Initial file dump from open source releaseHEADmaster

12 files changed, 4173 insertions, 0 deletions

diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
new file mode 100644
index 00000000..70b46eac
--- /dev/null
+++ b/arch/s390/kvm/Kconfig
@@ -0,0 +1,52 @@
+#
+# KVM configuration
+#
+source "virt/kvm/Kconfig"
+
+menuconfig VIRTUALIZATION
+	def_bool y
+	prompt "KVM"
+	---help---
+	  Say Y here to get to see options for using your Linux host to run other
+	  operating systems inside virtual machines (guests).
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and disabled.
+
+if VIRTUALIZATION
+
+config KVM
+	def_tristate y
+	prompt "Kernel-based Virtual Machine (KVM) support"
+	depends on HAVE_KVM
+	select PREEMPT_NOTIFIERS
+	select ANON_INODES
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select HAVE_KVM_EVENTFD
+	---help---
+	  Support hosting paravirtualized guest machines using the SIE
+	  virtualization capability on the mainframe. This should work
+	  on any 64bit machine.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  To compile this as a module, choose M here: the module
+	  will be called kvm.
+
+	  If unsure, say N.
+
+config KVM_S390_UCONTROL
+	bool "Userspace controlled virtual machines"
+	depends on KVM
+	---help---
+	  Allow CAP_SYS_ADMIN users to create KVM virtual machines that are
+	  controlled by userspace.
+
+	  If unsure, say N.
+
+# OK, it's a little counter-intuitive to do this, but it puts it neatly under
+# the virtualization menu.
+source drivers/vhost/Kconfig
+
+endif # VIRTUALIZATION
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
new file mode 100644
index 00000000..40b4c647
--- /dev/null
+++ b/arch/s390/kvm/Makefile
@@ -0,0 +1,15 @@
+# Makefile for kernel virtual machines on s390
+#
+# Copyright IBM Corp. 2008
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License (version 2 only)
+# as published by the Free Software Foundation.
+
+KVM := ../../../virt/kvm
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o
+
+ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
+
+kvm-objs := $(common-objs) kvm-s390.o intercept.o interrupt.o priv.o sigp.o diag.o
+obj-$(CONFIG_KVM) += kvm.o
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
new file mode 100644
index 00000000..6acb24d6
--- /dev/null
+++ b/arch/s390/kvm/diag.c
@@ -0,0 +1,150 @@
+/*
+ * handling diagnose instructions
+ *
+ * Copyright IBM Corp. 2008, 2011
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <asm/virtio-ccw.h>
+#include "kvm-s390.h"
+#include "trace.h"
+#include "trace-s390.h"
+
+static int diag_release_pages(struct kvm_vcpu *vcpu)
+{
+	unsigned long start, end;
+	unsigned long prefix  = vcpu->arch.sie_block->prefix;
+
+	start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+	end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + 4096;
+
+	if (start & ~PAGE_MASK || end & ~PAGE_MASK || start > end
+	    || start < 2 * PAGE_SIZE)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	VCPU_EVENT(vcpu, 5, "diag release pages %lX %lX", start, end);
+	vcpu->stat.diagnose_10++;
+
+	/* we checked for start > end above */
+	if (end < prefix || start >= prefix + 2 * PAGE_SIZE) {
+		gmap_discard(start, end, vcpu->arch.gmap);
+	} else {
+		if (start < prefix)
+			gmap_discard(start, prefix, vcpu->arch.gmap);
+		if (end >= prefix)
+			gmap_discard(prefix + 2 * PAGE_SIZE,
+				     end, vcpu->arch.gmap);
+	}
+	return 0;
+}
+
+static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
+	vcpu->stat.diagnose_44++;
+	kvm_vcpu_on_spin(vcpu);
+	return 0;
+}
+
+static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_vcpu *tcpu;
+	int tid;
+	int i;
+
+	tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+	vcpu->stat.diagnose_9c++;
+	VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d", tid);
+
+	if (tid == vcpu->vcpu_id)
+		return 0;
+
+	kvm_for_each_vcpu(i, tcpu, kvm)
+		if (tcpu->vcpu_id == tid) {
+			kvm_vcpu_yield_to(tcpu);
+			break;
+		}
+
+	return 0;
+}
+
+static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
+{
+	unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
+	unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
+
+	VCPU_EVENT(vcpu, 5, "diag ipl functions, subcode %lx", subcode);
+	switch (subcode) {
+	case 3:
+		vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
+		break;
+	case 4:
+		vcpu->run->s390_reset_flags = 0;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+	vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
+	vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
+	vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
+	vcpu->run->exit_reason = KVM_EXIT_S390_RESET;
+	VCPU_EVENT(vcpu, 3, "requesting userspace resets %llx",
+	  vcpu->run->s390_reset_flags);
+	trace_kvm_s390_request_resets(vcpu->run->s390_reset_flags);
+	return -EREMOTE;
+}
+
+static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu)
+{
+	int ret, idx;
+
+	/* No virtio-ccw notification? Get out quickly. */
+	if (!vcpu->kvm->arch.css_support ||
+	    (vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))
+		return -EOPNOTSUPP;
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	/*
+	 * The layout is as follows:
+	 * - gpr 2 contains the subchannel id (passed as addr)
+	 * - gpr 3 contains the virtqueue index (passed as datamatch)
+	 */
+	ret = kvm_io_bus_write(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS,
+				vcpu->run->s.regs.gprs[2],
+				8, &vcpu->run->s.regs.gprs[3]);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	/* kvm_io_bus_write returns -EOPNOTSUPP if it found no match. */
+	return ret < 0 ? ret : 0;
+}
+
+int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
+{
+	int code = kvm_s390_get_base_disp_rs(vcpu) & 0xffff;
+
+	trace_kvm_s390_handle_diag(vcpu, code);
+	switch (code) {
+	case 0x10:
+		return diag_release_pages(vcpu);
+	case 0x44:
+		return __diag_time_slice_end(vcpu);
+	case 0x9c:
+		return __diag_time_slice_end_directed(vcpu);
+	case 0x308:
+		return __diag_ipl_functions(vcpu);
+	case 0x500:
+		return __diag_virtio_hypercall(vcpu);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
new file mode 100644
index 00000000..302e0e52
--- /dev/null
+++ b/arch/s390/kvm/gaccess.h
@@ -0,0 +1,103 @@
+/*
+ * access guest memory
+ *
+ * Copyright IBM Corp. 2008, 2009
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ */
+
+#ifndef __KVM_S390_GACCESS_H
+#define __KVM_S390_GACCESS_H
+
+#include <linux/compiler.h>
+#include <linux/kvm_host.h>
+#include <asm/uaccess.h>
+#include "kvm-s390.h"
+
+static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu,
+					  void __user *gptr,
+					  int prefixing)
+{
+	unsigned long prefix  = vcpu->arch.sie_block->prefix;
+	unsigned long gaddr = (unsigned long) gptr;
+	unsigned long uaddr;
+
+	if (prefixing) {
+		if (gaddr < 2 * PAGE_SIZE)
+			gaddr += prefix;
+		else if ((gaddr >= prefix) && (gaddr < prefix + 2 * PAGE_SIZE))
+			gaddr -= prefix;
+	}
+	uaddr = gmap_fault(gaddr, vcpu->arch.gmap);
+	if (IS_ERR_VALUE(uaddr))
+		uaddr = -EFAULT;
+	return (void __user *)uaddr;
+}
+
+#define get_guest(vcpu, x, gptr)				\
+({								\
+	__typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\
+	int __mask = sizeof(__typeof__(*(gptr))) - 1;		\
+	int __ret = PTR_RET((void __force *)__uptr);		\
+								\
+	if (!__ret) {						\
+		BUG_ON((unsigned long)__uptr & __mask);		\
+		__ret = get_user(x, __uptr);			\
+	}							\
+	__ret;							\
+})
+
+#define put_guest(vcpu, x, gptr)				\
+({								\
+	__typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\
+	int __mask = sizeof(__typeof__(*(gptr))) - 1;		\
+	int __ret = PTR_RET((void __force *)__uptr);		\
+								\
+	if (!__ret) {						\
+		BUG_ON((unsigned long)__uptr & __mask);		\
+		__ret = put_user(x, __uptr);			\
+	}							\
+	__ret;							\
+})
+
+static inline int __copy_guest(struct kvm_vcpu *vcpu, unsigned long to,
+			       unsigned long from, unsigned long len,
+			       int to_guest, int prefixing)
+{
+	unsigned long _len, rc;
+	void __user *uptr;
+
+	while (len) {
+		uptr = to_guest ? (void __user *)to : (void __user *)from;
+		uptr = __gptr_to_uptr(vcpu, uptr, prefixing);
+		if (IS_ERR((void __force *)uptr))
+			return -EFAULT;
+		_len = PAGE_SIZE - ((unsigned long)uptr & (PAGE_SIZE - 1));
+		_len = min(_len, len);
+		if (to_guest)
+			rc = copy_to_user((void __user *) uptr, (void *)from, _len);
+		else
+			rc = copy_from_user((void *)to, (void __user *)uptr, _len);
+		if (rc)
+			return -EFAULT;
+		len -= _len;
+		from += _len;
+		to += _len;
+	}
+	return 0;
+}
+
+#define copy_to_guest(vcpu, to, from, size) \
+	__copy_guest(vcpu, to, (unsigned long)from, size, 1, 1)
+#define copy_from_guest(vcpu, to, from, size) \
+	__copy_guest(vcpu, (unsigned long)to, from, size, 0, 1)
+#define copy_to_guest_absolute(vcpu, to, from, size) \
+	__copy_guest(vcpu, to, (unsigned long)from, size, 1, 0)
+#define copy_from_guest_absolute(vcpu, to, from, size) \
+	__copy_guest(vcpu, (unsigned long)to, from, size, 0, 0)
+
+#endif /* __KVM_S390_GACCESS_H */
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
new file mode 100644
index 00000000..b7d1b2ed
--- /dev/null
+++ b/arch/s390/kvm/intercept.c
@@ -0,0 +1,280 @@
+/*
+ * in-kernel handling for sie intercepts
+ *
+ * Copyright IBM Corp. 2008, 2009
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/errno.h>
+#include <linux/pagemap.h>
+
+#include <asm/kvm_host.h>
+
+#include "kvm-s390.h"
+#include "gaccess.h"
+#include "trace.h"
+#include "trace-s390.h"
+
+static int handle_lctlg(struct kvm_vcpu *vcpu)
+{
+	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+	u64 useraddr;
+	int reg, rc;
+
+	vcpu->stat.instruction_lctlg++;
+
+	useraddr = kvm_s390_get_base_disp_rsy(vcpu);
+
+	if (useraddr & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	reg = reg1;
+
+	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
+	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr);
+
+	do {
+		rc = get_guest(vcpu, vcpu->arch.sie_block->gcr[reg],
+			       (u64 __user *) useraddr);
+		if (rc)
+			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		useraddr += 8;
+		if (reg == reg3)
+			break;
+		reg = (reg + 1) % 16;
+	} while (1);
+	return 0;
+}
+
+static int handle_lctl(struct kvm_vcpu *vcpu)
+{
+	int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+	u64 useraddr;
+	u32 val = 0;
+	int reg, rc;
+
+	vcpu->stat.instruction_lctl++;
+
+	useraddr = kvm_s390_get_base_disp_rs(vcpu);
+
+	if (useraddr & 3)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3,
+		   useraddr);
+	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr);
+
+	reg = reg1;
+	do {
+		rc = get_guest(vcpu, val, (u32 __user *) useraddr);
+		if (rc)
+			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul;
+		vcpu->arch.sie_block->gcr[reg] |= val;
+		useraddr += 4;
+		if (reg == reg3)
+			break;
+		reg = (reg + 1) % 16;
+	} while (1);
+	return 0;
+}
+
+static const intercept_handler_t eb_handlers[256] = {
+	[0x2f] = handle_lctlg,
+	[0x8a] = kvm_s390_handle_priv_eb,
+};
+
+static int handle_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
+static const intercept_handler_t instruction_handlers[256] = {
+	[0x01] = kvm_s390_handle_01,
+	[0x82] = kvm_s390_handle_lpsw,
+	[0x83] = kvm_s390_handle_diag,
+	[0xae] = kvm_s390_handle_sigp,
+	[0xb2] = kvm_s390_handle_b2,
+	[0xb7] = handle_lctl,
+	[0xb9] = kvm_s390_handle_b9,
+	[0xe5] = kvm_s390_handle_e5,
+	[0xeb] = handle_eb,
+};
+
+static int handle_noop(struct kvm_vcpu *vcpu)
+{
+	switch (vcpu->arch.sie_block->icptcode) {
+	case 0x0:
+		vcpu->stat.exit_null++;
+		break;
+	case 0x10:
+		vcpu->stat.exit_external_request++;
+		break;
+	case 0x14:
+		vcpu->stat.exit_external_interrupt++;
+		break;
+	default:
+		break; /* nothing */
+	}
+	return 0;
+}
+
+static int handle_stop(struct kvm_vcpu *vcpu)
+{
+	int rc = 0;
+
+	vcpu->stat.exit_stop_request++;
+	spin_lock_bh(&vcpu->arch.local_int.lock);
+
+	trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits);
+
+	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP;
+		rc = SIE_INTERCEPT_RERUNVCPU;
+		vcpu->run->exit_reason = KVM_EXIT_INTR;
+	}
+
+	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
+		atomic_set_mask(CPUSTAT_STOPPED,
+				&vcpu->arch.sie_block->cpuflags);
+		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
+		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
+		rc = -EOPNOTSUPP;
+	}
+
+	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
+		/* store status must be called unlocked. Since local_int.lock
+		 * only protects local_int.* and not guest memory we can give
+		 * up the lock here */
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
+		rc = kvm_s390_vcpu_store_status(vcpu,
+						KVM_S390_STORE_STATUS_NOADDR);
+		if (rc >= 0)
+			rc = -EOPNOTSUPP;
+	} else
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
+	return rc;
+}
+
+static int handle_validity(struct kvm_vcpu *vcpu)
+{
+	unsigned long vmaddr;
+	int viwhy = vcpu->arch.sie_block->ipb >> 16;
+	int rc;
+
+	vcpu->stat.exit_validity++;
+	trace_kvm_s390_intercept_validity(vcpu, viwhy);
+	if (viwhy == 0x37) {
+		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix,
+				    vcpu->arch.gmap);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		rc = fault_in_pages_writeable((char __user *) vmaddr,
+			 PAGE_SIZE);
+		if (rc) {
+			/* user will receive sigsegv, exit to user */
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix + PAGE_SIZE,
+				    vcpu->arch.gmap);
+		if (IS_ERR_VALUE(vmaddr)) {
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+		rc = fault_in_pages_writeable((char __user *) vmaddr,
+			 PAGE_SIZE);
+		if (rc) {
+			/* user will receive sigsegv, exit to user */
+			rc = -EOPNOTSUPP;
+			goto out;
+		}
+	} else
+		rc = -EOPNOTSUPP;
+
+out:
+	if (rc)
+		VCPU_EVENT(vcpu, 2, "unhandled validity intercept code %d",
+			   viwhy);
+	return rc;
+}
+
+static int handle_instruction(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	vcpu->stat.exit_instruction++;
+	trace_kvm_s390_intercept_instruction(vcpu,
+					     vcpu->arch.sie_block->ipa,
+					     vcpu->arch.sie_block->ipb);
+	handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
+static int handle_prog(struct kvm_vcpu *vcpu)
+{
+	vcpu->stat.exit_program_interruption++;
+	trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc);
+	return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc);
+}
+
+static int handle_instruction_and_prog(struct kvm_vcpu *vcpu)
+{
+	int rc, rc2;
+
