#ifndef __ASM_SPINLOCK_H
#define __ASM_SPINLOCK_H

#if __LINUX_ARM_ARCH__ < 6
#error SMP not supported on pre-ARMv6 CPUs
#endif

/*--------------------------------------------------------------------------------*\
\*--------------------------------------------------------------------------------*/
#if defined(CONFIG_ENABLE_SPINLOCK_PROFILING_HOOKS)
extern int avm_simple_profiling_is_enabled_func(void);
extern unsigned int avm_get_cycles_func(void);

#define avm_simple_profiling_spin_lock(lock) ({ \
    if(avm_simple_profiling_is_enabled_func()) { \
        unsigned int avm_simple_profiling_spinlock_endtime = avm_get_cycles_func(); \
        __avm_simple_profiling_spinlock(_RET_IP_, (unsigned int)lock, avm_simple_profiling_spinlock_endtime - avm_simple_profiling_spinlock_starttime, 0); \
    } \
})

#define avm_simple_profiling_spin_trylock(lock, success) ({ \
    if(avm_simple_profiling_is_enabled_func()) { \
        __avm_simple_profiling_spinlock(_RET_IP_, (unsigned int)lock, 0, success ? 1 : 2); \
    } \
})

#define avm_simple_profiling_spin_unlock(lock) ({ \
    if(avm_simple_profiling_is_enabled_func()) { \
        __avm_simple_profiling_spinlock(_RET_IP_, (unsigned int)lock, 0, 3); \
    } \
})

#define avm_simple_profiling_spin_gettime() unsigned int avm_simple_profiling_spinlock_starttime = avm_get_cycles_func()

extern void __avm_simple_profiling_spinlock(unsigned int addr, unsigned int lock, unsigned int time, unsigned int id);

#else
static inline void avm_simple_profiling_spin_lock(void *lock __attribute__ ((unused))) { };
static inline void avm_simple_profiling_spin_trylock(void *lock __attribute__ ((unused)), unsigned int success __attribute__ ((unused))) { };
static inline void avm_simple_profiling_spin_unlock(void *lock __attribute__ ((unused))) { };
static inline unsigned int avm_simple_profiling_spin_gettime(void) { return 0; }
#endif
#include <linux/prefetch.h>

/*
 * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
 * extensions, so when running on UP, we have to patch these instructions away.
 */
#ifdef CONFIG_THUMB2_KERNEL
/*
 * For Thumb-2, special care is needed to ensure that the conditional WFE
 * instruction really does assemble to exactly 4 bytes (as required by
 * the SMP_ON_UP fixup code).   By itself "wfene" might cause the
 * assembler to insert a extra (16-bit) IT instruction, depending on the
 * presence or absence of neighbouring conditional instructions.
 *
 * To avoid this unpredictableness, an approprite IT is inserted explicitly:
 * the assembler won't change IT instructions which are explicitly present
 * in the input.
 */
#define WFE(cond)	__ALT_SMP_ASM(		\
	"it " cond "\n\t"			\
	"wfe" cond ".n",			\
						\
	"nop.w"					\
)
#else
#define WFE(cond)	__ALT_SMP_ASM("wfe" cond, "nop")
#endif

#define SEV		__ALT_SMP_ASM(WASM(sev), WASM(nop))

static inline void dsb_sev(void)
{

	dsb(ishst);
	__asm__(SEV);
}

/*
 * ARMv6 ticket-based spin-locking.
 *
 * A memory barrier is required after we get a lock, and before we
 * release it, because V6 CPUs are assumed to have weakly ordered
 * memory.
 */

#define arch_spin_unlock_wait(lock) \
	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)

#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)

static inline void arch_spin_lock(arch_spinlock_t *lock)
{
	unsigned long tmp;
	u32 newval;
	arch_spinlock_t lockval;

    avm_simple_profiling_spin_gettime();
	prefetchw(&lock->slock);
	__asm__ __volatile__(
"1:	ldrex	%0, [%3]\n"
"	add	%1, %0, %4\n"
"	strex	%2, %1, [%3]\n"
"	teq	%2, #0\n"
"	bne	1b"
	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp)
	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
	: "cc");

	while (lockval.tickets.next != lockval.tickets.owner) {
		wfe();
		lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner);
	}

	smp_mb();
	avm_simple_profiling_spin_lock(lock);
}

static inline int arch_spin_trylock(arch_spinlock_t *lock)
{
	unsigned long contended, res;
	u32 slock;

	prefetchw(&lock->slock);
	do {
		__asm__ __volatile__(
		"	ldrex	%0, [%3]\n"
		"	mov	%2, #0\n"
		"	subs	%1, %0, %0, ror #16\n"
		"	addeq	%0, %0, %4\n"
		"	strexeq	%2, %0, [%3]"
		: "=&r" (slock), "=&r" (contended), "=&r" (res)
		: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
		: "cc");
	} while (res);
	avm_simple_profiling_spin_trylock(lock, contended);
	if (!contended) {
		smp_mb();
		return 1;
	} else {
		return 0;
	}
}

static inline void arch_spin_unlock(arch_spinlock_t *lock)
{
	smp_mb();
    
    avm_simple_profiling_spin_unlock(lock);
	lock->tickets.owner++;
	dsb_sev();
}

static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
	return lock.tickets.owner == lock.tickets.next;
}

static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
	return !arch_spin_value_unlocked(READ_ONCE(*lock));
}

static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
	struct __raw_tickets tickets = READ_ONCE(lock->tickets);
	return (tickets.next - tickets.owner) > 1;
}
#define arch_spin_is_contended	arch_spin_is_contended

