From: "Pali Rohár" <pali@kernel.org>
To: linux-fsdevel@vger.kernel.org,
linux-ntfs-dev@lists.sourceforge.net, linux-cifs@vger.kernel.org,
jfs-discussion@lists.sourceforge.net,
linux-kernel@vger.kernel.org,
"Alexander Viro" <viro@zeniv.linux.org.uk>,
"Jan Kara" <jack@suse.cz>,
"OGAWA Hirofumi" <hirofumi@mail.parknet.co.jp>,
"Theodore Y . Ts'o" <tytso@mit.edu>,
"Luis de Bethencourt" <luisbg@kernel.org>,
"Salah Triki" <salah.triki@gmail.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Dave Kleikamp" <shaggy@kernel.org>,
"Anton Altaparmakov" <anton@tuxera.com>,
"Pavel Machek" <pavel@ucw.cz>, "Marek Behún" <marek.behun@nic.cz>,
"Christoph Hellwig" <hch@infradead.org>
Subject: [RFC PATCH 01/20] fat: Fix iocharset=utf8 mount option
Date: Sun, 8 Aug 2021 18:24:34 +0200 [thread overview]
Message-ID: <20210808162453.1653-2-pali@kernel.org> (raw)
In-Reply-To: <20210808162453.1653-1-pali@kernel.org>
Currently iocharset=utf8 mount option is broken and error is printed to
dmesg when it is used. To use UTF-8 as iocharset, it is required to use
utf8=1 mount option.
Fix iocharset=utf8 mount option to use be equivalent to the utf8=1 mount
option and remove printing error from dmesg.
FAT by definition is case-insensitive but current Linux implementation is
case-sensitive for non-ASCII characters when UTF-8 is used. This patch does
not change this UTF-8 behavior. Only more comments in fat_utf8_strnicmp()
function are added about it.
After this patch iocharset=utf8 starts working, so there is no need to have
separate config option FAT_DEFAULT_UTF8 as FAT_DEFAULT_IOCHARSET for utf8
also starts working. So remove redundant config option FAT_DEFAULT_UTF8.
Signed-off-by: Pali Rohár <pali@kernel.org>
---
fs/fat/Kconfig | 15 ---------------
fs/fat/dir.c | 17 +++++++----------
fs/fat/fat.h | 22 ++++++++++++++++++++++
fs/fat/inode.c | 28 +++++++++++-----------------
fs/fat/namei_vfat.c | 26 +++++++++++++++++++-------
5 files changed, 59 insertions(+), 49 deletions(-)
diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig
index 66532a71e8fd..a31594137d5e 100644
--- a/fs/fat/Kconfig
+++ b/fs/fat/Kconfig
@@ -100,18 +100,3 @@ config FAT_DEFAULT_IOCHARSET
Enable any character sets you need in File Systems/Native Language
Support.
-
-config FAT_DEFAULT_UTF8
- bool "Enable FAT UTF-8 option by default"
- depends on VFAT_FS
- default n
- help
- Set this if you would like to have "utf8" mount option set
- by default when mounting FAT filesystems.
-
- Even if you say Y here can always disable UTF-8 for
- particular mount by adding "utf8=0" to mount options.
-
- Say Y if you use UTF-8 encoding for file names, N otherwise.
-
- See <file:Documentation/filesystems/vfat.rst> for more information.
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index c4a274285858..49fe8dc6e5f0 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -33,11 +33,6 @@
#define FAT_MAX_UNI_CHARS ((MSDOS_SLOTS - 1) * 13 + 1)
#define FAT_MAX_UNI_SIZE (FAT_MAX_UNI_CHARS * sizeof(wchar_t))
-static inline unsigned char fat_tolower(unsigned char c)
-{
- return ((c >= 'A') && (c <= 'Z')) ? c+32 : c;
-}
-
static inline loff_t fat_make_i_pos(struct super_block *sb,
struct buffer_head *bh,
struct msdos_dir_entry *de)
@@ -258,10 +253,12 @@ static inline int fat_name_match(struct msdos_sb_info *sbi,
if (a_len != b_len)
return 0;
- if (sbi->options.name_check != 's')
- return !nls_strnicmp(sbi->nls_io, a, b, a_len);
- else
+ if (sbi->options.name_check == 's')
return !memcmp(a, b, a_len);
+ else if (sbi->options.utf8)
+ return !fat_utf8_strnicmp(a, b, a_len);
+ else
+ return !nls_strnicmp(sbi->nls_io, a, b, a_len);
}
enum { PARSE_INVALID = 1, PARSE_NOT_LONGNAME, PARSE_EOF, };
@@ -384,7 +381,7 @@ static int fat_parse_short(struct super_block *sb,
de->lcase & CASE_LOWER_BASE);
if (chl <= 1) {
if (!isvfat)
- ptname[i] = nocase ? c : fat_tolower(c);
+ ptname[i] = nocase ? c : fat_ascii_to_lower(c);
i++;
if (c != ' ') {
name_len = i;
@@ -421,7 +418,7 @@ static int fat_parse_short(struct super_block *sb,
if (chl <= 1) {
k++;
if (!isvfat)
- ptname[i] = nocase ? c : fat_tolower(c);
+ ptname[i] = nocase ? c : fat_ascii_to_lower(c);
i++;
if (c != ' ') {
name_len = i;
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index 02d4d4234956..0cd15fb3b042 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -310,6 +310,28 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
