[permalink] [raw]

Subject: [RFC PATCH 10/20] befs: Allow to use native UTF-8 mode

befs driver already has a code which avoids usage of NLS when befs_sb->nls
is not set.

But befs_fill_super() always set befs_sb->nls, so activating native UTF-8
is not possible.

Fix it by not setting befs_sb->nls when iocharset is set to utf8. So now
after this cgange mount option iocharset=utf8 activates usage of native
UTF-8 code path in befs driver.

Signed-off-by: Pali Rohár <[email protected]>
---
fs/befs/linuxvfs.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 963da3e9ab5d..000f946b92b6 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -770,6 +770,7 @@ static int befs_show_options(struct seq_file *m, struct dentry *root)
{
struct befs_sb_info *befs_sb = BEFS_SB(root->d_sb);
struct befs_mount_options *opts = &befs_sb->mount_opts;
+ struct nls_table *nls = befs_sb->nls;

if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
seq_printf(m, ",uid=%u",
@@ -777,8 +778,10 @@ static int befs_show_options(struct seq_file *m, struct dentry *root)
if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
seq_printf(m, ",gid=%u",
from_kgid_munged(&init_user_ns, opts->gid));
- if (opts->iocharset)
- seq_printf(m, ",iocharset=%s", opts->iocharset);
+ if (nls)
+ seq_printf(m, ",iocharset=%s", nls->charset);
+ else
+ seq_puts(m, ",iocharset=utf8");
if (opts->debug)
seq_puts(m, ",debug");
return 0;
@@ -908,8 +911,10 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
goto unacquire_priv_sbp;
}

+ if (strcmp(opt.iocharset ? opt.iocharset : CONFIG_NLS_DEFAULT, "utf8") == 0) {
+ befs_debug(sb, "Using native UTF-8 without nls");
/* load nls library */
- if (befs_sb->mount_opts.iocharset) {
+ } else if (befs_sb->mount_opts.iocharset) {
befs_debug(sb, "Loading nls: %s",
befs_sb->mount_opts.iocharset);
befs_sb->nls = load_nls(befs_sb->mount_opts.iocharset);
--
2.20.1

2021-08-08 16:29:04

by Pali Rohár

[permalink] [raw]

Subject: [RFC PATCH 07/20] befs: Fix printing iocharset= mount option

Mount option is named iocharset= and not charset=

Signed-off-by: Pali Rohár <[email protected]>
---
fs/befs/linuxvfs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index c1ba13d19024..ed4d3afb8638 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -778,7 +778,7 @@ static int befs_show_options(struct seq_file *m, struct dentry *root)
seq_printf(m, ",gid=%u",
from_kgid_munged(&init_user_ns, opts->gid));
if (opts->iocharset)
- seq_printf(m, ",charset=%s", opts->iocharset);
+ seq_printf(m, ",iocharset=%s", opts->iocharset);
if (opts->debug)
seq_puts(m, ",debug");
return 0;
--
2.20.1

2021-08-08 16:29:10

by Pali Rohár

[permalink] [raw]

Subject: [RFC PATCH 03/20] udf: Fix iocharset=utf8 mount option

Currently iocharset=utf8 mount option is broken. To use UTF-8 as iocharset,
it is required to use utf8 mount option.

Fix iocharset=utf8 mount option to use be equivalent to the utf8 mount
option.

If UTF-8 as iocharset is used then s_nls_map is set to NULL. So simplify
code around, remove UDF_FLAG_NLS_MAP and UDF_FLAG_UTF8 flags as to
distinguish between UTF-8 and non-UTF-8 it is needed just to check if
s_nls_map set to NULL or not.

