mirror of
https://github.com/fluencelabs/musl
synced 2025-06-12 22:41:37 +00:00
reenable word-at-at-time copying in memmove
before restrict was added, memove called memcpy for forward copies and used a byte-at-a-time loop for reverse copies. this was changed to avoid invoking UB now that memcpy has an undefined copying order, making memmove considerably slower. performance is still rather bad, so I'll be adding asm soon.
This commit is contained in:
@ -1,13 +1,36 @@
|
||||
#include <string.h>
|
||||
#include <stdint.h>
|
||||
|
||||
#define WT size_t
|
||||
#define WS (sizeof(WT))
|
||||
|
||||
void *memmove(void *dest, const void *src, size_t n)
|
||||
{
|
||||
char *d = dest;
|
||||
const char *s = src;
|
||||
|
||||
if (d==s) return d;
|
||||
if ((size_t)(d-s) < n)
|
||||
while (n--) d[n] = s[n];
|
||||
else
|
||||
while (n--) *d++ = *s++;
|
||||
if (s+n <= d || d+n <= s) return memcpy(d, s, n);
|
||||
|
||||
if (d<s) {
|
||||
if ((uintptr_t)s % WS == (uintptr_t)d % WS) {
|
||||
while ((uintptr_t)d % WS) {
|
||||
if (!n--) return dest;
|
||||
*d++ = *s++;
|
||||
}
|
||||
for (; n>=WS; n-=WS, d+=WS, s+=WS) *(WT *)d = *(WT *)s;
|
||||
}
|
||||
for (; n; n--) *d++ = *s++;
|
||||
} else {
|
||||
if ((uintptr_t)s % WS == (uintptr_t)d % WS) {
|
||||
while ((uintptr_t)(d+n) % WS) {
|
||||
if (!n--) return dest;
|
||||
d[n] = s[n];
|
||||
}
|
||||
while (n>=WS) n-=WS, *(WT *)(d+n) = *(WT *)(s+n);
|
||||
}
|
||||
while (n) n--, d[n] = s[n];
|
||||
}
|
||||
|
||||
return dest;
|
||||
}
|
||||
|
Reference in New Issue
Block a user