/*
 * RWLOCKS
 *
 *
 * Write locks are easy - we just set bit 31.  When unlocking, we can
 * just write zero since the lock is exclusively held.
 */

static inline void arch_write_lock(arch_rwlock_t *rw)
{
	unsigned long tmp;

	prefetchw(&rw->lock);
	__asm__ __volatile__(
"1:	ldrex	%0, [%1]\n"
"	teq	%0, #0\n"
	WFE("ne")
"	strexeq	%0, %2, [%1]\n"
"	teq	%0, #0\n"
"	bne	1b"
	: "=&r" (tmp)
	: "r" (&rw->lock), "r" (0x80000000)
	: "cc");

	smp_mb();
}

static inline int arch_write_trylock(arch_rwlock_t *rw)
{
	unsigned long contended, res;

	prefetchw(&rw->lock);
	do {
		__asm__ __volatile__(
		"	ldrex	%0, [%2]\n"
		"	mov	%1, #0\n"
		"	teq	%0, #0\n"
		"	strexeq	%1, %3, [%2]"
		: "=&r" (contended), "=&r" (res)
		: "r" (&rw->lock), "r" (0x80000000)
		: "cc");
	} while (res);

	if (!contended) {
		smp_mb();
		return 1;
	} else {
		return 0;
	}
}

static inline void arch_write_unlock(arch_rwlock_t *rw)
{
	smp_mb();

	__asm__ __volatile__(
	"str	%1, [%0]\n"
	:
	: "r" (&rw->lock), "r" (0)
	: "cc");

	dsb_sev();
}

/* write_can_lock - would write_trylock() succeed? */
#define arch_write_can_lock(x)		(ACCESS_ONCE((x)->lock) == 0)

/*
 * Read locks are a bit more hairy:
 *  - Exclusively load the lock value.
 *  - Increment it.
 *  - Store new lock value if positive, and we still own this location.
 *    If the value is negative, we've already failed.
 *  - If we failed to store the value, we want a negative result.
 *  - If we failed, try again.
 * Unlocking is similarly hairy.  We may have multiple read locks
 * currently active.  However, we know we won't have any write
 * locks.
 */
static inline void arch_read_lock(arch_rwlock_t *rw)
{
	unsigned long tmp, tmp2;

	prefetchw(&rw->lock);
	__asm__ __volatile__(
"1:	ldrex	%0, [%2]\n"
"	adds	%0, %0, #1\n"
"	strexpl	%1, %0, [%2]\n"
	WFE("mi")
"	rsbpls	%0, %1, #0\n"
"	bmi	1b"
	: "=&r" (tmp), "=&r" (tmp2)
	: "r" (&rw->lock)
	: "cc");

	smp_mb();
}

static inline void arch_read_unlock(arch_rwlock_t *rw)
{
	unsigned long tmp, tmp2;

	smp_mb();

	prefetchw(&rw->lock);
	__asm__ __volatile__(
"1:	ldrex	%0, [%2]\n"
"	sub	%0, %0, #1\n"
"	strex	%1, %0, [%2]\n"
"	teq	%1, #0\n"
"	bne	1b"
	: "=&r" (tmp), "=&r" (tmp2)
	: "r" (&rw->lock)
	: "cc");

	if (tmp == 0)
		dsb_sev();
}

static inline int arch_read_trylock(arch_rwlock_t *rw)
{
	unsigned long contended, res;

	prefetchw(&rw->lock);
	do {
		__asm__ __volatile__(
		"	ldrex	%0, [%2]\n"
		"	mov	%1, #0\n"
		"	adds	%0, %0, #1\n"
		"	strexpl	%1, %0, [%2]"
		: "=&r" (contended), "=&r" (res)
		: "r" (&rw->lock)
		: "cc");
	} while (res);

	/* If the lock is negative, then it is already held for write. */
	if (contended < 0x80000000) {
		smp_mb();
		return 1;
	} else {
		return 0;
	}
}

/* read_can_lock - would read_trylock() succeed? */
#define arch_read_can_lock(x)		(ACCESS_ONCE((x)->lock) < 0x80000000)

#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)

#define arch_spin_relax(lock)	cpu_relax()
#define arch_read_relax(lock)	cpu_relax()
#define arch_write_relax(lock)	cpu_relax()

#endif /* __ASM_SPINLOCK_H */