Signed-off-by: Pali Rohár <[email protected]>
---
fs/udf/super.c | 50 ++++++++++++++++++------------------------------
fs/udf/udf_sb.h | 2 --
fs/udf/unicode.c | 4 ++--
3 files changed, 21 insertions(+), 35 deletions(-)

diff --git a/fs/udf/super.c b/fs/udf/super.c
index 2f83c1204e20..6e8c29107b04 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -349,10 +349,10 @@ static int udf_show_options(struct seq_file *seq, struct dentry *root)
seq_printf(seq, ",lastblock=%u", sbi->s_last_block);
if (sbi->s_anchor != 0)
seq_printf(seq, ",anchor=%u", sbi->s_anchor);
- if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8))
- seq_puts(seq, ",utf8");
- if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP) && sbi->s_nls_map)
+ if (sbi->s_nls_map)
seq_printf(seq, ",iocharset=%s", sbi->s_nls_map->charset);
+ else
+ seq_puts(seq, ",iocharset=utf8");

return 0;
}
@@ -558,19 +558,24 @@ static int udf_parse_options(char *options, struct udf_options *uopt,
/* Ignored (never implemented properly) */
break;
case Opt_utf8:
- uopt->flags |= (1 << UDF_FLAG_UTF8);
+ if (!remount) {
+ unload_nls(uopt->nls_map);
+ uopt->nls_map = NULL;
+ }
break;
case Opt_iocharset:
if (!remount) {
- if (uopt->nls_map)
- unload_nls(uopt->nls_map);
- /*
- * load_nls() failure is handled later in
- * udf_fill_super() after all options are
- * parsed.
- */
+ unload_nls(uopt->nls_map);
+ uopt->nls_map = NULL;
+ }
+ /* When nls_map is not loaded then UTF-8 is used */
+ if (!remount && strcmp(args[0].from, "utf8") != 0) {
uopt->nls_map = load_nls(args[0].from);
- uopt->flags |= (1 << UDF_FLAG_NLS_MAP);
+ if (!uopt->nls_map) {
+ pr_err("iocharset %s not found\n",
+ args[0].from);
+ return 0;
+ }
}
break;
case Opt_uforget:
@@ -2139,21 +2144,6 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
if (!udf_parse_options((char *)options, &uopt, false))
goto parse_options_failure;

- if (uopt.flags & (1 << UDF_FLAG_UTF8) &&
- uopt.flags & (1 << UDF_FLAG_NLS_MAP)) {
- udf_err(sb, "utf8 cannot be combined with iocharset\n");
- goto parse_options_failure;
- }
- if ((uopt.flags & (1 << UDF_FLAG_NLS_MAP)) && !uopt.nls_map) {
- uopt.nls_map = load_nls_default();
- if (!uopt.nls_map)
- uopt.flags &= ~(1 << UDF_FLAG_NLS_MAP);
- else
- udf_debug("Using default NLS map\n");
- }
- if (!(uopt.flags & (1 << UDF_FLAG_NLS_MAP)))
- uopt.flags |= (1 << UDF_FLAG_UTF8);
-
fileset.logicalBlockNum = 0xFFFFFFFF;
fileset.partitionReferenceNum = 0xFFFF;

@@ -2308,8 +2298,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
error_out:
iput(sbi->s_vat_inode);
parse_options_failure:
- if (uopt.nls_map)
- unload_nls(uopt.nls_map);
+ unload_nls(uopt.nls_map);
if (lvid_open)
udf_close_lvid(sb);
brelse(sbi->s_lvid_bh);
@@ -2359,8 +2348,7 @@ static void udf_put_super(struct super_block *sb)
sbi = UDF_SB(sb);

iput(sbi->s_vat_inode);
- if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP))
- unload_nls(sbi->s_nls_map);
+ unload_nls(sbi->s_nls_map);
if (!sb_rdonly(sb))
udf_close_lvid(sb);
brelse(sbi->s_lvid_bh);
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 758efe557a19..4fa620543d30 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -20,8 +20,6 @@
#define UDF_FLAG_UNDELETE 6
#define UDF_FLAG_UNHIDE 7
#define UDF_FLAG_VARCONV 8
-#define UDF_FLAG_NLS_MAP 9
-#define UDF_FLAG_UTF8 10
#define UDF_FLAG_UID_FORGET 11 /* save -1 for uid to disk */
#define UDF_FLAG_GID_FORGET 12
#define UDF_FLAG_UID_SET 13
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index 5fcfa96463eb..622569007b53 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -177,7 +177,7 @@ static int udf_name_from_CS0(struct super_block *sb,
return 0;
}

