[PATCH] KVM: X86: Count success and invalid yields

[Wanpeng Li <kernellwp@gmail.com>]

From: Wanpeng Li <wanpengli@tencent.com>

To analyze some performance issues with lock contention and scheduling,
it is nice to know when directed yield are successful or failing.

Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/x86.c              | 26 ++++++++++++++++++++------
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 44f8930..157bcaa 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1126,6 +1126,8 @@ struct kvm_vcpu_stat {
 	u64 halt_poll_success_ns;
 	u64 halt_poll_fail_ns;
 	u64 nested_run;
+	u64 yield_directed;
+	u64 yield_directed_ignore;
 };
 
 struct x86_instruction_info;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 16fb395..3b475cd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -246,6 +246,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("halt_poll_success_ns", halt_poll_success_ns),
 	VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns),
 	VCPU_STAT("nested_run", nested_run),
+	VCPU_STAT("yield_directed", yield_directed),
+	VCPU_STAT("yield_directed_ignore", yield_directed_ignore),
 	VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped),
 	VM_STAT("mmu_pte_write", mmu_pte_write),
 	VM_STAT("mmu_pde_zapped", mmu_pde_zapped),
@@ -8211,21 +8213,33 @@ void kvm_apicv_init(struct kvm *kvm, bool enable)
 }
 EXPORT_SYMBOL_GPL(kvm_apicv_init);
 
-static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
+static void kvm_sched_yield(struct kvm_vcpu *vcpu, unsigned long dest_id)
 {
 	struct kvm_vcpu *target = NULL;
 	struct kvm_apic_map *map;
 
+	vcpu->stat.yield_directed++;
+
 	rcu_read_lock();
-	map = rcu_dereference(kvm->arch.apic_map);
+	map = rcu_dereference(vcpu->kvm->arch.apic_map);
 
 	if (likely(map) && dest_id <= map->max_apic_id && map->phys_map[dest_id])
 		target = map->phys_map[dest_id]->vcpu;
 
 	rcu_read_unlock();
+	if (!target)
+		goto no_yield;
+
+	if (!READ_ONCE(target->ready))
+		goto no_yield;
 
-	if (target && READ_ONCE(target->ready))
-		kvm_vcpu_yield_to(target);
+	if (kvm_vcpu_yield_to(target) <= 0)
+		goto no_yield;
+	return;
+
+no_yield:
+	vcpu->stat.yield_directed_ignore++;
+	return;
 }
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
@@ -8272,7 +8286,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 			break;
 
 		kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
-		kvm_sched_yield(vcpu->kvm, a1);
+		kvm_sched_yield(vcpu, a1);
 		ret = 0;
 		break;
 #ifdef CONFIG_X86_64
@@ -8290,7 +8304,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_SCHED_YIELD))
 			break;
 
-		kvm_sched_yield(vcpu->kvm, a0);
+		kvm_sched_yield(vcpu, a0);
 		ret = 0;
 		break;
 	default:
-- 
2.7.4