Merge tag 'kvm-s390-next-4.16-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux

KVM: s390: Fixes and features for 4.16 part 2

- exitless interrupts for emulated devices (Michael Mueller)
- cleanup of cpuflag handling (David Hildenbrand)
- kvm stat counter improvements (Christian Borntraeger)
- vsie improvements (David Hildenbrand)
- mm cleanup (Janosch Frank)

7 files changed, 387 insertions, 130 deletions

diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 89aa114a2cba..45634b3d2e0a 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -257,6 +257,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 	case 0x500:
 		return __diag_virtio_hypercall(vcpu);
 	default:
+		vcpu->stat.diagnose_other++;
 		return -EOPNOTSUPP;
 	}
 }
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index f8eb2cfa763a..aabf46f5f883 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -36,7 +36,7 @@ static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
 {
 	int c, scn;
 
-	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+	if (!kvm_s390_test_cpuflags(vcpu, CPUSTAT_ECALL_PEND))
 		return 0;
 
 	BUG_ON(!kvm_s390_use_sca_entries());
@@ -101,7 +101,7 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
 		/* another external call is pending */
 		return -EBUSY;
 	}
-	atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
 	return 0;
 }
 
@@ -111,7 +111,7 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
 
 	if (!kvm_s390_use_sca_entries())
 		return;
-	atomic_andnot(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_ECALL_PEND);
 	read_lock(&vcpu->kvm->arch.sca_lock);
 	if (vcpu->kvm->arch.use_esca) {
 		struct esca_block *sca = vcpu->kvm->arch.sca;
@@ -189,8 +189,8 @@ static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
 
 static inline int is_ioirq(unsigned long irq_type)
 {
-	return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
-		(irq_type <= IRQ_PEND_IO_ISC_7));
+	return ((irq_type >= IRQ_PEND_IO_ISC_7) &&
+		(irq_type <= IRQ_PEND_IO_ISC_0));
 }
 
 static uint64_t isc_to_isc_bits(int isc)
@@ -198,25 +198,59 @@ static uint64_t isc_to_isc_bits(int isc)
 	return (0x80 >> isc) << 24;
 }
 
+static inline u32 isc_to_int_word(u8 isc)
+{
+	return ((u32)isc << 27) | 0x80000000;
+}
+
 static inline u8 int_word_to_isc(u32 int_word)
 {
 	return (int_word & 0x38000000) >> 27;
 }
 
+/*
+ * To use atomic bitmap functions, we have to provide a bitmap address
+ * that is u64 aligned. However, the ipm might be u32 aligned.
+ * Therefore, we logically start the bitmap at the very beginning of the
+ * struct and fixup the bit number.
+ */
+#define IPM_BIT_OFFSET (offsetof(struct kvm_s390_gisa, ipm) * BITS_PER_BYTE)
+
+static inline void kvm_s390_gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+	set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
+static inline u8 kvm_s390_gisa_get_ipm(struct kvm_s390_gisa *gisa)
+{
+	return READ_ONCE(gisa->ipm);
+}
+
+static inline void kvm_s390_gisa_clear_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+	clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
+static inline int kvm_s390_gisa_tac_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
+{
+	return test_and_clear_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
+}
+
 static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
 {
 	return vcpu->kvm->arch.float_int.pending_irqs |
-	       vcpu->arch.local_int.pending_irqs;
+		vcpu->arch.local_int.pending_irqs |
+		kvm_s390_gisa_get_ipm(vcpu->kvm->arch.gisa) << IRQ_PEND_IO_ISC_7;
 }
 
 static inline int isc_to_irq_type(unsigned long isc)
 {
-	return IRQ_PEND_IO_ISC_0 + isc;
+	return IRQ_PEND_IO_ISC_0 - isc;
 }
 
 static inline int irq_type_to_isc(unsigned long irq_type)
 {
-	return irq_type - IRQ_PEND_IO_ISC_0;
+	return IRQ_PEND_IO_ISC_0 - irq_type;
 }
 
 static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
@@ -277,20 +311,20 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
 
 static void __set_cpu_idle(struct kvm_vcpu *vcpu)
 {
-	atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
 	set_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
 }
 
 static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
 {
-	atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
 	clear_bit(vcpu->vcpu_id, vcpu->kvm->arch.float_int.idle_mask);
 }
 
 static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 {
-	atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
-		    &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IO_INT | CPUSTAT_EXT_INT |
+				      CPUSTAT_STOP_INT);
 	vcpu->arch.sie_block->lctl = 0x0000;
 	vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);
 
@@ -301,17 +335,12 @@ static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
 	}
 }
 
-static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
-{
-	atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
-}
-
 static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
 {
 	if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
 		return;
 	else if (psw_ioint_disabled(vcpu))
-		__set_cpuflag(vcpu, CPUSTAT_IO_INT);
+		kvm_s390_set_cpuflags(vcpu, CPUSTAT_IO_INT);
 	else
 		vcpu->arch.sie_block->lctl |= LCTL_CR6;
 }
@@ -321,7 +350,7 @@ static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
 	if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
 		return;
 	if (psw_extint_disabled(vcpu))
-		__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+		kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
 	else
 		vcpu->arch.sie_block->lctl |= LCTL_CR0;
 }
@@ -339,7 +368,7 @@ static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu)
 static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
 {
 	if (kvm_s390_is_stop_irq_pending(vcpu))
-		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+		kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
 }
 
 /* Set interception request for non-deliverable interrupts */
@@ -896,18 +925,38 @@ static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
 	return rc ? -EFAULT : 0;
 }
 
