| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAKYAXd9fEJP7XsZtCMdCPszhhdgUrVhN=8RARrWs=Pq9uTw2aA@mail.gmail.com>
Date: Fri, 18 Nov 2011 13:15:12 +0900
From: NamJae Jeon <linkinjeon@...il.com>
To: Alan Stern <stern@...land.harvard.edu>,
OGAWA Hirofumi <hirofumi@...l.parknet.co.jp>
Cc: Greg KH <greg@...ah.com>, Clemens Ladisch <clemens@...isch.de>,
USB list <linux-usb@...r.kernel.org>,
Kernel development list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] NLS: improve UTF8 -> UTF16 string conversion routine
2011/11/18 Alan Stern <stern@...land.harvard.edu>:
> The utf8s_to_utf16s conversion routine needs to be improved. Unlike
> its utf16s_to_utf8s sibling, it doesn't accept arguments specifying
> the maximum length of the output buffer or the endianness of its
> 16-bit output.
>
> This patch (as1501) adds the two missing arguments, and adjusts the
> only two places in the kernel where the function is called. A
> follow-on patch will add a third caller that does utilize the new
> capabilities.
>
> The two conversion routines are still annoyingly inconsistent in the
> way they handle invalid byte combinations. But that's a subject for a
> different patch.
>
> Signed-off-by: Alan Stern <stern@...land.harvard.edu>
> CC: Clemens Ladisch <clemens@...isch.de>
>
> ---
>
> drivers/hv/hv_kvp.c | 10 ++++++----
> fs/fat/namei_vfat.c | 3 ++-
> fs/nls/nls_base.c | 43 +++++++++++++++++++++++++++++++++----------
> include/linux/nls.h | 5 +++--
> 4 files changed, 44 insertions(+), 17 deletions(-)
>
> Index: usb-3.2/include/linux/nls.h
> ===================================================================
> --- usb-3.2.orig/include/linux/nls.h
> +++ usb-3.2/include/linux/nls.h
> @@ -43,7 +43,7 @@ enum utf16_endian {
> UTF16_BIG_ENDIAN
> };
>
> -/* nls.c */
> +/* nls_base.c */
> extern int register_nls(struct nls_table *);
> extern int unregister_nls(struct nls_table *);
> extern struct nls_table *load_nls(char *);
> @@ -52,7 +52,8 @@ extern struct nls_table *load_nls_defaul
>
> extern int utf8_to_utf32(const u8 *s, int len, unicode_t *pu);
> extern int utf32_to_utf8(unicode_t u, u8 *s, int maxlen);
> -extern int utf8s_to_utf16s(const u8 *s, int len, wchar_t *pwcs);
> +extern int utf8s_to_utf16s(const u8 *s, int len,
> + enum utf16_endian endian, wchar_t *pwcs, int maxlen);
> extern int utf16s_to_utf8s(const wchar_t *pwcs, int len,
> enum utf16_endian endian, u8 *s, int maxlen);
>
> Index: usb-3.2/fs/nls/nls_base.c
> ===================================================================
> --- usb-3.2.orig/fs/nls/nls_base.c
> +++ usb-3.2/fs/nls/nls_base.c
> @@ -114,34 +114,57 @@ int utf32_to_utf8(unicode_t u, u8 *s, in
> }
> EXPORT_SYMBOL(utf32_to_utf8);
>
> -int utf8s_to_utf16s(const u8 *s, int len, wchar_t *pwcs)
> +static inline void put_utf16(wchar_t *s, unsigned c, enum utf16_endian endian)
> +{
> + switch (endian) {
> + default:
> + *s = (wchar_t) c;
> + break;
> + case UTF16_LITTLE_ENDIAN:
> + *s = __cpu_to_le16(c);
> + break;
> + case UTF16_BIG_ENDIAN:
> + *s = __cpu_to_be16(c);
> + break;
> + }
> +}
> +
> +int utf8s_to_utf16s(const u8 *s, int len, enum utf16_endian endian,
> + wchar_t *pwcs, int maxlen)
> {
> u16 *op;
> int size;
> unicode_t u;
>
> op = pwcs;
> - while (*s && len > 0) {
> + while (len > 0 && maxlen > 0 && *s) {
> if (*s & 0x80) {
> size = utf8_to_utf32(s, len, &u);
> if (size < 0)
> return -EINVAL;
> + s += size;
> + len -= size;
Why did you move this code to here ?
