x86, ticketlock: Make __ticket_spin_trylock common

Make trylock code common regardless of ticket size.

(Also, rename arch_spinlock.slock to head_tail.)

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Link: http://lkml.kernel.org/r/4E5BCC40.3030501@goop.org
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>

arch/x86/include/asm/spinlock.h

@@ -69,60 +69,33 @@ static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
 	barrier();		/* make sure nothing creeps before the lock is taken */
 }
 
-#if (NR_CPUS < 256)
 static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned 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;
 
-	return tmp;
+	new.head_tail = old.head_tail + (1 << TICKET_SHIFT);
+
+	/* 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
-static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
-{
-	unsigned tmp;
-	unsigned 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");
 }

arch/x86/include/asm/spinlock_types.h

@@ -9,23 +9,25 @@
 
 #if (CONFIG_NR_CPUS < 256)
 typedef u8  __ticket_t;
+typedef u16 __ticketpair_t;
 #else
 typedef u16 __ticket_t;
+typedef u32 __ticketpair_t;
 #endif
 
 #define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
 #define TICKET_MASK	((__ticket_t)((1 << TICKET_SHIFT) - 1))
 
 typedef struct arch_spinlock {
 	union {
-		unsigned int slock;
+		__ticketpair_t head_tail;
 		struct __raw_tickets {
 			__ticket_t head, tail;
 		} tickets;
 	};
 } arch_spinlock_t;
 
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ { .slock = 0 } }
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
 
 #include <asm/rwlock.h>