+static int __do_deliver_io(struct kvm_vcpu *vcpu, struct kvm_s390_io_info *io)
+{
+	int rc;
+
+	rc  = put_guest_lc(vcpu, io->subchannel_id, (u16 *)__LC_SUBCHANNEL_ID);
+	rc |= put_guest_lc(vcpu, io->subchannel_nr, (u16 *)__LC_SUBCHANNEL_NR);
+	rc |= put_guest_lc(vcpu, io->io_int_parm, (u32 *)__LC_IO_INT_PARM);
+	rc |= put_guest_lc(vcpu, io->io_int_word, (u32 *)__LC_IO_INT_WORD);
+	rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
+			     &vcpu->arch.sie_block->gpsw,
+			     sizeof(psw_t));
+	rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
+			    &vcpu->arch.sie_block->gpsw,
+			    sizeof(psw_t));
+	return rc ? -EFAULT : 0;
+}
+
 static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 				     unsigned long irq_type)
 {
 	struct list_head *isc_list;
 	struct kvm_s390_float_interrupt *fi;
 	struct kvm_s390_interrupt_info *inti = NULL;
+	struct kvm_s390_io_info io;
+	u32 isc;
 	int rc = 0;
 
 	fi = &vcpu->kvm->arch.float_int;
 
 	spin_lock(&fi->lock);
-	isc_list = &fi->lists[irq_type_to_isc(irq_type)];
+	isc = irq_type_to_isc(irq_type);
+	isc_list = &fi->lists[isc];
 	inti = list_first_entry_or_null(isc_list,
 					struct kvm_s390_interrupt_info,
 					list);
@@ -935,24 +984,31 @@ static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
 	spin_unlock(&fi->lock);
 
 	if (inti) {
-		rc  = put_guest_lc(vcpu, inti->io.subchannel_id,
-				(u16 *)__LC_SUBCHANNEL_ID);
-		rc |= put_guest_lc(vcpu, inti->io.subchannel_nr,
-				(u16 *)__LC_SUBCHANNEL_NR);
-		rc |= put_guest_lc(vcpu, inti->io.io_int_parm,
-				(u32 *)__LC_IO_INT_PARM);
-		rc |= put_guest_lc(vcpu, inti->io.io_int_word,
-				(u32 *)__LC_IO_INT_WORD);
-		rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
-				&vcpu->arch.sie_block->gpsw,
-				sizeof(psw_t));
-		rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
-				&vcpu->arch.sie_block->gpsw,
-				sizeof(psw_t));
+		rc = __do_deliver_io(vcpu, &(inti->io));
 		kfree(inti);
+		goto out;
 	}
 
-	return rc ? -EFAULT : 0;
+	if (vcpu->kvm->arch.gisa &&
+	    kvm_s390_gisa_tac_ipm_gisc(vcpu->kvm->arch.gisa, isc)) {
+		/*
+		 * in case an adapter interrupt was not delivered
+		 * in SIE context KVM will handle the delivery
+		 */
+		VCPU_EVENT(vcpu, 4, "%s isc %u", "deliver: I/O (AI/gisa)", isc);
+		memset(&io, 0, sizeof(io));
+		io.io_int_word = isc_to_int_word(isc);
+		vcpu->stat.deliver_io_int++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
+			KVM_S390_INT_IO(1, 0, 0, 0),
+			((__u32)io.subchannel_id << 16) |
+			io.subchannel_nr,
+			((__u64)io.io_int_parm << 32) |
+			io.io_int_word);
+		rc = __do_deliver_io(vcpu, &io);
+	}
+out:
+	return rc;
 }
 
 typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);
@@ -1154,8 +1210,8 @@ int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
 		set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
 
 	while ((irqs = deliverable_irqs(vcpu)) && !rc) {
-		/* bits are in the order of interrupt priority */
-		irq_type = find_first_bit(&irqs, IRQ_PEND_COUNT);
+		/* bits are in the reverse order of interrupt priority */
+		irq_type = find_last_bit(&irqs, IRQ_PEND_COUNT);
 		if (is_ioirq(irq_type)) {
 			rc = __deliver_io(vcpu, irq_type);
 		} else {
@@ -1227,7 +1283,7 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 
 	li->irq.ext = irq->u.ext;
 	set_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
-	__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
 	return 0;
 }
 
@@ -1252,7 +1308,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
 		return -EBUSY;
 	*extcall = irq->u.extcall;
-	__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
 	return 0;
 }
 
@@ -1296,7 +1352,7 @@ static int __inject_sigp_stop(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
 	if (test_and_set_bit(IRQ_PEND_SIGP_STOP, &li->pending_irqs))
 		return -EBUSY;
 	stop->flags = irq->u.stop.flags;
-	__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
 	return 0;
 }
 
@@ -1328,7 +1384,7 @@ static int __inject_sigp_emergency(struct kvm_vcpu *vcpu,
 
 	set_bit(irq->u.emerg.code, li->sigp_emerg_pending);
 	set_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
-	__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
 	return 0;
 }
 
@@ -1372,7 +1428,7 @@ static int __inject_ckc(struct kvm_vcpu *vcpu)
 				   0, 0);
 
 	set_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
-	__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
 	return 0;
 }
 
@@ -1385,7 +1441,7 @@ static int __inject_cpu_timer(struct kvm_vcpu *vcpu)
 				   0, 0);
 
 	set_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
-	__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_EXT_INT);
 	return 0;
 }
 
@@ -1415,20 +1471,86 @@ static struct kvm_s390_interrupt_info *get_io_int(struct kvm *kvm,
 	return NULL;
 }
 
+static struct kvm_s390_interrupt_info *get_top_io_int(struct kvm *kvm,
+						      u64 isc_mask, u32 schid)
+{
+	struct kvm_s390_interrupt_info *inti = NULL;
+	int isc;
+
+	for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
+		if (isc_mask & isc_to_isc_bits(isc))
+			inti = get_io_int(kvm, isc, schid);
+	}
+	return inti;
+}
+
+static int get_top_gisa_isc(struct kvm *kvm, u64 isc_mask, u32 schid)
+{
+	unsigned long active_mask;
+	int isc;
+
+	if (schid)
+		goto out;
+	if (!kvm->arch.gisa)
+		goto out;
+
+	active_mask = (isc_mask & kvm_s390_gisa_get_ipm(kvm->arch.gisa) << 24) << 32;
+	while (active_mask) {
+		isc = __fls(active_mask) ^ (BITS_PER_LONG - 1);
+		if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, isc))
+			return isc;
+		clear_bit_inv(isc, &active_mask);
+	}
+out:
+	return -EINVAL;
+}
+
 /*
  * Dequeue and return an I/O interrupt matching any of the interruption
  * subclasses as designated by the isc mask in cr6 and the schid (if != 0).
+ * Take into account the interrupts pending in the interrupt list and in GISA.
+ *
+ * Note that for a guest that does not enable I/O interrupts
+ * but relies on TPI, a flood of classic interrupts may starve
+ * out adapter interrupts on the same isc. Linux does not do
+ * that, and it is possible to work around the issue by configuring
+ * different iscs for classic and adapter interrupts in the guest,
+ * but we may want to revisit this in the future.
  */
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 						    u64 isc_mask, u32 schid)
 {
-	struct kvm_s390_interrupt_info *inti = NULL;
+	struct kvm_s390_interrupt_info *inti, *tmp_inti;
 	int isc;
 
