klibc.cpp

// -*- c++ -*-
//
// Standalone base libc functions suitable for in-kernel use
//
// Copyright 2005-2008 Matt T. Yourst <yourst@yourst.com>
// Derived from Linux kernel and klibc
//
// This program is free software; it is licensed under the
// GNU General Public License, Version 2.
//

#include <globals.h>
#include <superstl.h>
#include <stdarg.h>
#include <stddef.h>
#include <syscalls.h>

//++MTY Needed for gcc 4.3+:
#undef __USE_EXTERN_INLINES

//
// From asm-x86_64/string.h and asm-i386/string.h:
//
#ifdef __x86_64__

/* Only used for special circumstances. Stolen from i386/string.h */ 
static inline void * __inline_memcpy(void * to, const void * from, size_t n)
{
unsigned long d0, d1, d2;
__asm__ __volatile__(
	"rep ; movsl\n\t"
	"testb $2,%b4\n\t"
	"je 1f\n\t"
	"movsw\n"
	"1:\ttestb $1,%b4\n\t"
	"je 2f\n\t"
	"movsb\n"
	"2:"
	: "=&c" (d0), "=&D" (d1), "=&S" (d2)
	:"0" (n/4), "q" (n),"1" ((long) to),"2" ((long) from)
	: "memory");
return (to);
}

/* Even with __builtin_ the compiler may decide to use the out of line
   function. */

#define __HAVE_ARCH_MEMCPY 1
extern "C" void *__memcpy(void *to, const void *from, size_t len); 
#define memcpy(dst,src,len) \
	({ size_t __len = (len);				\
	   void *__ret;						\
	   if (__builtin_constant_p(len) && __len >= 64)	\
		 __ret = __memcpy((dst),(src),__len);		\
	   else							\
		 __ret = __builtin_memcpy((dst),(src),__len);	\
	   __ret; }) 

#define __HAVE_ARCH_MEMSET
extern "C" void* memset(void* s, int c, size_t count) {
  W64 pat = ((W64)(byte)c) * 0x0101010101010101ULL; // distribute to all bytes

  byte* p = (byte*)s;

  while (count >= 8) {
    *((W64*)p) = pat;
    p += 8;
    count -= 8;
  }

  while (count) {
    *p++ = pat;
    count--;
  }

	return s;
}

#define __HAVE_ARCH_MEMMOVE
void* memmove(void * dest,const void *src,size_t count);

/* Use C out of line version for memcmp */ 
#define memcmp __builtin_memcmp

/* out of line string functions use always C versions */ 
#define strlen __builtin_strlen
#define strcpy __builtin_strcpy
#define strcat __builtin_strcat
#define strcmp __builtin_strcmp

#else

/* i386 */

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 __attribute__((always_inline)) 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
 
extern "C" void* memcpy(void* t, const void* f, size_t n) {
  if (__builtin_constant_p(n))
    return __constant_memcpy((t),(f),(n));
  else return __memcpy((t),(f),(n));
}

//#define __HAVE_ARCH_MEMMOVE
//void *memmove(void * dest,const void * src, size_t n);

#define memcmp __builtin_memcmp

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 __attribute__((always_inline)) 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);	
}

/* end of additional stuff */

/*
 * This looks horribly ugly, but the compiler can optimize it totally,
 * as we by now know that both pattern and count is constant..
 */
static __attribute__((always_inline)) 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
extern "C" void* memset(void* s, int c, size_t count) {
  if (__builtin_constant_p(c))
    return __constant_c_x_memset((s),(0x01010101UL*(unsigned char)(c)),(count));
  return __memset((s),(c),(count));
}
#endif // i386

#ifdef __x86_64__

// Nothing special here: compiler does a good job on its own

#else // 32-bit x86
//
// String functions:
//
/*
 * 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.
 */

#define __HAVE_ARCH_STRCPY
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
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
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
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
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
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
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const char * strchr(const char * s, int c)
#else
char * strchr(const char * s, int c)
#endif
{
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
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const char * strrchr(const char * s, int c)
#else
char * strrchr(const char * s, int c)
#endif
{
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
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;
}

/* Added by Gertjan van Wingerde to make minix and sysv module work */
#define __HAVE_ARCH_STRNLEN
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;
}

#define __HAVE_ARCH_MEMCHR
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const void* memchr(const void * cs,int c,size_t count)
#else
void* memchr(const void * cs,int c,size_t count)
#endif
{
int d0;
register void * __res;
if (!count)
	return 0;
__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;
}

/*
 * 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 // i386


//
// From ctype.h:
//
#define _U	0x01	/* upper */
#define _L	0x02	/* lower */
#define _D	0x04	/* digit */
#define _C	0x08	/* cntrl */
#define _P	0x10	/* punct */
#define _S	0x20	/* white space (space/lf/tab) */
#define _X	0x40	/* hex digit */
#define _SP	0x80	/* hard space (0x20) */