#endif
}
+static inline unsigned char fat_ascii_to_lower(unsigned char c)
+{
+ return ((c >= 'A') && (c <= 'Z')) ? c+32 : c;
+}
+
+static inline int fat_utf8_strnicmp(const unsigned char *a,
+ const unsigned char *b,
+ int len)
+{
+ int i;
+
+ /*
+ * FIXME: UTF-8 doesn't provide FAT semantics
+ * Case-insensitive support is only for 7-bit ASCII characters
+ */
+ for (i = 0; i < len; i++) {
+ if (fat_ascii_to_lower(a[i]) != fat_ascii_to_lower(b[i]))
+ return 1;
+ }
+ return 0;
+}
+
/* fat/cache.c */
extern void fat_cache_inval_inode(struct inode *inode);
extern int fat_get_cluster(struct inode *inode, int cluster,
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index de0c9b013a85..f8c8a739f8f0 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -957,7 +957,9 @@ static int fat_show_options(struct seq_file *m, struct dentry *root)
/* strip "cp" prefix from displayed option */
seq_printf(m, ",codepage=%s", &sbi->nls_disk->charset[2]);
if (isvfat) {
- if (sbi->nls_io)
+ if (opts->utf8)
+ seq_printf(m, ",iocharset=utf8");
+ else if (sbi->nls_io)
seq_printf(m, ",iocharset=%s", sbi->nls_io->charset);
switch (opts->shortname) {
@@ -994,8 +996,6 @@ static int fat_show_options(struct seq_file *m, struct dentry *root)
if (opts->nocase)
seq_puts(m, ",nocase");
} else {
- if (opts->utf8)
- seq_puts(m, ",utf8");
if (opts->unicode_xlate)
seq_puts(m, ",uni_xlate");
if (!opts->numtail)
@@ -1157,8 +1157,6 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
opts->errors = FAT_ERRORS_RO;
*debug = 0;
- opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat;
-
if (!options)
goto out;
@@ -1319,10 +1317,14 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
| VFAT_SFN_CREATE_WIN95;
break;
case Opt_utf8_no: /* 0 or no or false */
- opts->utf8 = 0;
+ fat_reset_iocharset(opts);
break;
case Opt_utf8_yes: /* empty or 1 or yes or true */
- opts->utf8 = 1;
+ fat_reset_iocharset(opts);
+ iocharset = kstrdup("utf8", GFP_KERNEL);
+ if (!iocharset)
+ return -ENOMEM;
+ opts->iocharset = iocharset;
break;
case Opt_uni_xl_no: /* 0 or no or false */
opts->unicode_xlate = 0;
@@ -1360,18 +1362,11 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
}
out:
- /* UTF-8 doesn't provide FAT semantics */
- if (!strcmp(opts->iocharset, "utf8")) {
- fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset"
- " for FAT filesystems, filesystem will be "
- "case sensitive!");
- }
+ opts->utf8 = !strcmp(opts->iocharset, "utf8") && is_vfat;
/* If user doesn't specify allow_utime, it's initialized from dmask. */
if (opts->allow_utime == (unsigned short)-1)
opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH);
- if (opts->unicode_xlate)
- opts->utf8 = 0;
if (opts->nfs == FAT_NFS_NOSTALE_RO) {
sb->s_flags |= SB_RDONLY;
sb->s_export_op = &fat_export_ops_nostale;
@@ -1832,8 +1827,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
goto out_fail;
}
- /* FIXME: utf8 is using iocharset for upper/lower conversion */
- if (sbi->options.isvfat) {
+ if (sbi->options.isvfat && !sbi->options.utf8) {
sbi->nls_io = load_nls(sbi->options.iocharset);
if (!sbi->nls_io) {
fat_msg(sb, KERN_ERR, "IO charset %s not found",
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index 5369d82e0bfb..efb3cb9ea8a8 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -134,6 +134,7 @@ static int vfat_hash(const struct dentry *dentry, struct qstr *qstr)
static int vfat_hashi(const struct dentry *dentry, struct qstr *qstr)
{
struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io;
+ int utf8 = MSDOS_SB(dentry->d_sb)->options.utf8;
const unsigned char *name;
unsigned int len;
unsigned long hash;
@@ -142,8 +143,17 @@ static int vfat_hashi(const struct dentry *dentry, struct qstr *qstr)
len = vfat_striptail_len(qstr);
hash = init_name_hash(dentry);
- while (len--)
- hash = partial_name_hash(nls_tolower(t, *name++), hash);
+ if (utf8) {
+ /*
+ * FIXME: UTF-8 doesn't provide FAT semantics
+ * Case-insensitive support is only for 7-bit ASCII characters
+ */
+ while (len--)
+ hash = partial_name_hash(fat_ascii_to_lower(*name++), hash);
+ } else {
+ while (len--)
+ hash = partial_name_hash(nls_tolower(t, *name++), hash);
+ }
qstr->hash = end_name_hash(hash);
return 0;
@@ -156,16 +166,18 @@ static int vfat_cmpi(const struct dentry *dentry,
unsigned int len, const char *str, const struct qstr *name)
