#ifndef __ASM_ARM_SYSTEM_H
#define __ASM_ARM_SYSTEM_H

#ifdef __KERNEL__

#include <asm/memory.h>

#define CPU_ARCH_UNKNOWN	0
#define CPU_ARCH_ARMv3		1
#define CPU_ARCH_ARMv4		2
#define CPU_ARCH_ARMv4T		3
#define CPU_ARCH_ARMv5		4
#define CPU_ARCH_ARMv5T		5
#define CPU_ARCH_ARMv5TE	6
#define CPU_ARCH_ARMv5TEJ	7
#define CPU_ARCH_ARMv6		8
#define CPU_ARCH_ARMv7		9

/*
 * CR1 bits (CP#15 CR1)
 */
#define CR_M	(1 << 0)	/* MMU enable				*/
#define CR_A	(1 << 1)	/* Alignment abort enable		*/
#define CR_C	(1 << 2)	/* Dcache enable			*/
#define CR_W	(1 << 3)	/* Write buffer enable			*/
#define CR_P	(1 << 4)	/* 32-bit exception handler		*/
#define CR_D	(1 << 5)	/* 32-bit data address range		*/
#define CR_L	(1 << 6)	/* Implementation defined		*/
#define CR_B	(1 << 7)	/* Big endian				*/
#define CR_S	(1 << 8)	/* System MMU protection		*/
#define CR_R	(1 << 9)	/* ROM MMU protection			*/
#define CR_F	(1 << 10)	/* Implementation defined		*/
#define CR_Z	(1 << 11)	/* Implementation defined		*/
#define CR_I	(1 << 12)	/* Icache enable			*/
#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
#define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
#define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
#define CR_DT	(1 << 16)
#define CR_IT	(1 << 18)
#define CR_ST	(1 << 19)
#define CR_FI	(1 << 21)	/* Fast interrupt (lower latency mode)	*/
#define CR_U	(1 << 22)	/* Unaligned access operation		*/
#define CR_XP	(1 << 23)	/* Extended page tables			*/
#define CR_VE	(1 << 24)	/* Vectored interrupts			*/

#define CPUID_ID	0
#define CPUID_CACHETYPE	1
#define CPUID_TCM	2
#define CPUID_TLBTYPE	3

#ifdef CONFIG_CPU_CP15
#define read_cpuid(reg)							\
	({								\
		unsigned int __val;					\
		asm("mrc	p15, 0, %0, c0, c0, " __stringify(reg)	\
		    : "=r" (__val)					\
		    :							\
		    : "cc");						\
		__val;							\
	})
#else
#define read_cpuid(reg) (processor_id)
#endif

/*
 * This is used to ensure the compiler did actually allocate the register we
 * asked it for some inline assembly sequences.  Apparently we can't trust
 * the compiler from one version to another so a bit of paranoia won't hurt.
 * This string is meant to be concatenated with the inline asm string and
 * will cause compilation to stop on mismatch.
 * (for details, see gcc PR 15089)
 */
#define __asmeq(x, y)  ".ifnc " x "," y " ; .err ; .endif\n\t"

#ifndef __ASSEMBLY__

#include <linux/linkage.h>
#include <linux/irqflags.h>

#define __exception	__attribute__((section(".exception.text")))

struct thread_info;
struct task_struct;

/* information about the system we're running on */
extern unsigned int system_rev;
extern unsigned int system_serial_low;
extern unsigned int system_serial_high;
extern unsigned int mem_fclk_21285;

struct pt_regs;

void die(const char *msg, struct pt_regs *regs, int err)
		__attribute__((noreturn));

struct siginfo;
void notify_die(const char *str, struct pt_regs *regs, struct siginfo *info,
		unsigned long err, unsigned long trap);

void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
				       struct pt_regs *),
		     int sig, const char *name);

#define xchg(ptr,x) \
	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))

