linux-kernel - [PATCH 4/7] KVM: VMX: Optimize posted-interrupt delivery for timer fastpath

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20200506161048.28840-5-pbonzini@redhat.com>
Date:   Wed,  6 May 2020 12:10:45 -0400
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     linux-kernel@...r.kernel.org, kvm@...r.kernel.org
Cc:     wanpengli@...cent.com, linxl3@...gsu.com,
        Haiwei Li <lihaiwei@...cent.com>
Subject: [PATCH 4/7] KVM: VMX: Optimize posted-interrupt delivery for timer fastpath

From: Wanpeng Li <wanpengli@...cent.com>

While optimizing posted-interrupt delivery especially for the timer
fastpath scenario, I measured kvm_x86_ops.deliver_posted_interrupt()
to introduce substantial latency because the processor has to perform
all vmentry tasks, ack the posted interrupt notification vector,
read the posted-interrupt descriptor etc.

This is not only slow, it is also unnecessary when delivering an
interrupt to the current CPU (as is the case for the LAPIC timer) because
PIR->IRR and IRR->RVI synchronization is already performed on vmentry
Therefore skip kvm_vcpu_trigger_posted_interrupt in this case, and
instead do vmx_sync_pir_to_irr() on the EXIT_FASTPATH_REENTER_GUEST
fastpath as well.

Tested-by: Haiwei Li <lihaiwei@...cent.com>
Cc: Haiwei Li <lihaiwei@...cent.com>
Suggested-by: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Wanpeng Li <wanpengli@...cent.com>
Message-Id: <1588055009-12677-6-git-send-email-wanpengli@...cent.com>
Signed-off-by: Paolo Bonzini <pbonzini@...hat.com>
---
 arch/x86/kvm/vmx/vmx.c | 4 +++-
 virt/kvm/kvm_main.c    | 1 +
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 215ae9682da1..b980481436e9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3928,7 +3928,8 @@ 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))
+	if (vcpu != kvm_get_running_vcpu() &&
+	    !kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
 
 	return 0;
@@ -6803,6 +6804,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 			 * but it would incur the cost of a retpoline for now.
 			 * Revisit once static calls are available.
 			 */
+			vmx_sync_pir_to_irr(vcpu);
 			goto reenter_guest;
 		}
 		exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 825d501df158..7f675d525981 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4638,6 +4638,7 @@ 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.
-- 
2.18.2