Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Wanpeng Li <kernellwp@gmail.com>
To:     linux-kernel@vger.kernel.org, kvm@vger.kernel.org
Cc:     Paolo Bonzini <pbonzini@redhat.com>,
        =?UTF-8?q?Radim=20Kr=C4=8Dm=C3=A1=C5=99?= <rkrcmar@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>
Subject: [PATCH v4] KVM: LAPIC: Tune lapic_timer_advance_ns smoothly
Date:   Mon, 16 Sep 2019 16:39:59 +0800
Message-Id: <1568623199-5294-1-git-send-email-wanpengli@tencent.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Wanpeng Li <wanpengli@tencent.com>

Filter out drastic fluctuation and random fluctuation, remove
timer_advance_adjust_done altogether, the adjustment would be 
continuous.

Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 arch/x86/kvm/lapic.c | 26 ++++++++++++--------------
 arch/x86/kvm/lapic.h |  1 -
 arch/x86/kvm/x86.c   |  2 +-
 arch/x86/kvm/x86.h   |  1 +
 4 files changed, 14 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dbbe478..2585b86 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -69,6 +69,7 @@
 #define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000
 /* step-by-step approximation to mitigate fluctuation */
 #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
+#define LAPIC_TIMER_ADVANCE_FILTER 5000
 
 static inline int apic_test_vector(int vec, void *bitmap)
 {
@@ -1482,29 +1483,28 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu,
 					      s64 advance_expire_delta)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns;
-	u64 ns;
+	u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns, ns;
+
+	if (abs(advance_expire_delta) > LAPIC_TIMER_ADVANCE_FILTER ||
+		abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_DONE) {
+		/* filter out random fluctuations */
+		return;
+	}
 
 	/* too early */
 	if (advance_expire_delta < 0) {
 		ns = -advance_expire_delta * 1000000ULL;
 		do_div(ns, vcpu->arch.virtual_tsc_khz);
-		timer_advance_ns -= min((u32)ns,
-			timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+		timer_advance_ns -= ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP;
 	} else {
 	/* too late */
 		ns = advance_expire_delta * 1000000ULL;
 		do_div(ns, vcpu->arch.virtual_tsc_khz);
-		timer_advance_ns += min((u32)ns,
-			timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+		timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP;
 	}
 
-	if (abs(advance_expire_delta) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
-		apic->lapic_timer.timer_advance_adjust_done = true;
-	if (unlikely(timer_advance_ns > 5000)) {
+	if (unlikely(timer_advance_ns > 5000))
 		timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
-		apic->lapic_timer.timer_advance_adjust_done = false;
-	}
 	apic->lapic_timer.timer_advance_ns = timer_advance_ns;
 }
 
@@ -1524,7 +1524,7 @@ static void __kvm_wait_lapic_expire(struct kvm_vcpu *vcpu)
 	if (guest_tsc < tsc_deadline)
 		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
 
-	if (unlikely(!apic->lapic_timer.timer_advance_adjust_done))
+	if (lapic_timer_advance_ns == -1)
 		adjust_lapic_timer_advance(vcpu, apic->lapic_timer.advance_expire_delta);
 }
 
@@ -2302,10 +2302,8 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 	apic->lapic_timer.timer.function = apic_timer_fn;
 	if (timer_advance_ns == -1) {
 		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
-		apic->lapic_timer.timer_advance_adjust_done = false;
 	} else {
 		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
-		apic->lapic_timer.timer_advance_adjust_done = true;
 	}
 
 
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 50053d2..2aad7e2 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -35,7 +35,6 @@ struct kvm_timer {
 	s64 advance_expire_delta;
 	atomic_t pending;			/* accumulated triggered timers */
 	bool hv_timer_in_use;
-	bool timer_advance_adjust_done;
 };
 
 struct kvm_lapic {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 83288ba..bb4574c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -141,7 +141,7 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
  * advancement entirely.  Any other value is used as-is and disables adaptive
  * tuning, i.e. allows priveleged userspace to set an exact advancement time.
  */
-static int __read_mostly lapic_timer_advance_ns = -1;
+int __read_mostly lapic_timer_advance_ns = -1;
 module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);
 
 static bool __read_mostly vector_hashing = true;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index b5274e2..1bf2d82 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -301,6 +301,7 @@ extern unsigned int min_timer_period_us;
 
 extern bool enable_vmware_backdoor;
 
+extern int lapic_timer_advance_ns;
 extern int pi_inject_timer;
 
 extern struct static_key kvm_no_apic_vcpu;
-- 
2.7.4