KVM: s390: Multiple Epoch Facility support

Allow for the enablement of MEF and the support for the extended
epoch in SIE and VSIE for the extended guest TOD-Clock.

A new interface is used for getting/setting a guest's extended TOD-Clock
that uses a single ioctl invocation, KVM_S390_VM_TOD_EXT.  Since the
host time is a moving target that might see an epoch switch or STP sync
checks we need an atomic ioctl and cannot use the exisiting two
interfaces. The old method of getting and setting the guest TOD-Clock is
still retained and is used when the old ioctls are called.

Signed-off-by: Collin L. Walling <walling@linux.vnet.ibm.com>
Reviewed-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Reviewed-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Reviewed-by: Jason J. Herne <jjherne@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>

Documentation/virtual/kvm/devices/vm.txt

@@ -176,7 +176,8 @@ Architectures: s390
 
 3.1. ATTRIBUTE: KVM_S390_VM_TOD_HIGH
 
-Allows user space to set/get the TOD clock extension (u8).
+Allows user space to set/get the TOD clock extension (u8) (superseded by
+KVM_S390_VM_TOD_EXT).
 
 Parameters: address of a buffer in user space to store the data (u8) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
@@ -190,6 +191,17 @@ the POP (u64).
 Parameters: address of a buffer in user space to store the data (u64) to
 Returns:    -EFAULT if the given address is not accessible from kernel space
 
+3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
+Allows user space to set/get bits 0-63 of the TOD clock register as defined in
+the POP (u64). If the guest CPU model supports the TOD clock extension (u8), it
+also allows user space to get/set it. If the guest CPU model does not support
+it, it is stored as 0 and not allowed to be set to a value != 0.
+
+Parameters: address of a buffer in user space to store the data
+            (kvm_s390_vm_tod_clock) to
+Returns:    -EFAULT if the given address is not accessible from kernel space
+	    -EINVAL if setting the TOD clock extension to != 0 is not supported
+
 4. GROUP: KVM_S390_VM_CRYPTO
 Architectures: s390
 

arch/s390/include/asm/kvm_host.h

@@ -226,7 +226,9 @@ struct kvm_s390_sie_block {
 #define ECB3_RI  0x01
 	__u8    ecb3;			/* 0x0063 */
 	__u32	scaol;			/* 0x0064 */
-	__u8	reserved68[4];		/* 0x0068 */
+	__u8	reserved68;		/* 0x0068 */
+	__u8    epdx;			/* 0x0069 */
+	__u8    reserved6a[2];		/* 0x006a */
 	__u32	todpr;			/* 0x006c */
 	__u8	reserved70[16];		/* 0x0070 */
 	__u64	mso;			/* 0x0080 */
@@ -265,6 +267,7 @@ struct kvm_s390_sie_block {
 	__u64	cbrlo;			/* 0x01b8 */
 	__u8	reserved1c0[8];		/* 0x01c0 */
 #define ECD_HOSTREGMGMT	0x20000000
+#define ECD_MEF		0x08000000
 	__u32	ecd;			/* 0x01c8 */
 	__u8	reserved1cc[18];	/* 0x01cc */
 	__u64	pp;			/* 0x01de */
@@ -739,6 +742,7 @@ struct kvm_arch{
 	struct kvm_s390_cpu_model model;
 	struct kvm_s390_crypto crypto;
 	struct kvm_s390_vsie vsie;
+	u8 epdx;
 	u64 epoch;
 	struct kvm_s390_migration_state *migration_state;
 	/* subset of available cpu features enabled by user space */

arch/s390/include/uapi/asm/kvm.h

@@ -88,6 +88,12 @@ struct kvm_s390_io_adapter_req {
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1
+#define KVM_S390_VM_TOD_EXT		2
+
+struct kvm_s390_vm_tod_clock {
+	__u8  epoch_idx;
+	__u64 tod;
+};
 
 /* kvm attributes for KVM_S390_VM_CPU_MODEL */
 /* processor related attributes are r/w */

arch/s390/kvm/kvm-s390.c

@@ -130,6 +130,12 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
+struct kvm_s390_tod_clock_ext {
+	__u8 epoch_idx;
+	__u64 tod;
+	__u8 reserved[7];
+} __packed;
+
 /* allow nested virtualization in KVM (if enabled by user space) */
 static int nested;
 module_param(nested, int, S_IRUGO);
@@ -874,6 +880,26 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm,
 	return 0;
 }
 
+static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_tod_clock gtod;
+
+	if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
+		return -EFAULT;
+
+	if (test_kvm_facility(kvm, 139))
+		kvm_s390_set_tod_clock_ext(kvm, &gtod);
+	else if (gtod.epoch_idx == 0)
+		kvm_s390_set_tod_clock(kvm, gtod.tod);
+	else
+		return -EINVAL;
+
+	VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
+		gtod.epoch_idx, gtod.tod);
+
+	return 0;
+}
+
 static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	u8 gtod_high;
@@ -909,6 +935,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 		return -EINVAL;
 
 	switch (attr->attr) {
+	case KVM_S390_VM_TOD_EXT:
+		ret = kvm_s390_set_tod_ext(kvm, attr);
+		break;
 	case KVM_S390_VM_TOD_HIGH:
 		ret = kvm_s390_set_tod_high(kvm, attr);
 		break;
@@ -922,6 +951,43 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 	return ret;
 }
 