- if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP))
+ if (UDF_SB(sb)->s_nls_map)
conv_f = UDF_SB(sb)->s_nls_map->uni2char;
else
conv_f = NULL;
@@ -285,7 +285,7 @@ static int udf_name_to_CS0(struct super_block *sb,
if (ocu_max_len <= 0)
return 0;

- if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP))
+ if (UDF_SB(sb)->s_nls_map)
conv_f = UDF_SB(sb)->s_nls_map->char2uni;
else
conv_f = NULL;
--
2.20.1

2021-08-08 16:29:12

by Pali Rohár

[permalink] [raw]

Subject: [RFC PATCH 05/20] ntfs: Undeprecate iocharset= mount option

Other fs drivers are using iocharset= mount option for specifying charset.
So mark iocharset= mount option as preferred and deprecate nls= mount
option.

Signed-off-by: Pali Rohár <[email protected]>
---
fs/ntfs/inode.c | 2 +-
fs/ntfs/super.c | 13 ++++---------
fs/ntfs/unistr.c | 3 ++-
3 files changed, 7 insertions(+), 11 deletions(-)

diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c
index 4474adb393ca..3676f185b4a0 100644
--- a/fs/ntfs/inode.c
+++ b/fs/ntfs/inode.c
@@ -2303,7 +2303,7 @@ int ntfs_show_options(struct seq_file *sf, struct dentry *root)
seq_printf(sf, ",fmask=0%o", vol->fmask);
seq_printf(sf, ",dmask=0%o", vol->dmask);
}
- seq_printf(sf, ",nls=%s", vol->nls_map->charset);
+ seq_printf(sf, ",iocharset=%s", vol->nls_map->charset);
if (NVolCaseSensitive(vol))
seq_printf(sf, ",case_sensitive");
if (NVolShowSystemFiles(vol))
diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
index 0d7e948cb29c..02de1aa05b7c 100644
--- a/fs/ntfs/super.c
+++ b/fs/ntfs/super.c
@@ -192,11 +192,6 @@ static bool parse_options(ntfs_volume *vol, char *opt)
ntfs_warning(vol->sb, "Ignoring obsolete option %s.",
p);
else if (!strcmp(p, "nls") || !strcmp(p, "iocharset")) {
- if (!strcmp(p, "iocharset"))
- ntfs_warning(vol->sb, "Option iocharset is "
- "deprecated. Please use "
- "option nls=<charsetname> in "
- "the future.");
if (!v || !*v)
goto needs_arg;
use_utf8:
@@ -218,10 +213,10 @@ static bool parse_options(ntfs_volume *vol, char *opt)
} else if (!strcmp(p, "utf8")) {
bool val = false;
ntfs_warning(vol->sb, "Option utf8 is no longer "
- "supported, using option nls=utf8. Please "
- "use option nls=utf8 in the future and "
- "make sure utf8 is compiled either as a "
- "module or into the kernel.");
+ "supported, using option iocharset=utf8. "
+ "Please use option iocharset=utf8 in the "
+ "future and make sure utf8 is compiled "
+ "either as a module or into the kernel.");
if (!v || !*v)
val = true;
else if (!simple_getbool(v, &val))
diff --git a/fs/ntfs/unistr.c b/fs/ntfs/unistr.c
index a6b6c64f14a9..75a7f73bccdd 100644
--- a/fs/ntfs/unistr.c
+++ b/fs/ntfs/unistr.c
@@ -372,7 +372,8 @@ retry: wc = nls->uni2char(le16_to_cpu(ins[i]), ns + o,
conversion_err:
ntfs_error(vol->sb, "Unicode name contains characters that cannot be "
"converted to character set %s. You might want to "
- "try to use the mount option nls=utf8.", nls->charset);
+ "try to use the mount option iocharset=utf8.",
+ nls->charset);
if (ns != *outs)
kfree(ns);
if (wc != -ENAMETOOLONG)
--
2.20.1

