commit 343d8a30851c48a4ef0f5ef61d5e9fbd847a6883 upstream

After commit 5f0addf7b890 ("btrfs: zoned: use dedicated lock for data relocation"), we observe IO errors on e.g, btrfs/232 like below.

[09.0][T4038707] WARNING: CPU: 3 PID: 4038707 at fs/btrfs/extent-tree.c:2381 btrfs_cross_ref_exist+0xfc/0x120 [btrfs] <snip> [09.9][T4038707] Call Trace: [09.5][T4038707] <TASK> [09.3][T4038707] run_delalloc_nocow+0x7f1/0x11a0 [btrfs] [09.6][T4038707] ? test_range_bit+0x174/0x320 [btrfs] [09.2][T4038707] ? fallback_to_cow+0x980/0x980 [btrfs] [09.3][T4038707] ? find_lock_delalloc_range+0x33e/0x3e0 [btrfs] [09.5][T4038707] btrfs_run_delalloc_range+0x445/0x1320 [btrfs] [09.2][T4038707] ? test_range_bit+0x320/0x320 [btrfs] [09.4][T4038707] ? lock_downgrade+0x6a0/0x6a0 [09.2][T4038707] ? orc_find.part.0+0x1ed/0x300 [09.5][T4038707] ? __module_address.part.0+0x25/0x300 [09.0][T4038707] writepage_delalloc+0x159/0x310 [btrfs] <snip> [09.4][ C3] sd 10:0:1:0: [sde] tag#2620 FAILED Result: hostbyte=DID_OK driverbyte=DRIVER_OK cmd_age=0s [09.5][ C3] sd 10:0:1:0: [sde] tag#2620 Sense Key : Illegal Request [current] [09.9][ C3] sd 10:0:1:0: [sde] tag#2620 Add. Sense: Unaligned write command [09.5][ C3] sd 10:0:1:0: [sde] tag#2620 CDB: Write(16) 8a 00 00 00 00 00 02 f3 63 87 00 00 00 2c 00 00 [09.4][ C3] critical target error, dev sde, sector 396041272 op 0x1:(WRITE) flags 0x800 phys_seg 3 prio class 0 [09.9][ C3] BTRFS error (device dm-1): bdev /dev/mapper/dml_102_2 errs: wr 1, rd 0, flush 0, corrupt 0, gen 0

The IO errors occur when we allocate a regular extent in previous data relocation block group.

On zoned btrfs, we use a dedicated block group to relocate a data extent. Thus, we allocate relocating data extents (pre-alloc) only from the dedicated block group and vice versa. Once the free space in the dedicated block group gets tight, a relocating extent may not fit into the block group. In that case, we need to switch the dedicated block group to the next one. Then, the previous one is now freed up for allocating a regular extent. The BG is already not enough to allocate the relocating extent, but there is still room to allocate a smaller extent. Now the problem happens. By allocating a regular extent while nocow IOs for the relocation is still on-going, we will issue WRITE IOs (for relocation) and ZONE APPEND IOs (for the regular writes) at the same time. That mixed IOs confuses the write pointer and arises the unaligned write errors.

This commit introduces a new bit 'zoned_data_reloc_ongoing' to the btrfs_block_group. We set this bit before releasing the dedicated block group, and no extent are allocated from a block group having this bit set. This bit is similar to setting block_group->ro, but is different from it by allowing nocow writes to start.

Once all the nocow IO for relocation is done (hooked from btrfs_finish_ordered_io), we reset the bit to release the block group for further allocation.

Fixes: c2707a255623 ("btrfs: zoned: add a dedicated data relocation block group") CC: stable@vger.kernel.org # 5.16+ Signed-off-by: Naohiro Aota naohiro.aota@wdc.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com --- fs/btrfs/block-group.h | 1 + fs/btrfs/extent-tree.c | 20 ++++++++++++++++++-- fs/btrfs/inode.c | 2 ++ fs/btrfs/zoned.c | 27 +++++++++++++++++++++++++++ fs/btrfs/zoned.h | 5 +++++ 5 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 37e55ebde735..d73db0dfacb2 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -98,6 +98,7 @@ struct btrfs_block_group { unsigned int to_copy:1; unsigned int relocating_repair:1; unsigned int chunk_item_inserted:1; + unsigned int zoned_data_reloc_ongoing:1;

int disk_cache_state;

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e3514f9a4e8d..248ea15c9734 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3804,7 +3804,7 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group, block_group->start == fs_info->data_reloc_bg || fs_info->data_reloc_bg == 0);

- if (block_group->ro) { + if (block_group->ro || block_group->zoned_data_reloc_ongoing) { ret = 1; goto out; } @@ -3865,8 +3865,24 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group, out: if (ret && ffe_ctl->for_treelog) fs_info->treelog_bg = 0; - if (ret && ffe_ctl->for_data_reloc) + if (ret && ffe_ctl->for_data_reloc && + fs_info->data_reloc_bg == block_group->start) { + /* + * Do not allow further allocations from this block group. + * Compared to increasing the ->ro, setting the + * ->zoned_data_reloc_ongoing flag still allows nocow + * writers to come in. See btrfs_inc_nocow_writers(). + * + * We need to disable an allocation to avoid an allocation of + * regular (non-relocation data) extent. With mix of relocation + * extents and regular extents, we can dispatch WRITE commands + * (for relocation extents) and ZONE APPEND commands (for + * regular extents) at the same time to the same zone, which + * easily break the write pointer. + */ + block_group->zoned_data_reloc_ongoing = 1; fs_info->data_reloc_bg = 0; + } spin_unlock(&fs_info->relocation_bg_lock); spin_unlock(&fs_info->treelog_bg_lock); spin_unlock(&block_group->lock); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ea7262050790..1b4fee8a2f28 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3069,6 +3069,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) ordered_extent->file_offset, ordered_extent->file_offset + logical_len); + btrfs_zoned_release_data_reloc_bg(fs_info, ordered_extent->disk_bytenr, + ordered_extent->disk_num_bytes); } else { BUG_ON(root == fs_info->tree_root); ret = insert_ordered_extent_file_extent(trans, ordered_extent); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 574769f921a2..fc791f7c7142 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -1623,3 +1623,30 @@ void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) } mutex_unlock(&fs_devices->device_list_mutex); } + +void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical, + u64 length) +{ + struct btrfs_block_group *block_group; + + if (!btrfs_is_zoned(fs_info)) + return; + + block_group = btrfs_lookup_block_group(fs_info, logical); + /* It should be called on a previous data relocation block group. */ + ASSERT(block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)); + + spin_lock(&block_group->lock); + if (!block_group->zoned_data_reloc_ongoing) + goto out; + + /* All relocation extents are written. */ + if (block_group->start + block_group->alloc_offset == logical + length) { + /* Now, release this block group for further allocations. */ + block_group->zoned_data_reloc_ongoing = 0; + } + +out: + spin_unlock(&block_group->lock); + btrfs_put_block_group(block_group); +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 3a826f7c2040..574490ea2cc8 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -70,6 +70,8 @@ struct btrfs_device *btrfs_zoned_get_device(struct btrfs_fs_info *fs_info, u64 logical, u64 length); void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg); void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info); +void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical, + u64 length); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) @@ -207,6 +209,9 @@ static inline struct btrfs_device *btrfs_zoned_get_device( static inline void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg) { }

static inline void btrfs_free_zone_cache(struct btrfs_fs_info *fs_info) { } + +static inline void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, + u64 logical, u64 length) { } #endif

static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)