summaryrefslogtreecommitdiffstats
path: root/arch/s390/kvm
diff options
context:
space:
mode:
authorAnton Arapov <anton@redhat.com>2012-04-16 10:05:28 +0200
committerAnton Arapov <anton@redhat.com>2012-04-16 10:05:28 +0200
commitb4b6116a13633898cf868f2f103c96a90c4c20f8 (patch)
tree93d1b7e2cfcdf473d8d4ff3ad141fa864f8491f6 /arch/s390/kvm
parentedd4be777c953e5faafc80d091d3084b4343f5d3 (diff)
downloadkernel-uprobes-b4b6116a13633898cf868f2f103c96a90c4c20f8.tar.gz
kernel-uprobes-b4b6116a13633898cf868f2f103c96a90c4c20f8.tar.xz
kernel-uprobes-b4b6116a13633898cf868f2f103c96a90c4c20f8.zip
fedora kernel: d9aad82f3319f3cfd1aebc01234254ef0c37ad84v3.3.2-1
Signed-off-by: Anton Arapov <anton@redhat.com>
Diffstat (limited to 'arch/s390/kvm')
-rw-r--r--arch/s390/kvm/Kconfig41
-rw-r--r--arch/s390/kvm/Makefile14
-rw-r--r--arch/s390/kvm/diag.c97
-rw-r--r--arch/s390/kvm/gaccess.h386
-rw-r--r--arch/s390/kvm/intercept.c261
-rw-r--r--arch/s390/kvm/interrupt.c642
-rw-r--r--arch/s390/kvm/kvm-s390.c763
-rw-r--r--arch/s390/kvm/kvm-s390.h74
-rw-r--r--arch/s390/kvm/priv.c383
-rw-r--r--arch/s390/kvm/sigp.c386
10 files changed, 3047 insertions, 0 deletions
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
new file mode 100644
index 00000000000..a21634173a6
--- /dev/null
+++ b/arch/s390/kvm/Kconfig
@@ -0,0 +1,41 @@
+#
+# KVM configuration
+#
+source "virt/kvm/Kconfig"
+
+menuconfig VIRTUALIZATION
+ def_bool y
+ prompt "Virtualization"
+ ---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 && EXPERIMENTAL
+ select PREEMPT_NOTIFIERS
+ select ANON_INODES
+ ---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.
+
+# 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 00000000000..3975722bb19
--- /dev/null
+++ b/arch/s390/kvm/Makefile
@@ -0,0 +1,14 @@
+# 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.
+
+common-objs = $(addprefix ../../../virt/kvm/, kvm_main.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 00000000000..8943e82cd4d
--- /dev/null
+++ b/arch/s390/kvm/diag.c
@@ -0,0 +1,97 @@
+/*
+ * diag.c - 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 "kvm-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->arch.guest_gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
+ end = vcpu->arch.guest_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++;
+ vcpu_put(vcpu);
+ yield();
+ vcpu_load(vcpu);
+ return 0;
+}
+
+static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
+{
+ unsigned int reg = vcpu->arch.sie_block->ipa & 0xf;
+ unsigned long subcode = vcpu->arch.guest_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);
+ return -EREMOTE;
+}
+
+int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
+{
+ int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
+
+ switch (code) {
+ case 0x10:
+ return diag_release_pages(vcpu);
+ case 0x44:
+ return __diag_time_slice_end(vcpu);
+ case 0x308:
+ return __diag_ipl_functions(vcpu);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
new file mode 100644
index 00000000000..c86f6ae43f7
--- /dev/null
+++ b/arch/s390/kvm/gaccess.h
@@ -0,0 +1,386 @@
+/*
+ * access.h - 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 *__guestaddr_to_user(struct kvm_vcpu *vcpu,
+ unsigned long guestaddr)
+{
+ unsigned long prefix = vcpu->arch.sie_block->prefix;
+
+ if (guestaddr < 2 * PAGE_SIZE)
+ guestaddr += prefix;
+ else if ((guestaddr >= prefix) && (guestaddr < prefix + 2 * PAGE_SIZE))
+ guestaddr -= prefix;
+
+ return (void __user *) gmap_fault(guestaddr, vcpu->arch.gmap);
+}
+
+static inline int get_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u64 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 7);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return get_user(*result, (unsigned long __user *) uptr);
+}
+
+static inline int get_guest_u32(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u32 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 3);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return get_user(*result, (u32 __user *) uptr);
+}
+
+static inline int get_guest_u16(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u16 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 1);
+
+ if (IS_ERR(uptr))
+ return PTR_ERR(uptr);
+
+ return get_user(*result, (u16 __user *) uptr);
+}
+
+static inline int get_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u8 *result)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return get_user(*result, (u8 __user *) uptr);
+}
+
