btrfs: fix race between writes to swap files and scrub

When we active a swap file, at btrfs_swap_activate(), we acquire the
exclusive operation lock to prevent the physical location of the swap
file extents to be changed by operations such as balance and device
replace/resize/remove. We also call there can_nocow_extent() which,
among other things, checks if the block group of a swap file extent is
currently RO, and if it is we can not use the extent, since a write
into it would result in COWing the extent.

However we have no protection against a scrub operation running after we
activate the swap file, which can result in the swap file extents to be
COWed while the scrub is running and operating on the respective block
group, because scrub turns a block group into RO before it processes it
and then back again to RW mode after processing it. That means an attempt
to write into a swap file extent while scrub is processing the respective
block group, will result in COWing the extent, changing its physical
location on disk.

Fix this by making sure that block groups that have extents that are used
by active swap files can not be turned into RO mode, therefore making it
not possible for a scrub to turn them into RO mode. When a scrub finds a
block group that can not be turned to RO due to the existence of extents
used by swap files, it proceeds to the next block group and logs a warning
message that mentions the block group was skipped due to active swap
files - this is the same approach we currently use for balance.

Fixes: ed46ff3d42378 ("Btrfs: support swap files")
CC: stable@vger.kernel.org # 5.4+
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 32 insertions, 1 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 5064be59dac5..744b99ddc28c 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1162,6 +1162,11 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
 	spin_lock(&sinfo->lock);
 	spin_lock(&cache->lock);
 
+	if (cache->swap_extents) {
+		ret = -ETXTBSY;
+		goto out;
+	}
+
 	if (cache->ro) {
 		cache->ro++;
 		ret = 0;
@@ -2307,7 +2312,7 @@ again:
 	}
 
 	ret = inc_block_group_ro(cache, 0);
-	if (!do_chunk_alloc)
+	if (!do_chunk_alloc || ret == -ETXTBSY)
 		goto unlock_out;
 	if (!ret)
 		goto out;
@@ -2316,6 +2321,8 @@ again:
 	if (ret < 0)
 		goto out;
 	ret = inc_block_group_ro(cache, 0);
+	if (ret == -ETXTBSY)
+		goto unlock_out;
 out:
 	if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
 		alloc_flags = btrfs_get_alloc_profile(fs_info, cache->flags);
@@ -3406,6 +3413,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		ASSERT(list_empty(&block_group->io_list));
 		ASSERT(list_empty(&block_group->bg_list));
 		ASSERT(refcount_read(&block_group->refs) == 1);
+		ASSERT(block_group->swap_extents == 0);
 		btrfs_put_block_group(block_group);
 
 		spin_lock(&info->block_group_cache_lock);
@@ -3472,3 +3480,26 @@ void btrfs_unfreeze_block_group(struct btrfs_block_group *block_group)
 		__btrfs_remove_free_space_cache(block_group->free_space_ctl);
 	}
 }
+
+bool btrfs_inc_block_group_swap_extents(struct btrfs_block_group *bg)
+{
+	bool ret = true;
+
+	spin_lock(&bg->lock);
+	if (bg->ro)
+		ret = false;
+	else
+		bg->swap_extents++;
+	spin_unlock(&bg->lock);
+
+	return ret;
+}
+
+void btrfs_dec_block_group_swap_extents(struct btrfs_block_group *bg, int amount)
+{
+	spin_lock(&bg->lock);
+	ASSERT(!bg->ro);
+	ASSERT(bg->swap_extents >= amount);
+	bg->swap_extents -= amount;
+	spin_unlock(&bg->lock);
+}