Commit 93bba24d4b5ad1e5cd8b43f64e66ff9d6355dd20 upstream.

Function btrfs_trim_fs() doesn't handle errors in a consistent way. If error happens when trimming existing block groups, it will skip the remaining blocks and continue to trim unallocated space for each device.

The return value will only reflect the final error from device trimming.

This patch will fix such behavior by:

1) Recording the last error from block group or device trimming The return value will also reflect the last error during trimming. Make developer more aware of the problem.

2) Continuing trimming if possible If we failed to trim one block group or device, we could still try the next block group or device.

3) Report number of failures during block group and device trimming It would be less noisy, but still gives user a brief summary of what's going wrong.

Such behavior can avoid confusion for cases like failure to trim the first block group and then only unallocated space is trimmed.

Reported-by: Chris Murphy lists@colorremedies.com CC: stable@vger.kernel.org # 4.9 Signed-off-by: Qu Wenruo wqu@suse.com Reviewed-by: David Sterba dsterba@suse.com [ add bg_ret and dev_ret to the messages ] Signed-off-by: David Sterba dsterba@suse.com --- fs/btrfs/extent-tree.c | 40 +++++++++++++++++++++++++++++----------- 1 file changed, 29 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 6661116c47d9..4f28fef9dc7f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -11124,6 +11124,10 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) u64 end; u64 trimmed = 0; u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy); + u64 bg_failed = 0; + u64 dev_failed = 0; + int bg_ret = 0; + int dev_ret = 0; int ret = 0;

/* @@ -11134,7 +11138,7 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) else cache = btrfs_lookup_block_group(fs_info, range->start);

- while (cache) { + for (; cache; cache = next_block_group(fs_info->tree_root, cache)) { if (cache->key.objectid >= (range->start + range->len)) { btrfs_put_block_group(cache); break; @@ -11148,13 +11152,15 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range) if (!block_group_cache_done(cache)) { ret = cache_block_group(cache, 0); if (ret) { - btrfs_put_block_group(cache); - break; + bg_failed++; + bg_ret = ret; + continue; } ret = wait_block_group_cache_done(cache); if (ret) { - btrfs_put_block_group(cache); - break; + bg_failed++; + bg_ret = ret; + continue; } } ret = btrfs_trim_block_group(cache, @@ -11165,28 +11171,40 @@ int btrfs_trim_fs(struct btrfs_root *root, struct fstrim_range *range)

trimmed += group_trimmed; if (ret) { - btrfs_put_block_group(cache); - break; + bg_failed++; + bg_ret = ret; + continue; } } - - cache = next_block_group(fs_info->tree_root, cache); }

+ if (bg_failed) + btrfs_warn(fs_info, + "failed to trim %llu block group(s), last error %d", + bg_failed, bg_ret); mutex_lock(&root->fs_info->fs_devices->device_list_mutex); devices = &root->fs_info->fs_devices->alloc_list; list_for_each_entry(device, devices, dev_alloc_list) { ret = btrfs_trim_free_extents(device, range->minlen, &group_trimmed); - if (ret) + if (ret) { + dev_failed++; + dev_ret = ret; break; + }

trimmed += group_trimmed; } mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);

+ if (dev_failed) + btrfs_warn(fs_info, + "failed to trim %llu device(s), last error %d", + dev_failed, dev_ret); range->len = trimmed; - return ret; + if (bg_ret) + return bg_ret; + return dev_ret; }

/*