+	vcpu->stat.exit_instr_and_program++;
+	rc = handle_instruction(vcpu);
+	rc2 = handle_prog(vcpu);
+
+	if (rc == -EOPNOTSUPP)
+		vcpu->arch.sie_block->icptcode = 0x04;
+	if (rc)
+		return rc;
+	return rc2;
+}
+
+static const intercept_handler_t intercept_funcs[] = {
+	[0x00 >> 2] = handle_noop,
+	[0x04 >> 2] = handle_instruction,
+	[0x08 >> 2] = handle_prog,
+	[0x0C >> 2] = handle_instruction_and_prog,
+	[0x10 >> 2] = handle_noop,
+	[0x14 >> 2] = handle_noop,
+	[0x18 >> 2] = handle_noop,
+	[0x1C >> 2] = kvm_s390_handle_wait,
+	[0x20 >> 2] = handle_validity,
+	[0x28 >> 2] = handle_stop,
+};
+
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t func;
+	u8 code = vcpu->arch.sie_block->icptcode;
+
+	if (code & 3 || (code >> 2) >= ARRAY_SIZE(intercept_funcs))
+		return -EOPNOTSUPP;
+	func = intercept_funcs[code >> 2];
+	if (func)
+		return func(vcpu);
+	return -EOPNOTSUPP;
+}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
new file mode 100644
index 00000000..bc79ab00
--- /dev/null
+++ b/arch/s390/kvm/interrupt.c
@@ -0,0 +1,841 @@
+/*
+ * handling kvm guest interrupts
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ */
+
+#include <linux/interrupt.h>
+#include <linux/kvm_host.h>
+#include <linux/hrtimer.h>
+#include <linux/signal.h>
+#include <linux/slab.h>
+#include <asm/asm-offsets.h>
+#include <asm/uaccess.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+#include "trace-s390.h"
+
+#define IOINT_SCHID_MASK 0x0000ffff
+#define IOINT_SSID_MASK 0x00030000
+#define IOINT_CSSID_MASK 0x03fc0000
+#define IOINT_AI_MASK 0x04000000
+
+static int is_ioint(u64 type)
+{
+	return ((type & 0xfffe0000u) != 0xfffe0000u);
+}
+
+static int psw_extint_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
+}
+
+static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
+}
+
+static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
+{
+	return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
+}
+
+static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
+{
+	if ((vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PER) ||
+	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO) ||
+	    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT))
+		return 0;
+	return 1;
+}
+
+static u64 int_word_to_isc_bits(u32 int_word)
+{
+	u8 isc = (int_word & 0x38000000) >> 27;
+
+	return (0x80 >> isc) << 24;
+}
+
+static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
+				      struct kvm_s390_interrupt_info *inti)
+{
+	switch (inti->type) {
+	case KVM_S390_INT_EXTERNAL_CALL:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x2000ul)
+			return 1;
+		return 0;
+	case KVM_S390_INT_EMERGENCY:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x4000ul)
+			return 1;
+		return 0;
+	case KVM_S390_INT_SERVICE:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
+			return 1;
+		return 0;
+	case KVM_S390_INT_VIRTIO:
+		if (psw_extint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[0] & 0x200ul)
+			return 1;
+		return 0;
+	case KVM_S390_PROGRAM_INT:
+	case KVM_S390_SIGP_STOP:
+	case KVM_S390_SIGP_SET_PREFIX:
+	case KVM_S390_RESTART:
+		return 1;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[14] & inti->mchk.cr14)
+			return 1;
+		return 0;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (psw_ioint_disabled(vcpu))
+			return 0;
+		if (vcpu->arch.sie_block->gcr[6] &
+		    int_word_to_isc_bits(inti->io.io_int_word))
+			return 1;
+		return 0;
+	default:
+		printk(KERN_WARNING "illegal interrupt type %llx\n",
+		       inti->type);
+		BUG();
+	}
+	return 0;
+}
+
+static void __set_cpu_idle(struct kvm_vcpu *vcpu)
+{
+	BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
+	atomic_set_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+}
+
+static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
+{
+	BUG_ON(vcpu->vcpu_id > KVM_MAX_VCPUS - 1);
+	atomic_clear_mask(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
+	clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
+}
+
+static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
+{
+	atomic_clear_mask(CPUSTAT_ECALL_PEND |
+		CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
+		&vcpu->arch.sie_block->cpuflags);
+	vcpu->arch.sie_block->lctl = 0x0000;
+	vcpu->arch.sie_block->ictl &= ~ICTL_LPSW;
+}
+
+static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
+{
+	atomic_set_mask(flag, &vcpu->arch.sie_block->cpuflags);
+}
+
+static void __set_intercept_indicator(struct kvm_vcpu *vcpu,
+				      struct kvm_s390_interrupt_info *inti)
+{
+	switch (inti->type) {
+	case KVM_S390_INT_EXTERNAL_CALL:
+	case KVM_S390_INT_EMERGENCY:
+	case KVM_S390_INT_SERVICE:
+	case KVM_S390_INT_VIRTIO:
+		if (psw_extint_disabled(vcpu))
+			__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR0;
+		break;
+	case KVM_S390_SIGP_STOP:
+		__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
+		break;
+	case KVM_S390_MCHK:
+		if (psw_mchk_disabled(vcpu))
+			vcpu->arch.sie_block->ictl |= ICTL_LPSW;
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR14;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (psw_ioint_disabled(vcpu))
+			__set_cpuflag(vcpu, CPUSTAT_IO_INT);
+		else
+			vcpu->arch.sie_block->lctl |= LCTL_CR6;
+		break;
+	default:
+		BUG();
+	}
+}
+
+static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
+				   struct kvm_s390_interrupt_info *inti)
+{
+	const unsigned short table[] = { 2, 4, 4, 6 };
+	int rc = 0;
+
+	switch (inti->type) {
+	case KVM_S390_INT_EMERGENCY:
+		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
+		vcpu->stat.deliver_emergency_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->emerg.code, 0);
+		rc  = put_guest(vcpu, 0x1201, (u16 __user *)__LC_EXT_INT_CODE);
+		rc |= put_guest(vcpu, inti->emerg.code,
+				(u16 __user *)__LC_EXT_CPU_ADDR);
+		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_EXT_NEW_PSW, sizeof(psw_t));
+		break;
+	case KVM_S390_INT_EXTERNAL_CALL:
+		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
+		vcpu->stat.deliver_external_call++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->extcall.code, 0);
+		rc  = put_guest(vcpu, 0x1202, (u16 __user *)__LC_EXT_INT_CODE);
+		rc |= put_guest(vcpu, inti->extcall.code,
+				(u16 __user *)__LC_EXT_CPU_ADDR);
+		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_EXT_NEW_PSW, sizeof(psw_t));
+		break;
+	case KVM_S390_INT_SERVICE:
+		VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
+			   inti->ext.ext_params);
+		vcpu->stat.deliver_service_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->ext.ext_params, 0);
+		rc  = put_guest(vcpu, 0x2401, (u16 __user *)__LC_EXT_INT_CODE);
+		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_EXT_NEW_PSW, sizeof(psw_t));
+		rc |= put_guest(vcpu, inti->ext.ext_params,
+				(u32 __user *)__LC_EXT_PARAMS);
+		break;
+	case KVM_S390_INT_VIRTIO:
+		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
+			   inti->ext.ext_params, inti->ext.ext_params2);
+		vcpu->stat.deliver_virtio_interrupt++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->ext.ext_params,
+						 inti->ext.ext_params2);
+		rc  = put_guest(vcpu, 0x2603, (u16 __user *)__LC_EXT_INT_CODE);
+		rc |= put_guest(vcpu, 0x0d00, (u16 __user *)__LC_EXT_CPU_ADDR);
+		rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_EXT_NEW_PSW, sizeof(psw_t));
+		rc |= put_guest(vcpu, inti->ext.ext_params,
+				(u32 __user *)__LC_EXT_PARAMS);
+		rc |= put_guest(vcpu, inti->ext.ext_params2,
+				(u64 __user *)__LC_EXT_PARAMS2);
+		break;
+	case KVM_S390_SIGP_STOP:
+		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
+		vcpu->stat.deliver_stop_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 0, 0);
+		__set_intercept_indicator(vcpu, inti);
+		break;
+
+	case KVM_S390_SIGP_SET_PREFIX:
+		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
+			   inti->prefix.address);
+		vcpu->stat.deliver_prefix_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->prefix.address, 0);
+		kvm_s390_set_prefix(vcpu, inti->prefix.address);
+		break;
+
+	case KVM_S390_RESTART:
+		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
+		vcpu->stat.deliver_restart_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 0, 0);
+		rc  = copy_to_guest(vcpu,
+				    offsetof(struct _lowcore, restart_old_psw),
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      offsetof(struct _lowcore, restart_psw),
+				      sizeof(psw_t));
+		atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+		break;
+	case KVM_S390_PROGRAM_INT:
+		VCPU_EVENT(vcpu, 4, "interrupt: pgm check code:%x, ilc:%x",
+			   inti->pgm.code,
+			   table[vcpu->arch.sie_block->ipa >> 14]);
+		vcpu->stat.deliver_program_int++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->pgm.code, 0);
+		rc  = put_guest(vcpu, inti->pgm.code, (u16 __user *)__LC_PGM_INT_CODE);
+		rc |= put_guest(vcpu, table[vcpu->arch.sie_block->ipa >> 14],
+				(u16 __user *)__LC_PGM_ILC);
+		rc |= copy_to_guest(vcpu, __LC_PGM_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_PGM_NEW_PSW, sizeof(psw_t));
+		break;
+
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 4, "interrupt: machine check mcic=%llx",
+			   inti->mchk.mcic);
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->mchk.cr14,
+						 inti->mchk.mcic);
+		rc  = kvm_s390_vcpu_store_status(vcpu,
+						 KVM_S390_STORE_STATUS_PREFIXED);
+		rc |= put_guest(vcpu, inti->mchk.mcic, (u64 __user *) __LC_MCCK_CODE);
+		rc |= copy_to_guest(vcpu, __LC_MCK_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_MCK_NEW_PSW, sizeof(psw_t));
+		break;
+
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+	{
+		__u32 param0 = ((__u32)inti->io.subchannel_id << 16) |
+			inti->io.subchannel_nr;
+		__u64 param1 = ((__u64)inti->io.io_int_parm << 32) |
+			inti->io.io_int_word;
+		VCPU_EVENT(vcpu, 4, "interrupt: I/O %llx", inti->type);
+		vcpu->stat.deliver_io_int++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 param0, param1);
+		rc  = put_guest(vcpu, inti->io.subchannel_id,
+				(u16 __user *) __LC_SUBCHANNEL_ID);
+		rc |= put_guest(vcpu, inti->io.subchannel_nr,
+				(u16 __user *) __LC_SUBCHANNEL_NR);
+		rc |= put_guest(vcpu, inti->io.io_int_parm,
+				(u32 __user *) __LC_IO_INT_PARM);
+		rc |= put_guest(vcpu, inti->io.io_int_word,
+				(u32 __user *) __LC_IO_INT_WORD);
+		rc |= copy_to_guest(vcpu, __LC_IO_OLD_PSW,
+				    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+		rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+				      __LC_IO_NEW_PSW, sizeof(psw_t));
+		break;
+	}
+	default:
+		BUG();
+	}
+	if (rc) {
+		printk("kvm: The guest lowcore is not mapped during interrupt "
+		       "delivery, killing userspace\n");
+		do_exit(SIGKILL);
+	}
+}
+
+static int __try_deliver_ckc_interrupt(struct kvm_vcpu *vcpu)
+{
+	int rc;
+
+	if (psw_extint_disabled(vcpu))
+		return 0;
+	if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+		return 0;
+	rc  = put_guest(vcpu, 0x1004, (u16 __user *)__LC_EXT_INT_CODE);
+	rc |= copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+			    &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+	rc |= copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+			      __LC_EXT_NEW_PSW, sizeof(psw_t));
+	if (rc) {
+		printk("kvm: The guest lowcore is not mapped during interrupt "
+			"delivery, killing userspace\n");
+		do_exit(SIGKILL);
+	}
+	return 1;
+}
+
+static int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *inti;
+	int rc = 0;
+
+	if (atomic_read(&li->active)) {
+		spin_lock_bh(&li->lock);
+		list_for_each_entry(inti, &li->list, list)
+			if (__interrupt_is_deliverable(vcpu, inti)) {
+				rc = 1;
+				break;
+			}
+		spin_unlock_bh(&li->lock);
+	}
+
+	if ((!rc) && atomic_read(&fi->active)) {
+		spin_lock(&fi->lock);
+		list_for_each_entry(inti, &fi->list, list)
+			if (__interrupt_is_deliverable(vcpu, inti)) {
+				rc = 1;
+				break;
+			}
+		spin_unlock(&fi->lock);
+	}
+
+	if ((!rc) && (vcpu->arch.sie_block->ckc <
+		get_tod_clock() + vcpu->arch.sie_block->epoch)) {
+		if ((!psw_extint_disabled(vcpu)) &&
+			(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+			rc = 1;
+	}
+
+	return rc;
+}
+
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
+{
+	u64 now, sltime;
+	DECLARE_WAITQUEUE(wait, current);
+
+	vcpu->stat.exit_wait_state++;
+	if (kvm_cpu_has_interrupt(vcpu))
+		return 0;
+
+	__set_cpu_idle(vcpu);
+	spin_lock_bh(&vcpu->arch.local_int.lock);
+	vcpu->arch.local_int.timer_due = 0;
+	spin_unlock_bh(&vcpu->arch.local_int.lock);
+
+	if (psw_interrupts_disabled(vcpu)) {
+		VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
+		__unset_cpu_idle(vcpu);
+		return -EOPNOTSUPP; /* disabled wait */
+	}
+
+	if (psw_extint_disabled(vcpu) ||
+	    (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))) {
+		VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
+		goto no_timer;
+	}
+
+	now = get_tod_clock() + vcpu->arch.sie_block->epoch;
+	if (vcpu->arch.sie_block->ckc < now) {
+		__unset_cpu_idle(vcpu);
+		return 0;
+	}
+
+	sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
+
+	hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
+	VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);
+no_timer:
+	spin_lock(&vcpu->arch.local_int.float_int->lock);
+	spin_lock_bh(&vcpu->arch.local_int.lock);
+	add_wait_queue(&vcpu->arch.local_int.wq, &wait);
+	while (list_empty(&vcpu->arch.local_int.list) &&
+		list_empty(&vcpu->arch.local_int.float_int->list) &&
+		(!vcpu->arch.local_int.timer_due) &&
+		!signal_pending(current)) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		spin_unlock_bh(&vcpu->arch.local_int.lock);
+		spin_unlock(&vcpu->arch.local_int.float_int->lock);
+		schedule();
+		spin_lock(&vcpu->arch.local_int.float_int->lock);
+		spin_lock_bh(&vcpu->arch.local_int.lock);
+	}
+	__unset_cpu_idle(vcpu);
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&vcpu->arch.local_int.wq, &wait);
+	spin_unlock_bh(&vcpu->arch.local_int.lock);
+	spin_unlock(&vcpu->arch.local_int.float_int->lock);
+	hrtimer_try_to_cancel(&vcpu->arch.ckc_timer);
+	return 0;
+}
+
+void kvm_s390_tasklet(unsigned long parm)
+{
+	struct kvm_vcpu *vcpu = (struct kvm_vcpu *) parm;
+
+	spin_lock(&vcpu->arch.local_int.lock);
+	vcpu->arch.local_int.timer_due = 1;
+	if (waitqueue_active(&vcpu->arch.local_int.wq))
+		wake_up_interruptible(&vcpu->arch.local_int.wq);
+	spin_unlock(&vcpu->arch.local_int.lock);
+}
+
+/*
+ * low level hrtimer wake routine. Because this runs in hardirq context
+ * we schedule a tasklet to do the real work.