+static inline int put_guest_u64(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u64 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 7);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u64 __user *) uptr);
+}
+
+static inline int put_guest_u32(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u32 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 3);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u32 __user *) uptr);
+}
+
+static inline int put_guest_u16(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u16 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ BUG_ON(guestaddr & 1);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u16 __user *) uptr);
+}
+
+static inline int put_guest_u8(struct kvm_vcpu *vcpu, unsigned long guestaddr,
+ u8 value)
+{
+ void __user *uptr = __guestaddr_to_user(vcpu, guestaddr);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ return put_user(value, (u8 __user *) uptr);
+}
+
+
+static inline int __copy_to_guest_slow(struct kvm_vcpu *vcpu,
+ unsigned long guestdest,
+ void *from, unsigned long n)
+{
+ int rc;
+ unsigned long i;
+ u8 *data = from;
+
+ for (i = 0; i < n; i++) {
+ rc = put_guest_u8(vcpu, guestdest++, *(data++));
+ if (rc < 0)
+ return rc;
+ }
+ return 0;
+}
+
+static inline int __copy_to_guest_fast(struct kvm_vcpu *vcpu,
+ unsigned long guestdest,
+ void *from, unsigned long n)
+{
+ int r;
+ void __user *uptr;
+ unsigned long size;
+
+ if (guestdest + n < guestdest)
+ return -EFAULT;
+
+ /* simple case: all within one segment table entry? */
+ if ((guestdest & PMD_MASK) == ((guestdest+n) & PMD_MASK)) {
+ uptr = (void __user *) gmap_fault(guestdest, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ r = copy_to_user(uptr, from, n);
+
+ if (r)
+ r = -EFAULT;
+
+ goto out;
+ }
+
+ /* copy first segment */
+ uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ size = PMD_SIZE - (guestdest & ~PMD_MASK);
+
+ r = copy_to_user(uptr, from, size);
+
+ if (r) {
+ r = -EFAULT;
+ goto out;
+ }
+ from += size;
+ n -= size;
+ guestdest += size;
+
+ /* copy full segments */
+ while (n >= PMD_SIZE) {
+ uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ r = copy_to_user(uptr, from, PMD_SIZE);
+
+ if (r) {
+ r = -EFAULT;
+ goto out;
+ }
+ from += PMD_SIZE;
+ n -= PMD_SIZE;
+ guestdest += PMD_SIZE;
+ }
+
+ /* copy the tail segment */
+ if (n) {
+ uptr = (void __user *)gmap_fault(guestdest, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ r = copy_to_user(uptr, from, n);
+
+ if (r)
+ r = -EFAULT;
+ }
+out:
+ return r;
+}
+
+static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu,
+ unsigned long guestdest,
+ void *from, unsigned long n)
+{
+ return __copy_to_guest_fast(vcpu, guestdest, from, n);
+}
+
+static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest,
+ void *from, unsigned long n)
+{
+ unsigned long prefix = vcpu->arch.sie_block->prefix;
+
+ if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if ((guestdest < prefix) && (guestdest + n > prefix))
+ goto slowpath;
+
+ if ((guestdest < prefix + 2 * PAGE_SIZE)
+ && (guestdest + n > prefix + 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if (guestdest < 2 * PAGE_SIZE)
+ guestdest += prefix;
+ else if ((guestdest >= prefix) && (guestdest < prefix + 2 * PAGE_SIZE))
+ guestdest -= prefix;
+
+ return __copy_to_guest_fast(vcpu, guestdest, from, n);
+slowpath:
+ return __copy_to_guest_slow(vcpu, guestdest, from, n);
+}
+
+static inline int __copy_from_guest_slow(struct kvm_vcpu *vcpu, void *to,
+ unsigned long guestsrc,
+ unsigned long n)
+{
+ int rc;
+ unsigned long i;
+ u8 *data = to;
+
+ for (i = 0; i < n; i++) {
+ rc = get_guest_u8(vcpu, guestsrc++, data++);
+ if (rc < 0)
+ return rc;
+ }
+ return 0;
+}
+
+static inline int __copy_from_guest_fast(struct kvm_vcpu *vcpu, void *to,
+ unsigned long guestsrc,
+ unsigned long n)
+{
+ int r;
+ void __user *uptr;
+ unsigned long size;
+
+ if (guestsrc + n < guestsrc)
+ return -EFAULT;
+
+ /* simple case: all within one segment table entry? */
+ if ((guestsrc & PMD_MASK) == ((guestsrc+n) & PMD_MASK)) {
+ uptr = (void __user *) gmap_fault(guestsrc, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ r = copy_from_user(to, uptr, n);
+
+ if (r)
+ r = -EFAULT;
+
+ goto out;
+ }
+
+ /* copy first segment */
+ uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ size = PMD_SIZE - (guestsrc & ~PMD_MASK);
+
+ r = copy_from_user(to, uptr, size);
+
+ if (r) {
+ r = -EFAULT;
+ goto out;
+ }
+ to += size;
+ n -= size;
+ guestsrc += size;
+
+ /* copy full segments */
+ while (n >= PMD_SIZE) {
+ uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ r = copy_from_user(to, uptr, PMD_SIZE);