2021-08-08 16:30:05

by Pali Rohár

[permalink] [raw]

> On Aug 8, 2021, at 9:24 AM, Pali Rohár <[email protected]> wrote:
>
> NLS table for utf8 is broken and cannot be fixed.
>
> So instead of broken utf8 nls functions char2uni() and uni2char() use
> functions utf8_to_utf32() and utf32_to_utf8() which implements correct
> encoding and decoding between Unicode code points and UTF-8 sequence.
>
> Note that this fs driver does not support full Unicode range, specially
> UTF-16 surrogate pairs are unsupported. This patch does not change this
> limitation and support for UTF-16 surrogate pairs stay unimplemented.
>
> When iochatset=utf8 is used then set sbi->nls to NULL and use it for
> distinguish between the fact if NLS table or native UTF-8 functions should
> be used.
>
> Signed-off-by: Pali Rohár <[email protected]>
> ---
> fs/hfsplus/dir.c | 6 ++++--
> fs/hfsplus/options.c | 32 ++++++++++++++++++--------------
> fs/hfsplus/super.c | 7 +------
> fs/hfsplus/unicode.c | 31 ++++++++++++++++++++++++++++---
> fs/hfsplus/xattr.c | 14 +++++++++-----
> fs/hfsplus/xattr_security.c | 3 ++-
> 6 files changed, 62 insertions(+), 31 deletions(-)
>
> diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
> index 84714bbccc12..2caf0cd82221 100644
> --- a/fs/hfsplus/dir.c
> +++ b/fs/hfsplus/dir.c
> @@ -144,7 +144,8 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
> err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
> if (err)
> return err;
> - strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN + 1, GFP_KERNEL);
> + strbuf = kmalloc((HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> + HFSPLUS_MAX_STRLEN + 1, GFP_KERNEL);

Maybe, introduce some variable that will contain the length calculation?

> if (!strbuf) {
> err = -ENOMEM;
> goto out;
> @@ -203,7 +204,8 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
> hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
> fd.entrylength);
> type = be16_to_cpu(entry.type);
> - len = NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN;
> + len = (HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> + HFSPLUS_MAX_STRLEN;
> err = hfsplus_uni2asc(sb, &fd.key->cat.name, strbuf, &len);
> if (err)
> goto out;
> diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
> index a975548f6b91..16c08cb5c4f8 100644
> --- a/fs/hfsplus/options.c
> +++ b/fs/hfsplus/options.c
> @@ -104,6 +104,9 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
> char *p;
> substring_t args[MAX_OPT_ARGS];
> int tmp, token;
> + int have_iocharset;
> +
> + have_iocharset = 0;

What’s about boolean type and to use true/false?

>
> if (!input)
> goto done;
> @@ -171,20 +174,24 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
> pr_warn("option nls= is deprecated, use iocharset=\n");
> /* fallthrough */
> case opt_iocharset:
> - if (sbi->nls) {
> + if (have_iocharset) {
> pr_err("unable to change nls mapping\n");
> return 0;
> }
> p = match_strdup(&args[0]);
> - if (p)
> - sbi->nls = load_nls(p);
> - if (!sbi->nls) {
> - pr_err("unable to load nls mapping \"%s\"\n",
> - p);
> - kfree(p);
> + if (!p)
> return 0;
> + if (strcmp(p, "utf8") != 0) {
> + sbi->nls = load_nls(p);
> + if (!sbi->nls) {
> + pr_err("unable to load nls mapping "
> + "\"%s\"\n", p);
> + kfree(p);
> + return 0;
> + }
> }
> kfree(p);
> + have_iocharset = 1;

Ditto. What’s about true here?

