vcpu_is_preempted() is performance sensitive called in function
osq_lock(), here set it as macro. So that parameter is not parsed
at most time, it can avoid cache line thrashing across numa node.

Here is part of unixbench result on 3C5000 DualWay machine with 32
Cores and 2 Numa node.
          original    inline   with patch
execl     7025.7      6991.2   7242.3
fstime    474.6       703.1    1071

From the test result, with macro method is the best, and there is
some improvment compared with original function method.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
---
 arch/loongarch/include/asm/qspinlock.h | 27 +++++++++++++++++++++-----
 arch/loongarch/kernel/paravirt.c       | 15 ++------------
 2 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/arch/loongarch/include/asm/qspinlock.h b/arch/loongarch/include/asm/qspinlock.h
index 66244801db67..b5d7a038faf1 100644
--- a/arch/loongarch/include/asm/qspinlock.h
+++ b/arch/loongarch/include/asm/qspinlock.h
@@ -5,8 +5,10 @@
 #include <linux/jump_label.h>
 
 #ifdef CONFIG_PARAVIRT
-
+#include <asm/kvm_para.h>
 DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key);
+DECLARE_STATIC_KEY_FALSE(virt_preempt_key);
+DECLARE_PER_CPU(struct kvm_steal_time, steal_time);
 
 #define virt_spin_lock virt_spin_lock
 
@@ -34,10 +36,25 @@ static inline bool virt_spin_lock(struct qspinlock *lock)
 	return true;
 }
 
-#define vcpu_is_preempted vcpu_is_preempted
-
-bool vcpu_is_preempted(int cpu);
-
+/*
+ * Macro is better than inline function here
+ * With inline function, parameter cpu is parsed even though it is not used.
+ * This may cause cache line thrashing across NUMA node.
+ * With macro method, parameter cpu is parsed only when it is used.
+ */
+#define vcpu_is_preempted(cpu)							\
+({										\
+	bool __val;								\
+										\
+	if (!static_branch_unlikely(&virt_preempt_key))				\
+		__val = false;							\
+	else {									\
+		struct kvm_steal_time *src;					\
+		src = &per_cpu(steal_time, cpu);				\
+		__val = !!(READ_ONCE(src->preempted) & KVM_VCPU_PREEMPTED);	\
+	}									\
+	__val;									\
+})
 #endif /* CONFIG_PARAVIRT */
 
 #include <asm-generic/qspinlock.h>
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index b74fe6db49ab..2d1206e486e2 100644
--- a/arch/loongarch/kernel/paravirt.c
+++ b/arch/loongarch/kernel/paravirt.c
@@ -10,8 +10,8 @@
 #include <asm/paravirt.h>
 
 static int has_steal_clock;
-static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
-static DEFINE_STATIC_KEY_FALSE(virt_preempt_key);
+DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
+DEFINE_STATIC_KEY_FALSE(virt_preempt_key);
 DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key);
 
 static bool steal_acc = true;
@@ -261,17 +261,6 @@ static int pv_time_cpu_down_prepare(unsigned int cpu)
 	return 0;
 }
 
-bool vcpu_is_preempted(int cpu)
-{
-	struct kvm_steal_time *src;
-
-	if (!static_branch_unlikely(&virt_preempt_key))
-		return false;
-
-	src = &per_cpu(steal_time, cpu);
-	return !!(src->preempted & KVM_VCPU_PREEMPTED);
-}
-EXPORT_SYMBOL(vcpu_is_preempted);
 #endif
 
 static void pv_cpu_reboot(void *unused)
-- 
2.39.3