-	for (isc = 0; isc <= MAX_ISC && !inti; isc++) {
-		if (isc_mask & isc_to_isc_bits(isc))
-			inti = get_io_int(kvm, isc, schid);
+	inti = get_top_io_int(kvm, isc_mask, schid);
+
+	isc = get_top_gisa_isc(kvm, isc_mask, schid);
+	if (isc < 0)
+		/* no AI in GISA */
+		goto out;
+
+	if (!inti)
+		/* AI in GISA but no classical IO int */
+		goto gisa_out;
+
+	/* both types of interrupts present */
+	if (int_word_to_isc(inti->io.io_int_word) <= isc) {
+		/* classical IO int with higher priority */
+		kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+		goto out;
 	}
+gisa_out:
+	tmp_inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (tmp_inti) {
+		tmp_inti->type = KVM_S390_INT_IO(1, 0, 0, 0);
+		tmp_inti->io.io_int_word = isc_to_int_word(isc);
+		if (inti)
+			kvm_s390_reinject_io_int(kvm, inti);
+		inti = tmp_inti;
+	} else
+		kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+out:
 	return inti;
 }
 
@@ -1516,6 +1638,15 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	struct list_head *list;
 	int isc;
 
+	isc = int_word_to_isc(inti->io.io_int_word);
+
+	if (kvm->arch.gisa && inti->type & KVM_S390_INT_IO_AI_MASK) {
+		VM_EVENT(kvm, 4, "%s isc %1u", "inject: I/O (AI/gisa)", isc);
+		kvm_s390_gisa_set_ipm_gisc(kvm->arch.gisa, isc);
+		kfree(inti);
+		return 0;
+	}
+
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
 	if (fi->counters[FIRQ_CNTR_IO] >= KVM_S390_MAX_FLOAT_IRQS) {
@@ -1531,7 +1662,6 @@ static int __inject_io(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 			inti->io.subchannel_id >> 8,
 			inti->io.subchannel_id >> 1 & 0x3,
 			inti->io.subchannel_nr);
-	isc = int_word_to_isc(inti->io.io_int_word);
 	list = &fi->lists[FIRQ_LIST_IO_ISC_0 + isc];
 	list_add_tail(&inti->list, list);
 	set_bit(isc_to_irq_type(isc), &fi->pending_irqs);
@@ -1568,13 +1698,13 @@ static void __floating_irq_kick(struct kvm *kvm, u64 type)
 	/* make the VCPU drop out of the SIE, or wake it up if sleeping */
 	switch (type) {
 	case KVM_S390_MCHK:
-		__set_cpuflag(dst_vcpu, CPUSTAT_STOP_INT);
+		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_STOP_INT);
 		break;
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
-		__set_cpuflag(dst_vcpu, CPUSTAT_IO_INT);
+		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_IO_INT);
 		break;
 	default:
-		__set_cpuflag(dst_vcpu, CPUSTAT_EXT_INT);
+		kvm_s390_set_cpuflags(dst_vcpu, CPUSTAT_EXT_INT);
 		break;
 	}
 	kvm_s390_vcpu_wakeup(dst_vcpu);
@@ -1815,6 +1945,7 @@ void kvm_s390_clear_float_irqs(struct kvm *kvm)
 	for (i = 0; i < FIRQ_MAX_COUNT; i++)
 		fi->counters[i] = 0;
 	spin_unlock(&fi->lock);
+	kvm_s390_gisa_clear(kvm);
 };
 
 static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
@@ -1842,6 +1973,22 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
 
 	max_irqs = len / sizeof(struct kvm_s390_irq);
 
+	if (kvm->arch.gisa &&
+	    kvm_s390_gisa_get_ipm(kvm->arch.gisa)) {
+		for (i = 0; i <= MAX_ISC; i++) {
+			if (n == max_irqs) {
+				/* signal userspace to try again */
+				ret = -ENOMEM;
+				goto out_nolock;
+			}
+			if (kvm_s390_gisa_tac_ipm_gisc(kvm->arch.gisa, i)) {
+				irq = (struct kvm_s390_irq *) &buf[n];
+				irq->type = KVM_S390_INT_IO(1, 0, 0, 0);
+				irq->u.io.io_int_word = isc_to_int_word(i);
+				n++;
+			}
+		}
+	}
 	fi = &kvm->arch.float_int;
 	spin_lock(&fi->lock);
 	for (i = 0; i < FIRQ_LIST_COUNT; i++) {
@@ -1880,6 +2027,7 @@ static int get_all_floating_irqs(struct kvm *kvm, u8 __user *usrbuf, u64 len)
 
 out:
 	spin_unlock(&fi->lock);
+out_nolock:
 	if (!ret && n > 0) {
 		if (copy_to_user(usrbuf, buf, sizeof(struct kvm_s390_irq) * n))
 			ret = -EFAULT;
@@ -2240,7 +2388,7 @@ static int kvm_s390_inject_airq(struct kvm *kvm,
 	struct kvm_s390_interrupt s390int = {
 		.type = KVM_S390_INT_IO(1, 0, 0, 0),
 		.parm = 0,
-		.parm64 = (adapter->isc << 27) | 0x80000000,
+		.parm64 = isc_to_int_word(adapter->isc),
 	};
 	int ret = 0;
 