static unsigned char _ctype[] = {
  _C,_C,_C,_C,_C,_C,_C,_C,			/* 0-7 */
  _C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C,		/* 8-15 */
  _C,_C,_C,_C,_C,_C,_C,_C,			/* 16-23 */
  _C,_C,_C,_C,_C,_C,_C,_C,			/* 24-31 */
  _S|_SP,_P,_P,_P,_P,_P,_P,_P,			/* 32-39 */
  _P,_P,_P,_P,_P,_P,_P,_P,			/* 40-47 */
  _D,_D,_D,_D,_D,_D,_D,_D,			/* 48-55 */
  _D,_D,_P,_P,_P,_P,_P,_P,			/* 56-63 */
  _P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U,	/* 64-71 */
  _U,_U,_U,_U,_U,_U,_U,_U,			/* 72-79 */
  _U,_U,_U,_U,_U,_U,_U,_U,			/* 80-87 */
  _U,_U,_U,_P,_P,_P,_P,_P,			/* 88-95 */
  _P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L,	/* 96-103 */
  _L,_L,_L,_L,_L,_L,_L,_L,			/* 104-111 */
  _L,_L,_L,_L,_L,_L,_L,_L,			/* 112-119 */
  _L,_L,_L,_P,_P,_P,_P,_C,			/* 120-127 */
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 128-143 */
  0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 144-159 */
  _S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,   /* 160-175 */
  _P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,       /* 176-191 */
  _U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,       /* 192-207 */
  _U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L,       /* 208-223 */
  _L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,       /* 224-239 */
  _L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L        /* 240-255 */
};

#define __ismask(x) (_ctype[(int)(unsigned char)(x)])

extern "C" {
  inline int isalnum(int c) { return ((__ismask(c)&(_U|_L|_D)) != 0); }
  inline int isalpha(int c) { return ((__ismask(c)&(_U|_L)) != 0); }
  inline int iscntrl(int c) { return ((__ismask(c)&(_C)) != 0); }
  inline int isdigit(int c) { return ((__ismask(c)&(_D)) != 0); }
  inline int isgraph(int c) { return ((__ismask(c)&(_P|_U|_L|_D)) != 0); }
  inline int islower(int c) { return ((__ismask(c)&(_L)) != 0); }
  inline int isprint(int c) { return ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0); }
  inline int ispunct(int c) { return ((__ismask(c)&(_P)) != 0); }
  inline int isspace(int c) { return ((__ismask(c)&(_S)) != 0); }
  inline int isupper(int c) { return ((__ismask(c)&(_U)) != 0); }
  inline int isxdigit(int c) { return ((__ismask(c)&(_D|_X)) != 0); }
  inline int isascii(int c) { return (((unsigned char)(c))<=0x7f); }
  inline int toascii(int c) { return (((unsigned char)(c))&0x7f); }
  inline int tolower(int c) { if (isupper(c)) c -= 'A'-'a'; return c; }
  inline int toupper(int c) { if (islower(c)) c -= 'a'-'A'; return c; }
};

#ifndef __HAVE_ARCH_STRNICMP
/**
 * strnicmp - Case insensitive, length-limited string comparison
 * @s1: One string
 * @s2: The other string
 * @len: the maximum number of characters to compare
 */
int strnicmp(const char *s1, const char *s2, size_t len)
{
	/* Yes, Virginia, it had better be unsigned */
	unsigned char c1, c2;

	c1 = c2 = 0;
	if (len) {
		do {
			c1 = *s1;
			c2 = *s2;
			s1++;
			s2++;
			if (!c1)
				break;
			if (!c2)
				break;
			if (c1 == c2)
				continue;
			c1 = tolower(c1);
			c2 = tolower(c2);
			if (c1 != c2)
				break;
		} while (--len);
	}
	return (int)c1 - (int)c2;
}

#endif

#ifndef __HAVE_ARCH_STRCPY
/**
 * strcpy - Copy a %NUL terminated string
 * @dest: Where to copy the string to
 * @src: Where to copy the string from
 */
#undef strcpy
char *strcpy(char *dest, const char *src)
{
	char *tmp = dest;

	while ((*dest++ = *src++) != '\0')
		/* nothing */;
	return tmp;
}

#endif

#ifndef __HAVE_ARCH_STRNCPY
/**
 * strncpy - Copy a length-limited, %NUL-terminated string
 * @dest: Where to copy the string to
 * @src: Where to copy the string from
 * @count: The maximum number of bytes to copy
 *
 * The result is not %NUL-terminated if the source exceeds
 * @count bytes.
 *
 * In the case where the length of @src is less than  that  of
 * count, the remainder of @dest will be padded with %NUL.
 *
 */
char *strncpy(char *dest, const char *src, size_t count)
{
	char *tmp = dest;

	while (count) {
		if ((*tmp = *src) != 0)
			src++;
		tmp++;
		count--;
	}
	return dest;
}

#endif

#ifndef __HAVE_ARCH_STRLCPY
/**
 * strlcpy - Copy a %NUL terminated string into a sized buffer
 * @dest: Where to copy the string to
 * @src: Where to copy the string from
 * @size: size of destination buffer
 *
 * Compatible with *BSD: the result is always a valid
 * NUL-terminated string that fits in the buffer (unless,
 * of course, the buffer size is zero). It does not pad
 * out the result like strncpy() does.
 */
size_t strlcpy(char *dest, const char *src, size_t size)
{
	size_t ret = strlen(src);

	if (size) {
		size_t len = (ret >= size) ? size - 1 : ret;
		memcpy(dest, src, len);
		dest[len] = '\0';
	}
	return ret;
}

#endif

#ifndef __HAVE_ARCH_STRCAT
/**
 * strcat - Append one %NUL-terminated string to another
 * @dest: The string to be appended to
 * @src: The string to append to it
 */
#undef strcat
char *strcat(char *dest, const char *src)
{
	char *tmp = dest;

	while (*dest)
		dest++;
	while ((*dest++ = *src++) != '\0')
		;
	return tmp;
}

#endif

#ifndef __HAVE_ARCH_STRNCAT
/**
 * strncat - Append a length-limited, %NUL-terminated string to another
 * @dest: The string to be appended to
 * @src: The string to append to it
 * @count: The maximum numbers of bytes to copy
 *
 * Note that in contrast to strncpy, strncat ensures the result is
 * terminated.
 */
char *strncat(char *dest, const char *src, size_t count)
{
	char *tmp = dest;

	if (count) {
		while (*dest)
			dest++;
		while ((*dest++ = *src++) != 0) {
			if (--count == 0) {
				*dest = '\0';
				break;
			}
		}
	}
	return tmp;
}

