KVM: lapic: mark LAPIC timer handler as irqsafe

Since lapic timer handler only wakes up a simple waitqueue,
it can be executed from hardirq context.

Also handle the case where hrtimer_start_expires fails due to -ETIME,
by injecting the interrupt to the guest immediately.

Reduces average cyclictest latency by 3us.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 8ee4aa7f567d6e244e5982f89afde38756bb3e9b..3feaefa5751e0b8d0c7762ee92f0704c5c3a6c5d 100644 (file)
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1141,8 +1141,36 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
                __delay(tsc_deadline - guest_tsc);
 }
 
+static enum hrtimer_restart apic_timer_fn(struct hrtimer *data);
+
+static void __apic_timer_expired(struct hrtimer *data)
+{
+       int ret, i = 0;
+       enum hrtimer_restart r;
+       struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+
+       r = apic_timer_fn(data);
+
+       if (r == HRTIMER_RESTART) {
+               do {
+                       ret = hrtimer_start_expires(data, HRTIMER_MODE_ABS);
+                       if (ret == -ETIME)
+                               hrtimer_add_expires_ns(&ktimer->timer,
+                                                      ktimer->period);
+                       i++;
+               } while (ret == -ETIME && i < 10);
+
+               if (ret == -ETIME) {
+                       printk_once(KERN_ERR "%s: failed to reprogram timer\n",
+                                   __func__);
+                       WARN_ON_ONCE(1);
+               }
+       }
+}
+
 static void start_apic_timer(struct kvm_lapic *apic)
 {
+       int ret;
        ktime_t now;
 
        atomic_set(&apic->lapic_timer.pending, 0);
@@ -1173,9 +1201,11 @@ static void start_apic_timer(struct kvm_lapic *apic)
                        }
                }
 
-               hrtimer_start(&apic->lapic_timer.timer,
+               ret = hrtimer_start(&apic->lapic_timer.timer,
                              ktime_add_ns(now, apic->lapic_timer.period),
                              HRTIMER_MODE_ABS);
+               if (ret == -ETIME)
+                       __apic_timer_expired(&apic->lapic_timer.timer);
 
                apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
                           PRIx64 ", "
@@ -1207,8 +1237,10 @@ static void start_apic_timer(struct kvm_lapic *apic)
                        do_div(ns, this_tsc_khz);
                        expire = ktime_add_ns(now, ns);
                        expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
-                       hrtimer_start(&apic->lapic_timer.timer,
+                       ret = hrtimer_start(&apic->lapic_timer.timer,
                                      expire, HRTIMER_MODE_ABS);
+                       if (ret == -ETIME)
+                               __apic_timer_expired(&apic->lapic_timer.timer);
                } else
                        apic_timer_expired(apic);
 
@@ -1683,6 +1715,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
        hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
                     HRTIMER_MODE_ABS);
        apic->lapic_timer.timer.function = apic_timer_fn;
+       apic->lapic_timer.timer.irqsafe = 1;
 
        /*
         * APIC is created enabled. This will prevent kvm_lapic_set_base from
@@ -1810,7 +1843,8 @@ 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);
+               if (hrtimer_start_expires(timer, HRTIMER_MODE_ABS) == -ETIME)
+                       __apic_timer_expired(timer);
 }
 
 /*