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, 18 insertions, 1 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d6f0e1ad3711..30358a2e2bc0 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10192,6 +10192,7 @@ static int btrfs_add_swapfile_pin(struct inode *inode, void *ptr,
 	sp->ptr = ptr;
 	sp->inode = inode;
 	sp->is_block_group = is_block_group;
+	sp->bg_extent_count = 1;
 
 	spin_lock(&fs_info->swapfile_pins_lock);
 	p = &fs_info->swapfile_pins.rb_node;
@@ -10205,6 +10206,8 @@ static int btrfs_add_swapfile_pin(struct inode *inode, void *ptr,
 			   (sp->ptr == entry->ptr && sp->inode > entry->inode)) {
 			p = &(*p)->rb_right;
 		} else {
+			if (is_block_group)
+				entry->bg_extent_count++;
 			spin_unlock(&fs_info->swapfile_pins_lock);
 			kfree(sp);
 			return 1;
@@ -10230,8 +10233,11 @@ static void btrfs_free_swapfile_pins(struct inode *inode)
 		sp = rb_entry(node, struct btrfs_swapfile_pin, node);
 		if (sp->inode == inode) {
 			rb_erase(&sp->node, &fs_info->swapfile_pins);
-			if (sp->is_block_group)
+			if (sp->is_block_group) {
+				btrfs_dec_block_group_swap_extents(sp->ptr,
+							   sp->bg_extent_count);
 				btrfs_put_block_group(sp->ptr);
+			}
 			kfree(sp);
 		}
 		node = next;
@@ -10446,6 +10452,17 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 			goto out;
 		}
 
+		if (!btrfs_inc_block_group_swap_extents(bg)) {
+			btrfs_warn(fs_info,
+			   "block group for swapfile at %llu is read-only%s",
+			   bg->start,
+			   atomic_read(&fs_info->scrubs_running) ?
+				       " (scrub running)" : "");
+			btrfs_put_block_group(bg);
+			ret = -EINVAL;
+			goto out;
+		}
+
 		ret = btrfs_add_swapfile_pin(inode, bg, true);
 		if (ret) {
 			btrfs_put_block_group(bg);