#ifndef _ASM_IO_H
#define _ASM_IO_H

/*
 * This file contains the definitions for the x86 IO instructions
 * inb/inw/inl/outb/outw/outl and the "string versions" of the same
 * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
 * versions of the single-IO instructions (inb_p/inw_p/..).
 *
 * This file is not meant to be obfuscating: it's just complicated
 * to (a) handle it all in a way that makes gcc able to optimize it
 * as well as possible and (b) trying to avoid writing the same thing
 * over and over again with slight variations and possibly making a
 * mistake somewhere.
 */

/*
 * Thanks to James van Artsdalen for a better timing-fix than
 * the two short jumps: using outb's to a nonexistent port seems
 * to guarantee better timings even on fast machines.
 *
 * On the other hand, I'd like to be sure of a non-existent port:
 * I feel a bit unsafe about using 0x80 (should be safe, though)
 *
 *		Linus
 */

 /*
  *  Bit simplified and optimized by Jan Hubicka
  */

#ifdef SLOW_IO_BY_JUMPING
#define __SLOW_DOWN_IO "\njmp 1f\n1:\tjmp 1f\n1:"
#else
#define __SLOW_DOWN_IO "\noutb %%al,$0x80"
#endif

#ifdef REALLY_SLOW_IO
#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO __SLOW_DOWN_IO
#else
#define __FULL_SLOW_DOWN_IO __SLOW_DOWN_IO
#endif

/*
 * Talk about misusing macros..
 */
#define __OUT1(s,x) \
extern inline void out##s(unsigned x value, unsigned short port) {

#define __OUT2(s,s1,s2) \
__asm__ __volatile__ ("out" #s " %" s1 "0,%" s2 "1"

#define __OUT(s,s1,x) \
__OUT1(s,x) __OUT2(s,s1,"w") : : "a" (value), "Nd" (port)); } \
__OUT1(s##_p,x) __OUT2(s,s1,"w") __FULL_SLOW_DOWN_IO : : "a" (value), "Nd" (port));} \

#define __IN1(s) \
extern inline RETURN_TYPE in##s(unsigned short port) { RETURN_TYPE _v;

#define __IN2(s,s1,s2) \
__asm__ __volatile__ ("in" #s " %" s2 "1,%" s1 "0"

#define __IN(s,s1,i...) \
__IN1(s) __IN2(s,s1,"w") : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \
__IN1(s##_p) __IN2(s,s1,"w") __FULL_SLOW_DOWN_IO : "=a" (_v) : "Nd" (port) ,##i ); return _v; } \

#define __INS(s) \
extern inline void ins##s(unsigned short port, void * addr, unsigned long count) \
{ __asm__ __volatile__ ("cld ; rep ; ins" #s \
: "=D" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }

#define __OUTS(s) \
extern inline void outs##s(unsigned short port, const void * addr, unsigned long count) \
{ __asm__ __volatile__ ("cld ; rep ; outs" #s \
: "=S" (addr), "=c" (count) : "d" (port),"0" (addr),"1" (count)); }

#define RETURN_TYPE unsigned char
__IN(b,"")
#undef RETURN_TYPE
#define RETURN_TYPE unsigned short
__IN(w,"")
#undef RETURN_TYPE
#define RETURN_TYPE unsigned int
__IN(l,"")
#undef RETURN_TYPE

__OUT(b,"b",char)
__OUT(w,"w",short)
__OUT(l,,int)

__INS(b)
__INS(w)
__INS(l)

__OUTS(b)
__OUTS(w)
__OUTS(l)

#ifdef __KERNEL__

#include <linux/vmalloc.h>
#include <asm/page.h>

#define __io_virt(x)		((void *)(PAGE_OFFSET | (unsigned long)(x)))
#define __io_phys(x)		((unsigned long)(x) & ~PAGE_OFFSET)
/*
 * Change virtual addresses to physical addresses and vv.
 * These are pretty trivial
 */
extern inline unsigned long virt_to_phys(volatile void * address)
{
	return __io_phys(address);
}

extern inline void * phys_to_virt(unsigned long address)
{
	return __io_virt(address);
}

extern void * __ioremap(unsigned long offset, unsigned long size, unsigned long flags);

extern inline void * ioremap (unsigned long offset, unsigned long size)
{
	return __ioremap(offset, size, 0);
}

/*
 * This one maps high address device memory and turns off caching for that area.
 * it's useful if some control registers are in such an area and write combining
 * or read caching is not desirable:
 */
extern inline void * ioremap_nocache (unsigned long offset, unsigned long size)
{
        return __ioremap(offset, size, _PAGE_PCD);
}

extern void iounmap(void *addr);

/*
 * IO bus memory addresses are also 1:1 with the physical address
 */
#define virt_to_bus virt_to_phys
#define bus_to_virt phys_to_virt

/*
 * readX/writeX() are used to access memory mapped devices. On some
 * architectures the memory mapped IO stuff needs to be accessed
 * differently. On the x86 architecture, we just read/write the
 * memory location directly.
 */

#define readb(addr) (*(volatile unsigned char *) __io_virt(addr))
#define readw(addr) (*(volatile unsigned short *) __io_virt(addr))
#define readl(addr) (*(volatile unsigned int *) __io_virt(addr))

#define writeb(b,addr) (*(volatile unsigned char *) __io_virt(addr) = (b))
#define writew(b,addr) (*(volatile unsigned short *) __io_virt(addr) = (b))
#define writel(b,addr) (*(volatile unsigned int *) __io_virt(addr) = (b))

#define memset_io(a,b,c)	memset(__io_virt(a),(b),(c))
#define memcpy_fromio(a,b,c)	memcpy((a),__io_virt(b),(c))
#define memcpy_toio(a,b,c)	memcpy(__io_virt(a),(b),(c))

/*
 * Again, i386 does not require mem IO specific function.
 */

#define eth_io_copy_and_sum(a,b,c,d)	eth_copy_and_sum((a),__io_virt(b),(c),(d))

static inline int check_signature(unsigned long io_addr,
	const unsigned char *signature, int length)
{
	int retval = 0;
	do {
		if (readb(io_addr) != *signature)
			goto out;
		io_addr++;
		signature++;
		length--;
	} while (length);
	retval = 1;
out:
	return retval;
}

/* Nothing to do */

#define dma_cache_inv(_start,_size)		do { } while (0)
#define dma_cache_wback(_start,_size)		do { } while (0)
#define dma_cache_wback_inv(_start,_size)	do { } while (0)

#endif /* __KERNEL__ */

#endif