+
+ if (r) {
+ r = -EFAULT;
+ goto out;
+ }
+ to += PMD_SIZE;
+ n -= PMD_SIZE;
+ guestsrc += PMD_SIZE;
+ }
+
+ /* copy the tail segment */
+ if (n) {
+ uptr = (void __user *)gmap_fault(guestsrc, vcpu->arch.gmap);
+
+ if (IS_ERR((void __force *) uptr))
+ return PTR_ERR((void __force *) uptr);
+
+ r = copy_from_user(to, uptr, n);
+
+ if (r)
+ r = -EFAULT;
+ }
+out:
+ return r;
+}
+
+static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to,
+ unsigned long guestsrc,
+ unsigned long n)
+{
+ return __copy_from_guest_fast(vcpu, to, guestsrc, n);
+}
+
+static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
+ unsigned long guestsrc, unsigned long n)
+{
+ unsigned long prefix = vcpu->arch.sie_block->prefix;
+
+ if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if ((guestsrc < prefix) && (guestsrc + n > prefix))
+ goto slowpath;
+
+ if ((guestsrc < prefix + 2 * PAGE_SIZE)
+ && (guestsrc + n > prefix + 2 * PAGE_SIZE))
+ goto slowpath;
+
+ if (guestsrc < 2 * PAGE_SIZE)
+ guestsrc += prefix;
+ else if ((guestsrc >= prefix) && (guestsrc < prefix + 2 * PAGE_SIZE))
+ guestsrc -= prefix;
+
+ return __copy_from_guest_fast(vcpu, to, guestsrc, n);
+slowpath:
+ return __copy_from_guest_slow(vcpu, to, guestsrc, n);
+}
+#endif
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
new file mode 100644
index 00000000000..02434543eab
--- /dev/null
+++ b/arch/s390/kvm/intercept.c
@@ -0,0 +1,261 @@
+/*
+ * intercept.c - 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"
+
+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;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16) +
+ ((vcpu->arch.sie_block->ipb & 0xff00) << 4);
+ u64 useraddr;
+ int reg, rc;
+
+ vcpu->stat.instruction_lctlg++;
+ if ((vcpu->arch.sie_block->ipb & 0xff) != 0x2f)
+ return -EOPNOTSUPP;
+
+ useraddr = disp2;
+ if (base2)
+ useraddr += vcpu->arch.guest_gprs[base2];
+
+ if (useraddr & 7)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ reg = reg1;
+
+ VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
+ disp2);
+
+ do {
+ rc = get_guest_u64(vcpu, useraddr,
+ &vcpu->arch.sie_block->gcr[reg]);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ break;
+ }
+ 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;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 useraddr;
+ u32 val = 0;
+ int reg, rc;
+
+ vcpu->stat.instruction_lctl++;
+
+ useraddr = disp2;
+ if (base2)
+ useraddr += vcpu->arch.guest_gprs[base2];
+
+ if (useraddr & 3)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
+ disp2);
+
+ reg = reg1;
+ do {
+ rc = get_guest_u32(vcpu, useraddr, &val);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ break;
+ }
+ 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 intercept_handler_t instruction_handlers[256] = {
+ [0x83] = kvm_s390_handle_diag,
+ [0xae] = kvm_s390_handle_sigp,
+ [0xb2] = kvm_s390_handle_b2,
+ [0xb7] = handle_lctl,
+ [0xe5] = kvm_s390_handle_e5,
+ [0xeb] = handle_lctlg,
+};
+
+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);
+ if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
+ vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
+ rc = kvm_s390_vcpu_store_status(vcpu,
+ KVM_S390_STORE_STATUS_NOADDR);
+ if (rc >= 0)
+ rc = -EOPNOTSUPP;
+ }
+
+ 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;
+ }
+
+ 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++;
+ 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++;
+ 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++;
+ 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,
+ [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 00000000000..278ee009ce6
--- /dev/null
+++ b/arch/s390/kvm/interrupt.c
@@ -0,0 +1,642 @@
+/*
+ * interrupt.c - 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"
+
+static int psw_extint_disabled(struct kvm_vcpu *vcpu)
+{
+ return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
+}
+
+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 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;
+ 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;
+ default:
+ 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;
+}
+
+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;
+ 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, exception = 0;
+
+ switch (inti->type) {
+ case KVM_S390_INT_EMERGENCY:
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
+ vcpu->stat.deliver_emergency_signal++;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1201);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->emerg.code);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ case KVM_S390_INT_EXTERNAL_CALL:
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
+ vcpu->stat.deliver_external_call++;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1202);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, inti->extcall.code);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ case KVM_S390_INT_SERVICE:
+ VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
+ inti->ext.ext_params);
+ vcpu->stat.deliver_service_signal++;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2401);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params);
+ if (rc == -EFAULT)
+ exception = 1;
+ 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++;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2603);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u16(vcpu, __LC_CPU_ADDRESS, 0x0d00);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u32(vcpu, __LC_EXT_PARAMS, inti->ext.ext_params);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u64(vcpu, __LC_EXT_PARAMS2,
+ inti->ext.ext_params2);
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ case KVM_S390_SIGP_STOP:
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
+ vcpu->stat.deliver_stop_signal++;
+ __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++;
+ vcpu->arch.sie_block->prefix = inti->prefix.address;
+ vcpu->arch.sie_block->ihcpu = 0xffff;
+ break;
+
+ case KVM_S390_RESTART:
+ VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
+ vcpu->stat.deliver_restart_signal++;
+ rc = copy_to_guest(vcpu, offsetof(struct _lowcore,
+ restart_old_psw), &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ offsetof(struct _lowcore, restart_psw), sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ 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++;
+ rc = put_guest_u16(vcpu, __LC_PGM_INT_CODE, inti->pgm.code);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = put_guest_u16(vcpu, __LC_PGM_ILC,
+ table[vcpu->arch.sie_block->ipa >> 14]);
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_to_guest(vcpu, __LC_PGM_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_PGM_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ break;
+
+ default:
+ BUG();
+ }
+ if (exception) {
+ 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, exception = 0;
+
+ if (psw_extint_disabled(vcpu))
+ return 0;
+ if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
+ return 0;
+ rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1004);
+ if (rc == -EFAULT)
+ exception = 1;
+ rc = copy_to_guest(vcpu, __LC_EXT_OLD_PSW,
+ &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ rc = copy_from_guest(vcpu, &vcpu->arch.sie_block->gpsw,
+ __LC_EXT_NEW_PSW, sizeof(psw_t));
+ if (rc == -EFAULT)
+ exception = 1;
+ if (exception) {
+ 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_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_clock() + vcpu->arch.sie_block->epoch;
+ if (vcpu->arch.sie_block->ckc < now) {
+ __unset_cpu_idle(vcpu);
+ return 0;
+ }
+
+ sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9;
+
+ 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);
+ vcpu_put(vcpu);
+ schedule();
+ vcpu_load(vcpu);
+ 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_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);
+ }
+}
+
+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);
+ 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;
+}
+
+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;
+ 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:
+ default:
+ kfree(inti);
+ return -EINVAL;
+ }
+
+ mutex_lock(&kvm->lock);
+ fi = &kvm->arch.float_int;
+ spin_lock(&fi->lock);
+ list_add_tail(&inti->list, &fi->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:
+ case KVM_S390_INT_EXTERNAL_CALL:
+ case KVM_S390_INT_EMERGENCY:
+ VCPU_EVENT(vcpu, 3, "inject: type %x", s390int->type);
+ inti->type = s390int->type;
+ break;
+ case KVM_S390_INT_VIRTIO:
+ case KVM_S390_INT_SERVICE:
+ default:
+ kfree(inti);
+ return -EINVAL;
+ }
+
+ 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 00000000000..d1c44573245
--- /dev/null
+++ b/arch/s390/kvm/kvm-s390.c
@@ -0,0 +1,763 @@
+/*
+ * s390host.c -- 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/system.h>
+#include "kvm-s390.h"
+#include "gaccess.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) },
+ { NULL }
+};
+
+static unsigned long long *facilities;
+
+/* Section: not file related */
+int kvm_arch_hardware_enable(void *garbage)