@@ -2682,3 +2830,28 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
 
 	return n;
 }
+
+void kvm_s390_gisa_clear(struct kvm *kvm)
+{
+	if (kvm->arch.gisa) {
+		memset(kvm->arch.gisa, 0, sizeof(struct kvm_s390_gisa));
+		kvm->arch.gisa->next_alert = (u32)(u64)kvm->arch.gisa;
+		VM_EVENT(kvm, 3, "gisa 0x%pK cleared", kvm->arch.gisa);
+	}
+}
+
+void kvm_s390_gisa_init(struct kvm *kvm)
+{
+	if (css_general_characteristics.aiv) {
+		kvm->arch.gisa = &kvm->arch.sie_page2->gisa;
+		VM_EVENT(kvm, 3, "gisa 0x%pK initialized", kvm->arch.gisa);
+		kvm_s390_gisa_clear(kvm);
+	}
+}
+
+void kvm_s390_gisa_destroy(struct kvm *kvm)
+{
+	if (!kvm->arch.gisa)
+		return;
+	kvm->arch.gisa = NULL;
+}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index de16c224319c..58bee42d7a9d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2,7 +2,7 @@
 /*
  * hosting IBM Z kernel virtual machines (s390x)
  *
- * Copyright IBM Corp. 2008, 2017
+ * Copyright IBM Corp. 2008, 2018
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -87,19 +87,31 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
 	{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
 	{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
+	{ "instruction_epsw", VCPU_STAT(instruction_epsw) },
+	{ "instruction_gs", VCPU_STAT(instruction_gs) },
+	{ "instruction_io_other", VCPU_STAT(instruction_io_other) },
+	{ "instruction_lpsw", VCPU_STAT(instruction_lpsw) },
+	{ "instruction_lpswe", VCPU_STAT(instruction_lpswe) },
 	{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
+	{ "instruction_ptff", VCPU_STAT(instruction_ptff) },
 	{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
+	{ "instruction_sck", VCPU_STAT(instruction_sck) },
+	{ "instruction_sckpf", VCPU_STAT(instruction_sckpf) },
 	{ "instruction_spx", VCPU_STAT(instruction_spx) },
 	{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
 	{ "instruction_stap", VCPU_STAT(instruction_stap) },
-	{ "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
+	{ "instruction_iske", VCPU_STAT(instruction_iske) },
+	{ "instruction_ri", VCPU_STAT(instruction_ri) },
+	{ "instruction_rrbe", VCPU_STAT(instruction_rrbe) },
+	{ "instruction_sske", VCPU_STAT(instruction_sske) },
 	{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
-	{ "instruction_stsch", VCPU_STAT(instruction_stsch) },
-	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
 	{ "instruction_essa", VCPU_STAT(instruction_essa) },
 	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
 	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+	{ "instruction_tb", VCPU_STAT(instruction_tb) },
+	{ "instruction_tpi", VCPU_STAT(instruction_tpi) },
 	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
+	{ "instruction_tsch", VCPU_STAT(instruction_tsch) },
 	{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
 	{ "instruction_sie", VCPU_STAT(instruction_sie) },
 	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
@@ -118,12 +130,13 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
 	{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
 	{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
-	{ "diagnose_10", VCPU_STAT(diagnose_10) },
-	{ "diagnose_44", VCPU_STAT(diagnose_44) },
-	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
-	{ "diagnose_258", VCPU_STAT(diagnose_258) },
-	{ "diagnose_308", VCPU_STAT(diagnose_308) },
-	{ "diagnose_500", VCPU_STAT(diagnose_500) },
+	{ "instruction_diag_10", VCPU_STAT(diagnose_10) },
+	{ "instruction_diag_44", VCPU_STAT(diagnose_44) },
+	{ "instruction_diag_9c", VCPU_STAT(diagnose_9c) },
+	{ "instruction_diag_258", VCPU_STAT(diagnose_258) },
+	{ "instruction_diag_308", VCPU_STAT(diagnose_308) },
+	{ "instruction_diag_500", VCPU_STAT(diagnose_500) },
+	{ "instruction_diag_other", VCPU_STAT(diagnose_other) },
 	{ NULL }
 };
 
@@ -1915,6 +1928,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (!kvm->arch.dbf)
 		goto out_err;
 
+	BUILD_BUG_ON(sizeof(struct sie_page2) != 4096);
 	kvm->arch.sie_page2 =
 	     (struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 	if (!kvm->arch.sie_page2)
@@ -1985,6 +1999,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
 	kvm_s390_vsie_init(kvm);
+	kvm_s390_gisa_init(kvm);
 	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
 
 	return 0;
@@ -2047,6 +2062,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_vcpus(kvm);
 	sca_dispose(kvm);
 	debug_unregister(kvm->arch.dbf);
+	kvm_s390_gisa_destroy(kvm);
 	free_page((unsigned long)kvm->arch.sie_page2);
 	if (!kvm_is_ucontrol(kvm))
 		gmap_remove(kvm->arch.gmap);
@@ -2316,7 +2332,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 
 	gmap_enable(vcpu->arch.enabled_gmap);
-	atomic_or(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_RUNNING);
 	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
 		__start_cpu_timer_accounting(vcpu);
 	vcpu->cpu = cpu;
@@ -2327,7 +2343,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	vcpu->cpu = -1;
 	if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
 		__stop_cpu_timer_accounting(vcpu);
-	atomic_andnot(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_RUNNING);
 	vcpu->arch.enabled_gmap = gmap_get_enabled();
 	gmap_disable(vcpu->arch.enabled_gmap);
 
@@ -2423,9 +2439,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 						    CPUSTAT_STOPPED);
 
 	if (test_kvm_facility(vcpu->kvm, 78))
-		atomic_or(CPUSTAT_GED2, &vcpu->arch.sie_block->cpuflags);
+		kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED2);
 	else if (test_kvm_facility(vcpu->kvm, 8))
-		atomic_or(CPUSTAT_GED, &vcpu->arch.sie_block->cpuflags);
+		kvm_s390_set_cpuflags(vcpu, CPUSTAT_GED);
 
 	kvm_s390_vcpu_setup_model(vcpu);
 
@@ -2457,12 +2473,17 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	if (test_kvm_facility(vcpu->kvm, 139))
 		vcpu->arch.sie_block->ecd |= ECD_MEF;
 
