Re: [RFC PATCH v1 6/6] tools/include/string: Implement `strdup()` and `strndup()`

[Willy Tarreau]

Hi Ammar,

On Sun, Mar 20, 2022 at 04:37:50PM +0700, Ammar Faizi wrote:
> Add strdup and strndup support. These functions are only available on
> architectures that have my_syscall6() macro from nolibc.
> 
> Signed-off-by: Ammar Faizi <ammarfaizi2@xxxxxxxxxxx>
> ---
>  tools/include/nolibc/string.h | 68 +++++++++++++++++++++++++++++++++++
>  1 file changed, 68 insertions(+)
> 
> diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
> index 4554b6fcb400..413c65f7c853 100644
> --- a/tools/include/nolibc/string.h
> +++ b/tools/include/nolibc/string.h
> @@ -9,6 +9,10 @@
>  
>  #include "std.h"
>  
> +static void free(void *ptr);
> +static void *malloc(size_t len);
> +static void *realloc(void *old_ptr, size_t new_size);

Better include the required h files here.

>  /*
>   * As much as possible, please keep functions alphabetically sorted.
>   */
> @@ -127,6 +131,70 @@ size_t nolibc_strlen(const char *str)
>  		nolibc_strlen((str));           \
>  })
>  
> +static __attribute__((unused))
> +char *strdup(const char *str)
> +{
> +	size_t allocated = 2048;
> +	size_t i;
> +	char *ret;
> +	char *tmp;
> +
> +	ret = malloc(allocated);
> +	if (__builtin_expect(!ret, 0))
> +		return NULL;
> +
> +	i = 0;
> +	for (;;) {
> +		char c = *str;
> +		if (!c)
> +			break;
> +
> +		if (i == allocated) {
> +			allocated += 2048;
> +			tmp = realloc(ret, allocated);
> +			if (__builtin_expect(!tmp, 0)) {
> +				free(ret);
> +				return NULL;
> +			}
> +			ret = tmp;
> +		}
> +
> +		ret[i++] = c;
> +		str++;
> +	}
> +
> +	ret[i] = '\0';
> +	return ret;
> +}

This version is suboptimal in terms of code size, CPU usage and memory
usage. And it even seems it contains a buffer overflow: if the string
is exactly a multiple of 2048, it seems to me that you'll write the
trailing zero past the end. Please instead use the more intuitive form
below (not tested but you get the idea):

	size_t len = strlen(str);
	char *ret = malloc(len + 1);
	if (ret)
		memcpy(ret, str, len);
	return ret;

> +static __attribute__((unused))
> +char *strndup(const char *str, size_t maxlen)
> +{
> +	size_t i;
> +	char *ret;
> +
> +	ret = malloc(maxlen + 1);
> +	if (__builtin_expect(!ret, 0))
> +		return NULL;
> +
> +	i = 0;
> +	for (;;) {
> +		char c = *str;
> +		if (!c)
> +			break;
> +
> +		if (i == maxlen)
> +			break;
> +
> +		ret[i++] = c;
> +		str++;
> +	}
> +
> +	ret[i] = '\0';
> +	return ret;
> +}

Here it can cost quite a lot for large values of maxlen. Please just use
a variant of the proposal above like this one:

	size_t len;
	char *ret;

	len = strlen(str);
	if (len > maxlen)
		len = maxlen;
	ret = malloc(len + 1);
	if (ret)
		memcpy(ret, str, len);
	return ret;

Thanks,
Willy