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 c83ad55eaa ("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>
This commit is contained in:
Daniel Rosenberg 2019-07-23 16:05:28 -07:00 committed by Jaegeuk Kim
parent 71e90b4654
commit 5aba54302a
6 changed files with 142 additions and 1 deletions

View File

@ -251,3 +251,10 @@ Description:
If checkpoint=disable, it displays the number of blocks that are unusable. If checkpoint=disable, it displays the number of blocks that are unusable.
If checkpoint=enable it displays the enumber of blocks that would be unusable If checkpoint=enable it displays the enumber of blocks that would be unusable
if checkpoint=disable were to be set. if checkpoint=disable were to be set.
What: /sys/fs/f2fs/<disk>/encoding
Date July 2019
Contact: "Daniel Rosenberg" <drosen@google.com>
Description:
Displays name and version of the encoding set for the filesystem.
If no encoding is set, displays (none)

View File

@ -413,6 +413,9 @@ Files in /sys/fs/f2fs/<devname>
that would be unusable if checkpoint=disable were that would be unusable if checkpoint=disable were
to be set. to be set.
encoding This shows the encoding used for casefolding.
If casefolding is not enabled, returns (none)
================================================================================ ================================================================================
USAGE USAGE
================================================================================ ================================================================================

View File

@ -153,6 +153,7 @@ struct f2fs_mount_info {
#define F2FS_FEATURE_LOST_FOUND 0x0200 #define F2FS_FEATURE_LOST_FOUND 0x0200
#define F2FS_FEATURE_VERITY 0x0400 /* reserved */ #define F2FS_FEATURE_VERITY 0x0400 /* reserved */
#define F2FS_FEATURE_SB_CHKSUM 0x0800 #define F2FS_FEATURE_SB_CHKSUM 0x0800
#define F2FS_FEATURE_CASEFOLD 0x1000
#define __F2FS_HAS_FEATURE(raw_super, mask) \ #define __F2FS_HAS_FEATURE(raw_super, mask) \
((raw_super->feature & cpu_to_le32(mask)) != 0) ((raw_super->feature & cpu_to_le32(mask)) != 0)
@ -1169,6 +1170,10 @@ struct f2fs_sb_info {
int valid_super_block; /* valid super block no */ int valid_super_block; /* valid super block no */
unsigned long s_flag; /* flags for sbi */ unsigned long s_flag; /* flags for sbi */
struct mutex writepages; /* mutex for writepages() */ struct mutex writepages; /* mutex for writepages() */
#ifdef CONFIG_UNICODE
struct unicode_map *s_encoding;
__u16 s_encoding_flags;
#endif
#ifdef CONFIG_BLK_DEV_ZONED #ifdef CONFIG_BLK_DEV_ZONED
unsigned int blocks_per_blkz; /* F2FS blocks per zone */ unsigned int blocks_per_blkz; /* F2FS blocks per zone */
@ -3565,6 +3570,7 @@ F2FS_FEATURE_FUNCS(quota_ino, QUOTA_INO);
F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME); F2FS_FEATURE_FUNCS(inode_crtime, INODE_CRTIME);
F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND); F2FS_FEATURE_FUNCS(lost_found, LOST_FOUND);
F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM); F2FS_FEATURE_FUNCS(sb_chksum, SB_CHKSUM);
F2FS_FEATURE_FUNCS(casefold, CASEFOLD);
#ifdef CONFIG_BLK_DEV_ZONED #ifdef CONFIG_BLK_DEV_ZONED
static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi, static inline bool f2fs_blkz_is_seq(struct f2fs_sb_info *sbi, int devi,

