f2fs: include charset encoding information in the superblock

Add charset encoding to f2fs to support casefolding. It is modeled after
the same feature introduced in commit c83ad55eaa91 ("ext4: include charset
encoding information in the superblock")

Currently this is not compatible with encryption, similar to the current
ext4 imlpementation. This will change in the future.

>From the ext4 patch:
"""
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: Daniel Rosenberg <drosen@google.com>
Reviewed-by: Chao Yu <yuchao0@huawei.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 9167deb..8bebee8 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -23,6 +23,7 @@
 #include <linux/f2fs_fs.h>
 #include <linux/sysfs.h>
 #include <linux/quota.h>
+#include <linux/unicode.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -222,6 +223,36 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
 	va_end(args);
 }
 
+#ifdef CONFIG_UNICODE
+static const struct f2fs_sb_encodings {
+	__u16 magic;
+	char *name;
+	char *version;
+} f2fs_sb_encoding_map[] = {
+	{F2FS_ENC_UTF8_12_1, "utf8", "12.1.0"},
+};
+
+static int f2fs_sb_read_encoding(const struct f2fs_super_block *sb,
+				 const struct f2fs_sb_encodings **encoding,
+				 __u16 *flags)
+{
+	__u16 magic = le16_to_cpu(sb->s_encoding);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(f2fs_sb_encoding_map); i++)
+		if (magic == f2fs_sb_encoding_map[i].magic)
+			break;
+
+	if (i >= ARRAY_SIZE(f2fs_sb_encoding_map))
+		return -EINVAL;
+
+	*encoding = &f2fs_sb_encoding_map[i];
+	*flags = le16_to_cpu(sb->s_encoding_flags);
+
+	return 0;
+}
+#endif
+
 static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
 {
 	block_t limit = min((sbi->user_block_count << 1) / 1000,
@@ -798,6 +829,13 @@ static int parse_options(struct super_block *sb, char *options)
 		return -EINVAL;
 	}
 #endif
+#ifndef CONFIG_UNICODE
+	if (f2fs_sb_has_casefold(sbi)) {
+		f2fs_err(sbi,
+			"Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE");
+		return -EINVAL;
+	}
+#endif
 
 	if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
 		f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO",
@@ -1103,6 +1141,9 @@ static void f2fs_put_super(struct super_block *sb)
 	destroy_percpu_info(sbi);
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
+#ifdef CONFIG_UNICODE
+	utf8_unload(sbi->s_encoding);
+#endif
 	kvfree(sbi);
 }
 
@@ -3075,6 +3116,52 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 	return 0;
 }
 
+static int f2fs_setup_casefold(struct f2fs_sb_info *sbi)
+{
+#ifdef CONFIG_UNICODE
+	if (f2fs_sb_has_casefold(sbi) && !sbi->s_encoding) {
+		const struct f2fs_sb_encodings *encoding_info;
+		struct unicode_map *encoding;
+		__u16 encoding_flags;
+
+		if (f2fs_sb_has_encrypt(sbi)) {
+			f2fs_err(sbi,
+				"Can't mount with encoding and encryption");
+			return -EINVAL;
+		}
+
+		if (f2fs_sb_read_encoding(sbi->raw_super, &encoding_info,
+					  &encoding_flags)) {
+			f2fs_err(sbi,
+				 "Encoding requested by superblock is unknown");
+			return -EINVAL;
+		}
+
+		encoding = utf8_load(encoding_info->version);
+		if (IS_ERR(encoding)) {
+			f2fs_err(sbi,
+				 "can't mount with superblock charset: %s-%s "
+				 "not supported by the kernel. flags: 0x%x.",
+				 encoding_info->name, encoding_info->version,
+				 encoding_flags);
+			return PTR_ERR(encoding);
+		}
+		f2fs_info(sbi, "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;
+	}
+#else
+	if (f2fs_sb_has_casefold(sbi)) {
+		f2fs_err(sbi, "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE");
+		return -EINVAL;
+	}
+#endif
+	return 0;
+}
+
 static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_sm_info *sm_i = SM_I(sbi);
@@ -3171,6 +3258,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 				le32_to_cpu(raw_super->log_blocksize);
 	sb->s_max_links = F2FS_LINK_MAX;
 
+	err = f2fs_setup_casefold(sbi);
+	if (err)
+		goto free_options;
+
 #ifdef CONFIG_QUOTA
 	sb->dq_op = &f2fs_quota_operations;
 	sb->s_qcop = &f2fs_quotactl_ops;
@@ -3521,6 +3612,10 @@ static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
 free_bio_info:
 	for (i = 0; i < NR_PAGE_TYPE; i++)
 		kvfree(sbi->write_io[i]);
+
+#ifdef CONFIG_UNICODE
+	utf8_unload(sbi->s_encoding);
+#endif
 free_options:
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < MAXQUOTAS; i++)