> break;
> case opt_decompose:
> clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
> @@ -207,13 +214,10 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
> }
>
> done:
> - if (!sbi->nls) {
> - /* try utf8 first, as this is the old default behaviour */
> - sbi->nls = load_nls("utf8");
> - if (!sbi->nls)
> - sbi->nls = load_nls_default();
> - if (!sbi->nls)
> - return 0;
> + if (!have_iocharset) {
> + /* use utf8, as this is the old default behaviour */
> + pr_debug("using native UTF-8 without nls\n");
> + /* no sbi->nls means that native UTF-8 code is used */
> }
>
> return 1;
> diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
> index b9e3db3f855f..985662451bfc 100644
> --- a/fs/hfsplus/super.c
> +++ b/fs/hfsplus/super.c
> @@ -403,11 +403,7 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
>
> /* temporarily use utf8 to correctly find the hidden dir below */
> nls = sbi->nls;
> - sbi->nls = load_nls("utf8");
> - if (!sbi->nls) {
> - pr_err("unable to load nls for utf8\n");
> - goto out_unload_nls;
> - }
> + sbi->nls = NULL;
>
> /* Grab the volume header */
> if (hfsplus_read_wrapper(sb)) {
> @@ -585,7 +581,6 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
> }
> }
>
> - unload_nls(sbi->nls);
> sbi->nls = nls;
> return 0;
>
> diff --git a/fs/hfsplus/unicode.c b/fs/hfsplus/unicode.c
> index 73342c925a4b..1d8c31c5126f 100644
> --- a/fs/hfsplus/unicode.c
> +++ b/fs/hfsplus/unicode.c
> @@ -190,7 +190,12 @@ int hfsplus_uni2asc(struct super_block *sb,
> c0 = ':';
> break;
> }
> - res = nls->uni2char(c0, op, len);
> + if (nls)
> + res = nls->uni2char(c0, op, len);
> + else (len > 0)
> + res = utf32_to_utf8(c0, op, len);
> + else
> + res = -ENAMETOOLONG;
> if (res < 0) {
> if (res == -ENAMETOOLONG)
> goto out;
> @@ -233,7 +238,12 @@ int hfsplus_uni2asc(struct super_block *sb,
> cc = c0;
> }
> done:
> - res = nls->uni2char(cc, op, len);
> + if (nls)
> + res = nls->uni2char(cc, op, len);
> + else (len > 0)
> + res = utf32_to_utf8(cc, op, len);
> + else
> + res = -ENAMETOOLONG;
> if (res < 0) {
> if (res == -ENAMETOOLONG)
> goto out;
> @@ -256,7 +266,22 @@ int hfsplus_uni2asc(struct super_block *sb,
> static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
> wchar_t *uc)
> {
> - int size = HFSPLUS_SB(sb)->nls->char2uni(astr, len, uc);
> + struct nls_table *nls = HFSPLUS_SB(sb)->nls;
> + unicode_t u;
> + int size;
> +
> + if (nls)
> + size = nls->char2uni(astr, len, uc);
> + else {
> + size = utf8_to_utf32(astr, len, &u);
> + if (size >= 0) {
> + /* TODO: Add support for UTF-16 surrogate pairs */

Have you forgot to delete this string? Or do you plan to implement this?

> + if (u <= MAX_WCHAR_T)
> + *uc = u;
> + else
> + size = -EINVAL;
> + }
> + }
> if (size <= 0) {
> *uc = '?';
> size = 1;
> diff --git a/fs/hfsplus/xattr.c b/fs/hfsplus/xattr.c
> index e2855ceefd39..9b2653f08a5f 100644
> --- a/fs/hfsplus/xattr.c
> +++ b/fs/hfsplus/xattr.c
> @@ -425,7 +425,8 @@ int hfsplus_setxattr(struct inode *inode, const char *name,
> char *xattr_name;
> int res;
>
> - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
> + xattr_name = kmalloc((HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> + HFSPLUS_ATTR_MAX_STRLEN + 1,
> GFP_KERNEL);

What’s about to introduce a variable for length calculation?

> if (!xattr_name)
> return -ENOMEM;
> @@ -579,7 +580,8 @@ ssize_t hfsplus_getxattr(struct inode *inode, const char *name,
> int res;
> char *xattr_name;
>
> - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
> + xattr_name = kmalloc((HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> + HFSPLUS_ATTR_MAX_STRLEN + 1,
> GFP_KERNEL);

Ditto. What’s about to introduce a variable for length calculation?

