Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 bug fixes from Ted Ts'o:
 "Ext4 bug fixes, including a regression fix"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: clarify impact of 'commit' mount option
  ext4: fix unused-but-set-variable warning in ext4_add_entry()
  jbd2: fix kernel-doc notation warning
  ext4: use RCU API in debug_print_tree
  ext4: validate the debug_want_extra_isize mount option at parse time
  ext4: reserve revoke credits in __ext4_new_inode
  ext4: unlock on error in ext4_expand_extra_isize()
  ext4: optimize __ext4_check_dir_entry()
  ext4: check for directory entries too close to block end
  ext4: fix ext4_empty_dir() for directories with holes

Author: torvalds

Documentation/admin-guide/ext4.rst

@@ -181,14 +181,17 @@ When mounting an ext4 filesystem, the following option are accepted:
         system after its metadata has been committed to the journal.
 
   commit=nrsec	(*)
-        Ext4 can be told to sync all its data and metadata every 'nrsec'
-        seconds. The default value is 5 seconds.  This means that if you lose
-        your power, you will lose as much as the latest 5 seconds of work (your
-        filesystem will not be damaged though, thanks to the journaling).  This
-        default value (or any low value) will hurt performance, but it's good
-        for data-safety.  Setting it to 0 will have the same effect as leaving
-        it at the default (5 seconds).  Setting it to very large values will
-        improve performance.
+        This setting limits the maximum age of the running transaction to
+        'nrsec' seconds.  The default value is 5 seconds.  This means that if
+        you lose your power, you will lose as much as the latest 5 seconds of
+        metadata changes (your filesystem will not be damaged though, thanks
+        to the journaling). This default value (or any low value) will hurt
+        performance, but it's good for data-safety.  Setting it to 0 will have
+        the same effect as leaving it at the default (5 seconds).  Setting it
+        to very large values will improve performance.  Note that due to
+        delayed allocation even older data can be lost on power failure since
+        writeback of those data begins only after time set in
+        /proc/sys/vm/dirty_expire_centisecs.
 
   barrier=<0|1(*)>, barrier(*), nobarrier
         This enables/disables the use of write barriers in the jbd code.

fs/ext4/block_validity.c

@@ -133,17 +133,21 @@ static void debug_print_tree(struct ext4_sb_info *sbi)
 {
 	struct rb_node *node;
 	struct ext4_system_zone *entry;
+	struct ext4_system_blocks *system_blks;
 	int first = 1;
 
 	printk(KERN_INFO "System zones: ");
-	node = rb_first(&sbi->system_blks->root);
+	rcu_read_lock();
+	system_blks = rcu_dereference(sbi->system_blks);
+	node = rb_first(&system_blks->root);
 	while (node) {
 		entry = rb_entry(node, struct ext4_system_zone, node);
 		printk(KERN_CONT "%s%llu-%llu", first ? "" : ", ",
 		       entry->start_blk, entry->start_blk + entry->count - 1);
 		first = 0;
 		node = rb_next(node);
 	}
+	rcu_read_unlock();
 	printk(KERN_CONT "\n");
 }
 

fs/ext4/dir.c

@@ -72,15 +72,19 @@ int __ext4_check_dir_entry(const char *function, unsigned int line,
 	const char *error_msg = NULL;
 	const int rlen = ext4_rec_len_from_disk(de->rec_len,
 						dir->i_sb->s_blocksize);
+	const int next_offset = ((char *) de - buf) + rlen;
 
 	if (unlikely(rlen < EXT4_DIR_REC_LEN(1)))
 		error_msg = "rec_len is smaller than minimal";
 	else if (unlikely(rlen % 4 != 0))
 		error_msg = "rec_len % 4 != 0";
 	else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len)))
 		error_msg = "rec_len is too small for name_len";
-	else if (unlikely(((char *) de - buf) + rlen > size))
+	else if (unlikely(next_offset > size))
 		error_msg = "directory entry overrun";
+	else if (unlikely(next_offset > size - EXT4_DIR_REC_LEN(1) &&
+			  next_offset != size))
+		error_msg = "directory entry too close to block end";
 	else if (unlikely(le32_to_cpu(de->inode) >
 			le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count)))
 		error_msg = "inode out of bounds";

