btrfs: add missing inode updates on each iteration when replacing extents

When replacing file extents, called during fallocate, hole punching,
clone and deduplication, we may not be able to replace/drop all the
target file extent items with a single transaction handle. We may get
-ENOSPC while doing it, in which case we release the transaction handle,
balance the dirty pages of the btree inode, flush delayed items and get
a new transaction handle to operate on what's left of the target range.

By dropping and replacing file extent items we have effectively modified
the inode, so we should bump its iversion and update its mtime/ctime
before we update the inode item. This is because if the transaction
we used for partially modifying the inode gets committed by someone after
we release it and before we finish the rest of the range, a power failure
happens, then after mounting the filesystem our inode has an outdated
iversion and mtime/ctime, corresponding to the values it had before we
changed it.

So add the missing iversion and mtime/ctime updates.

Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

4 files changed, 23 insertions, 0 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0e49b1a0c071..415bf1823fb3 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1330,6 +1330,8 @@ struct btrfs_replace_extent_info {
 	 * existing extent into a file range.
 	 */
 	bool is_new_extent;
+	/* Indicate if we should update the inode's mtime and ctime. */
+	bool update_times;
 	/* Meaningful only if is_new_extent is true. */
 	int qgroup_reserved;
 	/*
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 46c2baa8fdf5..8e7fb3e6f79c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2802,6 +2802,25 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
 			extent_info->file_offset += replace_len;
 		}
 
+		/*
+		 * We are releasing our handle on the transaction, balance the
+		 * dirty pages of the btree inode and flush delayed items, and
+		 * then get a new transaction handle, which may now point to a
+		 * new transaction in case someone else may have committed the
+		 * transaction we used to replace/drop file extent items. So
+		 * bump the inode's iversion and update mtime and ctime except
+		 * if we are called from a dedupe context. This is because a
+		 * power failure/crash may happen after the transaction is
+		 * committed and before we finish replacing/dropping all the
+		 * file extent items we need.
+		 */
+		inode_inc_iversion(&inode->vfs_inode);
+
+		if (!extent_info || extent_info->update_times) {
+			inode->vfs_inode.i_mtime = current_time(&inode->vfs_inode);
+			inode->vfs_inode.i_ctime = inode->vfs_inode.i_mtime;
+		}
+
 		ret = btrfs_update_inode(trans, root, inode);
 		if (ret)
 			break;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index da13bd0d10f1..a642d34c1363 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9897,6 +9897,7 @@ static struct btrfs_trans_handle *insert_prealloc_file_extent(
 	extent_info.file_offset = file_offset;
 	extent_info.extent_buf = (char *)&stack_fi;
 	extent_info.is_new_extent = true;
+	extent_info.update_times = true;
 	extent_info.qgroup_reserved = qgroup_released;
 	extent_info.insertions = 0;
 
diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c
index 912f4aa21a24..a3549d587464 100644
--- a/fs/btrfs/reflink.c
+++ b/fs/btrfs/reflink.c
@@ -496,6 +496,7 @@ process_slot:
 			clone_info.file_offset = new_key.offset;
 			clone_info.extent_buf = buf;
 			clone_info.is_new_extent = false;
+			clone_info.update_times = !no_time_update;
 			ret = btrfs_replace_file_extents(BTRFS_I(inode), path,
 					drop_start, new_key.offset + datal - 1,
 					&clone_info, &trans);