+	if (vcpu->arch.sie_block->gd) {
+		vcpu->arch.sie_block->eca |= ECA_AIV;
+		VCPU_EVENT(vcpu, 3, "AIV gisa format-%u enabled for cpu %03u",
+			   vcpu->arch.sie_block->gd & 0x3, vcpu->vcpu_id);
+	}
 	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;
 
 	if (sclp.has_kss)
-		atomic_or(CPUSTAT_KSS, &vcpu->arch.sie_block->cpuflags);
+		kvm_s390_set_cpuflags(vcpu, CPUSTAT_KSS);
 	else
 		vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
 
@@ -2509,6 +2530,9 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 	vcpu->arch.sie_block->icpua = id;
 	spin_lock_init(&vcpu->arch.local_int.lock);
+	vcpu->arch.sie_block->gd = (u32)(u64)kvm->arch.gisa;
+	if (vcpu->arch.sie_block->gd && sclp.has_gisaf)
+		vcpu->arch.sie_block->gd |= GISA_FORMAT1;
 	seqcount_init(&vcpu->arch.cputm_seqcount);
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
@@ -2565,7 +2589,7 @@ static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
  * return immediately. */
 void exit_sie(struct kvm_vcpu *vcpu)
 {
-	atomic_or(CPUSTAT_STOP_INT, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOP_INT);
 	while (vcpu->arch.sie_block->prog0c & PROG_IN_SIE)
 		cpu_relax();
 }
@@ -2840,19 +2864,19 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	if (dbg->control & KVM_GUESTDBG_ENABLE) {
 		vcpu->guest_debug = dbg->control;
 		/* enforce guest PER */
-		atomic_or(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		kvm_s390_set_cpuflags(vcpu, CPUSTAT_P);
 
 		if (dbg->control & KVM_GUESTDBG_USE_HW_BP)
 			rc = kvm_s390_import_bp_data(vcpu, dbg);
 	} else {
-		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P);
 		vcpu->arch.guestdbg.last_bp = 0;
 	}
 
 	if (rc) {
 		vcpu->guest_debug = 0;
 		kvm_s390_clear_bp_data(vcpu);
-		atomic_andnot(CPUSTAT_P, &vcpu->arch.sie_block->cpuflags);
+		kvm_s390_clear_cpuflags(vcpu, CPUSTAT_P);
 	}
 
 out:
@@ -2905,7 +2929,7 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 
 static bool ibs_enabled(struct kvm_vcpu *vcpu)
 {
-	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_IBS;
+	return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS);
 }
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
@@ -2941,8 +2965,7 @@ retry:
 	if (kvm_check_request(KVM_REQ_ENABLE_IBS, vcpu)) {
 		if (!ibs_enabled(vcpu)) {
 			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 1);
-			atomic_or(CPUSTAT_IBS,
-					&vcpu->arch.sie_block->cpuflags);
+			kvm_s390_set_cpuflags(vcpu, CPUSTAT_IBS);
 		}
 		goto retry;
 	}
@@ -2950,8 +2973,7 @@ retry:
 	if (kvm_check_request(KVM_REQ_DISABLE_IBS, vcpu)) {
 		if (ibs_enabled(vcpu)) {
 			trace_kvm_s390_enable_disable_ibs(vcpu->vcpu_id, 0);
-			atomic_andnot(CPUSTAT_IBS,
-					  &vcpu->arch.sie_block->cpuflags);
+			kvm_s390_clear_cpuflags(vcpu, CPUSTAT_IBS);
 		}
 		goto retry;
 	}
@@ -3601,7 +3623,7 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 		__disable_ibs_on_all_vcpus(vcpu->kvm);
 	}
 
-	atomic_andnot(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED);
 	/*
 	 * Another VCPU might have used IBS while we were offline.
 	 * Let's play safe and flush the VCPU at startup.
@@ -3627,7 +3649,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
 	kvm_s390_clear_stop_irq(vcpu);
 
-	atomic_or(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
 	__disable_ibs_on_vcpu(vcpu);
 
 	for (i = 0; i < online_vcpus; i++) {
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 8877116f0159..bd31b37b0e6f 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -47,9 +47,24 @@ do { \
 	  d_args); \
 } while (0)
 
+static inline void kvm_s390_set_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+	atomic_or(flags, &vcpu->arch.sie_block->cpuflags);
+}
+
+static inline void kvm_s390_clear_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+	atomic_andnot(flags, &vcpu->arch.sie_block->cpuflags);
+}
+
+static inline bool kvm_s390_test_cpuflags(struct kvm_vcpu *vcpu, u32 flags)
+{
+	return (atomic_read(&vcpu->arch.sie_block->cpuflags) & flags) == flags;
+}
+
 static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu)
 {
-	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED;
+	return kvm_s390_test_cpuflags(vcpu, CPUSTAT_STOPPED);
 }
 
 static inline int is_vcpu_idle(struct kvm_vcpu *vcpu)
@@ -367,6 +382,9 @@ int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
 			   void __user *buf, int len);
 int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu,
 			   __u8 __user *buf, int len);
+void kvm_s390_gisa_init(struct kvm *kvm);
+void kvm_s390_gisa_clear(struct kvm *kvm);
+void kvm_s390_gisa_destroy(struct kvm *kvm);
 
 /* implemented in guestdbg.c */
 void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 572496c688cc..125a7ff98e2a 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -2,7 +2,7 @@
 /*
  * handling privileged instructions
  *
- * Copyright IBM Corp. 2008, 2013
+ * Copyright IBM Corp. 2008, 2018
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -34,6 +34,8 @@
 
 static int handle_ri(struct kvm_vcpu *vcpu)
 {
+	vcpu->stat.instruction_ri++;
+
 	if (test_kvm_facility(vcpu->kvm, 64)) {
 		VCPU_EVENT(vcpu, 3, "%s", "ENABLE: RI (lazy)");
 		vcpu->arch.sie_block->ecb3 |= ECB3_RI;
@@ -53,6 +55,8 @@ int kvm_s390_handle_aa(struct kvm_vcpu *vcpu)
 
 static int handle_gs(struct kvm_vcpu *vcpu)
 {
+	vcpu->stat.instruction_gs++;
+
 	if (test_kvm_facility(vcpu->kvm, 133)) {
 		VCPU_EVENT(vcpu, 3, "%s", "ENABLE: GS (lazy)");
 		preempt_disable();
@@ -85,6 +89,8 @@ static int handle_set_clock(struct kvm_vcpu *vcpu)
 	u8 ar;
 	u64 op2, val;
 
