Hello!
On Monday 09 August 2021 10:42:02 Viacheslav Dubeyko wrote:
> > On Aug 8, 2021, at 9:24 AM, Pali Rohár <pali@xxxxxxxxxx> 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 <pali@xxxxxxxxxx>
> > ---
> > 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;
> > + }
> > + }
