ext4: check journal inode extents more carefully

commit ce9f24cccdc019229b70a5c15e2b09ad9c0ab5d1 upstream.

Currently, system zones just track ranges of block, that are "important"
fs metadata (bitmaps, group descriptors, journal blocks, etc.). This
however complicates how extent tree (or indirect blocks) can be checked
for inodes that actually track such metadata - currently the journal
inode but arguably we should be treating quota files or resize inode
similarly. We cannot run __ext4_ext_check() on such metadata inodes when
loading their extents as that would immediately trigger the validity
checks and so we just hack around that and special-case the journal
inode. This however leads to a situation that a journal inode which has
extent tree of depth at least one can have invalid extent tree that gets
unnoticed until ext4_cache_extents() crashes.

To overcome this limitation, track inode number each system zone belongs
to (0 is used for zones not belonging to any inode). We can then verify
inode number matches the expected one when verifying extent tree and
thus avoid the false errors. With this there's no need to to
special-case journal inode during extent tree checking anymore so remove
it.

Fixes: 0a944e8a6c66 ("ext4: don't perform block validity checks on the journal inode")
Reported-by: Wolfgang Frisch <wolfgang.frisch@suse.com>
Reviewed-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20200728130437.7804-4-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 22 insertions, 21 deletions

diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index f22a89cdb407..1ea8fc9ff048 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -24,6 +24,7 @@ struct ext4_system_zone {
 	struct rb_node	node;
 	ext4_fsblk_t	start_blk;
 	unsigned int	count;
+	u32		ino;
 };
 
 static struct kmem_cache *ext4_system_zone_cachep;
@@ -45,7 +46,8 @@ void ext4_exit_system_zone(void)
 static inline int can_merge(struct ext4_system_zone *entry1,
 		     struct ext4_system_zone *entry2)
 {
-	if ((entry1->start_blk + entry1->count) == entry2->start_blk)
+	if ((entry1->start_blk + entry1->count) == entry2->start_blk &&
+	    entry1->ino == entry2->ino)
 		return 1;
 	return 0;
 }
@@ -66,7 +68,7 @@ static void release_system_zone(struct ext4_system_blocks *system_blks)
  */
 static int add_system_zone(struct ext4_system_blocks *system_blks,
 			   ext4_fsblk_t start_blk,
-			   unsigned int count)
+			   unsigned int count, u32 ino)
 {
 	struct ext4_system_zone *new_entry, *entry;
 	struct rb_node **n = &system_blks->root.rb_node, *node;
@@ -89,6 +91,7 @@ static int add_system_zone(struct ext4_system_blocks *system_blks,
 		return -ENOMEM;
 	new_entry->start_blk = start_blk;
 	new_entry->count = count;
+	new_entry->ino = ino;
 	new_node = &new_entry->node;
 
 	rb_link_node(new_node, parent, n);
@@ -145,7 +148,7 @@ static void debug_print_tree(struct ext4_sb_info *sbi)
 static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi,
 				     struct ext4_system_blocks *system_blks,
 				     ext4_fsblk_t start_blk,
-				     unsigned int count)
+				     unsigned int count, ino_t ino)
 {
 	struct ext4_system_zone *entry;
 	struct rb_node *n;
@@ -169,7 +172,7 @@ static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi,
 			n = n->rb_right;
 		else {
 			sbi->s_es->s_last_error_block = cpu_to_le64(start_blk);
-			return 0;
+			return entry->ino == ino;
 		}
 	}
 	return 1;
@@ -204,17 +207,16 @@ static int ext4_protect_reserved_inode(struct super_block *sb,
 		if (n == 0) {
 			i++;
 		} else {
-			if (!ext4_data_block_valid_rcu(sbi, system_blks,
-						map.m_pblk, n)) {
-				ext4_error(sb, "blocks %llu-%llu from inode %u "
+			err = add_system_zone(system_blks, map.m_pblk, n, ino);
+			if (err < 0) {
+				if (err == -EFSCORRUPTED) {
+					ext4_error(sb,
+					   "blocks %llu-%llu from inode %u "
 					   "overlap system zone", map.m_pblk,
 					   map.m_pblk + map.m_len - 1, ino);
-				err = -EFSCORRUPTED;
+				}
 				break;
 			}
-			err = add_system_zone(system_blks, map.m_pblk, n);
-			if (err < 0)
-				break;
 			i += n;
 		}
 	}
@@ -259,19 +261,19 @@ int ext4_setup_system_zone(struct super_block *sb)
 		    ((i < 5) || ((i % flex_size) == 0)))
 			add_system_zone(system_blks,
 					ext4_group_first_block_no(sb, i),
-					ext4_bg_num_gdb(sb, i) + 1);
+					ext4_bg_num_gdb(sb, i) + 1, 0);
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		ret = add_system_zone(system_blks,
-				ext4_block_bitmap(sb, gdp), 1);
+				ext4_block_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			goto err;
 		ret = add_system_zone(system_blks,
-				ext4_inode_bitmap(sb, gdp), 1);
+				ext4_inode_bitmap(sb, gdp), 1, 0);
 		if (ret)
 			goto err;
 		ret = add_system_zone(system_blks,
 				ext4_inode_table(sb, gdp),
-				sbi->s_itb_per_group);
+				sbi->s_itb_per_group, 0);
 		if (ret)
 			goto err;
 	}
@@ -320,7 +322,7 @@ void ext4_release_system_zone(struct super_block *sb)
 		call_rcu(&system_blks->rcu, ext4_destroy_system_zone);
 }
 
-int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
+int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk,
 			  unsigned int count)
 {
 	struct ext4_system_blocks *system_blks;
@@ -332,9 +334,9 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk,
 	 * mount option.
 	 */
 	rcu_read_lock();
-	system_blks = rcu_dereference(sbi->system_blks);
-	ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk,
-					count);
+	system_blks = rcu_dereference(EXT4_SB(inode->i_sb)->system_blks);
+	ret = ext4_data_block_valid_rcu(EXT4_SB(inode->i_sb), system_blks,
+					start_blk, count, inode->i_ino);
 	rcu_read_unlock();
 	return ret;
 }
@@ -354,8 +356,7 @@ int ext4_check_blockref(const char *function, unsigned int line,
 	while (bref < p+max) {
 		blk = le32_to_cpu(*bref++);
 		if (blk &&
-		    unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb),
-						    blk, 1))) {
+		    unlikely(!ext4_inode_block_valid(inode, blk, 1))) {
 			es->s_last_error_block = cpu_to_le64(blk);
 			ext4_error_inode(inode, function, line, blk,
 					 "invalid block");