@@ -302,12 +302,31 @@ static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu)
*/
static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
{
- ktime_t expires;
+ struct mips_coproc *cop0 = vcpu->arch.cop0;
+ ktime_t expires, threshold;
+ uint32_t count, compare;
int running;
- /* Is the hrtimer pending? */
+ /* Calculate the biased and scaled guest CP0_Count */
+ count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+ compare = kvm_read_c0_guest_compare(cop0);
+
+ /*
+ * Find whether CP0_Count has reached the closest timer interrupt. If
+ * not, we shouldn't inject it.
+ */
+ if ((int32_t)(count - compare) < 0)
+ return count;
+
+ /*
+ * The CP0_Count we're going to return has already reached the closest
+ * timer interrupt. Quickly check if it really is a new interrupt by
+ * looking at whether the interval until the hrtimer expiry time is
+ * less than 1/4 of the timer period.
+ */
expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer);
- if (ktime_compare(now, expires) >= 0) {
+ threshold = ktime_add_ns(now, vcpu->arch.count_period / 4);
+ if (ktime_before(expires, threshold)) {
/*
* Cancel it while we handle it so there's no chance of
* interference with the timeout handler.
@@ -329,8 +348,7 @@ static uint32_t kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
}
}
- /* Return the biased and scaled guest CP0_Count */
- return vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
+ return count;
}
/**
There's a particularly narrow and subtle race condition when the software emulated guest timer is frozen which can allow a guest timer interrupt to be missed. This happens due to the hrtimer expiry being inexact, so very occasionally the freeze time will be after the moment when the emulated CP0_Count transitions to the same value as CP0_Compare (so an IRQ should be generated), but before the moment when the hrtimer is due to expire (so no IRQ is generated). The IRQ won't be generated when the timer is resumed either, since the resume CP0_Count will already match CP0_Compare. With VZ guests in particular this is far more likely to happen, since the soft timer may be frozen frequently in order to restore the timer state to the hardware guest timer. This happens after 5-10 hours of guest soak testing, resulting in an overflow in guest kernel timekeeping calculations, hanging the guest. A more focussed test case to intentionally hit the race (with the help of a new hypcall to cause the timer state to migrated between hardware & software) hits the condition fairly reliably within around 30 seconds. Instead of relying purely on the inexact hrtimer expiry to determine whether an IRQ should be generated, read the guest CP0_Compare and directly check whether the freeze time is before or after it. Only if CP0_Count is on or after CP0_Compare do we check the hrtimer expiry to determine whether the last IRQ has already been generated (which will have pushed back the expiry by one timer period). Fixes: e30492bbe95a ("MIPS: KVM: Rewrite count/compare timer emulation") Signed-off-by: James Hogan <james.hogan@imgtec.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: "Radim Kr?má?" <rkrcmar@redhat.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: linux-mips@linux-mips.org Cc: kvm@vger.kernel.org Cc: <stable@vger.kernel.org> # 3.16.x- --- arch/mips/kvm/emulate.c | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-)