{
struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io;
+ int utf8 = MSDOS_SB(dentry->d_sb)->options.utf8;
unsigned int alen, blen;
/* A filename cannot end in '.' or we treat it like it has none */
alen = vfat_striptail_len(name);
blen = __vfat_striptail_len(len, str);
- if (alen == blen) {
- if (nls_strnicmp(t, name->name, str, alen) == 0)
- return 0;
- }
- return 1;
+ if (alen != blen)
+ return 1;
+ else if (utf8)
+ return fat_utf8_strnicmp(name->name, str, alen);
+ else
+ return nls_strnicmp(t, name->name, str, alen);
}
/*
--
2.20.1
next prev parent reply other threads:[~2021-08-08 16:25 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-08 16:24 [RFC PATCH 00/20] fs: Remove usage of broken nls_utf8 and drop it Pali Rohár
2021-08-08 16:24 ` Pali Rohár [this message]
2021-08-15 3:42 ` [RFC PATCH 01/20] fat: Fix iocharset=utf8 mount option OGAWA Hirofumi
2021-08-15 9:42 ` Pali Rohár
2021-08-15 11:23 ` OGAWA Hirofumi
2021-08-23 3:51 ` Kari Argillander
2021-08-08 16:24 ` [RFC PATCH 02/20] hfsplus: Add iocharset= mount option as alias for nls= Pali Rohár
2021-08-09 17:51 ` Viacheslav Dubeyko
2021-08-09 20:49 ` Kari Argillander
2021-08-09 21:25 ` Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 03/20] udf: Fix iocharset=utf8 mount option Pali Rohár
2021-08-12 14:17 ` Jan Kara
2021-08-12 15:51 ` Pali Rohár
2021-08-13 13:48 ` Jan Kara
2021-08-19 8:34 ` Pali Rohár
2021-08-19 10:41 ` Jan Kara
2021-08-08 16:24 ` [RFC PATCH 04/20] isofs: joliet: " Pali Rohár
2021-08-12 14:18 ` Jan Kara
2021-08-08 16:24 ` [RFC PATCH 05/20] ntfs: Undeprecate iocharset= " Pali Rohár
2021-08-09 20:52 ` Kari Argillander
2021-08-19 1:21 ` Kari Argillander
2021-08-19 8:12 ` Pali Rohár
2021-08-19 10:23 ` Kari Argillander
2021-08-19 22:04 ` Pali Rohár
2021-08-19 23:18 ` Kari Argillander
2021-08-08 16:24 ` [RFC PATCH 06/20] ntfs: Fix error processing when load_nls() fails Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 07/20] befs: Fix printing iocharset= mount option Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 08/20] befs: Rename enum value Opt_charset to Opt_iocharset to match " Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 09/20] befs: Fix error processing when load_nls() fails Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 10/20] befs: Allow to use native UTF-8 mode Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 11/20] hfs: Explicitly set hsb->nls_disk when hsb->nls_io is set Pali Rohár
2021-08-09 17:31 ` Viacheslav Dubeyko
2021-08-09 17:37 ` Matthew Wilcox
2021-08-09 17:47 ` Pali Rohár
2021-08-09 20:43 ` Steve French
2021-08-09 18:00 ` Viacheslav Dubeyko
2021-08-08 16:24 ` [RFC PATCH 12/20] hfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option Pali Rohár
2021-08-09 17:49 ` Viacheslav Dubeyko
2022-09-25 12:06 ` Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 13/20] hfsplus: " Pali Rohár
2021-08-09 17:42 ` Viacheslav Dubeyko
2022-09-25 12:12 ` Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 14/20] jfs: Remove custom iso8859-1 implementation Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 15/20] jfs: Fix buffer overflow in jfs_strfromUCS_le() function Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 16/20] jfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 17/20] ntfs: " Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 18/20] cifs: " Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 19/20] cifs: Remove usage of load_nls_default() calls Pali Rohár
2021-08-08 16:24 ` [RFC PATCH 20/20] nls: Drop broken nls_utf8 module Pali Rohár
2021-09-03 21:26 ` [RFC PATCH 00/20] fs: Remove usage of broken nls_utf8 and drop it Kari Argillander
2021-09-03 21:37 ` Pali Rohár
2021-09-03 22:06 ` Kari Argillander
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210808162453.1653-2-pali@kernel.org \
--to=pali@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=anton@tuxera.com \
--cc=hch@infradead.org \
--cc=hirofumi@mail.parknet.co.jp \
--cc=jack@suse.cz \
--cc=jfs-discussion@lists.sourceforge.net \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-ntfs-dev@lists.sourceforge.net \
--cc=luisbg@kernel.org \
--cc=marek.behun@nic.cz \
--cc=pavel@ucw.cz \
--cc=salah.triki@gmail.com \
--cc=shaggy@kernel.org \
--cc=tytso@mit.edu \
--cc=viro@zeniv.linux.org.uk \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).