#endif

#ifndef __HAVE_ARCH_STRLCAT
/**
 * strlcat - Append a length-limited, %NUL-terminated string to another
 * @dest: The string to be appended to
 * @src: The string to append to it
 * @count: The size of the destination buffer.
 */
size_t strlcat(char *dest, const char *src, size_t count)
{
	size_t dsize = strlen(dest);
	size_t len = strlen(src);
	size_t res = dsize + len;

	/* This would be a bug */
	//BUG_ON(dsize >= count);

	dest += dsize;
	count -= dsize;
	if (len >= count)
		len = count-1;
	memcpy(dest, src, len);
	dest[len] = 0;
	return res;
}

#endif

#ifndef __HAVE_ARCH_STRCMP
/**
 * strcmp - Compare two strings
 * @cs: One string
 * @ct: Another string
 */
#undef strcmp
int strcmp(const char *cs, const char *ct)
{
	signed char __res;

	while (1) {
		if ((__res = *cs - *ct++) != 0 || !*cs++)
			break;
	}
	return __res;
}

#endif

#ifndef __HAVE_ARCH_STRNCMP
/**
 * strncmp - Compare two length-limited strings
 * @cs: One string
 * @ct: Another string
 * @count: The maximum number of bytes to compare
 */
int strncmp(const char *cs, const char *ct, size_t count)
{
	signed char __res = 0;

	while (count) {
		if ((__res = *cs - *ct++) != 0 || !*cs++)
			break;
		count--;
	}
	return __res;
}

#endif

#ifndef __HAVE_ARCH_STRCHR
/**
 * strchr - Find the first occurrence of a character in a string
 * @s: The string to be searched
 * @c: The character to search for
 */
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const char *strchr(const char *s, int c)
#else
char *strchr(const char *s, int c)
#endif
{
	for (; *s != (char)c; ++s)
		if (*s == '\0')
			return NULL;
	return (char *)s;
}

#endif

#ifndef __HAVE_ARCH_STRRCHR
/**
 * strrchr - Find the last occurrence of a character in a string
 * @s: The string to be searched
 * @c: The character to search for
 */
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const char *strrchr(const char *s, int c)
#else
char *strrchr(const char *s, int c)
#endif
{
       const char *p = s + strlen(s);
       do {
           if (*p == (char)c)
               return (char *)p;
       } while (--p >= s);
       return NULL;
}

#endif

#ifndef __HAVE_ARCH_STRNCHR
/**
 * strnchr - Find a character in a length limited string
 * @s: The string to be searched
 * @count: The number of characters to be searched
 * @c: The character to search for
 */
char *strnchr(const char *s, size_t count, int c)
{
	for (; count-- && *s != '\0'; ++s)
		if (*s == (char)c)
			return (char *)s;
	return NULL;
}

#endif

#ifndef __HAVE_ARCH_STRLEN
/**
 * strlen - Find the length of a string
 * @s: The string to be sized
 */
size_t strlen(const char *s)
{
	const char *sc;

	for (sc = s; *sc != '\0'; ++sc)
		/* nothing */;
	return sc - s;
}

#endif

#ifndef __HAVE_ARCH_STRNLEN
/**
 * strnlen - Find the length of a length-limited string
 * @s: The string to be sized
 * @count: The maximum number of bytes to search
 */
size_t strnlen(const char *s, size_t count)
{
	const char *sc;

	for (sc = s; count-- && *sc != '\0'; ++sc)
		/* nothing */;
	return sc - s;
}

#endif

#ifndef __HAVE_ARCH_STRSPN
/**
 * strspn - Calculate the length of the initial substring of @s which only
 * 	contain letters in @accept
 * @s: The string to be searched
 * @accept: The string to search for
 */
size_t strspn(const char *s, const char *accept)
{
	const char *p;
	const char *a;
	size_t count = 0;

	for (p = s; *p != '\0'; ++p) {
		for (a = accept; *a != '\0'; ++a) {
			if (*p == *a)
				break;
		}
		if (*a == '\0')
			return count;
		++count;
	}
	return count;
}

#endif

/**
 * strcspn - Calculate the length of the initial substring of @s which does
 * 	not contain letters in @reject
 * @s: The string to be searched
 * @reject: The string to avoid
 */
size_t strcspn(const char *s, const char *reject)
{
	const char *p;
	const char *r;
	size_t count = 0;

	for (p = s; *p != '\0'; ++p) {
		for (r = reject; *r != '\0'; ++r) {
			if (*p == *r)
				return count;
		}
		++count;
	}
	return count;
}


#ifndef __HAVE_ARCH_STRPBRK
/**
 * strpbrk - Find the first occurrence of a set of characters
 * @cs: The string to be searched
 * @ct: The characters to search for
 */
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const char *strpbrk(const char *cs, const char *ct)
#else
char *strpbrk(const char *cs, const char *ct)
#endif
{
	const char *sc1, *sc2;

	for (sc1 = cs; *sc1 != '\0'; ++sc1) {
		for (sc2 = ct; *sc2 != '\0'; ++sc2) {
			if (*sc1 == *sc2)
				return (char *)sc1;
		}
	}
	return NULL;
}

