Back in 2014, commit
04216820fe83d5 ("Btrfs: fix race between fs trimming
and block group remove/allocation"), I added the 'trimming' member to the
block group structure. Its purpose was to prevent races between trimming
and block group deletion/allocation by pinning the block group in a way
that prevents its logical address and device extents from being reused
while trimming is in progress for a block group, so that if another task
deletes the block group and then another task allocates a new block group
that gets the same logical address and device extents while the trimming
task is still in progress.
After the previous fix for scrub (patch "btrfs: fix a race between scrub
and block group removal/allocation"), scrub now also has the same needs that
trimming has, so the member name 'trimming' no longer makes sense.
Since there is already a 'pinned' member in the block group that refers
to space reservations (pinned bytes), rename the member to 'frozen',
add a comment on top of it to describe its general purpose and rename
the helpers to increment and decrement the counter as well, to match
the new member name.
The next patch in the series will move the helpers into a more suitable
file (from free-space-cache.c to block-group.c).
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
spin_lock(&block_group->lock);
block_group->removed = 1;
/*
- * At this point trimming can't start on this block group, because we
- * removed the block group from the tree fs_info->block_group_cache_tree
- * so no one can't find it anymore and even if someone already got this
- * block group before we removed it from the rbtree, they have already
- * incremented block_group->trimming - if they didn't, they won't find
- * any free space entries because we already removed them all when we
- * called btrfs_remove_free_space_cache().
+ * At this point trimming or scrub can't start on this block group,
+ * because we removed the block group from the rbtree
+ * fs_info->block_group_cache_tree so no one can't find it anymore and
+ * even if someone already got this block group before we removed it
+ * from the rbtree, they have already incremented block_group->frozen -
+ * if they didn't, for the trimming case they won't find any free space
+ * entries because we already removed them all when we called
+ * btrfs_remove_free_space_cache().
*
* And we must not remove the extent map from the fs_info->mapping_tree
* to prevent the same logical address range and physical device space
- * ranges from being reused for a new block group. This is because our
- * fs trim operation (btrfs_trim_fs() / btrfs_ioctl_fitrim()) is
+ * ranges from being reused for a new block group. This is needed to
+ * avoid races with trimming and scrub.
+ *
+ * An fs trim operation (btrfs_trim_fs() / btrfs_ioctl_fitrim()) is
* completely transactionless, so while it is trimming a range the
* currently running transaction might finish and a new one start,
* allowing for new block groups to be created that can reuse the same
* in place until the extents have been discarded completely when
* the transaction commit has completed.
*/
- remove_em = (atomic_read(&block_group->trimming) == 0);
+ remove_em = (atomic_read(&block_group->frozen) == 0);
spin_unlock(&block_group->lock);
mutex_unlock(&fs_info->chunk_mutex);
/* Implicit trim during transaction commit. */
if (trimming)
- btrfs_get_block_group_trimming(block_group);
+ btrfs_freeze_block_group(block_group);
/*
* Btrfs_remove_chunk will abort the transaction if things go
if (ret) {
if (trimming)
- btrfs_put_block_group_trimming(block_group);
+ btrfs_unfreeze_block_group(block_group);
goto end_trans;
}
INIT_LIST_HEAD(&cache->dirty_list);
INIT_LIST_HEAD(&cache->io_list);
btrfs_init_free_space_ctl(cache);
- atomic_set(&cache->trimming, 0);
+ atomic_set(&cache->frozen, 0);
mutex_init(&cache->free_space_lock);
btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);
/* For read-only block groups */
struct list_head ro_list;
+ /*
+ * When non-zero it means the block group's logical address and its
+ * device extents can not be reused for future block group allocations
+ * until the counter goes down to 0. This is to prevent them from being
+ * reused while some task is still using the block group after it was
+ * deleted - we want to make sure they can only be reused for new block
+ * groups after that task is done with the deleted block group.
