This patch makes the necessary changes at the x86 architecture
specific layer to enable the use of queue spinlock for x86-64. As
x86-32 machines are typically not multi-socket. The benefit of queue
spinlock may not be apparent. So queue spinlock is not enabled.
Currently, there is some incompatibilities between the para-virtualized
spinlock code (which hard-codes the use of ticket spinlock) and the
queue spinlock. Therefore, the use of queue spinlock is disabled when
the para-virtualized spinlock is enabled.
The arch/x86/include/asm/qspinlock.h header file includes some x86
specific optimization which will make the queue spinlock code perform
better than the generic implementation.
Signed-off-by: Waiman Long <Waiman.Long@xxxxxx>
Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
---
arch/x86/Kconfig | 1 +
arch/x86/include/asm/qspinlock.h | 29 +++++++++++++++++++++++++++++
arch/x86/include/asm/spinlock.h | 5 +++++
arch/x86/include/asm/spinlock_types.h | 4 ++++
4 files changed, 39 insertions(+), 0 deletions(-)
create mode 100644 arch/x86/include/asm/qspinlock.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 25d2c6f..95c9c4e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -29,6 +29,7 @@ config X86
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_SUPPORTS_INT128 if X86_64
select ARCH_WANTS_PROT_NUMA_PROT_NONE
+ select ARCH_USE_QUEUE_SPINLOCK
select HAVE_IDE
select HAVE_OPROFILE
select HAVE_PCSPKR_PLATFORM
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
new file mode 100644
index 0000000..e4a4f5d
--- /dev/null
+++ b/arch/x86/include/asm/qspinlock.h
@@ -0,0 +1,29 @@
+#ifndef _ASM_X86_QSPINLOCK_H
+#define _ASM_X86_QSPINLOCK_H
+
+#include <asm-generic/qspinlock_types.h>
+
+#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+
+#define queue_spin_unlock queue_spin_unlock
+/**
+ * queue_spin_unlock - release a queue spinlock
+ * @lock : Pointer to queue spinlock structure
+ *
+ * No special memory barrier other than a compiler one is needed for the
+ * x86 architecture. A compiler barrier is added at the end to make sure
+ * that the clearing the lock bit is done ASAP without artificial delay
+ * due to compiler optimization.
+ */
+static inline void queue_spin_unlock(struct qspinlock *lock)
+{
+ barrier();
+ ACCESS_ONCE(*(u8 *)lock) = 0;
+ barrier();
+}
+
+#endif /* !CONFIG_X86_OOSTORE && !CONFIG_X86_PPRO_FENCE */
+
+#include <asm-generic/qspinlock.h>
+
+#endif /* _ASM_X86_QSPINLOCK_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 0f62f54..958d20f 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -42,6 +42,10 @@
extern struct static_key paravirt_ticketlocks_enabled;
static __always_inline bool static_key_false(struct static_key *key);
+#ifdef CONFIG_QUEUE_SPINLOCK
+#include <asm/qspinlock.h>
+#else
+
#ifdef CONFIG_PARAVIRT_SPINLOCKS
static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
@@ -180,6 +184,7 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
{
arch_spin_lock(lock);
}
+#endif /* CONFIG_QUEUE_SPINLOCK */
static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 4f1bea1..7960268 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -23,6 +23,9 @@ typedef u32 __ticketpair_t;
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
+#ifdef CONFIG_QUEUE_SPINLOCK
+#include <asm-generic/qspinlock_types.h>
+#else
typedef struct arch_spinlock {
union {
__ticketpair_t head_tail;
@@ -33,6 +36,7 @@ typedef struct arch_spinlock {
} arch_spinlock_t;
#define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } }
+#endif /* CONFIG_QUEUE_SPINLOCK */
#include <asm/rwlock.h>
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