#endif

#ifndef __HAVE_ARCH_STRSEP
/**
 * strsep - Split a string into tokens
 * @s: The string to be searched
 * @ct: The characters to search for
 *
 * strsep() updates @s to point after the token, ready for the next call.
 *
 * It returns empty tokens, too, behaving exactly like the libc function
 * of that name. In fact, it was stolen from glibc2 and de-fancy-fied.
 * Same semantics, slimmer shape. ;)
 */
char *strsep(char **s, const char *ct)
{
	char *sbegin = *s;
	char *end;

	if (sbegin == NULL)
		return NULL;

	end = strpbrk(sbegin, ct);
	if (end)
		*end++ = '\0';
	*s = end;
	return sbegin;
}

#endif

#ifndef __HAVE_ARCH_MEMSET
/**
 * memset - Fill a region of memory with the given value
 * @s: Pointer to the start of the area.
 * @c: The byte to fill the area with
 * @count: The size of the area.
 *
 * Do not use memset() to access IO space, use memset_io() instead.
 */
void *memset(void *s, int c, size_t count)
{
	char *xs = s;

	while (count--)
		*xs++ = c;
	return s;
}

#endif

#ifndef __HAVE_ARCH_MEMCPY
/**
 * memcpy - Copy one area of memory to another
 * @dest: Where to copy to
 * @src: Where to copy from
 * @count: The size of the area.
 *
 * You should not use this function to access IO space, use memcpy_toio()
 * or memcpy_fromio() instead.
 */
void *memcpy(void *dest, const void *src, size_t count)
{
	char *tmp = dest;
	char *s = src;

	while (count--)
		*tmp++ = *s++;
	return dest;
}

#endif

#ifndef __HAVE_ARCH_MEMMOVE
/**
 * memmove - Copy one area of memory to another
 * @dest: Where to copy to
 * @src: Where to copy from
 * @count: The size of the area.
 *
 * Unlike memcpy(), memmove() copes with overlapping areas.
 */
void *memmove(void *dest, const void *src, size_t count)
{
	char *tmp;
	const char *s;

	if (dest <= src) {
		tmp = (char *) dest;
		s = (const char *) src;
		while (count--)
			*tmp++ = *s++;
	} else {
		tmp = (char *)dest;
		tmp += count;
		s = (const char *) src;
		s += count;
		while (count--)
			*--tmp = *--s;
	}
	return dest;
}

#endif

#ifndef __HAVE_ARCH_MEMCMP
/**
 * memcmp - Compare two areas of memory
 * @cs: One area of memory
 * @ct: Another area of memory
 * @count: The size of the area.
 */
#undef memcmp
int memcmp(const void *cs, const void *ct, size_t count)
{
	const unsigned char *su1, *su2;
	int res = 0;

	for (su1 = (const unsigned char*)cs, su2 = (const unsigned char*)ct; 0 < count; ++su1, ++su2, count--)
		if ((res = *su1 - *su2) != 0)
			break;
	return res;
}

#endif

#ifndef __HAVE_ARCH_MEMSCAN
/**
 * memscan - Find a character in an area of memory.
 * @addr: The memory area
 * @c: The byte to search for
 * @size: The size of the area.
 *
 * returns the address of the first occurrence of @c, or 1 byte past
 * the area if @c is not found
 */
void *memscan(void *addr, int c, size_t size)
{
	unsigned char *p = (unsigned char*)addr;

	while (size) {
		if (*p == c)
			return (void *)p;
		p++;
		size--;
	}
  	return (void *)p;
}

#endif

#ifndef __HAVE_ARCH_STRSTR
/**
 * strstr - Find the first substring in a %NUL terminated string
 * @s1: The string to be searched
 * @s2: The string to search for
 */
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const char *strstr(const char *s1, const char *s2)
#else
char *strstr(const char *s1, const char *s2)
#endif
{
	int l1, l2;

	l2 = strlen(s2);
	if (!l2)
		return (char *)s1;
	l1 = strlen(s1);
	while (l1 >= l2) {
		l1--;
		if (!memcmp(s1, s2, l2))
			return (char *)s1;
		s1++;
	}
	return NULL;
}

#endif

#ifndef __HAVE_ARCH_MEMCHR
/**
 * memchr - Find a character in an area of memory.
 * @s: The memory area
 * @c: The byte to search for
 * @n: The size of the area.
 *
 * returns the address of the first occurrence of @c, or %NULL
 * if @c is not found
 */
#ifdef __CORRECT_ISO_CPP_STRING_H_PROTO
const void *memchr(const void *s, int c, size_t n)
#else
void *memchr(const void *s, int c, size_t n)
#endif
{
	const unsigned char *p = (unsigned char*)s;
	while (n-- != 0) {
        	if ((unsigned char)c == *p++) {
			return (void *)(p - 1);
		}
	}
	return NULL;
}

