The device decides the written location of ZONE_APPEND write IO. Thus, we
cannot ensure two bios to be written continuously on the device. So, we
need to follow "one bio == one ordered extent" rule to ensure the region of
ordered extent maps to contiguous region on the disk.
This commit implements splitting of an ordered extent and an extent map on
submitting bio to follow the rule.
Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
fs/btrfs/inode.c | 87 +++++++++++++++++++++++++++++++++++++++++
fs/btrfs/ordered-data.c | 73 ++++++++++++++++++++++++++++++++++
fs/btrfs/ordered-data.h | 2 +
3 files changed, 162 insertions(+)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 36efed0a24de..4bc975eafbd8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2158,6 +2158,87 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
}
+int extract_ordered_extent(struct inode *inode, struct bio *bio)
+{
+ struct btrfs_ordered_extent *ordered;
+ struct extent_map *em = NULL, *em_new = NULL;
+ struct page *page = bio_first_bvec_all(bio)->bv_page;
+ struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+ u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
+ u64 len = bio->bi_iter.bi_size;
+ u64 end = start + len;
+ u64 ordered_end;
+ u64 pre, post;
+ int ret = 0;
+
+ ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode),
+ page_offset(page));
+ if (WARN_ON_ONCE(!ordered))
+ return -EIO;
+
+ /* no need to split */
+ if (ordered->disk_num_bytes == len)
+ goto out;
+
+ /* cannot split once end_bio'd ordered extent */
+ if (WARN_ON_ONCE(ordered->bytes_left != ordered->disk_num_bytes)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* we cannot split compressed ordered extent */
+ if (WARN_ON_ONCE(ordered->disk_num_bytes != ordered->num_bytes)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* cannot split waietd ordered extent */
+ if (WARN_ON_ONCE(wq_has_sleeper(&ordered->wait))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ordered_end = ordered->disk_bytenr + ordered->disk_num_bytes;
+ /* bio must be in one ordered extent */
+ if (WARN_ON_ONCE(start < ordered->disk_bytenr || end > ordered_end)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* checksum list should be empty */
+ if (WARN_ON_ONCE(!list_empty(&ordered->list))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ pre = start - ordered->disk_bytenr;
+ post = ordered_end - end;
+
+ btrfs_split_ordered_extent(ordered, pre, post);
+
+ read_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, ordered->file_offset, len);
+ if (!em) {
+ read_unlock(&em_tree->lock);
+ ret = -EIO;
+ goto out;
+ }
+ read_unlock(&em_tree->lock);
+
+ ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+ em_new = create_io_em(BTRFS_I(inode), em->start + pre, len,
+ em->start + pre, em->block_start + pre, len,
+ len, len, BTRFS_COMPRESS_NONE,
+ BTRFS_ORDERED_REGULAR);
+ free_extent_map(em_new);
+
+out:
+ free_extent_map(em);
+ btrfs_put_ordered_extent(ordered);
+
+ return ret;
+}
+
/*
* extent_io.c submission hook. This does the right thing for csum calculation
* on write, or reading the csums from the tree before a read.
@@ -2192,6 +2273,12 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
if (btrfs_is_free_space_inode(BTRFS_I(inode)))
metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ ret = extract_ordered_extent(inode, bio);
+ if (ret)
+ goto out;
+ }
+
if (bio_op(bio) != REQ_OP_WRITE) {
ret = btrfs_bio_wq_end_io(fs_info, bio, metadata);
if (ret)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 87bac9ecdf4c..7cd22cb07f26 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -943,6 +943,79 @@ void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
}
}
+static void 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;
+
+ weight = hweight_long(flags_masked);
+ WARN_ON_ONCE(weight > 1);
+ if (!weight)
+ type = 0;
+ else
+ type = __ffs(flags_masked);
+
+ ASSERT(!test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags));
+ if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered->flags)) {
+ WARN_ON_ONCE(1);
+ btrfs_add_ordered_extent_compress(BTRFS_I(inode), file_offset,
+ disk_bytenr, num_bytes,
+ disk_num_bytes, type,
+ compress_type);
+ } else {
+ btrfs_add_ordered_extent(BTRFS_I(inode), file_offset,
+ disk_bytenr, num_bytes, disk_num_bytes,
+ type);
+ }
+}
+
+void 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);
+
+ 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,
+ "inconsistency in ordered tree at offset %llu",
+ ordered->file_offset);
+
+ spin_unlock_irq(&tree->lock);
+
+ if (pre)
+ clone_ordered_extent(ordered, 0, pre);
+ if (post)
+ clone_ordered_extent(ordered, pre + ordered->disk_num_bytes, post);
+}
+
int __init ordered_data_init(void)
{
btrfs_ordered_extent_cache = kmem_cache_create("btrfs_ordered_extent",
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index c3a2325e64a4..e346b03bd66a 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -193,6 +193,8 @@ void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
void btrfs_lock_and_flush_ordered_range(struct btrfs_inode *inode, u64 start,
u64 end,
struct extent_state **cached_state);
+void btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre,
+ u64 post);
int __init ordered_data_init(void);
void __cold ordered_data_exit(void);
--
2.27.0
