[PATCH 2/3] riscv: optimized memmove

[Nick Kossifidis]

On 1/28/24 13:10, Jisheng Zhang wrote:
> From: Matteo Croce <mcroce at microsoft.com>
> 
> When the destination buffer is before the source one, or when the
> buffers doesn't overlap, it's safe to use memcpy() instead, which is
> optimized to use a bigger data size possible.
> 
> Signed-off-by: Matteo Croce <mcroce at microsoft.com>
> Reported-by: kernel test robot <lkp at intel.com>
> Signed-off-by: Jisheng Zhang <jszhang at kernel.org>

I'd expect to have memmove handle both fw/bw copying and then memcpy 
being an alias to memmove, to also take care when regions overlap and 
avoid undefined behavior.


> --- a/arch/riscv/lib/string.c
> +++ b/arch/riscv/lib/string.c
> @@ -119,3 +119,28 @@ void *memcpy(void *dest, const void *src, size_t count) __weak __alias(__memcpy)
>   EXPORT_SYMBOL(memcpy);
>   void *__pi_memcpy(void *dest, const void *src, size_t count) __alias(__memcpy);
>   void *__pi___memcpy(void *dest, const void *src, size_t count) __alias(__memcpy);
> +
> +/*
> + * Simply check if the buffer overlaps an call memcpy() in case,
> + * otherwise do a simple one byte at time backward copy.
> + */
> +void *__memmove(void *dest, const void *src, size_t count)
> +{
> +	if (dest < src || src + count <= dest)
> +		return __memcpy(dest, src, count);
> +
> +	if (dest > src) {
> +		const char *s = src + count;
> +		char *tmp = dest + count;
> +
> +		while (count--)
> +			*--tmp = *--s;
> +	}
> +	return dest;
> +}
> +EXPORT_SYMBOL(__memmove);
> +

Here is an approach for the backwards case to get things started...

static void
copy_bw(void *dst_ptr, const void *src_ptr, size_t len)
{
	union const_data src = { .as_bytes = src_ptr + len };
	union data dst = { .as_bytes = dst_ptr + len };
	size_t remaining = len;
	size_t src_offt = 0;

	if (len < 2 * WORD_SIZE)
		goto trailing_bw;

	for(; dst.as_uptr & WORD_MASK; remaining--)
		*--dst.as_bytes = *--src.as_bytes;

	src_offt = src.as_uptr & WORD_MASK;
	if (!src_offt) {
		for (; remaining >= WORD_SIZE; remaining -= WORD_SIZE)
			*--dst.as_ulong = *--src.as_ulong;
	} else {
		unsigned long cur, prev;
		src.as_bytes -= src_offt;
		for (; remaining >= WORD_SIZE; remaining -= WORD_SIZE) {
			cur = *src.as_ulong;
			prev = *--src.as_ulong;
			*--dst.as_ulong = cur << ((WORD_SIZE - src_offt) * 8) |
					  prev >> (src_offt * 8);
		}
		src.as_bytes += src_offt;
	}

  trailing_bw:
	while (remaining-- > 0)
		*--dst.as_bytes = *--src.as_bytes;
}

Regards,
Nick