mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-27 15:15:02 +07:00
793ae77469
They don't actually clobber memory, but gcc doesn't even know they _read_ memory, so can apparently re-order memory accesses around them. Which obviously does the wrong thing if the memory access happens to change the memory that the compare function is accessing.. Verified to fix a strange boot problem by Jens Axboe.
495 lines
11 KiB
C
495 lines
11 KiB
C
#ifndef _I386_STRING_H_
|
|
#define _I386_STRING_H_
|
|
|
|
#ifdef __KERNEL__
|
|
#include <linux/config.h>
|
|
/*
|
|
* On a 486 or Pentium, we are better off not using the
|
|
* byte string operations. But on a 386 or a PPro the
|
|
* byte string ops are faster than doing it by hand
|
|
* (MUCH faster on a Pentium).
|
|
*/
|
|
|
|
/*
|
|
* This string-include defines all string functions as inline
|
|
* functions. Use gcc. It also assumes ds=es=data space, this should be
|
|
* normal. Most of the string-functions are rather heavily hand-optimized,
|
|
* see especially strsep,strstr,str[c]spn. They should work, but are not
|
|
* very easy to understand. Everything is done entirely within the register
|
|
* set, making the functions fast and clean. String instructions have been
|
|
* used through-out, making for "slightly" unclear code :-)
|
|
*
|
|
* NO Copyright (C) 1991, 1992 Linus Torvalds,
|
|
* consider these trivial functions to be PD.
|
|
*/
|
|
|
|
/* AK: in fact I bet it would be better to move this stuff all out of line.
|
|
*/
|
|
|
|
#define __HAVE_ARCH_STRCPY
|
|
static inline char * strcpy(char * dest,const char *src)
|
|
{
|
|
int d0, d1, d2;
|
|
__asm__ __volatile__(
|
|
"1:\tlodsb\n\t"
|
|
"stosb\n\t"
|
|
"testb %%al,%%al\n\t"
|
|
"jne 1b"
|
|
: "=&S" (d0), "=&D" (d1), "=&a" (d2)
|
|
:"0" (src),"1" (dest) : "memory");
|
|
return dest;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRNCPY
|
|
static inline char * strncpy(char * dest,const char *src,size_t count)
|
|
{
|
|
int d0, d1, d2, d3;
|
|
__asm__ __volatile__(
|
|
"1:\tdecl %2\n\t"
|
|
"js 2f\n\t"
|
|
"lodsb\n\t"
|
|
"stosb\n\t"
|
|
"testb %%al,%%al\n\t"
|
|
"jne 1b\n\t"
|
|
"rep\n\t"
|
|
"stosb\n"
|
|
"2:"
|
|
: "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
|
|
:"0" (src),"1" (dest),"2" (count) : "memory");
|
|
return dest;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRCAT
|
|
static inline char * strcat(char * dest,const char * src)
|
|
{
|
|
int d0, d1, d2, d3;
|
|
__asm__ __volatile__(
|
|
"repne\n\t"
|
|
"scasb\n\t"
|
|
"decl %1\n"
|
|
"1:\tlodsb\n\t"
|
|
"stosb\n\t"
|
|
"testb %%al,%%al\n\t"
|
|
"jne 1b"
|
|
: "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
|
|
: "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu):"memory");
|
|
return dest;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRNCAT
|
|
static inline char * strncat(char * dest,const char * src,size_t count)
|
|
{
|
|
int d0, d1, d2, d3;
|
|
__asm__ __volatile__(
|
|
"repne\n\t"
|
|
"scasb\n\t"
|
|
"decl %1\n\t"
|
|
"movl %8,%3\n"
|
|
"1:\tdecl %3\n\t"
|
|
"js 2f\n\t"
|
|
"lodsb\n\t"
|
|
"stosb\n\t"
|
|
"testb %%al,%%al\n\t"
|
|
