2 files changed, 86 insertions, 16 deletions

diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index b002e71..9f92c18 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -1,6 +1,65 @@
 #ifndef __ASM_QSPINLOCK_PARAVIRT_H
 #define __ASM_QSPINLOCK_PARAVIRT_H
 
+/*
+ * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit
+ * registers. For i386, however, only 1 32-bit register needs to be saved
+ * and restored. So an optimized version of __pv_queued_spin_unlock() is
+ * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit.
+ */
+#ifdef CONFIG_64BIT
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
+#define __pv_queued_spin_unlock	__pv_queued_spin_unlock
+#define PV_UNLOCK		"__raw_callee_save___pv_queued_spin_unlock"
+#define PV_UNLOCK_SLOWPATH	"__raw_callee_save___pv_queued_spin_unlock_slowpath"
+
+/*
+ * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock
+ * which combines the registers saving trunk and the body of the following
+ * C code:
+ *
+ * void __pv_queued_spin_unlock(struct qspinlock *lock)
+ * {
+ *	struct __qspinlock *l = (void *)lock;
+ *	u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+ *
+ *	if (likely(lockval == _Q_LOCKED_VAL))
+ *		return;
+ *	pv_queued_spin_unlock_slowpath(lock, lockval);
+ * }
+ *
+ * For x86-64,
+ *   rdi = lock              (first argument)
+ *   rsi = lockval           (second argument)
+ *   rdx = internal variable (set to 0)
+ */
+asm    (".pushsection .text;"
+	".globl " PV_UNLOCK ";"
+	".align 4,0x90;"
+	PV_UNLOCK ": "
+	"push  %rdx;"
+	"mov   $0x1,%eax;"
+	"xor   %edx,%edx;"
+	"lock cmpxchg %dl,(%rdi);"
+	"cmp   $0x1,%al;"
+	"jne   .slowpath;"
+	"pop   %rdx;"
+	"ret;"
+	".slowpath: "
+	"push   %rsi;"
+	"movzbl %al,%esi;"
+	"call " PV_UNLOCK_SLOWPATH ";"
+	"pop    %rsi;"
+	"pop    %rdx;"
+	"ret;"
+	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
+	".popsection");
+
+#else /* CONFIG_64BIT */
+
+extern void __pv_queued_spin_unlock(struct qspinlock *lock);
 PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
 
+#endif /* CONFIG_64BIT */
 #endif
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index f0450ff..4bd323d 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -308,23 +308,14 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
 }
 
 /*
- * PV version of the unlock function to be used in stead of
- * queued_spin_unlock().
+ * PV versions of the unlock fastpath and slowpath functions to be used
+ * instead of queued_spin_unlock().
  */
-__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+__visible void
+__pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 {
 	struct __qspinlock *l = (void *)lock;
 	struct pv_node *node;
-	u8 locked;
-
-	/*
-	 * We must not unlock if SLOW, because in that case we must first
-	 * unhash. Otherwise it would be possible to have multiple @lock
-	 * entries, which would be BAD.
-	 */
-	locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
-	if (likely(locked == _Q_LOCKED_VAL))
-		return;
 
 	if (unlikely(locked != _Q_SLOW_VAL)) {
 		WARN(!debug_locks_silent,
@@ -363,12 +354,32 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 	 */
 	pv_kick(node->cpu);
 }
+
 /*
  * Include the architecture specific callee-save thunk of the
  * __pv_queued_spin_unlock(). This thunk is put together with
- * __pv_queued_spin_unlock() near the top of the file to make sure
- * that the callee-save thunk and the real unlock function are close
- * to each other sharing consecutive instruction cachelines.
+ * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
+ * function close to each other sharing consecutive instruction cachelines.
+ * Alternatively, architecture specific version of __pv_queued_spin_unlock()
+ * can be defined.
  */
 #include <asm/qspinlock_paravirt.h>
 
+#ifndef __pv_queued_spin_unlock
+__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+	u8 locked;
+
+	/*
+	 * We must not unlock if SLOW, because in that case we must first
+	 * unhash. Otherwise it would be possible to have multiple @lock
+	 * entries, which would be BAD.
+	 */
+	locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+	if (likely(locked == _Q_LOCKED_VAL))
+		return;
+
+	__pv_queued_spin_unlock_slowpath(lock, locked);
+}
+#endif /* __pv_queued_spin_unlock */