#define tas(ptr) (xchg((ptr),1))

extern asmlinkage void __backtrace(void);
extern asmlinkage void c_backtrace(unsigned long fp, int pmode);

struct mm_struct;
extern void show_pte(struct mm_struct *mm, unsigned long addr);
extern void __show_regs(struct pt_regs *);

extern int cpu_architecture(void);
extern void cpu_init(void);

void arm_machine_restart(char mode);
extern void (*arm_pm_restart)(char str);

/*
 * Intel's XScale3 core supports some v6 features (supersections, L2)
 * but advertises itself as v5 as it does not support the v6 ISA.  For
 * this reason, we need a way to explicitly test for this type of CPU.
 */
#ifndef CONFIG_CPU_XSC3
#define cpu_is_xsc3()	0
#else
static inline int cpu_is_xsc3(void)
{
	extern unsigned int processor_id;

	if ((processor_id & 0xffffe000) == 0x69056000)
		return 1;

	return 0;
}
#endif

#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3)
#define	cpu_is_xscale()	0
#else
#define	cpu_is_xscale()	1
#endif

#define UDBG_UNDEFINED	(1 << 0)
#define UDBG_SYSCALL	(1 << 1)
#define UDBG_BADABORT	(1 << 2)
#define UDBG_SEGV	(1 << 3)
#define UDBG_BUS	(1 << 4)

extern unsigned int user_debug;

#if __LINUX_ARM_ARCH__ >= 4
#define vectors_high()	(cr_alignment & CR_V)
#else
#define vectors_high()	(0)
#endif

#if __LINUX_ARM_ARCH__ >= 7
#define isb() __asm__ __volatile__ ("isb" : : : "memory")
#define dsb() __asm__ __volatile__ ("dsb" : : : "memory")
#define dmb() __asm__ __volatile__ ("dmb" : : : "memory")
#elif defined(CONFIG_CPU_XSC3) || __LINUX_ARM_ARCH__ == 6
#define isb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c5, 4" \
				    : : "r" (0) : "memory")
#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
				    : : "r" (0) : "memory")
#define dmb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 5" \
				    : : "r" (0) : "memory")
#else
#define isb() __asm__ __volatile__ ("" : : : "memory")
#define dsb() __asm__ __volatile__ ("mcr p15, 0, %0, c7, c10, 4" \
				    : : "r" (0) : "memory")
#define dmb() __asm__ __volatile__ ("" : : : "memory")
#endif

#ifndef CONFIG_SMP
#define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
#define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
#define wmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
#define smp_mb()	barrier()
#define smp_rmb()	barrier()
#define smp_wmb()	barrier()
#else
#define mb()		dmb()
#define rmb()		dmb()
#define wmb()		dmb()
#define smp_mb()	dmb()
#define smp_rmb()	dmb()
#define smp_wmb()	dmb()
#endif
#define read_barrier_depends()		do { } while(0)
#define smp_read_barrier_depends()	do { } while(0)

#define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
#define nop() __asm__ __volatile__("mov\tr0,r0\t@ nop\n\t");

extern unsigned long cr_no_alignment;	/* defined in entry-armv.S */
extern unsigned long cr_alignment;	/* defined in entry-armv.S */

static inline unsigned int get_cr(void)
{
	unsigned int val;
	asm("mrc p15, 0, %0, c1, c0, 0	@ get CR" : "=r" (val) : : "cc");
	return val;
}

static inline void set_cr(unsigned int val)
{
	asm volatile("mcr p15, 0, %0, c1, c0, 0	@ set CR"
	  : : "r" (val) : "cc");
	isb();
}

#ifndef CONFIG_SMP
extern void adjust_cr(unsigned long mask, unsigned long set);
#endif

#define CPACC_FULL(n)		(3 << (n * 2))
#define CPACC_SVC(n)		(1 << (n * 2))
#define CPACC_DISABLE(n)	(0 << (n * 2))

static inline unsigned int get_copro_access(void)
{
	unsigned int val;
	asm("mrc p15, 0, %0, c1, c0, 2 @ get copro access"
	  : "=r" (val) : : "cc");
	return val;
}

static inline void set_copro_access(unsigned int val)
{
	asm volatile("mcr p15, 0, %0, c1, c0, 2 @ set copro access"
	  : : "r" (val) : "cc");
	isb();
}

