linux-kernel - [PATCH v2 4/4] KVM: LAPIC: Optimize timer latency further

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: <1557893514-5815-5-git-send-email-wanpengli@tencent.com>
Date:   Wed, 15 May 2019 12:11:54 +0800
From:   Wanpeng Li <kernellwp@...il.com>
To:     linux-kernel@...r.kernel.org, kvm@...r.kernel.org
Cc:     Paolo Bonzini <pbonzini@...hat.com>,
        Radim Krčmář <rkrcmar@...hat.com>,
        Sean Christopherson <sean.j.christopherson@...el.com>,
        Liran Alon <liran.alon@...cle.com>
Subject: [PATCH v2 4/4] KVM: LAPIC: Optimize timer latency further

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

Advance lapic timer tries to hidden the hypervisor overhead between the 
host emulated timer fires and the guest awares the timer is fired. However, 
it just hidden the time between apic_timer_fn/handle_preemption_timer -> 
wait_lapic_expire, instead of the real position of vmentry which is 
mentioned in the orignial commit d0659d946be0 ("KVM: x86: add option to 
advance tscdeadline hrtimer expiration"). There is 700+ cpu cycles between 
the end of wait_lapic_expire and before world switch on my haswell desktop, 
it will be 2400+ cycles if vmentry_l1d_flush is tuned to always. 

This patch tries to narrow the last gap(wait_lapic_expire -> world switch), 
it takes the real overhead time between apic_timer_fn/handle_preemption_timer
and before world switch into consideration when adaptively tuning timer 
advancement. The patch can reduce 40% latency (~1600+ cycles to ~1000+ cycles 
on a haswell desktop) for kvm-unit-tests/tscdeadline_latency when testing 
busy waits.

Cc: Paolo Bonzini <pbonzini@...hat.com>
Cc: Radim Krčmář <rkrcmar@...hat.com>
Cc: Sean Christopherson <sean.j.christopherson@...el.com>
Cc: Liran Alon <liran.alon@...cle.com>
Signed-off-by: Wanpeng Li <wanpengli@...cent.com>
---
 arch/x86/kvm/lapic.c   | 3 ++-
 arch/x86/kvm/lapic.h   | 2 +-
 arch/x86/kvm/svm.c     | 4 ++++
 arch/x86/kvm/vmx/vmx.c | 4 ++++
 arch/x86/kvm/x86.c     | 3 ---
 5 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index af38ece..63513de 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1531,7 +1531,7 @@ static inline void adaptive_tune_timer_advancement(struct kvm_vcpu *vcpu,
 	apic->lapic_timer.timer_advance_ns = timer_advance_ns;
 }
 
-void wait_lapic_expire(struct kvm_vcpu *vcpu)
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u64 guest_tsc, tsc_deadline;
@@ -1553,6 +1553,7 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 	if (unlikely(!apic->lapic_timer.timer_advance_adjust_done))
 		adaptive_tune_timer_advancement(vcpu, apic->lapic_timer.advance_expire_delta);
 }
+EXPORT_SYMBOL_GPL(kvm_wait_lapic_expire);
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
 {
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 3e72a25..f974a3d 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -220,7 +220,7 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu)
 
 bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector);
 
-void wait_lapic_expire(struct kvm_vcpu *vcpu);
+void kvm_wait_lapic_expire(struct kvm_vcpu *vcpu);
 
 bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
 			struct kvm_vcpu **dest_vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 406b558..740fb3f 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -5646,6 +5646,10 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	 */
 	x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
 
+	if (lapic_in_kernel(vcpu) &&
+		vcpu->arch.apic->lapic_timer.timer_advance_ns)
+		kvm_wait_lapic_expire(vcpu);
+
 	local_irq_enable();
 
 	asm volatile (
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9663d41..1c49946 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6437,6 +6437,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.cr2 != read_cr2())
 		write_cr2(vcpu->arch.cr2);
 
+	if (lapic_in_kernel(vcpu) &&
+		vcpu->arch.apic->lapic_timer.timer_advance_ns)
+		kvm_wait_lapic_expire(vcpu);
+
 	vmx->fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
 				   vmx->loaded_vmcs->launched);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1d89cb9..0eb9549 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7894,9 +7894,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
-	if (lapic_in_kernel(vcpu) &&
-	    vcpu->arch.apic->lapic_timer.timer_advance_ns)
-		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
 	fpregs_assert_state_consistent();
-- 
2.7.4