diff options
| author | Filipe Manana <fdmanana@suse.com> | 2024-09-24 15:58:31 +0100 |
|---|---|---|
| committer | David Sterba <dsterba@suse.com> | 2024-10-11 18:33:35 +0200 |
| commit | 97420be7bda57030110c7032ad190d320f2e0157 (patch) | |
| tree | 82cee71ce13b7e21ecc428a939f8ecea10e6a475 /fs/btrfs/delayed-ref.c | |
| parent | e761be2a0744086fc4793a4870d4b5746b7fe8cd (diff) | |
| download | linux-97420be7bda57030110c7032ad190d320f2e0157.tar.gz linux-97420be7bda57030110c7032ad190d320f2e0157.tar.bz2 linux-97420be7bda57030110c7032ad190d320f2e0157.zip | |
btrfs: use sector numbers as keys for the dirty extents xarray
We are using the logical address ("bytenr") of an extent as the key for
qgroup records in the dirty extents xarray. This is a problem because the
xarrays use "unsigned long" for keys/indices, meaning that on a 32 bits
platform any extent starting at or beyond 4G is truncated, which is a too
low limitation as virtually everyone is using storage with more than 4G of
space. This means a "bytenr" of 4G gets truncated to 0, and so does 8G and
16G for example, resulting in incorrect qgroup accounting.
Fix this by using sector numbers as keys instead, that is, using keys that
match the logical address right shifted by fs_info->sectorsize_bits, which
is what we do for the fs_info->buffer_radix that tracks extent buffers
(radix trees also use an "unsigned long" type for keys). This also makes
the index space more dense which helps optimize the xarray (as mentioned
at Documentation/core-api/xarray.rst).
Fixes: 3cce39a8ca4e ("btrfs: qgroup: use xarray to track dirty extents in transaction")
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Diffstat (limited to 'fs/btrfs/delayed-ref.c')
| -rw-r--r-- | fs/btrfs/delayed-ref.c | 15 |
1 files changed, 8 insertions, 7 deletions
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 32f719b9e661..115b90d29b1d 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -849,6 +849,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, struct btrfs_qgroup_extent_record *qrecord, int action, bool *qrecord_inserted_ret) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_root *delayed_refs; bool qrecord_inserted = false; @@ -859,11 +860,11 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, if (qrecord) { int ret; - ret = btrfs_qgroup_trace_extent_nolock(trans->fs_info, - delayed_refs, qrecord); + ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, qrecord); if (ret) { /* Clean up if insertion fails or item exists. */ - xa_release(&delayed_refs->dirty_extents, qrecord->bytenr); + xa_release(&delayed_refs->dirty_extents, + qrecord->bytenr >> fs_info->sectorsize_bits); /* Caller responsible for freeing qrecord on error. */ if (ret < 0) return ERR_PTR(ret); @@ -873,7 +874,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, } } - trace_add_delayed_ref_head(trans->fs_info, head_ref, action); + trace_add_delayed_ref_head(fs_info, head_ref, action); existing = htree_insert(&delayed_refs->href_root, &head_ref->href_node); @@ -895,8 +896,7 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans, if (head_ref->is_data && head_ref->ref_mod < 0) { delayed_refs->pending_csums += head_ref->num_bytes; trans->delayed_ref_csum_deletions += - btrfs_csum_bytes_to_leaves(trans->fs_info, - head_ref->num_bytes); + btrfs_csum_bytes_to_leaves(fs_info, head_ref->num_bytes); } delayed_refs->num_heads++; delayed_refs->num_heads_ready++; @@ -1030,7 +1030,8 @@ static int add_delayed_ref(struct btrfs_trans_handle *trans, goto free_head_ref; } if (xa_reserve(&trans->transaction->delayed_refs.dirty_extents, - generic_ref->bytenr, GFP_NOFS)) { + generic_ref->bytenr >> fs_info->sectorsize_bits, + GFP_NOFS)) { ret = -ENOMEM; goto free_record; } |