#include <asm/page.h>
#include <asm/processor.h>
#include <linux/compiler.h>
-
+#include <asm/paravirt.h>
/*
* Your basic SMP spinlocks, allowing only a single CPU anywhere
*
*/
#ifdef CONFIG_X86_32
-typedef char _slock_t;
-# define LOCK_INS_DEC "decb"
-# define LOCK_INS_XCH "xchgb"
-# define LOCK_INS_MOV "movb"
-# define LOCK_INS_CMP "cmpb"
# define LOCK_PTR_REG "a"
#else
-typedef int _slock_t;
-# define LOCK_INS_DEC "decl"
-# define LOCK_INS_XCH "xchgl"
-# define LOCK_INS_MOV "movl"
-# define LOCK_INS_CMP "cmpl"
# define LOCK_PTR_REG "D"
#endif
-#if (NR_CPUS > 256)
-#error spinlock supports a maximum of 256 CPUs
+#if defined(CONFIG_X86_32) && \
+ (defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+/*
+ * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * (PPro errata 66, 92)
+ */
+# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
+#else
+# define UNLOCK_LOCK_PREFIX
#endif
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+/*
+ * Ticket locks are conceptually two parts, one indicating the current head of
+ * the queue, and the other indicating the current tail. The lock is acquired
+ * by atomically noting the tail and incrementing it by one (thus adding
+ * ourself to the queue and noting our position), then waiting until the head
+ * becomes equal to the the initial value of the tail.
+ *
+ * We use an xadd covering *both* parts of the lock, to increment the tail and
+ * also load the position of the head, which takes care of memory ordering
+ * 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)
+static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
{
- int tmp = *(volatile signed int *)(&(lock)->slock);
+ int tmp = ACCESS_ONCE(lock->slock);
return (((tmp >> 8) & 0xff) != (tmp & 0xff));
}
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
{
- int tmp = *(volatile signed int *)(&(lock)->slock);
+ int tmp = ACCESS_ONCE(lock->slock);
return (((tmp >> 8) & 0xff) - (tmp & 0xff)) > 1;
}
-static inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
{
short inc = 0x0100;
- /*
- * Ticket locks are conceptually two bytes, one indicating the current
- * head of the queue, and the other indicating the current tail. The
- * lock is acquired by atomically noting the tail and incrementing it
- * by one (thus adding ourself to the queue and noting our position),
- * then waiting until the head becomes equal to the the initial value
- * of the tail.
- *
- * This uses a 16-bit xadd to increment the tail and also load the
- * position of the head, which takes care of memory ordering issues
- * and should be optimal for the uncontended case. Note the tail must
- * be in the high byte, otherwise the 16-bit wide increment of the low
- * byte would carry up and contaminate the high byte.
- */
-
- __asm__ __volatile__ (
+ asm volatile (
LOCK_PREFIX "xaddw %w0, %1\n"
"1:\t"
"cmpb %h0, %b0\n\t"
/* don't need lfence here, because loads are in-order */
"jmp 1b\n"
"2:"
- :"+Q" (inc), "+m" (lock->slock)
+ : "+Q" (inc), "+m" (lock->slock)
:
- :"memory", "cc");
+ : "memory", "cc");
}
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
-
-static inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
{
int tmp;
short new;
- asm volatile(
- "movw %2,%w0\n\t"
- "cmpb %h0,%b0\n\t"
- "jne 1f\n\t"
- "movw %w0,%w1\n\t"
- "incb %h1\n\t"
- "lock ; cmpxchgw %w1,%2\n\t"
- "1:"
- "sete %b1\n\t"
- "movzbl %b1,%0\n\t"
- :"=&a" (tmp), "=Q" (new), "+m" (lock->slock)
- :
- : "memory", "cc");
+ asm volatile("movw %2,%w0\n\t"
+ "cmpb %h0,%b0\n\t"
+ "jne 1f\n\t"
+ "movw %w0,%w1\n\t"
+ "incb %h1\n\t"
+ "lock ; cmpxchgw %w1,%2\n\t"
+ "1:"
+ "sete %b1\n\t"
+ "movzbl %b1,%0\n\t"
+ : "=&a" (tmp), "=Q" (new), "+m" (lock->slock)
+ :
+ : "memory", "cc");
return tmp;
}
-#if defined(CONFIG_X86_32) && \
- (defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
