[PATCH 5/5] KVM: PPC: Book3S HV: Implement scheduling wait interval counters in the VPA

[Nicholas Piggin]

PAPR specifies accumulated virtual processor wait intervals that relate
to partition scheduling interval times. Implement these counters in the
same way as they are repoted by dtl.

Reviewed-by: Fabiano Rosas <farosas at linux.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin at gmail.com>
---
This requires patch "powerpc/pseries: Add wait interval counter
definitions to struct lppaca"

https://lists.ozlabs.org/pipermail/linuxppc-dev/2022-September/247798.html

When running a host with this patch and a guest with the corresponding
pseries implementation, the guest shows 10% stolen time with vmstat in a
160 vCPU guest running busy work on all CPUs on a 144 CPU host.
144/160 = 90%.

 arch/powerpc/kvm/book3s_hv.c | 62 ++++++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index c3a4785b10d5..2aca86290f76 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -733,16 +733,15 @@ static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
 }
 
 static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
+					struct lppaca *vpa,
 					unsigned int pcpu, u64 now,
 					unsigned long stolen)
 {
 	struct dtl_entry *dt;
-	struct lppaca *vpa;
 
 	dt = vcpu->arch.dtl_ptr;
-	vpa = vcpu->arch.vpa.pinned_addr;
 
-	if (!dt || !vpa)
+	if (!dt)
 		return;
 
 	dt->dispatch_reason = 7;
@@ -763,29 +762,23 @@ static void __kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	/* order writing *dt vs. writing vpa->dtl_idx */
 	smp_wmb();
 	vpa->dtl_idx = cpu_to_be64(++vcpu->arch.dtl_index);
-	vcpu->arch.dtl.dirty = true;
-}
-
-static void kvmppc_create_dtl_entry_p9(struct kvm_vcpu *vcpu,
-				       struct kvmppc_vcore *vc,
-				       u64 now)
-{
-	unsigned long stolen;
 
-	stolen = vc->stolen_tb - vcpu->arch.stolen_logged;
-	vcpu->arch.stolen_logged = vc->stolen_tb;
-
-	__kvmppc_create_dtl_entry(vcpu, vc->pcpu, now, stolen);
+	/* vcpu->arch.dtl.dirty is set by the caller */
 }
 
-static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
-				    struct kvmppc_vcore *vc)
+static void kvmppc_update_vpa_dispatch(struct kvm_vcpu *vcpu,
+				       struct kvmppc_vcore *vc)
 {
+	struct lppaca *vpa;
 	unsigned long stolen;
 	unsigned long core_stolen;
 	u64 now;
 	unsigned long flags;
 
+	vpa = vcpu->arch.vpa.pinned_addr;
+	if (!vpa)
+		return;
+
 	now = mftb();
 
 	core_stolen = vcore_stolen_time(vc, now);
@@ -796,7 +789,34 @@ static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
 	vcpu->arch.busy_stolen = 0;
 	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 
-	__kvmppc_create_dtl_entry(vcpu, vc->pcpu, now + vc->tb_offset, stolen);
+	vpa->enqueue_dispatch_tb = cpu_to_be64(be64_to_cpu(vpa->enqueue_dispatch_tb) + stolen);
+
+	__kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now + vc->tb_offset, stolen);
+
+	vcpu->arch.vpa.dirty = true;
+}
+
+static void kvmppc_update_vpa_dispatch_p9(struct kvm_vcpu *vcpu,
+				       struct kvmppc_vcore *vc,
+				       u64 now)
+{
+	struct lppaca *vpa;
+	unsigned long stolen;
+	unsigned long stolen_delta;
+
+	vpa = vcpu->arch.vpa.pinned_addr;
+	if (!vpa)
+		return;
+
+	stolen = vc->stolen_tb;
+	stolen_delta = stolen - vcpu->arch.stolen_logged;
+	vcpu->arch.stolen_logged = stolen;
+
+	vpa->enqueue_dispatch_tb = cpu_to_be64(stolen);
+
+	__kvmppc_create_dtl_entry(vcpu, vpa, vc->pcpu, now, stolen_delta);
+
+	vcpu->arch.vpa.dirty = true;
 }
 
 /* See if there is a doorbell interrupt pending for a vcpu */
@@ -3838,7 +3858,7 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 			 * kvmppc_core_prepare_to_enter.
 			 */
 			kvmppc_start_thread(vcpu, pvc);
-			kvmppc_create_dtl_entry(vcpu, pvc);
+			kvmppc_update_vpa_dispatch(vcpu, pvc);
 			trace_kvm_guest_enter(vcpu);
 			if (!vcpu->arch.ptid)
 				thr0_done = true;
@@ -4435,7 +4455,7 @@ static int kvmppc_run_vcpu(struct kvm_vcpu *vcpu)
 		if ((vc->vcore_state == VCORE_PIGGYBACK ||
 		     vc->vcore_state == VCORE_RUNNING) &&
 			   !VCORE_IS_EXITING(vc)) {
-			kvmppc_create_dtl_entry(vcpu, vc);
+			kvmppc_update_vpa_dispatch(vcpu, vc);
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
@@ -4623,7 +4643,7 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit,
 
 	tb = mftb();
 
-	kvmppc_create_dtl_entry_p9(vcpu, vc, tb + vc->tb_offset);
+	kvmppc_update_vpa_dispatch_p9(vcpu, vc, tb + vc->tb_offset);
 
 	trace_kvm_guest_enter(vcpu);
 
-- 
2.37.2