+ */
+enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
+	tasklet_schedule(&vcpu->arch.tasklet);
+
+	return HRTIMER_NORESTART;
+}
+
+void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *n, *inti = NULL;
+	int deliver;
+
+	__reset_intercept_indicators(vcpu);
+	if (atomic_read(&li->active)) {
+		do {
+			deliver = 0;
+			spin_lock_bh(&li->lock);
+			list_for_each_entry_safe(inti, n, &li->list, list) {
+				if (__interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&li->list))
+				atomic_set(&li->active, 0);
+			spin_unlock_bh(&li->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+
+	if ((vcpu->arch.sie_block->ckc <
+		get_tod_clock() + vcpu->arch.sie_block->epoch))
+		__try_deliver_ckc_interrupt(vcpu);
+
+	if (atomic_read(&fi->active)) {
+		do {
+			deliver = 0;
+			spin_lock(&fi->lock);
+			list_for_each_entry_safe(inti, n, &fi->list, list) {
+				if (__interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&fi->list))
+				atomic_set(&fi->active, 0);
+			spin_unlock(&fi->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+}
+
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_float_interrupt *fi = vcpu->arch.local_int.float_int;
+	struct kvm_s390_interrupt_info  *n, *inti = NULL;
+	int deliver;
+
+	__reset_intercept_indicators(vcpu);
+	if (atomic_read(&li->active)) {
+		do {
+			deliver = 0;
+			spin_lock_bh(&li->lock);
+			list_for_each_entry_safe(inti, n, &li->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&li->list))
+				atomic_set(&li->active, 0);
+			spin_unlock_bh(&li->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+
+	if (atomic_read(&fi->active)) {
+		do {
+			deliver = 0;
+			spin_lock(&fi->lock);
+			list_for_each_entry_safe(inti, n, &fi->list, list) {
+				if ((inti->type == KVM_S390_MCHK) &&
+				    __interrupt_is_deliverable(vcpu, inti)) {
+					list_del(&inti->list);
+					deliver = 1;
+					break;
+				}
+				__set_intercept_indicator(vcpu, inti);
+			}
+			if (list_empty(&fi->list))
+				atomic_set(&fi->active, 0);
+			spin_unlock(&fi->lock);
+			if (deliver) {
+				__do_deliver_interrupt(vcpu, inti);
+				kfree(inti);
+			}
+		} while (deliver);
+	}
+}
+
+int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	struct kvm_s390_interrupt_info *inti;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	inti->type = KVM_S390_PROGRAM_INT;
+	inti->pgm.code = code;
+
+	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1);
+	spin_lock_bh(&li->lock);
+	list_add(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	BUG_ON(waitqueue_active(&li->wq));
+	spin_unlock_bh(&li->lock);
+	return 0;
+}
+
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid)
+{
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info *inti, *iter;
+
+	if ((!schid && !cr6) || (schid && cr6))
+		return NULL;
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	inti = NULL;
+	list_for_each_entry(iter, &fi->list, list) {
+		if (!is_ioint(iter->type))
+			continue;
+		if (cr6 &&
+		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
+			continue;
+		if (schid) {
+			if (((schid & 0x00000000ffff0000) >> 16) !=
+			    iter->io.subchannel_id)
+				continue;
+			if ((schid & 0x000000000000ffff) !=
+			    iter->io.subchannel_nr)
+				continue;
+		}
+		inti = iter;
+		break;
+	}
+	if (inti)
+		list_del_init(&inti->list);
+	if (list_empty(&fi->list))
+		atomic_set(&fi->active, 0);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+	return inti;
+}
+
+int kvm_s390_inject_vm(struct kvm *kvm,
+		       struct kvm_s390_interrupt *s390int)
+{
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_float_interrupt *fi;
+	struct kvm_s390_interrupt_info *inti, *iter;
+	int sigcpu;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	switch (s390int->type) {
+	case KVM_S390_INT_VIRTIO:
+		VM_EVENT(kvm, 5, "inject: virtio parm:%x,parm64:%llx",
+			 s390int->parm, s390int->parm64);
+		inti->type = s390int->type;
+		inti->ext.ext_params = s390int->parm;
+		inti->ext.ext_params2 = s390int->parm64;
+		break;
+	case KVM_S390_INT_SERVICE:
+		VM_EVENT(kvm, 5, "inject: sclp parm:%x", s390int->parm);
+		inti->type = s390int->type;
+		inti->ext.ext_params = s390int->parm;
+		break;
+	case KVM_S390_PROGRAM_INT:
+	case KVM_S390_SIGP_STOP:
+	case KVM_S390_INT_EXTERNAL_CALL:
+	case KVM_S390_INT_EMERGENCY:
+		kfree(inti);
+		return -EINVAL;
+	case KVM_S390_MCHK:
+		VM_EVENT(kvm, 5, "inject: machine check parm64:%llx",
+			 s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.cr14 = s390int->parm; /* upper bits are not used */
+		inti->mchk.mcic = s390int->parm64;
+		break;
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+		if (s390int->type & IOINT_AI_MASK)
+			VM_EVENT(kvm, 5, "%s", "inject: I/O (AI)");
+		else
+			VM_EVENT(kvm, 5, "inject: I/O css %x ss %x schid %04x",
+				 s390int->type & IOINT_CSSID_MASK,
+				 s390int->type & IOINT_SSID_MASK,
+				 s390int->type & IOINT_SCHID_MASK);
+		inti->type = s390int->type;
+		inti->io.subchannel_id = s390int->parm >> 16;
+		inti->io.subchannel_nr = s390int->parm & 0x0000ffffu;
+		inti->io.io_int_parm = s390int->parm64 >> 32;
+		inti->io.io_int_word = s390int->parm64 & 0x00000000ffffffffull;
+		break;
+	default:
+		kfree(inti);
+		return -EINVAL;
+	}
+	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
+				 2);
+
+	mutex_lock(&kvm->lock);
+	fi = &kvm->arch.float_int;
+	spin_lock(&fi->lock);
+	if (!is_ioint(inti->type))
+		list_add_tail(&inti->list, &fi->list);
+	else {
+		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+
+		/* Keep I/O interrupts sorted in isc order. */
+		list_for_each_entry(iter, &fi->list, list) {
+			if (!is_ioint(iter->type))
+				continue;
+			if (int_word_to_isc_bits(iter->io.io_int_word)
+			    <= isc_bits)
+				continue;
+			break;
+		}
+		list_add_tail(&inti->list, &iter->list);
+	}
+	atomic_set(&fi->active, 1);
+	sigcpu = find_first_bit(fi->idle_mask, KVM_MAX_VCPUS);
+	if (sigcpu == KVM_MAX_VCPUS) {
+		do {
+			sigcpu = fi->next_rr_cpu++;
+			if (sigcpu == KVM_MAX_VCPUS)
+				sigcpu = fi->next_rr_cpu = 0;
+		} while (fi->local_int[sigcpu] == NULL);
+	}
+	li = fi->local_int[sigcpu];
+	spin_lock_bh(&li->lock);
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	spin_unlock_bh(&li->lock);
+	spin_unlock(&fi->lock);
+	mutex_unlock(&kvm->lock);
+	return 0;
+}
+
+int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
+			 struct kvm_s390_interrupt *s390int)
+{
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_interrupt_info *inti;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	switch (s390int->type) {
+	case KVM_S390_PROGRAM_INT:
+		if (s390int->parm & 0xffff0000) {
+			kfree(inti);
+			return -EINVAL;
+		}
+		inti->type = s390int->type;
+		inti->pgm.code = s390int->parm;
+		VCPU_EVENT(vcpu, 3, "inject: program check %d (from user)",
+			   s390int->parm);
+		break;
+	case KVM_S390_SIGP_SET_PREFIX:
+		inti->prefix.address = s390int->parm;
+		inti->type = s390int->type;
+		VCPU_EVENT(vcpu, 3, "inject: set prefix to %x (from user)",
+			   s390int->parm);
+		break;
+	case KVM_S390_SIGP_STOP:
+	case KVM_S390_RESTART:
+		VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
+		inti->type = s390int->type;
+		break;
+	case KVM_S390_INT_EXTERNAL_CALL:
+		if (s390int->parm & 0xffff0000) {
+			kfree(inti);
+			return -EINVAL;
+		}
+		VCPU_EVENT(vcpu, 3, "inject: external call source-cpu:%u",
+			   s390int->parm);
+		inti->type = s390int->type;
+		inti->extcall.code = s390int->parm;
+		break;
+	case KVM_S390_INT_EMERGENCY:
+		if (s390int->parm & 0xffff0000) {
+			kfree(inti);
+			return -EINVAL;
+		}
+		VCPU_EVENT(vcpu, 3, "inject: emergency %u\n", s390int->parm);
+		inti->type = s390int->type;
+		inti->emerg.code = s390int->parm;
+		break;
+	case KVM_S390_MCHK:
+		VCPU_EVENT(vcpu, 5, "inject: machine check parm64:%llx",
+			   s390int->parm64);
+		inti->type = s390int->type;
+		inti->mchk.mcic = s390int->parm64;
+		break;
+	case KVM_S390_INT_VIRTIO:
+	case KVM_S390_INT_SERVICE:
+	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
+	default:
+		kfree(inti);
+		return -EINVAL;
+	}
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, s390int->type, s390int->parm,
+				   s390int->parm64, 2);
+
+	mutex_lock(&vcpu->kvm->lock);
+	li = &vcpu->arch.local_int;
+	spin_lock_bh(&li->lock);
+	if (inti->type == KVM_S390_PROGRAM_INT)
+		list_add(&inti->list, &li->list);
+	else
+		list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	if (inti->type == KVM_S390_SIGP_STOP)
+		li->action_bits |= ACTION_STOP_ON_STOP;
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&vcpu->arch.local_int.wq);
+	spin_unlock_bh(&li->lock);
+	mutex_unlock(&vcpu->kvm->lock);
+	return 0;
+}
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
new file mode 100644
index 00000000..412fbc5d
--- /dev/null
+++ b/arch/s390/kvm/kvm-s390.c
@@ -0,0 +1,1034 @@
+/*
+ * hosting zSeries kernel virtual machines
+ *
+ * Copyright IBM Corp. 2008, 2009
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ *               Heiko Carstens <heiko.carstens@de.ibm.com>
+ *               Christian Ehrhardt <ehrhardt@de.ibm.com>
+ */
+
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/hrtimer.h>
+#include <linux/init.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <asm/asm-offsets.h>
+#include <asm/lowcore.h>
+#include <asm/pgtable.h>
+#include <asm/nmi.h>
+#include <asm/switch_to.h>
+#include <asm/sclp.h>
+#include "kvm-s390.h"
+#include "gaccess.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+#include "trace-s390.h"
+
+#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+
+struct kvm_stats_debugfs_item debugfs_entries[] = {
+	{ "userspace_handled", VCPU_STAT(exit_userspace) },
+	{ "exit_null", VCPU_STAT(exit_null) },
+	{ "exit_validity", VCPU_STAT(exit_validity) },
+	{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
+	{ "exit_external_request", VCPU_STAT(exit_external_request) },
+	{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
+	{ "exit_instruction", VCPU_STAT(exit_instruction) },
+	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
+	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
+	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
+	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
+	{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
+	{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
+	{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
+	{ "deliver_virtio_interrupt", VCPU_STAT(deliver_virtio_interrupt) },
+	{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
+	{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
+	{ "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_stidp", VCPU_STAT(instruction_stidp) },
+	{ "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_stsch", VCPU_STAT(instruction_stsch) },
+	{ "instruction_chsc", VCPU_STAT(instruction_chsc) },
+	{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
+	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
+	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
+	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
+	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
+	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
+	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
+	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
+	{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
+	{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
+	{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
+	{ "diagnose_10", VCPU_STAT(diagnose_10) },
+	{ "diagnose_44", VCPU_STAT(diagnose_44) },
+	{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
+	{ NULL }
+};
+
+static unsigned long long *facilities;
+
+/* Section: not file related */
+int kvm_arch_hardware_enable(void)
+{
+	/* every s390 is virtualization enabled ;-) */
+	return 0;
+}
+
+int kvm_arch_hardware_setup(void)
