Re: [PATCH 03/10] cifs: add replacement for cifs_strtoUCS_le called cifs_utf16le_to_host

On Wed, Apr 29, 2009 at 8:29 AM, Jeff Layton <[email protected]> wrote:
> Add a replacement function for cifs_strtoUCS_le. cifs_utf16le_to_host
> takes args for the source and destination length so that we can ensure
> that the function is confined within the intended buffers.
>
> Signed-off-by: Jeff Layton <[email protected]>
> ---
>  fs/cifs/cifs_unicode.c |  121 ++++++++++++++++++++++++++++++++++++++++++++++++
>  fs/cifs/cifs_unicode.h |    2 +
>  2 files changed, 123 insertions(+), 0 deletions(-)
>
> diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
> index 7d75272..aafaf0d 100644
> --- a/fs/cifs/cifs_unicode.c
> +++ b/fs/cifs/cifs_unicode.c
> @@ -26,6 +26,127 @@
>  #include "cifs_debug.h"
>
>  /*
> + * cifs_mapchar - convert a little-endian char to proper char in codepage
> + * @target - where converted character should be copied
> + * @src_char - 2 byte little-endian source character
> + * @cp - codepage to which character should be converted
> + * @mapchar - should character be mapped according to mapchars mount option?
> + *
> + * This function handles the conversion of a single character. It is the
> + * responsibility of the caller to ensure that the target buffer is large
> + * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
> + */
> +static int
> +cifs_mapchar(char *target, const __le16 src_char, const struct nls_table *cp,
> +            bool mapchar)
> +{
> +       int len = 1;
> +
> +       if (!mapchar)
> +               goto cp_convert;
> +
> +       /*
> +        * BB: Cannot handle remapping UNI_SLASH until all the calls to
> +        *     build_path_from_dentry are modified, as they use slash as
> +        *     separator.
> +        */
> +       switch (le16_to_cpu(src_char)) {
> +       case UNI_COLON:
> +               *target = ':';
> +               break;
> +       case UNI_ASTERIK:
> +               *target = '*';
> +               break;
> +       case UNI_QUESTION:
> +               *target = '?';
> +               break;
> +       case UNI_PIPE:
> +               *target = '|';
> +               break;
> +       case UNI_GRTRTHAN:
> +               *target = '>';
> +               break;
> +       case UNI_LESSTHAN:
> +               *target = '<';
> +               break;
> +       default:
> +               goto cp_convert;
> +       }
> +
> +out:
> +       return len;
> +
> +cp_convert:
> +       len = cp->uni2char(le16_to_cpu(src_char), target,
> +                          NLS_MAX_CHARSET_SIZE);
> +       if (len <= 0) {
> +               *target = '?';
> +               len = 1;
> +       }
> +       goto out;
> +}
> +
> +/*
> + * cifs_utf16le_to_host - convert utf16le string to local charset
> + * @to - destination buffer
> + * @from - source buffer
> + * @tolen - destination buffer size (in bytes)
> + * @fromlen - source buffer size (in bytes)
> + * @codepage - codepage to which characters should be converted
> + * @mapchar - should characters be remapped according to the mapchars option?
> + *
> + * Convert a little-endian utf16le string (as sent by the server) to a string
> + * in the provided codepage. The tolen and fromlen parameters are to ensure
> + * that the code doesn't walk off of the end of the buffer (which is always
> + * a danger if the alignment of the source buffer is off). The destination
> + * string is always properly null terminated and fits in the destination
> + * buffer. Returns the length of the destination string in bytes (including
> + * null terminator).
> + */
> +int
> +cifs_utf16le_to_host(char *to, const __le16 *from, int tolen, int fromlen,
> +                    const struct nls_table *codepage, bool mapchar)
> +{
> +       int i, charlen, safelen;
> +       int outlen = 0;
> +       int nullsize = null_charlen(codepage);
> +       int fromwords = fromlen / 2;

I think assumption here is code values are two bytes.  I think that is
correct in case of UCS-2 encoding
but in case of UTF-16, the code values can be either two or four bytes.

> +       char tmp[NLS_MAX_CHARSET_SIZE];
> +
> +       /*
> +        * because the chars can be of varying widths, we need to take care
> +        * not to overflow the destination buffer when we get close to the
> +        * end of it. Until we get to this offset, we don't need to check
> +        * for overflow however.
> +        */
> +       safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);

Can safelen become negative?  In case of a code value byte stream
consisting of say two, two byte code values?

> +
> +       for (i = 0; i < fromwords && from[i]; i++) {
> +               /*
> +                * check to see if converting this character might make the
> +                * conversion bleed into the null terminator
> +                */
> +               if (outlen >= safelen) {
> +                       charlen = cifs_mapchar(tmp, from[i], codepage, mapchar);

If mapchar is not set, cifs_mapchar is always going to return 1 (since
uni2char always returns 1)
in case of no error.

> +                       if (charlen <= 0)
> +                               charlen = 1;
> +                       if ((outlen + charlen) > (tolen - nullsize))
> +                               break;
> +               }
> +
> +               /* put converted char into 'to' buffer */
> +               charlen = cifs_mapchar(&to[outlen], from[i], codepage, mapchar);
> +               outlen += charlen;
> +       }
> +
> +       /* properly null-terminate string */
> +       for (i = 0; i < nullsize; i++)
> +               to[outlen++] = 0;
> +
> +       return outlen;
> +}
> +
> +/*
>  * NAME:       cifs_strfromUCS()
>  *
>  * FUNCTION:   Convert little-endian unicode string to character string
> diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
> index 2dfae68..e23ef08 100644
> --- a/fs/cifs/cifs_unicode.h
> +++ b/fs/cifs/cifs_unicode.h
> @@ -72,6 +72,8 @@ extern struct UniCaseRange UniLowerRange[];
>  #endif                         /* UNIUPR_NOLOWER */
>
>  #ifdef __KERNEL__
> +int cifs_utf16le_to_host(char *to, const __le16 *from, int tolen, int fromlen,
> +                        const struct nls_table *codepage, bool mapchar);
>  int cifs_strfromUCS_le(char *, const __le16 *, int, const struct nls_table *);
>  int cifs_strtoUCS(__le16 *, const char *, int, const struct nls_table *);
>  #endif
> --
> 1.6.0.6
>
> _______________________________________________
> linux-cifs-client mailing list
> [email protected]
> https://lists.samba.org/mailman/listinfo/linux-cifs-client
>