+{
+ /* every s390 is virtualization enabled ;-) */
+ return 0;
+}
+
+void kvm_arch_hardware_disable(void *garbage)
+{
+}
+
+int kvm_arch_hardware_setup(void)
+{
+ return 0;
+}
+
+void kvm_arch_hardware_unsetup(void)
+{
+}
+
+void kvm_arch_check_processor_compat(void *rtn)
+{
+}
+
+int kvm_arch_init(void *opaque)
+{
+ return 0;
+}
+
+void kvm_arch_exit(void)
+{
+}
+
+/* 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_dev_ioctl_check_extension(long ext)
+{
+ int r;
+
+ switch (ext) {
+ case KVM_CAP_S390_PSW:
+ case KVM_CAP_S390_GMAP:
+ case KVM_CAP_SYNC_MMU:
+ r = 1;
+ 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)
+{
+ int rc;
+ char debug_name[16];
+
+ 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");
+
+ kvm->arch.gmap = gmap_alloc(current->mm);
+ if (!kvm->arch.gmap)
+ goto out_nogmap;
+
+ 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");
+ 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();
+ 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_sync_events(struct kvm *kvm)
+{
+}
+
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+ kvm_free_vcpus(kvm);
+ free_page((unsigned long)(kvm->arch.sca));
+ debug_unregister(kvm->arch.dbf);
+ gmap_free(kvm->arch.gmap);
+}
+
+/* Section: vcpu related */
+int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+ return 0;
+}
+
+void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
+{
+ /* Nothing todo */
+}
+
+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->arch.guest_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->arch.guest_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;
+ vcpu->arch.sie_block->prefix = 0UL;
+ vcpu->arch.sie_block->ihcpu = 0xffff;
+ 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;
+}
+
+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;
+ BUG_ON(!kvm->arch.sca);
+ 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);
+
+ 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;
+}
+
+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->arch.guest_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->arch.guest_gprs, sizeof(regs->gprs));
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ memcpy(&vcpu->arch.guest_acrs, &sregs->acrs, sizeof(sregs->acrs));
+ memcpy(&vcpu->arch.sie_block->gcr, &sregs->crs, sizeof(sregs->crs));
+ restore_access_regs(vcpu->arch.guest_acrs);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+ struct kvm_sregs *sregs)
+{
+ memcpy(&sregs->acrs, &vcpu->arch.guest_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;
+ 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 void __vcpu_run(struct kvm_vcpu *vcpu)
+{
+ memcpy(&vcpu->arch.sie_block->gg14, &vcpu->arch.guest_gprs[14], 16);
+
+ if (need_resched())
+ schedule();
+
+ if (test_thread_flag(TIF_MCCK_PENDING))
+ s390_handle_mcck();
+
+ kvm_s390_deliver_pending_interrupts(vcpu);
+
+ vcpu->arch.sie_block->icptcode = 0;
+ local_irq_disable();
+ kvm_guest_enter();
+ local_irq_enable();
+ VCPU_EVENT(vcpu, 6, "entering sie flags %x",
+ atomic_read(&vcpu->arch.sie_block->cpuflags));
+ if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
+ VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ }
+ VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
+ vcpu->arch.sie_block->icptcode);
+ local_irq_disable();
+ kvm_guest_exit();
+ local_irq_enable();
+
+ memcpy(&vcpu->arch.guest_gprs[14], &vcpu->arch.sie_block->gg14, 16);
+}
+
+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:
+ break;
+ default:
+ BUG();
+ }
+
+ vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
+ vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+
+ might_fault();
+
+ do {
+ __vcpu_run(vcpu);
+ 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;
+ }
+
+ 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;
+
+ 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;
+
+ 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->arch.guest_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->arch.guest_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;
+}
+
+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;
+ default:
+ r = -EINVAL;
+ }
+ return r;
+}
+
+/* Section: memory related */
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ struct kvm_memory_slot old,
+ struct kvm_userspace_memory_region *mem,
+ int user_alloc)
+{
+ /* A few sanity checks. We can have exactly one memory slot which has
+ to start at guest virtual zero and which has to be located at a
+ page boundary in userland and which has to end at a page boundary.
