Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Pierre Morel <pmorel@linux.ibm.com>
To:     kvm@vger.kernel.org
Cc:     linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org,
        borntraeger@de.ibm.com, frankja@linux.ibm.com, cohuck@redhat.com,
        david@redhat.com, thuth@redhat.com, imbrenda@linux.ibm.com,
        hca@linux.ibm.com, gor@linux.ibm.com, pmorel@linux.ibm.com,
        wintera@linux.ibm.com, seiden@linux.ibm.com, nrb@linux.ibm.com
Subject: [PATCH v7 1/1] s390x: KVM: guest support for topology function
Date:   Thu, 17 Feb 2022 10:59:23 +0100
Message-Id: <20220217095923.114489-2-pmorel@linux.ibm.com>
In-Reply-To: <20220217095923.114489-1-pmorel@linux.ibm.com>
References: <20220217095923.114489-1-pmorel@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

We let the userland hypervisor know if the machine support the CPU
topology facility using a new KVM capability: KVM_CAP_S390_CPU_TOPOLOGY.

The PTF instruction will report a topology change if there is any change
with a previous STSI_15_1_2 SYSIB.
Changes inside a STSI_15_1_2 SYSIB occur if CPU bits are set or clear
inside the CPU Topology List Entry CPU mask field, which happens with
changes in CPU polarization, dedication, CPU types and adding or
removing CPUs in a socket.

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

To check if the topology has been modified we use a new field of the
arch vCPU to save the previous real CPU ID at the end of a schedule
and verify on next schedule that the CPU used is in the same socket.
We do not report polarization, CPU Type or dedication change.

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
support the CPU Topology facility.

Signed-off-by: Pierre Morel <pmorel@linux.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.ibm.com>
---
 Documentation/virt/kvm/api.rst   | 16 +++++++++++
 arch/s390/include/asm/kvm_host.h | 12 ++++++--
 arch/s390/kvm/kvm-s390.c         | 48 +++++++++++++++++++++++++++++++-
 arch/s390/kvm/kvm-s390.h         | 25 +++++++++++++++++
 arch/s390/kvm/priv.c             | 14 +++++++---
 arch/s390/kvm/vsie.c             |  3 ++
 include/uapi/linux/kvm.h         |  1 +
 7 files changed, 111 insertions(+), 8 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index a4267104db50..8b8e8b5758e0 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -7561,3 +7561,19 @@ The argument to KVM_ENABLE_CAP is also a bitmask, and must be a subset
 of the result of KVM_CHECK_EXTENSION.  KVM will forward to userspace
 the hypercalls whose corresponding bit is in the argument, and return
 ENOSYS for the others.
+
+8.17 KVM_CAP_S390_CPU_TOPOLOGY
+------------------------------
+
+:Capability: KVM_CAP_S390_CPU_TOPOLOGY
+:Architectures: s390
+:Type: vm
+
+This capability indicates that kvm will provide the S390 CPU Topology facility
+which consist of the interpretation of the PTF instruction for the Function
+Code 2 along with interception and forwarding of both the PTF instruction
+with Function Codes 0 or 1 and the STSI(15,1,x) instruction to the userland
+hypervisor.
+
+The stfle facility 11, CPU Topology facility, should not be provided to the
+guest without this capability.
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index a22c9266ea05..c7d5720d6aec 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -95,15 +95,19 @@ struct bsca_block {
 	union ipte_control ipte_control;
 	__u64	reserved[5];
 	__u64	mcn;
-	__u64	reserved2;
+#define ESCA_UTILITY_MTCR	0x8000
+	__u16	utility;
+	__u8	reserved2[6];
 	struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS];
 };
 
 struct esca_block {
 	union ipte_control ipte_control;
-	__u64   reserved1[7];
+	__u64   reserved1[6];
+	__u16	utility;
+	__u8	reserved2[6];
 	__u64   mcn[4];
-	__u64   reserved2[20];
+	__u64   reserved3[20];
 	struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS];
 };
 
@@ -247,6 +251,7 @@ struct kvm_s390_sie_block {
 #define ECB_SPECI	0x08
 #define ECB_SRSI	0x04
 #define ECB_HOSTPROTINT	0x02
+#define ECB_PTF		0x01
 	__u8	ecb;			/* 0x0061 */
 #define ECB2_CMMA	0x80
 #define ECB2_IEP	0x20
@@ -748,6 +753,7 @@ struct kvm_vcpu_arch {
 	bool skey_enabled;
 	struct kvm_s390_pv_vcpu pv;
 	union diag318_info diag318_info;
+	int prev_cpu;
 };
 