+	vcpu->stat.instruction_sck++;
+
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -203,14 +209,14 @@ int kvm_s390_skey_check_enable(struct kvm_vcpu *vcpu)
 
 	trace_kvm_s390_skey_related_inst(vcpu);
 	if (!(sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)) &&
-	    !(atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS))
+	    !kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS))
 		return rc;
 
 	rc = s390_enable_skey();
 	VCPU_EVENT(vcpu, 3, "enabling storage keys for guest: %d", rc);
 	if (!rc) {
-		if (atomic_read(&sie_block->cpuflags) & CPUSTAT_KSS)
-			atomic_andnot(CPUSTAT_KSS, &sie_block->cpuflags);
+		if (kvm_s390_test_cpuflags(vcpu, CPUSTAT_KSS))
+			kvm_s390_clear_cpuflags(vcpu, CPUSTAT_KSS);
 		else
 			sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE |
 					     ICTL_RRBE);
@@ -222,7 +228,6 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
 {
 	int rc;
 
-	vcpu->stat.instruction_storage_key++;
 	rc = kvm_s390_skey_check_enable(vcpu);
 	if (rc)
 		return rc;
@@ -242,6 +247,8 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	vcpu->stat.instruction_iske++;
+
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -274,6 +281,8 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	vcpu->stat.instruction_rrbe++;
+
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -312,6 +321,8 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	vcpu->stat.instruction_sske++;
+
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -392,6 +403,8 @@ static int handle_test_block(struct kvm_vcpu *vcpu)
 	gpa_t addr;
 	int reg2;
 
+	vcpu->stat.instruction_tb++;
+
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -424,6 +437,8 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 	u64 addr;
 	u8 ar;
 
+	vcpu->stat.instruction_tpi++;
+
 	addr = kvm_s390_get_base_disp_s(vcpu, &ar);
 	if (addr & 3)
 		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
@@ -484,6 +499,8 @@ static int handle_tsch(struct kvm_vcpu *vcpu)
 	struct kvm_s390_interrupt_info *inti = NULL;
 	const u64 isc_mask = 0xffUL << 24; /* all iscs set */
 
+	vcpu->stat.instruction_tsch++;
+
 	/* a valid schid has at least one bit set */
 	if (vcpu->run->s.regs.gprs[1])
 		inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask,
@@ -527,6 +544,7 @@ static int handle_io_inst(struct kvm_vcpu *vcpu)
 		if (vcpu->arch.sie_block->ipa == 0xb235)
 			return handle_tsch(vcpu);
 		/* Handle in userspace. */
+		vcpu->stat.instruction_io_other++;
 		return -EOPNOTSUPP;
 	} else {
 		/*
@@ -592,6 +610,8 @@ int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
 	int rc;
 	u8 ar;
 
+	vcpu->stat.instruction_lpsw++;
+
 	if (gpsw->mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -619,6 +639,8 @@ static int handle_lpswe(struct kvm_vcpu *vcpu)
 	int rc;
 	u8 ar;
 
+	vcpu->stat.instruction_lpswe++;
+
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -828,6 +850,8 @@ static int handle_epsw(struct kvm_vcpu *vcpu)
 {
 	int reg1, reg2;
 
+	vcpu->stat.instruction_epsw++;
+
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
 	/* This basically extracts the mask half of the psw. */
@@ -1332,6 +1356,8 @@ static int handle_sckpf(struct kvm_vcpu *vcpu)
 {
 	u32 value;
 
+	vcpu->stat.instruction_sckpf++;
+
 	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
 		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 
@@ -1347,6 +1373,8 @@ static int handle_sckpf(struct kvm_vcpu *vcpu)
 
 static int handle_ptff(struct kvm_vcpu *vcpu)
 {
+	vcpu->stat.instruction_ptff++;
+
 	/* we don't emulate any control instructions yet */
 	kvm_s390_set_psw_cc(vcpu, 3);
 	return 0;
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 5cafd1e2651b..683036c1c92a 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -20,19 +20,18 @@
 static int __sigp_sense(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu,
 			u64 *reg)
 {
-	int cpuflags;
+	const bool stopped = kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED);
 	int rc;
 	int ext_call_pending;
 
-	cpuflags = atomic_read(&dst_vcpu->arch.sie_block->cpuflags);
 	ext_call_pending = kvm_s390_ext_call_pending(dst_vcpu);
-	if (!(cpuflags & CPUSTAT_STOPPED) && !ext_call_pending)
+	if (!stopped && !ext_call_pending)
 		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 	else {
 		*reg &= 0xffffffff00000000UL;
 		if (ext_call_pending)
 			*reg |= SIGP_STATUS_EXT_CALL_PENDING;
-		if (cpuflags & CPUSTAT_STOPPED)
+		if (stopped)
 			*reg |= SIGP_STATUS_STOPPED;
 		rc = SIGP_CC_STATUS_STORED;
 	}
@@ -205,11 +204,9 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu,
 				       struct kvm_vcpu *dst_vcpu,
 				       u32 addr, u64 *reg)
 {
-	int flags;
 	int rc;
 
-	flags = atomic_read(&dst_vcpu->arch.sie_block->cpuflags);
-	if (!(flags & CPUSTAT_STOPPED)) {
+	if (!kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_STOPPED)) {
 		*reg &= 0xffffffff00000000UL;
 		*reg |= SIGP_STATUS_INCORRECT_STATE;
 		return SIGP_CC_STATUS_STORED;
@@ -236,8 +233,7 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu,
 		return SIGP_CC_STATUS_STORED;
 	}
 