"jne 1b\n"
|
|
"2:\txorl %2,%2\n\t"
|
|
"stosb"
|
|
: "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
|
|
: "0" (src),"1" (dest),"2" (0),"3" (0xffffffffu), "g" (count)
|
|
: "memory");
|
|
return dest;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRCMP
|
|
static inline int strcmp(const char * cs,const char * ct)
|
|
{
|
|
int d0, d1;
|
|
register int __res;
|
|
__asm__ __volatile__(
|
|
"1:\tlodsb\n\t"
|
|
"scasb\n\t"
|
|
"jne 2f\n\t"
|
|
"testb %%al,%%al\n\t"
|
|
"jne 1b\n\t"
|
|
"xorl %%eax,%%eax\n\t"
|
|
"jmp 3f\n"
|
|
"2:\tsbbl %%eax,%%eax\n\t"
|
|
"orb $1,%%al\n"
|
|
"3:"
|
|
:"=a" (__res), "=&S" (d0), "=&D" (d1)
|
|
:"1" (cs),"2" (ct)
|
|
:"memory");
|
|
return __res;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRNCMP
|
|
static inline int strncmp(const char * cs,const char * ct,size_t count)
|
|
{
|
|
register int __res;
|
|
int d0, d1, d2;
|
|
__asm__ __volatile__(
|
|
"1:\tdecl %3\n\t"
|
|
"js 2f\n\t"
|
|
"lodsb\n\t"
|
|
"scasb\n\t"
|
|
"jne 3f\n\t"
|
|
"testb %%al,%%al\n\t"
|
|
"jne 1b\n"
|
|
"2:\txorl %%eax,%%eax\n\t"
|
|
"jmp 4f\n"
|
|
"3:\tsbbl %%eax,%%eax\n\t"
|
|
"orb $1,%%al\n"
|
|
"4:"
|
|
:"=a" (__res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
|
|
:"1" (cs),"2" (ct),"3" (count)
|
|
:"memory");
|
|
return __res;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRCHR
|
|
static inline char * strchr(const char * s, int c)
|
|
{
|
|
int d0;
|
|
register char * __res;
|
|
__asm__ __volatile__(
|
|
"movb %%al,%%ah\n"
|
|
"1:\tlodsb\n\t"
|
|
"cmpb %%ah,%%al\n\t"
|
|
"je 2f\n\t"
|
|
"testb %%al,%%al\n\t"
|
|
"jne 1b\n\t"
|
|
"movl $1,%1\n"
|
|
"2:\tmovl %1,%0\n\t"
|
|
"decl %0"
|
|
:"=a" (__res), "=&S" (d0)
|
|
:"1" (s),"0" (c)
|
|
:"memory");
|
|
return __res;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRRCHR
|
|
static inline char * strrchr(const char * s, int c)
|
|
{
|
|
int d0, d1;
|
|
register char * __res;
|
|
__asm__ __volatile__(
|
|
"movb %%al,%%ah\n"
|
|
"1:\tlodsb\n\t"
|
|
"cmpb %%ah,%%al\n\t"
|
|
"jne 2f\n\t"
|
|
"leal -1(%%esi),%0\n"
|
|
"2:\ttestb %%al,%%al\n\t"
|
|
"jne 1b"
|
|
:"=g" (__res), "=&S" (d0), "=&a" (d1)
|
|
:"0" (0),"1" (s),"2" (c)
|
|
:"memory");
|
|
return __res;
|
|
}
|
|
|
|
#define __HAVE_ARCH_STRLEN
|
|
static inline size_t strlen(const char * s)
|
|
{
|
|
int d0;
|
|
register int __res;
|
|
__asm__ __volatile__(
|
|
"repne\n\t"
|
|
"scasb\n\t"
|
|
"notl %0\n\t"
|
|
"decl %0"
|
|
:"=c" (__res), "=&D" (d0)
|
|
:"1" (s),"a" (0), "0" (0xffffffffu)
|
|
:"memory");
|
|
return __res;
|
|
}
|
|
|
|
static inline void * __memcpy(void * to, const void * from, size_t n)
|
|
{
|
|
int d0, d1, d2;
|
|
__asm__ __volatile__(
|
|
"rep ; movsl\n\t"
|
|
"movl %4,%%ecx\n\t"
|
|
"andl $3,%%ecx\n\t"
|
|
#if 1 /* want to pay 2 byte penalty for a chance to skip microcoded rep? */
|
|
"jz 1f\n\t"
|
|
#endif
|
|
"rep ; movsb\n\t"
|
|
"1:"
|
|
: "=&c" (d0), "=&D" (d1), "=&S" (d2)
|
|
: "0" (n/4), "g" (n), "1" ((long) to), "2" ((long) from)
|
|
: "memory");
|
|
return (to);
|
|
}
|
|
|
|
/*
|
|
* This looks ugly, but the compiler can optimize it totally,
|
|
* as the count is constant.