View File

@ -23,6 +23,7 @@
#include <linux/f2fs_fs.h> #include <linux/f2fs_fs.h>
#include <linux/sysfs.h> #include <linux/sysfs.h>
#include <linux/quota.h> #include <linux/quota.h>
#include <linux/unicode.h>
#include "f2fs.h" #include "f2fs.h"
#include "node.h" #include "node.h"
@ -222,6 +223,36 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...)
va_end(args); 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) static inline void limit_reserve_root(struct f2fs_sb_info *sbi)
{ {
block_t limit = min((sbi->user_block_count << 1) / 1000, 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; return -EINVAL;
} }
#endif #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)) { if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
f2fs_err(sbi, "Should set mode=lfs with %uKB-sized IO", 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); destroy_percpu_info(sbi);
for (i = 0; i < NR_PAGE_TYPE; i++) for (i = 0; i < NR_PAGE_TYPE; i++)
kvfree(sbi->write_io[i]); kvfree(sbi->write_io[i]);
#ifdef CONFIG_UNICODE
utf8_unload(sbi->s_encoding);
#endif
kvfree(sbi); kvfree(sbi);
} }
@ -3075,6 +3116,52 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
return 0; 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) static void f2fs_tuning_parameters(struct f2fs_sb_info *sbi)
{ {
struct f2fs_sm_info *sm_i = SM_I(sbi); struct f2fs_sm_info *sm_i = SM_I(sbi);
@ -3171,6 +3258,10 @@ try_onemore:
le32_to_cpu(raw_super->log_blocksize); le32_to_cpu(raw_super->log_blocksize);
sb->s_max_links = F2FS_LINK_MAX; sb->s_max_links = F2FS_LINK_MAX;
err = f2fs_setup_casefold(sbi);
if (err)
goto free_options;
#ifdef CONFIG_QUOTA #ifdef CONFIG_QUOTA
sb->dq_op = &f2fs_quota_operations; sb->dq_op = &f2fs_quota_operations;
sb->s_qcop = &f2fs_quotactl_ops; sb->s_qcop = &f2fs_quotactl_ops;
@ -3521,6 +3612,10 @@ free_percpu:
free_bio_info: free_bio_info:
for (i = 0; i < NR_PAGE_TYPE; i++) for (i = 0; i < NR_PAGE_TYPE; i++)
kvfree(sbi->write_io[i]); kvfree(sbi->write_io[i]);
#ifdef CONFIG_UNICODE
utf8_unload(sbi->s_encoding);
#endif
free_options: free_options:
#ifdef CONFIG_QUOTA #ifdef CONFIG_QUOTA
for (i = 0; i < MAXQUOTAS; i++) for (i = 0; i < MAXQUOTAS; i++)

