KVM: Add "exiting guest mode" state

Currently we keep track of only two states: guest mode and host
mode.  This patch adds an "exiting guest mode" state that tells
us that an IPI will happen soon, so unless we need to wait for the
IPI, we can avoid it completely.

Also
1: No need atomically to read/write ->mode in vcpu's thread

2: reorganize struct kvm_vcpu to make ->mode and ->requests
   in the same cache line explicitly

Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

4 files changed, 35 insertions, 12 deletions

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 70d224d..8213efe 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -662,6 +662,7 @@ again:
 		goto vcpu_run_fail;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	vcpu->mode = IN_GUEST_MODE;
 	kvm_guest_enter();
 
 	/*
@@ -683,6 +684,7 @@ again:
 	 */
 	barrier();
 	kvm_guest_exit();
+	vcpu->mode = OUTSIDE_GUEST_MODE;
 	preempt_enable();
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5eccdba..a7f65aa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5210,14 +5210,18 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_load_guest_fpu(vcpu);
 	kvm_load_guest_xcr0(vcpu);
 
-	atomic_set(&vcpu->guest_mode, 1);
-	smp_wmb();
+	vcpu->mode = IN_GUEST_MODE;
+
+	/* We should set ->mode before check ->requests,
+	 * see the comment in make_all_cpus_request.
+	 */
+	smp_mb();
 
 	local_irq_disable();
 
-	if (!atomic_read(&vcpu->guest_mode) || vcpu->requests
+	if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests
 	    || need_resched() || signal_pending(current)) {
-		atomic_set(&vcpu->guest_mode, 0);
+		vcpu->mode = OUTSIDE_GUEST_MODE;
 		smp_wmb();
 		local_irq_enable();
 		preempt_enable();
@@ -5253,7 +5257,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
 
-	atomic_set(&vcpu->guest_mode, 0);
+	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 	local_irq_enable();
 
@@ -6157,7 +6161,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 
 	me = get_cpu();
 	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
-		if (atomic_xchg(&vcpu->guest_mode, 0))
+		if (kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE)
 			smp_send_reschedule(cpu);
 	put_cpu();
 }
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b5021db..b99eacd 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -98,19 +98,26 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
+enum {
+	OUTSIDE_GUEST_MODE,
+	IN_GUEST_MODE,
+	EXITING_GUEST_MODE
+};
+
 struct kvm_vcpu {
 	struct kvm *kvm;
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	struct preempt_notifier preempt_notifier;
 #endif
+	int cpu;
 	int vcpu_id;
-	struct mutex mutex;
-	int   cpu;
-	atomic_t guest_mode;
-	struct kvm_run *run;
+	int srcu_idx;
+	int mode;
 	unsigned long requests;
 	unsigned long guest_debug;
-	int srcu_idx;
+
+	struct mutex mutex;
+	struct kvm_run *run;
 
 	int fpu_active;
 	int guest_fpu_loaded, guest_xcr0_loaded;
@@ -140,6 +147,11 @@ struct kvm_vcpu {
 	struct kvm_vcpu_arch arch;
 };
 
+static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
+{
+	return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE);
+}
+
 /*
  * Some of the bitops functions do not support too long bitmaps.
  * This number must be determined not to exceed such limits.
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fd67bcd..19209f8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -171,7 +171,12 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
 		if (kvm_make_check_request(req, vcpu))
 			continue;
 		cpu = vcpu->cpu;
-		if (cpus != NULL && cpu != -1 && cpu != me)
+
+		/* Set ->requests bit before we read ->mode */
+		smp_mb();
+
+		if (cpus != NULL && cpu != -1 && cpu != me &&
+		      kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE)
 			cpumask_set_cpu(cpu, cpus);
 	}
 	if (unlikely(cpus == NULL))