#endif

/**
 * simple_strtoul - convert a string to an unsigned long
 * @cp: The start of the string
 * @endp: A pointer to the end of the parsed string will be placed here
 * @base: The number base to use
 */
#ifdef __USE_EXTERN_INLINES
extern "C" unsigned long __strtoul_internal(const char *cp,char **endp,int base, int group)
#else
extern "C" unsigned long strtoul(const char *cp,char **endp,int base)
#endif
{
	unsigned long result = 0,value;

	if (!base) {
		base = 10;
		if (*cp == '0') {
			base = 8;
			cp++;
			if ((toupper(*cp) == 'X') && isxdigit(cp[1])) {
				cp++;
				base = 16;
			}
		}
	} else if (base == 16) {
		if (cp[0] == '0' && toupper(cp[1]) == 'X')
			cp += 2;
	}
	while (isxdigit(*cp) &&
	       (value = isdigit(*cp) ? *cp-'0' : toupper(*cp)-'A'+10) < base) {
		result = result*base + value;
		cp++;
	}
	if (endp)
		*endp = (char *)cp;
	return result;
}

/**
 * simple_strtol - convert a string to a signed long
 * @cp: The start of the string
 * @endp: A pointer to the end of the parsed string will be placed here
 * @base: The number base to use
 */
#ifdef __USE_EXTERN_INLINES
extern "C" long __strtol_internal(const char *cp,char **endp,int base, int group)
#else
extern "C" long strtol(const char *cp,char **endp,int base)
#endif
{
	if(*cp=='-')
		return -strtoul(cp+1,endp,base);
	return strtoul(cp,endp,base);
}

/**
 * simple_strtoull - convert a string to an unsigned long long
 * @cp: The start of the string
 * @endp: A pointer to the end of the parsed string will be placed here
 * @base: The number base to use
 */
#ifdef __USE_EXTERN_INLINES
extern "C" unsigned long long __strtoull_internal(const char *cp,char **endp,int base, int group)
#else
extern "C" unsigned long long strtoull(const char *cp,char **endp,int base)
#endif
{
	unsigned long long result = 0,value;

	if (!base) {
		base = 10;
		if (*cp == '0') {
			base = 8;
			cp++;
			if ((toupper(*cp) == 'X') && isxdigit(cp[1])) {
				cp++;
				base = 16;
			}
		}
	} else if (base == 16) {
		if (cp[0] == '0' && toupper(cp[1]) == 'X')
			cp += 2;
	}
	while (isxdigit(*cp) && (value = isdigit(*cp) ? *cp-'0' : (islower(*cp)
	    ? toupper(*cp) : *cp)-'A'+10) < base) {
		result = result*base + value;
		cp++;
	}
	if (endp)
		*endp = (char *)cp;
	return result;
}

/**
 * simple_strtoll - convert a string to a signed long long
 * @cp: The start of the string
 * @endp: A pointer to the end of the parsed string will be placed here
 * @base: The number base to use
 */
#ifdef __USE_EXTERN_INLINES
extern "C" long long __strtoll_internal(const char *cp,char **endp,int base, int group)
#else
extern "C" long long strtoll(const char *cp,char **endp,int base)
#endif
{
	if(*cp=='-')
		return -strtoull(cp+1,endp,base);
	return strtoull(cp,endp,base);
}

static int skip_atoi(const char **s)
{
	int i=0;

	while (isdigit(**s))
		i = i*10 + *((*s)++) - '0';
	return i;
}

/*
int atoi(const char* s) {
  const char* p = s;
  return skip_atoi(&p);
}
*/

#define ZEROPAD FMT_ZEROPAD
#define SIGN    FMT_SIGN
#define PLUS    FMT_PLUS
#define SPACE   FMT_SPACE
#define LEFT    FMT_LEFT
#define SPECIAL FMT_SPECIAL
#define LARGE   FMT_LARGE

//
// This function is very simple and does not handle FP numbers
// larger than the range of a W64. It avoids a lot of the baggage
// associated with the normal glibc implementation.
//
int format_float(char* buf, int bufsize, double v, int precision, int pad) {
  static const double M = 1e18;
  static const double Ms = 1e-18;
  static const int logM = 18;

  W64orDouble u;
  u.d = v;

  bool signbit = u.ieee.negative;
  u.ieee.negative = 0;
  v = u.d;

  double whole = math::trunc(v);
  double frac = v - whole;

  if (math::isnan(u.d)) {
    snprintf(buf, bufsize, "%snan", (signbit ? "-" : "+"));
    return 0;
  }

  if (math::isinf(u.d)) {
    snprintf(buf, bufsize, "%sinf", (signbit ? "-" : "+"));
    return 0;
  }

  if (v >= M) {
    snprintf(buf, bufsize, "<too large>");
    return 0;
  }

  int i;

  W64 fracint = (W64)math::trunc(frac * M);
  W64 wholeint = (W64)whole;

  bool left = (pad < 0);

  int total = 0;

  int remaining = bufsize;

  if (signbit) {
    buf[0] = '-';
    buf++;
    total++;
    remaining--;
  }

  int n = format_integer(buf, remaining, wholeint, abs(pad), (left ? FMT_LEFT : 0));
  remaining = max(remaining - n, 0);
  total += n;
  if (remaining < 1) return total;
  assert(n < bufsize-1);
  buf[n] = '.';
  total++;
  remaining--;
  n = format_integer(buf + n + 1, max(min(remaining, precision+1), 0), fracint, 0, 0);
  total += n;
  buf[total] = 0;
  return total;
}