View File

@ -10,6 +10,7 @@
#include <linux/proc_fs.h> #include <linux/proc_fs.h>
#include <linux/f2fs_fs.h> #include <linux/f2fs_fs.h>
#include <linux/seq_file.h> #include <linux/seq_file.h>
#include <linux/unicode.h>
#include "f2fs.h" #include "f2fs.h"
#include "segment.h" #include "segment.h"
@ -81,6 +82,19 @@ static ssize_t unusable_show(struct f2fs_attr *a,
(unsigned long long)unusable); (unsigned long long)unusable);
} }
static ssize_t encoding_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf)
{
#ifdef CONFIG_UNICODE
if (f2fs_sb_has_casefold(sbi))
return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n",
sbi->s_encoding->charset,
(sbi->s_encoding->version >> 16) & 0xff,
(sbi->s_encoding->version >> 8) & 0xff,
sbi->s_encoding->version & 0xff);
#endif
return snprintf(buf, PAGE_SIZE, "(none)");
}
static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a, static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
struct f2fs_sb_info *sbi, char *buf) struct f2fs_sb_info *sbi, char *buf)
@ -134,6 +148,9 @@ static ssize_t features_show(struct f2fs_attr *a,
if (f2fs_sb_has_sb_chksum(sbi)) if (f2fs_sb_has_sb_chksum(sbi))
len += snprintf(buf + len, PAGE_SIZE - len, "%s%s", len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
len ? ", " : "", "sb_checksum"); len ? ", " : "", "sb_checksum");
if (f2fs_sb_has_casefold(sbi))
len += snprintf(buf + len, PAGE_SIZE - len, "%s%s",
len ? ", " : "", "casefold");
len += snprintf(buf + len, PAGE_SIZE - len, "\n"); len += snprintf(buf + len, PAGE_SIZE - len, "\n");
return len; return len;
} }
@ -365,6 +382,7 @@ enum feat_id {
FEAT_INODE_CRTIME, FEAT_INODE_CRTIME,
FEAT_LOST_FOUND, FEAT_LOST_FOUND,
FEAT_SB_CHECKSUM, FEAT_SB_CHECKSUM,
FEAT_CASEFOLD,
}; };
static ssize_t f2fs_feature_show(struct f2fs_attr *a, static ssize_t f2fs_feature_show(struct f2fs_attr *a,
@ -382,6 +400,7 @@ static ssize_t f2fs_feature_show(struct f2fs_attr *a,
case FEAT_INODE_CRTIME: case FEAT_INODE_CRTIME:
case FEAT_LOST_FOUND: case FEAT_LOST_FOUND:
case FEAT_SB_CHECKSUM: case FEAT_SB_CHECKSUM:
case FEAT_CASEFOLD:
return snprintf(buf, PAGE_SIZE, "supported\n"); return snprintf(buf, PAGE_SIZE, "supported\n");
} }
return 0; return 0;
@ -455,6 +474,7 @@ F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
F2FS_GENERAL_RO_ATTR(features); F2FS_GENERAL_RO_ATTR(features);
F2FS_GENERAL_RO_ATTR(current_reserved_blocks); F2FS_GENERAL_RO_ATTR(current_reserved_blocks);
F2FS_GENERAL_RO_ATTR(unusable); F2FS_GENERAL_RO_ATTR(unusable);
F2FS_GENERAL_RO_ATTR(encoding);
#ifdef CONFIG_FS_ENCRYPTION #ifdef CONFIG_FS_ENCRYPTION
F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO); F2FS_FEATURE_RO_ATTR(encryption, FEAT_CRYPTO);
@ -471,6 +491,7 @@ F2FS_FEATURE_RO_ATTR(quota_ino, FEAT_QUOTA_INO);
F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME); F2FS_FEATURE_RO_ATTR(inode_crtime, FEAT_INODE_CRTIME);
F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND); F2FS_FEATURE_RO_ATTR(lost_found, FEAT_LOST_FOUND);
F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM); F2FS_FEATURE_RO_ATTR(sb_checksum, FEAT_SB_CHECKSUM);
F2FS_FEATURE_RO_ATTR(casefold, FEAT_CASEFOLD);
#define ATTR_LIST(name) (&f2fs_attr_##name.attr) #define ATTR_LIST(name) (&f2fs_attr_##name.attr)
static struct attribute *f2fs_attrs[] = { static struct attribute *f2fs_attrs[] = {
@ -515,6 +536,7 @@ static struct attribute *f2fs_attrs[] = {
ATTR_LIST(features), ATTR_LIST(features),
ATTR_LIST(reserved_blocks), ATTR_LIST(reserved_blocks),
ATTR_LIST(current_reserved_blocks), ATTR_LIST(current_reserved_blocks),
ATTR_LIST(encoding),
NULL, NULL,
}; };
ATTRIBUTE_GROUPS(f2fs); ATTRIBUTE_GROUPS(f2fs);
@ -535,6 +557,7 @@ static struct attribute *f2fs_feat_attrs[] = {
ATTR_LIST(inode_crtime), ATTR_LIST(inode_crtime),
ATTR_LIST(lost_found), ATTR_LIST(lost_found),
ATTR_LIST(sb_checksum), ATTR_LIST(sb_checksum),
ATTR_LIST(casefold),
NULL, NULL,
}; };
ATTRIBUTE_GROUPS(f2fs_feat); ATTRIBUTE_GROUPS(f2fs_feat);

View File

@ -36,6 +36,11 @@
#define F2FS_MAX_QUOTAS 3 #define F2FS_MAX_QUOTAS 3
#define F2FS_ENC_UTF8_12_1 1
#define F2FS_ENC_STRICT_MODE_FL (1 << 0)
#define f2fs_has_strict_mode(sbi) \
(sbi->s_encoding_flags & F2FS_ENC_STRICT_MODE_FL)
#define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */ #define F2FS_IO_SIZE(sbi) (1 << F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
#define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */ #define F2FS_IO_SIZE_KB(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 2)) /* KB */
#define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */ #define F2FS_IO_SIZE_BYTES(sbi) (1 << (F2FS_OPTION(sbi).write_io_size_bits + 12)) /* B */
@ -110,7 +115,9 @@ struct f2fs_super_block {
struct f2fs_device devs[MAX_DEVICES]; /* device list */ struct f2fs_device devs[MAX_DEVICES]; /* device list */
__le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */ __le32 qf_ino[F2FS_MAX_QUOTAS]; /* quota inode numbers */
__u8 hot_ext_count; /* # of hot file extension */ __u8 hot_ext_count; /* # of hot file extension */
__u8 reserved[310]; /* valid reserved region */ __le16 s_encoding; /* Filename charset encoding */
__le16 s_encoding_flags; /* Filename charset encoding flags */
__u8 reserved[306]; /* valid reserved region */
__le32 crc; /* checksum of superblock */ __le32 crc; /* checksum of superblock */
} __packed; } __packed;