+ */
+ atomic_t frozen;
+
/* For discard operations */
- atomic_t trimming;
struct list_head discard_list;
int discard_index;
u64 discard_eligible_time;
struct btrfs_ref *generic_ref);
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
-void btrfs_get_block_group_trimming(struct btrfs_block_group *cache);
-void btrfs_put_block_group_trimming(struct btrfs_block_group *cache);
+void btrfs_freeze_block_group(struct btrfs_block_group *cache);
+void btrfs_unfreeze_block_group(struct btrfs_block_group *cache);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
enum btrfs_reserve_flush_enum {
&trimmed);
list_del_init(&block_group->bg_list);
- btrfs_put_block_group_trimming(block_group);
+ btrfs_unfreeze_block_group(block_group);
btrfs_put_block_group(block_group);
if (ret) {
return ret;
}
-void btrfs_get_block_group_trimming(struct btrfs_block_group *cache)
+void btrfs_freeze_block_group(struct btrfs_block_group *cache)
{
- atomic_inc(&cache->trimming);
+ atomic_inc(&cache->frozen);
}
-void btrfs_put_block_group_trimming(struct btrfs_block_group *block_group)
+void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group)
{
struct btrfs_fs_info *fs_info = block_group->fs_info;
struct extent_map_tree *em_tree;
bool cleanup;
spin_lock(&block_group->lock);
- cleanup = (atomic_dec_and_test(&block_group->trimming) &&
+ cleanup = (atomic_dec_and_test(&block_group->frozen) &&
block_group->removed);
spin_unlock(&block_group->lock);
free_extent_map(em);
/*
- * We've left one free space entry and other tasks trimming
- * this block group have left 1 entry each one. Free them.
+ * We may have left one free space entry and other possible
+ * tasks trimming this block group have left 1 entry each one.
+ * Free them if any.
*/
__btrfs_remove_free_space_cache(block_group->free_space_ctl);
}
spin_unlock(&block_group->lock);
return 0;
}
- btrfs_get_block_group_trimming(block_group);
+ btrfs_freeze_block_group(block_group);
spin_unlock(&block_group->lock);
ret = trim_no_bitmap(block_group, trimmed, start, end, minlen, false);
if (rem)
reset_trimming_bitmap(ctl, offset_to_bitmap(ctl, end));
out:
- btrfs_put_block_group_trimming(block_group);
+ btrfs_unfreeze_block_group(block_group);
return ret;
}
spin_unlock(&block_group->lock);
return 0;
}
- btrfs_get_block_group_trimming(block_group);
+ btrfs_freeze_block_group(block_group);
spin_unlock(&block_group->lock);
ret = trim_no_bitmap(block_group, trimmed, start, end, minlen, async);
- btrfs_put_block_group_trimming(block_group);
+ btrfs_unfreeze_block_group(block_group);
return ret;
}
spin_unlock(&block_group->lock);
return 0;
}
- btrfs_get_block_group_trimming(block_group);
+ btrfs_freeze_block_group(block_group);
spin_unlock(&block_group->lock);
ret = trim_bitmaps(block_group, trimmed, start, end, minlen, maxlen,
async);
- btrfs_put_block_group_trimming(block_group);
+ btrfs_unfreeze_block_group(block_group);
return ret;
}
btrfs_put_block_group(cache);
goto skip;
}
- btrfs_get_block_group_trimming(cache);
+ btrfs_freeze_block_group(cache);
spin_unlock(&cache->lock);
/*
} else {
btrfs_warn(fs_info,
"failed setting block group ro: %d", ret);
- btrfs_put_block_group_trimming(cache);
+ btrfs_unfreeze_block_group(cache);
btrfs_put_block_group(cache);
scrub_pause_off(fs_info);
break;
spin_unlock(&cache->lock);
}
- btrfs_put_block_group_trimming(cache);
+ btrfs_unfreeze_block_group(cache);
btrfs_put_block_group(cache);
if (ret)
break;
struct btrfs_block_group,
bg_list);
list_del_init(&cache->bg_list);
- btrfs_put_block_group_trimming(cache);
+ btrfs_unfreeze_block_group(cache);
btrfs_put_block_group(cache);
}
WARN_ON(!list_empty(&transaction->dev_update_list));
projects / mirror_ubuntu-jammy-kernel.git / commitdiff