 struct kvm_vm_stat {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2296b1ff1e02..af7ea8488fa2 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -606,6 +606,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_PROTECTED:
 		r = is_prot_virt_host();
 		break;
+	case KVM_CAP_S390_CPU_TOPOLOGY:
+		r = test_facility(11);
+		break;
 	default:
 		r = 0;
 	}
@@ -817,6 +820,20 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		icpt_operexc_on_all_vcpus(kvm);
 		r = 0;
 		break;
+	case KVM_CAP_S390_CPU_TOPOLOGY:
+		r = -EINVAL;
+		mutex_lock(&kvm->lock);
+		if (kvm->created_vcpus) {
+			r = -EBUSY;
+		} else if (test_facility(11)) {
+			set_kvm_facility(kvm->arch.model.fac_mask, 11);
+			set_kvm_facility(kvm->arch.model.fac_list, 11);
+			r = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CPU TOPOLOGY %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -3043,18 +3060,40 @@ __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
 	return value;
 }
 
-void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+/**
+ * kvm_s390_vcpu_set_mtcr
+ * @vcp: the virtual CPU
+ *
+ * Is only relevant if the topology facility is present.
+ *
+ * Updates the Multiprocessor Topology-Change-Report to signal
+ * the guest with a topology change.
+ */
+static void kvm_s390_vcpu_set_mtcr(struct kvm_vcpu *vcpu)
 {
+	struct esca_block *esca = vcpu->kvm->arch.sca;
+
+	ipte_lock(vcpu);
+	WRITE_ONCE(esca->utility, ESCA_UTILITY_MTCR);
+	ipte_unlock(vcpu);
+}
 
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
 	gmap_enable(vcpu->arch.enabled_gmap);
 	kvm_s390_set_cpuflags(vcpu, CPUSTAT_RUNNING);
 	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
 		__start_cpu_timer_accounting(vcpu);
 	vcpu->cpu = cpu;
+
+	if (kvm_s390_topology_changed(vcpu))
+		kvm_s390_vcpu_set_mtcr(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	/* Remember which CPU was backing the vCPU */
+	vcpu->arch.prev_cpu = vcpu->cpu;
 	vcpu->cpu = -1;
 	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
 		__stop_cpu_timer_accounting(vcpu);
@@ -3174,6 +3213,13 @@ 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;
+
+	/* PTF needs guest facilities to enable interpretation */
+	if (test_kvm_facility(vcpu->kvm, 11))
+		vcpu->arch.sie_block->ecb |= ECB_PTF;
+	/* Indicate this is a new vcpu */
+	vcpu->arch.prev_cpu = S390_KVM_TOPOLOGY_NEW_CPU;
+
 	if (test_kvm_facility(vcpu->kvm, 73))
 		vcpu->arch.sie_block->ecb |= ECB_TE;
 	if (!kvm_is_ucontrol(vcpu->kvm))
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 098831e815e6..af04ffbfd587 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -503,4 +503,29 @@ void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm);
  */
 extern unsigned int diag9c_forwarding_hz;
 
+#define S390_KVM_TOPOLOGY_NEW_CPU -1
+/**
+ * kvm_s390_topology_changed
+ * @vcpu: the virtual CPU
+ *
+ * If the topology facility is present, checks if the CPU toplogy
+ * viewed by the guest changed due to load balancing or CPU hotplug.
+ */
+static inline bool kvm_s390_topology_changed(struct kvm_vcpu *vcpu)
+{
+	if (!test_kvm_facility(vcpu->kvm, 11))
+		return false;
+
+	/* A new vCPU has been hotplugged */
+	if (vcpu->arch.prev_cpu == S390_KVM_TOPOLOGY_NEW_CPU)
+		return true;
+
+	/* The real CPU backing up the vCPU moved to another socket */
+	if (topology_physical_package_id(vcpu->cpu) !=
+	    topology_physical_package_id(vcpu->arch.prev_cpu))
+		return true;
+
+	return false;
+}
+
 #endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 417154b314a6..5ff6be498cbd 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -861,10 +861,12 @@ 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;
-	}
+	if (fc > 3 && fc != 15)
+		goto out_no_data;
+
+	/* fc 15 is provided with PTF/CPU topology support */
+	if (fc == 15 && !test_kvm_facility(vcpu->kvm, 11))
+		goto out_no_data;
 
 	if (vcpu->run->s.regs.gprs[0] & 0x0fffff00
 	    || vcpu->run->s.regs.gprs[1] & 0xffff0000)
@@ -898,6 +900,10 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 			goto out_no_data;
 		handle_stsi_3_2_2(vcpu, (void *) mem);
 		break;
+	case 15:
+		trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
+		insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2);
+		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 acda4b6fc851..da0397cf2cc7 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -503,6 +503,9 @@ 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 */
+	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 */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 5191b57e1562..23e3913992c5 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_GPA_BITS 207
 #define KVM_CAP_XSAVE2 208
 #define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_S390_CPU_TOPOLOGY 210
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
2.27.0