diff options
Diffstat (limited to 'arch/x86/include/asm/spinlock.h')
| -rw-r--r-- | arch/x86/include/asm/spinlock.h | 153 |
1 files changed, 50 insertions, 103 deletions
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 3089f70c0c52..972c260919a3 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -1,8 +1,7 @@ #ifndef _ASM_X86_SPINLOCK_H #define _ASM_X86_SPINLOCK_H -#include <asm/atomic.h> -#include <asm/rwlock.h> +#include <linux/atomic.h> #include <asm/page.h> #include <asm/processor.h> #include <linux/compiler.h> @@ -50,109 +49,49 @@ * issues and should be optimal for the uncontended case. Note the tail must be * in the high part, because a wide xadd increment of the low part would carry * up and contaminate the high part. - * - * With fewer than 2^8 possible CPUs, we can use x86's partial registers to - * save some instructions and make the code more elegant. There really isn't - * much between them in performance though, especially as locks are out of line. */ -#if (NR_CPUS < 256) -#define TICKET_SHIFT 8 - static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) { - short inc = 0x0100; - - asm volatile ( - LOCK_PREFIX "xaddw %w0, %1\n" - "1:\t" - "cmpb %h0, %b0\n\t" - "je 2f\n\t" - "rep ; nop\n\t" - "movb %1, %b0\n\t" - /* don't need lfence here, because loads are in-order */ - "jmp 1b\n" - "2:" - : "+Q" (inc), "+m" (lock->slock) - : - : "memory", "cc"); + register struct __raw_tickets inc = { .tail = 1 }; + + inc = xadd(&lock->tickets, inc); + + for (;;) { + if (inc.head == inc.tail) + break; + cpu_relax(); + inc.head = ACCESS_ONCE(lock->tickets.head); + } + barrier(); /* make sure nothing creeps before the lock is taken */ } static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) { - int tmp, new; - - asm volatile("movzwl %2, %0\n\t" - "cmpb %h0,%b0\n\t" - "leal 0x100(%" REG_PTR_MODE "0), %1\n\t" - "jne 1f\n\t" - LOCK_PREFIX "cmpxchgw %w1,%2\n\t" - "1:" - "sete %b1\n\t" - "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=&q" (new), "+m" (lock->slock) - : - : "memory", "cc"); + arch_spinlock_t old, new; + + old.tickets = ACCESS_ONCE(lock->tickets); + if (old.tickets.head != old.tickets.tail) + return 0; + + new.head_tail = old.head_tail + (1 << TICKET_SHIFT); - return tmp; + /* cmpxchg is a full barrier, so nothing can move before it */ + return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail; } +#if (NR_CPUS < 256) static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) { asm volatile(UNLOCK_LOCK_PREFIX "incb %0" - : "+m" (lock->slock) + : "+m" (lock->head_tail) : : "memory", "cc"); } #else -#define TICKET_SHIFT 16 - -static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) -{ - int inc = 0x00010000; - int tmp; - - asm volatile(LOCK_PREFIX "xaddl %0, %1\n" - "movzwl %w0, %2\n\t" - "shrl $16, %0\n\t" - "1:\t" - "cmpl %0, %2\n\t" - "je 2f\n\t" - "rep ; nop\n\t" - "movzwl %1, %2\n\t" - /* don't need lfence here, because loads are in-order */ - "jmp 1b\n" - "2:" - : "+r" (inc), "+m" (lock->slock), "=&r" (tmp) - : - : "memory", "cc"); -} - -static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) -{ - int tmp; - int new; - - asm volatile("movl %2,%0\n\t" - "movl %0,%1\n\t" - "roll $16, %0\n\t" - "cmpl %0,%1\n\t" - "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t" - "jne 1f\n\t" - LOCK_PREFIX "cmpxchgl %1,%2\n\t" - "1:" - "sete %b1\n\t" - "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=&q" (new), "+m" (lock->slock) - : - : "memory", "cc"); - - return tmp; -} - static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) { asm volatile(UNLOCK_LOCK_PREFIX "incw %0" - : "+m" (lock->slock) + : "+m" (lock->head_tail) : : "memory", "cc"); } @@ -160,16 +99,16 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) { - int tmp = ACCESS_ONCE(lock->slock); + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); - return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1)); + return !!(tmp.tail ^ tmp.head); } static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) { - int tmp = ACCESS_ONCE(lock->slock); + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); - return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1; + return ((tmp.tail - tmp.head) & TICKET_MASK) > 1; } #ifndef CONFIG_PARAVIRT_SPINLOCKS @@ -234,7 +173,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) */ static inline int arch_read_can_lock(arch_rwlock_t *lock) { - return (int)(lock)->lock > 0; + return lock->lock > 0; } /** @@ -243,12 +182,12 @@ static inline int arch_read_can_lock(arch_rwlock_t *lock) */ static inline int arch_write_can_lock(arch_rwlock_t *lock) { - return (lock)->lock == RW_LOCK_BIAS; + return lock->write == WRITE_LOCK_CMP; } static inline void arch_read_lock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t" + asm volatile(LOCK_PREFIX READ_LOCK_SIZE(dec) " (%0)\n\t" "jns 1f\n" "call __read_lock_failed\n\t" "1:\n" @@ -257,47 +196,55 @@ static inline void arch_read_lock(arch_rwlock_t *rw) static inline void arch_write_lock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX " subl %1,(%0)\n\t" + asm volatile(LOCK_PREFIX WRITE_LOCK_SUB(%1) "(%0)\n\t" "jz 1f\n" "call __write_lock_failed\n\t" "1:\n" - ::LOCK_PTR_REG (rw), "i" (RW_LOCK_BIAS) : "memory"); + ::LOCK_PTR_REG (&rw->write), "i" (RW_LOCK_BIAS) + : "memory"); } static inline int arch_read_trylock(arch_rwlock_t *lock) { - atomic_t *count = (atomic_t *)lock; + READ_LOCK_ATOMIC(t) *count = (READ_LOCK_ATOMIC(t) *)lock; - if (atomic_dec_return(count) >= 0) + if (READ_LOCK_ATOMIC(dec_return)(count) >= 0) return 1; - atomic_inc(count); + READ_LOCK_ATOMIC(inc)(count); return 0; } static inline int arch_write_trylock(arch_rwlock_t *lock) { - atomic_t *count = (atomic_t *)lock; + atomic_t *count = (atomic_t *)&lock->write; - if (atomic_sub_and_test(RW_LOCK_BIAS, count)) + if (atomic_sub_and_test(WRITE_LOCK_CMP, count)) return 1; - atomic_add(RW_LOCK_BIAS, count); + atomic_add(WRITE_LOCK_CMP, count); return 0; } static inline void arch_read_unlock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory"); + asm volatile(LOCK_PREFIX READ_LOCK_SIZE(inc) " %0" + :"+m" (rw->lock) : : "memory"); } static inline void arch_write_unlock(arch_rwlock_t *rw) { - asm volatile(LOCK_PREFIX "addl %1, %0" - : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory"); + asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0" + : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory"); } #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) +#undef READ_LOCK_SIZE +#undef READ_LOCK_ATOMIC +#undef WRITE_LOCK_ADD +#undef WRITE_LOCK_SUB +#undef WRITE_LOCK_CMP + #define arch_spin_relax(lock) cpu_relax() #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() |