+{
+	return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+int kvm_arch_init(void *opaque)
+{
+	return 0;
+}
+
+/* Section: device related */
+long kvm_arch_dev_ioctl(struct file *filp,
+			unsigned int ioctl, unsigned long arg)
+{
+	if (ioctl == KVM_S390_ENABLE_SIE)
+		return s390_enable_sie();
+	return -EINVAL;
+}
+
+int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
+{
+	int r;
+
+	switch (ext) {
+	case KVM_CAP_S390_PSW:
+	case KVM_CAP_S390_GMAP:
+	case KVM_CAP_SYNC_MMU:
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_CAP_S390_UCONTROL:
+#endif
+	case KVM_CAP_SYNC_REGS:
+	case KVM_CAP_ONE_REG:
+	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_S390_CSS_SUPPORT:
+	case KVM_CAP_IOEVENTFD:
+		r = 1;
+		break;
+	case KVM_CAP_NR_VCPUS:
+	case KVM_CAP_MAX_VCPUS:
+		r = KVM_MAX_VCPUS;
+		break;
+	case KVM_CAP_NR_MEMSLOTS:
+		r = KVM_USER_MEM_SLOTS;
+		break;
+	case KVM_CAP_S390_COW:
+		r = MACHINE_HAS_ESOP;
+		break;
+	default:
+		r = 0;
+	}
+	return r;
+}
+
+/* Section: vm related */
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+			       struct kvm_dirty_log *log)
+{
+	return 0;
+}
+
+long kvm_arch_vm_ioctl(struct file *filp,
+		       unsigned int ioctl, unsigned long arg)
+{
+	struct kvm *kvm = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	int r;
+
+	switch (ioctl) {
+	case KVM_S390_INTERRUPT: {
+		struct kvm_s390_interrupt s390int;
+
+		r = -EFAULT;
+		if (copy_from_user(&s390int, argp, sizeof(s390int)))
+			break;
+		r = kvm_s390_inject_vm(kvm, &s390int);
+		break;
+	}
+	default:
+		r = -ENOTTY;
+	}
+
+	return r;
+}
+
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
+{
+	int rc;
+	char debug_name[16];
+
+	rc = -EINVAL;
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (type & ~KVM_VM_S390_UCONTROL)
+		goto out_err;
+	if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
+		goto out_err;
+#else
+	if (type)
+		goto out_err;
+#endif
+
+	rc = s390_enable_sie();
+	if (rc)
+		goto out_err;
+
+	rc = -ENOMEM;
+
+	kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+	if (!kvm->arch.sca)
+		goto out_err;
+
+	sprintf(debug_name, "kvm-%u", current->pid);
+
+	kvm->arch.dbf = debug_register(debug_name, 8, 2, 8 * sizeof(long));
+	if (!kvm->arch.dbf)
+		goto out_nodbf;
+
+	spin_lock_init(&kvm->arch.float_int.lock);
+	INIT_LIST_HEAD(&kvm->arch.float_int.list);
+
+	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
+	VM_EVENT(kvm, 3, "%s", "vm created");
+
+	if (type & KVM_VM_S390_UCONTROL) {
+		kvm->arch.gmap = NULL;
+	} else {
+		kvm->arch.gmap = gmap_alloc(current->mm);
+		if (!kvm->arch.gmap)
+			goto out_nogmap;
+	}
+
+	kvm->arch.css_support = 0;
+
+	return 0;
+out_nogmap:
+	debug_unregister(kvm->arch.dbf);
+out_nodbf:
+	free_page((unsigned long)(kvm->arch.sca));
+out_err:
+	return rc;
+}
+
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
+	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
+	if (!kvm_is_ucontrol(vcpu->kvm)) {
+		clear_bit(63 - vcpu->vcpu_id,
+			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
+		if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
+		    (__u64) vcpu->arch.sie_block)
+			vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
+	}
+	smp_mb();
+
+	if (kvm_is_ucontrol(vcpu->kvm))
+		gmap_free(vcpu->arch.gmap);
+
+	free_page((unsigned long)(vcpu->arch.sie_block));
+	kvm_vcpu_uninit(vcpu);
+	kfree(vcpu);
+}
+
+static void kvm_free_vcpus(struct kvm *kvm)
+{
+	unsigned int i;
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		kvm_arch_vcpu_destroy(vcpu);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
+		kvm->vcpus[i] = NULL;
+
+	atomic_set(&kvm->online_vcpus, 0);
+	mutex_unlock(&kvm->lock);
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+	kvm_free_vcpus(kvm);
+	free_page((unsigned long)(kvm->arch.sca));
+	debug_unregister(kvm->arch.dbf);
+	if (!kvm_is_ucontrol(kvm))
+		gmap_free(kvm->arch.gmap);
+}
+
+/* Section: vcpu related */
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		vcpu->arch.gmap = gmap_alloc(current->mm);
+		if (!vcpu->arch.gmap)
+			return -ENOMEM;
+		return 0;
+	}
+
+	vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+	vcpu->run->kvm_valid_regs = KVM_SYNC_PREFIX |
+				    KVM_SYNC_GPRS |
+				    KVM_SYNC_ACRS |
+				    KVM_SYNC_CRS;
+	return 0;
+}
+
+void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	save_fp_regs(&vcpu->arch.host_fpregs);
+	save_access_regs(vcpu->arch.host_acrs);
+	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
+	restore_fp_regs(&vcpu->arch.guest_fpregs);
+	restore_access_regs(vcpu->run->s.regs.acrs);
+	gmap_enable(vcpu->arch.gmap);
+	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+}
+
+void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	gmap_disable(vcpu->arch.gmap);
+	save_fp_regs(&vcpu->arch.guest_fpregs);
+	save_access_regs(vcpu->run->s.regs.acrs);
+	restore_fp_regs(&vcpu->arch.host_fpregs);
+	restore_access_regs(vcpu->arch.host_acrs);
+}
+
+static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
+{
+	/* this equals initial cpu reset in pop, but we don't switch to ESA */
+	vcpu->arch.sie_block->gpsw.mask = 0UL;
+	vcpu->arch.sie_block->gpsw.addr = 0UL;
+	kvm_s390_set_prefix(vcpu, 0);
+	vcpu->arch.sie_block->cputm     = 0UL;
+	vcpu->arch.sie_block->ckc       = 0UL;
+	vcpu->arch.sie_block->todpr     = 0;
+	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
+	vcpu->arch.sie_block->gcr[0]  = 0xE0UL;
+	vcpu->arch.sie_block->gcr[14] = 0xC2000000UL;
+	vcpu->arch.guest_fpregs.fpc = 0;
+	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
+	vcpu->arch.sie_block->gbea = 1;
+	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+}
+
+int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
+{
+	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
+						    CPUSTAT_SM |
+						    CPUSTAT_STOPPED);
+	vcpu->arch.sie_block->ecb   = 6;
+	vcpu->arch.sie_block->eca   = 0xC1002001U;
+	vcpu->arch.sie_block->fac   = (int) (long) facilities;
+	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
+		     (unsigned long) vcpu);
+	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
+	get_cpu_id(&vcpu->arch.cpu_id);
+	vcpu->arch.cpu_id.version = 0xff;
+	return 0;
+}
+
+struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
+				      unsigned int id)
+{
+	struct kvm_vcpu *vcpu;
+	int rc = -EINVAL;
+
+	if (id >= KVM_MAX_VCPUS)
+		goto out;
+
+	rc = -ENOMEM;
+
+	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+	if (!vcpu)
+		goto out;
+
+	vcpu->arch.sie_block = (struct kvm_s390_sie_block *)
+					get_zeroed_page(GFP_KERNEL);
+
+	if (!vcpu->arch.sie_block)
+		goto out_free_cpu;
+
+	vcpu->arch.sie_block->icpua = id;
+	if (!kvm_is_ucontrol(kvm)) {
+		if (!kvm->arch.sca) {
+			WARN_ON_ONCE(1);
+			goto out_free_cpu;
+		}
+		if (!kvm->arch.sca->cpu[id].sda)
+			kvm->arch.sca->cpu[id].sda =
+				(__u64) vcpu->arch.sie_block;
+		vcpu->arch.sie_block->scaoh =
+			(__u32)(((__u64)kvm->arch.sca) >> 32);
+		vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
+		set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
+	}
+
+	spin_lock_init(&vcpu->arch.local_int.lock);
+	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
+	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
+	spin_lock(&kvm->arch.float_int.lock);
+	kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
+	init_waitqueue_head(&vcpu->arch.local_int.wq);
+	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+	spin_unlock(&kvm->arch.float_int.lock);
+
+	rc = kvm_vcpu_init(vcpu, kvm, id);
+	if (rc)
+		goto out_free_sie_block;
+	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+		 vcpu->arch.sie_block);
+	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
+
+	return vcpu;
+out_free_sie_block:
+	free_page((unsigned long)(vcpu->arch.sie_block));
+out_free_cpu:
+	kfree(vcpu);
+out:
+	return ERR_PTR(rc);
+}
+
+int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
+{
+	/* kvm common code refers to this, but never calls it */
+	BUG();
+	return 0;
+}
+
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
+{
+	/* kvm common code refers to this, but never calls it */
+	BUG();
+	return 0;
+}
+
+static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
+					   struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_S390_TODPR:
+		r = put_user(vcpu->arch.sie_block->todpr,
+			     (u32 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_EPOCHDIFF:
+		r = put_user(vcpu->arch.sie_block->epoch,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CPU_TIMER:
+		r = put_user(vcpu->arch.sie_block->cputm,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CLOCK_COMP:
+		r = put_user(vcpu->arch.sie_block->ckc,
+			     (u64 __user *)reg->addr);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
+static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
+					   struct kvm_one_reg *reg)
+{
+	int r = -EINVAL;
+
+	switch (reg->id) {
+	case KVM_REG_S390_TODPR:
+		r = get_user(vcpu->arch.sie_block->todpr,
+			     (u32 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_EPOCHDIFF:
+		r = get_user(vcpu->arch.sie_block->epoch,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CPU_TIMER:
+		r = get_user(vcpu->arch.sie_block->cputm,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_CLOCK_COMP:
+		r = get_user(vcpu->arch.sie_block->ckc,
+			     (u64 __user *)reg->addr);
+		break;
+	default:
+		break;
+	}
+
+	return r;
+}
+
+static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
+{
+	kvm_s390_vcpu_initial_reset(vcpu);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	memcpy(&vcpu->run->s.regs.gprs, &regs->gprs, sizeof(regs->gprs));
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
+{
+	memcpy(&regs->gprs, &vcpu->run->s.regs.gprs, sizeof(regs->gprs));
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	memcpy(&vcpu->run->s.regs.acrs, &sregs->acrs, sizeof(sregs->acrs));
+	memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
+	restore_access_regs(vcpu->run->s.regs.acrs);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+				  struct kvm_sregs *sregs)
+{
+	memcpy(&sregs->acrs, &vcpu->run->s.regs.acrs, sizeof(sregs->acrs));
+	memcpy(&sregs->crs, &vcpu->arch.sie_block->gcr, sizeof(sregs->crs));
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	memcpy(&vcpu->arch.guest_fpregs.fprs, &fpu->fprs, sizeof(fpu->fprs));
+	vcpu->arch.guest_fpregs.fpc = fpu->fpc & FPC_VALID_MASK;
+	restore_fp_regs(&vcpu->arch.guest_fpregs);
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
+{
+	memcpy(&fpu->fprs, &vcpu->arch.guest_fpregs.fprs, sizeof(fpu->fprs));
+	fpu->fpc = vcpu->arch.guest_fpregs.fpc;
+	return 0;
+}
+
+static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
+{
+	int rc = 0;
+
+	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
+		rc = -EBUSY;
+	else {
+		vcpu->run->psw_mask = psw.mask;
+		vcpu->run->psw_addr = psw.addr;
+	}
+	return rc;
+}
+
+int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
+				  struct kvm_translation *tr)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+					struct kvm_guest_debug *dbg)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state)
+{
+	return -EINVAL; /* not implemented yet */
+}
+
+static int __vcpu_run(struct kvm_vcpu *vcpu)
+{
+	int rc;
+
+	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
+
+	if (need_resched())
+		schedule();
+
+	if (test_thread_flag(TIF_MCCK_PENDING))
+		s390_handle_mcck();
+
+	if (!kvm_is_ucontrol(vcpu->kvm))
+		kvm_s390_deliver_pending_interrupts(vcpu);
+
+	vcpu->arch.sie_block->icptcode = 0;
+	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
+		   atomic_read(&vcpu->arch.sie_block->cpuflags));
+	trace_kvm_s390_sie_enter(vcpu,
+				 atomic_read(&vcpu->arch.sie_block->cpuflags));
+
+	/*
+	 * As PF_VCPU will be used in fault handler, between guest_enter
+	 * and guest_exit should be no uaccess.
