KVM: s390: guest support for topology function

We report a topology change to the guest for any CPU hotplug.

The reporting to the guest is done using the Multiprocessor
Topology-Change-Report (MTCR) bit of the utility entry in the guest's
SCA which will be cleared during the interpretation of PTF.

On every vCPU creation we set the MCTR bit to let the guest know the
next time it uses the PTF with command 2 instruction that the
topology changed and that it should use the STSI(15.1.x) instruction
to get the topology details.

STSI(15.1.x) gives information on the CPU configuration topology.
Let's accept the interception of STSI with the function code 15 and
let the userland part of the hypervisor handle it when userland
supports the CPU Topology facility.

Signed-off-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: Nico Boehr <nrb@linux.ibm.com>
Reviewed-by: Janis Schoetterl-Glausch <scgl@linux.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20220714101824.101601-2-pmorel@linux.ibm.com
Message-Id: <20220714101824.101601-2-pmorel@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>

3 files changed, 55 insertions, 4 deletions

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 5b77c43fbb01..5d18b66a08c9 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1763,6 +1763,32 @@ static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
 	return ret;
 }
 
+/**
+ * kvm_s390_update_topology_change_report - update CPU topology change report
+ * @kvm: guest KVM description
+ * @val: set or clear the MTCR bit
+ *
+ * Updates the Multiprocessor Topology-Change-Report bit to signal
+ * the guest with a topology change.
+ * This is only relevant if the topology facility is present.
+ *
+ * The SCA version, bsca or esca, doesn't matter as offset is the same.
+ */
+static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val)
+{
+	union sca_utility new, old;
+	struct bsca_block *sca;
+
+	read_lock(&kvm->arch.sca_lock);
+	sca = kvm->arch.sca;
+	do {
+		old = READ_ONCE(sca->utility);
+		new = old;
+		new.mtcr = val;
+	} while (cmpxchg(&sca->utility.val, old.val, new.val) != old.val);
+	read_unlock(&kvm->arch.sca_lock);
+}
+
 static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	int ret;
@@ -3172,6 +3198,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 	kvm_clear_async_pf_completion_queue(vcpu);
 	if (!kvm_is_ucontrol(vcpu->kvm))
 		sca_del_vcpu(vcpu);
+	kvm_s390_update_topology_change_report(vcpu->kvm, 1);
 
 	if (kvm_is_ucontrol(vcpu->kvm))
 		gmap_remove(vcpu->arch.gmap);
@@ -3574,6 +3601,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->ecb |= ECB_HOSTPROTINT;
 	if (test_kvm_facility(vcpu->kvm, 9))
 		vcpu->arch.sie_block->ecb |= ECB_SRSI;
+	if (test_kvm_facility(vcpu->kvm, 11))
+		vcpu->arch.sie_block->ecb |= ECB_PTF;
 	if (test_kvm_facility(vcpu->kvm, 73))
 		vcpu->arch.sie_block->ecb |= ECB_TE;
 	if (!kvm_is_ucontrol(vcpu->kvm))
@@ -3707,6 +3736,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	rc = kvm_s390_vcpu_setup(vcpu);
 	if (rc)
 		goto out_ucontrol_uninit;
+
+	kvm_s390_update_topology_change_report(vcpu->kvm, 1);
 	return 0;
 
 out_ucontrol_uninit:
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 12c464c7cddf..3335fa09b6f1 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -873,10 +873,18 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
-	if (fc > 3) {
-		kvm_s390_set_psw_cc(vcpu, 3);
-		return 0;
-	}
+	/* Bailout forbidden function codes */
+	if (fc > 3 && fc != 15)
+		goto out_no_data;
+
+	/*
+	 * fc 15 is provided only with
+	 *   - PTF/CPU topology support through facility 15
+	 *   - KVM_CAP_S390_USER_STSI
+	 */
+	if (fc == 15 && (!test_kvm_facility(vcpu->kvm, 11) ||
+			 !vcpu->kvm->arch.user_stsi))
+		goto out_no_data;
 
 	if (vcpu->run->s.regs.gprs[0] & 0x0fffff00
 	    || vcpu->run->s.regs.gprs[1] & 0xffff0000)
@@ -910,6 +918,10 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 			goto out_no_data;
 		handle_stsi_3_2_2(vcpu, (void *) mem);
 		break;
+	case 15: /* fc 15 is fully handled in userspace */
+		insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2);
+		trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
+		return -EREMOTE;
 	}
 	if (kvm_s390_pv_cpu_is_protected(vcpu)) {
 		memcpy((void *)sida_origin(vcpu->arch.sie_block), (void *)mem,
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index dada78b92691..94138f8f0c1c 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -503,6 +503,14 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	/* Host-protection-interruption introduced with ESOP */
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
 		scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT;
+	/*
+	 * CPU Topology
+	 * This facility only uses the utility field of the SCA and none of
+	 * the cpu entries that are problematic with the other interpretation
+	 * facilities so we can pass it through
+	 */
+	if (test_kvm_facility(vcpu->kvm, 11))
+		scb_s->ecb |= scb_o->ecb & ECB_PTF;
 	/* transactional execution */
 	if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) {
 		/* remap the prefix is tx is toggled on */