|
|
*/
|
|
static inline void * __constant_memcpy(void * to, const void * from, size_t n)
|
|
{
|
|
long esi, edi;
|
|
if (!n) return to;
|
|
#if 1 /* want to do small copies with non-string ops? */
|
|
switch (n) {
|
|
case 1: *(char*)to = *(char*)from; return to;
|
|
case 2: *(short*)to = *(short*)from; return to;
|
|
case 4: *(int*)to = *(int*)from; return to;
|
|
#if 1 /* including those doable with two moves? */
|
|
case 3: *(short*)to = *(short*)from;
|
|
*((char*)to+2) = *((char*)from+2); return to;
|
|
case 5: *(int*)to = *(int*)from;
|
|
*((char*)to+4) = *((char*)from+4); return to;
|
|
case 6: *(int*)to = *(int*)from;
|
|
*((short*)to+2) = *((short*)from+2); return to;
|
|
case 8: *(int*)to = *(int*)from;
|
|
*((int*)to+1) = *((int*)from+1); return to;
|
|
#endif
|
|
}
|
|
#endif
|
|
esi = (long) from;
|
|
edi = (long) to;
|
|
if (n >= 5*4) {
|
|
/* large block: use rep prefix */
|
|
int ecx;
|
|
__asm__ __volatile__(
|
|
"rep ; movsl"
|
|
: "=&c" (ecx), "=&D" (edi), "=&S" (esi)
|
|
: "0" (n/4), "1" (edi),"2" (esi)
|
|
: "memory"
|
|
);
|
|
} else {
|
|
/* small block: don't clobber ecx + smaller code */
|
|
if (n >= 4*4) __asm__ __volatile__("movsl"
|
|
:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
|
|
if (n >= 3*4) __asm__ __volatile__("movsl"
|
|
:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
|
|
if (n >= 2*4) __asm__ __volatile__("movsl"
|
|
:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
|
|
if (n >= 1*4) __asm__ __volatile__("movsl"
|
|
:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
|
|
}
|
|
switch (n % 4) {
|
|
/* tail */
|
|
case 0: return to;
|
|
case 1: __asm__ __volatile__("movsb"
|
|
:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
|
|
return to;
|
|
case 2: __asm__ __volatile__("movsw"
|
|
:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
|
|
return to;
|
|
default: __asm__ __volatile__("movsw\n\tmovsb"
|
|
:"=&D"(edi),"=&S"(esi):"0"(edi),"1"(esi):"memory");
|
|
return to;
|
|
}
|
|
}
|
|
|
|
#define __HAVE_ARCH_MEMCPY
|
|
|
|
#ifdef CONFIG_X86_USE_3DNOW
|
|
|
|
#include <asm/mmx.h>
|
|
|
|
/*
|
|
* This CPU favours 3DNow strongly (eg AMD Athlon)
|
|
*/
|
|
|
|
static inline void * __constant_memcpy3d(void * to, const void * from, size_t len)
|
|
{
|
|
if (len < 512)
|
|
return __constant_memcpy(to, from, len);
|
|
return _mmx_memcpy(to, from, len);
|
|
}
|
|
|
|
static __inline__ void *__memcpy3d(void *to, const void *from, size_t len)
|
|
{
|
|
if (len < 512)
|
|
return __memcpy(to, from, len);
|
|
return _mmx_memcpy(to, from, len);
|
|
}
|
|
|
|
#define memcpy(t, f, n) \
|
|
(__builtin_constant_p(n) ? \
|
|
__constant_memcpy3d((t),(f),(n)) : \
|
|
__memcpy3d((t),(f),(n)))
|
|
|
|
#else
|
|
|
|
/*
|
|
* No 3D Now!
|
|
*/
|
|
|
|
#define memcpy(t, f, n) \
|
|
(__builtin_constant_p(n) ? \
|
|
__constant_memcpy((t),(f),(n)) : \
|
|
__memcpy((t),(f),(n)))
|
|
|
|
#endif
|
|
|
|
#define __HAVE_ARCH_MEMMOVE
|
|
void *memmove(void * dest,const void * src, size_t n);
|
|
|
|
#define memcmp __builtin_memcmp
|
|
|
|
#define __HAVE_ARCH_MEMCHR
|
|
static inline void * memchr(const void * cs,int c,size_t count)
|
|
{
|
|
int d0;
|
|
register void * __res;
|
|
if (!count)
|
|
return NULL;
|
|
__asm__ __volatile__(
|
|
"repne\n\t"
|
|
"scasb\n\t"
|
|
"je 1f\n\t"
|
|
"movl $1,%0\n"
|
|
"1:\tdecl %0"
|
|
:"=D" (__res), "=&c" (d0)
|
|
:"a" (c),"0" (cs),"1" (count)
|
|
:"memory");
|
|
return __res;
|
|
}
|
|
|
|
static inline void * __memset_generic(void * s, char c,size_t count)
|
|
{
|
|
int d0, d1;
|
|
__asm__ __volatile__(
|
|
"rep\n\t"
|
|
"stosb"
|
|
: "=&c" (d0), "=&D" (d1)
|
|
:"a" (c),"1" (s),"0" (count)
|
|
:"memory");
|
|
return s;
|
|
}
|
|
|
|
/* we might want to write optimized versions of these later */
|
|
#define __constant_count_memset(s,c,count) __memset_generic((s),(c),(count))
|
|
|
|
/*
|
|
* memset(x,0,y) is a reasonably common thing to do, so we want to fill
|
|
* things 32 bits at a time even when we don't know the size of the
|
|
* area at compile-time..
