[PATCH 08/10] KVM: PPC: Book3S HV: Run virtual core whenever any vcpus in it can run

[Paul Mackerras <paulus@samba.org>]

Currently the Book3S HV code implements a policy on multi-threaded
processors (i.e. POWER7) that requires all of the active vcpus in a
virtual core to be ready to run before we run the virtual core.
However, that causes problems on reset, because reset stops all vcpus
except vcpu 0, and can also reduce throughput since all four threads
in a virtual core have to wait whenever any one of them hits a
hypervisor page fault.

This relaxes the policy, allowing the virtual core to run as soon as
any vcpu in it is runnable.  With this, the KVMPPC_VCPU_STOPPED state
and the KVMPPC_VCPU_BUSY_IN_HOST state have been combined into a single
KVMPPC_VCPU_NOTREADY state, since we no longer need to distinguish
between them.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_host.h |    5 +--
 arch/powerpc/kvm/book3s_hv.c        |   74 ++++++++++++++++++-----------------
 2 files changed, 40 insertions(+), 39 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 218534d..1e8cbd1 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -563,9 +563,8 @@ struct kvm_vcpu_arch {
 };
 
 /* Values for vcpu->arch.state */
-#define KVMPPC_VCPU_STOPPED		0
-#define KVMPPC_VCPU_BUSY_IN_HOST	1
-#define KVMPPC_VCPU_RUNNABLE		2
+#define KVMPPC_VCPU_NOTREADY		0
+#define KVMPPC_VCPU_RUNNABLE		1
 
 /* Values for vcpu->arch.io_gpr */
 #define KVM_MMIO_REG_MASK	0x001f
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8e84625..dc34a69 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -669,10 +669,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
-	/*
-	 * We consider the vcpu stopped until we see the first run ioctl for it.
-	 */
-	vcpu->arch.state = KVMPPC_VCPU_STOPPED;
+	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 
 	init_waitqueue_head(&vcpu->arch.cpu_run);
 
@@ -759,9 +756,8 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 {
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
-	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
+	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 	--vc->n_runnable;
-	++vc->n_busy;
 	list_del(&vcpu->arch.run_list);
 }
 
@@ -1062,7 +1058,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int n_ceded;
-	int prev_state;
 	struct kvmppc_vcore *vc;
 	struct kvm_vcpu *v, *vn;
 
@@ -1079,7 +1074,6 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	vcpu->arch.ceded = 0;
 	vcpu->arch.run_task = current;
 	vcpu->arch.kvm_run = kvm_run;
-	prev_state = vcpu->arch.state;
 	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
 	list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
 	++vc->n_runnable;
@@ -1089,35 +1083,26 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	 * If the vcore is already running, we may be able to start
 	 * this thread straight away and have it join in.
 	 */
-	if (prev_state == KVMPPC_VCPU_STOPPED) {
+	if (!signal_pending(current)) {
 		if (vc->vcore_state == VCORE_RUNNING &&
 		    VCORE_EXIT_COUNT(vc) == 0) {
 			vcpu->arch.ptid = vc->n_runnable - 1;
 			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu);
+		} else if (vc->vcore_state == VCORE_SLEEPING) {
+			wake_up(&vc->wq);
 		}
 
-	} else if (prev_state == KVMPPC_VCPU_BUSY_IN_HOST)
-		--vc->n_busy;
+	}
 
 	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
 	       !signal_pending(current)) {
-		if (vc->n_busy || vc->vcore_state != VCORE_INACTIVE) {
+		if (vc->vcore_state != VCORE_INACTIVE) {
 			spin_unlock(&vc->lock);
 			kvmppc_wait_for_exec(vcpu, TASK_INTERRUPTIBLE);
 			spin_lock(&vc->lock);
 			continue;
 		}
-		vc->runner = vcpu;
-		n_ceded = 0;
-		list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
-			if (!v->arch.pending_exceptions)
-				n_ceded += v->arch.ceded;
-		if (n_ceded == vc->n_runnable)
-			kvmppc_vcore_blocked(vc);
-		else
-			kvmppc_run_core(vc);
-
 		list_for_each_entry_safe(v, vn, &vc->runnable_threads,
 					 arch.run_list) {
 			kvmppc_core_prepare_to_enter(v);
@@ -1129,23 +1114,40 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 				wake_up(&v->arch.cpu_run);
 			}
 		}
+		if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
+			break;
+		vc->runner = vcpu;
+		n_ceded = 0;
+		list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
+			if (!v->arch.pending_exceptions)
+				n_ceded += v->arch.ceded;
+		if (n_ceded == vc->n_runnable)
+			kvmppc_vcore_blocked(vc);
+		else
+			kvmppc_run_core(vc);
 		vc->runner = NULL;
 	}
 
-	if (signal_pending(current)) {
-		while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
-		       (vc->vcore_state == VCORE_RUNNING ||
-			vc->vcore_state == VCORE_EXITING)) {
-			spin_unlock(&vc->lock);
-			kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
-			spin_lock(&vc->lock);
-		}
-		if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
-			kvmppc_remove_runnable(vc, vcpu);
-			vcpu->stat.signal_exits++;
-			kvm_run->exit_reason = KVM_EXIT_INTR;
-			vcpu->arch.ret = -EINTR;
-		}
+	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
+	       (vc->vcore_state == VCORE_RUNNING ||
+		vc->vcore_state == VCORE_EXITING)) {
+		spin_unlock(&vc->lock);
+		kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
+		spin_lock(&vc->lock);
+	}
+
+	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
+		kvmppc_remove_runnable(vc, vcpu);
+		vcpu->stat.signal_exits++;
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		vcpu->arch.ret = -EINTR;
+	}
+
+	if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) {
+		/* Wake up some vcpu to run the core */
+		v = list_first_entry(&vc->runnable_threads,
+				     struct kvm_vcpu, arch.run_list);
+		wake_up(&v->arch.cpu_run);
 	}
 
 	spin_unlock(&vc->lock);
-- 
1.7.10