[S390] s390-kvm: leave sie context on work. Removes preemption requirement
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
This patch fixes a bug with cpu bound guest on kvm-s390. Sometimes it
was impossible to deliver a signal to a spinning guest. We used
preemption as a circumvention. The preemption notifiers called
vcpu_load, which checked for pending signals and triggered a host
intercept. But even with preemption, a sigkill was not delivered
immediately.
This patch changes the low level host interrupt handler to check for the
SIE instruction, if TIF_WORK is set. In that case we change the
instruction pointer of the return PSW to rerun the vcpu_run loop. The kvm
code sees an intercept reason 0 if that happens. This patch adds accounting
for these types of intercept as well.
The advantages:
- works with and without preemption
- signals are delivered immediately
- much better host latencies without preemption
Acked-by: Carsten Otte <cotte@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 349581a..47a0b64 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -105,6 +105,9 @@
static int handle_noop(struct kvm_vcpu *vcpu)
{
switch (vcpu->arch.sie_block->icptcode) {
+ case 0x0:
+ vcpu->stat.exit_null++;
+ break;
case 0x10:
vcpu->stat.exit_external_request++;
break;