/**
 * vsnprintf - Format a string and place it in a buffer
 * @buf: The buffer to place the result into
 * @size: The size of the buffer, including the trailing null space
 * @fmt: The format string to use
 * @args: Arguments for the format string
 *
 * The return value is the number of characters which would
 * be generated for the given input, excluding the trailing
 * '\0', as per ISO C99. If you want to have the exact
 * number of characters written into @buf as return value
 * (not including the trailing '\0'), use vscnprintf. If the
 * return is greater than or equal to @size, the resulting
 * string is truncated.
 *
 * Call this function if you are already dealing with a va_list.
 * You probably want snprintf instead.
 */
int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
{
	int len;
	unsigned long long num;
	int i, base;
	char *str, *end, c;
	const char *s;

	int flags;		/* flags to number() */

	int field_width;	/* width of output field */
	int precision;		/* min. # of digits for integers; max
				   number of chars for from string */
	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
				/* 'z' support added 23/7/1999 S.H.    */
				/* 'z' changed to 'Z' --davidm 1/25/99 */
				/* 't' added for ptrdiff_t */

	/* Reject out-of-range values early */
	if (unlikely((int) size < 0)) {
		/* There can be only one.. */
		static int warn = 1;
		//WARN_ON(warn);
		warn = 0;
		return 0;
	}

	str = buf;
	end = buf + size - 1;

	if (end < buf - 1) {
		end = ((char*) -1);
		size = end - buf + 1;
	}

	for (; *fmt ; ++fmt) {
		if (*fmt != '%') {
			if (str <= end)
				*str = *fmt;
			++str;
			continue;
		}

		/* process flags */
		flags = 0;
		repeat:
			++fmt;		/* this also skips first '%' */
			switch (*fmt) {
				case '-': flags |= LEFT; goto repeat;
				case '+': flags |= PLUS; goto repeat;
				case ' ': flags |= SPACE; goto repeat;
				case '#': flags |= SPECIAL; goto repeat;
				case '0': flags |= ZEROPAD; goto repeat;
			}

		/* get field width */
		field_width = -1;
		if (isdigit(*fmt))
			field_width = skip_atoi(&fmt);
		else if (*fmt == '*') {
			++fmt;
			/* it's the next argument */
			field_width = va_arg(args, int);
			if (field_width < 0) {
				field_width = -field_width;
				flags |= LEFT;
			}
		}

		/* get the precision */
		precision = -1;
		if (*fmt == '.') {
			++fmt;	
			if (isdigit(*fmt))
				precision = skip_atoi(&fmt);
			else if (*fmt == '*') {
				++fmt;
				/* it's the next argument */
				precision = va_arg(args, int);
			}
			if (precision < 0)
				precision = 0;
		}

		/* get the conversion qualifier */
		qualifier = -1;
		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
		    *fmt =='Z' || *fmt == 'z' || *fmt == 't') {
			qualifier = *fmt;
			++fmt;
			if (qualifier == 'l' && *fmt == 'l') {
				qualifier = 'L';
				++fmt;
			}
		}

		/* default base */
		base = 10;

		switch (*fmt) {
			case 'c':
				if (!(flags & LEFT)) {
					while (--field_width > 0) {
						if (str <= end)
							*str = ' ';
						++str;
					}
				}
				c = (unsigned char) va_arg(args, int);
				if (str <= end)
					*str = c;
				++str;
				while (--field_width > 0) {
					if (str <= end)
						*str = ' ';
					++str;
				}
				continue;

			case 's':
				s = va_arg(args, char *);
				if ((unsigned long)s < PAGE_SIZE)
					s = "<NULL>";

				len = strnlen(s, precision);

				if (!(flags & LEFT)) {
					while (len < field_width--) {
						if (str <= end)
							*str = ' ';
						++str;
					}
				}
				for (i = 0; i < len; ++i) {
					if (str <= end)
						*str = *s;
					++str; ++s;
				}
				while (len < field_width--) {
					if (str <= end)
						*str = ' ';
					++str;
				}
				continue;

			case 'p':
				if (field_width == -1) {
					field_width = 2*sizeof(void *);
					flags |= ZEROPAD;
				}
				str = format_number(str, end,
						(unsigned long) va_arg(args, void *),
						16, field_width, precision, flags);
				continue;


			case 'n':
				/* FIXME:
				* What does C99 say about the overflow case here? */
				if (qualifier == 'l') {
					long * ip = va_arg(args, long *);
					*ip = (str - buf);
				} else if (qualifier == 'Z' || qualifier == 'z') {
					size_t * ip = va_arg(args, size_t *);
					*ip = (str - buf);
				} else {
					int * ip = va_arg(args, int *);
					*ip = (str - buf);
				}
				continue;

			case '%':
				if (str <= end)
					*str = '%';
				++str;
				continue;

				/* integer number formats - set up the flags and "break" */
			case 'o':
				base = 8;
				break;

			case 'X':
				flags |= LARGE;
			case 'x':
				base = 16;
				break;

			case 'd':
			case 'i':
				flags |= SIGN;
			case 'u':
				break;

			default:
				if (str <= end)
					*str = '%';
				++str;
				if (*fmt) {
					if (str <= end)
						*str = *fmt;
					++str;
				} else {
					--fmt;
				}
				continue;
		}
		if (qualifier == 'L')
			num = va_arg(args, long long);
		else if (qualifier == 'l') {
			num = va_arg(args, unsigned long);
			if (flags & SIGN)
				num = (signed long) num;
		} else if (qualifier == 'Z' || qualifier == 'z') {
			num = va_arg(args, size_t);
		} else if (qualifier == 't') {
			num = va_arg(args, ptrdiff_t);
		} else if (qualifier == 'h') {
			num = (unsigned short) va_arg(args, int);
			if (flags & SIGN)
				num = (signed short) num;
		} else {
			num = va_arg(args, unsigned int);
			if (flags & SIGN)
				num = (signed int) num;
		}
		str = format_number(str, end, num, base,
				field_width, precision, flags);
	}
	if (str <= end)
		*str = '\0';
	else if (size > 0)
		/* don't write out a null byte if the buf size is zero */
		*end = '\0';
	/* the trailing null byte doesn't count towards the total
	* ++str;
	*/
	return str-buf;
}