-	if (atomic_read(&dst_vcpu->arch.sie_block->cpuflags) &
-	    CPUSTAT_RUNNING) {
+	if (kvm_s390_test_cpuflags(dst_vcpu, CPUSTAT_RUNNING)) {
 		/* running */
 		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 	} else {
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index 5d6ae0326d9e..6d494ed5907e 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -28,13 +28,23 @@ struct vsie_page {
 	 * the same offset as that in struct sie_page!
 	 */
 	struct mcck_volatile_info mcck_info;    /* 0x0200 */
-	/* the pinned originial scb */
+	/*
+	 * The pinned original scb. Be aware that other VCPUs can modify
+	 * it while we read from it. Values that are used for conditions or
+	 * are reused conditionally, should be accessed via READ_ONCE.
+	 */
 	struct kvm_s390_sie_block *scb_o;	/* 0x0218 */
 	/* the shadow gmap in use by the vsie_page */
 	struct gmap *gmap;			/* 0x0220 */
 	/* address of the last reported fault to guest2 */
 	unsigned long fault_addr;		/* 0x0228 */
-	__u8 reserved[0x0700 - 0x0230];		/* 0x0230 */
+	/* calculated guest addresses of satellite control blocks */
+	gpa_t sca_gpa;				/* 0x0230 */
+	gpa_t itdba_gpa;			/* 0x0238 */
+	gpa_t gvrd_gpa;				/* 0x0240 */
+	gpa_t riccbd_gpa;			/* 0x0248 */
+	gpa_t sdnx_gpa;				/* 0x0250 */
+	__u8 reserved[0x0700 - 0x0258];		/* 0x0258 */
 	struct kvm_s390_crypto_cb crycb;	/* 0x0700 */
 	__u8 fac[S390_ARCH_FAC_LIST_SIZE_BYTE];	/* 0x0800 */
 };
@@ -140,12 +150,13 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
-	u32 crycb_addr = scb_o->crycbd & 0x7ffffff8U;
+	const uint32_t crycbd_o = READ_ONCE(scb_o->crycbd);
+	const u32 crycb_addr = crycbd_o & 0x7ffffff8U;
 	unsigned long *b1, *b2;
 	u8 ecb3_flags;
 
 	scb_s->crycbd = 0;
-	if (!(scb_o->crycbd & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
+	if (!(crycbd_o & vcpu->arch.sie_block->crycbd & CRYCB_FORMAT1))
 		return 0;
 	/* format-1 is supported with message-security-assist extension 3 */
 	if (!test_kvm_facility(vcpu->kvm, 76))
@@ -183,12 +194,15 @@ static void prepare_ibc(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
+	/* READ_ONCE does not work on bitfields - use a temporary variable */
+	const uint32_t __new_ibc = scb_o->ibc;
+	const uint32_t new_ibc = READ_ONCE(__new_ibc) & 0x0fffU;
 	__u64 min_ibc = (sclp.ibc >> 16) & 0x0fffU;
 
 	scb_s->ibc = 0;
 	/* ibc installed in g2 and requested for g3 */
-	if (vcpu->kvm->arch.model.ibc && (scb_o->ibc & 0x0fffU)) {
-		scb_s->ibc = scb_o->ibc & 0x0fffU;
+	if (vcpu->kvm->arch.model.ibc && new_ibc) {
+		scb_s->ibc = new_ibc;
 		/* takte care of the minimum ibc level of the machine */
 		if (scb_s->ibc < min_ibc)
 			scb_s->ibc = min_ibc;
@@ -253,6 +267,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
+	/* READ_ONCE does not work on bitfields - use a temporary variable */
+	const uint32_t __new_prefix = scb_o->prefix;
+	const uint32_t new_prefix = READ_ONCE(__new_prefix);
+	const bool wants_tx = READ_ONCE(scb_o->ecb) & ECB_TE;
 	bool had_tx = scb_s->ecb & ECB_TE;
 	unsigned long new_mso = 0;
 	int rc;
@@ -299,14 +317,14 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	scb_s->icpua = scb_o->icpua;
 
 	if (!(atomic_read(&scb_s->cpuflags) & CPUSTAT_SM))
-		new_mso = scb_o->mso & 0xfffffffffff00000UL;
+		new_mso = READ_ONCE(scb_o->mso) & 0xfffffffffff00000UL;
 	/* if the hva of the prefix changes, we have to remap the prefix */
-	if (scb_s->mso != new_mso || scb_s->prefix != scb_o->prefix)
+	if (scb_s->mso != new_mso || scb_s->prefix != new_prefix)
 		prefix_unmapped(vsie_page);
 	 /* SIE will do mso/msl validity and exception checks for us */
 	scb_s->msl = scb_o->msl & 0xfffffffffff00000UL;
 	scb_s->mso = new_mso;
-	scb_s->prefix = scb_o->prefix;
+	scb_s->prefix = new_prefix;
 
 	/* We have to definetly flush the tlb if this scb never ran */
 	if (scb_s->ihcpu != 0xffffU)
@@ -318,11 +336,11 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_ESOP))
 		scb_s->ecb |= scb_o->ecb & ECB_HOSTPROTINT;
 	/* transactional execution */
-	if (test_kvm_facility(vcpu->kvm, 73)) {
+	if (test_kvm_facility(vcpu->kvm, 73) && wants_tx) {
 		/* remap the prefix is tx is toggled on */
-		if ((scb_o->ecb & ECB_TE) && !had_tx)
+		if (!had_tx)
 			prefix_unmapped(vsie_page);
-		scb_s->ecb |= scb_o->ecb & ECB_TE;
+		scb_s->ecb |= ECB_TE;
 	}
 	/* SIMD */
 	if (test_kvm_facility(vcpu->kvm, 129)) {
@@ -463,46 +481,42 @@ static void unpin_guest_page(struct kvm *kvm, gpa_t gpa, hpa_t hpa)
 /* unpin all blocks previously pinned by pin_blocks(), marking them dirty */
 static void unpin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
-	struct kvm_s390_sie_block *scb_o = vsie_page->scb_o;
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
 	hpa_t hpa;
-	gpa_t gpa;
 
 	hpa = (u64) scb_s->scaoh << 32 | scb_s->scaol;
 	if (hpa) {
-		gpa = scb_o->scaol & ~0xfUL;
-		if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
-			gpa |= (u64) scb_o->scaoh << 32;
-		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		unpin_guest_page(vcpu->kvm, vsie_page->sca_gpa, hpa);
+		vsie_page->sca_gpa = 0;
 		scb_s->scaol = 0;
 		scb_s->scaoh = 0;
 	}
 
