Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Wanpeng Li <kernellwp@gmail.com>
To:     linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc:     Paolo Bonzini <pbonzini@redhat.com>,
        Sean Christopherson <sean.j.christopherson@intel.com>,
        Vitaly Kuznetsov <vkuznets@redhat.com>,
        Wanpeng Li <wanpengli@tencent.com>,
        Jim Mattson <jmattson@google.com>,
        Joerg Roedel <joro@8bytes.org>,
        Haiwei Li <lihaiwei@tencent.com>
Subject: [PATCH v3 3/5] KVM: VMX: Optimize posted-interrupt delivery for timer fastpath
Date:   Fri, 24 Apr 2020 14:22:42 +0800
Message-Id: <1587709364-19090-4-git-send-email-wanpengli@tencent.com>
In-Reply-To: <1587709364-19090-1-git-send-email-wanpengli@tencent.com>
References: <1587709364-19090-1-git-send-email-wanpengli@tencent.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Wanpeng Li <wanpengli@tencent.com>

Optimizing posted-interrupt delivery especially for the timer fastpath 
scenario, I observe kvm_x86_ops.deliver_posted_interrupt() has more latency 
then vmx_sync_pir_to_irr() in the case of timer fastpath scenario, since 
it needs to wait vmentry, after that it can handle external interrupt, ack 
the notification vector, read posted-interrupt descriptor etc, it is slower 
than evaluate and delivery during vmentry immediately approach. Let's skip 
sending interrupt to notify target pCPU and replace by vmx_sync_pir_to_irr() 
before each cont_run.

Tested-by: Haiwei Li <lihaiwei@tencent.com>
Cc: Haiwei Li <lihaiwei@tencent.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 arch/x86/kvm/vmx/vmx.c | 9 ++++++---
 virt/kvm/kvm_main.c    | 1 +
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 5c21027..d21b66b 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3909,8 +3909,9 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	if (pi_test_and_set_on(&vmx->pi_desc))
 		return 0;
 
-	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
-		kvm_vcpu_kick(vcpu);
+	if (vcpu != kvm_get_running_vcpu() &&
+		!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
+		kvm_vcpu_kick(vcpu);
 
 	return 0;
 }
@@ -6757,8 +6758,10 @@ static enum exit_fastpath_completion vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (!kvm_need_cancel_enter_guest(vcpu)) {
 		exit_fastpath = vmx_exit_handlers_fastpath(vcpu);
 		/* static call is better with retpolines */
-		if (exit_fastpath == EXIT_FASTPATH_CONT_RUN)
+		if (exit_fastpath == EXIT_FASTPATH_CONT_RUN) {
+			vmx_sync_pir_to_irr(vcpu);
 			goto cont_run;
+		}
 	}
 
 	return exit_fastpath;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e7436d0..6a289d1 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4633,6 +4633,7 @@ struct kvm_vcpu *kvm_get_running_vcpu(void)
 
 	return vcpu;
 }
+EXPORT_SYMBOL_GPL(kvm_get_running_vcpu);
 
 /**
  * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus.
-- 
2.7.4