/**
 * vscnprintf - Format a string and place it in a buffer
 * @buf: The buffer to place the result into
 * @size: The size of the buffer, including the trailing null space
 * @fmt: The format string to use
 * @args: Arguments for the format string
 *
 * The return value is the number of characters which have been written into
 * the @buf not including the trailing '\0'. If @size is <= 0 the function
 * returns 0.
 *
 * Call this function if you are already dealing with a va_list.
 * You probably want scnprintf instead.
 */
int vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
{
	int i;

	i=vsnprintf(buf,size,fmt,args);
	return (i >= size) ? (size - 1) : i;
}

/**
 * snprintf - Format a string and place it in a buffer
 * @buf: The buffer to place the result into
 * @size: The size of the buffer, including the trailing null space
 * @fmt: The format string to use
 * @...: Arguments for the format string
 *
 * The return value is the number of characters which would be
 * generated for the given input, excluding the trailing null,
 * as per ISO C99.  If the return is greater than or equal to
 * @size, the resulting string is truncated.
 */

static void early_printk(const char* str) {
  sys_write(2, str, strlen(str));
}

int snprintf(char * buf, size_t size, const char *fmt, ...)
{
	va_list args;
	int i;

	va_start(args, fmt);
	i=vsnprintf(buf,size,fmt,args);
	va_end(args);
	return i;
}

/**
 * scnprintf - Format a string and place it in a buffer
 * @buf: The buffer to place the result into
 * @size: The size of the buffer, including the trailing null space
 * @fmt: The format string to use
 * @...: Arguments for the format string
 *
 * The return value is the number of characters written into @buf not including
 * the trailing '\0'. If @size is <= 0 the function returns 0. If the return is
 * greater than or equal to @size, the resulting string is truncated.
 */

int scnprintf(char * buf, size_t size, const char *fmt, ...)
{
	va_list args;
	int i;

	va_start(args, fmt);
	i = vsnprintf(buf, size, fmt, args);
	va_end(args);
	return (i >= size) ? (size - 1) : i;
}

/**
 * vsscanf - Unformat a buffer into a list of arguments
 * @buf:	input buffer
 * @fmt:	format of buffer
 * @args:	arguments
 */
int vsscanf(const char * buf, const char * fmt, va_list args)
{
	const char *str = buf;
	char *next;
	char digit;
	int num = 0;
	int qualifier;
	int base;
	int field_width;
	int is_sign = 0;

	while(*fmt && *str) {
		/* skip any white space in format */
		/* white space in format matchs any amount of
		 * white space, including none, in the input.
		 */
		if (isspace(*fmt)) {
			while (isspace(*fmt))
				++fmt;
			while (isspace(*str))
				++str;
		}

		/* anything that is not a conversion must match exactly */
		if (*fmt != '%' && *fmt) {
			if (*fmt++ != *str++)
				break;
			continue;
		}

		if (!*fmt)
			break;
		++fmt;
		
		/* skip this conversion.
		 * advance both strings to next white space
		 */
		if (*fmt == '*') {
			while (!isspace(*fmt) && *fmt)
				fmt++;
			while (!isspace(*str) && *str)
				str++;
			continue;
		}

		/* get field width */
		field_width = -1;
		if (isdigit(*fmt))
			field_width = skip_atoi(&fmt);

		/* get conversion qualifier */
		qualifier = -1;
		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
		    *fmt == 'Z' || *fmt == 'z') {
			qualifier = *fmt++;
			if (unlikely(qualifier == *fmt)) {
				if (qualifier == 'h') {
					qualifier = 'H';
					fmt++;
				} else if (qualifier == 'l') {
					qualifier = 'L';
					fmt++;
				}
			}
		}
		base = 10;
		is_sign = 0;

		if (!*fmt || !*str)
			break;

		switch(*fmt++) {
		case 'c':
		{
			char *s = (char *) va_arg(args,char*);
			if (field_width == -1)
				field_width = 1;
			do {
				*s++ = *str++;
			} while (--field_width > 0 && *str);
			num++;
		}
		continue;
		case 's':
		{
			char *s = (char *) va_arg(args, char *);
			if(field_width == -1)
				field_width = limits<int>::max;
			/* first, skip leading white space in buffer */
			while (isspace(*str))
				str++;

			/* now copy until next white space */
			while (*str && !isspace(*str) && field_width--) {
				*s++ = *str++;
			}
			*s = '\0';
			num++;
		}
		continue;
		case 'n':
			/* return number of characters read so far */
		{
			int *i = (int *)va_arg(args,int*);
			*i = str - buf;
		}
		continue;
		case 'o':
			base = 8;
			break;
		case 'x':
		case 'X':
			base = 16;
			break;
		case 'i':
                        base = 0;
		case 'd':
			is_sign = 1;
		case 'u':
			break;
		case '%':
			/* looking for '%' in str */
			if (*str++ != '%') 
				return num;
			continue;
		default:
			/* invalid format; stop here */
			return num;
		}

