ext4: include charset encoding information in the superblock

Support for encoding is considered an incompatible feature, since it has
potential to create collisions of file names in existing filesystems.
If the feature flag is not enabled, the entire filesystem will operate
on opaque byte sequences, respecting the original behavior.

The s_encoding field stores a magic number indicating the encoding
format and version used globally by file and directory names in the
filesystem.  The s_encoding_flags defines policies for using the charset
encoding, like how to handle invalid sequences.  The magic number is
mapped to the exact charset table, but the mapping is specific to ext4.
Since we don't have any commitment to support old encodings, the only
encoding I am supporting right now is utf8-12.1.0.

The current implementation prevents the user from enabling encoding and
per-directory encryption on the same filesystem at the same time.  The
incompatibility between these features lies in how we do efficient
directory searches when we cannot be sure the encryption of the user
provided fname will match the actual hash stored in the disk without
decrypting every directory entry, because of normalization cases.  My
quickest solution is to simply block the concurrent use of these
features for now, and enable it later, once we have a better solution.

Signed-off-by: Gabriel Krisman Bertazi <krisman@collabora.co.uk>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 85 insertions, 0 deletions

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 184944d4d8d1..c1b02c3a5a68 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -42,6 +42,7 @@
 #include <linux/cleancache.h>
 #include <linux/uaccess.h>
 #include <linux/iversion.h>
+#include <linux/unicode.h>
 
 #include <linux/kthread.h>
 #include <linux/freezer.h>
@@ -1054,6 +1055,9 @@ static void ext4_put_super(struct super_block *sb)
 		crypto_free_shash(sbi->s_chksum_driver);
 	kfree(sbi->s_blockgroup_lock);
 	fs_put_dax(sbi->s_daxdev);
+#ifdef CONFIG_UNICODE
+	utf8_unload(sbi->s_encoding);
+#endif
 	kfree(sbi);
 }
 
@@ -1750,6 +1754,36 @@ static const struct mount_opts {
 	{Opt_err, 0, 0}
 };
 
+#ifdef CONFIG_UNICODE
+static const struct ext4_sb_encodings {
+	__u16 magic;
+	char *name;
+	char *version;
+} ext4_sb_encoding_map[] = {
+	{EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"},
+};
+
+static int ext4_sb_read_encoding(const struct ext4_super_block *es,
+				 const struct ext4_sb_encodings **encoding,
+				 __u16 *flags)
+{
+	__u16 magic = le16_to_cpu(es->s_encoding);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ext4_sb_encoding_map); i++)
+		if (magic == ext4_sb_encoding_map[i].magic)
+			break;
+
+	if (i >= ARRAY_SIZE(ext4_sb_encoding_map))
+		return -EINVAL;
+
+	*encoding = &ext4_sb_encoding_map[i];
+	*flags = le16_to_cpu(es->s_encoding_flags);
+
+	return 0;
+}
+#endif
+
 static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 			    substring_t *args, unsigned long *journal_devnum,
 			    unsigned int *journal_ioprio, int is_remount)
@@ -2880,6 +2914,15 @@ static int ext4_feature_set_ok(struct super_block *sb, int readonly)
 		return 0;
 	}
 
+#ifndef CONFIG_UNICODE
+	if (ext4_has_feature_casefold(sb)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Filesystem with casefold feature cannot be "
+			 "mounted without CONFIG_UNICODE");
+		return 0;
+	}
+#endif
+
 	if (readonly)
 		return 1;
 
@@ -3770,6 +3813,43 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			   &journal_ioprio, 0))
 		goto failed_mount;
 
+#ifdef CONFIG_UNICODE
+	if (ext4_has_feature_casefold(sb) && !sbi->s_encoding) {
+		const struct ext4_sb_encodings *encoding_info;
+		struct unicode_map *encoding;
+		__u16 encoding_flags;
+
+		if (ext4_has_feature_encrypt(sb)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Can't mount with encoding and encryption");
+			goto failed_mount;
+		}
+
+		if (ext4_sb_read_encoding(es, &encoding_info,
+					  &encoding_flags)) {
+			ext4_msg(sb, KERN_ERR,
+				 "Encoding requested by superblock is unknown");
+			goto failed_mount;
+		}
+
+		encoding = utf8_load(encoding_info->version);
+		if (IS_ERR(encoding)) {
+			ext4_msg(sb, KERN_ERR,
+				 "can't mount with superblock charset: %s-%s "
+				 "not supported by the kernel. flags: 0x%x.",
+				 encoding_info->name, encoding_info->version,
+				 encoding_flags);
+			goto failed_mount;
+		}
+		ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: "
+			 "%s-%s with flags 0x%hx", encoding_info->name,
+			 encoding_info->version?:"\b", encoding_flags);
+
+		sbi->s_encoding = encoding;
+		sbi->s_encoding_flags = encoding_flags;
+	}
+#endif
+
 	if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) {
 		printk_once(KERN_WARNING "EXT4-fs: Warning: mounting "
 			    "with data=journal disables delayed "
@@ -4586,6 +4666,11 @@ failed_mount2:
 failed_mount:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);
+
+#ifdef CONFIG_UNICODE
+	utf8_unload(sbi->s_encoding);
+#endif
+
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(sbi->s_qf_names[i]);