#ifndef _ASM_X86_SYSTEM_H_
#define _ASM_X86_SYSTEM_H_

#include <asm/asm.h>

#include <linux/kernel.h>

#ifdef CONFIG_X86_32
# include "system_32.h"
#else
# include "system_64.h"
#endif

#ifdef __KERNEL__
#define _set_base(addr, base) do { unsigned long __pr; \
__asm__ __volatile__ ("movw %%dx,%1\n\t" \
	"rorl $16,%%edx\n\t" \
	"movb %%dl,%2\n\t" \
	"movb %%dh,%3" \
	:"=&d" (__pr) \
	:"m" (*((addr)+2)), \
	 "m" (*((addr)+4)), \
	 "m" (*((addr)+7)), \
	 "0" (base) \
	); } while (0)

#define _set_limit(addr, limit) do { unsigned long __lr; \
__asm__ __volatile__ ("movw %%dx,%1\n\t" \
	"rorl $16,%%edx\n\t" \
	"movb %2,%%dh\n\t" \
	"andb $0xf0,%%dh\n\t" \
	"orb %%dh,%%dl\n\t" \
	"movb %%dl,%2" \
	:"=&d" (__lr) \
	:"m" (*(addr)), \
	 "m" (*((addr)+6)), \
	 "0" (limit) \
	); } while (0)

#define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base))
#define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1))

extern void load_gs_index(unsigned);

/*
 * Load a segment. Fall back on loading the zero
 * segment if something goes wrong..
 */
#define loadsegment(seg, value)			\
	asm volatile("\n"			\
		"1:\t"				\
		"movl %k0,%%" #seg "\n"		\
		"2:\n"				\
		".section .fixup,\"ax\"\n"	\
		"3:\t"				\
		"movl %k1, %%" #seg "\n\t"	\
		"jmp 2b\n"			\
		".previous\n"			\
		".section __ex_table,\"a\"\n\t"	\
		_ASM_ALIGN "\n\t"		\
		_ASM_PTR " 1b,3b\n"		\
		".previous"			\
		: :"r" (value), "r" (0))


/*
 * Save a segment register away
 */
#define savesegment(seg, value) \
	asm volatile("mov %%" #seg ",%0":"=rm" (value))

static inline unsigned long get_limit(unsigned long segment)
{
	unsigned long __limit;
	__asm__("lsll %1,%0"
		:"=r" (__limit):"r" (segment));
	return __limit+1;
}

static inline void native_clts(void)
{
	asm volatile ("clts");
}

/*
 * Volatile isn't enough to prevent the compiler from reordering the
 * read/write functions for the control registers and messing everything up.
 * A memory clobber would solve the problem, but would prevent reordering of
 * all loads stores around it, which can hurt performance. Solution is to
 * use a variable and mimic reads and writes to it to enforce serialization
 */
static unsigned long __force_order;

static inline unsigned long native_read_cr0(void)
{
	unsigned long val;
	asm volatile("mov %%cr0,%0\n\t" :"=r" (val), "=m" (__force_order));
	return val;
}

static inline void native_write_cr0(unsigned long val)
{
	asm volatile("mov %0,%%cr0": :"r" (val), "m" (__force_order));
}

static inline unsigned long native_read_cr2(void)
{
	unsigned long val;
	asm volatile("mov %%cr2,%0\n\t" :"=r" (val), "=m" (__force_order));
	return val;
}

static inline void native_write_cr2(unsigned long val)
{
	asm volatile("mov %0,%%cr2": :"r" (val), "m" (__force_order));
}

static inline unsigned long native_read_cr3(void)
{
	unsigned long val;
	asm volatile("mov %%cr3,%0\n\t" :"=r" (val), "=m" (__force_order));
	return val;
}

static inline void native_write_cr3(unsigned long val)
{
	asm volatile("mov %0,%%cr3": :"r" (val), "m" (__force_order));
}

static inline unsigned long native_read_cr4(void)
{
	unsigned long val;
	asm volatile("mov %%cr4,%0\n\t" :"=r" (val), "=m" (__force_order));
	return val;
}

static inline unsigned long native_read_cr4_safe(void)
{
	unsigned long val;
	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
	 * exists, so it will never fail. */
#ifdef CONFIG_X86_32
	asm volatile("1: mov %%cr4, %0		\n"
		"2:				\n"
		".section __ex_table,\"a\"	\n"
		".long 1b,2b			\n"
		".previous			\n"
		: "=r" (val), "=m" (__force_order) : "0" (0));
#else
	val = native_read_cr4();
#endif
	return val;
}