+ 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->slot)
+ return -EINVAL;
+
+ if (mem->guest_phys_addr)
+ return -EINVAL;
+
+ if (mem->userspace_addr & 0xffffful)
+ return -EINVAL;
+
+ if (mem->memory_size & 0xffffful)
+ return -EINVAL;
+
+ if (!user_alloc)
+ return -EINVAL;
+
+ return 0;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old,
+ int user_alloc)
+{
+ int rc;
+
+
+ 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;
+}
+
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
+
+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] &= 0x201c000000000000ULL;
+ 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 00000000000..99b0b759711
--- /dev/null
+++ b/arch/s390/kvm/kvm-s390.h
@@ -0,0 +1,74 @@
+/*
+ * kvm_s390.h - 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)
+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;
+}
+
+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);
+int kvm_s390_inject_vm(struct kvm *kvm,
+ struct kvm_s390_interrupt *s390int);
+int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
+ struct kvm_s390_interrupt *s390int);
+int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
+int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
+
+/* implemented in priv.c */
+int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
+int kvm_s390_handle_e5(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 00000000000..d0263895992
--- /dev/null
+++ b/arch/s390/kvm/priv.c
@@ -0,0 +1,383 @@
+/*
+ * priv.c - 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 <asm/current.h>
+#include <asm/debug.h>
+#include <asm/ebcdic.h>
+#include <asm/sysinfo.h>
+#include "gaccess.h"
+#include "kvm-s390.h"
+
+static int handle_set_prefix(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ u32 address = 0;
+ u8 tmp;
+
+ vcpu->stat.instruction_spx++;
+
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ /* must be word boundary */
+ if (operand2 & 3) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ /* get the value */
+ if (get_guest_u32(vcpu, operand2, &address)) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ 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))) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ vcpu->arch.sie_block->prefix = address;
+ vcpu->arch.sie_block->ihcpu = 0xffff;
+
+ VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
+out:
+ return 0;
+}
+
+static int handle_store_prefix(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ u32 address;
+
+ vcpu->stat.instruction_stpx++;
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ /* must be word boundary */
+ if (operand2 & 3) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ address = vcpu->arch.sie_block->prefix;
+ address = address & 0x7fffe000u;
+
+ /* get the value */
+ if (put_guest_u32(vcpu, operand2, address)) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
+out:
+ return 0;
+}
+
+static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 useraddr;
+ int rc;
+
+ vcpu->stat.instruction_stap++;
+ useraddr = disp2;
+ if (base2)
+ useraddr += vcpu->arch.guest_gprs[base2];
+
+ if (useraddr & 1) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ rc = put_guest_u16(vcpu, useraddr, vcpu->vcpu_id);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", useraddr);
+out:
+ 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_stsch(struct kvm_vcpu *vcpu)
+{
+ vcpu->stat.instruction_stsch++;
+ VCPU_EVENT(vcpu, 4, "%s", "store subchannel - CC3");
+ /* condition code 3 */
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44;
+ return 0;
+}
+
+static int handle_chsc(struct kvm_vcpu *vcpu)
+{
+ vcpu->stat.instruction_chsc++;
+ VCPU_EVENT(vcpu, 4, "%s", "channel subsystem call - CC3");
+ /* condition code 3 */
+ 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 == -EFAULT)
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ else
+ VCPU_EVENT(vcpu, 5, "store facility list value %x",
+ facility_list);
+ return 0;
+}
+
+static int handle_stidp(struct kvm_vcpu *vcpu)
+{
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ int rc;
+
+ vcpu->stat.instruction_stidp++;
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ if (operand2 & 7) {
+ kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+ goto out;
+ }
+
+ rc = put_guest_u64(vcpu, operand2, vcpu->arch.stidp_data);