> if (!xattr_name)
> return -ENOMEM;
> @@ -699,8 +701,9 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
> return err;
> }
>
> - strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN +
> - XATTR_MAC_OSX_PREFIX_LEN + 1, GFP_KERNEL);
> + strbuf = kmalloc((HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> + HFSPLUS_ATTR_MAX_STRLEN + XATTR_MAC_OSX_PREFIX_LEN + 1,
> + GFP_KERNEL);

Ditto. What’s about to introduce a variable for length calculation?

> if (!strbuf) {
> res = -ENOMEM;
> goto out;
> @@ -732,7 +735,8 @@ ssize_t hfsplus_listxattr(struct dentry *dentry, char *buffer, size_t size)
> if (be32_to_cpu(attr_key.cnid) != inode->i_ino)
> goto end_listxattr;
>
> - xattr_name_len = NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN;
> + xattr_name_len = (HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4)
> + * HFSPLUS_ATTR_MAX_STRLEN;
> if (hfsplus_uni2asc(inode->i_sb,
> (const struct hfsplus_unistr *)&fd.key->attr.key_name,
> strbuf, &xattr_name_len)) {
> diff --git a/fs/hfsplus/xattr_security.c b/fs/hfsplus/xattr_security.c
> index c1c7a16cbf21..438ebcd1359b 100644
> --- a/fs/hfsplus/xattr_security.c
> +++ b/fs/hfsplus/xattr_security.c
> @@ -41,7 +41,8 @@ static int hfsplus_initxattrs(struct inode *inode,
> char *xattr_name;
> int err = 0;
>
> - xattr_name = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_ATTR_MAX_STRLEN + 1,
> + xattr_name = kmalloc((HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> + HFSPLUS_ATTR_MAX_STRLEN + 1,
> GFP_KERNEL);

Ditto. What’s about to introduce a variable for length calculation?

Thanks,
Slava.

> if (!xattr_name)
> return -ENOMEM;
> --
> 2.20.1
>

2021-08-09 21:22:14

by Viacheslav Dubeyko

[permalink] [raw]

Subject: Re: [RFC PATCH 12/20] hfs: Do not use broken utf8 NLS table for iocharset=utf8 mount option

2021-08-10 00:09:17

by Kari Argillander

[permalink] [raw]

Hello!

On Monday 09 August 2021 10:42:02 Viacheslav Dubeyko wrote:
> > On Aug 8, 2021, at 9:24 AM, Pali Rohár <[email protected]> wrote:
> >
> > NLS table for utf8 is broken and cannot be fixed.
> >
> > So instead of broken utf8 nls functions char2uni() and uni2char() use
> > functions utf8_to_utf32() and utf32_to_utf8() which implements correct
> > encoding and decoding between Unicode code points and UTF-8 sequence.
> >
> > Note that this fs driver does not support full Unicode range, specially
> > UTF-16 surrogate pairs are unsupported. This patch does not change this
> > limitation and support for UTF-16 surrogate pairs stay unimplemented.
> >
> > When iochatset=utf8 is used then set sbi->nls to NULL and use it for
> > distinguish between the fact if NLS table or native UTF-8 functions should
> > be used.
> >
> > Signed-off-by: Pali Rohár <[email protected]>
> > ---
> > fs/hfsplus/dir.c | 6 ++++--
> > fs/hfsplus/options.c | 32 ++++++++++++++++++--------------
> > fs/hfsplus/super.c | 7 +------
> > fs/hfsplus/unicode.c | 31 ++++++++++++++++++++++++++++---
> > fs/hfsplus/xattr.c | 14 +++++++++-----
> > fs/hfsplus/xattr_security.c | 3 ++-
> > 6 files changed, 62 insertions(+), 31 deletions(-)
> >
> > diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
> > index 84714bbccc12..2caf0cd82221 100644
> > --- a/fs/hfsplus/dir.c
> > +++ b/fs/hfsplus/dir.c
> > @@ -144,7 +144,8 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
> > err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
> > if (err)
> > return err;
> > - strbuf = kmalloc(NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN + 1, GFP_KERNEL);
> > + strbuf = kmalloc((HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> > + HFSPLUS_MAX_STRLEN + 1, GFP_KERNEL);
>
> Maybe, introduce some variable that will contain the length calculation?