fs/ext4/ialloc.c

@@ -921,8 +921,8 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 		if (!handle) {
 			BUG_ON(nblocks <= 0);
 			handle = __ext4_journal_start_sb(dir->i_sb, line_no,
-							 handle_type, nblocks,
-							 0, 0);
+				 handle_type, nblocks, 0,
+				 ext4_trans_default_revoke_credits(sb));
 			if (IS_ERR(handle)) {
 				err = PTR_ERR(handle);
 				ext4_std_error(sb, err);

fs/ext4/inode.c

@@ -5692,7 +5692,7 @@ int ext4_expand_extra_isize(struct inode *inode,
 	error = ext4_journal_get_write_access(handle, iloc->bh);
 	if (error) {
 		brelse(iloc->bh);
-		goto out_stop;
+		goto out_unlock;
 	}
 
 	error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc,
@@ -5702,8 +5702,8 @@ int ext4_expand_extra_isize(struct inode *inode,
 	if (!error)
 		error = rc;
 
+out_unlock:
 	ext4_write_unlock_xattr(inode, &no_expand);
-out_stop:
 	ext4_journal_stop(handle);
 	return error;
 }

fs/ext4/namei.c

@@ -2164,7 +2164,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	struct buffer_head *bh = NULL;
 	struct ext4_dir_entry_2 *de;
 	struct super_block *sb;
+#ifdef CONFIG_UNICODE
 	struct ext4_sb_info *sbi;
+#endif
 	struct ext4_filename fname;
 	int	retval;
 	int	dx_fallback=0;
@@ -2176,12 +2178,12 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 		csum_size = sizeof(struct ext4_dir_entry_tail);
 
 	sb = dir->i_sb;
-	sbi = EXT4_SB(sb);
 	blocksize = sb->s_blocksize;
 	if (!dentry->d_name.len)
 		return -EINVAL;
 
 #ifdef CONFIG_UNICODE
+	sbi = EXT4_SB(sb);
 	if (ext4_has_strict_mode(sbi) && IS_CASEFOLDED(dir) &&
 	    sbi->s_encoding && utf8_validate(sbi->s_encoding, &dentry->d_name))
 		return -EINVAL;
@@ -2822,7 +2824,7 @@ bool ext4_empty_dir(struct inode *inode)
 {
 	unsigned int offset;
 	struct buffer_head *bh;
-	struct ext4_dir_entry_2 *de, *de1;
+	struct ext4_dir_entry_2 *de;
 	struct super_block *sb;
 
 	if (ext4_has_inline_data(inode)) {
@@ -2847,19 +2849,25 @@ bool ext4_empty_dir(struct inode *inode)
 		return true;
 
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
-	de1 = ext4_next_entry(de, sb->s_blocksize);
-	if (le32_to_cpu(de->inode) != inode->i_ino ||
-			le32_to_cpu(de1->inode) == 0 ||
-			strcmp(".", de->name) || strcmp("..", de1->name)) {
-		ext4_warning_inode(inode, "directory missing '.' and/or '..'");
+	if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size,
+				 0) ||
+	    le32_to_cpu(de->inode) != inode->i_ino || strcmp(".", de->name)) {
+		ext4_warning_inode(inode, "directory missing '.'");
+		brelse(bh);
+		return true;
+	}
+	offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
+	de = ext4_next_entry(de, sb->s_blocksize);
+	if (ext4_check_dir_entry(inode, NULL, de, bh, bh->b_data, bh->b_size,
+				 offset) ||
+	    le32_to_cpu(de->inode) == 0 || strcmp("..", de->name)) {
+		ext4_warning_inode(inode, "directory missing '..'");
 		brelse(bh);
 		return true;
 	}
-	offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) +
-		 ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
-	de = ext4_next_entry(de1, sb->s_blocksize);
+	offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
 	while (offset < inode->i_size) {
-		if ((void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
+		if (!(offset & (sb->s_blocksize - 1))) {
 			unsigned int lblock;
 			brelse(bh);
 			lblock = offset >> EXT4_BLOCK_SIZE_BITS(sb);
@@ -2870,12 +2878,11 @@ bool ext4_empty_dir(struct inode *inode)
 			}
 			if (IS_ERR(bh))
 				return true;
-			de = (struct ext4_dir_entry_2 *) bh->b_data;
 		}
+		de = (struct ext4_dir_entry_2 *) (bh->b_data +
+					(offset & (sb->s_blocksize - 1)));
 		if (ext4_check_dir_entry(inode, NULL, de, bh,
 					 bh->b_data, bh->b_size, offset)) {
-			de = (struct ext4_dir_entry_2 *)(bh->b_data +
-							 sb->s_blocksize);
 			offset = (offset | (sb->s_blocksize - 1)) + 1;
 			continue;
 		}
@@ -2884,7 +2891,6 @@ bool ext4_empty_dir(struct inode *inode)
 			return false;
 		}
 		offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
-		de = ext4_next_entry(de, sb->s_blocksize);
 	}
 	brelse(bh);
 	return true;

