KVM: s390: Clarify SIGP orders versus STOP/RESTART

commit 812de04 upstream.

With KVM_CAP_S390_USER_SIGP, there are only five Signal Processor
orders (CONDITIONAL EMERGENCY SIGNAL, EMERGENCY SIGNAL, EXTERNAL CALL,
SENSE, and SENSE RUNNING STATUS) which are intended for frequent use
and thus are processed in-kernel. The remainder are sent to userspace
with the KVM_CAP_S390_USER_SIGP capability. Of those, three orders
(RESTART, STOP, and STOP AND STORE STATUS) have the potential to
inject work back into the kernel, and thus are asynchronous.

Let's look for those pending IRQs when processing one of the in-kernel
SIGP orders, and return BUSY (CC2) if one is in process. This is in
agreement with the Principles of Operation, which states that only one
order can be "active" on a CPU at a time.

Cc: stable@vger.kernel.org
Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Eric Farman <farman@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Link: https://lore.kernel.org/r/20211213210550.856213-2-farman@linux.ibm.com
[borntraeger@linux.ibm.com: add stable tag]
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: efarman

arch/s390/kvm/interrupt.c

@@ -2115,6 +2115,13 @@ int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu)
 	return test_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs);
 }
 
+int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+
+	return test_bit(IRQ_PEND_RESTART, &li->pending_irqs);
+}
+
 void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu)
 {
 	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;

arch/s390/kvm/kvm-s390.c

@@ -4588,10 +4588,15 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+	/*
+	 * Set the VCPU to STOPPED and THEN clear the interrupt flag,
+	 * now that the SIGP STOP and SIGP STOP AND STORE STATUS orders
+	 * have been fully processed. This will ensure that the VCPU
+	 * is kept BUSY if another VCPU is inquiring with SIGP SENSE.
+	 */
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	kvm_s390_clear_stop_irq(vcpu);
 
-	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {

arch/s390/kvm/kvm-s390.h

@@ -418,6 +418,7 @@ void kvm_s390_destroy_adapters(struct kvm *kvm);
 int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu);
 extern struct kvm_device_ops kvm_flic_ops;
 int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu);
+int kvm_s390_is_restart_irq_pending(struct kvm_vcpu *vcpu);
 void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu);
 int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
 			   void __user *buf, int len);

arch/s390/kvm/sigp.c

@@ -288,6 +288,34 @@ static int handle_sigp_dst(struct kvm_vcpu *vcpu, u8 order_code,
 	if (!dst_vcpu)
 		return SIGP_CC_NOT_OPERATIONAL;
 
+	/*
+	 * SIGP RESTART, SIGP STOP, and SIGP STOP AND STORE STATUS orders
+	 * are processed asynchronously. Until the affected VCPU finishes
+	 * its work and calls back into KVM to clear the (RESTART or STOP)
+	 * interrupt, we need to return any new non-reset orders "busy".
+	 *
+	 * This is important because a single VCPU could issue:
+	 *  1) SIGP STOP $DESTINATION
+	 *  2) SIGP SENSE $DESTINATION
+	 *
+	 * If the SIGP SENSE would not be rejected as "busy", it could
+	 * return an incorrect answer as to whether the VCPU is STOPPED
+	 * or OPERATING.
+	 */
+	if (order_code != SIGP_INITIAL_CPU_RESET &&
+	    order_code != SIGP_CPU_RESET) {
+		/*
+		 * Lockless check. Both SIGP STOP and SIGP (RE)START
+		 * properly synchronize everything while processing
+		 * their orders, while the guest cannot observe a
+		 * difference when issuing other orders from two
+		 * different VCPUs.
+		 */
+		if (kvm_s390_is_stop_irq_pending(dst_vcpu) ||
+		    kvm_s390_is_restart_irq_pending(dst_vcpu))
+			return SIGP_CC_BUSY;
+	}
+
 	switch (order_code) {
 	case SIGP_SENSE:
 		vcpu->stat.instruction_sigp_sense++;