+	 */
+	preempt_disable();
+	kvm_guest_enter();
+	preempt_enable();
+	rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
+	kvm_guest_exit();
+
+	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
+		   vcpu->arch.sie_block->icptcode);
+	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
+
+	if (rc) {
+		if (kvm_is_ucontrol(vcpu->kvm)) {
+			rc = SIE_INTERCEPT_UCONTROL;
+		} else {
+			VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+			trace_kvm_s390_sie_fault(vcpu);
+			rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		}
+	}
+
+	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	return rc;
+}
+
+int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	int rc;
+	sigset_t sigsaved;
+
+rerun_vcpu:
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+
+	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
+
+	BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
+
+	switch (kvm_run->exit_reason) {
+	case KVM_EXIT_S390_SIEIC:
+	case KVM_EXIT_UNKNOWN:
+	case KVM_EXIT_INTR:
+	case KVM_EXIT_S390_RESET:
+	case KVM_EXIT_S390_UCONTROL:
+	case KVM_EXIT_S390_TSCH:
+		break;
+	default:
+		BUG();
+	}
+
+	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
+	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_PREFIX;
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
+		kvm_run->kvm_dirty_regs &= ~KVM_SYNC_CRS;
+		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	}
+
+	might_fault();
+
+	do {
+		rc = __vcpu_run(vcpu);
+		if (rc)
+			break;
+		if (kvm_is_ucontrol(vcpu->kvm))
+			rc = -EOPNOTSUPP;
+		else
+			rc = kvm_handle_sie_intercept(vcpu);
+	} while (!signal_pending(current) && !rc);
+
+	if (rc == SIE_INTERCEPT_RERUNVCPU)
+		goto rerun_vcpu;
+
+	if (signal_pending(current) && !rc) {
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		rc = -EINTR;
+	}
+
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (rc == SIE_INTERCEPT_UCONTROL) {
+		kvm_run->exit_reason = KVM_EXIT_S390_UCONTROL;
+		kvm_run->s390_ucontrol.trans_exc_code =
+			current->thread.gmap_addr;
+		kvm_run->s390_ucontrol.pgm_code = 0x10;
+		rc = 0;
+	}
+#endif
+
+	if (rc == -EOPNOTSUPP) {
+		/* intercept cannot be handled in-kernel, prepare kvm-run */
+		kvm_run->exit_reason         = KVM_EXIT_S390_SIEIC;
+		kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+		kvm_run->s390_sieic.ipa      = vcpu->arch.sie_block->ipa;
+		kvm_run->s390_sieic.ipb      = vcpu->arch.sie_block->ipb;
+		rc = 0;
+	}
+
+	if (rc == -EREMOTE) {
+		/* intercept was handled, but userspace support is needed
+		 * kvm_run has been prepared by the handler */
+		rc = 0;
+	}
+
+	kvm_run->psw_mask     = vcpu->arch.sie_block->gpsw.mask;
+	kvm_run->psw_addr     = vcpu->arch.sie_block->gpsw.addr;
+	kvm_run->s.regs.prefix = vcpu->arch.sie_block->prefix;
+	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
+
+	if (vcpu->sigset_active)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	vcpu->stat.exit_userspace++;
+	return rc;
+}
+
+static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, void *from,
+		       unsigned long n, int prefix)
+{
+	if (prefix)
+		return copy_to_guest(vcpu, guestdest, from, n);
+	else
+		return copy_to_guest_absolute(vcpu, guestdest, from, n);
+}
+
+/*
+ * store status at address
+ * we use have two special cases:
+ * KVM_S390_STORE_STATUS_NOADDR: -> 0x1200 on 64 bit
+ * KVM_S390_STORE_STATUS_PREFIXED: -> prefix
+ */
+int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
+{
+	unsigned char archmode = 1;
+	int prefix;
+
+	if (addr == KVM_S390_STORE_STATUS_NOADDR) {
+		if (copy_to_guest_absolute(vcpu, 163ul, &archmode, 1))
+			return -EFAULT;
+		addr = SAVE_AREA_BASE;
+		prefix = 0;
+	} else if (addr == KVM_S390_STORE_STATUS_PREFIXED) {
+		if (copy_to_guest(vcpu, 163ul, &archmode, 1))
+			return -EFAULT;
+		addr = SAVE_AREA_BASE;
+		prefix = 1;
+	} else
+		prefix = 0;
+
+	/*
+	 * The guest FPRS and ACRS are in the host FPRS/ACRS due to the lazy
+	 * copying in vcpu load/put. Lets update our copies before we save
+	 * it into the save area
+	 */
+	save_fp_regs(&vcpu->arch.guest_fpregs);
+	save_access_regs(vcpu->run->s.regs.acrs);
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
+			vcpu->arch.guest_fpregs.fprs, 128, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
+			vcpu->run->s.regs.gprs, 128, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
+			&vcpu->arch.sie_block->gpsw, 16, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, pref_reg),
+			&vcpu->arch.sie_block->prefix, 4, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu,
+			addr + offsetof(struct save_area, fp_ctrl_reg),
+			&vcpu->arch.guest_fpregs.fpc, 4, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, tod_reg),
+			&vcpu->arch.sie_block->todpr, 4, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, timer),
+			&vcpu->arch.sie_block->cputm, 8, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
+			&vcpu->arch.sie_block->ckc, 8, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
+			&vcpu->run->s.regs.acrs, 64, prefix))
+		return -EFAULT;
+
+	if (__guestcopy(vcpu,
+			addr + offsetof(struct save_area, ctrl_regs),
+			&vcpu->arch.sie_block->gcr, 128, prefix))
+		return -EFAULT;
+	return 0;
+}
+
+static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+				     struct kvm_enable_cap *cap)
+{
+	int r;
+
+	if (cap->flags)
+		return -EINVAL;
+
+	switch (cap->cap) {
+	case KVM_CAP_S390_CSS_SUPPORT:
+		if (!vcpu->kvm->arch.css_support) {
+			vcpu->kvm->arch.css_support = 1;
+			trace_kvm_s390_enable_css(vcpu->kvm);
+		}
+		r = 0;
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+	return r;
+}
+
+long kvm_arch_vcpu_ioctl(struct file *filp,
+			 unsigned int ioctl, unsigned long arg)
+{
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	long r;
+
+	switch (ioctl) {
+	case KVM_S390_INTERRUPT: {
+		struct kvm_s390_interrupt s390int;
+
+		r = -EFAULT;
+		if (copy_from_user(&s390int, argp, sizeof(s390int)))
+			break;
+		r = kvm_s390_inject_vcpu(vcpu, &s390int);
+		break;
+	}
+	case KVM_S390_STORE_STATUS:
+		r = kvm_s390_vcpu_store_status(vcpu, arg);
+		break;
+	case KVM_S390_SET_INITIAL_PSW: {
+		psw_t psw;
+
+		r = -EFAULT;
+		if (copy_from_user(&psw, argp, sizeof(psw)))
+			break;
+		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
+		break;
+	}
+	case KVM_S390_INITIAL_RESET:
+		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+		break;
+	case KVM_SET_ONE_REG:
+	case KVM_GET_ONE_REG: {
+		struct kvm_one_reg reg;
+		r = -EFAULT;
+		if (copy_from_user(&reg, argp, sizeof(reg)))
+			break;
+		if (ioctl == KVM_SET_ONE_REG)
+			r = kvm_arch_vcpu_ioctl_set_one_reg(vcpu, &reg);
+		else
+			r = kvm_arch_vcpu_ioctl_get_one_reg(vcpu, &reg);
+		break;
+	}
+#ifdef CONFIG_KVM_S390_UCONTROL
+	case KVM_S390_UCAS_MAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_map_segment(vcpu->arch.gmap, ucasmap.user_addr,
+				     ucasmap.vcpu_addr, ucasmap.length);
+		break;
+	}
+	case KVM_S390_UCAS_UNMAP: {
+		struct kvm_s390_ucas_mapping ucasmap;
+
+		if (copy_from_user(&ucasmap, argp, sizeof(ucasmap))) {
+			r = -EFAULT;
+			break;
+		}
+
+		if (!kvm_is_ucontrol(vcpu->kvm)) {
+			r = -EINVAL;
+			break;
+		}
+
+		r = gmap_unmap_segment(vcpu->arch.gmap, ucasmap.vcpu_addr,
+			ucasmap.length);
+		break;
+	}
+#endif
+	case KVM_S390_VCPU_FAULT: {
+		r = gmap_fault(arg, vcpu->arch.gmap);
+		if (!IS_ERR_VALUE(r))
+			r = 0;
+		break;
+	}
+	case KVM_ENABLE_CAP:
+	{
+		struct kvm_enable_cap cap;
+		r = -EFAULT;
+		if (copy_from_user(&cap, argp, sizeof(cap)))
+			break;
+		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
+		break;
+	}
+	default:
+		r = -ENOTTY;
+	}
+	return r;
+}
+
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if ((vmf->pgoff == KVM_S390_SIE_PAGE_OFFSET)
+		 && (kvm_is_ucontrol(vcpu->kvm))) {
+		vmf->page = virt_to_page(vcpu->arch.sie_block);
+		get_page(vmf->page);
+		return 0;
+	}
+#endif
+	return VM_FAULT_SIGBUS;
+}
+
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
+{
+	return 0;
+}
+
+/* Section: memory related */
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_userspace_memory_region *mem,
+				   enum kvm_mr_change change)
+{
+	/* A few sanity checks. We can have memory slots which have to be
+	   located/ended at a segment boundary (1MB). The memory in userland is
+	   ok to be fragmented into various different vmas. It is okay to mmap()
+	   and munmap() stuff in this slot after doing this call at any time */
+
+	if (mem->userspace_addr & 0xffffful)
+		return -EINVAL;
+
+	if (mem->memory_size & 0xffffful)
+		return -EINVAL;
+
+	return 0;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old,
+				enum kvm_mr_change change)
+{
+	int rc;
+
+	/* If the basics of the memslot do not change, we do not want
+	 * to update the gmap. Every update causes several unnecessary
+	 * segment translation exceptions. This is usually handled just
+	 * fine by the normal fault handler + gmap, but it will also
+	 * cause faults on the prefix page of running guest CPUs.
+	 */
+	if (old->userspace_addr == mem->userspace_addr &&
+	    old->base_gfn * PAGE_SIZE == mem->guest_phys_addr &&
+	    old->npages * PAGE_SIZE == mem->memory_size)
+		return;
+
+	rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
+		mem->guest_phys_addr, mem->memory_size);
+	if (rc)
+		printk(KERN_WARNING "kvm-s390: failed to commit memory region\n");
+	return;
+}
+
+static int __init kvm_s390_init(void)
+{
+	int ret;
+	ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	if (ret)
+		return ret;
+
+	/*
+	 * guests can ask for up to 255+1 double words, we need a full page
+	 * to hold the maximum amount of facilities. On the other hand, we
+	 * only set facilities that are known to work in KVM.
+	 */
+	facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
+	if (!facilities) {
+		kvm_exit();
+		return -ENOMEM;
+	}
+	memcpy(facilities, S390_lowcore.stfle_fac_list, 16);
+	facilities[0] &= 0xff00fff3f47c0000ULL;
+	facilities[1] &= 0x001c000000000000ULL;
+	return 0;
+}
+
+static void __exit kvm_s390_exit(void)
+{
+	free_page((unsigned long) facilities);
+	kvm_exit();
+}
+
+module_init(kvm_s390_init);
+module_exit(kvm_s390_exit);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
new file mode 100644
index 00000000..efc14f68
--- /dev/null
+++ b/arch/s390/kvm/kvm-s390.h
@@ -0,0 +1,139 @@
+/*
+ * definition for kvm on s390
+ *
+ * Copyright IBM Corp. 2008, 2009
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ *               Christian Ehrhardt <ehrhardt@de.ibm.com>
+ */
+
+#ifndef ARCH_S390_KVM_S390_H
+#define ARCH_S390_KVM_S390_H
+
+#include <linux/hrtimer.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+
+/* The current code can have up to 256 pages for virtio */
+#define VIRTIODESCSPACE (256ul * 4096ul)
+
+typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
+
+/* negativ values are error codes, positive values for internal conditions */
+#define SIE_INTERCEPT_RERUNVCPU		(1<<0)
+#define SIE_INTERCEPT_UCONTROL		(1<<1)
+int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
+
+#define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\
+do { \
+	debug_sprintf_event(d_kvm->arch.dbf, d_loglevel, d_string "\n", \
+	  d_args); \
+} while (0)
+
+#define VCPU_EVENT(d_vcpu, d_loglevel, d_string, d_args...)\
+do { \
+	debug_sprintf_event(d_vcpu->kvm->arch.dbf, d_loglevel, \
+	  "%02d[%016lx-%016lx]: " d_string "\n", d_vcpu->vcpu_id, \
+	  d_vcpu->arch.sie_block->gpsw.mask, d_vcpu->arch.sie_block->gpsw.addr,\
+	  d_args); \
+} while (0)
+
+static inline int __cpu_is_stopped(struct kvm_vcpu *vcpu)
+{
+	return atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOP_INT;
+}
+
+static inline int kvm_is_ucontrol(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_S390_UCONTROL
+	if (kvm->arch.gmap)
+		return 0;
+	return 1;
+#else
+	return 0;
+#endif
+}
+
+static inline void kvm_s390_set_prefix(struct kvm_vcpu *vcpu, u32 prefix)
+{
+	vcpu->arch.sie_block->prefix = prefix & 0x7fffe000u;
+	vcpu->arch.sie_block->ihcpu  = 0xffff;
+}
+
+static inline u64 kvm_s390_get_base_disp_s(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline void kvm_s390_get_base_disp_sse(struct kvm_vcpu *vcpu,
+					      u64 *address1, u64 *address2)
+{
+	u32 base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+	u32 disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+	u32 base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+	u32 disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+
+	*address1 = (base1 ? vcpu->run->s.regs.gprs[base1] : 0) + disp1;
+	*address2 = (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rsy(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+			((vcpu->arch.sie_block->ipb & 0xff00) << 4);
+	/* The displacement is a 20bit _SIGNED_ value */
+	if (disp2 & 0x80000)
+		disp2+=0xfff00000;
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + (long)(int)disp2;
+}
+
+static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu)
+{
+	u32 base2 = vcpu->arch.sie_block->ipb >> 28;
+	u32 disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+
+	return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2;
+}
+
+int kvm_s390_handle_wait(struct kvm_vcpu *vcpu);
+enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer);
+void kvm_s390_tasklet(unsigned long parm);
+void kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu);
+void kvm_s390_deliver_pending_machine_checks(struct kvm_vcpu *vcpu);
+int __must_check kvm_s390_inject_vm(struct kvm *kvm,
+				    struct kvm_s390_interrupt *s390int);
+int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
+				      struct kvm_s390_interrupt *s390int);
+int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
+int __must_check kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
+struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
+						    u64 cr6, u64 schid);
+
+/* implemented in priv.c */
+int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_e5(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_01(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu);
+
+/* implemented in sigp.c */
+int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
+
+/* implemented in kvm-s390.c */
+int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu,
+				 unsigned long addr);
+/* implemented in diag.c */
+int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
+
+#endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
new file mode 100644
index 00000000..6bbd7b5a
--- /dev/null
+++ b/arch/s390/kvm/priv.c
@@ -0,0 +1,588 @@
+/*
+ * handling privileged instructions
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/gfp.h>
+#include <linux/errno.h>
+#include <linux/compat.h>
+#include <asm/asm-offsets.h>
+#include <asm/current.h>
+#include <asm/debug.h>
+#include <asm/ebcdic.h>
+#include <asm/sysinfo.h>
+#include <asm/ptrace.h>
+#include <asm/compat.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+#include "trace.h"
+
+static int handle_set_prefix(struct kvm_vcpu *vcpu)
+{
+	u64 operand2;
+	u32 address = 0;
+	u8 tmp;
+
+	vcpu->stat.instruction_spx++;
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
+
+	/* must be word boundary */
+	if (operand2 & 3)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	/* get the value */
+	if (get_guest(vcpu, address, (u32 __user *) operand2))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	address = address & 0x7fffe000u;
+
+	/* make sure that the new value is valid memory */
+	if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
+	   (copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	kvm_s390_set_prefix(vcpu, address);
+
+	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
+	trace_kvm_s390_handle_prefix(vcpu, 1, address);
+	return 0;
+}
+
+static int handle_store_prefix(struct kvm_vcpu *vcpu)
+{
+	u64 operand2;
+	u32 address;
+
+	vcpu->stat.instruction_stpx++;
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
+
+	/* must be word boundary */
+	if (operand2 & 3)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	address = vcpu->arch.sie_block->prefix;
+	address = address & 0x7fffe000u;
+
+	/* get the value */
+	if (put_guest(vcpu, address, (u32 __user *)operand2))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
+	trace_kvm_s390_handle_prefix(vcpu, 0, address);
+	return 0;
+}
+
+static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
+{
+	u64 useraddr;
+
+	vcpu->stat.instruction_stap++;
+
+	useraddr = kvm_s390_get_base_disp_s(vcpu);
+
+	if (useraddr & 1)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	if (put_guest(vcpu, vcpu->vcpu_id, (u16 __user *)useraddr))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", useraddr);
+	trace_kvm_s390_handle_stap(vcpu, useraddr);
+	return 0;
+}
+
+static int handle_skey(struct kvm_vcpu *vcpu)
+{
+	vcpu->stat.instruction_storage_key++;
+	vcpu->arch.sie_block->gpsw.addr -= 4;
+	VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
+	return 0;
+}
+
+static int handle_tpi(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_interrupt_info *inti;
+	u64 addr;
+	int cc;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+	if (addr & 3)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	cc = 0;
+	inti = kvm_s390_get_io_int(vcpu->kvm, vcpu->run->s.regs.crs[6], 0);
+	if (!inti)
+		goto no_interrupt;
+	cc = 1;
+	if (addr) {
+		/*
+		 * Store the two-word I/O interruption code into the
+		 * provided area.
