From 61abdbe0bcc2b32745ab4479cc550f4c1f518ee2 Mon Sep 17 00:00:00 2001 From: Luiz Capitulino Date: Mon, 4 Apr 2016 16:46:07 -0400 Subject: [PATCH] kvm: x86: make lapic hrtimer pinned When a vCPU runs on a nohz_full core, the hrtimer used by the lapic emulation code can be migrated to another core. When this happens, it's possible to observe milisecond latency when delivering timer IRQs to KVM guests. The huge latency is mainly due to the fact that apic_timer_fn() expects to run during a kvm exit. It sets KVM_REQ_PENDING_TIMER and let it be handled on kvm entry. However, if the timer fires on a different core, we have to wait until the next kvm exit for the guest to see KVM_REQ_PENDING_TIMER set. This problem became visible after commit 9642d18ee. This commit changed the timer migration code to always attempt to migrate timers away from nohz_full cores. While it's discussable if this is correct/desirable (I don't think it is), it's clear that the lapic emulation code has a requirement on firing the hrtimer in the same core where it was started. This is achieved by making the hrtimer pinned. Lastly, note that KVM has code to migrate timers when a vCPU is scheduled to run in different core. However, this forced migration may fail. When this happens, we can have the same problem. If we want 100% correctness, we'll have to modify apic_timer_fn() to cause a kvm exit when it runs on a different core than the vCPU. Not sure if this is possible. Here's a reproducer for the issue being fixed: 1. Set all cores but core0 to be nohz_full cores 2. Start a guest with a single vCPU 3. Trace apic_timer_fn() and kvm_inject_apic_timer_irqs() You'll see that apic_timer_fn() will run in core0 while kvm_inject_apic_timer_irqs() runs in a different core. If you get both on core0, try running a program that takes 100% of the CPU and pin it to core0 to force the vCPU out. Signed-off-by: Luiz Capitulino Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 443d2a57ad3d..1a2da0e5a373 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1369,7 +1369,7 @@ static void start_apic_timer(struct kvm_lapic *apic) hrtimer_start(&apic->lapic_timer.timer, ktime_add_ns(now, apic->lapic_timer.period), - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_PINNED); apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016" PRIx64 ", " @@ -1402,7 +1402,7 @@ static void start_apic_timer(struct kvm_lapic *apic) expire = ktime_add_ns(now, ns); expire = ktime_sub_ns(expire, lapic_timer_advance_ns); hrtimer_start(&apic->lapic_timer.timer, - expire, HRTIMER_MODE_ABS); + expire, HRTIMER_MODE_ABS_PINNED); } else apic_timer_expired(apic); @@ -1868,7 +1868,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu) apic->vcpu = vcpu; hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS); + HRTIMER_MODE_ABS_PINNED); apic->lapic_timer.timer.function = apic_timer_fn; /* @@ -2003,7 +2003,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) timer = &vcpu->arch.apic->lapic_timer.timer; if (hrtimer_cancel(timer)) - hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); } /* -- 2.34.1