[PATCH 3/3] KVM: make make_all_cpus_request() lockless

[Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>]

Now, we have 'vcpu->guest_mode' to judge whether need to send
ipi to other cpus, this way is very exact, so checking request
bit is needless, then we can drop the spinlock let it's collateral

There is the simple test result of kernbench:
  before patch:
   real    5m5.100s                                                                
   user    3m58.051s                                                               
   sys     9m4.742s                                      
                                                
   real    5m3.443s                                                                
   user    3m58.837s                                                               
   sys     9m6.007s

  after patch:
   real    5m0.769s                                                                
   user    3m59.666s                                                               
   sys     8m41.406s  

   real    4m57.980s                                                               
   user    3m59.302s                                                               
   sys     8m38.916s 

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
---
 include/linux/kvm_host.h |    6 ------
 virt/kvm/kvm_main.c      |    9 +++------
 2 files changed, 3 insertions(+), 12 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b5021db..3e64133 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -212,7 +212,6 @@ struct kvm_memslots {
 
 struct kvm {
 	spinlock_t mmu_lock;
-	raw_spinlock_t requests_lock;
 	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots *memslots;
@@ -719,11 +718,6 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 	set_bit(req, &vcpu->requests);
 }
 
-static inline bool kvm_make_check_request(int req, struct kvm_vcpu *vcpu)
-{
-	return test_and_set_bit(req, &vcpu->requests);
-}
-
 static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 {
 	if (test_bit(req, &vcpu->requests)) {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 6648c6e..34066ab 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -147,11 +147,9 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 
 	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
 
-	raw_spin_lock(&kvm->requests_lock);
-	me = smp_processor_id();
+	me = get_cpu();
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if (kvm_make_check_request(req, vcpu))
-			continue;
+		kvm_make_request(req, vcpu);
 		cpu = vcpu->cpu;
 		if (cpus != NULL && cpu != -1 && cpu != me &&
 		      atomic_read(&vcpu->guest_mode))
@@ -163,7 +161,7 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 		smp_call_function_many(cpus, ack_flush, NULL, 1);
 	else
 		called = false;
-	raw_spin_unlock(&kvm->requests_lock);
+	put_cpu();
 	free_cpumask_var(cpus);
 	return called;
 }
@@ -429,7 +427,6 @@ static struct kvm *kvm_create_vm(void)
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
 	spin_lock_init(&kvm->mmu_lock);
-	raw_spin_lock_init(&kvm->requests_lock);
 	kvm_eventfd_init(kvm);
 	mutex_init(&kvm->lock);
 	mutex_init(&kvm->irq_lock);
-- 
1.7.3.4