+		 */
+		put_guest(vcpu, inti->io.subchannel_id, (u16 __user *) addr);
+		put_guest(vcpu, inti->io.subchannel_nr, (u16 __user *) (addr + 2));
+		put_guest(vcpu, inti->io.io_int_parm, (u32 __user *) (addr + 4));
+	} else {
+		/*
+		 * Store the three-word I/O interruption code into
+		 * the appropriate lowcore area.
+		 */
+		put_guest(vcpu, inti->io.subchannel_id, (u16 __user *) __LC_SUBCHANNEL_ID);
+		put_guest(vcpu, inti->io.subchannel_nr, (u16 __user *) __LC_SUBCHANNEL_NR);
+		put_guest(vcpu, inti->io.io_int_parm, (u32 __user *) __LC_IO_INT_PARM);
+		put_guest(vcpu, inti->io.io_int_word, (u32 __user *) __LC_IO_INT_WORD);
+	}
+	kfree(inti);
+no_interrupt:
+	/* Set condition code and we're done. */
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44;
+	return 0;
+}
+
+static int handle_tsch(struct kvm_vcpu *vcpu)
+{
+	struct kvm_s390_interrupt_info *inti;
+
+	inti = kvm_s390_get_io_int(vcpu->kvm, 0,
+				   vcpu->run->s.regs.gprs[1]);
+
+	/*
+	 * Prepare exit to userspace.
+	 * We indicate whether we dequeued a pending I/O interrupt
+	 * so that userspace can re-inject it if the instruction gets
+	 * a program check. While this may re-order the pending I/O
+	 * interrupts, this is no problem since the priority is kept
+	 * intact.
+	 */
+	vcpu->run->exit_reason = KVM_EXIT_S390_TSCH;
+	vcpu->run->s390_tsch.dequeued = !!inti;
+	if (inti) {
+		vcpu->run->s390_tsch.subchannel_id = inti->io.subchannel_id;
+		vcpu->run->s390_tsch.subchannel_nr = inti->io.subchannel_nr;
+		vcpu->run->s390_tsch.io_int_parm = inti->io.io_int_parm;
+		vcpu->run->s390_tsch.io_int_word = inti->io.io_int_word;
+	}
+	vcpu->run->s390_tsch.ipb = vcpu->arch.sie_block->ipb;
+	kfree(inti);
+	return -EREMOTE;
+}
+
+static int handle_io_inst(struct kvm_vcpu *vcpu)
+{
+	VCPU_EVENT(vcpu, 4, "%s", "I/O instruction");
+
+	if (vcpu->kvm->arch.css_support) {
+		/*
+		 * Most I/O instructions will be handled by userspace.
+		 * Exceptions are tpi and the interrupt portion of tsch.
+		 */
+		if (vcpu->arch.sie_block->ipa == 0xb236)
+			return handle_tpi(vcpu);
+		if (vcpu->arch.sie_block->ipa == 0xb235)
+			return handle_tsch(vcpu);
+		/* Handle in userspace. */
+		return -EOPNOTSUPP;
+	} else {
+		/*
+		 * Set condition code 3 to stop the guest from issueing channel
+		 * I/O instructions.
+		 */
+		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+		vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+		return 0;
+	}
+}
+
+static int handle_stfl(struct kvm_vcpu *vcpu)
+{
+	unsigned int facility_list;
+	int rc;
+
+	vcpu->stat.instruction_stfl++;
+	/* only pass the facility bits, which we can handle */
+	facility_list = S390_lowcore.stfl_fac_list & 0xff00fff3;
+
+	rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list),
+			   &facility_list, sizeof(facility_list));
+	if (rc)
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	VCPU_EVENT(vcpu, 5, "store facility list value %x", facility_list);
+	trace_kvm_s390_handle_stfl(vcpu, facility_list);
+	return 0;
+}
+
+static void handle_new_psw(struct kvm_vcpu *vcpu)
+{
+	/* Check whether the new psw is enabled for machine checks. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK)
+		kvm_s390_deliver_pending_machine_checks(vcpu);
+}
+
+#define PSW_MASK_ADDR_MODE (PSW_MASK_EA | PSW_MASK_BA)
+#define PSW_MASK_UNASSIGNED 0xb80800fe7fffffffUL
+#define PSW_ADDR_24 0x0000000000ffffffUL
+#define PSW_ADDR_31 0x000000007fffffffUL
+
+static int is_valid_psw(psw_t *psw) {
+	if (psw->mask & PSW_MASK_UNASSIGNED)
+		return 0;
+	if ((psw->mask & PSW_MASK_ADDR_MODE) == PSW_MASK_BA) {
+		if (psw->addr & ~PSW_ADDR_31)
+			return 0;
+	}
+	if (!(psw->mask & PSW_MASK_ADDR_MODE) && (psw->addr & ~PSW_ADDR_24))
+		return 0;
+	if ((psw->mask & PSW_MASK_ADDR_MODE) ==  PSW_MASK_EA)
+		return 0;
+	return 1;
+}
+
+int kvm_s390_handle_lpsw(struct kvm_vcpu *vcpu)
+{
+	psw_t *gpsw = &vcpu->arch.sie_block->gpsw;
+	psw_compat_t new_psw;
+	u64 addr;
+
+	if (gpsw->mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+	addr = kvm_s390_get_base_disp_s(vcpu);
+	if (addr & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw)))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	if (!(new_psw.mask & PSW32_MASK_BASE))
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	gpsw->mask = (new_psw.mask & ~PSW32_MASK_BASE) << 32;
+	gpsw->mask |= new_psw.addr & PSW32_ADDR_AMODE;
+	gpsw->addr = new_psw.addr & ~PSW32_ADDR_AMODE;
+	if (!is_valid_psw(gpsw))
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	handle_new_psw(vcpu);
+	return 0;
+}
+
+static int handle_lpswe(struct kvm_vcpu *vcpu)
+{
+	psw_t new_psw;
+	u64 addr;
+
+	addr = kvm_s390_get_base_disp_s(vcpu);
+	if (addr & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	if (copy_from_guest(vcpu, &new_psw, addr, sizeof(new_psw)))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	vcpu->arch.sie_block->gpsw = new_psw;
+	if (!is_valid_psw(&vcpu->arch.sie_block->gpsw))
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+	handle_new_psw(vcpu);
+	return 0;
+}
+
+static int handle_stidp(struct kvm_vcpu *vcpu)
+{
+	u64 operand2;
+
+	vcpu->stat.instruction_stidp++;
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
+
+	if (operand2 & 7)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	if (put_guest(vcpu, vcpu->arch.stidp_data, (u64 __user *)operand2))
+		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+
+	VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
+	return 0;
+}
+
+static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	int cpus = 0;
+	int n;
+
+	spin_lock(&fi->lock);
+	for (n = 0; n < KVM_MAX_VCPUS; n++)
+		if (fi->local_int[n])
+			cpus++;
+	spin_unlock(&fi->lock);
+
+	/* deal with other level 3 hypervisors */
+	if (stsi(mem, 3, 2, 2))
+		mem->count = 0;
+	if (mem->count < 8)
+		mem->count++;
+	for (n = mem->count - 1; n > 0 ; n--)
+		memcpy(&mem->vm[n], &mem->vm[n - 1], sizeof(mem->vm[0]));
+
+	mem->vm[0].cpus_total = cpus;
+	mem->vm[0].cpus_configured = cpus;
+	mem->vm[0].cpus_standby = 0;
+	mem->vm[0].cpus_reserved = 0;
+	mem->vm[0].caf = 1000;
+	memcpy(mem->vm[0].name, "KVMguest", 8);
+	ASCEBC(mem->vm[0].name, 8);
+	memcpy(mem->vm[0].cpi, "KVM/Linux       ", 16);
+	ASCEBC(mem->vm[0].cpi, 16);
+}
+
+static int handle_stsi(struct kvm_vcpu *vcpu)
+{
+	int fc = (vcpu->run->s.regs.gprs[0] & 0xf0000000) >> 28;
+	int sel1 = vcpu->run->s.regs.gprs[0] & 0xff;
+	int sel2 = vcpu->run->s.regs.gprs[1] & 0xffff;
+	unsigned long mem = 0;
+	u64 operand2;
+	int rc = 0;
+
+	vcpu->stat.instruction_stsi++;
+	VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
+
+	operand2 = kvm_s390_get_base_disp_s(vcpu);
+
+	if (operand2 & 0xfff && fc > 0)
+		return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+	switch (fc) {
+	case 0:
+		vcpu->run->s.regs.gprs[0] = 3 << 28;
+		vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+		return 0;
+	case 1: /* same handling for 1 and 2 */
+	case 2:
+		mem = get_zeroed_page(GFP_KERNEL);
+		if (!mem)
+			goto out_no_data;
+		if (stsi((void *) mem, fc, sel1, sel2))
+			goto out_no_data;
+		break;
+	case 3:
+		if (sel1 != 2 || sel2 != 2)
+			goto out_no_data;
+		mem = get_zeroed_page(GFP_KERNEL);
+		if (!mem)
+			goto out_no_data;
+		handle_stsi_3_2_2(vcpu, (void *) mem);
+		break;
+	default:
+		goto out_no_data;
+	}
+
+	if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) {
+		rc = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+		goto out_exception;
+	}
+	trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
+	free_page(mem);
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	vcpu->run->s.regs.gprs[0] = 0;
+	return 0;
+out_no_data:
+	/* condition code 3 */
+	vcpu->arch.sie_block->gpsw.mask |= 3ul << 44;
+out_exception:
+	free_page(mem);
+	return rc;
+}
+
+static const intercept_handler_t b2_handlers[256] = {
+	[0x02] = handle_stidp,
+	[0x10] = handle_set_prefix,
+	[0x11] = handle_store_prefix,
+	[0x12] = handle_store_cpu_address,
+	[0x29] = handle_skey,
+	[0x2a] = handle_skey,
+	[0x2b] = handle_skey,
+	[0x30] = handle_io_inst,
+	[0x31] = handle_io_inst,
+	[0x32] = handle_io_inst,
+	[0x33] = handle_io_inst,
+	[0x34] = handle_io_inst,
+	[0x35] = handle_io_inst,
+	[0x36] = handle_io_inst,
+	[0x37] = handle_io_inst,
+	[0x38] = handle_io_inst,
+	[0x39] = handle_io_inst,
+	[0x3a] = handle_io_inst,
+	[0x3b] = handle_io_inst,
+	[0x3c] = handle_io_inst,
+	[0x5f] = handle_io_inst,
+	[0x74] = handle_io_inst,
+	[0x76] = handle_io_inst,
+	[0x7d] = handle_stsi,
+	[0xb1] = handle_stfl,
+	[0xb2] = handle_lpswe,
+};
+
+int kvm_s390_handle_b2(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/*
+	 * a lot of B2 instructions are priviledged. We first check for
+	 * the privileged ones, that we can handle in the kernel. If the
+	 * kernel can handle this instruction, we check for the problem
+	 * state bit and (a) handle the instruction or (b) send a code 2
+	 * program check.
