linux-d22002fd37bd970480c59754dfa448866a1f38bd.tar.xz |
btrfs: zoned: split ordered extent when bio is sent
For a zone append write, the device decides the location the data is being
written to. Therefore we cannot ensure that two bios are written
consecutively on the device. In order to ensure that an ordered extent
maps to a contiguous region on disk, we need to maintain a "one bio ==
one ordered extent" rule.
Implement splitting of an ordered extent and extent map on bio submission
to adhere to the rule.
extract_ordered_extent() hooks into btrfs_submit_data_bio() and splits the
corresponding ordered extent so that the ordered extent's region fits into
one bio and the corresponding device limits.
Several sanity checks need to be done in extract_ordered_extent() e.g.
- We cannot split once end_bio'd ordered extent because we cannot divide
ordered->bytes_left for the split ones
- We do not expect a compressed ordered extent
- We should not have checksum list because we omit the list splitting.
Since the function is called before btrfs_wq_submit_bio() or
btrfs_csum_one_bio(), this should be always ensured.
We also need to split an extent map by creating a new one. If not,
unpin_extent_cache() complains about the difference between the start of
the extent map and the file's logical offset.
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/ordered-data.c')
-rw-r--r-- | fs/btrfs/ordered-data.c | 78 |
1 files changed, 78 insertions, 0 deletions
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index e8dee1578d4a..2dc707f02f00 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -920,6 +920,84 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start, } } +static int clone_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pos, + u64 len) +{ + struct inode *inode = ordered->inode; + u64 file_offset = ordered->file_offset + pos; + u64 disk_bytenr = ordered->disk_bytenr + pos; + u64 num_bytes = len; + u64 disk_num_bytes = len; + int type; + unsigned long flags_masked = ordered->flags & ~(1 << BTRFS_ORDERED_DIRECT); + int compress_type = ordered->compress_type; + unsigned long weight; + int ret; + + weight = hweight_long(flags_masked); + WARN_ON_ONCE(weight > 1); + if (!weight) + type = 0; + else + type = __ffs(flags_masked); + + if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) { + WARN_ON_ONCE(1); + ret = btrfs_add_ordered_extent_compress(BTRFS_I(inode), + file_offset, disk_bytenr, num_bytes, + disk_num_bytes, compress_type); + } else if (test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) { + ret = btrfs_add_ordered_extent_dio(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } else { + ret = btrfs_add_ordered_extent(BTRFS_I(inode), file_offset, + disk_bytenr, num_bytes, disk_num_bytes, type); + } + + return ret; +} + +int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre, + u64 post) +{ + struct inode *inode = ordered->inode; + struct btrfs_ordered_inode_tree *tree = &BTRFS_I(inode)->ordered_tree; + struct rb_node *node; + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + int ret = 0; + + spin_lock_irq(&tree->lock); + /* Remove from tree once */ + node = &ordered->rb_node; + rb_erase(node, &tree->tree); + RB_CLEAR_NODE(node); + if (tree->last == node) + tree->last = NULL; + + ordered->file_offset += pre; + ordered->disk_bytenr += pre; + ordered->num_bytes -= (pre + post); + ordered->disk_num_bytes -= (pre + post); + ordered->bytes_left -= (pre + post); + + /* Re-insert the node */ + node = tree_insert(&tree->tree, ordered->file_offset, &ordered->rb_node); + if (node) + btrfs_panic(fs_info, -EEXIST, + "zoned: inconsistency in ordered tree at offset %llu", + ordered->file_offset); + + spin_unlock_irq(&tree->lock); + + if (pre) + ret = clone_ordered_extent(ordered, 0, pre); + if (post) + ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, + post); + + return ret; +} + int __init ordered_data_init(void) { btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent", |