From d8e3fb106f393858b90b3befc4f6092a76c86d1c Mon Sep 17 00:00:00 2001 From: Naohiro Aota Date: Thu, 4 Feb 2021 19:22:05 +0900 Subject: btrfs: zoned: use ZONE_APPEND write for zoned mode Enable zone append writing for zoned mode. When using zone append, a bio is issued to the start of a target zone and the device decides to place it inside the zone. Upon completion the device reports the actual written position back to the host. Three parts are necessary to enable zone append mode. First, modify the bio to use REQ_OP_ZONE_APPEND in btrfs_submit_bio_hook() and adjust the bi_sector to point the beginning of the zone. Second, record the returned physical address (and disk/partno) to the ordered extent in end_bio_extent_writepage() after the bio has been completed. We cannot resolve the physical address to the logical address because we can neither take locks nor allocate a buffer in this end_bio context. So, we need to record the physical address to resolve it later in btrfs_finish_ordered_io(). And finally, rewrite the logical addresses of the extent mapping and checksum data according to the physical address using btrfs_rmap_block. If the returned address matches the originally allocated address, we can skip this rewriting process. Reviewed-by: Josef Bacik Signed-off-by: Johannes Thumshirn Signed-off-by: Naohiro Aota Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/zoned.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) (limited to 'fs/btrfs/zoned.c') diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index f6c68704c840..f4e226bda9b0 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1247,3 +1247,73 @@ bool btrfs_use_zone_append(struct btrfs_inode *inode, struct extent_map *em) return ret; } + +void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset, + struct bio *bio) +{ + struct btrfs_ordered_extent *ordered; + const u64 physical = bio->bi_iter.bi_sector << SECTOR_SHIFT; + + if (bio_op(bio) != REQ_OP_ZONE_APPEND) + return; + + ordered = btrfs_lookup_ordered_extent(BTRFS_I(inode), file_offset); + if (WARN_ON(!ordered)) + return; + + ordered->physical = physical; + ordered->disk = bio->bi_disk; + ordered->partno = bio->bi_partno; + + btrfs_put_ordered_extent(ordered); +} + +void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered) +{ + struct btrfs_inode *inode = BTRFS_I(ordered->inode); + struct btrfs_fs_info *fs_info = inode->root->fs_info; + struct extent_map_tree *em_tree; + struct extent_map *em; + struct btrfs_ordered_sum *sum; + struct block_device *bdev; + u64 orig_logical = ordered->disk_bytenr; + u64 *logical = NULL; + int nr, stripe_len; + + /* Zoned devices should not have partitions. So, we can assume it is 0 */ + ASSERT(ordered->partno == 0); + bdev = bdgrab(ordered->disk->part0); + if (WARN_ON(!bdev)) + return; + + if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, bdev, + ordered->physical, &logical, &nr, + &stripe_len))) + goto out; + + WARN_ON(nr != 1); + + if (orig_logical == *logical) + goto out; + + ordered->disk_bytenr = *logical; + + em_tree = &inode->extent_tree; + write_lock(&em_tree->lock); + em = search_extent_mapping(em_tree, ordered->file_offset, + ordered->num_bytes); + em->block_start = *logical; + free_extent_map(em); + write_unlock(&em_tree->lock); + + list_for_each_entry(sum, &ordered->list, list) { + if (*logical < orig_logical) + sum->bytenr -= orig_logical - *logical; + else + sum->bytenr += *logical - orig_logical; + } + +out: + kfree(logical); + bdput(bdev); +} -- cgit v1.2.3