KVM: s390: rework broken SIGP STOP interrupt handling

A VCPU might never stop if it intercepts (for whatever reason) between
"fake interrupt delivery" and execution of the stop function.

Heart of the problem is that SIGP STOP is an interrupt that has to be
processed on every SIE entry until the VCPU finally executes the stop
function.

This problem was made apparent by commit d1884be0f3e8fd8f41a6e5a720b
(KVM: s390: allow only one SIGP STOP (AND STORE STATUS) at a time).
With the old code, the guest could (incorrectly) inject SIGP STOPs
multiple times. The bug of losing a sigp stop exists in KVM before
d1884be0f3, but it was hidden by Linux guests doing a sigp stop loop.
The new code (rightfully) returns CC=2 and does not queue a new
interrupt.

This patch is a simple fix of the problem. Longterm we are going to
rework that code - e.g. get rid of the action bits and so on.

Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
[some additional patch description]

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 1be3d8da49e91d6fb16807e459a8867a9d7be879..92528a0bdda6c0063de80e4a5d22fdefef7edd25 100644 (file)
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -158,6 +158,9 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
                                               LCTL_CR10 | LCTL_CR11);
                vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT);
        }
+
+       if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP)
+               atomic_set_mask(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
 }
 
 static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)