		/* have some sort of integer conversion.
		 * first, skip white space in buffer.
		 */
		while (isspace(*str))
			str++;

		digit = *str;
		if (is_sign && digit == '-')
			digit = *(str + 1);

		if (!digit
                    || (base == 16 && !isxdigit(digit))
                    || (base == 10 && !isdigit(digit))
                    || (base == 8 && (!isdigit(digit) || digit > '7'))
                    || (base == 0 && !isdigit(digit)))
				break;

		switch(qualifier) {
		case 'H':	/* that's 'hh' in format */
			if (is_sign) {
				signed char *s = (signed char *) va_arg(args,signed char *);
				*s = (signed char) strtol(str,&next,base);
			} else {
				unsigned char *s = (unsigned char *) va_arg(args, unsigned char *);
				*s = (unsigned char) strtoul(str, &next, base);
			}
			break;
		case 'h':
			if (is_sign) {
				short *s = (short *) va_arg(args,short *);
				*s = (short) strtol(str,&next,base);
			} else {
				unsigned short *s = (unsigned short *) va_arg(args, unsigned short *);
				*s = (unsigned short) strtoul(str, &next, base);
			}
			break;
		case 'l':
			if (is_sign) {
				long *l = (long *) va_arg(args,long *);
				*l = strtol(str,&next,base);
			} else {
				unsigned long *l = (unsigned long*) va_arg(args,unsigned long*);
				*l = strtoul(str,&next,base);
			}
			break;
		case 'L':
			if (is_sign) {
				long long *l = (long long*) va_arg(args,long long *);
				*l = strtoll(str,&next,base);
			} else {
				unsigned long long *l = (unsigned long long*) va_arg(args,unsigned long long*);
				*l = strtoull(str,&next,base);
			}
			break;
		case 'Z':
		case 'z':
		{
			size_t *s = (size_t*) va_arg(args,size_t*);
			*s = (size_t) strtoul(str,&next,base);
		}
		break;
		default:
			if (is_sign) {
				int *i = (int *) va_arg(args, int*);
				*i = (int) strtol(str,&next,base);
			} else {
				unsigned int *i = (unsigned int*) va_arg(args, unsigned int*);
				*i = (unsigned int) strtoul(str,&next,base);
			}
			break;
		}
		num++;

		if (!next)
			break;
		str = next;
	}
	return num;
}

/**
 * sscanf - Unformat a buffer into a list of arguments
 * @buf:	input buffer
 * @fmt:	formatting of buffer
 * @...:	resulting arguments
 */
int sscanf(const char * buf, const char * fmt, ...)
{
	va_list args;
	int i;

	va_start(args,fmt);
	i = vsscanf(buf,fmt,args);
	va_end(args);
	return i;
}

char* strdup(const char *s) {
  if (!s) return null;
  int n = strlen(s) + 1;
  char* p = (char*)malloc(n);
  memcpy(p, s, n);
  return p;
}

char* strndup(const char *s, size_t n) {
  if (!s) return null;
  n = min(strlen(s), n) + 1;
  char* p = (char*)malloc(n);
  memcpy(p, s, n);
  p[n-1] = 0;
  return p;
}

extern ostream logfile;

// We now use the abort() macro identical to assert(false):
extern "C" void abort() {
  cerr << "Aborted by caller ", getcaller(), endl, flush;
  cout.flush();
  cerr.flush();
  logfile.flush();
  if (logfile) logfile.close();
  asm("ud2a" : : "a" (getcaller()));
  for (;;) { asm("nop"); }
}

#ifdef __USE_EXTERN_INLINES
extern "C" double __strtod_internal(const char* __nptr, char **__endptr, int group) {
  for (;;) { asm("nop"); } // FP not supported
  return 0;
}
#else
extern "C" double strtod(const char* s, char **endp) {
  for (;;) { asm("nop"); } // FP not supported
  return 0;
}

extern "C" double atof(const char* s) {
  for (;;) { asm("nop"); } // FP not supported
  return 0;
}
#endif

char* base_environ[] = {null};

char** environ = null;

char* getenv(const char* name) {
  int namelen = strlen(name);

  for (int i = 0; (environ[i] != null); i++) {
    if ((strncmp(environ[i], name, namelen) == 0) && (environ[i][namelen] == '=')) {
      return environ[i] + namelen + 1;
    }
  }
  return null;
}

//
// From http://ecos.sourceware.org/ml/ecos-discuss/2005-02/msg00056.html
//
// Versions of gcc/g++ after 3.0 (approx.), when configured for Linux
// native development (specifically, --with-__cxa_enable), have
// additional dependencies related to the destructors for static
// objects. When compiling C++ code with static objects the compiler
// inserts a call to __cxa_atexit() with __dso_handle as one of the
// arguments. __cxa_atexit() would normally be provided by glibc, and
// __dso_handle is part of crtstuff.c. Synthetic target applications
// are linked rather differently, so either a differently-configured
// compiler is needed or dummy versions of these symbols should be
// provided. If these symbols are not actually used then providing
// them is still harmless, linker garbage collection will remove them.
//

extern "C" void __cxa_atexit(void (*arg1)(void*), void* arg2, void* arg3) { }
void* __dso_handle = (void*)&__dso_handle;

// gcc 4.x generates these for static constructors:
extern "C" int __cxa_guard_acquire() { return 0; }
extern "C" int __cxa_guard_release() { return 0; }

extern "C" int atexit(void (*function)(void)) { return 0; }

typedef void (*ctor_func_ptr) (void);

extern ctor_func_ptr ctor_list[];
extern ctor_func_ptr ctor_list_end[];

//
// See http://gcc.gnu.org/onlinedocs/gccint/Initialization.html
//
void call_global_constuctors() {

  int ctor_count = &ctor_list_end[0] - &ctor_list[0];

  foreach (i, ctor_count) {
    ctor_list[i]();
  }
}