+static void kvm_s390_get_tod_clock_ext(struct kvm *kvm,
+					struct kvm_s390_vm_tod_clock *gtod)
+{
+	struct kvm_s390_tod_clock_ext htod;
+
+	preempt_disable();
+
+	get_tod_clock_ext((char *)&htod);
+
+	gtod->tod = htod.tod + kvm->arch.epoch;
+	gtod->epoch_idx = htod.epoch_idx + kvm->arch.epdx;
+
+	if (gtod->tod < htod.tod)
+		gtod->epoch_idx += 1;
+
+	preempt_enable();
+}
+
+static int kvm_s390_get_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+	struct kvm_s390_vm_tod_clock gtod;
+
+	memset(&gtod, 0, sizeof(gtod));
+
+	if (test_kvm_facility(kvm, 139))
+		kvm_s390_get_tod_clock_ext(kvm, &gtod);
+	else
+		gtod.tod = kvm_s390_get_tod_clock_fast(kvm);
+
+	if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
+		return -EFAULT;
+
+	VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x, TOD base: 0x%llx",
+		gtod.epoch_idx, gtod.tod);
+	return 0;
+}
+
 static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
 {
 	u8 gtod_high = 0;
@@ -954,6 +1020,9 @@ static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr)
 		return -EINVAL;
 
 	switch (attr->attr) {
+	case KVM_S390_VM_TOD_EXT:
+		ret = kvm_s390_get_tod_ext(kvm, attr);
+		break;
 	case KVM_S390_VM_TOD_HIGH:
 		ret = kvm_s390_get_tod_high(kvm, attr);
 		break;
@@ -2369,6 +2438,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->eca |= ECA_VX;
 		vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT;
 	}
+	if (test_kvm_facility(vcpu->kvm, 139))
+		vcpu->arch.sie_block->ecd |= ECD_MEF;
+
 	vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx)
 					| SDNXC;
 	vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
@@ -2855,6 +2927,35 @@ retry:
 	return 0;
 }
 
+void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
+				 const struct kvm_s390_vm_tod_clock *gtod)
+{
+	struct kvm_vcpu *vcpu;
+	struct kvm_s390_tod_clock_ext htod;
+	int i;
+
+	mutex_lock(&kvm->lock);
+	preempt_disable();
+
+	get_tod_clock_ext((char *)&htod);
+
+	kvm->arch.epoch = gtod->tod - htod.tod;
+	kvm->arch.epdx = gtod->epoch_idx - htod.epoch_idx;
+
+	if (kvm->arch.epoch > gtod->tod)
+		kvm->arch.epdx -= 1;
+
+	kvm_s390_vcpu_block_all(kvm);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		vcpu->arch.sie_block->epoch = kvm->arch.epoch;
+		vcpu->arch.sie_block->epdx  = kvm->arch.epdx;
+	}
+
+	kvm_s390_vcpu_unblock_all(kvm);
+	preempt_enable();
+	mutex_unlock(&kvm->lock);
+}
+
 void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod)
 {
 	struct kvm_vcpu *vcpu;

arch/s390/kvm/kvm-s390.h

@@ -272,6 +272,8 @@ int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
 int handle_sthyi(struct kvm_vcpu *vcpu);
 
 /* implemented in kvm-s390.c */
+void kvm_s390_set_tod_clock_ext(struct kvm *kvm,
+				 const struct kvm_s390_vm_tod_clock *gtod);
 void kvm_s390_set_tod_clock(struct kvm *kvm, u64 tod);
 long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
 int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);

arch/s390/kvm/vsie.c

@@ -349,6 +349,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		scb_s->eca |= scb_o->eca & ECA_IB;
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI))
 		scb_s->eca |= scb_o->eca & ECA_CEI;
+	/* Epoch Extension */
+	if (test_kvm_facility(vcpu->kvm, 139))
+		scb_s->ecd |= scb_o->ecd & ECD_MEF;
 
 	prepare_ibc(vcpu, vsie_page);
 	rc = shadow_crycb(vcpu, vsie_page);
@@ -919,6 +922,13 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu,
 	 */
 	preempt_disable();
 	scb_s->epoch += vcpu->kvm->arch.epoch;
+
+	if (scb_s->ecd & ECD_MEF) {
+		scb_s->epdx += vcpu->kvm->arch.epdx;
+		if (scb_s->epoch < vcpu->kvm->arch.epoch)
+			scb_s->epdx += 1;
+	}
+
 	preempt_enable();
 }
 

arch/s390/tools/gen_facilities.c

@@ -81,6 +81,7 @@ static struct facility_def facility_defs[] = {
 			130, /* instruction-execution-protection */
 			131, /* enhanced-SOP 2 and side-effect */
 			138, /* configuration z/architecture mode (czam) */
+			139, /* multiple epoch facility */
 			146, /* msa extension 8 */
 			-1  /* END */
 		}