-/*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
- * (PPro errata 66, 92)
- */
-# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+{
+ asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
+ : "+m" (lock->slock)
+ :
+ : "memory", "cc");
+}
#else
-# define UNLOCK_LOCK_PREFIX
+static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
+{
+ int tmp = ACCESS_ONCE(lock->slock);
+
+ return (((tmp >> 16) & 0xffff) != (tmp & 0xffff));
+}
+
+static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
+{
+ int tmp = ACCESS_ONCE(lock->slock);
+
+ return (((tmp >> 16) & 0xffff) - (tmp & 0xffff)) > 1;
+}
+
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+{
+ int inc = 0x00010000;
+ int tmp;
+
+ asm volatile("lock ; 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:"
+ : "+Q" (inc), "+m" (lock->slock), "=r" (tmp)
+ :
+ : "memory", "cc");
+}
+
+static __always_inline int __ticket_spin_trylock(raw_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"
+ "jne 1f\n\t"
+ "addl $0x00010000, %1\n\t"
+ "lock ; cmpxchgl %1,%2\n\t"
+ "1:"
+ "sete %b1\n\t"
+ "movzbl %b1,%0\n\t"
+ : "=&a" (tmp), "=r" (new), "+m" (lock->slock)
+ :
+ : "memory", "cc");
+
+ return tmp;
+}
+
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+{
+ asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
+ : "+m" (lock->slock)
+ :
+ : "memory", "cc");
+}
#endif
-static inline void __raw_spin_unlock(raw_spinlock_t *lock)
+#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
+
+#ifdef CONFIG_PARAVIRT
+/*
+ * Define virtualization-friendly old-style lock byte lock, for use in
+ * pv_lock_ops if desired.
+ *
+ * This differs from the pre-2.6.24 spinlock by always using xchgb
+ * rather than decb to take the lock; this allows it to use a
+ * zero-initialized lock structure. It also maintains a 1-byte
+ * contention counter, so that we can implement
+ * __byte_spin_is_contended.
+ */
+struct __byte_spinlock {
+ s8 lock;
+ s8 spinners;
+};
+
+static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
{
- __asm__ __volatile__(
- UNLOCK_LOCK_PREFIX "incb %0"
- :"+m" (lock->slock)
- :
- :"memory", "cc");
+ struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+ return bl->lock != 0;
+}
+
+static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
+{
+ struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+ return bl->spinners != 0;
+}
+
+static inline void __byte_spin_lock(raw_spinlock_t *lock)
+{
+ struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+ s8 val = 1;
+
+ asm("1: xchgb %1, %0\n"
+ " test %1,%1\n"
+ " jz 3f\n"
+ " " LOCK_PREFIX "incb %2\n"
+ "2: rep;nop\n"
+ " cmpb $1, %0\n"
+ " je 2b\n"
+ " " LOCK_PREFIX "decb %2\n"
+ " jmp 1b\n"
+ "3:"
+ : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
+}
+
+static inline int __byte_spin_trylock(raw_spinlock_t *lock)
+{
+ struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+ u8 old = 1;
+
+ asm("xchgb %1,%0"
+ : "+m" (bl->lock), "+q" (old) : : "memory");
+
+ return old == 0;
+}
+
+static inline void __byte_spin_unlock(raw_spinlock_t *lock)
+{
+ struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+ smp_wmb();
+ bl->lock = 0;
+}
+#else /* !CONFIG_PARAVIRT */
+static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+{
+ return __ticket_spin_is_locked(lock);
+}
+
+static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+{
+ return __ticket_spin_is_contended(lock);
+}
+
+static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+{
+ __ticket_spin_lock(lock);
+}
+
+static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+{
+ return __ticket_spin_trylock(lock);
+}
+
+static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+ __ticket_spin_unlock(lock);
}
+#endif /* CONFIG_PARAVIRT */
static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
{