+ if (rc == -EFAULT) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out;
+ }
+
+ VCPU_EVENT(vcpu, 5, "%s", "store cpu id");
+out:
+ 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) == -ENOSYS)
+ 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->arch.guest_gprs[0] & 0xf0000000) >> 28;
+ int sel1 = vcpu->arch.guest_gprs[0] & 0xff;
+ int sel2 = vcpu->arch.guest_gprs[1] & 0xffff;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u64 operand2;
+ unsigned long mem;
+
+ vcpu->stat.instruction_stsi++;
+ VCPU_EVENT(vcpu, 4, "stsi: fc: %x sel1: %x sel2: %x", fc, sel1, sel2);
+
+ operand2 = disp2;
+ if (base2)
+ operand2 += vcpu->arch.guest_gprs[base2];
+
+ if (operand2 & 0xfff && fc > 0)
+ return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+ switch (fc) {
+ case 0:
+ vcpu->arch.guest_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_fail;
+ if (stsi((void *) mem, fc, sel1, sel2) == -ENOSYS)
+ goto out_mem;
+ break;
+ case 3:
+ if (sel1 != 2 || sel2 != 2)
+ goto out_fail;
+ mem = get_zeroed_page(GFP_KERNEL);
+ if (!mem)
+ goto out_fail;
+ handle_stsi_3_2_2(vcpu, (void *) mem);
+ break;
+ default:
+ goto out_fail;
+ }
+
+ if (copy_to_guest_absolute(vcpu, operand2, (void *) mem, PAGE_SIZE)) {
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ goto out_mem;
+ }
+ free_page(mem);
+ vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
+ vcpu->arch.guest_gprs[0] = 0;
+ return 0;
+out_mem:
+ free_page(mem);
+out_fail:
+ /* condition code 3 */
+ vcpu->arch.sie_block->gpsw.mask |= 3ul << 44;
+ return 0;
+}
+
+static intercept_handler_t priv_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,
+ [0x34] = handle_stsch,
+ [0x5f] = handle_chsc,
+ [0x7d] = handle_stsi,
+ [0xb1] = handle_stfl,
+};
+
+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 = priv_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_tprot(struct kvm_vcpu *vcpu)
+{
+ int base1 = (vcpu->arch.sie_block->ipb & 0xf0000000) >> 28;
+ int disp1 = (vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16;
+ int base2 = (vcpu->arch.sie_block->ipb & 0xf000) >> 12;
+ int disp2 = vcpu->arch.sie_block->ipb & 0x0fff;
+ u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
+ u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
+ struct vm_area_struct *vma;
+ unsigned long user_address;
+
+ vcpu->stat.instruction_tprot++;
+
+ /* 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;
+
+
+ /* we must resolve the address without holding the mmap semaphore.
+ * This is ok since the userspace hypervisor is not supposed to change
+ * the mapping while the guest queries the memory. Otherwise the guest
+ * might crash or get wrong info anyway. */
+ user_address = (unsigned long) __guestaddr_to_user(vcpu, address1);
+
+ down_read(&current->mm->mmap_sem);
+ vma = find_vma(current->mm, user_address);
+ if (!vma) {
+ up_read(&current->mm->mmap_sem);
+ return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ }
+
+ 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;
+}
+
+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;
+}
+
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
new file mode 100644
index 00000000000..0a7941d74bc
--- /dev/null
+++ b/arch/s390/kvm/sigp.c
@@ -0,0 +1,386 @@
+/*
+ * sigp.c - handlinge 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 "gaccess.h"
+#include "kvm-s390.h"
+
+/* sigp order codes */
+#define SIGP_SENSE 0x01
+#define SIGP_EXTERNAL_CALL 0x02
+#define SIGP_EMERGENCY 0x03
+#define SIGP_START 0x04
+#define SIGP_STOP 0x05
+#define SIGP_RESTART 0x06
+#define SIGP_STOP_STORE_STATUS 0x09
+#define SIGP_INITIAL_CPU_RESET 0x0b
+#define SIGP_CPU_RESET 0x0c
+#define SIGP_SET_PREFIX 0x0d
+#define SIGP_STORE_STATUS_ADDR 0x0e
+#define SIGP_SET_ARCH 0x12
+#define SIGP_SENSE_RUNNING 0x15
+
+/* cpu status bits */
+#define SIGP_STAT_EQUIPMENT_CHECK 0x80000000UL
+#define SIGP_STAT_NOT_RUNNING 0x00000400UL
+#define SIGP_STAT_INCORRECT_STATE 0x00000200UL
+#define SIGP_STAT_INVALID_PARAMETER 0x00000100UL
+#define SIGP_STAT_EXT_CALL_PENDING 0x00000080UL
+#define SIGP_STAT_STOPPED 0x00000040UL
+#define SIGP_STAT_OPERATOR_INTERV 0x00000020UL
+#define SIGP_STAT_CHECK_STOP 0x00000010UL
+#define SIGP_STAT_INOPERATIVE 0x00000004UL
+#define SIGP_STAT_INVALID_ORDER 0x00000002UL