 	hpa = scb_s->itdba;
 	if (hpa) {
-		gpa = scb_o->itdba & ~0xffUL;
-		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		unpin_guest_page(vcpu->kvm, vsie_page->itdba_gpa, hpa);
+		vsie_page->itdba_gpa = 0;
 		scb_s->itdba = 0;
 	}
 
 	hpa = scb_s->gvrd;
 	if (hpa) {
-		gpa = scb_o->gvrd & ~0x1ffUL;
-		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		unpin_guest_page(vcpu->kvm, vsie_page->gvrd_gpa, hpa);
+		vsie_page->gvrd_gpa = 0;
 		scb_s->gvrd = 0;
 	}
 
 	hpa = scb_s->riccbd;
 	if (hpa) {
-		gpa = scb_o->riccbd & ~0x3fUL;
-		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		unpin_guest_page(vcpu->kvm, vsie_page->riccbd_gpa, hpa);
+		vsie_page->riccbd_gpa = 0;
 		scb_s->riccbd = 0;
 	}
 
 	hpa = scb_s->sdnxo;
 	if (hpa) {
-		gpa = scb_o->sdnxo;
-		unpin_guest_page(vcpu->kvm, gpa, hpa);
+		unpin_guest_page(vcpu->kvm, vsie_page->sdnx_gpa, hpa);
+		vsie_page->sdnx_gpa = 0;
 		scb_s->sdnxo = 0;
 	}
 }
@@ -529,9 +543,9 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 	gpa_t gpa;
 	int rc = 0;
 
-	gpa = scb_o->scaol & ~0xfUL;
+	gpa = READ_ONCE(scb_o->scaol) & ~0xfUL;
 	if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_64BSCAO))
-		gpa |= (u64) scb_o->scaoh << 32;
+		gpa |= (u64) READ_ONCE(scb_o->scaoh) << 32;
 	if (gpa) {
 		if (!(gpa & ~0x1fffUL))
 			rc = set_validity_icpt(scb_s, 0x0038U);
@@ -547,11 +561,12 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 		}
 		if (rc)
 			goto unpin;
+		vsie_page->sca_gpa = gpa;
 		scb_s->scaoh = (u32)((u64)hpa >> 32);
 		scb_s->scaol = (u32)(u64)hpa;
 	}
 
-	gpa = scb_o->itdba & ~0xffUL;
+	gpa = READ_ONCE(scb_o->itdba) & ~0xffUL;
 	if (gpa && (scb_s->ecb & ECB_TE)) {
 		if (!(gpa & ~0x1fffU)) {
 			rc = set_validity_icpt(scb_s, 0x0080U);
@@ -563,10 +578,11 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			rc = set_validity_icpt(scb_s, 0x0080U);
 			goto unpin;
 		}
+		vsie_page->itdba_gpa = gpa;
 		scb_s->itdba = hpa;
 	}
 
-	gpa = scb_o->gvrd & ~0x1ffUL;
+	gpa = READ_ONCE(scb_o->gvrd) & ~0x1ffUL;
 	if (gpa && (scb_s->eca & ECA_VX) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
 		if (!(gpa & ~0x1fffUL)) {
 			rc = set_validity_icpt(scb_s, 0x1310U);
@@ -581,10 +597,11 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			rc = set_validity_icpt(scb_s, 0x1310U);
 			goto unpin;
 		}
+		vsie_page->gvrd_gpa = gpa;
 		scb_s->gvrd = hpa;
 	}
 
-	gpa = scb_o->riccbd & ~0x3fUL;
+	gpa = READ_ONCE(scb_o->riccbd) & ~0x3fUL;
 	if (gpa && (scb_s->ecb3 & ECB3_RI)) {
 		if (!(gpa & ~0x1fffUL)) {
 			rc = set_validity_icpt(scb_s, 0x0043U);
@@ -597,13 +614,14 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			goto unpin;
 		}
 		/* Validity 0x0044 will be checked by SIE */
+		vsie_page->riccbd_gpa = gpa;
 		scb_s->riccbd = hpa;
 	}
 	if ((scb_s->ecb & ECB_GS) && !(scb_s->ecd & ECD_HOSTREGMGMT)) {
 		unsigned long sdnxc;
 
-		gpa = scb_o->sdnxo & ~0xfUL;
-		sdnxc = scb_o->sdnxo & 0xfUL;
+		gpa = READ_ONCE(scb_o->sdnxo) & ~0xfUL;
+		sdnxc = READ_ONCE(scb_o->sdnxo) & 0xfUL;
 		if (!gpa || !(gpa & ~0x1fffUL)) {
 			rc = set_validity_icpt(scb_s, 0x10b0U);
 			goto unpin;
@@ -624,6 +642,7 @@ static int pin_blocks(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 			rc = set_validity_icpt(scb_s, 0x10b0U);
 			goto unpin;
 		}
+		vsie_page->sdnx_gpa = gpa;
 		scb_s->sdnxo = hpa | sdnxc;
 	}
 	return 0;
@@ -768,7 +787,7 @@ static void retry_vsie_icpt(struct vsie_page *vsie_page)
 static int handle_stfle(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page)
 {
 	struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s;
-	__u32 fac = vsie_page->scb_o->fac & 0x7ffffff8U;
+	__u32 fac = READ_ONCE(vsie_page->scb_o->fac) & 0x7ffffff8U;
 
 	if (fac && test_kvm_facility(vcpu->kvm, 7)) {
 		retry_vsie_icpt(vsie_page);
@@ -894,7 +913,7 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu,
 	 * External calls have to lead to a kick of the vcpu and
 	 * therefore the vsie -> Simulate Wait state.
 	 */
-	atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT);
 	/*
 	 * We have to adjust the g3 epoch by the g2 epoch. The epoch will
 	 * automatically be adjusted on tod clock changes via kvm_sync_clock.
@@ -916,7 +935,7 @@ static void register_shadow_scb(struct kvm_vcpu *vcpu,
  */
 static void unregister_shadow_scb(struct kvm_vcpu *vcpu)
 {
-	atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT);
 	WRITE_ONCE(vcpu->arch.vsie_block, NULL);
 }