>
> if (u >= PLANE_SIZE) {
> + if (maxlen < 2)
> + break;
> u -= PLANE_SIZE;
> - *op++ = (wchar_t) (SURROGATE_PAIR |
> - ((u >> 10) & SURROGATE_BITS));
> - *op++ = (wchar_t) (SURROGATE_PAIR |
> + put_utf16(op++, SURROGATE_PAIR |
> + ((u >> 10) & SURROGATE_BITS),
> + endian);
> + put_utf16(op++, SURROGATE_PAIR |
> SURROGATE_LOW |
> - (u & SURROGATE_BITS));
> + (u & SURROGATE_BITS),
> + endian);
> + maxlen -= 2;
Why did you use contants value(-2) instead of maxlen -= size; value ?
> } else {
> - *op++ = (wchar_t) u;
> + put_utf16(op++, u, endian);
> + maxlen--;
> }
> - s += size;
> - len -= size;
> } else {
> - *op++ = *s++;
> + put_utf16(op++, *s++, endian);
> len--;
> + maxlen--;
> }
> }
> return op - pwcs;
> Index: usb-3.2/fs/fat/namei_vfat.c
> ===================================================================
> --- usb-3.2.orig/fs/fat/namei_vfat.c
> +++ usb-3.2/fs/fat/namei_vfat.c
> @@ -512,7 +512,8 @@ xlate_to_uni(const unsigned char *name,
> int charlen;
>
> if (utf8) {
> - *outlen = utf8s_to_utf16s(name, len, (wchar_t *)outname);
> + *outlen = utf8s_to_utf16s(name, len, UTF16_HOST_ENDIAN,
> + (wchar_t *) outname, FAT_LFN_LEN + 2);
Is there the reason why you plus 2 to FAT_LFN_LEN ?
> if (*outlen < 0)
> return *outlen;
> else if (*outlen > FAT_LFN_LEN)
return -ENAMETOOLONG;
"else if (*outlen > FAT_LFN_LEN)" code is needed ? Is there the case
that *outlen is over FAT_LFN_LEN in your patch ?
Thanks.
> Index: usb-3.2/drivers/hv/hv_kvp.c
> ===================================================================
> --- usb-3.2.orig/drivers/hv/hv_kvp.c
> +++ usb-3.2/drivers/hv/hv_kvp.c
> @@ -212,11 +212,13 @@ kvp_respond_to_host(char *key, char *val
> * The windows host expects the key/value pair to be encoded
> * in utf16.
> */
> - keylen = utf8s_to_utf16s(key_name, strlen(key_name),
> - (wchar_t *)kvp_data->data.key);
> + keylen = utf8s_to_utf16s(key_name, strlen(key_name), UTF16_HOST_ENDIAN,
> + (wchar_t *) kvp_data->data.key,
> + HV_KVP_EXCHANGE_MAX_KEY_SIZE / 2);
> kvp_data->data.key_size = 2*(keylen + 1); /* utf16 encoding */
> - valuelen = utf8s_to_utf16s(value, strlen(value),
> - (wchar_t *)kvp_data->data.value);
> + valuelen = utf8s_to_utf16s(value, strlen(value), UTF16_HOST_ENDIAN,
> + (wchar_t *) kvp_data->data.value,
> + HV_KVP_EXCHANGE_MAX_VALUE_SIZE / 2);
> kvp_data->data.value_size = 2*(valuelen + 1); /* utf16 encoding */
>
> kvp_data->data.value_type = REG_SZ; /* all our values are strings */
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@...r.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
Powered by blists - more mailing lists