From: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
Increment ticket head/tails by 2 rather than 1 to leave the LSB free
to store a "is in slowpath state" bit. This halves the number
of possible CPUs for a given ticket size, but this shouldn't matter
in practice - kernels built for 32k+ CPU systems are probably
specially built for the hardware rather than a generic distro
kernel.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
---
arch/x86/include/asm/spinlock.h | 16 ++++++++--------
arch/x86/include/asm/spinlock_types.h | 10 +++++++++-
2 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index d1a3970..7a1c0c4 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -82,7 +82,7 @@ static __always_inline void __ticket_unlock_kick(struct
arch_spinlock *lock, __t
*/
static __always_inline void arch_spin_lock(struct arch_spinlock *lock)
{
- register struct __raw_tickets inc = { .tail = 1 };
+ register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC };
inc = xadd(&lock->tickets, inc);
@@ -108,7 +108,7 @@ static __always_inline int
arch_spin_trylock(arch_spinlock_t *lock)
if (old.tickets.head != old.tickets.tail)
return 0;
- new.head_tail = old.head_tail + (1 << TICKET_SHIFT);
+ new.head_tail = old.head_tail + (TICKET_LOCK_INC << 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;
@@ -117,24 +117,24 @@ static __always_inline int
arch_spin_trylock(arch_spinlock_t *lock)
#if (NR_CPUS < 256)
static __always_inline void __ticket_unlock_release(arch_spinlock_t *lock)
{
- asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
+ asm volatile(UNLOCK_LOCK_PREFIX "addb %1, %0"
: "+m" (lock->head_tail)
- :
+ : "i" (TICKET_LOCK_INC)
: "memory", "cc");
}
#else
static __always_inline void __ticket_unlock_release(arch_spinlock_t *lock)
{
- asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
+ asm volatile(UNLOCK_LOCK_PREFIX "addw %1, %0"
: "+m" (lock->head_tail)
- :
+ : "i" (TICKET_LOCK_INC)
: "memory", "cc");
}
#endif
static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
{
- __ticket_t next = lock->tickets.head + 1;
+ __ticket_t next = lock->tickets.head + TICKET_LOCK_INC;
__ticket_unlock_release(lock);
__ticket_unlock_kick(lock, next);
@@ -151,7 +151,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t
*lock)
{
struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
- return ((tmp.tail - tmp.head) & TICKET_MASK) > 1;
+ return ((tmp.tail - tmp.head) & TICKET_MASK) > TICKET_LOCK_INC;
}
#define arch_spin_is_contended arch_spin_is_contended
diff --git a/arch/x86/include/asm/spinlock_types.h
b/arch/x86/include/asm/spinlock_types.h
index dbe223d..aa9a205 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -3,7 +3,13 @@
#include <linux/types.h>
-#if (CONFIG_NR_CPUS < 256)
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define __TICKET_LOCK_INC 2
+#else
+#define __TICKET_LOCK_INC 1
+#endif
+
+#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC))
typedef u8 __ticket_t;
typedef u16 __ticketpair_t;
#else
@@ -11,6 +17,8 @@ typedef u16 __ticket_t;
typedef u32 __ticketpair_t;
#endif
+#define TICKET_LOCK_INC ((__ticket_t)__TICKET_LOCK_INC)
+
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
#define TICKET_MASK ((__ticket_t)((1 << TICKET_SHIFT) - 1))
--
1.7.6
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
Home