1 files changed, 33 insertions, 8 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c886557638a1..6fa518f6501d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -225,6 +225,13 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 	int cpu;
 	struct rcuwait *waitp;
 
+	/*
+	 * rcuwait_wake_up contains smp_mb() which orders prior stores that
+	 * create pending work vs below loads of cpu fields. The other side
+	 * is the barrier in vcpu run that orders setting the cpu fields vs
+	 * testing for pending work.
+	 */
+
 	waitp = kvm_arch_vcpu_get_wait(vcpu);
 	if (rcuwait_wake_up(waitp))
 		++vcpu->stat.generic.halt_wakeup;
@@ -1089,7 +1096,7 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 			break;
 		}
 		tvcpu->arch.prodded = 1;
-		smp_mb();
+		smp_mb(); /* This orders prodded store vs ceded load */
 		if (tvcpu->arch.ceded)
 			kvmppc_fast_vcpu_kick_hv(tvcpu);
 		break;
@@ -3766,6 +3773,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 		pvc = core_info.vc[sub];
 		pvc->pcpu = pcpu + thr;
 		for_each_runnable_thread(i, vcpu, pvc) {
+			/*
+			 * XXX: is kvmppc_start_thread called too late here?
+			 * It updates vcpu->cpu and vcpu->arch.thread_cpu
+			 * which are used by kvmppc_fast_vcpu_kick_hv(), but
+			 * kick is called after new exceptions become available
+			 * and exceptions are checked earlier than here, by
+			 * kvmppc_core_prepare_to_enter.
+			 */
 			kvmppc_start_thread(vcpu, pvc);
 			kvmppc_create_dtl_entry(vcpu, pvc);
 			trace_kvm_guest_enter(vcpu);
@@ -4487,6 +4502,21 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	if (need_resched() || !kvm->arch.mmu_ready)
 		goto out;
 
+	vcpu->cpu = pcpu;
+	vcpu->arch.thread_cpu = pcpu;
+	vc->pcpu = pcpu;
+	local_paca->kvm_hstate.kvm_vcpu = vcpu;
+	local_paca->kvm_hstate.ptid = 0;
+	local_paca->kvm_hstate.fake_suspend = 0;
+
+	/*
+	 * Orders set cpu/thread_cpu vs testing for pending interrupts and
+	 * doorbells below. The other side is when these fields are set vs
+	 * kvmppc_fast_vcpu_kick_hv reading the cpu/thread_cpu fields to
+	 * kick a vCPU to notice the pending interrupt.
+	 */
+	smp_mb();
+
 	if (!nested) {
 		kvmppc_core_prepare_to_enter(vcpu);
 		if (test_bit(BOOK3S_IRQPRIO_EXTERNAL,
@@ -4506,13 +4536,6 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	tb = mftb();
 
-	vcpu->cpu = pcpu;
-	vcpu->arch.thread_cpu = pcpu;
-	vc->pcpu = pcpu;
-	local_paca->kvm_hstate.kvm_vcpu = vcpu;
-	local_paca->kvm_hstate.ptid = 0;
-	local_paca->kvm_hstate.fake_suspend = 0;
-
 	__kvmppc_create_dtl_entry(vcpu, pcpu, tb + vc->tb_offset, 0);
 
 	trace_kvm_guest_enter(vcpu);
@@ -4614,6 +4637,8 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 	run->exit_reason = KVM_EXIT_INTR;
 	vcpu->arch.ret = -EINTR;
  out:
+	vcpu->cpu = -1;
+	vcpu->arch.thread_cpu = -1;
 	powerpc_local_irq_pmu_restore(flags);
 	preempt_enable();
 	goto done;