fs/ext4/super.c

@@ -1900,6 +1900,13 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		}
 		sbi->s_commit_interval = HZ * arg;
 	} else if (token == Opt_debug_want_extra_isize) {
+		if ((arg & 1) ||
+		    (arg < 4) ||
+		    (arg > (sbi->s_inode_size - EXT4_GOOD_OLD_INODE_SIZE))) {
+			ext4_msg(sb, KERN_ERR,
+				 "Invalid want_extra_isize %d", arg);
+			return -1;
+		}
 		sbi->s_want_extra_isize = arg;
 	} else if (token == Opt_max_batch_time) {
 		sbi->s_max_batch_time = arg;
@@ -3554,40 +3561,6 @@ int ext4_calculate_overhead(struct super_block *sb)
 	return 0;
 }
 
-static void ext4_clamp_want_extra_isize(struct super_block *sb)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_super_block *es = sbi->s_es;
-	unsigned def_extra_isize = sizeof(struct ext4_inode) -
-						EXT4_GOOD_OLD_INODE_SIZE;
-
-	if (sbi->s_inode_size == EXT4_GOOD_OLD_INODE_SIZE) {
-		sbi->s_want_extra_isize = 0;
-		return;
-	}
-	if (sbi->s_want_extra_isize < 4) {
-		sbi->s_want_extra_isize = def_extra_isize;
-		if (ext4_has_feature_extra_isize(sb)) {
-			if (sbi->s_want_extra_isize <
-			    le16_to_cpu(es->s_want_extra_isize))
-				sbi->s_want_extra_isize =
-					le16_to_cpu(es->s_want_extra_isize);
-			if (sbi->s_want_extra_isize <
-			    le16_to_cpu(es->s_min_extra_isize))
-				sbi->s_want_extra_isize =
-					le16_to_cpu(es->s_min_extra_isize);
-		}
-	}
-	/* Check if enough inode space is available */
-	if ((sbi->s_want_extra_isize > sbi->s_inode_size) ||
-	    (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
-							sbi->s_inode_size)) {
-		sbi->s_want_extra_isize = def_extra_isize;
-		ext4_msg(sb, KERN_INFO,
-			 "required extra inode space not available");
-	}
-}
-
 static void ext4_set_resv_clusters(struct super_block *sb)
 {
 	ext4_fsblk_t resv_clusters;
@@ -3795,6 +3768,68 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 */
 	sbi->s_li_wait_mult = EXT4_DEF_LI_WAIT_MULT;
 