+#define SIGP_STAT_RECEIVER_CHECK 0x00000001UL
+
+
+static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
+ unsigned long *reg)
+{
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+ int rc;
+
+ if (cpu_addr >= KVM_MAX_VCPUS)
+ return 3; /* not operational */
+
+ spin_lock(&fi->lock);
+ if (fi->local_int[cpu_addr] == NULL)
+ rc = 3; /* not operational */
+ else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
+ & CPUSTAT_STOPPED)) {
+ *reg &= 0xffffffff00000000UL;
+ rc = 1; /* status stored */
+ } else {
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STAT_STOPPED;
+ rc = 1; /* 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 3; /* 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 = 3; /* 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 = 0; /* order 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 3; /* 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 = 3; /* 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 = 0; /* order 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);
+ 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);
+ spin_unlock_bh(&li->lock);
+
+ return 0; /* order 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 3; /* not operational */
+
+ spin_lock(&fi->lock);
+ li = fi->local_int[cpu_addr];
+ if (li == NULL) {
+ rc = 3; /* 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 = 3; /* not operational */
+ break;
+ case 1:
+ case 2:
+ rc = 0; /* order accepted */
+ break;
+ default:
+ rc = -EOPNOTSUPP;
+ }
+ return rc;
+}
+
+static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
+ unsigned long *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 |= SIGP_STAT_INVALID_PARAMETER;
+ return 1; /* invalid parameter */
+ }
+
+ inti = kzalloc(sizeof(*inti), GFP_KERNEL);
+ if (!inti)
+ return 2; /* busy */
+
+ spin_lock(&fi->lock);
+ if (cpu_addr < KVM_MAX_VCPUS)
+ li = fi->local_int[cpu_addr];
+
+ if (li == NULL) {
+ rc = 1; /* incorrect state */
+ *reg &= SIGP_STAT_INCORRECT_STATE;
+ kfree(inti);
+ goto out_fi;
+ }
+
+ spin_lock_bh(&li->lock);
+ /* cpu must be in stopped state */
+ if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
+ rc = 1; /* incorrect state */
+ *reg &= SIGP_STAT_INCORRECT_STATE;
+ 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 = 0; /* order 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,
+ unsigned long *reg)
+{
+ int rc;
+ struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+
+ if (cpu_addr >= KVM_MAX_VCPUS)
+ return 3; /* not operational */
+
+ spin_lock(&fi->lock);
+ if (fi->local_int[cpu_addr] == NULL)
+ rc = 3; /* not operational */
+ else {
+ if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+ & CPUSTAT_RUNNING) {
+ /* running */
+ rc = 1;
+ } else {
+ /* not running */
+ *reg &= 0xffffffff00000000UL;
+ *reg |= SIGP_STAT_NOT_RUNNING;
+ rc = 0;
+ }
+ }
+ spin_unlock(&fi->lock);
+
+ VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
+ rc);
+
+ 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;
+ int base2 = vcpu->arch.sie_block->ipb >> 28;
+ int disp2 = ((vcpu->arch.sie_block->ipb & 0x0fff0000) >> 16);
+ u32 parameter;
+ u16 cpu_addr = vcpu->arch.guest_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 = disp2;
+ if (base2)
+ order_code += vcpu->arch.guest_gprs[base2];
+
+ if (r1 % 2)
+ parameter = vcpu->arch.guest_gprs[r1];
+ else
+ parameter = vcpu->arch.guest_gprs[r1 + 1];
+
+ switch (order_code) {
+ case SIGP_SENSE:
+ vcpu->stat.instruction_sigp_sense++;
+ rc = __sigp_sense(vcpu, cpu_addr,
+ &vcpu->arch.guest_gprs[r1]);
+ break;
+ case SIGP_EXTERNAL_CALL:
+ vcpu->stat.instruction_sigp_external_call++;
+ rc = __sigp_external_call(vcpu, cpu_addr);
+ break;
+ case SIGP_EMERGENCY:
+ 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_STORE_STATUS:
+ vcpu->stat.instruction_sigp_stop++;
+ rc = __sigp_stop(vcpu, cpu_addr, ACTION_STORE_ON_STOP);
+ break;
+ case SIGP_SET_ARCH:
+ 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->arch.guest_gprs[r1]);
+ break;
+ case SIGP_SENSE_RUNNING:
+ vcpu->stat.instruction_sigp_sense_running++;
+ rc = __sigp_sense_running(vcpu, cpu_addr,
+ &vcpu->arch.guest_gprs[r1]);
+ break;
+ case SIGP_RESTART:
+ vcpu->stat.instruction_sigp_restart++;
+ /* 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;
+}