KVM: x86: fix LAPIC pending count calculation

Simplify LAPIC TMCCT calculation by using hrtimer provided
function to query remaining time until expiration.

Fixes host hang with nested ESX.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

6 files changed, 15 insertions, 63 deletions

diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index c019b8edcdb7..cf17ed52f6fb 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -87,13 +87,6 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs);
 
-void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
-        kvm_apic_timer_intr_post(vcpu, vec);
-        /* TODO: PIT, RTC etc. */
-}
-EXPORT_SYMBOL_GPL(kvm_timer_intr_post);
-
 void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
 {
         __kvm_migrate_apic_timer(vcpu);
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 2bf32a03ceec..82579ee538d0 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -89,7 +89,6 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
 
 void kvm_pic_reset(struct kvm_kpic_state *s);
 
-void kvm_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index afac68c0815c..f0b67f2cdd69 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -35,6 +35,12 @@
 #include "kvm_cache_regs.h"
 #include "irq.h"
 
+#ifndef CONFIG_X86_64
+#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
+#else
+#define mod_64(x, y) ((x) % (y))
+#endif
+
 #define PRId64 "d"
 #define PRIx64 "llx"
 #define PRIu64 "u"
@@ -511,52 +517,22 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 
 static u32 apic_get_tmcct(struct kvm_lapic *apic)
 {
-        u64 counter_passed;
-        ktime_t passed, now;
+        ktime_t remaining;
+        s64 ns;
         u32 tmcct;
 
         ASSERT(apic != NULL);
 
-        now = apic->timer.dev.base->get_time();
-        tmcct = apic_get_reg(apic, APIC_TMICT);
-
         /* if initial count is 0, current count should also be 0 */
-        if (tmcct == 0)
+        if (apic_get_reg(apic, APIC_TMICT) == 0)
                 return 0;
 
-        if (unlikely(ktime_to_ns(now) <=
-                ktime_to_ns(apic->timer.last_update))) {
-                /* Wrap around */
-                passed = ktime_add(( {
-                                    (ktime_t) {
-                                    .tv64 = KTIME_MAX -
-                                    (apic->timer.last_update).tv64}; }
-                                   ), now);
-                apic_debug("time elapsed\n");
-        } else
-                passed = ktime_sub(now, apic->timer.last_update);
-
-        counter_passed = div64_u64(ktime_to_ns(passed),
-                                   (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
-
-        if (counter_passed > tmcct) {
-                if (unlikely(!apic_lvtt_period(apic))) {
-                        /* one-shot timers stick at 0 until reset */
-                        tmcct = 0;
-                } else {
-                        /*
-                         * periodic timers reset to APIC_TMICT when they
-                         * hit 0. The while loop simulates this happening N
-                         * times. (counter_passed %= tmcct) would also work,
-                         * but might be slower or not work on 32-bit??
-                         */
-                        while (counter_passed > tmcct)
-                                counter_passed -= tmcct;
-                        tmcct -= counter_passed;
-                }
-        } else {
-                tmcct -= counter_passed;
-        }
+        remaining = hrtimer_expires_remaining(&apic->timer.dev);
+        if (ktime_to_ns(remaining) < 0)
+                remaining = ktime_set(0, 0);
+
+        ns = mod_64(ktime_to_ns(remaining), apic->timer.period);
+        tmcct = div64_u64(ns, (APIC_BUS_CYCLE_NS * apic->timer.divide_count));
 
         return tmcct;
 }
@@ -653,8 +629,6 @@ static void start_apic_timer(struct kvm_lapic *apic)
 {
         ktime_t now = apic->timer.dev.base->get_time();
 
-        apic->timer.last_update = now;
-
         apic->timer.period = apic_get_reg(apic, APIC_TMICT) *
                     APIC_BUS_CYCLE_NS * apic->timer.divide_count;
         atomic_set(&apic->timer.pending, 0);
@@ -1110,16 +1084,6 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
         }
 }
 
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec)
-{
-        struct kvm_lapic *apic = vcpu->arch.apic;
-
-        if (apic && apic_lvt_vector(apic, APIC_LVTT) == vec)
-                apic->timer.last_update = ktime_add_ns(
-                                apic->timer.last_update,
-                                apic->timer.period);
-}
-
 int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 {
         int vector = kvm_apic_has_interrupt(vcpu);
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 81858881287e..45ab6ee71209 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -12,7 +12,6 @@ struct kvm_lapic {
                 atomic_t pending;
                 s64 period;     /* unit: ns */
                 u32 divide_count;
-                ktime_t last_update;
                 struct hrtimer dev;
         } timer;
         struct kvm_vcpu *vcpu;
@@ -42,7 +41,6 @@ void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
 void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
 int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
-void kvm_apic_timer_intr_post(struct kvm_vcpu *vcpu, int vec);
 
 void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1452851ae258..a9e769e4e251 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1600,7 +1600,6 @@ static void svm_intr_assist(struct kvm_vcpu *vcpu)
         /* Okay, we can deliver the interrupt: grab it and update PIC state. */
         intr_vector = kvm_cpu_get_interrupt(vcpu);
         svm_inject_irq(svm, intr_vector);
-        kvm_timer_intr_post(vcpu, intr_vector);
 out:
         update_cr8_intercept(vcpu);
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 07491c9c6ed0..b1fe1422afb1 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3285,7 +3285,6 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
         }
         if (vcpu->arch.interrupt.pending) {
                 vmx_inject_irq(vcpu, vcpu->arch.interrupt.nr);
-                kvm_timer_intr_post(vcpu, vcpu->arch.interrupt.nr);
                 if (kvm_cpu_has_interrupt(vcpu))
                         enable_irq_window(vcpu);
         }