+	 * Anything else goes to userspace.*/
+	handler = b2_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler) {
+		if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+			return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+		else
+			return handler(vcpu);
+	}
+	return -EOPNOTSUPP;
+}
+
+static int handle_epsw(struct kvm_vcpu *vcpu)
+{
+	int reg1, reg2;
+
+	reg1 = (vcpu->arch.sie_block->ipb & 0x00f00000) >> 24;
+	reg2 = (vcpu->arch.sie_block->ipb & 0x000f0000) >> 16;
+
+	/* This basically extracts the mask half of the psw. */
+	vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000;
+	vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32;
+	if (reg2) {
+		vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000;
+		vcpu->run->s.regs.gprs[reg2] |=
+			vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff;
+	}
+	return 0;
+}
+
+static const intercept_handler_t b9_handlers[256] = {
+	[0x8d] = handle_epsw,
+	[0x9c] = handle_io_inst,
+};
+
+int kvm_s390_handle_b9(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* This is handled just as for the B2 instructions. */
+	handler = b9_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler) {
+		if ((handler != handle_epsw) &&
+		    (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE))
+			return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+		else
+			return handler(vcpu);
+	}
+	return -EOPNOTSUPP;
+}
+
+static const intercept_handler_t eb_handlers[256] = {
+	[0x8a] = handle_io_inst,
+};
+
+int kvm_s390_handle_priv_eb(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	/* All eb instructions that end up here are privileged. */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+	handler = eb_handlers[vcpu->arch.sie_block->ipb & 0xff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
+
+static int handle_tprot(struct kvm_vcpu *vcpu)
+{
+	u64 address1, address2;
+	struct vm_area_struct *vma;
+	unsigned long user_address;
+
+	vcpu->stat.instruction_tprot++;
+
+	kvm_s390_get_base_disp_sse(vcpu, &address1, &address2);
+
+	/* we only handle the Linux memory detection case:
+	 * access key == 0
+	 * guest DAT == off
+	 * everything else goes to userspace. */
+	if (address2 & 0xf0)
+		return -EOPNOTSUPP;
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT)
+		return -EOPNOTSUPP;
+
+	down_read(&current->mm->mmap_sem);
+	user_address = __gmap_translate(address1, vcpu->arch.gmap);
+	if (IS_ERR_VALUE(user_address))
+		goto out_inject;
+	vma = find_vma(current->mm, user_address);
+	if (!vma)
+		goto out_inject;
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (1ul << 44);
+	if (!(vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_READ))
+		vcpu->arch.sie_block->gpsw.mask |= (2ul << 44);
+
+	up_read(&current->mm->mmap_sem);
+	return 0;
+
+out_inject:
+	up_read(&current->mm->mmap_sem);
+	return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+}
+
+int kvm_s390_handle_e5(struct kvm_vcpu *vcpu)
+{
+	/* For e5xx... instructions we only handle TPROT */
+	if ((vcpu->arch.sie_block->ipa & 0x00ff) == 0x01)
+		return handle_tprot(vcpu);
+	return -EOPNOTSUPP;
+}
+
+static int handle_sckpf(struct kvm_vcpu *vcpu)
+{
+	u32 value;
+
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+
+	if (vcpu->run->s.regs.gprs[0] & 0x00000000ffff0000)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_SPECIFICATION);
+
+	value = vcpu->run->s.regs.gprs[0] & 0x000000000000ffff;
+	vcpu->arch.sie_block->todpr = value;
+
+	return 0;
+}
+
+static const intercept_handler_t x01_handlers[256] = {
+	[0x07] = handle_sckpf,
+};
+
+int kvm_s390_handle_01(struct kvm_vcpu *vcpu)
+{
+	intercept_handler_t handler;
+
+	handler = x01_handlers[vcpu->arch.sie_block->ipa & 0x00ff];
+	if (handler)
+		return handler(vcpu);
+	return -EOPNOTSUPP;
+}
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
new file mode 100644
index 00000000..1c48ab28
--- /dev/null
+++ b/arch/s390/kvm/sigp.c
@@ -0,0 +1,400 @@
+/*
+ * handling interprocessor communication
+ *
+ * Copyright IBM Corp. 2008, 2009
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ *
+ *    Author(s): Carsten Otte <cotte@de.ibm.com>
+ *               Christian Borntraeger <borntraeger@de.ibm.com>
+ *               Christian Ehrhardt <ehrhardt@de.ibm.com>
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/slab.h>
+#include <asm/sigp.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+#include "trace.h"
+
+static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
+			u64 *reg)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return SIGP_CC_NOT_OPERATIONAL;
+
+	spin_lock(&fi->lock);
+	if (fi->local_int[cpu_addr] == NULL)
+		rc = SIGP_CC_NOT_OPERATIONAL;
+	else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		   & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED)))
+		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+	else {
+		*reg &= 0xffffffff00000000UL;
+		if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		    & CPUSTAT_ECALL_PEND)
+			*reg |= SIGP_STATUS_EXT_CALL_PENDING;
+		if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		    & CPUSTAT_STOPPED)
+			*reg |= SIGP_STATUS_STOPPED;
+		rc = SIGP_CC_STATUS_STORED;
+	}
+	spin_unlock(&fi->lock);
+
+	VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc);
+	return rc;
+}
+
+static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_interrupt_info *inti;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return SIGP_CC_NOT_OPERATIONAL;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	inti->type = KVM_S390_INT_EMERGENCY;
+	inti->emerg.code = vcpu->vcpu_id;
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = SIGP_CC_NOT_OPERATIONAL;
+		kfree(inti);
+		goto unlock;
+	}
+	spin_lock_bh(&li->lock);
+	list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	spin_unlock_bh(&li->lock);
+	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+	VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
+unlock:
+	spin_unlock(&fi->lock);
+	return rc;
+}
+
+static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_s390_interrupt_info *inti;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return SIGP_CC_NOT_OPERATIONAL;
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return -ENOMEM;
+
+	inti->type = KVM_S390_INT_EXTERNAL_CALL;
+	inti->extcall.code = vcpu->vcpu_id;
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = SIGP_CC_NOT_OPERATIONAL;
+		kfree(inti);
+		goto unlock;
+	}
+	spin_lock_bh(&li->lock);
+	list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	spin_unlock_bh(&li->lock);
+	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+	VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr);
+unlock:
+	spin_unlock(&fi->lock);
+	return rc;
+}
+
+static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
+{
+	struct kvm_s390_interrupt_info *inti;
+
+	inti = kzalloc(sizeof(*inti), GFP_ATOMIC);
+	if (!inti)
+		return -ENOMEM;
+	inti->type = KVM_S390_SIGP_STOP;
+
+	spin_lock_bh(&li->lock);
+	if ((atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
+		kfree(inti);
+		goto out;
+	}
+	list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	atomic_set_mask(CPUSTAT_STOP_INT, li->cpuflags);
+	li->action_bits |= action;
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+out:
+	spin_unlock_bh(&li->lock);
+
+	return SIGP_CC_ORDER_CODE_ACCEPTED;
+}
+
+static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	int rc;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return SIGP_CC_NOT_OPERATIONAL;
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = SIGP_CC_NOT_OPERATIONAL;
+		goto unlock;
+	}
+
+	rc = __inject_sigp_stop(li, action);
+
+unlock:
+	spin_unlock(&fi->lock);
+	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
+	return rc;
+}
+
+int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action)
+{
+	struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+	return __inject_sigp_stop(li, action);
+}
+
+static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
+{
+	int rc;
+
+	switch (parameter & 0xff) {
+	case 0:
+		rc = SIGP_CC_NOT_OPERATIONAL;
+		break;
+	case 1:
+	case 2:
+		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+		break;
+	default:
+		rc = -EOPNOTSUPP;
+	}
+	return rc;
+}
+
+static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
+			     u64 *reg)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li = NULL;
+	struct kvm_s390_interrupt_info *inti;
+	int rc;
+	u8 tmp;
+
+	/* make sure that the new value is valid memory */
+	address = address & 0x7fffe000u;
+	if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
+	   copy_from_guest_absolute(vcpu, &tmp, address + PAGE_SIZE, 1)) {
+		*reg &= 0xffffffff00000000UL;
+		*reg |= SIGP_STATUS_INVALID_PARAMETER;
+		return SIGP_CC_STATUS_STORED;
+	}
+
+	inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+	if (!inti)
+		return SIGP_CC_BUSY;
+
+	spin_lock(&fi->lock);
+	if (cpu_addr < KVM_MAX_VCPUS)
+		li = fi->local_int[cpu_addr];
+
+	if (li == NULL) {
+		*reg &= 0xffffffff00000000UL;
+		*reg |= SIGP_STATUS_INCORRECT_STATE;
+		rc = SIGP_CC_STATUS_STORED;
+		kfree(inti);
+		goto out_fi;
+	}
+
+	spin_lock_bh(&li->lock);
+	/* cpu must be in stopped state */
+	if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
+		*reg &= 0xffffffff00000000UL;
+		*reg |= SIGP_STATUS_INCORRECT_STATE;
+		rc = SIGP_CC_STATUS_STORED;
+		kfree(inti);
+		goto out_li;
+	}
+
+	inti->type = KVM_S390_SIGP_SET_PREFIX;
+	inti->prefix.address = address;
+
+	list_add_tail(&inti->list, &li->list);
+	atomic_set(&li->active, 1);
+	if (waitqueue_active(&li->wq))
+		wake_up_interruptible(&li->wq);
+	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+
+	VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address);
+out_li:
+	spin_unlock_bh(&li->lock);
+out_fi:
+	spin_unlock(&fi->lock);
+	return rc;
+}
+
+static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
+				u64 *reg)
+{
+	int rc;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return SIGP_CC_NOT_OPERATIONAL;
+
+	spin_lock(&fi->lock);
+	if (fi->local_int[cpu_addr] == NULL)
+		rc = SIGP_CC_NOT_OPERATIONAL;
+	else {
+		if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		    & CPUSTAT_RUNNING) {
+			/* running */
+			rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+		} else {
+			/* not running */
+			*reg &= 0xffffffff00000000UL;
+			*reg |= SIGP_STATUS_NOT_RUNNING;
+			rc = SIGP_CC_STATUS_STORED;
+		}
+	}
+	spin_unlock(&fi->lock);
+
+	VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
+		   rc);
+
+	return rc;
+}
+
+static int __sigp_restart(struct kvm_vcpu *vcpu, u16 cpu_addr)
+{
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return SIGP_CC_NOT_OPERATIONAL;
+
+	spin_lock(&fi->lock);
+	li = fi->local_int[cpu_addr];
+	if (li == NULL) {
+		rc = SIGP_CC_NOT_OPERATIONAL;
+		goto out;
+	}
+
+	spin_lock_bh(&li->lock);
+	if (li->action_bits & ACTION_STOP_ON_STOP)
+		rc = SIGP_CC_BUSY;
+	else
+		VCPU_EVENT(vcpu, 4, "sigp restart %x to handle userspace",
+			cpu_addr);
+	spin_unlock_bh(&li->lock);
+out:
+	spin_unlock(&fi->lock);
+	return rc;
+}
+
+int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
+{
+	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
+	int r3 = vcpu->arch.sie_block->ipa & 0x000f;
+	u32 parameter;
+	u16 cpu_addr = vcpu->run->s.regs.gprs[r3];
+	u8 order_code;
+	int rc;
+
+	/* sigp in userspace can exit */
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu,
+						   PGM_PRIVILEGED_OPERATION);
+
+	order_code = kvm_s390_get_base_disp_rs(vcpu);
+
+	if (r1 % 2)
+		parameter = vcpu->run->s.regs.gprs[r1];
+	else
+		parameter = vcpu->run->s.regs.gprs[r1 + 1];
+
+	trace_kvm_s390_handle_sigp(vcpu, order_code, cpu_addr, parameter);
+	switch (order_code) {
+	case SIGP_SENSE:
+		vcpu->stat.instruction_sigp_sense++;
+		rc = __sigp_sense(vcpu, cpu_addr,
+				  &vcpu->run->s.regs.gprs[r1]);
+		break;
+	case SIGP_EXTERNAL_CALL:
+		vcpu->stat.instruction_sigp_external_call++;
+		rc = __sigp_external_call(vcpu, cpu_addr);
+		break;
+	case SIGP_EMERGENCY_SIGNAL:
+		vcpu->stat.instruction_sigp_emergency++;
+		rc = __sigp_emergency(vcpu, cpu_addr);
+		break;
+	case SIGP_STOP:
+		vcpu->stat.instruction_sigp_stop++;
+		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STOP_ON_STOP);
+		break;
+	case SIGP_STOP_AND_STORE_STATUS:
+		vcpu->stat.instruction_sigp_stop++;
+		rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP |
+						 ACTION_STOP_ON_STOP);
+		break;
+	case SIGP_SET_ARCHITECTURE:
+		vcpu->stat.instruction_sigp_arch++;
+		rc = __sigp_set_arch(vcpu, parameter);
+		break;
+	case SIGP_SET_PREFIX:
+		vcpu->stat.instruction_sigp_prefix++;
+		rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
+				       &vcpu->run->s.regs.gprs[r1]);
+		break;
+	case SIGP_SENSE_RUNNING:
+		vcpu->stat.instruction_sigp_sense_running++;
+		rc = __sigp_sense_running(vcpu, cpu_addr,
+					  &vcpu->run->s.regs.gprs[r1]);
+		break;
+	case SIGP_RESTART:
+		vcpu->stat.instruction_sigp_restart++;
+		rc = __sigp_restart(vcpu, cpu_addr);
+		if (rc == SIGP_CC_BUSY)
+			break;
+		/* user space must know about restart */
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (rc < 0)
+		return rc;
+
+	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+	vcpu->arch.sie_block->gpsw.mask |= (rc & 3ul) << 44;
+	return 0;
+}
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
new file mode 100644
index 00000000..13f30f58
--- /dev/null
+++ b/arch/s390/kvm/trace-s390.h
@@ -0,0 +1,230 @@
+#if !defined(_TRACE_KVMS390_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVMS390_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm-s390
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace-s390
+
+/*
+ * Trace point for the creation of the kvm instance.
+ */
+TRACE_EVENT(kvm_s390_create_vm,
+	    TP_PROTO(unsigned long type),
+	    TP_ARGS(type),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned long, type)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->type = type;
+		    ),
+
+	    TP_printk("create vm%s",
+		      __entry->type & KVM_VM_S390_UCONTROL ? " (UCONTROL)" : "")
+	);
+
+/*
+ * Trace points for creation and destruction of vpcus.