static inline void native_write_cr4(unsigned long val)
{
	asm volatile("mov %0,%%cr4": :"r" (val), "m" (__force_order));
}

static inline void native_wbinvd(void)
{
	asm volatile("wbinvd": : :"memory");
}
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define read_cr0()	(native_read_cr0())
#define write_cr0(x)	(native_write_cr0(x))
#define read_cr2()	(native_read_cr2())
#define write_cr2(x)	(native_write_cr2(x))
#define read_cr3()	(native_read_cr3())
#define write_cr3(x)	(native_write_cr3(x))
#define read_cr4()	(native_read_cr4())
#define read_cr4_safe()	(native_read_cr4_safe())
#define write_cr4(x)	(native_write_cr4(x))
#define wbinvd()	(native_wbinvd())

/* Clear the 'TS' bit */
#define clts()		(native_clts())

#endif/* CONFIG_PARAVIRT */

#define stts() write_cr0(8 | read_cr0())

#endif /* __KERNEL__ */

static inline void clflush(void *__p)
{
	asm volatile("clflush %0" : "+m" (*(char __force *)__p));
}

#define nop() __asm__ __volatile__ ("nop")

void disable_hlt(void);
void enable_hlt(void);

extern int es7000_plat;
void cpu_idle_wait(void);

extern unsigned long arch_align_stack(unsigned long sp);
extern void free_init_pages(char *what, unsigned long begin, unsigned long end);

void default_idle(void);

/*
 * Force strict CPU ordering.
 * And yes, this is required on UP too when we're talking
 * to devices.
 */
#ifdef CONFIG_X86_32
/*
 * For now, "wmb()" doesn't actually do anything, as all
 * Intel CPU's follow what Intel calls a *Processor Order*,
 * in which all writes are seen in the program order even
 * outside the CPU.
 *
 * I expect future Intel CPU's to have a weaker ordering,
 * but I'd also expect them to finally get their act together
 * and add some real memory barriers if so.
 *
 * Some non intel clones support out of order store. wmb() ceases to be a
 * nop for these.
 */
#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
#else
#define mb() 	asm volatile("mfence":::"memory")
#define rmb()	asm volatile("lfence":::"memory")
#define wmb()	asm volatile("sfence" ::: "memory")
#endif

/**
 * read_barrier_depends - Flush all pending reads that subsequents reads
 * depend on.
 *
 * No data-dependent reads from memory-like regions are ever reordered
 * over this barrier.  All reads preceding this primitive are guaranteed
 * to access memory (but not necessarily other CPUs' caches) before any
 * reads following this primitive that depend on the data return by
 * any of the preceding reads.  This primitive is much lighter weight than
 * rmb() on most CPUs, and is never heavier weight than is
 * rmb().
 *
 * These ordering constraints are respected by both the local CPU
 * and the compiler.
 *
 * Ordering is not guaranteed by anything other than these primitives,
 * not even by data dependencies.  See the documentation for
 * memory_barrier() for examples and URLs to more information.
 *
 * For example, the following code would force ordering (the initial
 * value of "a" is zero, "b" is one, and "p" is "&a"):
 *
 * <programlisting>
 *	CPU 0				CPU 1
 *
 *	b = 2;
 *	memory_barrier();
 *	p = &b;				q = p;
 *					read_barrier_depends();
 *					d = *q;
 * </programlisting>
 *
 * because the read of "*q" depends on the read of "p" and these
 * two reads are separated by a read_barrier_depends().  However,
 * the following code, with the same initial values for "a" and "b":
 *
 * <programlisting>
 *	CPU 0				CPU 1
 *
 *	a = 2;
 *	memory_barrier();
 *	b = 3;				y = b;
 *					read_barrier_depends();
 *					x = a;
 * </programlisting>
 *
 * does not enforce ordering, since there is no data dependency between
 * the read of "a" and the read of "b".  Therefore, on some CPUs, such
 * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
 * in cases like this where there are no data dependencies.
 **/

#define read_barrier_depends()	do { } while (0)

#ifdef CONFIG_SMP
#define smp_mb()	mb()
#ifdef CONFIG_X86_PPRO_FENCE
# define smp_rmb()	rmb()
#else
# define smp_rmb()	barrier()
#endif
#ifdef CONFIG_X86_OOSTORE
# define smp_wmb() 	wmb()
#else
# define smp_wmb()	barrier()
#endif
#define smp_read_barrier_depends()	read_barrier_depends()
#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
#else
#define smp_mb()	barrier()
#define smp_rmb()	barrier()
#define smp_wmb()	barrier()
#define smp_read_barrier_depends()	do { } while (0)
#define set_mb(var, value) do { var = value; barrier(); } while (0)
#endif


#endif