|
|
*/
|
|
static inline void * __constant_c_memset(void * s, unsigned long c, size_t count)
|
|
{
|
|
int d0, d1;
|
|
__asm__ __volatile__(
|
|
"rep ; stosl\n\t"
|
|
"testb $2,%b3\n\t"
|
|
"je 1f\n\t"
|
|
"stosw\n"
|
|
"1:\ttestb $1,%b3\n\t"
|
|
"je 2f\n\t"
|
|
"stosb\n"
|
|
"2:"
|
|
:"=&c" (d0), "=&D" (d1)
|
|
:"a" (c), "q" (count), "0" (count/4), "1" ((long) s)
|
|
:"memory");
|
|
return (s);
|
|
}
|
|
|
|
/* Added by Gertjan van Wingerde to make minix and sysv module work */
|
|
#define __HAVE_ARCH_STRNLEN
|
|
static inline size_t strnlen(const char * s, size_t count)
|
|
{
|
|
int d0;
|
|
register int __res;
|
|
__asm__ __volatile__(
|
|
"movl %2,%0\n\t"
|
|
"jmp 2f\n"
|
|
"1:\tcmpb $0,(%0)\n\t"
|
|
"je 3f\n\t"
|
|
"incl %0\n"
|
|
"2:\tdecl %1\n\t"
|
|
"cmpl $-1,%1\n\t"
|
|
"jne 1b\n"
|
|
"3:\tsubl %2,%0"
|
|
:"=a" (__res), "=&d" (d0)
|
|
:"c" (s),"1" (count)
|
|
:"memory");
|
|
return __res;
|
|
}
|
|
/* end of additional stuff */
|
|
|
|
#define __HAVE_ARCH_STRSTR
|
|
|
|
extern char *strstr(const char *cs, const char *ct);
|
|
|
|
/*
|
|
* This looks horribly ugly, but the compiler can optimize it totally,
|
|
* as we by now know that both pattern and count is constant..
|
|
*/
|
|
static inline void * __constant_c_and_count_memset(void * s, unsigned long pattern, size_t count)
|
|
{
|
|
switch (count) {
|
|
case 0:
|
|
return s;
|
|
case 1:
|
|
*(unsigned char *)s = pattern;
|
|
return s;
|
|
case 2:
|
|
*(unsigned short *)s = pattern;
|
|
return s;
|
|
case 3:
|
|
*(unsigned short *)s = pattern;
|
|
*(2+(unsigned char *)s) = pattern;
|
|
return s;
|
|
case 4:
|
|
*(unsigned long *)s = pattern;
|
|
return s;
|
|
}
|
|
#define COMMON(x) \
|
|
__asm__ __volatile__( \
|
|
"rep ; stosl" \
|
|
x \
|
|
: "=&c" (d0), "=&D" (d1) \
|
|
: "a" (pattern),"0" (count/4),"1" ((long) s) \
|
|
: "memory")
|
|
{
|
|
int d0, d1;
|
|
switch (count % 4) {
|
|
case 0: COMMON(""); return s;
|
|
case 1: COMMON("\n\tstosb"); return s;
|
|
case 2: COMMON("\n\tstosw"); return s;
|
|
default: COMMON("\n\tstosw\n\tstosb"); return s;
|
|
}
|
|
}
|
|
|
|
#undef COMMON
|
|
}
|
|
|
|
#define __constant_c_x_memset(s, c, count) \
|
|
(__builtin_constant_p(count) ? \
|
|
__constant_c_and_count_memset((s),(c),(count)) : \
|
|
__constant_c_memset((s),(c),(count)))
|
|
|
|
#define __memset(s, c, count) \
|
|
(__builtin_constant_p(count) ? \
|
|
__constant_count_memset((s),(c),(count)) : \
|
|
__memset_generic((s),(c),(count)))
|
|
|
|
#define __HAVE_ARCH_MEMSET
|
|
#define memset(s, c, count) \
|
|
(__builtin_constant_p(c) ? \
|
|
__constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count)) : \
|
|
__memset((s),(c),(count)))
|
|
|
|
/*
|
|
* find the first occurrence of byte 'c', or 1 past the area if none
|
|
*/
|
|
#define __HAVE_ARCH_MEMSCAN
|
|
static inline void * memscan(void * addr, int c, size_t size)
|
|
{
|
|
if (!size)
|
|
return addr;
|
|
__asm__("repnz; scasb\n\t"
|
|
"jnz 1f\n\t"
|
|
"dec %%edi\n"
|
|
"1:"
|
|
: "=D" (addr), "=c" (size)
|
|
: "0" (addr), "1" (size), "a" (c)
|
|
: "memory");
|
|
return addr;
|
|
}
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif
|