Ok! I can introduce variable with calculated length into all places.

> > if (!strbuf) {
> > err = -ENOMEM;
> > goto out;
> > @@ -203,7 +204,8 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
> > hfs_bnode_read(fd.bnode, &entry, fd.entryoffset,
> > fd.entrylength);
> > type = be16_to_cpu(entry.type);
> > - len = NLS_MAX_CHARSET_SIZE * HFSPLUS_MAX_STRLEN;
> > + len = (HFSPLUS_SB(sb)->nls ? NLS_MAX_CHARSET_SIZE : 4) *
> > + HFSPLUS_MAX_STRLEN;
> > err = hfsplus_uni2asc(sb, &fd.key->cat.name, strbuf, &len);
> > if (err)
> > goto out;
> > diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
> > index a975548f6b91..16c08cb5c4f8 100644
> > --- a/fs/hfsplus/options.c
> > +++ b/fs/hfsplus/options.c
> > @@ -104,6 +104,9 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
> > char *p;
> > substring_t args[MAX_OPT_ARGS];
> > int tmp, token;
> > + int have_iocharset;
> > +
> > + have_iocharset = 0;
>
> What’s about boolean type and to use true/false?

Ok. I can change type to "bool" and use "true"/"false" values.

> >
> > if (!input)
> > goto done;
> > @@ -171,20 +174,24 @@ int hfsplus_parse_options(char *input, struct hfsplus_sb_info *sbi)
> > pr_warn("option nls= is deprecated, use iocharset=\n");
> > /* fallthrough */
> > case opt_iocharset:
> > - if (sbi->nls) {
> > + if (have_iocharset) {
> > pr_err("unable to change nls mapping\n");
> > return 0;
> > }
> > p = match_strdup(&args[0]);
> > - if (p)
> > - sbi->nls = load_nls(p);
> > - if (!sbi->nls) {
> > - pr_err("unable to load nls mapping \"%s\"\n",
> > - p);
> > - kfree(p);
> > + if (!p)
> > return 0;
> > + if (strcmp(p, "utf8") != 0) {
> > + sbi->nls = load_nls(p);
> > + if (!sbi->nls) {
> > + pr_err("unable to load nls mapping "
> > + "\"%s\"\n", p);
> > + kfree(p);
> > + return 0;
> > + }
> > }
> > kfree(p);
> > + have_iocharset = 1;
>
> Ditto. What’s about true here?
>
> > break;
> > case opt_decompose:
> > clear_bit(HFSPLUS_SB_NODECOMPOSE, &sbi->flags);
...
> > @@ -256,7 +266,22 @@ int hfsplus_uni2asc(struct super_block *sb,
> > static inline int asc2unichar(struct super_block *sb, const char *astr, int len,
> > wchar_t *uc)
> > {
> > - int size = HFSPLUS_SB(sb)->nls->char2uni(astr, len, uc);
> > + struct nls_table *nls = HFSPLUS_SB(sb)->nls;
> > + unicode_t u;
> > + int size;
> > +
> > + if (nls)
> > + size = nls->char2uni(astr, len, uc);
> > + else {
> > + size = utf8_to_utf32(astr, len, &u);
> > + if (size >= 0) {
> > + /* TODO: Add support for UTF-16 surrogate pairs */
>
> Have you forgot to delete this string? Or do you plan to implement this?

No. I have not forgot. In current version there is missing support for
UTF-16 surrogate pairs and this my patch still does not implement it.

So this is kind a issue / bug in the driver and at least it should be
documented. So reader of this code would know it and maybe somebody in
future will implement it.

> > + if (u <= MAX_WCHAR_T)
> > + *uc = u;
> > + else
> > + size = -EINVAL;
> > + }
> > + }