+ */
+TRACE_EVENT(kvm_s390_create_vcpu,
+	    TP_PROTO(unsigned int id, struct kvm_vcpu *vcpu,
+		     struct kvm_s390_sie_block *sie_block),
+	    TP_ARGS(id, vcpu, sie_block),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, id)
+		    __field(struct kvm_vcpu *, vcpu)
+		    __field(struct kvm_s390_sie_block *, sie_block)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->vcpu = vcpu;
+		    __entry->sie_block = sie_block;
+		    ),
+
+	    TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
+		      __entry->vcpu, __entry->sie_block)
+	);
+
+TRACE_EVENT(kvm_s390_destroy_vcpu,
+	    TP_PROTO(unsigned int id),
+	    TP_ARGS(id),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, id)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    ),
+
+	    TP_printk("destroy cpu %d", __entry->id)
+	);
+
+/*
+ * Trace points for injection of interrupts, either per machine or
+ * per vcpu.
+ */
+
+#define kvm_s390_int_type						\
+	{KVM_S390_SIGP_STOP, "sigp stop"},				\
+	{KVM_S390_PROGRAM_INT, "program interrupt"},			\
+	{KVM_S390_SIGP_SET_PREFIX, "sigp set prefix"},			\
+	{KVM_S390_RESTART, "sigp restart"},				\
+	{KVM_S390_INT_VIRTIO, "virtio interrupt"},			\
+	{KVM_S390_INT_SERVICE, "sclp interrupt"},			\
+	{KVM_S390_INT_EMERGENCY, "sigp emergency"},			\
+	{KVM_S390_INT_EXTERNAL_CALL, "sigp ext call"}
+
+TRACE_EVENT(kvm_s390_inject_vm,
+	    TP_PROTO(__u64 type, __u32 parm, __u64 parm64, int who),
+	    TP_ARGS(type, parm, parm64, who),
+
+	    TP_STRUCT__entry(
+		    __field(__u32, inttype)
+		    __field(__u32, parm)
+		    __field(__u64, parm64)
+		    __field(int, who)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->inttype = type & 0x00000000ffffffff;
+		    __entry->parm = parm;
+		    __entry->parm64 = parm64;
+		    __entry->who = who;
+		    ),
+
+	    TP_printk("inject%s: type:%x (%s) parm:%x parm64:%llx",
+		      (__entry->who == 1) ? " (from kernel)" :
+		      (__entry->who == 2) ? " (from user)" : "",
+		      __entry->inttype,
+		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->parm, __entry->parm64)
+	);
+
+TRACE_EVENT(kvm_s390_inject_vcpu,
+	    TP_PROTO(unsigned int id, __u64 type, __u32 parm, __u64 parm64, \
+		     int who),
+	    TP_ARGS(id, type, parm, parm64, who),
+
+	    TP_STRUCT__entry(
+		    __field(int, id)
+		    __field(__u32, inttype)
+		    __field(__u32, parm)
+		    __field(__u64, parm64)
+		    __field(int, who)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->inttype = type & 0x00000000ffffffff;
+		    __entry->parm = parm;
+		    __entry->parm64 = parm64;
+		    __entry->who = who;
+		    ),
+
+	    TP_printk("inject%s (vcpu %d): type:%x (%s) parm:%x parm64:%llx",
+		      (__entry->who == 1) ? " (from kernel)" :
+		      (__entry->who == 2) ? " (from user)" : "",
+		      __entry->id, __entry->inttype,
+		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->parm, __entry->parm64)
+	);
+
+/*
+ * Trace point for the actual delivery of interrupts.
+ */
+TRACE_EVENT(kvm_s390_deliver_interrupt,
+	    TP_PROTO(unsigned int id, __u64 type, __u64 data0, __u64 data1),
+	    TP_ARGS(id, type, data0, data1),
+
+	    TP_STRUCT__entry(
+		    __field(int, id)
+		    __field(__u32, inttype)
+		    __field(__u64, data0)
+		    __field(__u64, data1)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->inttype = type & 0x00000000ffffffff;
+		    __entry->data0 = data0;
+		    __entry->data1 = data1;
+		    ),
+
+	    TP_printk("deliver interrupt (vcpu %d): type:%x (%s) "	\
+		      "data:%08llx %016llx",
+		      __entry->id, __entry->inttype,
+		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->data0, __entry->data1)
+	);
+
+/*
+ * Trace point for resets that may be requested from userspace.
+ */
+TRACE_EVENT(kvm_s390_request_resets,
+	    TP_PROTO(__u64 resets),
+	    TP_ARGS(resets),
+
+	    TP_STRUCT__entry(
+		    __field(__u64, resets)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->resets = resets;
+		    ),
+
+	    TP_printk("requesting userspace resets %llx",
+		      __entry->resets)
+	);
+
+/*
+ * Trace point for a vcpu's stop requests.
+ */
+TRACE_EVENT(kvm_s390_stop_request,
+	    TP_PROTO(unsigned int action_bits),
+	    TP_ARGS(action_bits),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, action_bits)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->action_bits = action_bits;
+		    ),
+
+	    TP_printk("stop request, action_bits = %08x",
+		      __entry->action_bits)
+	);
+
+
+/*
+ * Trace point for enabling channel I/O instruction support.
+ */
+TRACE_EVENT(kvm_s390_enable_css,
+	    TP_PROTO(void *kvm),
+	    TP_ARGS(kvm),
+
+	    TP_STRUCT__entry(
+		    __field(void *, kvm)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->kvm = kvm;
+		    ),
+
+	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
+		      __entry->kvm)
+	);
+
+
+#endif /* _TRACE_KVMS390_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/s390/kvm/trace.h b/arch/s390/kvm/trace.h
new file mode 100644
index 00000000..c2f582bb
--- /dev/null
+++ b/arch/s390/kvm/trace.h
@@ -0,0 +1,341 @@
+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+#include <asm/sigp.h>
+#include <asm/debug.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/*
+ * Helpers for vcpu-specific tracepoints containing the same information
+ * as s390dbf VCPU_EVENTs.
+ */
+#define VCPU_PROTO_COMMON struct kvm_vcpu *vcpu
+#define VCPU_ARGS_COMMON vcpu
+#define VCPU_FIELD_COMMON __field(int, id)			\
+	__field(unsigned long, pswmask)				\
+	__field(unsigned long, pswaddr)
+#define VCPU_ASSIGN_COMMON do {						\
+	__entry->id = vcpu->vcpu_id;					\
+	__entry->pswmask = vcpu->arch.sie_block->gpsw.mask;		\
+	__entry->pswaddr = vcpu->arch.sie_block->gpsw.addr;		\
+	} while (0);
+#define VCPU_TP_PRINTK(p_str, p_args...)				\
+	TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id,		\
+		  __entry->pswmask, __entry->pswaddr, p_args)
+
+/*
+ * Tracepoints for SIE entry and exit.
+ */
+TRACE_EVENT(kvm_s390_sie_enter,
+	    TP_PROTO(VCPU_PROTO_COMMON, int cpuflags),
+	    TP_ARGS(VCPU_ARGS_COMMON, cpuflags),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, cpuflags)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->cpuflags = cpuflags;
+		    ),
+
+	    VCPU_TP_PRINTK("entering sie flags %x", __entry->cpuflags)
+	);
+
+TRACE_EVENT(kvm_s390_sie_fault,
+	    TP_PROTO(VCPU_PROTO_COMMON),
+	    TP_ARGS(VCPU_ARGS_COMMON),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    ),
+
+	    VCPU_TP_PRINTK("%s", "fault in sie instruction")
+	);
+
+#define sie_intercept_code				\
+	{0x04, "Instruction"},				\
+	{0x08, "Program interruption"},			\
+	{0x0C, "Instruction and program interruption"},	\
+	{0x10, "External request"},			\
+	{0x14, "External interruption"},		\
+	{0x18, "I/O request"},				\
+	{0x1C, "Wait state"},				\
+	{0x20, "Validity"},				\
+	{0x28, "Stop request"}
+
+TRACE_EVENT(kvm_s390_sie_exit,
+	    TP_PROTO(VCPU_PROTO_COMMON, u8 icptcode),
+	    TP_ARGS(VCPU_ARGS_COMMON, icptcode),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(u8, icptcode)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->icptcode = icptcode;
+		    ),
+
+	    VCPU_TP_PRINTK("exit sie icptcode %d (%s)", __entry->icptcode,
+			   __print_symbolic(__entry->icptcode,
+					    sie_intercept_code))
+	);
+
+/*
+ * Trace point for intercepted instructions.
+ */
+TRACE_EVENT(kvm_s390_intercept_instruction,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 ipa, __u32 ipb),
+	    TP_ARGS(VCPU_ARGS_COMMON, ipa, ipb),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u64, instruction)
+		    __field(char, insn[8])
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->instruction = ((__u64)ipa << 48) |
+		    ((__u64)ipb << 16);
+		    ),
+
+	    VCPU_TP_PRINTK("intercepted instruction %016llx (%s)",
+			   __entry->instruction,
+			   insn_to_mnemonic((unsigned char *)
+					    &__entry->instruction,
+					 __entry->insn, sizeof(__entry->insn)) ?
+			   "unknown" : __entry->insn)
+	);
+
+/*
+ * Trace point for intercepted program interruptions.
+ */
+TRACE_EVENT(kvm_s390_intercept_prog,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 code),
+	    TP_ARGS(VCPU_ARGS_COMMON, code),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u16, code)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->code = code;
+		    ),
+
+	    VCPU_TP_PRINTK("intercepted program interruption %04x",
+			   __entry->code)
+	);
+
+/*
+ * Trace point for validity intercepts.
+ */
+TRACE_EVENT(kvm_s390_intercept_validity,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 viwhy),
+	    TP_ARGS(VCPU_ARGS_COMMON, viwhy),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u16, viwhy)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->viwhy = viwhy;
+		    ),
+
+	    VCPU_TP_PRINTK("got validity intercept %04x", __entry->viwhy)
+	);
+
+/*
+ * Trace points for instructions that are of special interest.
+ */
+
+#define sigp_order_codes					\
+	{SIGP_SENSE, "sense"},					\
+	{SIGP_EXTERNAL_CALL, "external call"},			\
+	{SIGP_EMERGENCY_SIGNAL, "emergency signal"},		\
+	{SIGP_STOP, "stop"},					\
+	{SIGP_STOP_AND_STORE_STATUS, "stop and store status"},	\
+	{SIGP_SET_ARCHITECTURE, "set architecture"},		\
+	{SIGP_SET_PREFIX, "set prefix"},			\
+	{SIGP_SENSE_RUNNING, "sense running"},			\
+	{SIGP_RESTART, "restart"}
+
+TRACE_EVENT(kvm_s390_handle_sigp,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u8 order_code, __u16 cpu_addr, \
+		     __u32 parameter),
+	    TP_ARGS(VCPU_ARGS_COMMON, order_code, cpu_addr, parameter),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u8, order_code)
+		    __field(__u16, cpu_addr)
+		    __field(__u32, parameter)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->order_code = order_code;
+		    __entry->cpu_addr = cpu_addr;
+		    __entry->parameter = parameter;
+		    ),
+
+	    VCPU_TP_PRINTK("handle sigp order %02x (%s), cpu address %04x, " \
+			   "parameter %08x", __entry->order_code,
+			   __print_symbolic(__entry->order_code,
+					    sigp_order_codes),
+			   __entry->cpu_addr, __entry->parameter)
+	);
+
+#define diagnose_codes				\
+	{0x10, "release pages"},		\
+	{0x44, "time slice end"},		\
+	{0x308, "ipl functions"},		\
+	{0x500, "kvm hypercall"},		\
+	{0x501, "kvm breakpoint"}
+
+TRACE_EVENT(kvm_s390_handle_diag,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 code),
+	    TP_ARGS(VCPU_ARGS_COMMON, code),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u16, code)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->code = code;
+		    ),
+
+	    VCPU_TP_PRINTK("handle diagnose call %04x (%s)", __entry->code,
+			   __print_symbolic(__entry->code, diagnose_codes))
+	);
+
+TRACE_EVENT(kvm_s390_handle_lctl,
+	    TP_PROTO(VCPU_PROTO_COMMON, int g, int reg1, int reg3, u64 addr),
+	    TP_ARGS(VCPU_ARGS_COMMON, g, reg1, reg3, addr),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, g)
+		    __field(int, reg1)
+		    __field(int, reg3)
+		    __field(u64, addr)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->g = g;
+		    __entry->reg1 = reg1;
+		    __entry->reg3 = reg3;
+		    __entry->addr = addr;
+		    ),
+
+	    VCPU_TP_PRINTK("%s: loading cr %x-%x from %016llx",
+			   __entry->g ? "lctlg" : "lctl",
+			   __entry->reg1, __entry->reg3, __entry->addr)
+	);
+
+TRACE_EVENT(kvm_s390_handle_prefix,
+	    TP_PROTO(VCPU_PROTO_COMMON, int set, u32 address),
+	    TP_ARGS(VCPU_ARGS_COMMON, set, address),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, set)
+		    __field(u32, address)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->set = set;
+		    __entry->address = address;
+		    ),
+
+	    VCPU_TP_PRINTK("%s prefix to %08x",
+			   __entry->set ? "setting" : "storing",
+			   __entry->address)
+	);
+
+TRACE_EVENT(kvm_s390_handle_stap,
+	    TP_PROTO(VCPU_PROTO_COMMON, u64 address),
+	    TP_ARGS(VCPU_ARGS_COMMON, address),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(u64, address)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->address = address;
+		    ),
+
+	    VCPU_TP_PRINTK("storing cpu address to %016llx",
+			   __entry->address)
+	);
+
+TRACE_EVENT(kvm_s390_handle_stfl,
+	    TP_PROTO(VCPU_PROTO_COMMON, unsigned int facility_list),
+	    TP_ARGS(VCPU_ARGS_COMMON, facility_list),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(unsigned int, facility_list)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->facility_list = facility_list;
+		    ),
+
+	    VCPU_TP_PRINTK("store facility list value %08x",
+			   __entry->facility_list)
+	);
+
+TRACE_EVENT(kvm_s390_handle_stsi,
+	    TP_PROTO(VCPU_PROTO_COMMON, int fc, int sel1, int sel2, u64 addr),
+	    TP_ARGS(VCPU_ARGS_COMMON, fc, sel1, sel2, addr),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, fc)
+		    __field(int, sel1)
+		    __field(int, sel2)
+		    __field(u64, addr)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->fc = fc;
+		    __entry->sel1 = sel1;
+		    __entry->sel2 = sel2;
+		    __entry->addr = addr;
+		    ),
+
+	    VCPU_TP_PRINTK("STSI %d.%d.%d information stored to %016llx",
+			   __entry->fc, __entry->sel1, __entry->sel2,
+			   __entry->addr)
+	);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>