+	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
+		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
+		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
+	} else {
+		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
+		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+		if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) {
+			ext4_msg(sb, KERN_ERR, "invalid first ino: %u",
+				 sbi->s_first_ino);
+			goto failed_mount;
+		}
+		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
+		    (!is_power_of_2(sbi->s_inode_size)) ||
+		    (sbi->s_inode_size > blocksize)) {
+			ext4_msg(sb, KERN_ERR,
+			       "unsupported inode size: %d",
+			       sbi->s_inode_size);
+			goto failed_mount;
+		}
+		/*
+		 * i_atime_extra is the last extra field available for
+		 * [acm]times in struct ext4_inode. Checking for that
+		 * field should suffice to ensure we have extra space
+		 * for all three.
+		 */
+		if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) +
+			sizeof(((struct ext4_inode *)0)->i_atime_extra)) {
+			sb->s_time_gran = 1;
+			sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX;
+		} else {
+			sb->s_time_gran = NSEC_PER_SEC;
+			sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX;
+		}
+		sb->s_time_min = EXT4_TIMESTAMP_MIN;
+	}
+	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
+		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+			EXT4_GOOD_OLD_INODE_SIZE;
+		if (ext4_has_feature_extra_isize(sb)) {
+			unsigned v, max = (sbi->s_inode_size -
+					   EXT4_GOOD_OLD_INODE_SIZE);
+
+			v = le16_to_cpu(es->s_want_extra_isize);
+			if (v > max) {
+				ext4_msg(sb, KERN_ERR,
+					 "bad s_want_extra_isize: %d", v);
+				goto failed_mount;
+			}
+			if (sbi->s_want_extra_isize < v)
+				sbi->s_want_extra_isize = v;
+
+			v = le16_to_cpu(es->s_min_extra_isize);
+			if (v > max) {
+				ext4_msg(sb, KERN_ERR,
+					 "bad s_min_extra_isize: %d", v);
+				goto failed_mount;
+			}
+			if (sbi->s_want_extra_isize < v)
+				sbi->s_want_extra_isize = v;
+		}
+	}
+
 	if (sbi->s_es->s_mount_opts[0]) {
 		char *s_mount_opts = kstrndup(sbi->s_es->s_mount_opts,
 					      sizeof(sbi->s_es->s_mount_opts),
@@ -4033,42 +4068,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 						      has_huge_files);
 	sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits, has_huge_files);
 
-	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
-		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
-		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
-	} else {
-		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
-		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
-		if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) {
-			ext4_msg(sb, KERN_ERR, "invalid first ino: %u",
-				 sbi->s_first_ino);
-			goto failed_mount;
-		}
-		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
-		    (!is_power_of_2(sbi->s_inode_size)) ||
-		    (sbi->s_inode_size > blocksize)) {
-			ext4_msg(sb, KERN_ERR,
-			       "unsupported inode size: %d",
-			       sbi->s_inode_size);
-			goto failed_mount;
-		}
-		/*
-		 * i_atime_extra is the last extra field available for [acm]times in
-		 * struct ext4_inode. Checking for that field should suffice to ensure
-		 * we have extra space for all three.
-		 */
-		if (sbi->s_inode_size >= offsetof(struct ext4_inode, i_atime_extra) +
-			sizeof(((struct ext4_inode *)0)->i_atime_extra)) {
-			sb->s_time_gran = 1;
-			sb->s_time_max = EXT4_EXTRA_TIMESTAMP_MAX;
-		} else {
-			sb->s_time_gran = NSEC_PER_SEC;
-			sb->s_time_max = EXT4_NON_EXTRA_TIMESTAMP_MAX;
-		}
-
-		sb->s_time_min = EXT4_TIMESTAMP_MIN;
-	}
-
 	sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
 	if (ext4_has_feature_64bit(sb)) {
 		if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
@@ -4517,8 +4516,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	} else if (ret)
 		goto failed_mount4a;
 
-	ext4_clamp_want_extra_isize(sb);
-
 	ext4_set_resv_clusters(sb);
 
 	err = ext4_setup_system_zone(sb);
@@ -5306,8 +5303,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
-	ext4_clamp_want_extra_isize(sb);
-
 	if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
 	    test_opt(sb, JOURNAL_CHECKSUM)) {
 		ext4_msg(sb, KERN_ERR, "changing journal_checksum "

include/linux/jbd2.h

@@ -457,7 +457,7 @@ struct jbd2_revoke_table_s;
  * @h_journal: Which journal handle belongs to - used iff h_reserved set.
  * @h_rsv_handle: Handle reserved for finishing the logical operation.
  * @h_total_credits: Number of remaining buffers we are allowed to add to
-	journal. These are dirty buffers and revoke descriptor blocks.
+ *	journal. These are dirty buffers and revoke descriptor blocks.
  * @h_revoke_credits: Number of remaining revoke records available for handle
  * @h_ref: Reference count on this handle.
  * @h_err: Field for caller's use to track errors through large fs operations.