/*
 * switch_mm() may do a full cache flush over the context switch,
 * so enable interrupts over the context switch to avoid high
 * latency.
 */
#define __ARCH_WANT_INTERRUPTS_ON_CTXSW

/*
 * switch_to(prev, next) should switch from task `prev' to `next'
 * `prev' will never be the same as `next'.  schedule() itself
 * contains the memory barrier to tell GCC not to cache `current'.
 */
extern struct task_struct *__switch_to(struct task_struct *, struct thread_info *, struct thread_info *);

#define switch_to(prev,next,last)					\
do {									\
	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
} while (0)

/*
 * On SMP systems, when the scheduler does migration-cost autodetection,
 * it needs a way to flush as much of the CPU's caches as possible.
 *
 * TODO: fill this in!
 */
static inline void sched_cacheflush(void)
{
}

#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
/*
 * On the StrongARM, "swp" is terminally broken since it bypasses the
 * cache totally.  This means that the cache becomes inconsistent, and,
 * since we use normal loads/stores as well, this is really bad.
 * Typically, this causes oopsen in filp_close, but could have other,
 * more disasterous effects.  There are two work-arounds:
 *  1. Disable interrupts and emulate the atomic swap
 *  2. Clean the cache, perform atomic swap, flush the cache
 *
 * We choose (1) since its the "easiest" to achieve here and is not
 * dependent on the processor type.
 *
 * NOTE that this solution won't work on an SMP system, so explcitly
 * forbid it here.
 */
#define swp_is_buggy
#endif

static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
{
	extern void __bad_xchg(volatile void *, int);
	unsigned long ret;
#ifdef swp_is_buggy
	unsigned long flags;
#endif
#if __LINUX_ARM_ARCH__ >= 6
	unsigned int tmp;
#endif

	switch (size) {
#if __LINUX_ARM_ARCH__ >= 6
	case 1:
		asm volatile("@	__xchg1\n"
		"1:	ldrexb	%0, [%3]\n"
		"	strexb	%1, %2, [%3]\n"
		"	teq	%1, #0\n"
		"	bne	1b"
			: "=&r" (ret), "=&r" (tmp)
			: "r" (x), "r" (ptr)
			: "memory", "cc");
		break;
	case 4:
		asm volatile("@	__xchg4\n"
		"1:	ldrex	%0, [%3]\n"
		"	strex	%1, %2, [%3]\n"
		"	teq	%1, #0\n"
		"	bne	1b"
			: "=&r" (ret), "=&r" (tmp)
			: "r" (x), "r" (ptr)
			: "memory", "cc");
		break;
#elif defined(swp_is_buggy)
#ifdef CONFIG_SMP
#error SMP is not supported on this platform
#endif
	case 1:
		raw_local_irq_save(flags);
		ret = *(volatile unsigned char *)ptr;
		*(volatile unsigned char *)ptr = x;
		raw_local_irq_restore(flags);
		break;

	case 4:
		raw_local_irq_save(flags);
		ret = *(volatile unsigned long *)ptr;
		*(volatile unsigned long *)ptr = x;
		raw_local_irq_restore(flags);
		break;
#else
	case 1:
		asm volatile("@	__xchg1\n"
		"	swpb	%0, %1, [%2]"
			: "=&r" (ret)
			: "r" (x), "r" (ptr)
			: "memory", "cc");
		break;
	case 4:
		asm volatile("@	__xchg4\n"
		"	swp	%0, %1, [%2]"
			: "=&r" (ret)
			: "r" (x), "r" (ptr)
			: "memory", "cc");
		break;
#endif
	default:
		__bad_xchg(ptr, size), ret = 0;
		break;
	}

	return ret;
}

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

#endif /* __ASSEMBLY__ */

#define arch_align_stack(x) (x)

#endif /* __KERNEL__ */

#endif