1 files changed, 27 insertions, 87 deletions

diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index ee67edf86fdd..972c260919a3 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -49,109 +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");
 }
@@ -159,16 +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